diff options
102 files changed, 6198 insertions, 8496 deletions
@@ -1,3 +1,4 @@ +<<<<<<< HEAD 2015-02-08 Andrew J. Schorr <aschorr@telemetry-investments.com> * awk.h (RED_NON_FATAL): Removed. @@ -16,6 +17,109 @@ * awk.h (is_non_fatal_std): Declare new function. * io.c (is_non_fatal_std): New function. * builtin.c (efwrite): Call it. +======= +2015-02-07 Arnold D. Robbins <arnold@skeeve.com> + + * regcomp.c, regex.c, regex.h, regex_internal.c, regex_internal.h, + regexec.c: Sync with GLIBC. Mostly copyright date updates. + +2015-02-05 Andrew J. Schorr <aschorr@telemetry-investments.com> + + * eval.c (set_IGNORECASE): If IGNORECASE has a numeric value, try + using that before treating it as a string. This fixes a problem + where setting -v IGNORECASE=0 on the command line was not working + properly. + +2015-02-01 Arnold D. Robbins <arnold@skeeve.com> + + Move POSIX requirement for disallowing paramater names with the + same name as a function into --posix. + + * NEWS: Document it. + * awkgram.y (parse_program): Check do_posix before calling + check_param_names(). + * symbol.c (check_param_names): Set up a fake node and call + in_array() for function parameter names instead of linear + searching the function list a second time. Thanks to Andrew + Schorr for the motivation. + +2015-01-30 Arnold D. Robbins <arnold@skeeve.com> + + Don't allow function parameter names to be the same as function + names - required by POSIX. Bug first reported in comp.lang.awk. + + In addition, don't allow use of a parameter as a function name + in a call (but it's ok in indirect calls). + + * NEWS: Updated. + * awk.h (check_param_names): Add declaration. + * awkgram.y (at_seen): New variable. Communicates between + yylex() and the parser. + (FUNC_CALL production): Check at_seen and check that the identifier + is a function name. + (parse_program): Call check_param_names() and set errcount. + (yylex): Set at_seen after seeing an at-sign. + * symbol.c (check_param_names): New function. + +2015-01-24 Arnold D. Robbins <arnold@skeeve.com> + + Infrastructure updates. + + Bison 3.0.4. Automake 1.15. Gettext 0.19.4. + +2015-01-20 Arnold D. Robbins <arnold@skeeve.com> + + * gawkapi.c (api_set_array_element): Remove useless call to + make_aname. + * symbol.c (load_symbols): Ditto. + Thanks to Andrew Schorr for pointing out the problem. + +2015-01-19 Arnold D. Robbins <arnold@skeeve.com> + + * awkgram.c: Update to bison 3.0.3. + * command.c: Ditto. + * NEWS: Note same. + +2015-01-16 Stephen Davies <sdavies@sdc.com.au> + + * awkgram.y (rule): Set first_rule to false. Catches more cases + for gathering comments. Thanks to Hermann Peifer for the test case. + +2015-01-15 Arnold D. Robbins <arnold@skeeve.com> + + * dfa.h, dfa.c: Sync with grep. Mainly copyright updates. + * getopt.c, getopt.h, getopt1.c getopt_int.h: Sync with GLIBC. + Mainly copyright updates, one minor code fix. + +2015-01-14 Arnold D. Robbins <arnold@skeeve.com> + + Remove deferred variables. + + * awk.h (register_deferred_variable): Remove declaration. + * awkgram.y (is_deferred_variable, process_deferred, + symtab_used, extensions_used, deferred_variables, + process_deferred): Remove declarations, bodies, and uses. + * builtin.c (do_length): Update comment. + * main.c (init_vars): Just call load_procinfo() and `load_environ()'. + +2015-01-07 Arnold D. Robbins <arnold@skeeve.com> + + * configure.ac: Update debug flags if developing. + * awkgram.y (yylex): Regex parsing bug fix for bracket expressions. + Thanks to Mike Brennan for the report. + * builtin.c (format_tree): Catch non-use of count$ for dynamic + field width or precision. + + Unrelated: + + Load deferred variables if extensions are used; they might + want to access PROCINFO and/or ENVIRON. Thanks to Andrew Schorr + for pointing out the issue. + + * awkgram.y (extensions_used): New variable. Set it on @load. + (do_add_scrfile): Set it on -l. + (process_deferred): Check it also. +>>>>>>> master 2014-12-24 Arnold D. Robbins <arnold@skeeve.com> @@ -1787,7 +1891,7 @@ 2012-12-25 Arnold D. Robbins <arnold@skeeve.com> Remove sym-constant from API after discussions with John - Haque and Andy Schorr. + Haque and Andrew Schorr. * gawkapi.h (api_sym_constant): Removed field in API struct. (sym_constant): Remove macro. @@ -1,7 +1,7 @@ Installation Instructions ************************* -Copyright (C) 1994-1996, 1999-2002, 2004-2012 Free Software Foundation, +Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation, Inc. Copying and distribution of this file, with or without modification, @@ -12,8 +12,8 @@ without warranty of any kind. Basic Installation ================== - Briefly, the shell commands `./configure; make; make install' should -configure, build, and install this package. The following + Briefly, the shell command `./configure && make && make install' +should configure, build, and install this package. The following more-detailed instructions are generic; see the `README' file for instructions specific to this package. Some packages provide this `INSTALL' file but do not implement all of the features documented diff --git a/Makefile.in b/Makefile.in index e45c520f..7e39cbf7 100644 --- a/Makefile.in +++ b/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -39,7 +39,17 @@ VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -103,13 +113,6 @@ build_triplet = @build@ host_triplet = @host@ bin_PROGRAMS = gawk$(EXEEXT) subdir = . -DIST_COMMON = INSTALL NEWS README AUTHORS ChangeLog \ - $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ - $(top_srcdir)/configure $(am__configure_deps) \ - $(srcdir)/configh.in mkinstalldirs ABOUT-NLS awkgram.c \ - command.c depcomp ylwrap $(include_HEADERS) COPYING TODO \ - compile config.guess config.rpath config.sub install-sh \ - missing ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/codeset.m4 $(top_srcdir)/m4/gettext.m4 \ @@ -124,6 +127,8 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/ulonglong.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(top_srcdir)/configure \ + $(am__configure_deps) $(include_HEADERS) $(am__DIST_COMMON) am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \ configure.lineno config.status.lineno mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs @@ -257,6 +262,10 @@ ETAGS = etags CTAGS = ctags CSCOPE = cscope DIST_SUBDIRS = $(SUBDIRS) +am__DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/configh.in ABOUT-NLS \ + AUTHORS COPYING ChangeLog INSTALL NEWS README TODO awkgram.c \ + command.c compile config.guess config.rpath config.sub depcomp \ + install-sh missing mkinstalldirs ylwrap DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) distdir = $(PACKAGE)-$(VERSION) top_distdir = $(distdir) @@ -570,7 +579,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -913,15 +921,15 @@ dist-xz: distdir $(am__post_remove_distdir) dist-tarZ: distdir - @echo WARNING: "Support for shar distribution archives is" \ - "deprecated." >&2 + @echo WARNING: "Support for distribution archives compressed with" \ + "legacy program 'compress' is deprecated." >&2 @echo WARNING: "It will be removed altogether in Automake 2.0" >&2 tardir=$(distdir) && $(am__tar) | compress -c >$(distdir).tar.Z $(am__post_remove_distdir) dist-shar: distdir - @echo WARNING: "Support for distribution archives compressed with" \ - "legacy program 'compress' is deprecated." >&2 + @echo WARNING: "Support for shar distribution archives is" \ + "deprecated." >&2 @echo WARNING: "It will be removed altogether in Automake 2.0" >&2 shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz $(am__post_remove_distdir) @@ -957,17 +965,17 @@ distcheck: dist esac chmod -R a-w $(distdir) chmod u+w $(distdir) - mkdir $(distdir)/_build $(distdir)/_inst + mkdir $(distdir)/_build $(distdir)/_build/sub $(distdir)/_inst chmod a-w $(distdir) test -d $(distdir)/_build || exit 0; \ dc_install_base=`$(am__cd) $(distdir)/_inst && pwd | sed -e 's,^[^:\\/]:[\\/],/,'` \ && dc_destdir="$${TMPDIR-/tmp}/am-dc-$$$$/" \ && am__cwd=`pwd` \ - && $(am__cd) $(distdir)/_build \ - && ../configure \ + && $(am__cd) $(distdir)/_build/sub \ + && ../../configure \ $(AM_DISTCHECK_CONFIGURE_FLAGS) \ $(DISTCHECK_CONFIGURE_FLAGS) \ - --srcdir=.. --prefix="$$dc_install_base" \ + --srcdir=../.. --prefix="$$dc_install_base" \ && $(MAKE) $(AM_MAKEFLAGS) \ && $(MAKE) $(AM_MAKEFLAGS) dvi \ && $(MAKE) $(AM_MAKEFLAGS) check \ @@ -1157,6 +1165,8 @@ uninstall-am: uninstall-binPROGRAMS uninstall-includeHEADERS tags tags-am uninstall uninstall-am uninstall-binPROGRAMS \ uninstall-includeHEADERS +.PRECIOUS: Makefile + # First, add a link from gawk to gawk-X.Y.Z. # @@ -53,6 +53,7 @@ Changes from 4.1.1 to 4.1.2 - Chapter 15 on MPFR reworked. - Summary sections added to all chapters. - Exercises added in several chapters. + - Heavily proof-read and copyedited. 2. The debugger's "restart" command now works again. @@ -60,14 +61,14 @@ Changes from 4.1.1 to 4.1.2 4. A number of bugs have been fixed in the MPFR code. -5. Indirect function calls now work for both built-in and - extension functions. +5. Indirect function calls now work for both built-in and extension functions. 6. Built-in functions are now included in FUNCTAB. -7. In non-English locales, it was accidentally possible to use "letters" - beside those of the English alphabet in identifiers. This has - been fixed. (isalpha and isalnum are NOT our friends.) +7. POSIX and historical practice require the exclusive use of the English + alphabet in identifiers. In non-English locales, it was accidentally + possible to use "letters" beside those of the English alphabet. This + has been fixed. (isalpha and isalnum are NOT our friends.) If you feel that you must have this misfeature, use `configure --help' to see what option to use when configuring gawk to reenable it. @@ -81,7 +82,17 @@ Changes from 4.1.1 to 4.1.2 AWKPATH setting, be sure to put "." in it somewhere. The documentation has been updated and clarified. -10. Infrastructure upgrades: Automake 1.14.1, Gettext 0.19.3, Libtool 2.4.3. +10. Infrastructure upgrades: Automake 1.15, Gettext 0.19.4, Libtool 2.4.5, + Bison 3.0.4. + +11. If a user-defined function has a parameter with the same name as another + user-defined function, it is no longer possible to call the second + function from inside the first. + +12. POSIX requires that the names of function parameters not be the + same as any of the special built-in variables and also not conflict + with the names of any functions. Gawk has checked for the former + since 3.1.7. With --posix, it now also checks for the latter. XX. A number of bugs have been fixed. See the ChangeLog. @@ -60,8 +60,6 @@ Major New Features Also needed: - Indirect calls of built-ins - Indirect calls of extension functions Indirect through array elements, not just scalar variables Some way to make regexp constants first class citizens: @@ -124,8 +122,6 @@ Things To Think About That May Never Happen Patch lexer for @include and @load to make quotes optional. (Really needed?) - ? Have strftime() pay attention to the value of ENVIRON["TZ"] - Add a lint check if the return value of a function is used but the function did not supply a value. @@ -1,6 +1,6 @@ -# generated automatically by aclocal 1.14.1 -*- Autoconf -*- +# generated automatically by aclocal 1.15 -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -20,7 +20,7 @@ You have another version of autoconf. It may work, but is not guaranteed to. If you have problems, you may need to regenerate the build system entirely. To do so, use the procedure documented by the package, typically 'autoreconf'.])]) -# Copyright (C) 2002-2013 Free Software Foundation, Inc. +# Copyright (C) 2002-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -32,10 +32,10 @@ To do so, use the procedure documented by the package, typically 'autoreconf'.]) # generated from the m4 files accompanying Automake X.Y. # (This private macro should not be called outside this file.) AC_DEFUN([AM_AUTOMAKE_VERSION], -[am__api_version='1.14' +[am__api_version='1.15' dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to dnl require some minimum version. Point them to the right macro. -m4_if([$1], [1.14.1], [], +m4_if([$1], [1.15], [], [AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl ]) @@ -51,14 +51,14 @@ m4_define([_AM_AUTOCONF_VERSION], []) # Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced. # This function is AC_REQUIREd by AM_INIT_AUTOMAKE. AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION], -[AM_AUTOMAKE_VERSION([1.14.1])dnl +[AM_AUTOMAKE_VERSION([1.15])dnl m4_ifndef([AC_AUTOCONF_VERSION], [m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl _AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))]) # AM_AUX_DIR_EXPAND -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -103,15 +103,14 @@ _AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))]) # configured tree to be moved without reconfiguration. AC_DEFUN([AM_AUX_DIR_EXPAND], -[dnl Rely on autoconf to set up CDPATH properly. -AC_PREREQ([2.50])dnl -# expand $ac_aux_dir to an absolute path -am_aux_dir=`cd $ac_aux_dir && pwd` +[AC_REQUIRE([AC_CONFIG_AUX_DIR_DEFAULT])dnl +# Expand $ac_aux_dir to an absolute path. +am_aux_dir=`cd "$ac_aux_dir" && pwd` ]) # AM_CONDITIONAL -*- Autoconf -*- -# Copyright (C) 1997-2013 Free Software Foundation, Inc. +# Copyright (C) 1997-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -142,7 +141,7 @@ AC_CONFIG_COMMANDS_PRE( Usually this means the macro was only invoked conditionally.]]) fi])]) -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -333,7 +332,7 @@ _AM_SUBST_NOTMAKE([am__nodep])dnl # Generate code to set up dependency tracking. -*- Autoconf -*- -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -409,7 +408,7 @@ AC_DEFUN([AM_OUTPUT_DEPENDENCY_COMMANDS], # Do all the work for Automake. -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -499,8 +498,8 @@ AC_REQUIRE([AC_PROG_MKDIR_P])dnl # <http://lists.gnu.org/archive/html/automake/2012-07/msg00001.html> # <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html> AC_SUBST([mkdir_p], ['$(MKDIR_P)']) -# We need awk for the "check" target. The system "awk" is bad on -# some platforms. +# We need awk for the "check" target (and possibly the TAP driver). The +# system "awk" is bad on some platforms. AC_REQUIRE([AC_PROG_AWK])dnl AC_REQUIRE([AC_PROG_MAKE_SET])dnl AC_REQUIRE([AM_SET_LEADING_DOT])dnl @@ -573,7 +572,11 @@ to "yes", and re-run configure. END AC_MSG_ERROR([Your 'rm' program is bad, sorry.]) fi -fi]) +fi +dnl The trailing newline in this macro's definition is deliberate, for +dnl backward compatibility and to allow trailing 'dnl'-style comments +dnl after the AM_INIT_AUTOMAKE invocation. See automake bug#16841. +]) dnl Hook into '_AC_COMPILER_EXEEXT' early to learn its expansion. Do not dnl add the conditional right here, as _AC_COMPILER_EXEEXT may be further @@ -602,7 +605,7 @@ for _am_header in $config_headers :; do done echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_count]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -613,7 +616,7 @@ echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_co # Define $install_sh. AC_DEFUN([AM_PROG_INSTALL_SH], [AC_REQUIRE([AM_AUX_DIR_EXPAND])dnl -if test x"${install_sh}" != xset; then +if test x"${install_sh+set}" != xset; then case $am_aux_dir in *\ * | *\ *) install_sh="\${SHELL} '$am_aux_dir/install-sh'" ;; @@ -623,7 +626,7 @@ if test x"${install_sh}" != xset; then fi AC_SUBST([install_sh])]) -# Copyright (C) 2003-2013 Free Software Foundation, Inc. +# Copyright (C) 2003-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -644,7 +647,7 @@ AC_SUBST([am__leading_dot])]) # Check to see how 'make' treats includes. -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -694,7 +697,7 @@ rm -f confinc confmf # Fake the existence of programs that GNU maintainers use. -*- Autoconf -*- -# Copyright (C) 1997-2013 Free Software Foundation, Inc. +# Copyright (C) 1997-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -733,7 +736,7 @@ fi # Helper functions for option handling. -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -762,7 +765,7 @@ AC_DEFUN([_AM_SET_OPTIONS], AC_DEFUN([_AM_IF_OPTION], [m4_ifset(_AM_MANGLE_OPTION([$1]), [$2], [$3])]) -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -809,7 +812,7 @@ AC_LANG_POP([C])]) # For backward compatibility. AC_DEFUN_ONCE([AM_PROG_CC_C_O], [AC_REQUIRE([AC_PROG_CC])]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -828,7 +831,7 @@ AC_DEFUN([AM_RUN_LOG], # Check to make sure that the build environment is sane. -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -909,7 +912,7 @@ AC_CONFIG_COMMANDS_PRE( rm -f conftest.file ]) -# Copyright (C) 2009-2013 Free Software Foundation, Inc. +# Copyright (C) 2009-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -969,7 +972,7 @@ AC_SUBST([AM_BACKSLASH])dnl _AM_SUBST_NOTMAKE([AM_BACKSLASH])dnl ]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -997,7 +1000,7 @@ fi INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s" AC_SUBST([INSTALL_STRIP_PROGRAM])]) -# Copyright (C) 2006-2013 Free Software Foundation, Inc. +# Copyright (C) 2006-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -1016,7 +1019,7 @@ AC_DEFUN([AM_SUBST_NOTMAKE], [_AM_SUBST_NOTMAKE($@)]) # Check how to create a tarball. -*- Autoconf -*- -# Copyright (C) 2004-2013 Free Software Foundation, Inc. +# Copyright (C) 2004-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 1986, 1988, 1989, 1991-2014 the Free Software Foundation, Inc. + * Copyright (C) 1986, 1988, 1989, 1991-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -1329,7 +1329,6 @@ extern void shadow_funcs(void); extern int check_special(const char *name); extern SRCFILE *add_srcfile(enum srctype stype, char *src, SRCFILE *curr, bool *already_included, int *errcode); extern void free_srcfile(SRCFILE *thisfile); -extern void register_deferred_variable(const char *name, NODE *(*load_func)(void)); extern int files_are_same(char *path, SRCFILE *src); extern void valinfo(NODE *n, Func_print print_func, FILE *fp); extern void negate_num(NODE *n); @@ -1619,6 +1618,7 @@ extern void free_context(AWK_CONTEXT *ctxt, bool keep_globals); extern NODE **variable_list(); extern NODE **function_list(bool sort); extern void print_vars(NODE **table, Func_print print_func, FILE *fp); +extern bool check_param_names(void); /* floatcomp.c */ #ifdef HAVE_UINTMAX_T @@ -1,8 +1,8 @@ -/* A Bison parser, made by GNU Bison 3.0.2. */ +/* A Bison parser, made by GNU Bison 3.0.4. */ /* Bison implementation for Yacc-like parsers in C - Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc. + Copyright (C) 1984, 1989-1990, 2000-2015 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -44,7 +44,7 @@ #define YYBISON 1 /* Bison version. */ -#define YYBISON_VERSION "3.0.2" +#define YYBISON_VERSION "3.0.4" /* Skeleton name. */ #define YYSKELETON_NAME "yacc.c" @@ -97,7 +97,6 @@ static int include_source(INSTRUCTION *file); static int load_library(INSTRUCTION *file); static void next_sourcefile(void); static char *tokexpand(void); -static bool is_deferred_variable(const char *name); #define instruction(t) bcalloc(t, 1, 0) @@ -119,8 +118,6 @@ static int count_expressions(INSTRUCTION **list, bool isarg); static INSTRUCTION *optimize_assignment(INSTRUCTION *exp); static void add_lint(INSTRUCTION *list, LINTTYPE linttype); -static void process_deferred(); - enum defref { FUNC_DEFINE, FUNC_USE, FUNC_EXT }; static void func_use(const char *name, enum defref how); static void check_funcs(void); @@ -130,10 +127,10 @@ static int one_line_close(int fd); static void split_comment(void); static void check_comment(void); +static bool at_seen = false; static bool want_source = false; static bool want_regexp = false; /* lexical scanning kludge */ static char *in_function; /* parsing kludge */ -static bool symtab_used = false; /* program used SYMTAB */ static int rule = 0; const char *const ruletab[] = { @@ -205,7 +202,7 @@ extern double fmod(double x, double y); #define YYSTYPE INSTRUCTION * -#line 209 "awkgram.c" /* yacc.c:339 */ +#line 206 "awkgram.c" /* yacc.c:339 */ # ifndef YY_NULLPTR # if defined __cplusplus && 201103L <= __cplusplus @@ -359,7 +356,7 @@ int yyparse (void); /* Copy the second part of user declarations. */ -#line 363 "awkgram.c" /* yacc.c:358 */ +#line 360 "awkgram.c" /* yacc.c:358 */ #ifdef short # undef short @@ -661,25 +658,25 @@ static const yytype_uint8 yytranslate[] = /* YYRLINE[YYN] -- Source line where rule number YYN was defined. */ static const yytype_uint16 yyrline[] = { - 0, 208, 208, 210, 215, 216, 222, 234, 238, 249, - 255, 260, 268, 276, 278, 283, 291, 293, 299, 307, - 317, 347, 361, 375, 383, 394, 406, 408, 410, 416, - 421, 422, 426, 461, 460, 494, 496, 501, 507, 535, - 540, 541, 545, 547, 549, 556, 646, 688, 730, 843, - 850, 857, 867, 876, 885, 894, 905, 921, 920, 944, - 956, 956, 1054, 1054, 1087, 1117, 1123, 1124, 1130, 1131, - 1138, 1143, 1155, 1169, 1171, 1179, 1184, 1186, 1194, 1196, - 1205, 1206, 1214, 1219, 1219, 1230, 1234, 1242, 1243, 1246, - 1248, 1253, 1254, 1263, 1264, 1269, 1274, 1280, 1282, 1284, - 1291, 1292, 1298, 1299, 1304, 1306, 1311, 1313, 1321, 1326, - 1335, 1342, 1344, 1346, 1362, 1372, 1379, 1381, 1386, 1388, - 1390, 1398, 1400, 1405, 1407, 1412, 1414, 1416, 1466, 1468, - 1470, 1472, 1474, 1476, 1478, 1480, 1494, 1499, 1504, 1529, - 1535, 1537, 1539, 1541, 1543, 1545, 1550, 1554, 1586, 1588, - 1594, 1600, 1613, 1614, 1615, 1620, 1625, 1629, 1633, 1648, - 1661, 1666, 1702, 1720, 1721, 1727, 1728, 1733, 1735, 1742, - 1759, 1776, 1778, 1785, 1790, 1798, 1808, 1820, 1829, 1833, - 1837, 1841, 1845, 1849, 1852, 1854, 1858, 1862, 1866 + 0, 205, 205, 207, 212, 213, 217, 229, 234, 245, + 251, 257, 266, 274, 276, 281, 289, 291, 297, 305, + 315, 345, 359, 373, 381, 392, 404, 406, 408, 414, + 422, 423, 427, 462, 461, 495, 497, 502, 508, 536, + 541, 542, 546, 548, 550, 557, 647, 689, 731, 844, + 851, 858, 868, 877, 886, 895, 906, 922, 921, 945, + 957, 957, 1055, 1055, 1088, 1118, 1124, 1125, 1131, 1132, + 1139, 1144, 1156, 1170, 1172, 1180, 1185, 1187, 1195, 1197, + 1206, 1207, 1215, 1220, 1220, 1231, 1235, 1243, 1244, 1247, + 1249, 1254, 1255, 1264, 1265, 1270, 1275, 1281, 1283, 1285, + 1292, 1293, 1299, 1300, 1305, 1307, 1312, 1314, 1322, 1327, + 1336, 1343, 1345, 1347, 1363, 1373, 1380, 1382, 1387, 1389, + 1391, 1399, 1401, 1406, 1408, 1413, 1415, 1417, 1467, 1469, + 1471, 1473, 1475, 1477, 1479, 1481, 1495, 1500, 1505, 1530, + 1536, 1538, 1540, 1542, 1544, 1546, 1551, 1555, 1587, 1589, + 1595, 1601, 1614, 1615, 1616, 1621, 1626, 1630, 1634, 1649, + 1662, 1667, 1704, 1733, 1734, 1740, 1741, 1746, 1748, 1755, + 1772, 1789, 1791, 1798, 1803, 1811, 1821, 1833, 1842, 1846, + 1850, 1854, 1858, 1862, 1865, 1867, 1871, 1875, 1879 }; #endif @@ -1852,26 +1849,24 @@ yyreduce: switch (yyn) { case 3: -#line 211 "awkgram.y" /* yacc.c:1646 */ +#line 208 "awkgram.y" /* yacc.c:1646 */ { rule = 0; yyerrok; } -#line 1861 "awkgram.c" /* yacc.c:1646 */ +#line 1858 "awkgram.c" /* yacc.c:1646 */ break; case 5: -#line 217 "awkgram.y" /* yacc.c:1646 */ +#line 214 "awkgram.y" /* yacc.c:1646 */ { next_sourcefile(); - if (sourcefile == srcfiles) - process_deferred(); } -#line 1871 "awkgram.c" /* yacc.c:1646 */ +#line 1866 "awkgram.c" /* yacc.c:1646 */ break; case 6: -#line 223 "awkgram.y" /* yacc.c:1646 */ +#line 218 "awkgram.y" /* yacc.c:1646 */ { rule = 0; /* @@ -1880,19 +1875,20 @@ yyreduce: */ /* yyerrok; */ } -#line 1884 "awkgram.c" /* yacc.c:1646 */ +#line 1879 "awkgram.c" /* yacc.c:1646 */ break; case 7: -#line 235 "awkgram.y" /* yacc.c:1646 */ +#line 230 "awkgram.y" /* yacc.c:1646 */ { (void) append_rule((yyvsp[-1]), (yyvsp[0])); + first_rule = false; } -#line 1892 "awkgram.c" /* yacc.c:1646 */ +#line 1888 "awkgram.c" /* yacc.c:1646 */ break; case 8: -#line 239 "awkgram.y" /* yacc.c:1646 */ +#line 235 "awkgram.y" /* yacc.c:1646 */ { if (rule != Rule) { msg(_("%s blocks must have an action part"), ruletab[rule]); @@ -1903,39 +1899,41 @@ yyreduce: } else /* pattern rule with non-empty pattern */ (void) append_rule((yyvsp[-1]), NULL); } -#line 1907 "awkgram.c" /* yacc.c:1646 */ +#line 1903 "awkgram.c" /* yacc.c:1646 */ break; case 9: -#line 250 "awkgram.y" /* yacc.c:1646 */ +#line 246 "awkgram.y" /* yacc.c:1646 */ { in_function = NULL; (void) mk_function((yyvsp[-1]), (yyvsp[0])); yyerrok; } -#line 1917 "awkgram.c" /* yacc.c:1646 */ +#line 1913 "awkgram.c" /* yacc.c:1646 */ break; case 10: -#line 256 "awkgram.y" /* yacc.c:1646 */ +#line 252 "awkgram.y" /* yacc.c:1646 */ { want_source = false; + at_seen = false; yyerrok; } -#line 1926 "awkgram.c" /* yacc.c:1646 */ +#line 1923 "awkgram.c" /* yacc.c:1646 */ break; case 11: -#line 261 "awkgram.y" /* yacc.c:1646 */ +#line 258 "awkgram.y" /* yacc.c:1646 */ { want_source = false; + at_seen = false; yyerrok; } -#line 1935 "awkgram.c" /* yacc.c:1646 */ +#line 1933 "awkgram.c" /* yacc.c:1646 */ break; case 12: -#line 269 "awkgram.y" /* yacc.c:1646 */ +#line 267 "awkgram.y" /* yacc.c:1646 */ { if (include_source((yyvsp[0])) < 0) YYABORT; @@ -1943,23 +1941,23 @@ yyreduce: bcfree((yyvsp[0])); (yyval) = NULL; } -#line 1947 "awkgram.c" /* yacc.c:1646 */ +#line 1945 "awkgram.c" /* yacc.c:1646 */ break; case 13: -#line 277 "awkgram.y" /* yacc.c:1646 */ +#line 275 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 1953 "awkgram.c" /* yacc.c:1646 */ +#line 1951 "awkgram.c" /* yacc.c:1646 */ break; case 14: -#line 279 "awkgram.y" /* yacc.c:1646 */ +#line 277 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 1959 "awkgram.c" /* yacc.c:1646 */ +#line 1957 "awkgram.c" /* yacc.c:1646 */ break; case 15: -#line 284 "awkgram.y" /* yacc.c:1646 */ +#line 282 "awkgram.y" /* yacc.c:1646 */ { if (load_library((yyvsp[0])) < 0) YYABORT; @@ -1967,23 +1965,23 @@ yyreduce: bcfree((yyvsp[0])); (yyval) = NULL; } -#line 1971 "awkgram.c" /* yacc.c:1646 */ +#line 1969 "awkgram.c" /* yacc.c:1646 */ break; case 16: -#line 292 "awkgram.y" /* yacc.c:1646 */ +#line 290 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 1977 "awkgram.c" /* yacc.c:1646 */ +#line 1975 "awkgram.c" /* yacc.c:1646 */ break; case 17: -#line 294 "awkgram.y" /* yacc.c:1646 */ +#line 292 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 1983 "awkgram.c" /* yacc.c:1646 */ +#line 1981 "awkgram.c" /* yacc.c:1646 */ break; case 18: -#line 299 "awkgram.y" /* yacc.c:1646 */ +#line 297 "awkgram.y" /* yacc.c:1646 */ { rule = Rule; if (comment != NULL) { @@ -1992,11 +1990,11 @@ yyreduce: } else (yyval) = NULL; } -#line 1996 "awkgram.c" /* yacc.c:1646 */ +#line 1994 "awkgram.c" /* yacc.c:1646 */ break; case 19: -#line 308 "awkgram.y" /* yacc.c:1646 */ +#line 306 "awkgram.y" /* yacc.c:1646 */ { rule = Rule; if (comment != NULL) { @@ -2005,11 +2003,11 @@ yyreduce: } else (yyval) = (yyvsp[0]); } -#line 2009 "awkgram.c" /* yacc.c:1646 */ +#line 2007 "awkgram.c" /* yacc.c:1646 */ break; case 20: -#line 318 "awkgram.y" /* yacc.c:1646 */ +#line 316 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *tp; @@ -2039,11 +2037,11 @@ yyreduce: (yyval) = list_append(list_merge((yyvsp[-3]), (yyvsp[0])), tp); rule = Rule; } -#line 2043 "awkgram.c" /* yacc.c:1646 */ +#line 2041 "awkgram.c" /* yacc.c:1646 */ break; case 21: -#line 348 "awkgram.y" /* yacc.c:1646 */ +#line 346 "awkgram.y" /* yacc.c:1646 */ { static int begin_seen = 0; @@ -2057,11 +2055,11 @@ yyreduce: check_comment(); (yyval) = (yyvsp[0]); } -#line 2061 "awkgram.c" /* yacc.c:1646 */ +#line 2059 "awkgram.c" /* yacc.c:1646 */ break; case 22: -#line 362 "awkgram.y" /* yacc.c:1646 */ +#line 360 "awkgram.y" /* yacc.c:1646 */ { static int end_seen = 0; @@ -2075,11 +2073,11 @@ yyreduce: check_comment(); (yyval) = (yyvsp[0]); } -#line 2079 "awkgram.c" /* yacc.c:1646 */ +#line 2077 "awkgram.c" /* yacc.c:1646 */ break; case 23: -#line 376 "awkgram.y" /* yacc.c:1646 */ +#line 374 "awkgram.y" /* yacc.c:1646 */ { func_first = false; (yyvsp[0])->in_rule = rule = BEGINFILE; @@ -2087,11 +2085,11 @@ yyreduce: check_comment(); (yyval) = (yyvsp[0]); } -#line 2091 "awkgram.c" /* yacc.c:1646 */ +#line 2089 "awkgram.c" /* yacc.c:1646 */ break; case 24: -#line 384 "awkgram.y" /* yacc.c:1646 */ +#line 382 "awkgram.y" /* yacc.c:1646 */ { func_first = false; (yyvsp[0])->in_rule = rule = ENDFILE; @@ -2099,11 +2097,11 @@ yyreduce: check_comment(); (yyval) = (yyvsp[0]); } -#line 2103 "awkgram.c" /* yacc.c:1646 */ +#line 2101 "awkgram.c" /* yacc.c:1646 */ break; case 25: -#line 395 "awkgram.y" /* yacc.c:1646 */ +#line 393 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *ip; if ((yyvsp[-3]) == NULL) @@ -2112,39 +2110,42 @@ yyreduce: ip = (yyvsp[-3]); (yyval) = ip; } -#line 2116 "awkgram.c" /* yacc.c:1646 */ +#line 2114 "awkgram.c" /* yacc.c:1646 */ break; case 26: -#line 407 "awkgram.y" /* yacc.c:1646 */ +#line 405 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 2122 "awkgram.c" /* yacc.c:1646 */ +#line 2120 "awkgram.c" /* yacc.c:1646 */ break; case 27: -#line 409 "awkgram.y" /* yacc.c:1646 */ +#line 407 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 2128 "awkgram.c" /* yacc.c:1646 */ +#line 2126 "awkgram.c" /* yacc.c:1646 */ break; case 28: -#line 411 "awkgram.y" /* yacc.c:1646 */ +#line 409 "awkgram.y" /* yacc.c:1646 */ { yyerror(_("`%s' is a built-in function, it cannot be redefined"), tokstart); YYABORT; } -#line 2138 "awkgram.c" /* yacc.c:1646 */ +#line 2136 "awkgram.c" /* yacc.c:1646 */ break; case 29: -#line 417 "awkgram.y" /* yacc.c:1646 */ - { (yyval) = (yyvsp[0]); } -#line 2144 "awkgram.c" /* yacc.c:1646 */ +#line 415 "awkgram.y" /* yacc.c:1646 */ + { + (yyval) = (yyvsp[0]); + at_seen = false; + } +#line 2145 "awkgram.c" /* yacc.c:1646 */ break; case 32: -#line 427 "awkgram.y" /* yacc.c:1646 */ +#line 428 "awkgram.y" /* yacc.c:1646 */ { /* * treat any comments between BOF and the first function @@ -2171,17 +2172,17 @@ yyreduce: /* $4 already free'd in install_function */ (yyval) = (yyvsp[-5]); } -#line 2175 "awkgram.c" /* yacc.c:1646 */ +#line 2176 "awkgram.c" /* yacc.c:1646 */ break; case 33: -#line 461 "awkgram.y" /* yacc.c:1646 */ +#line 462 "awkgram.y" /* yacc.c:1646 */ { want_regexp = true; } -#line 2181 "awkgram.c" /* yacc.c:1646 */ +#line 2182 "awkgram.c" /* yacc.c:1646 */ break; case 34: -#line 463 "awkgram.y" /* yacc.c:1646 */ +#line 464 "awkgram.y" /* yacc.c:1646 */ { NODE *n, *exp; char *re; @@ -2210,28 +2211,28 @@ yyreduce: (yyval)->opcode = Op_match_rec; (yyval)->memory = n; } -#line 2214 "awkgram.c" /* yacc.c:1646 */ +#line 2215 "awkgram.c" /* yacc.c:1646 */ break; case 35: -#line 495 "awkgram.y" /* yacc.c:1646 */ +#line 496 "awkgram.y" /* yacc.c:1646 */ { bcfree((yyvsp[0])); } -#line 2220 "awkgram.c" /* yacc.c:1646 */ +#line 2221 "awkgram.c" /* yacc.c:1646 */ break; case 37: -#line 501 "awkgram.y" /* yacc.c:1646 */ +#line 502 "awkgram.y" /* yacc.c:1646 */ { if (comment != NULL) { (yyval) = list_create(comment); comment = NULL; } else (yyval) = NULL; } -#line 2231 "awkgram.c" /* yacc.c:1646 */ +#line 2232 "awkgram.c" /* yacc.c:1646 */ break; case 38: -#line 508 "awkgram.y" /* yacc.c:1646 */ +#line 509 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[0]) == NULL) { if (comment == NULL) @@ -2259,40 +2260,40 @@ yyreduce: } yyerrok; } -#line 2263 "awkgram.c" /* yacc.c:1646 */ +#line 2264 "awkgram.c" /* yacc.c:1646 */ break; case 39: -#line 536 "awkgram.y" /* yacc.c:1646 */ +#line 537 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 2269 "awkgram.c" /* yacc.c:1646 */ +#line 2270 "awkgram.c" /* yacc.c:1646 */ break; case 42: -#line 546 "awkgram.y" /* yacc.c:1646 */ +#line 547 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 2275 "awkgram.c" /* yacc.c:1646 */ +#line 2276 "awkgram.c" /* yacc.c:1646 */ break; case 43: -#line 548 "awkgram.y" /* yacc.c:1646 */ +#line 549 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 2281 "awkgram.c" /* yacc.c:1646 */ +#line 2282 "awkgram.c" /* yacc.c:1646 */ break; case 44: -#line 550 "awkgram.y" /* yacc.c:1646 */ +#line 551 "awkgram.y" /* yacc.c:1646 */ { if (do_pretty_print) (yyval) = list_prepend((yyvsp[0]), instruction(Op_exec_count)); else (yyval) = (yyvsp[0]); } -#line 2292 "awkgram.c" /* yacc.c:1646 */ +#line 2293 "awkgram.c" /* yacc.c:1646 */ break; case 45: -#line 557 "awkgram.y" /* yacc.c:1646 */ +#line 558 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *dflt, *curr = NULL, *cexp, *cstmt; INSTRUCTION *ip, *nextc, *tbreak; @@ -2382,11 +2383,11 @@ yyreduce: break_allowed--; fix_break_continue(ip, tbreak, NULL); } -#line 2386 "awkgram.c" /* yacc.c:1646 */ +#line 2387 "awkgram.c" /* yacc.c:1646 */ break; case 46: -#line 647 "awkgram.y" /* yacc.c:1646 */ +#line 648 "awkgram.y" /* yacc.c:1646 */ { /* * ----------------- @@ -2428,11 +2429,11 @@ yyreduce: continue_allowed--; fix_break_continue(ip, tbreak, tcont); } -#line 2432 "awkgram.c" /* yacc.c:1646 */ +#line 2433 "awkgram.c" /* yacc.c:1646 */ break; case 47: -#line 689 "awkgram.y" /* yacc.c:1646 */ +#line 690 "awkgram.y" /* yacc.c:1646 */ { /* * ----------------- @@ -2474,11 +2475,11 @@ yyreduce: } /* else $1 and $4 are NULLs */ } -#line 2478 "awkgram.c" /* yacc.c:1646 */ +#line 2479 "awkgram.c" /* yacc.c:1646 */ break; case 48: -#line 731 "awkgram.y" /* yacc.c:1646 */ +#line 732 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *ip; char *var_name = (yyvsp[-5])->lextok; @@ -2591,44 +2592,44 @@ regular_loop: break_allowed--; continue_allowed--; } -#line 2595 "awkgram.c" /* yacc.c:1646 */ +#line 2596 "awkgram.c" /* yacc.c:1646 */ break; case 49: -#line 844 "awkgram.y" /* yacc.c:1646 */ +#line 845 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_for_loop((yyvsp[-11]), (yyvsp[-9]), (yyvsp[-6]), (yyvsp[-3]), (yyvsp[0])); break_allowed--; continue_allowed--; } -#line 2606 "awkgram.c" /* yacc.c:1646 */ +#line 2607 "awkgram.c" /* yacc.c:1646 */ break; case 50: -#line 851 "awkgram.y" /* yacc.c:1646 */ +#line 852 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_for_loop((yyvsp[-10]), (yyvsp[-8]), (INSTRUCTION *) NULL, (yyvsp[-3]), (yyvsp[0])); break_allowed--; continue_allowed--; } -#line 2617 "awkgram.c" /* yacc.c:1646 */ +#line 2618 "awkgram.c" /* yacc.c:1646 */ break; case 51: -#line 858 "awkgram.y" /* yacc.c:1646 */ +#line 859 "awkgram.y" /* yacc.c:1646 */ { if (do_pretty_print) (yyval) = list_prepend((yyvsp[0]), instruction(Op_exec_count)); else (yyval) = (yyvsp[0]); } -#line 2628 "awkgram.c" /* yacc.c:1646 */ +#line 2629 "awkgram.c" /* yacc.c:1646 */ break; case 52: -#line 868 "awkgram.y" /* yacc.c:1646 */ +#line 869 "awkgram.y" /* yacc.c:1646 */ { if (! break_allowed) error_ln((yyvsp[-1])->source_line, @@ -2637,11 +2638,11 @@ regular_loop: (yyval) = list_create((yyvsp[-1])); } -#line 2641 "awkgram.c" /* yacc.c:1646 */ +#line 2642 "awkgram.c" /* yacc.c:1646 */ break; case 53: -#line 877 "awkgram.y" /* yacc.c:1646 */ +#line 878 "awkgram.y" /* yacc.c:1646 */ { if (! continue_allowed) error_ln((yyvsp[-1])->source_line, @@ -2650,11 +2651,11 @@ regular_loop: (yyval) = list_create((yyvsp[-1])); } -#line 2654 "awkgram.c" /* yacc.c:1646 */ +#line 2655 "awkgram.c" /* yacc.c:1646 */ break; case 54: -#line 886 "awkgram.y" /* yacc.c:1646 */ +#line 887 "awkgram.y" /* yacc.c:1646 */ { /* if inside function (rule = 0), resolve context at run-time */ if (rule && rule != Rule) @@ -2663,11 +2664,11 @@ regular_loop: (yyvsp[-1])->target_jmp = ip_rec; (yyval) = list_create((yyvsp[-1])); } -#line 2667 "awkgram.c" /* yacc.c:1646 */ +#line 2668 "awkgram.c" /* yacc.c:1646 */ break; case 55: -#line 895 "awkgram.y" /* yacc.c:1646 */ +#line 896 "awkgram.y" /* yacc.c:1646 */ { /* if inside function (rule = 0), resolve context at run-time */ if (rule == BEGIN || rule == END || rule == ENDFILE) @@ -2678,11 +2679,11 @@ regular_loop: (yyvsp[-1])->target_endfile = ip_endfile; (yyval) = list_create((yyvsp[-1])); } -#line 2682 "awkgram.c" /* yacc.c:1646 */ +#line 2683 "awkgram.c" /* yacc.c:1646 */ break; case 56: -#line 906 "awkgram.y" /* yacc.c:1646 */ +#line 907 "awkgram.y" /* yacc.c:1646 */ { /* Initialize the two possible jump targets, the actual target * is resolved at run-time. @@ -2697,20 +2698,20 @@ regular_loop: } else (yyval) = list_append((yyvsp[-1]), (yyvsp[-2])); } -#line 2701 "awkgram.c" /* yacc.c:1646 */ +#line 2702 "awkgram.c" /* yacc.c:1646 */ break; case 57: -#line 921 "awkgram.y" /* yacc.c:1646 */ +#line 922 "awkgram.y" /* yacc.c:1646 */ { if (! in_function) yyerror(_("`return' used outside function context")); } -#line 2710 "awkgram.c" /* yacc.c:1646 */ +#line 2711 "awkgram.c" /* yacc.c:1646 */ break; case 58: -#line 924 "awkgram.y" /* yacc.c:1646 */ +#line 925 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[-1]) == NULL) { (yyval) = list_create((yyvsp[-3])); @@ -2731,17 +2732,17 @@ regular_loop: (yyval) = list_append((yyvsp[-1]), (yyvsp[-3])); } } -#line 2735 "awkgram.c" /* yacc.c:1646 */ +#line 2736 "awkgram.c" /* yacc.c:1646 */ break; case 60: -#line 956 "awkgram.y" /* yacc.c:1646 */ +#line 957 "awkgram.y" /* yacc.c:1646 */ { in_print = true; in_parens = 0; } -#line 2741 "awkgram.c" /* yacc.c:1646 */ +#line 2742 "awkgram.c" /* yacc.c:1646 */ break; case 61: -#line 957 "awkgram.y" /* yacc.c:1646 */ +#line 958 "awkgram.y" /* yacc.c:1646 */ { /* * Optimization: plain `print' has no expression list, so $3 is null. @@ -2838,17 +2839,17 @@ regular_print: } } } -#line 2842 "awkgram.c" /* yacc.c:1646 */ +#line 2843 "awkgram.c" /* yacc.c:1646 */ break; case 62: -#line 1054 "awkgram.y" /* yacc.c:1646 */ +#line 1055 "awkgram.y" /* yacc.c:1646 */ { sub_counter = 0; } -#line 2848 "awkgram.c" /* yacc.c:1646 */ +#line 2849 "awkgram.c" /* yacc.c:1646 */ break; case 63: -#line 1055 "awkgram.y" /* yacc.c:1646 */ +#line 1056 "awkgram.y" /* yacc.c:1646 */ { char *arr = (yyvsp[-2])->lextok; @@ -2881,11 +2882,11 @@ regular_print: (yyval) = list_append(list_append((yyvsp[0]), (yyvsp[-2])), (yyvsp[-3])); } } -#line 2885 "awkgram.c" /* yacc.c:1646 */ +#line 2886 "awkgram.c" /* yacc.c:1646 */ break; case 64: -#line 1092 "awkgram.y" /* yacc.c:1646 */ +#line 1093 "awkgram.y" /* yacc.c:1646 */ { static bool warned = false; char *arr = (yyvsp[-1])->lextok; @@ -2911,52 +2912,52 @@ regular_print: fatal(_("`delete' is not allowed with FUNCTAB")); } } -#line 2915 "awkgram.c" /* yacc.c:1646 */ +#line 2916 "awkgram.c" /* yacc.c:1646 */ break; case 65: -#line 1118 "awkgram.y" /* yacc.c:1646 */ +#line 1119 "awkgram.y" /* yacc.c:1646 */ { (yyval) = optimize_assignment((yyvsp[0])); } -#line 2921 "awkgram.c" /* yacc.c:1646 */ +#line 2922 "awkgram.c" /* yacc.c:1646 */ break; case 66: -#line 1123 "awkgram.y" /* yacc.c:1646 */ +#line 1124 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 2927 "awkgram.c" /* yacc.c:1646 */ +#line 2928 "awkgram.c" /* yacc.c:1646 */ break; case 67: -#line 1125 "awkgram.y" /* yacc.c:1646 */ +#line 1126 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 2933 "awkgram.c" /* yacc.c:1646 */ +#line 2934 "awkgram.c" /* yacc.c:1646 */ break; case 68: -#line 1130 "awkgram.y" /* yacc.c:1646 */ +#line 1131 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 2939 "awkgram.c" /* yacc.c:1646 */ +#line 2940 "awkgram.c" /* yacc.c:1646 */ break; case 69: -#line 1132 "awkgram.y" /* yacc.c:1646 */ +#line 1133 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[-1]) == NULL) (yyval) = list_create((yyvsp[0])); else (yyval) = list_prepend((yyvsp[-1]), (yyvsp[0])); } -#line 2950 "awkgram.c" /* yacc.c:1646 */ +#line 2951 "awkgram.c" /* yacc.c:1646 */ break; case 70: -#line 1139 "awkgram.y" /* yacc.c:1646 */ +#line 1140 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 2956 "awkgram.c" /* yacc.c:1646 */ +#line 2957 "awkgram.c" /* yacc.c:1646 */ break; case 71: -#line 1144 "awkgram.y" /* yacc.c:1646 */ +#line 1145 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *casestmt = (yyvsp[0]); if ((yyvsp[0]) == NULL) @@ -2968,11 +2969,11 @@ regular_print: bcfree((yyvsp[-2])); (yyval) = (yyvsp[-4]); } -#line 2972 "awkgram.c" /* yacc.c:1646 */ +#line 2973 "awkgram.c" /* yacc.c:1646 */ break; case 72: -#line 1156 "awkgram.y" /* yacc.c:1646 */ +#line 1157 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *casestmt = (yyvsp[0]); if ((yyvsp[0]) == NULL) @@ -2983,17 +2984,17 @@ regular_print: (yyvsp[-3])->case_stmt = casestmt; (yyval) = (yyvsp[-3]); } -#line 2987 "awkgram.c" /* yacc.c:1646 */ +#line 2988 "awkgram.c" /* yacc.c:1646 */ break; case 73: -#line 1170 "awkgram.y" /* yacc.c:1646 */ +#line 1171 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 2993 "awkgram.c" /* yacc.c:1646 */ +#line 2994 "awkgram.c" /* yacc.c:1646 */ break; case 74: -#line 1172 "awkgram.y" /* yacc.c:1646 */ +#line 1173 "awkgram.y" /* yacc.c:1646 */ { NODE *n = (yyvsp[0])->memory; (void) force_number(n); @@ -3001,71 +3002,71 @@ regular_print: bcfree((yyvsp[-1])); (yyval) = (yyvsp[0]); } -#line 3005 "awkgram.c" /* yacc.c:1646 */ +#line 3006 "awkgram.c" /* yacc.c:1646 */ break; case 75: -#line 1180 "awkgram.y" /* yacc.c:1646 */ +#line 1181 "awkgram.y" /* yacc.c:1646 */ { bcfree((yyvsp[-1])); (yyval) = (yyvsp[0]); } -#line 3014 "awkgram.c" /* yacc.c:1646 */ +#line 3015 "awkgram.c" /* yacc.c:1646 */ break; case 76: -#line 1185 "awkgram.y" /* yacc.c:1646 */ +#line 1186 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3020 "awkgram.c" /* yacc.c:1646 */ +#line 3021 "awkgram.c" /* yacc.c:1646 */ break; case 77: -#line 1187 "awkgram.y" /* yacc.c:1646 */ +#line 1188 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_push_re; (yyval) = (yyvsp[0]); } -#line 3029 "awkgram.c" /* yacc.c:1646 */ +#line 3030 "awkgram.c" /* yacc.c:1646 */ break; case 78: -#line 1195 "awkgram.y" /* yacc.c:1646 */ +#line 1196 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3035 "awkgram.c" /* yacc.c:1646 */ +#line 3036 "awkgram.c" /* yacc.c:1646 */ break; case 79: -#line 1197 "awkgram.y" /* yacc.c:1646 */ +#line 1198 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3041 "awkgram.c" /* yacc.c:1646 */ +#line 3042 "awkgram.c" /* yacc.c:1646 */ break; case 81: -#line 1207 "awkgram.y" /* yacc.c:1646 */ +#line 1208 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 3049 "awkgram.c" /* yacc.c:1646 */ +#line 3050 "awkgram.c" /* yacc.c:1646 */ break; case 82: -#line 1214 "awkgram.y" /* yacc.c:1646 */ +#line 1215 "awkgram.y" /* yacc.c:1646 */ { in_print = false; in_parens = 0; (yyval) = NULL; } -#line 3059 "awkgram.c" /* yacc.c:1646 */ +#line 3060 "awkgram.c" /* yacc.c:1646 */ break; case 83: -#line 1219 "awkgram.y" /* yacc.c:1646 */ +#line 1220 "awkgram.y" /* yacc.c:1646 */ { in_print = false; in_parens = 0; } -#line 3065 "awkgram.c" /* yacc.c:1646 */ +#line 3066 "awkgram.c" /* yacc.c:1646 */ break; case 84: -#line 1220 "awkgram.y" /* yacc.c:1646 */ +#line 1221 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[-2])->redir_type == redirect_twoway && (yyvsp[0])->lasti->opcode == Op_K_getline_redir @@ -3073,136 +3074,136 @@ regular_print: yyerror(_("multistage two-way pipelines don't work")); (yyval) = list_prepend((yyvsp[0]), (yyvsp[-2])); } -#line 3077 "awkgram.c" /* yacc.c:1646 */ +#line 3078 "awkgram.c" /* yacc.c:1646 */ break; case 85: -#line 1231 "awkgram.y" /* yacc.c:1646 */ +#line 1232 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_condition((yyvsp[-3]), (yyvsp[-5]), (yyvsp[0]), NULL, NULL); } -#line 3085 "awkgram.c" /* yacc.c:1646 */ +#line 3086 "awkgram.c" /* yacc.c:1646 */ break; case 86: -#line 1236 "awkgram.y" /* yacc.c:1646 */ +#line 1237 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_condition((yyvsp[-6]), (yyvsp[-8]), (yyvsp[-3]), (yyvsp[-2]), (yyvsp[0])); } -#line 3093 "awkgram.c" /* yacc.c:1646 */ +#line 3094 "awkgram.c" /* yacc.c:1646 */ break; case 91: -#line 1253 "awkgram.y" /* yacc.c:1646 */ +#line 1254 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3099 "awkgram.c" /* yacc.c:1646 */ +#line 3100 "awkgram.c" /* yacc.c:1646 */ break; case 92: -#line 1255 "awkgram.y" /* yacc.c:1646 */ +#line 1256 "awkgram.y" /* yacc.c:1646 */ { bcfree((yyvsp[-1])); (yyval) = (yyvsp[0]); } -#line 3108 "awkgram.c" /* yacc.c:1646 */ +#line 3109 "awkgram.c" /* yacc.c:1646 */ break; case 93: -#line 1263 "awkgram.y" /* yacc.c:1646 */ +#line 1264 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3114 "awkgram.c" /* yacc.c:1646 */ +#line 3115 "awkgram.c" /* yacc.c:1646 */ break; case 94: -#line 1265 "awkgram.y" /* yacc.c:1646 */ +#line 1266 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3120 "awkgram.c" /* yacc.c:1646 */ +#line 3121 "awkgram.c" /* yacc.c:1646 */ break; case 95: -#line 1270 "awkgram.y" /* yacc.c:1646 */ +#line 1271 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->param_count = 0; (yyval) = list_create((yyvsp[0])); } -#line 3129 "awkgram.c" /* yacc.c:1646 */ +#line 3130 "awkgram.c" /* yacc.c:1646 */ break; case 96: -#line 1275 "awkgram.y" /* yacc.c:1646 */ +#line 1276 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->param_count = (yyvsp[-2])->lasti->param_count + 1; (yyval) = list_append((yyvsp[-2]), (yyvsp[0])); yyerrok; } -#line 3139 "awkgram.c" /* yacc.c:1646 */ +#line 3140 "awkgram.c" /* yacc.c:1646 */ break; case 97: -#line 1281 "awkgram.y" /* yacc.c:1646 */ +#line 1282 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3145 "awkgram.c" /* yacc.c:1646 */ +#line 3146 "awkgram.c" /* yacc.c:1646 */ break; case 98: -#line 1283 "awkgram.y" /* yacc.c:1646 */ +#line 1284 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 3151 "awkgram.c" /* yacc.c:1646 */ +#line 3152 "awkgram.c" /* yacc.c:1646 */ break; case 99: -#line 1285 "awkgram.y" /* yacc.c:1646 */ +#line 1286 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-2]); } -#line 3157 "awkgram.c" /* yacc.c:1646 */ +#line 3158 "awkgram.c" /* yacc.c:1646 */ break; case 100: -#line 1291 "awkgram.y" /* yacc.c:1646 */ +#line 1292 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3163 "awkgram.c" /* yacc.c:1646 */ +#line 3164 "awkgram.c" /* yacc.c:1646 */ break; case 101: -#line 1293 "awkgram.y" /* yacc.c:1646 */ +#line 1294 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3169 "awkgram.c" /* yacc.c:1646 */ +#line 3170 "awkgram.c" /* yacc.c:1646 */ break; case 102: -#line 1298 "awkgram.y" /* yacc.c:1646 */ +#line 1299 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3175 "awkgram.c" /* yacc.c:1646 */ +#line 3176 "awkgram.c" /* yacc.c:1646 */ break; case 103: -#line 1300 "awkgram.y" /* yacc.c:1646 */ +#line 1301 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3181 "awkgram.c" /* yacc.c:1646 */ +#line 3182 "awkgram.c" /* yacc.c:1646 */ break; case 104: -#line 1305 "awkgram.y" /* yacc.c:1646 */ +#line 1306 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_expression_list(NULL, (yyvsp[0])); } -#line 3187 "awkgram.c" /* yacc.c:1646 */ +#line 3188 "awkgram.c" /* yacc.c:1646 */ break; case 105: -#line 1307 "awkgram.y" /* yacc.c:1646 */ +#line 1308 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_expression_list((yyvsp[-2]), (yyvsp[0])); yyerrok; } -#line 3196 "awkgram.c" /* yacc.c:1646 */ +#line 3197 "awkgram.c" /* yacc.c:1646 */ break; case 106: -#line 1312 "awkgram.y" /* yacc.c:1646 */ +#line 1313 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3202 "awkgram.c" /* yacc.c:1646 */ +#line 3203 "awkgram.c" /* yacc.c:1646 */ break; case 107: -#line 1314 "awkgram.y" /* yacc.c:1646 */ +#line 1315 "awkgram.y" /* yacc.c:1646 */ { /* * Returning the expression list instead of NULL lets @@ -3210,52 +3211,52 @@ regular_print: */ (yyval) = (yyvsp[-1]); } -#line 3214 "awkgram.c" /* yacc.c:1646 */ +#line 3215 "awkgram.c" /* yacc.c:1646 */ break; case 108: -#line 1322 "awkgram.y" /* yacc.c:1646 */ +#line 1323 "awkgram.y" /* yacc.c:1646 */ { /* Ditto */ (yyval) = mk_expression_list((yyvsp[-2]), (yyvsp[0])); } -#line 3223 "awkgram.c" /* yacc.c:1646 */ +#line 3224 "awkgram.c" /* yacc.c:1646 */ break; case 109: -#line 1327 "awkgram.y" /* yacc.c:1646 */ +#line 1328 "awkgram.y" /* yacc.c:1646 */ { /* Ditto */ (yyval) = (yyvsp[-2]); } -#line 3232 "awkgram.c" /* yacc.c:1646 */ +#line 3233 "awkgram.c" /* yacc.c:1646 */ break; case 110: -#line 1336 "awkgram.y" /* yacc.c:1646 */ +#line 1337 "awkgram.y" /* yacc.c:1646 */ { if (do_lint && (yyvsp[0])->lasti->opcode == Op_match_rec) lintwarn_ln((yyvsp[-1])->source_line, _("regular expression on right of assignment")); (yyval) = mk_assignment((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3243 "awkgram.c" /* yacc.c:1646 */ +#line 3244 "awkgram.c" /* yacc.c:1646 */ break; case 111: -#line 1343 "awkgram.y" /* yacc.c:1646 */ +#line 1344 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_boolean((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3249 "awkgram.c" /* yacc.c:1646 */ +#line 3250 "awkgram.c" /* yacc.c:1646 */ break; case 112: -#line 1345 "awkgram.y" /* yacc.c:1646 */ +#line 1346 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_boolean((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3255 "awkgram.c" /* yacc.c:1646 */ +#line 3256 "awkgram.c" /* yacc.c:1646 */ break; case 113: -#line 1347 "awkgram.y" /* yacc.c:1646 */ +#line 1348 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[-2])->lasti->opcode == Op_match_rec) warning_ln((yyvsp[-1])->source_line, @@ -3271,11 +3272,11 @@ regular_print: (yyval) = list_append(list_merge((yyvsp[-2]), (yyvsp[0])), (yyvsp[-1])); } } -#line 3275 "awkgram.c" /* yacc.c:1646 */ +#line 3276 "awkgram.c" /* yacc.c:1646 */ break; case 114: -#line 1363 "awkgram.y" /* yacc.c:1646 */ +#line 1364 "awkgram.y" /* yacc.c:1646 */ { if (do_lint_old) warning_ln((yyvsp[-1])->source_line, @@ -3285,91 +3286,91 @@ regular_print: (yyvsp[-1])->expr_count = 1; (yyval) = list_append(list_merge((yyvsp[-2]), (yyvsp[0])), (yyvsp[-1])); } -#line 3289 "awkgram.c" /* yacc.c:1646 */ +#line 3290 "awkgram.c" /* yacc.c:1646 */ break; case 115: -#line 1373 "awkgram.y" /* yacc.c:1646 */ +#line 1374 "awkgram.y" /* yacc.c:1646 */ { if (do_lint && (yyvsp[0])->lasti->opcode == Op_match_rec) lintwarn_ln((yyvsp[-1])->source_line, _("regular expression on right of comparison")); (yyval) = list_append(list_merge((yyvsp[-2]), (yyvsp[0])), (yyvsp[-1])); } -#line 3300 "awkgram.c" /* yacc.c:1646 */ +#line 3301 "awkgram.c" /* yacc.c:1646 */ break; case 116: -#line 1380 "awkgram.y" /* yacc.c:1646 */ +#line 1381 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_condition((yyvsp[-4]), (yyvsp[-3]), (yyvsp[-2]), (yyvsp[-1]), (yyvsp[0])); } -#line 3306 "awkgram.c" /* yacc.c:1646 */ +#line 3307 "awkgram.c" /* yacc.c:1646 */ break; case 117: -#line 1382 "awkgram.y" /* yacc.c:1646 */ +#line 1383 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3312 "awkgram.c" /* yacc.c:1646 */ +#line 3313 "awkgram.c" /* yacc.c:1646 */ break; case 118: -#line 1387 "awkgram.y" /* yacc.c:1646 */ +#line 1388 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3318 "awkgram.c" /* yacc.c:1646 */ +#line 3319 "awkgram.c" /* yacc.c:1646 */ break; case 119: -#line 1389 "awkgram.y" /* yacc.c:1646 */ +#line 1390 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3324 "awkgram.c" /* yacc.c:1646 */ +#line 3325 "awkgram.c" /* yacc.c:1646 */ break; case 120: -#line 1391 "awkgram.y" /* yacc.c:1646 */ +#line 1392 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_assign_quotient; (yyval) = (yyvsp[0]); } -#line 3333 "awkgram.c" /* yacc.c:1646 */ +#line 3334 "awkgram.c" /* yacc.c:1646 */ break; case 121: -#line 1399 "awkgram.y" /* yacc.c:1646 */ +#line 1400 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3339 "awkgram.c" /* yacc.c:1646 */ +#line 3340 "awkgram.c" /* yacc.c:1646 */ break; case 122: -#line 1401 "awkgram.y" /* yacc.c:1646 */ +#line 1402 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3345 "awkgram.c" /* yacc.c:1646 */ +#line 3346 "awkgram.c" /* yacc.c:1646 */ break; case 123: -#line 1406 "awkgram.y" /* yacc.c:1646 */ +#line 1407 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3351 "awkgram.c" /* yacc.c:1646 */ +#line 3352 "awkgram.c" /* yacc.c:1646 */ break; case 124: -#line 1408 "awkgram.y" /* yacc.c:1646 */ +#line 1409 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3357 "awkgram.c" /* yacc.c:1646 */ +#line 3358 "awkgram.c" /* yacc.c:1646 */ break; case 125: -#line 1413 "awkgram.y" /* yacc.c:1646 */ +#line 1414 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3363 "awkgram.c" /* yacc.c:1646 */ +#line 3364 "awkgram.c" /* yacc.c:1646 */ break; case 126: -#line 1415 "awkgram.y" /* yacc.c:1646 */ +#line 1416 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3369 "awkgram.c" /* yacc.c:1646 */ +#line 3370 "awkgram.c" /* yacc.c:1646 */ break; case 127: -#line 1417 "awkgram.y" /* yacc.c:1646 */ +#line 1418 "awkgram.y" /* yacc.c:1646 */ { int count = 2; bool is_simple_var = false; @@ -3416,47 +3417,47 @@ regular_print: max_args = count; } } -#line 3420 "awkgram.c" /* yacc.c:1646 */ +#line 3421 "awkgram.c" /* yacc.c:1646 */ break; case 129: -#line 1469 "awkgram.y" /* yacc.c:1646 */ +#line 1470 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3426 "awkgram.c" /* yacc.c:1646 */ +#line 3427 "awkgram.c" /* yacc.c:1646 */ break; case 130: -#line 1471 "awkgram.y" /* yacc.c:1646 */ +#line 1472 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3432 "awkgram.c" /* yacc.c:1646 */ +#line 3433 "awkgram.c" /* yacc.c:1646 */ break; case 131: -#line 1473 "awkgram.y" /* yacc.c:1646 */ +#line 1474 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3438 "awkgram.c" /* yacc.c:1646 */ +#line 3439 "awkgram.c" /* yacc.c:1646 */ break; case 132: -#line 1475 "awkgram.y" /* yacc.c:1646 */ +#line 1476 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3444 "awkgram.c" /* yacc.c:1646 */ +#line 3445 "awkgram.c" /* yacc.c:1646 */ break; case 133: -#line 1477 "awkgram.y" /* yacc.c:1646 */ +#line 1478 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3450 "awkgram.c" /* yacc.c:1646 */ +#line 3451 "awkgram.c" /* yacc.c:1646 */ break; case 134: -#line 1479 "awkgram.y" /* yacc.c:1646 */ +#line 1480 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3456 "awkgram.c" /* yacc.c:1646 */ +#line 3457 "awkgram.c" /* yacc.c:1646 */ break; case 135: -#line 1481 "awkgram.y" /* yacc.c:1646 */ +#line 1482 "awkgram.y" /* yacc.c:1646 */ { /* * In BEGINFILE/ENDFILE, allow `getline [var] < file' @@ -3470,29 +3471,29 @@ regular_print: _("non-redirected `getline' undefined inside END action")); (yyval) = mk_getline((yyvsp[-2]), (yyvsp[-1]), (yyvsp[0]), redirect_input); } -#line 3474 "awkgram.c" /* yacc.c:1646 */ +#line 3475 "awkgram.c" /* yacc.c:1646 */ break; case 136: -#line 1495 "awkgram.y" /* yacc.c:1646 */ +#line 1496 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_postincrement; (yyval) = mk_assignment((yyvsp[-1]), NULL, (yyvsp[0])); } -#line 3483 "awkgram.c" /* yacc.c:1646 */ +#line 3484 "awkgram.c" /* yacc.c:1646 */ break; case 137: -#line 1500 "awkgram.y" /* yacc.c:1646 */ +#line 1501 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_postdecrement; (yyval) = mk_assignment((yyvsp[-1]), NULL, (yyvsp[0])); } -#line 3492 "awkgram.c" /* yacc.c:1646 */ +#line 3493 "awkgram.c" /* yacc.c:1646 */ break; case 138: -#line 1505 "awkgram.y" /* yacc.c:1646 */ +#line 1506 "awkgram.y" /* yacc.c:1646 */ { if (do_lint_old) { warning_ln((yyvsp[-1])->source_line, @@ -3512,64 +3513,64 @@ regular_print: (yyval) = list_append(list_merge(t, (yyvsp[0])), (yyvsp[-1])); } } -#line 3516 "awkgram.c" /* yacc.c:1646 */ +#line 3517 "awkgram.c" /* yacc.c:1646 */ break; case 139: -#line 1530 "awkgram.y" /* yacc.c:1646 */ +#line 1531 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_getline((yyvsp[-1]), (yyvsp[0]), (yyvsp[-3]), (yyvsp[-2])->redir_type); bcfree((yyvsp[-2])); } -#line 3525 "awkgram.c" /* yacc.c:1646 */ +#line 3526 "awkgram.c" /* yacc.c:1646 */ break; case 140: -#line 1536 "awkgram.y" /* yacc.c:1646 */ +#line 1537 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3531 "awkgram.c" /* yacc.c:1646 */ +#line 3532 "awkgram.c" /* yacc.c:1646 */ break; case 141: -#line 1538 "awkgram.y" /* yacc.c:1646 */ +#line 1539 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3537 "awkgram.c" /* yacc.c:1646 */ +#line 3538 "awkgram.c" /* yacc.c:1646 */ break; case 142: -#line 1540 "awkgram.y" /* yacc.c:1646 */ +#line 1541 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3543 "awkgram.c" /* yacc.c:1646 */ +#line 3544 "awkgram.c" /* yacc.c:1646 */ break; case 143: -#line 1542 "awkgram.y" /* yacc.c:1646 */ +#line 1543 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3549 "awkgram.c" /* yacc.c:1646 */ +#line 3550 "awkgram.c" /* yacc.c:1646 */ break; case 144: -#line 1544 "awkgram.y" /* yacc.c:1646 */ +#line 1545 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3555 "awkgram.c" /* yacc.c:1646 */ +#line 3556 "awkgram.c" /* yacc.c:1646 */ break; case 145: -#line 1546 "awkgram.y" /* yacc.c:1646 */ +#line 1547 "awkgram.y" /* yacc.c:1646 */ { (yyval) = mk_binary((yyvsp[-2]), (yyvsp[0]), (yyvsp[-1])); } -#line 3561 "awkgram.c" /* yacc.c:1646 */ +#line 3562 "awkgram.c" /* yacc.c:1646 */ break; case 146: -#line 1551 "awkgram.y" /* yacc.c:1646 */ +#line 1552 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_create((yyvsp[0])); } -#line 3569 "awkgram.c" /* yacc.c:1646 */ +#line 3570 "awkgram.c" /* yacc.c:1646 */ break; case 147: -#line 1555 "awkgram.y" /* yacc.c:1646 */ +#line 1556 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[0])->opcode == Op_match_rec) { (yyvsp[0])->opcode = Op_nomatch; @@ -3601,37 +3602,37 @@ regular_print: } } } -#line 3605 "awkgram.c" /* yacc.c:1646 */ +#line 3606 "awkgram.c" /* yacc.c:1646 */ break; case 148: -#line 1587 "awkgram.y" /* yacc.c:1646 */ +#line 1588 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 3611 "awkgram.c" /* yacc.c:1646 */ +#line 3612 "awkgram.c" /* yacc.c:1646 */ break; case 149: -#line 1589 "awkgram.y" /* yacc.c:1646 */ +#line 1590 "awkgram.y" /* yacc.c:1646 */ { (yyval) = snode((yyvsp[-1]), (yyvsp[-3])); if ((yyval) == NULL) YYABORT; } -#line 3621 "awkgram.c" /* yacc.c:1646 */ +#line 3622 "awkgram.c" /* yacc.c:1646 */ break; case 150: -#line 1595 "awkgram.y" /* yacc.c:1646 */ +#line 1596 "awkgram.y" /* yacc.c:1646 */ { (yyval) = snode((yyvsp[-1]), (yyvsp[-3])); if ((yyval) == NULL) YYABORT; } -#line 3631 "awkgram.c" /* yacc.c:1646 */ +#line 3632 "awkgram.c" /* yacc.c:1646 */ break; case 151: -#line 1601 "awkgram.y" /* yacc.c:1646 */ +#line 1602 "awkgram.y" /* yacc.c:1646 */ { static bool warned = false; @@ -3644,45 +3645,45 @@ regular_print: if ((yyval) == NULL) YYABORT; } -#line 3648 "awkgram.c" /* yacc.c:1646 */ +#line 3649 "awkgram.c" /* yacc.c:1646 */ break; case 154: -#line 1616 "awkgram.y" /* yacc.c:1646 */ +#line 1617 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[-1])->opcode = Op_preincrement; (yyval) = mk_assignment((yyvsp[0]), NULL, (yyvsp[-1])); } -#line 3657 "awkgram.c" /* yacc.c:1646 */ +#line 3658 "awkgram.c" /* yacc.c:1646 */ break; case 155: -#line 1621 "awkgram.y" /* yacc.c:1646 */ +#line 1622 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[-1])->opcode = Op_predecrement; (yyval) = mk_assignment((yyvsp[0]), NULL, (yyvsp[-1])); } -#line 3666 "awkgram.c" /* yacc.c:1646 */ +#line 3667 "awkgram.c" /* yacc.c:1646 */ break; case 156: -#line 1626 "awkgram.y" /* yacc.c:1646 */ +#line 1627 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_create((yyvsp[0])); } -#line 3674 "awkgram.c" /* yacc.c:1646 */ +#line 3675 "awkgram.c" /* yacc.c:1646 */ break; case 157: -#line 1630 "awkgram.y" /* yacc.c:1646 */ +#line 1631 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_create((yyvsp[0])); } -#line 3682 "awkgram.c" /* yacc.c:1646 */ +#line 3683 "awkgram.c" /* yacc.c:1646 */ break; case 158: -#line 1634 "awkgram.y" /* yacc.c:1646 */ +#line 1635 "awkgram.y" /* yacc.c:1646 */ { if ((yyvsp[0])->lasti->opcode == Op_push_i && ((yyvsp[0])->lasti->memory->flags & (STRCUR|STRING)) == 0 @@ -3697,11 +3698,11 @@ regular_print: (yyval) = list_append((yyvsp[0]), (yyvsp[-1])); } } -#line 3701 "awkgram.c" /* yacc.c:1646 */ +#line 3702 "awkgram.c" /* yacc.c:1646 */ break; case 159: -#line 1649 "awkgram.y" /* yacc.c:1646 */ +#line 1650 "awkgram.y" /* yacc.c:1646 */ { /* * was: $$ = $2 @@ -3711,20 +3712,20 @@ regular_print: (yyvsp[-1])->memory = make_number(0.0); (yyval) = list_append((yyvsp[0]), (yyvsp[-1])); } -#line 3715 "awkgram.c" /* yacc.c:1646 */ +#line 3716 "awkgram.c" /* yacc.c:1646 */ break; case 160: -#line 1662 "awkgram.y" /* yacc.c:1646 */ +#line 1663 "awkgram.y" /* yacc.c:1646 */ { func_use((yyvsp[0])->lasti->func_name, FUNC_USE); (yyval) = (yyvsp[0]); } -#line 3724 "awkgram.c" /* yacc.c:1646 */ +#line 3725 "awkgram.c" /* yacc.c:1646 */ break; case 161: -#line 1667 "awkgram.y" /* yacc.c:1646 */ +#line 1668 "awkgram.y" /* yacc.c:1646 */ { /* indirect function call */ INSTRUCTION *f, *t; @@ -3756,13 +3757,25 @@ regular_print: */ (yyval) = list_prepend((yyvsp[0]), t); + at_seen = false; } -#line 3761 "awkgram.c" /* yacc.c:1646 */ +#line 3763 "awkgram.c" /* yacc.c:1646 */ break; case 162: -#line 1703 "awkgram.y" /* yacc.c:1646 */ +#line 1705 "awkgram.y" /* yacc.c:1646 */ { + NODE *n; + + if (! at_seen) { + n = lookup((yyvsp[-3])->func_name); + if (n != NULL && n->type != Node_func + && n->type != Node_ext_func && n->type != Node_old_ext_func) { + error_ln((yyvsp[-3])->source_line, + _("attempt to use non-function `%s' in function call"), + (yyvsp[-3])->func_name); + } + } param_sanity((yyvsp[-1])); (yyvsp[-3])->opcode = Op_func_call; (yyvsp[-3])->func_body = NULL; @@ -3775,49 +3788,49 @@ regular_print: (yyval) = list_append(t, (yyvsp[-3])); } } -#line 3779 "awkgram.c" /* yacc.c:1646 */ +#line 3792 "awkgram.c" /* yacc.c:1646 */ break; case 163: -#line 1720 "awkgram.y" /* yacc.c:1646 */ +#line 1733 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3785 "awkgram.c" /* yacc.c:1646 */ +#line 3798 "awkgram.c" /* yacc.c:1646 */ break; case 164: -#line 1722 "awkgram.y" /* yacc.c:1646 */ +#line 1735 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3791 "awkgram.c" /* yacc.c:1646 */ +#line 3804 "awkgram.c" /* yacc.c:1646 */ break; case 165: -#line 1727 "awkgram.y" /* yacc.c:1646 */ +#line 1740 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3797 "awkgram.c" /* yacc.c:1646 */ +#line 3810 "awkgram.c" /* yacc.c:1646 */ break; case 166: -#line 1729 "awkgram.y" /* yacc.c:1646 */ +#line 1742 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 3803 "awkgram.c" /* yacc.c:1646 */ +#line 3816 "awkgram.c" /* yacc.c:1646 */ break; case 167: -#line 1734 "awkgram.y" /* yacc.c:1646 */ +#line 1747 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3809 "awkgram.c" /* yacc.c:1646 */ +#line 3822 "awkgram.c" /* yacc.c:1646 */ break; case 168: -#line 1736 "awkgram.y" /* yacc.c:1646 */ +#line 1749 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_merge((yyvsp[-1]), (yyvsp[0])); } -#line 3817 "awkgram.c" /* yacc.c:1646 */ +#line 3830 "awkgram.c" /* yacc.c:1646 */ break; case 169: -#line 1743 "awkgram.y" /* yacc.c:1646 */ +#line 1756 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *ip = (yyvsp[0])->lasti; int count = ip->sub_count; /* # of SUBSEP-seperated expressions */ @@ -3831,11 +3844,11 @@ regular_print: sub_counter++; /* count # of dimensions */ (yyval) = (yyvsp[0]); } -#line 3835 "awkgram.c" /* yacc.c:1646 */ +#line 3848 "awkgram.c" /* yacc.c:1646 */ break; case 170: -#line 1760 "awkgram.y" /* yacc.c:1646 */ +#line 1773 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *t = (yyvsp[-1]); if ((yyvsp[-1]) == NULL) { @@ -3849,31 +3862,31 @@ regular_print: (yyvsp[0])->sub_count = count_expressions(&t, false); (yyval) = list_append(t, (yyvsp[0])); } -#line 3853 "awkgram.c" /* yacc.c:1646 */ +#line 3866 "awkgram.c" /* yacc.c:1646 */ break; case 171: -#line 1777 "awkgram.y" /* yacc.c:1646 */ +#line 1790 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); } -#line 3859 "awkgram.c" /* yacc.c:1646 */ +#line 3872 "awkgram.c" /* yacc.c:1646 */ break; case 172: -#line 1779 "awkgram.y" /* yacc.c:1646 */ +#line 1792 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_merge((yyvsp[-1]), (yyvsp[0])); } -#line 3867 "awkgram.c" /* yacc.c:1646 */ +#line 3880 "awkgram.c" /* yacc.c:1646 */ break; case 173: -#line 1786 "awkgram.y" /* yacc.c:1646 */ +#line 1799 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[-1]); } -#line 3873 "awkgram.c" /* yacc.c:1646 */ +#line 3886 "awkgram.c" /* yacc.c:1646 */ break; case 174: -#line 1791 "awkgram.y" /* yacc.c:1646 */ +#line 1804 "awkgram.y" /* yacc.c:1646 */ { char *var_name = (yyvsp[0])->lextok; @@ -3881,22 +3894,22 @@ regular_print: (yyvsp[0])->memory = variable((yyvsp[0])->source_line, var_name, Node_var_new); (yyval) = list_create((yyvsp[0])); } -#line 3885 "awkgram.c" /* yacc.c:1646 */ +#line 3898 "awkgram.c" /* yacc.c:1646 */ break; case 175: -#line 1799 "awkgram.y" /* yacc.c:1646 */ +#line 1812 "awkgram.y" /* yacc.c:1646 */ { char *arr = (yyvsp[-1])->lextok; (yyvsp[-1])->memory = variable((yyvsp[-1])->source_line, arr, Node_var_new); (yyvsp[-1])->opcode = Op_push_array; (yyval) = list_prepend((yyvsp[0]), (yyvsp[-1])); } -#line 3896 "awkgram.c" /* yacc.c:1646 */ +#line 3909 "awkgram.c" /* yacc.c:1646 */ break; case 176: -#line 1809 "awkgram.y" /* yacc.c:1646 */ +#line 1822 "awkgram.y" /* yacc.c:1646 */ { INSTRUCTION *ip = (yyvsp[0])->nexti; if (ip->opcode == Op_push @@ -3908,73 +3921,73 @@ regular_print: } else (yyval) = (yyvsp[0]); } -#line 3912 "awkgram.c" /* yacc.c:1646 */ +#line 3925 "awkgram.c" /* yacc.c:1646 */ break; case 177: -#line 1821 "awkgram.y" /* yacc.c:1646 */ +#line 1834 "awkgram.y" /* yacc.c:1646 */ { (yyval) = list_append((yyvsp[-1]), (yyvsp[-2])); if ((yyvsp[0]) != NULL) mk_assignment((yyvsp[-1]), NULL, (yyvsp[0])); } -#line 3922 "awkgram.c" /* yacc.c:1646 */ +#line 3935 "awkgram.c" /* yacc.c:1646 */ break; case 178: -#line 1830 "awkgram.y" /* yacc.c:1646 */ +#line 1843 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_postincrement; } -#line 3930 "awkgram.c" /* yacc.c:1646 */ +#line 3943 "awkgram.c" /* yacc.c:1646 */ break; case 179: -#line 1834 "awkgram.y" /* yacc.c:1646 */ +#line 1847 "awkgram.y" /* yacc.c:1646 */ { (yyvsp[0])->opcode = Op_postdecrement; } -#line 3938 "awkgram.c" /* yacc.c:1646 */ +#line 3951 "awkgram.c" /* yacc.c:1646 */ break; case 180: -#line 1837 "awkgram.y" /* yacc.c:1646 */ +#line 1850 "awkgram.y" /* yacc.c:1646 */ { (yyval) = NULL; } -#line 3944 "awkgram.c" /* yacc.c:1646 */ +#line 3957 "awkgram.c" /* yacc.c:1646 */ break; case 182: -#line 1845 "awkgram.y" /* yacc.c:1646 */ +#line 1858 "awkgram.y" /* yacc.c:1646 */ { yyerrok; } -#line 3950 "awkgram.c" /* yacc.c:1646 */ +#line 3963 "awkgram.c" /* yacc.c:1646 */ break; case 183: -#line 1849 "awkgram.y" /* yacc.c:1646 */ +#line 1862 "awkgram.y" /* yacc.c:1646 */ { yyerrok; } -#line 3956 "awkgram.c" /* yacc.c:1646 */ +#line 3969 "awkgram.c" /* yacc.c:1646 */ break; case 186: -#line 1858 "awkgram.y" /* yacc.c:1646 */ +#line 1871 "awkgram.y" /* yacc.c:1646 */ { yyerrok; } -#line 3962 "awkgram.c" /* yacc.c:1646 */ +#line 3975 "awkgram.c" /* yacc.c:1646 */ break; case 187: -#line 1862 "awkgram.y" /* yacc.c:1646 */ +#line 1875 "awkgram.y" /* yacc.c:1646 */ { (yyval) = (yyvsp[0]); yyerrok; } -#line 3968 "awkgram.c" /* yacc.c:1646 */ +#line 3981 "awkgram.c" /* yacc.c:1646 */ break; case 188: -#line 1866 "awkgram.y" /* yacc.c:1646 */ +#line 1879 "awkgram.y" /* yacc.c:1646 */ { yyerrok; } -#line 3974 "awkgram.c" /* yacc.c:1646 */ +#line 3987 "awkgram.c" /* yacc.c:1646 */ break; -#line 3978 "awkgram.c" /* yacc.c:1646 */ +#line 3991 "awkgram.c" /* yacc.c:1646 */ default: break; } /* User semantic actions sometimes alter yychar, and that requires @@ -4202,7 +4215,7 @@ yyreturn: #endif return yyresult; } -#line 1868 "awkgram.y" /* yacc.c:1906 */ +#line 1881 "awkgram.y" /* yacc.c:1906 */ struct token { @@ -4741,6 +4754,9 @@ parse_program(INSTRUCTION **pcode) if (ret == 0) /* avoid spurious warning if parser aborted with YYABORT */ check_funcs(); + if (do_posix && ! check_param_names()) + errcount++; + if (args_array == NULL) emalloc(args_array, NODE **, (max_args + 2) * sizeof(NODE *), "parse_program"); else @@ -5571,10 +5587,8 @@ yylex(void) pushback(); break; case ']': - if (tokstart[0] == '[' - && (tok == tokstart + 1 - || (tok == tokstart + 2 - && tokstart[1] == '^'))) + if (tok[-1] == '[' + || (tok[-2] == '[' && tok[-1] == '^')) /* do nothing */; else in_brack--; @@ -5672,6 +5686,7 @@ retry: return lasttok = NEWLINE; case '@': + at_seen = true; return lasttok = '@'; case '\\': @@ -6815,7 +6830,7 @@ install_function(char *fname, INSTRUCTION *fi, INSTRUCTION *plist) int pcount = 0; r = lookup(fname); - if (r != NULL || is_deferred_variable(fname)) { + if (r != NULL) { error_ln(fi->source_line, _("function name `%s' previously defined"), fname); return -1; } @@ -7008,50 +7023,6 @@ param_sanity(INSTRUCTION *arglist) } } -/* deferred variables --- those that are only defined if needed. */ - -/* - * Is there any reason to use a hash table for deferred variables? At the - * moment, there are only 1 to 3 such variables, so it may not be worth - * the overhead. If more modules start using this facility, it should - * probably be converted into a hash table. - */ - -static struct deferred_variable { - NODE *(*load_func)(void); - struct deferred_variable *next; - char name[1]; /* variable-length array */ -} *deferred_variables; - -/* register_deferred_variable --- add a var name and loading function to the list */ - -void -register_deferred_variable(const char *name, NODE *(*load_func)(void)) -{ - struct deferred_variable *dv; - size_t sl = strlen(name); - - emalloc(dv, struct deferred_variable *, sizeof(*dv)+sl, - "register_deferred_variable"); - dv->load_func = load_func; - dv->next = deferred_variables; - memcpy(dv->name, name, sl+1); - deferred_variables = dv; -} - -/* is_deferred_variable --- check if NAME is a deferred variable */ - -static bool -is_deferred_variable(const char *name) -{ - struct deferred_variable *dv; - for (dv = deferred_variables; dv != NULL; dv = dv->next) - if (strcmp(name, dv->name) == 0) - return true; - return false; -} - - /* variable --- make sure NAME is in the symbol table */ NODE * @@ -7063,44 +7034,14 @@ variable(int location, char *name, NODETYPE type) if (r->type == Node_func || r->type == Node_ext_func ) error_ln(location, _("function `%s' called with space between name and `(',\nor used as a variable or an array"), r->vname); - if (r == symbol_table) - symtab_used = true; } else { /* not found */ - struct deferred_variable *dv; - - for (dv = deferred_variables; true; dv = dv->next) { - if (dv == NULL) { - /* - * This is the only case in which we may not free the string. - */ - return install_symbol(name, type); - } - if (strcmp(name, dv->name) == 0) { - r = (*dv->load_func)(); - break; - } - } + return install_symbol(name, type); } efree(name); return r; } -/* process_deferred --- if the program uses SYMTAB, load deferred variables */ - -static void -process_deferred() -{ - struct deferred_variable *dv; - - if (! symtab_used) - return; - - for (dv = deferred_variables; dv != NULL; dv = dv->next) { - (void) dv->load_func(); - } -} - /* make_regnode --- make a regular expression node */ static NODE * @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 1986, 1988, 1989, 1991-2014 the Free Software Foundation, Inc. + * Copyright (C) 1986, 1988, 1989, 1991-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -57,7 +57,6 @@ static int include_source(INSTRUCTION *file); static int load_library(INSTRUCTION *file); static void next_sourcefile(void); static char *tokexpand(void); -static bool is_deferred_variable(const char *name); #define instruction(t) bcalloc(t, 1, 0) @@ -79,8 +78,6 @@ static int count_expressions(INSTRUCTION **list, bool isarg); static INSTRUCTION *optimize_assignment(INSTRUCTION *exp); static void add_lint(INSTRUCTION *list, LINTTYPE linttype); -static void process_deferred(); - enum defref { FUNC_DEFINE, FUNC_USE, FUNC_EXT }; static void func_use(const char *name, enum defref how); static void check_funcs(void); @@ -90,10 +87,10 @@ static int one_line_close(int fd); static void split_comment(void); static void check_comment(void); +static bool at_seen = false; static bool want_source = false; static bool want_regexp = false; /* lexical scanning kludge */ static char *in_function; /* parsing kludge */ -static bool symtab_used = false; /* program used SYMTAB */ static int rule = 0; const char *const ruletab[] = { @@ -216,8 +213,6 @@ program | program LEX_EOF { next_sourcefile(); - if (sourcefile == srcfiles) - process_deferred(); } | program error { @@ -234,6 +229,7 @@ rule : pattern action { (void) append_rule($1, $2); + first_rule = false; } | pattern statement_term { @@ -255,11 +251,13 @@ rule | '@' LEX_INCLUDE source statement_term { want_source = false; + at_seen = false; yyerrok; } | '@' LEX_LOAD library statement_term { want_source = false; + at_seen = false; yyerrok; } ; @@ -414,7 +412,10 @@ func_name YYABORT; } | '@' LEX_EVAL - { $$ = $2; } + { + $$ = $2; + at_seen = false; + } ; lex_builtin @@ -1695,12 +1696,24 @@ func_call */ $$ = list_prepend($2, t); + at_seen = false; } ; direct_func_call : FUNC_CALL '(' opt_expression_list r_paren { + NODE *n; + + if (! at_seen) { + n = lookup($1->func_name); + if (n != NULL && n->type != Node_func + && n->type != Node_ext_func && n->type != Node_old_ext_func) { + error_ln($1->source_line, + _("attempt to use non-function `%s' in function call"), + $1->func_name); + } + } param_sanity($3); $1->opcode = Op_func_call; $1->func_body = NULL; @@ -2403,6 +2416,9 @@ parse_program(INSTRUCTION **pcode) if (ret == 0) /* avoid spurious warning if parser aborted with YYABORT */ check_funcs(); + if (do_posix && ! check_param_names()) + errcount++; + if (args_array == NULL) emalloc(args_array, NODE **, (max_args + 2) * sizeof(NODE *), "parse_program"); else @@ -3233,10 +3249,8 @@ yylex(void) pushback(); break; case ']': - if (tokstart[0] == '[' - && (tok == tokstart + 1 - || (tok == tokstart + 2 - && tokstart[1] == '^'))) + if (tok[-1] == '[' + || (tok[-2] == '[' && tok[-1] == '^')) /* do nothing */; else in_brack--; @@ -3334,6 +3348,7 @@ retry: return lasttok = NEWLINE; case '@': + at_seen = true; return lasttok = '@'; case '\\': @@ -4477,7 +4492,7 @@ install_function(char *fname, INSTRUCTION *fi, INSTRUCTION *plist) int pcount = 0; r = lookup(fname); - if (r != NULL || is_deferred_variable(fname)) { + if (r != NULL) { error_ln(fi->source_line, _("function name `%s' previously defined"), fname); return -1; } @@ -4670,50 +4685,6 @@ param_sanity(INSTRUCTION *arglist) } } -/* deferred variables --- those that are only defined if needed. */ - -/* - * Is there any reason to use a hash table for deferred variables? At the - * moment, there are only 1 to 3 such variables, so it may not be worth - * the overhead. If more modules start using this facility, it should - * probably be converted into a hash table. - */ - -static struct deferred_variable { - NODE *(*load_func)(void); - struct deferred_variable *next; - char name[1]; /* variable-length array */ -} *deferred_variables; - -/* register_deferred_variable --- add a var name and loading function to the list */ - -void -register_deferred_variable(const char *name, NODE *(*load_func)(void)) -{ - struct deferred_variable *dv; - size_t sl = strlen(name); - - emalloc(dv, struct deferred_variable *, sizeof(*dv)+sl, - "register_deferred_variable"); - dv->load_func = load_func; - dv->next = deferred_variables; - memcpy(dv->name, name, sl+1); - deferred_variables = dv; -} - -/* is_deferred_variable --- check if NAME is a deferred variable */ - -static bool -is_deferred_variable(const char *name) -{ - struct deferred_variable *dv; - for (dv = deferred_variables; dv != NULL; dv = dv->next) - if (strcmp(name, dv->name) == 0) - return true; - return false; -} - - /* variable --- make sure NAME is in the symbol table */ NODE * @@ -4725,44 +4696,14 @@ variable(int location, char *name, NODETYPE type) if (r->type == Node_func || r->type == Node_ext_func ) error_ln(location, _("function `%s' called with space between name and `(',\nor used as a variable or an array"), r->vname); - if (r == symbol_table) - symtab_used = true; } else { /* not found */ - struct deferred_variable *dv; - - for (dv = deferred_variables; true; dv = dv->next) { - if (dv == NULL) { - /* - * This is the only case in which we may not free the string. - */ - return install_symbol(name, type); - } - if (strcmp(name, dv->name) == 0) { - r = (*dv->load_func)(); - break; - } - } + return install_symbol(name, type); } efree(name); return r; } -/* process_deferred --- if the program uses SYMTAB, load deferred variables */ - -static void -process_deferred() -{ - struct deferred_variable *dv; - - if (! symtab_used) - return; - - for (dv = deferred_variables; dv != NULL; dv = dv->next) { - (void) dv->load_func(); - } -} - /* make_regnode --- make a regular expression node */ static NODE * diff --git a/awklib/Makefile.in b/awklib/Makefile.in index b4b887a1..6dc8ea81 100644 --- a/awklib/Makefile.in +++ b/awklib/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -38,7 +38,17 @@ # VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -101,8 +111,6 @@ build_triplet = @build@ host_triplet = @host@ pkglibexec_PROGRAMS = pwcat$(EXEEXT) grcat$(EXEEXT) subdir = awklib -DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ - $(top_srcdir)/mkinstalldirs $(top_srcdir)/depcomp ChangeLog ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/codeset.m4 $(top_srcdir)/m4/gettext.m4 \ @@ -117,6 +125,7 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/ulonglong.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs CONFIG_HEADER = $(top_builddir)/config.h CONFIG_CLEAN_FILES = @@ -183,6 +192,8 @@ am__define_uniq_tagged_files = \ done | $(am__uniquify_input)` ETAGS = etags CTAGS = ctags +am__DIST_COMMON = $(srcdir)/Makefile.in $(top_srcdir)/depcomp \ + $(top_srcdir)/mkinstalldirs ChangeLog DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) pkgdatadir = $(datadir)/awk pkglibexecdir = $(libexecdir)/awk @@ -340,7 +351,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu awklib/Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu awklib/Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -631,6 +641,8 @@ uninstall-am: uninstall-local uninstall-pkglibexecPROGRAMS tags tags-am uninstall uninstall-am uninstall-local \ uninstall-pkglibexecPROGRAMS +.PRECIOUS: Makefile + all: $(srcdir)/stamp-eg $(AUXPROGS) $(AUXAWK) diff --git a/awklib/eg/lib/assert.awk b/awklib/eg/lib/assert.awk index 75fd8853..c8e13490 100644 --- a/awklib/eg/lib/assert.awk +++ b/awklib/eg/lib/assert.awk @@ -1,4 +1,4 @@ -# assert --- assert that a condition is true. Otherwise exit. +# assert --- assert that a condition is true. Otherwise, exit. # # Arnold Robbins, arnold@skeeve.com, Public Domain diff --git a/awklib/eg/lib/bits2str.awk b/awklib/eg/lib/bits2str.awk index 9725ee8f..a10ffad1 100644 --- a/awklib/eg/lib/bits2str.awk +++ b/awklib/eg/lib/bits2str.awk @@ -1,4 +1,4 @@ -# bits2str --- turn a byte into readable 1's and 0's +# bits2str --- turn a byte into readable ones and zeros function bits2str(bits, data, mask) { diff --git a/awklib/eg/lib/quicksort.awk b/awklib/eg/lib/quicksort.awk index 3ba2d6e3..e0ed8bc7 100644 --- a/awklib/eg/lib/quicksort.awk +++ b/awklib/eg/lib/quicksort.awk @@ -4,8 +4,9 @@ # Arnold Robbins, arnold@skeeve.com, Public Domain # January 2009 -# quicksort --- C.A.R. Hoare's quick sort algorithm. See Wikipedia -# or almost any algorithms or computer science text + +# quicksort --- C.A.R. Hoare's quicksort algorithm. See Wikipedia +# or almost any algorithms or computer science text. # # Adapted from K&R-II, page 110 diff --git a/awklib/eg/prog/anagram.awk b/awklib/eg/prog/anagram.awk index 7ca14559..df2768d9 100644 --- a/awklib/eg/prog/anagram.awk +++ b/awklib/eg/prog/anagram.awk @@ -1,5 +1,5 @@ -# anagram.awk --- An implementation of the anagram finding algorithm -# from Jon Bentley's "Programming Pearls", 2nd edition. +# anagram.awk --- An implementation of the anagram-finding algorithm +# from Jon Bentley's "Programming Pearls," 2nd edition. # Addison Wesley, 2000, ISBN 0-201-65788-0. # Column 2, Problem C, section 2.8, pp 18-20. # @@ -21,7 +21,7 @@ key = word2key($1) # Build signature data[key][$1] = $1 # Store word with signature } -# word2key --- split word apart into letters, sort, joining back together +# word2key --- split word apart into letters, sort, and join back together function word2key(word, a, i, n, result) { diff --git a/awklib/eg/prog/extract.awk b/awklib/eg/prog/extract.awk index 24f40ce5..f5dfcf40 100644 --- a/awklib/eg/prog/extract.awk +++ b/awklib/eg/prog/extract.awk @@ -1,4 +1,4 @@ -# extract.awk --- extract files and run programs from texinfo files +# extract.awk --- extract files and run programs from Texinfo files # # Arnold Robbins, arnold@skeeve.com, Public Domain # May 1993 diff --git a/awklib/eg/prog/translate.awk b/awklib/eg/prog/translate.awk index cf7f3897..e7403717 100644 --- a/awklib/eg/prog/translate.awk +++ b/awklib/eg/prog/translate.awk @@ -4,7 +4,7 @@ # August 1989 # February 2009 - bug fix -# Bugs: does not handle things like: tr A-Z a-z, it has +# Bugs: does not handle things like tr A-Z a-z; it has # to be spelled out. However, if `to' is shorter than `from', # the last character in `to' is used for the rest of `from'. @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 1986, 1988, 1989, 1991-2014 the Free Software Foundation, Inc. + * Copyright (C) 1986, 1988, 1989, 1991-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -514,6 +514,9 @@ do_length(int nargs) * Support for deferred loading of array elements requires that * we use the array length interface even though it isn't * necessary for the built-in array types. + * + * 1/2015: The deferred arrays are gone, but this is probably + * still a good idea. */ size = assoc_length(tmp); @@ -908,7 +911,10 @@ check_pos: case '*': if (cur == NULL) break; - if (! do_traditional && isdigit((unsigned char) *s1)) { + if (! do_traditional && used_dollar && ! isdigit((unsigned char) *s1)) { + fatal(_("fatal: must use `count$' on all formats or none")); + break; /* silence warnings */ + } else if (! do_traditional && isdigit((unsigned char) *s1)) { int val = 0; for (; n0 > 0 && *s1 && isdigit((unsigned char) *s1); s1++, n0--) { @@ -1,8 +1,8 @@ -/* A Bison parser, made by GNU Bison 3.0.2. */ +/* A Bison parser, made by GNU Bison 3.0.4. */ /* Bison implementation for Yacc-like parsers in C - Copyright (C) 1984, 1989-1990, 2000-2013 Free Software Foundation, Inc. + Copyright (C) 1984, 1989-1990, 2000-2015 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -44,7 +44,7 @@ #define YYBISON 1 /* Bison version. */ -#define YYBISON_VERSION "3.0.2" +#define YYBISON_VERSION "3.0.4" /* Skeleton name. */ #define YYSKELETON_NAME "yacc.c" @@ -3,7 +3,7 @@ scriptversion=2012-10-14.11; # UTC -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # Written by Tom Tromey <tromey@cygnus.com>. # # This program is free software; you can redistribute it and/or modify diff --git a/config.guess b/config.guess index 4438cd70..6c32c864 100755 --- a/config.guess +++ b/config.guess @@ -2,7 +2,7 @@ # Attempt to guess a canonical system name. # Copyright 1992-2014 Free Software Foundation, Inc. -timestamp='2014-01-01' +timestamp='2014-11-04' # This file is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by @@ -24,12 +24,12 @@ timestamp='2014-01-01' # program. This Exception is an additional permission under section 7 # of the GNU General Public License, version 3 ("GPLv3"). # -# Originally written by Per Bothner. +# Originally written by Per Bothner; maintained since 2000 by Ben Elliston. # # You can get the latest version of this script from: # http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD # -# Please send patches with a ChangeLog entry to config-patches@gnu.org. +# Please send patches to <config-patches@gnu.org>. me=`echo "$0" | sed -e 's,.*/,,'` @@ -149,7 +149,7 @@ Linux|GNU|GNU/*) LIBC=gnu #endif EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^LIBC'` + eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^LIBC' | sed 's, ,,g'` ;; esac @@ -579,8 +579,9 @@ EOF else IBM_ARCH=powerpc fi - if [ -x /usr/bin/oslevel ] ; then - IBM_REV=`/usr/bin/oslevel` + if [ -x /usr/bin/lslpp ] ; then + IBM_REV=`/usr/bin/lslpp -Lqc bos.rte.libc | + awk -F: '{ print $3 }' | sed s/[0-9]*$/0/` else IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} fi @@ -826,7 +827,7 @@ EOF *:MINGW*:*) echo ${UNAME_MACHINE}-pc-mingw32 exit ;; - i*:MSYS*:*) + *:MSYS*:*) echo ${UNAME_MACHINE}-pc-msys exit ;; i*:windows32*:*) @@ -969,10 +970,10 @@ EOF eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^CPU'` test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } ;; - or1k:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + openrisc*:Linux:*:*) + echo or1k-unknown-linux-${LIBC} exit ;; - or32:Linux:*:*) + or32:Linux:*:* | or1k*:Linux:*:*) echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; padre:Linux:*:*) @@ -1371,154 +1372,6 @@ EOF exit ;; esac -eval $set_cc_for_build -cat >$dummy.c <<EOF -#ifdef _SEQUENT_ -# include <sys/types.h> -# include <sys/utsname.h> -#endif -main () -{ -#if defined (sony) -#if defined (MIPSEB) - /* BFD wants "bsd" instead of "newsos". Perhaps BFD should be changed, - I don't know.... */ - printf ("mips-sony-bsd\n"); exit (0); -#else -#include <sys/param.h> - printf ("m68k-sony-newsos%s\n", -#ifdef NEWSOS4 - "4" -#else - "" -#endif - ); exit (0); -#endif -#endif - -#if defined (__arm) && defined (__acorn) && defined (__unix) - printf ("arm-acorn-riscix\n"); exit (0); -#endif - -#if defined (hp300) && !defined (hpux) - printf ("m68k-hp-bsd\n"); exit (0); -#endif - -#if defined (NeXT) -#if !defined (__ARCHITECTURE__) -#define __ARCHITECTURE__ "m68k" -#endif - int version; - version=`(hostinfo | sed -n 's/.*NeXT Mach \([0-9]*\).*/\1/p') 2>/dev/null`; - if (version < 4) - printf ("%s-next-nextstep%d\n", __ARCHITECTURE__, version); - else - printf ("%s-next-openstep%d\n", __ARCHITECTURE__, version); - exit (0); -#endif - -#if defined (MULTIMAX) || defined (n16) -#if defined (UMAXV) - printf ("ns32k-encore-sysv\n"); exit (0); -#else -#if defined (CMU) - printf ("ns32k-encore-mach\n"); exit (0); -#else - printf ("ns32k-encore-bsd\n"); exit (0); -#endif -#endif -#endif - -#if defined (__386BSD__) - printf ("i386-pc-bsd\n"); exit (0); -#endif - -#if defined (sequent) -#if defined (i386) - printf ("i386-sequent-dynix\n"); exit (0); -#endif -#if defined (ns32000) - printf ("ns32k-sequent-dynix\n"); exit (0); -#endif -#endif - -#if defined (_SEQUENT_) - struct utsname un; - - uname(&un); - - if (strncmp(un.version, "V2", 2) == 0) { - printf ("i386-sequent-ptx2\n"); exit (0); - } - if (strncmp(un.version, "V1", 2) == 0) { /* XXX is V1 correct? */ - printf ("i386-sequent-ptx1\n"); exit (0); - } - printf ("i386-sequent-ptx\n"); exit (0); - -#endif - -#if defined (vax) -# if !defined (ultrix) -# include <sys/param.h> -# if defined (BSD) -# if BSD == 43 - printf ("vax-dec-bsd4.3\n"); exit (0); -# else -# if BSD == 199006 - printf ("vax-dec-bsd4.3reno\n"); exit (0); -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# endif -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# else - printf ("vax-dec-ultrix\n"); exit (0); -# endif -#endif - -#if defined (alliant) && defined (i860) - printf ("i860-alliant-bsd\n"); exit (0); -#endif - - exit (1); -} -EOF - -$CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null && SYSTEM_NAME=`$dummy` && - { echo "$SYSTEM_NAME"; exit; } - -# Apollos put the system type in the environment. - -test -d /usr/apollo && { echo ${ISP}-apollo-${SYSTYPE}; exit; } - -# Convex versions that predate uname can use getsysinfo(1) - -if [ -x /usr/convex/getsysinfo ] -then - case `getsysinfo -f cpu_type` in - c1*) - echo c1-convex-bsd - exit ;; - c2*) - if getsysinfo -f scalar_acc - then echo c32-convex-bsd - else echo c2-convex-bsd - fi - exit ;; - c34*) - echo c34-convex-bsd - exit ;; - c38*) - echo c38-convex-bsd - exit ;; - c4*) - echo c4-convex-bsd - exit ;; - esac -fi - cat >&2 <<EOF $0: unable to guess system type @@ -2,7 +2,7 @@ # Configuration validation subroutine script. # Copyright 1992-2014 Free Software Foundation, Inc. -timestamp='2014-01-01' +timestamp='2014-12-03' # This file is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by @@ -25,7 +25,7 @@ timestamp='2014-01-01' # of the GNU General Public License, version 3 ("GPLv3"). -# Please send patches with a ChangeLog entry to config-patches@gnu.org. +# Please send patches to <config-patches@gnu.org>. # # Configuration subroutine to validate and canonicalize a configuration type. # Supply the specified configuration type as an argument. @@ -283,8 +283,10 @@ case $basic_machine in | mips64vr5900 | mips64vr5900el \ | mipsisa32 | mipsisa32el \ | mipsisa32r2 | mipsisa32r2el \ + | mipsisa32r6 | mipsisa32r6el \ | mipsisa64 | mipsisa64el \ | mipsisa64r2 | mipsisa64r2el \ + | mipsisa64r6 | mipsisa64r6el \ | mipsisa64sb1 | mipsisa64sb1el \ | mipsisa64sr71k | mipsisa64sr71kel \ | mipsr5900 | mipsr5900el \ @@ -296,11 +298,11 @@ case $basic_machine in | nds32 | nds32le | nds32be \ | nios | nios2 | nios2eb | nios2el \ | ns16k | ns32k \ - | open8 \ - | or1k | or32 \ + | open8 | or1k | or1knd | or32 \ | pdp10 | pdp11 | pj | pjl \ | powerpc | powerpc64 | powerpc64le | powerpcle \ | pyramid \ + | riscv32 | riscv64 \ | rl78 | rx \ | score \ | sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \ @@ -311,6 +313,7 @@ case $basic_machine in | tahoe | tic4x | tic54x | tic55x | tic6x | tic80 | tron \ | ubicom32 \ | v850 | v850e | v850e1 | v850e2 | v850es | v850e2v3 \ + | visium \ | we32k \ | x86 | xc16x | xstormy16 | xtensa \ | z8k | z80) @@ -325,6 +328,9 @@ case $basic_machine in c6x) basic_machine=tic6x-unknown ;; + leon|leon[3-9]) + basic_machine=sparc-$basic_machine + ;; m6811 | m68hc11 | m6812 | m68hc12 | m68hcs12x | nvptx | picochip) basic_machine=$basic_machine-unknown os=-none @@ -402,8 +408,10 @@ case $basic_machine in | mips64vr5900-* | mips64vr5900el-* \ | mipsisa32-* | mipsisa32el-* \ | mipsisa32r2-* | mipsisa32r2el-* \ + | mipsisa32r6-* | mipsisa32r6el-* \ | mipsisa64-* | mipsisa64el-* \ | mipsisa64r2-* | mipsisa64r2el-* \ + | mipsisa64r6-* | mipsisa64r6el-* \ | mipsisa64sb1-* | mipsisa64sb1el-* \ | mipsisa64sr71k-* | mipsisa64sr71kel-* \ | mipsr5900-* | mipsr5900el-* \ @@ -415,6 +423,7 @@ case $basic_machine in | nios-* | nios2-* | nios2eb-* | nios2el-* \ | none-* | np1-* | ns16k-* | ns32k-* \ | open8-* \ + | or1k*-* \ | orion-* \ | pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \ | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* \ @@ -432,6 +441,7 @@ case $basic_machine in | ubicom32-* \ | v850-* | v850e-* | v850e1-* | v850es-* | v850e2-* | v850e2v3-* \ | vax-* \ + | visium-* \ | we32k-* \ | x86-* | x86_64-* | xc16x-* | xps100-* \ | xstormy16-* | xtensa*-* \ @@ -769,6 +779,9 @@ case $basic_machine in basic_machine=m68k-isi os=-sysv ;; + leon-*|leon[3-9]-*) + basic_machine=sparc-`echo $basic_machine | sed 's/-.*//'` + ;; m68knommu) basic_machine=m68k-unknown os=-linux @@ -824,6 +837,10 @@ case $basic_machine in basic_machine=powerpc-unknown os=-morphos ;; + moxiebox) + basic_machine=moxie-unknown + os=-moxiebox + ;; msdos) basic_machine=i386-pc os=-msdos @@ -1369,14 +1386,14 @@ case $os in | -cygwin* | -msys* | -pe* | -psos* | -moss* | -proelf* | -rtems* \ | -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \ | -linux-newlib* | -linux-musl* | -linux-uclibc* \ - | -uxpv* | -beos* | -mpeix* | -udk* \ + | -uxpv* | -beos* | -mpeix* | -udk* | -moxiebox* \ | -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \ | -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \ | -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \ | -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \ | -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \ | -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \ - | -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es*) + | -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* | -tirtos*) # Remember, each alternative MUST END IN *, to match a version number. ;; -qnx*) @@ -1594,9 +1611,6 @@ case $basic_machine in mips*-*) os=-elf ;; - or1k-*) - os=-elf - ;; or32-*) os=-coff ;; @@ -2592,7 +2592,7 @@ then fi -am__api_version='1.14' +am__api_version='1.15' ac_aux_dir= for ac_dir in "$srcdir" "$srcdir/.." "$srcdir/../.."; do @@ -2793,8 +2793,8 @@ test "$program_suffix" != NONE && ac_script='s/[\\$]/&&/g;s/;s,x,x,$//' program_transform_name=`$as_echo "$program_transform_name" | sed "$ac_script"` -# expand $ac_aux_dir to an absolute path -am_aux_dir=`cd $ac_aux_dir && pwd` +# Expand $ac_aux_dir to an absolute path. +am_aux_dir=`cd "$ac_aux_dir" && pwd` if test x"${MISSING+set}" != xset; then case $am_aux_dir in @@ -2813,7 +2813,7 @@ else $as_echo "$as_me: WARNING: 'missing' script is too old or missing" >&2;} fi -if test x"${install_sh}" != xset; then +if test x"${install_sh+set}" != xset; then case $am_aux_dir in *\ * | *\ *) install_sh="\${SHELL} '$am_aux_dir/install-sh'" ;; @@ -3141,8 +3141,8 @@ MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"} # <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html> mkdir_p='$(MKDIR_P)' -# We need awk for the "check" target. The system "awk" is bad on -# some platforms. +# We need awk for the "check" target (and possibly the TAP driver). The +# system "awk" is bad on some platforms. # Always define AMTAR for backward compatibility. Yes, it's still used # in the wild :-( We should find a proper way to deprecate it ... AMTAR='$${TAR-tar}' @@ -3203,6 +3203,7 @@ fi + # Check whether --with-whiny-user-strftime was given. if test "${with_whiny_user_strftime+set}" = set; then : withval=$with_whiny_user_strftime; if test "$withval" = yes @@ -5845,7 +5846,7 @@ then # enable debugging using macros also if test "$GCC" = yes then - CFLAGS="$CFLAGS -Wall -fno-builtin -g3 -gdwarf-2" + CFLAGS="$CFLAGS -Wall -fno-builtin -g3" fi { $as_echo "$as_me:${as_lineno-$LINENO}: result: yes" >&5 $as_echo "yes" >&6; } @@ -7515,36 +7516,42 @@ else if test $am_cv_lib_iconv = yes; then LIBS="$LIBS $LIBICONV" fi - if test "$cross_compiling" = yes; then : - - case "$host_os" in - aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; - *) am_cv_func_iconv_works="guessing yes" ;; - esac - + am_cv_func_iconv_works=no + for ac_iconv_const in '' 'const'; do + if test "$cross_compiling" = yes; then : + case "$host_os" in + aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; + *) am_cv_func_iconv_works="guessing yes" ;; + esac else cat confdefs.h - <<_ACEOF >conftest.$ac_ext /* end confdefs.h. */ #include <iconv.h> #include <string.h> -int main () + +#ifndef ICONV_CONST +# define ICONV_CONST $ac_iconv_const +#endif + +int +main () { - int result = 0; +int result = 0; /* Test against AIX 5.1 bug: Failures are not distinguishable from successful returns. */ { iconv_t cd_utf8_to_88591 = iconv_open ("ISO8859-1", "UTF-8"); if (cd_utf8_to_88591 != (iconv_t)(-1)) { - static const char input[] = "\342\202\254"; /* EURO SIGN */ + static ICONV_CONST char input[] = "\342\202\254"; /* EURO SIGN */ char buf[10]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_utf8_to_88591, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res == 0) result |= 1; @@ -7557,14 +7564,14 @@ int main () iconv_t cd_ascii_to_88591 = iconv_open ("ISO8859-1", "646"); if (cd_ascii_to_88591 != (iconv_t)(-1)) { - static const char input[] = "\263"; + static ICONV_CONST char input[] = "\263"; char buf[10]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_ascii_to_88591, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res == 0) result |= 2; @@ -7576,14 +7583,14 @@ int main () iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1"); if (cd_88591_to_utf8 != (iconv_t)(-1)) { - static const char input[] = "\304"; + static ICONV_CONST char input[] = "\304"; static char buf[2] = { (char)0xDE, (char)0xAD }; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = 1; char *outptr = buf; size_t outbytesleft = 1; size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res != (size_t)(-1) || outptr - buf > 1 || buf[1] != (char)0xAD) result |= 4; @@ -7596,14 +7603,14 @@ int main () iconv_t cd_88591_to_utf8 = iconv_open ("utf8", "iso88591"); if (cd_88591_to_utf8 != (iconv_t)(-1)) { - static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static ICONV_CONST char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; char buf[50]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if ((int)res > 0) result |= 8; @@ -7623,17 +7630,20 @@ int main () && iconv_open ("utf8", "eucJP") == (iconv_t)(-1)) result |= 16; return result; + + ; + return 0; } _ACEOF if ac_fn_c_try_run "$LINENO"; then : am_cv_func_iconv_works=yes -else - am_cv_func_iconv_works=no fi rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \ conftest.$ac_objext conftest.beam conftest.$ac_ext fi + test "$am_cv_func_iconv_works" = no || break + done LIBS="$am_save_LIBS" fi diff --git a/configure.ac b/configure.ac index 0b33b966..548a3ce3 100644 --- a/configure.ac +++ b/configure.ac @@ -1,7 +1,7 @@ dnl dnl configure.ac --- autoconf input file for gawk dnl -dnl Copyright (C) 1995-2014 the Free Software Foundation, Inc. +dnl Copyright (C) 1995-2015 the Free Software Foundation, Inc. dnl dnl This file is part of GAWK, the GNU implementation of the dnl AWK Programming Language. @@ -40,7 +40,7 @@ then fi AC_PREREQ(2.69) -AM_INIT_AUTOMAKE([1.14 dist-xz dist-lzip]) +AM_INIT_AUTOMAKE([1.15 dist-xz dist-lzip]) AC_CONFIG_MACRO_DIR([m4]) @@ -97,7 +97,7 @@ then # enable debugging using macros also if test "$GCC" = yes then - CFLAGS="$CFLAGS -Wall -fno-builtin -g3 -gdwarf-2" + CFLAGS="$CFLAGS -Wall -fno-builtin -g3" fi AC_MSG_RESULT([yes]) else @@ -131,7 +131,7 @@ AC_LANG([C]) dnl initialize GNU gettext AM_GNU_GETTEXT([external]) -AM_GNU_GETTEXT_VERSION([0.19.3]) +AM_GNU_GETTEXT_VERSION([0.19.4]) AM_LANGINFO_CODESET gt_LC_MESSAGES @@ -3,7 +3,7 @@ scriptversion=2013-05-30.07; # UTC -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -251,6 +251,41 @@ hp) exit 1 ;; +sgi) + if test "$libtool" = yes; then + "$@" "-Wp,-MDupdate,$tmpdepfile" + else + "$@" -MDupdate "$tmpdepfile" + fi + stat=$? + if test $stat -ne 0; then + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + + if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files + echo "$object : \\" > "$depfile" + # Clip off the initial element (the dependent). Don't try to be + # clever and replace this with sed code, as IRIX sed won't handle + # lines with more than a fixed number of characters (4096 in + # IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines; + # the IRIX cc adds comments like '#:fec' to the end of the + # dependency line. + tr ' ' "$nl" < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' \ + | tr "$nl" ' ' >> "$depfile" + echo >> "$depfile" + # The second pass generates a dummy entry for each header file. + tr ' ' "$nl" < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \ + >> "$depfile" + else + make_dummy_depfile + fi + rm -f "$tmpdepfile" + ;; + xlc) # This case exists only to let depend.m4 do its work. It works by # looking at the text of this script. This case will never be run, @@ -1,5 +1,5 @@ /* dfa.c - deterministic extended regexp routines for GNU - Copyright (C) 1988, 1998, 2000, 2002, 2004-2005, 2007-2014 Free Software + Copyright (C) 1988, 1998, 2000, 2002, 2004-2005, 2007-2015 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify @@ -1,5 +1,5 @@ /* dfa.h - declarations for GNU deterministic regexp compiler - Copyright (C) 1988, 1998, 2007, 2009-2014 Free Software Foundation, Inc. + Copyright (C) 1988, 1998, 2007, 2009-2015 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by diff --git a/doc/ChangeLog b/doc/ChangeLog index ba473168..5d8c4a5e 100644 --- a/doc/ChangeLog +++ b/doc/ChangeLog @@ -1,3 +1,66 @@ +2015-02-08 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + +2015-02-06 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + +2015-02-04 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + * gawktexi.in: Update various version-related bits of info. + +2015-02-02 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + +2015-02-01 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: POSIX requirement that function parameters cannot + have the same name as a function is now --posix. + Restore indirectcall example. + + More O'Reilly fixes. + +2015-01-30 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: Document POSIX requirement that function parameters + cannot have the same name as a function. Fix indirectcall example. + +2015-01-27 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + And still more. Also, fix @code --> @command in a number of places. + +2015-01-26 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + +2015-01-25 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: Fix a bad URL. And another one. + More O'Reilly fixes. + +2015-01-23 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + (Glossary): Many new entries from Antonio Giovanni Columbo. + +2015-01-21 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + Remove obsolete start/end of range indexing comments. + +2015-01-20 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: O'Reilly fixes. + +2015-01-19 Arnold D. Robbins <arnold@skeeve.com> + + * gawkinet.texi: Fix capitalization in document title. + * gawktexi.in: Here we go again: Starting on more O'Reilly fixes. + 2014-12-27 Arnold D. Robbins <arnold@skeeve.com> * gawktexi.in: Add info that nonfatal I/O works with stdout and diff --git a/doc/Makefile.in b/doc/Makefile.in index a17000bc..68aacf48 100644 --- a/doc/Makefile.in +++ b/doc/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -38,7 +38,17 @@ # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA # VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -102,8 +112,6 @@ POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ subdir = doc -DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ - $(top_srcdir)/mkinstalldirs texinfo.tex ChangeLog ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/codeset.m4 $(top_srcdir)/m4/gettext.m4 \ @@ -118,6 +126,7 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/ulonglong.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs CONFIG_HEADER = $(top_builddir)/config.h CONFIG_CLEAN_FILES = @@ -213,6 +222,8 @@ man1dir = $(mandir)/man1 NROFF = nroff MANS = $(man_MANS) am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +am__DIST_COMMON = $(srcdir)/Makefile.in $(top_srcdir)/mkinstalldirs \ + ChangeLog texinfo.tex DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) ACLOCAL = @ACLOCAL@ AMTAR = @AMTAR@ @@ -394,7 +405,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu doc/Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu doc/Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -856,6 +866,8 @@ uninstall-man: uninstall-man1 uninstall-info-am uninstall-man uninstall-man1 \ uninstall-pdf-am uninstall-ps-am +.PRECIOUS: Makefile + # Uncomment the following definition of AWKCARD if your troff can produce # Postscript but still has troubles with macros from 'colors'. As this diff --git a/doc/gawk.info b/doc/gawk.info index 08ec4452..d83370e8 100644 --- a/doc/gawk.info +++ b/doc/gawk.info @@ -9,7 +9,7 @@ START-INFO-DIR-ENTRY * awk: (gawk)Invoking gawk. Text scanning and processing. END-INFO-DIR-ENTRY - Copyright (C) 1989, 1991, 1992, 1993, 1996-2005, 2007, 2009-2014 + Copyright (C) 1989, 1991, 1992, 1993, 1996-2005, 2007, 2009-2015 Free Software Foundation, Inc. @@ -37,7 +37,7 @@ General Introduction This file documents `awk', a program that you can use to select particular records in a file and perform operations upon them. - Copyright (C) 1989, 1991, 1992, 1993, 1996-2005, 2007, 2009-2014 + Copyright (C) 1989, 1991, 1992, 1993, 1996-2005, 2007, 2009-2015 Free Software Foundation, Inc. @@ -749,10 +749,10 @@ and associative arrays. Those looking for something new can try out The programs in this book make clear that an AWK program is typically much smaller and faster to develop than a counterpart written -in C. Consequently, there is often a payoff to prototype an algorithm -or design in AWK to get it running quickly and expose problems early. -Often, the interpreted performance is adequate and the AWK prototype -becomes the product. +in C. Consequently, there is often a payoff to prototyping an +algorithm or design in AWK to get it running quickly and expose +problems early. Often, the interpreted performance is adequate and the +AWK prototype becomes the product. The new `pgawk' (profiling `gawk'), produces program execution counts. I recently experimented with an algorithm that for n lines of @@ -776,16 +776,16 @@ Foreword to the Fourth Edition ****************************** Some things don't change. Thirteen years ago I wrote: "If you use AWK -or want to learn how, then read this book." True then and still true +or want to learn how, then read this book." True then, and still true today. - Learning to use a programming language is more than mastering the -syntax. One needs to acquire an understanding of how to use the + Learning to use a programming language is about more than mastering +the syntax. One needs to acquire an understanding of how to use the features of the language to solve practical programming problems. A focus of this book is many examples that show how to use AWK. Some things do change. Our computers are much faster and have more -memory. Consequently, speed and storage inefficiencies of a high level +memory. Consequently, speed and storage inefficiencies of a high-level language matter less. Prototyping in AWK and then rewriting in C for performance reasons happens less, because more often the prototype is fast enough. @@ -794,9 +794,9 @@ fast enough. C++. With `gawk' 4.1 and later, you do not have to choose between writing your program in AWK or in C/C++. You can write most of your program in AWK and the aspects that require C/C++ capabilities can be -written in C/C++ and then the pieces glued together when the `gawk' +written in C/C++, and then the pieces glued together when the `gawk' module loads the C/C++ module as a dynamic plug-in. *note Dynamic -Extensions::, has all the details, and as expected, many examples to +Extensions::, has all the details, and, as expected, many examples to help you learn the ins and outs. I enjoy programming in AWK and had fun (re)reading this book. I @@ -835,7 +835,7 @@ So most of the time, we don't distinguish between `gawk' and other * Validate data - * Produce indexes and perform other document preparation tasks + * Produce indexes and perform other document-preparation tasks * Experiment with algorithms that you can adapt later to other computer languages @@ -927,7 +927,7 @@ advice from Richard Stallman. John Woods contributed parts of the code as well. In 1988 and 1989, David Trueman, with help from me, thoroughly reworked `gawk' for compatibility with the newer `awk'. Circa 1994, I became the primary maintainer. Current development -focuses on bug fixes, performance improvements, standards compliance +focuses on bug fixes, performance improvements, standards compliance, and, occasionally, new features. In May 1997, Ju"rgen Kahrs felt the need for network access from @@ -939,10 +939,10 @@ the `gawk' distribution). His code finally became part of the main John Haque rewrote the `gawk' internals, in the process providing an `awk'-level debugger. This version became available as `gawk' version -4.0, in 2011. +4.0 in 2011. - *Note Contributors::, for a full list of those who made important -contributions to `gawk'. + *Note Contributors::, for a full list of those who have made +important contributions to `gawk'. File: gawk.info, Node: Names, Next: This Manual, Prev: History, Up: Preface @@ -955,7 +955,7 @@ provided in *note Language History::. The language described in this Info file is often referred to as "new `awk'." By analogy, the original version of `awk' is referred to as "old `awk'." - Today, on most systems, when you run the `awk' utility, you get some + Today, on most systems, when you run the `awk' utility you get some version of new `awk'.(1) If your system's standard `awk' is the old one, you will see something like this if you try the test program: @@ -1015,9 +1015,9 @@ in *note Sample Programs::, should be of interest. This Info file is split into several parts, as follows: - * Part I describes the `awk' language and `gawk' program in detail. - It starts with the basics, and continues through all of the - features of `awk'. It contains the following chapters: + * Part I describes the `awk' language and the `gawk' program in + detail. It starts with the basics, and continues through all of + the features of `awk'. It contains the following chapters: - *note Getting Started::, provides the essentials you need to know to begin using `awk'. @@ -1048,9 +1048,10 @@ in *note Sample Programs::, should be of interest. `gawk' use. - *note Arrays::, covers `awk''s one-and-only data structure: - associative arrays. Deleting array elements and whole arrays - is also described, as well as sorting arrays in `gawk'. It - also describes how `gawk' provides arrays of arrays. + the associative array. Deleting array elements and whole + arrays is described, as well as sorting arrays in `gawk'. + The major node also describes how `gawk' provides arrays of + arrays. - *note Functions::, describes the built-in functions `awk' and `gawk' provide, as well as how to define your own functions. @@ -1058,14 +1059,13 @@ in *note Sample Programs::, should be of interest. indirectly. * Part II shows how to use `awk' and `gawk' for problem solving. - There is lots of code here for you to read and learn from. It - contains the following chapters: + There is lots of code here for you to read and learn from. This + part contains the following chapters: - - *note Library Functions::, which provides a number of - functions meant to be used from main `awk' programs. + - *note Library Functions::, provides a number of functions + meant to be used from main `awk' programs. - - *note Sample Programs::, which provides many sample `awk' - programs. + - *note Sample Programs::, provides many sample `awk' programs. Reading these two chapters allows you to see `awk' solving real problems. @@ -1097,7 +1097,7 @@ in *note Sample Programs::, should be of interest. It contains the following appendices: - *note Language History::, describes how the `awk' language - has evolved since its first release to present. It also + has evolved since its first release to the present. It also describes how `gawk' has acquired features over time. - *note Installation::, describes how to get `gawk', how to @@ -1114,7 +1114,7 @@ in *note Sample Programs::, should be of interest. material for those who are completely unfamiliar with computer programming. - The *note Glossary::, defines most, if not all of, the + The *note Glossary::, defines most, if not all, of the significant terms used throughout the Info file. If you find terms that you aren't familiar with, try looking them up here. @@ -1143,8 +1143,8 @@ node briefly documents the typographical conventions used in Texinfo. common shell primary and secondary prompts, `$' and `>'. Input that you type is shown `like this'. Output from the command is preceded by the glyph "-|". This typically represents the command's standard -output. Error messages, and other output on the command's standard -error, are preceded by the glyph "error-->". For example: +output. Error messages and other output on the command's standard +error are preceded by the glyph "error-->". For example: $ echo hi on stdout -| hi on stdout @@ -1156,7 +1156,7 @@ particular, there are special characters called "control characters." These are characters that you type by holding down both the `CONTROL' key and another key, at the same time. For example, a `Ctrl-d' is typed by first pressing and holding the `CONTROL' key, next pressing the `d' -key and finally releasing both keys. +key, and finally releasing both keys. For the sake of brevity, throughout this Info file, we refer to Brian Kernighan's version of `awk' as "BWK `awk'." (*Note Other @@ -1172,7 +1172,7 @@ Dark Corners Until the POSIX standard (and `GAWK: Effective AWK Programming'), many features of `awk' were either poorly documented or not documented at all. Descriptions of such features (often called "dark corners") -are noted in this Info file with "(d.c.)". They also appear in the +are noted in this Info file with "(d.c.)." They also appear in the index under the heading "dark corner." But, as noted by the opening quote, any coverage of dark corners is @@ -1195,8 +1195,8 @@ editor. GNU Emacs is the most widely used version of Emacs today. The GNU(1) Project is an ongoing effort on the part of the Free Software Foundation to create a complete, freely distributable, -POSIX-compliant computing environment. The FSF uses the "GNU General -Public License" (GPL) to ensure that their software's source code is +POSIX-compliant computing environment. The FSF uses the GNU General +Public License (GPL) to ensure that its software's source code is always available to the end user. A copy of the GPL is included for your reference (*note Copying::). The GPL applies to the C language source code for `gawk'. To find out more about the FSF and the GNU @@ -1224,26 +1224,26 @@ original, "old" version of `awk'. I started working with that version in the fall of 1988. As work on it progressed, the FSF published several preliminary versions (numbered -0.X). In 1996, Edition 1.0 was released with `gawk' 3.0.0. The FSF +0.X). In 1996, edition 1.0 was released with `gawk' 3.0.0. The FSF published the first two editions under the title `The GNU Awk User's Guide'. This edition maintains the basic structure of the previous editions. For FSF edition 4.0, the content was thoroughly reviewed and updated. All references to `gawk' versions prior to 4.0 were removed. Of -significant note for that edition was *note Debugger::. +significant note for that edition was the addition of *note Debugger::. For FSF edition 4.1, the content has been reorganized into parts, and the major new additions are *note Arbitrary Precision Arithmetic::, and *note Dynamic Extensions::. This Info file will undoubtedly continue to evolve. If you find an -error in this Info file, please report it! *Note Bugs::, for +error in the Info file, please report it! *Note Bugs::, for information on submitting problem reports electronically. ---------- Footnotes ---------- - (1) GNU stands for "GNU's not Unix." + (1) GNU stands for "GNU's Not Unix." (2) The terminology "GNU/Linux" is explained in the *note Glossary::. @@ -1287,7 +1287,7 @@ acknowledgments: this manual. Jay Fenlason contributed many ideas and sample programs. Richard Mlynarik and Robert Chassell gave helpful comments on drafts of this manual. The paper `A Supplemental - Document for `awk'' by John W. Pierce of the Chemistry Department + Document for AWK' by John W. Pierce of the Chemistry Department at UC San Diego, pinpointed several issues relevant both to `awk' implementation and to this manual, that would otherwise have escaped us. @@ -1300,7 +1300,7 @@ GNU Project. acknowledgements: The following people (in alphabetical order) provided helpful - comments on various versions of this book, Rick Adams, Dr. Nelson + comments on various versions of this book: Rick Adams, Dr. Nelson H.F. Beebe, Karl Berry, Dr. Michael Brennan, Rich Burridge, Claire Cloutier, Diane Close, Scott Deifik, Christopher ("Topher") Eliot, Jeffrey Friedl, Dr. Darrel Hankerson, Michal Jaegermann, Dr. @@ -1309,7 +1309,7 @@ acknowledgements: Robert J. Chassell provided much valuable advice on the use of Texinfo. He also deserves special thanks for convincing me _not_ - to title this Info file `How To Gawk Politely'. Karl Berry helped + to title this Info file `How to Gawk Politely'. Karl Berry helped significantly with the TeX part of Texinfo. I would like to thank Marshall and Elaine Hartholz of Seattle and @@ -1349,18 +1349,18 @@ of people. *Note Contributors::, for the full list. Thanks to Michael Brennan for the Forewords. Thanks to Patrice Dumas for the new `makeinfo' program. Thanks to -Karl Berry who continues to work to keep the Texinfo markup language +Karl Berry, who continues to work to keep the Texinfo markup language sane. Robert P.J. Day, Michael Brennan, and Brian Kernighan kindly acted as reviewers for the 2015 edition of this Info file. Their feedback helped improve the final work. - I would like to thank Brian Kernighan for invaluable assistance -during the testing and debugging of `gawk', and for ongoing help and -advice in clarifying numerous points about the language. We could not -have done nearly as good a job on either `gawk' or its documentation -without his help. + I would also like to thank Brian Kernighan for his invaluable +assistance during the testing and debugging of `gawk', and for his +ongoing help and advice in clarifying numerous points about the +language. We could not have done nearly as good a job on either `gawk' +or its documentation without his help. Brian is in a class by himself as a programmer and technical author. I have to thank him (yet again) for his ongoing friendship and for @@ -1403,10 +1403,10 @@ contain "function definitions", an advanced feature that we will ignore for now; *note User-defined::). Each rule specifies one pattern to search for and one action to perform upon finding the pattern. - Syntactically, a rule consists of a pattern followed by an action. -The action is enclosed in braces to separate it from the pattern. -Newlines usually separate rules. Therefore, an `awk' program looks -like this: + Syntactically, a rule consists of a "pattern" followed by an +"action". The action is enclosed in braces to separate it from the +pattern. Newlines usually separate rules. Therefore, an `awk' program +looks like this: PATTERN { ACTION } PATTERN { ACTION } @@ -1474,7 +1474,7 @@ program as the first argument of the `awk' command, like this: awk 'PROGRAM' INPUT-FILE1 INPUT-FILE2 ... -where PROGRAM consists of a series of PATTERNS and ACTIONS, as +where PROGRAM consists of a series of patterns and actions, as described earlier. This command format instructs the "shell", or command interpreter, @@ -1489,8 +1489,8 @@ programs from shell scripts, because it avoids the need for a separate file for the `awk' program. A self-contained shell script is more reliable because there are no other files to misplace. - Later in this chapter, *note Very Simple::, presents several short, -self-contained programs. + Later in this chapter, in *note Very Simple::, we'll see examples of +several short, self-contained programs. File: gawk.info, Node: Read Terminal, Next: Long, Prev: One-shot, Up: Running gawk @@ -1505,7 +1505,7 @@ following command line: `awk' applies the PROGRAM to the "standard input", which usually means whatever you type on the keyboard. This continues until you indicate -end-of-file by typing `Ctrl-d'. (On other operating systems, the +end-of-file by typing `Ctrl-d'. (On non-POSIX operating systems, the end-of-file character may be different. For example, on OS/2, it is `Ctrl-z'.) @@ -1580,10 +1580,9 @@ that are provided on the `awk' command line. (Also, placing the program in a file allows us to use a literal single quote in the program text, instead of the magic `\47'.) - If you want to clearly identify your `awk' program files as such, -you can add the extension `.awk' to the file name. This doesn't affect -the execution of the `awk' program but it does make "housekeeping" -easier. + If you want to clearly identify an `awk' program file as such, you +can add the extension `.awk' to the file name. This doesn't affect the +execution of the `awk' program but it does make "housekeeping" easier. File: gawk.info, Node: Executable Scripts, Next: Comments, Prev: Long, Up: Running gawk @@ -1712,7 +1711,7 @@ at a later time. File: gawk.info, Node: Quoting, Prev: Comments, Up: Running gawk -1.1.6 Shell-Quoting Issues +1.1.6 Shell Quoting Issues -------------------------- * Menu: @@ -1807,7 +1806,7 @@ shell quoting tricks, like this: -| Here is a single quote <'> This program consists of three concatenated quoted strings. The first -and the third are single quoted, the second is double quoted. +and the third are single-quoted, and the second is double-quoted. This can be "simplified" to: @@ -1834,8 +1833,7 @@ like so: $ awk 'BEGIN { print "Here is a double quote <\42>" }' -| Here is a double quote <"> -This works nicely, except that you should comment clearly what the -escapes mean. +This works nicely, but you should comment clearly what the escapes mean. A fourth option is to use command-line variable assignment, like this: @@ -1844,11 +1842,11 @@ this: -| Here is a single quote <'> (Here, the two string constants and the value of `sq' are -concatenated into a single string which is printed by `print'.) +concatenated into a single string that is printed by `print'.) If you really need both single and double quotes in your `awk' program, it is probably best to move it into a separate file, where the -shell won't be part of the picture, and you can say what you mean. +shell won't be part of the picture and you can say what you mean. File: gawk.info, Node: DOS Quoting, Up: Quoting @@ -1906,7 +1904,7 @@ of green crates shipped, the number of red boxes shipped, the number of orange bags shipped, and the number of blue packages shipped, respectively. There are 16 entries, covering the 12 months of last year and the first four months of the current year. An empty line separates -the data for the two years. +the data for the two years: Jan 13 25 15 115 Feb 15 32 24 226 @@ -1938,7 +1936,7 @@ File: gawk.info, Node: Very Simple, Next: Two Rules, Prev: Sample Data Files, The following command runs a simple `awk' program that searches the input file `mail-list' for the character string `li' (a grouping of characters is usually called a "string"; the term "string" is based on -similar usage in English, such as "a string of pearls," or "a string of +similar usage in English, such as "a string of pearls" or "a string of cars in a train"): awk '/li/ { print $0 }' mail-list @@ -1974,24 +1972,25 @@ prints all lines matching the pattern `li'. By comparison, omitting the `print' statement but retaining the braces makes an empty action that does nothing (i.e., no lines are printed). - Many practical `awk' programs are just a line or two. Following is a -collection of useful, short programs to get you started. Some of these -programs contain constructs that haven't been covered yet. (The -description of the program will give you a good idea of what is going -on, but you'll need to read the rest of the Info file to become an -`awk' expert!) Most of the examples use a data file named `data'. -This is just a placeholder; if you use these programs yourself, -substitute your own file names for `data'. For future reference, note -that there is often more than one way to do things in `awk'. At some -point, you may want to look back at these examples and see if you can -come up with different ways to do the same things shown here: + Many practical `awk' programs are just a line or two long. +Following is a collection of useful, short programs to get you started. +Some of these programs contain constructs that haven't been covered +yet. (The description of the program will give you a good idea of what +is going on, but you'll need to read the rest of the Info file to +become an `awk' expert!) Most of the examples use a data file named +`data'. This is just a placeholder; if you use these programs +yourself, substitute your own file names for `data'. For future +reference, note that there is often more than one way to do things in +`awk'. At some point, you may want to look back at these examples and +see if you can come up with different ways to do the same things shown +here: * Print every line that is longer than 80 characters: awk 'length($0) > 80' data - The sole rule has a relational expression as its pattern and it - has no action--so it uses the default action, printing the record. + The sole rule has a relational expression as its pattern and has no + action--so it uses the default action, printing the record. * Print the length of the longest input line: @@ -2046,8 +2045,8 @@ come up with different ways to do the same things shown here: awk 'NR % 2 == 0' data - If you use the expression `NR % 2 == 1' instead, the program would - print the odd-numbered lines. + If you used the expression `NR % 2 == 1' instead, the program + would print the odd-numbered lines. File: gawk.info, Node: Two Rules, Next: More Complex, Prev: Very Simple, Up: Getting Started @@ -2280,9 +2279,10 @@ built-in functions for working with timestamps, performing bit manipulation, for runtime string translation (internationalization), determining the type of a variable, and array sorting. - As we develop our presentation of the `awk' language, we introduce -most of the variables and many of the functions. They are described -systematically in *note Built-in Variables::, and in *note Built-in::. + As we develop our presentation of the `awk' language, we will +introduce most of the variables and many of the functions. They are +described systematically in *note Built-in Variables::, and in *note +Built-in::. File: gawk.info, Node: When, Next: Intro Summary, Prev: Other Features, Up: Getting Started @@ -2347,7 +2347,7 @@ File: gawk.info, Node: Intro Summary, Prev: When, Up: Getting Started * You may use backslash continuation to continue a source line. Lines are automatically continued after a comma, open brace, - question mark, colon, `||', `&&', `do' and `else'. + question mark, colon, `||', `&&', `do', and `else'. File: gawk.info, Node: Invoking Gawk, Next: Regexp, Prev: Getting Started, Up: Top @@ -2414,8 +2414,8 @@ File: gawk.info, Node: Options, Next: Other Arguments, Prev: Command Line, U Options begin with a dash and consist of a single character. GNU-style long options consist of two dashes and a keyword. The keyword can be abbreviated, as long as the abbreviation allows the option to be -uniquely identified. If the option takes an argument, then the keyword -is either immediately followed by an equals sign (`=') and the +uniquely identified. If the option takes an argument, either the +keyword is immediately followed by an equals sign (`=') and the argument's value, or the keyword and the argument's value are separated by whitespace. If a particular option with a value is given more than once, it is the last value that counts. @@ -2430,10 +2430,10 @@ The following list describes options mandated by the POSIX standard: `-f SOURCE-FILE' `--file SOURCE-FILE' - Read `awk' program source from SOURCE-FILE instead of in the first - nonoption argument. This option may be given multiple times; the - `awk' program consists of the concatenation of the contents of - each specified SOURCE-FILE. + Read the `awk' program source from SOURCE-FILE instead of in the + first nonoption argument. This option may be given multiple + times; the `awk' program consists of the concatenation of the + contents of each specified SOURCE-FILE. `-v VAR=VAL' `--assign VAR=VAL' @@ -2474,7 +2474,7 @@ The following list describes options mandated by the POSIX standard: `-b' `--characters-as-bytes' Cause `gawk' to treat all input data as single-byte characters. - In addition, all output written with `print' or `printf' are + In addition, all output written with `print' or `printf' is treated as single-byte characters. Normally, `gawk' follows the POSIX standard and attempts to process @@ -2482,7 +2482,7 @@ The following list describes options mandated by the POSIX standard: This can often involve converting multibyte characters into wide characters (internally), and can lead to problems or confusion if the input data does not contain valid multibyte characters. This - option is an easy way to tell `gawk': "hands off my data!". + option is an easy way to tell `gawk', "Hands off my data!" `-c' `--traditional' @@ -2517,7 +2517,7 @@ The following list describes options mandated by the POSIX standard: default, the debugger reads commands interactively from the keyboard (standard input). The optional FILE argument allows you to specify a file with a list of commands for the debugger to - execute non-interactively. No space is allowed between the `-D' + execute noninteractively. No space is allowed between the `-D' and FILE, if FILE is supplied. `-e' PROGRAM-TEXT @@ -2552,23 +2552,23 @@ The following list describes options mandated by the POSIX standard: `-g' `--gen-pot' - Analyze the source program and generate a GNU `gettext' Portable - Object Template file on standard output for all string constants + Analyze the source program and generate a GNU `gettext' portable + object template file on standard output for all string constants that have been marked for translation. *Note Internationalization::, for information about this option. `-h' `--help' - Print a "usage" message summarizing the short and long style + Print a "usage" message summarizing the short- and long-style options that `gawk' accepts and then exit. `-i' SOURCE-FILE `--include' SOURCE-FILE Read an `awk' source library from SOURCE-FILE. This option is completely equivalent to using the `@include' directive inside - your program. This option is very similar to the `-f' option, but - there are two important differences. First, when `-i' is used, - the program source is not loaded if it has been previously loaded, + your program. It is very similar to the `-f' option, but there + are two important differences. First, when `-i' is used, the + program source is not loaded if it has been previously loaded, whereas with `-f', `gawk' always loads the file. Second, because this option is intended to be used with code libraries, `gawk' does not recognize such files as constituting main program input. @@ -2630,7 +2630,7 @@ The following list describes options mandated by the POSIX standard: `-o'[FILE] `--pretty-print'[`='FILE] - Enable pretty-printing of `awk' programs. By default, output + Enable pretty-printing of `awk' programs. By default, the output program is created in a file named `awkprof.out' (*note Profiling::). The optional FILE argument allows you to specify a different file name for the output. No space is allowed between @@ -2736,7 +2736,7 @@ input as a source of data.) Because it is clumsy using the standard `awk' mechanisms to mix source file and command-line `awk' programs, `gawk' provides the `-e' -option. This does not require you to pre-empt the standard input for +option. This does not require you to preempt the standard input for your source code; it allows you to easily mix command-line and library source code (*note AWKPATH Variable::). As with `-f', the `-e' and `-i' options may also be used multiple times on the command line. @@ -2895,7 +2895,7 @@ implementations, you must supply a precise pathname for each program file, unless the file is in the current directory. But with `gawk', if the file name supplied to the `-f' or `-i' options does not contain a directory separator `/', then `gawk' searches a list of directories -(called the "search path"), one by one, looking for a file with the +(called the "search path") one by one, looking for a file with the specified name. The search path is a string consisting of directory names separated by @@ -2928,9 +2928,9 @@ or by placing two colons next to each other [`::'].) Different past versions of `gawk' would also look explicitly in the current directory, either before or after the path search. As - of version 4.1.2, this no longer happens, and if you wish to look - in the current directory, you must include `.' either as a separate - entry, or as a null entry in the search path. + of version 4.1.2, this no longer happens; if you wish to look in + the current directory, you must include `.' either as a separate + entry or as a null entry in the search path. The default value for `AWKPATH' is `.:/usr/local/share/awk'.(2) Since `.' is included at the beginning, `gawk' searches first in the @@ -3042,7 +3042,7 @@ change. The variables are: If this variable exists, `gawk' includes the file name and line number within the `gawk' source code from which warning and/or fatal messages are generated. Its purpose is to help isolate the - source of a message, as there are multiple places which produce the + source of a message, as there are multiple places that produce the same warning or error message. `GAWK_NO_DFA' @@ -3058,16 +3058,16 @@ change. The variables are: evaluation stack, when needed. `INT_CHAIN_MAX' - The intended maximum number of items `gawk' will maintain on a - hash chain for managing arrays indexed by integers. + This specifies intended maximum number of items `gawk' will + maintain on a hash chain for managing arrays indexed by integers. `STR_CHAIN_MAX' - The intended maximum number of items `gawk' will maintain on a - hash chain for managing arrays indexed by strings. + This specifies intended maximum number of items `gawk' will + maintain on a hash chain for managing arrays indexed by strings. `TIDYMEM' If this variable exists, `gawk' uses the `mtrace()' library calls - from GNU LIBC to help track down possible memory leaks. + from the GNU C library to help track down possible memory leaks. File: gawk.info, Node: Exit Status, Next: Include Files, Prev: Environment Variables, Up: Invoking Gawk @@ -3099,11 +3099,11 @@ This minor node describes a feature that is specific to `gawk'. files. This gives you the ability to split large `awk' source files into smaller, more manageable pieces, and also lets you reuse common `awk' code from various `awk' scripts. In other words, you can group -together `awk' functions, used to carry out specific tasks, into -external files. These files can be used just like function libraries, -using the `@include' keyword in conjunction with the `AWKPATH' -environment variable. Note that source files may also be included -using the `-i' option. +together `awk' functions used to carry out specific tasks into external +files. These files can be used just like function libraries, using the +`@include' keyword in conjunction with the `AWKPATH' environment +variable. Note that source files may also be included using the `-i' +option. Let's see an example. We'll start with two (trivial) `awk' scripts, namely `test1' and `test2'. Here is the `test1' script: @@ -3165,11 +3165,11 @@ Variable::) apply to `@include' also. This is very helpful in constructing `gawk' function libraries. If you have a large script with useful, general-purpose `awk' functions, you can break it down into library files and put those files in a -special directory. You can then include those "libraries," using -either the full pathnames of the files, or by setting the `AWKPATH' +special directory. You can then include those "libraries," either by +using the full pathnames of the files, or by setting the `AWKPATH' environment variable accordingly and then using `@include' with just -the file part of the full pathname. Of course, you can have more than -one directory to keep library files; the more complex the working +the file part of the full pathname. Of course, you can keep library +files in more than one directory; the more complex the working environment is, the more directories you may need to organize the files to be included. @@ -3181,8 +3181,8 @@ particular, `@include' is very useful for writing CGI scripts to be run from web pages. As mentioned in *note AWKPATH Variable::, the current directory is -always searched first for source files, before searching in `AWKPATH', -and this also applies to files named with `@include'. +always searched first for source files, before searching in `AWKPATH'; +this also applies to files named with `@include'. File: gawk.info, Node: Loading Shared Libraries, Next: Obsolete, Prev: Include Files, Up: Invoking Gawk @@ -3227,8 +3227,8 @@ File: gawk.info, Node: Obsolete, Next: Undocumented, Prev: Loading Shared Lib ==================================== This minor node describes features and/or command-line options from -previous releases of `gawk' that are either not available in the -current version or that are still supported but deprecated (meaning that +previous releases of `gawk' that either are not available in the +current version or are still supported but deprecated (meaning that they will _not_ be in the next release). The process-related special files `/dev/pid', `/dev/ppid', @@ -3256,7 +3256,7 @@ File: gawk.info, Node: Invoking Summary, Prev: Undocumented, Up: Invoking Gaw run `awk'. * The three standard options for all versions of `awk' are `-f', - `-F' and `-v'. `gawk' supplies these and many others, as well as + `-F', and `-v'. `gawk' supplies these and many others, as well as corresponding GNU-style long options. * Nonoption command-line arguments are usually treated as file names, @@ -3286,7 +3286,7 @@ File: gawk.info, Node: Invoking Summary, Prev: Undocumented, Up: Invoking Gaw * `gawk' allows you to load additional functions written in C or C++ using the `@load' statement and/or the `-l' option. (This - advanced feature is described later on in *note Dynamic + advanced feature is described later, in *note Dynamic Extensions::.) @@ -3435,7 +3435,7 @@ sequences apply to both string constants and regexp constants: Horizontal TAB, `Ctrl-i', ASCII code 9 (HT). `\v' - Vertical tab, `Ctrl-k', ASCII code 11 (VT). + Vertical TAB, `Ctrl-k', ASCII code 11 (VT). `\NNN' The octal value NNN, where NNN stands for 1 to 3 digits between @@ -3485,7 +3485,7 @@ normally be a regexp operator. For example, `/a\+b/' matches the three characters `a+b'. For complete portability, do not use a backslash before any -character not shown in the previous list and that is not an operator. +character not shown in the previous list or that is not an operator. Backslash Before Regular Characters @@ -3547,7 +3547,7 @@ and converted into corresponding real characters as the very first step in processing regexps. Here is a list of metacharacters. All characters that are not escape -sequences and that are not listed in the following stand for themselves: +sequences and that are not listed here stand for themselves: `\' This suppresses the special meaning of a character when matching. @@ -3630,7 +3630,7 @@ sequences and that are not listed in the following stand for themselves: There are two subtle points to understand about how `*' works. First, the `*' applies only to the single preceding regular expression component (e.g., in `ph*', it applies just to the `h'). - To cause `*' to apply to a larger sub-expression, use parentheses: + To cause `*' to apply to a larger subexpression, use parentheses: `(ph)*' matches `ph', `phph', `phphph', and so on. Second, `*' finds as many repetitions as possible. If the text to @@ -3661,10 +3661,10 @@ sequences and that are not listed in the following stand for themselves: Matches `whhhy', but not `why' or `whhhhy'. `wh{3,5}y' - Matches `whhhy', `whhhhy', or `whhhhhy', only. + Matches `whhhy', `whhhhy', or `whhhhhy' only. `wh{2,}y' - Matches `whhy' or `whhhy', and so on. + Matches `whhy', `whhhy', and so on. Interval expressions were not traditionally available in `awk'. They were added as part of the POSIX standard to make `awk' and @@ -3766,7 +3766,7 @@ Class Meaning `[:print:]' Printable characters (characters that are not control characters) `[:punct:]' Punctuation characters (characters that are not letters, - digits control characters, or space characters) + digits, control characters, or space characters) `[:space:]' Space characters (such as space, TAB, and formfeed, to name a few) `[:upper:]' Uppercase alphabetic characters @@ -3804,8 +3804,9 @@ Collating symbols Equivalence classes Locale-specific names for a list of characters that are equal. The name is enclosed between `[=' and `=]'. For example, the name `e' - might be used to represent all of "e," "e`," and "e'." In this - case, `[[=e=]]' is a regexp that matches any of `e', `e'', or `e`'. + might be used to represent all of "e," "e^," "e`," and "e'." In + this case, `[[=e=]]' is a regexp that matches any of `e', `e^', + `e'', or `e`'. These features are very valuable in non-English-speaking locales. @@ -3827,7 +3828,7 @@ Consider the following: This example uses the `sub()' function to make a change to the input record. (`sub()' replaces the first instance of any text matched by the first argument with the string provided as the second argument; -*note String Functions::). Here, the regexp `/a+/' indicates "one or +*note String Functions::.) Here, the regexp `/a+/' indicates "one or more `a' characters," and the replacement text is `<A>'. The input contains four `a' characters. `awk' (and POSIX) regular @@ -3864,15 +3865,16 @@ regexp": This sets `digits_regexp' to a regexp that describes one or more digits, and tests whether the input record matches this regexp. - NOTE: When using the `~' and `!~' operators, there is a difference - between a regexp constant enclosed in slashes and a string - constant enclosed in double quotes. If you are going to use a - string constant, you have to understand that the string is, in - essence, scanned _twice_: the first time when `awk' reads your + NOTE: When using the `~' and `!~' operators, be aware that there + is a difference between a regexp constant enclosed in slashes and + a string constant enclosed in double quotes. If you are going to + use a string constant, you have to understand that the string is, + in essence, scanned _twice_: the first time when `awk' reads your program, and the second time when it goes to match the string on the lefthand side of the operator with the pattern on the right. This is true of any string-valued expression (such as - `digits_regexp', shown previously), not just string constants. + `digits_regexp', shown in the previous example), not just string + constants. What difference does it make if the string is scanned twice? The answer has to do with escape sequences, and particularly with @@ -3969,7 +3971,7 @@ letters, digits, or underscores (`_'): `\B' Matches the empty string that occurs between two word-constituent - characters. For example, `/\Brat\B/' matches `crate' but it does + characters. For example, `/\Brat\B/' matches `crate', but it does not match `dirty rat'. `\B' is essentially the opposite of `\y'. There are two other operators that work on buffers. In Emacs, a @@ -3978,10 +3980,10 @@ letters, digits, or underscores (`_'): operators are: `\`' - Matches the empty string at the beginning of a buffer (string). + Matches the empty string at the beginning of a buffer (string) `\'' - Matches the empty string at the end of a buffer (string). + Matches the empty string at the end of a buffer (string) Because `^' and `$' always work in terms of the beginning and end of strings, these operators don't add any new capabilities for `awk'. @@ -4152,7 +4154,7 @@ one line. Each record is automatically split into chunks called parts of a record. On rare occasions, you may need to use the `getline' command. The -`getline' command is valuable, both because it can do explicit input +`getline' command is valuable both because it can do explicit input from any number of files, and because the files used with it do not have to be named on the `awk' command line (*note Getline::). @@ -4201,8 +4203,8 @@ File: gawk.info, Node: awk split records, Next: gawk split records, Up: Recor Records are separated by a character called the "record separator". By default, the record separator is the newline character. This is why -records are, by default, single lines. A different character can be -used for the record separator by assigning the character to the +records are, by default, single lines. To use a different character +for the record separator, simply assign that character to the predefined variable `RS'. Like any other variable, the value of `RS' can be changed in the @@ -4217,14 +4219,14 @@ BEGIN/END::). For example: awk 'BEGIN { RS = "u" } { print $0 }' mail-list -changes the value of `RS' to `u', before reading any input. This is a -string whose first character is the letter "u"; as a result, records -are separated by the letter "u." Then the input file is read, and the -second rule in the `awk' program (the action with no pattern) prints -each record. Because each `print' statement adds a newline at the end -of its output, this `awk' program copies the input with each `u' -changed to a newline. Here are the results of running the program on -`mail-list': +changes the value of `RS' to `u', before reading any input. The new +value is a string whose first character is the letter "u"; as a result, +records are separated by the letter "u". Then the input file is read, +and the second rule in the `awk' program (the action with no pattern) +prints each record. Because each `print' statement adds a newline at +the end of its output, this `awk' program copies the input with each +`u' changed to a newline. Here are the results of running the program +on `mail-list': $ awk 'BEGIN { RS = "u" } > { print $0 }' mail-list @@ -4272,11 +4274,11 @@ data file (*note Sample Data Files::), the line looks like this: Bill 555-1675 bill.drowning@hotmail.com A -It contains no `u' so there is no reason to split the record, unlike -the others which have one or more occurrences of the `u'. In fact, -this record is treated as part of the previous record; the newline -separating them in the output is the original newline in the data file, -not the one added by `awk' when it printed the record! +It contains no `u', so there is no reason to split the record, unlike +the others, which each have one or more occurrences of the `u'. In +fact, this record is treated as part of the previous record; the +newline separating them in the output is the original newline in the +data file, not the one added by `awk' when it printed the record! Another way to change the record separator is on the command line, using the variable-assignment feature (*note Other Arguments::): @@ -4342,8 +4344,8 @@ part of either record. character. However, when `RS' is a regular expression, `RT' contains the actual input text that matched the regular expression. - If the input file ended without any text that matches `RS', `gawk' -sets `RT' to the null string. + If the input file ends without any text matching `RS', `gawk' sets +`RT' to the null string. The following example illustrates both of these features. It sets `RS' equal to a regular expression that matches either a newline or a @@ -4441,12 +4443,12 @@ to these pieces of the record. You don't have to use them--you can operate on the whole record if you want--but fields are what make simple `awk' programs so powerful. - You use a dollar-sign (`$') to refer to a field in an `awk' program, + You use a dollar sign (`$') to refer to a field in an `awk' program, followed by the number of the field you want. Thus, `$1' refers to the -first field, `$2' to the second, and so on. (Unlike the Unix shells, -the field numbers are not limited to single digits. `$127' is the -127th field in the record.) For example, suppose the following is a -line of input: +first field, `$2' to the second, and so on. (Unlike in the Unix +shells, the field numbers are not limited to single digits. `$127' is +the 127th field in the record.) For example, suppose the following is +a line of input: This seems like a pretty nice example. @@ -4463,10 +4465,9 @@ as `$7', which is `example.'. If you try to reference a field beyond the last one (such as `$8' when the record has only seven fields), you get the empty string. (If used in a numeric operation, you get zero.) - The use of `$0', which looks like a reference to the "zero-th" -field, is a special case: it represents the whole input record. Use it -when you are not interested in specific fields. Here are some more -examples: + The use of `$0', which looks like a reference to the "zeroth" field, +is a special case: it represents the whole input record. Use it when +you are not interested in specific fields. Here are some more examples: $ awk '$1 ~ /li/ { print $0 }' mail-list -| Amelia 555-5553 amelia.zodiacusque@gmail.com F @@ -4514,8 +4515,8 @@ is another example of using expressions as field numbers: awk '{ print $(2*2) }' mail-list `awk' evaluates the expression `(2*2)' and uses its value as the -number of the field to print. The `*' sign represents multiplication, -so the expression `2*2' evaluates to four. The parentheses are used so +number of the field to print. The `*' represents multiplication, so +the expression `2*2' evaluates to four. The parentheses are used so that the multiplication is done before the `$' operation; they are necessary whenever there is a binary operator(1) in the field-number expression. This example, then, prints the type of relationship (the @@ -4539,7 +4540,7 @@ field number. ---------- Footnotes ---------- (1) A "binary operator", such as `*' for multiplication, is one that -takes two operands. The distinction is required, because `awk' also has +takes two operands. The distinction is required because `awk' also has unary (one-operand) and ternary (three-operand) operators. @@ -4661,7 +4662,7 @@ value of `NF' and recomputes `$0'. (d.c.) Here is an example: decremented. Finally, there are times when it is convenient to force `awk' to -rebuild the entire record, using the current value of the fields and +rebuild the entire record, using the current values of the fields and `OFS'. To do this, use the seemingly innocuous assignment: $1 = $1 # force record to be reconstituted @@ -4681,7 +4682,7 @@ built-in function that updates `$0', such as `sub()' and `gsub()' It is important to remember that `$0' is the _full_ record, exactly as it was read from the input. This includes any leading or trailing whitespace, and the exact whitespace (or other characters) that -separate the fields. +separates the fields. It is a common error to try to change the field separators in a record simply by setting `FS' and `OFS', and then expecting a plain @@ -4749,7 +4750,7 @@ attached, such as: John Q. Smith, LXIX, 29 Oak St., Walamazoo, MI 42139 -The same program would extract `*LXIX', instead of `*29*Oak*St.'. If +The same program would extract `*LXIX' instead of `*29*Oak*St.'. If you were expecting the program to print the address, you would be surprised. The moral is to choose your data layout and separator characters carefully to prevent such problems. (If the data is not in @@ -4948,11 +4949,11 @@ your field and record separators. Perhaps the most common use of a single character as the field separator occurs when processing the Unix system password file. On many Unix systems, each user has a separate entry in the system -password file, one line per user. The information in these lines is -separated by colons. The first field is the user's login name and the -second is the user's encrypted or shadow password. (A shadow password -is indicated by the presence of a single `x' in the second field.) A -password file entry might look like this: +password file, with one line per user. The information in these lines +is separated by colons. The first field is the user's login name and +the second is the user's encrypted or shadow password. (A shadow +password is indicated by the presence of a single `x' in the second +field.) A password file entry might look like this: arnold:x:2076:10:Arnold Robbins:/home/arnold:/bin/bash @@ -4980,15 +4981,14 @@ When you do this, `$1' is the same as `$0'. According to the POSIX standard, `awk' is supposed to behave as if each record is split into fields at the time it is read. In particular, this means that if you change the value of `FS' after a -record is read, the value of the fields (i.e., how they were split) +record is read, the values of the fields (i.e., how they were split) should reflect the old value of `FS', not the new one. However, many older implementations of `awk' do not work this way. Instead, they defer splitting the fields until a field is actually referenced. The fields are split using the _current_ value of `FS'! (d.c.) This behavior can be difficult to diagnose. The following -example illustrates the difference between the two methods. (The -`sed'(2) command prints just the first line of `/etc/passwd'.) +example illustrates the difference between the two methods: sed 1q /etc/passwd | awk '{ FS = ":" ; print $1 }' @@ -5001,6 +5001,8 @@ first line of the file, something like: root:x:0:0:Root:/: + (The `sed'(2) command prints just the first line of `/etc/passwd'.) + ---------- Footnotes ---------- (1) Thanks to Andrew Schorr for this tip. @@ -5154,7 +5156,7 @@ run on a system with card readers is another story!) splitting again. Use `FS = FS' to make this happen, without having to know the current value of `FS'. In order to tell which kind of field splitting is in effect, use `PROCINFO["FS"]' (*note Auto-set::). The -value is `"FS"' if regular field splitting is being used, or it is +value is `"FS"' if regular field splitting is being used, or `"FIELDWIDTHS"' if fixed-width field splitting is being used: if (PROCINFO["FS"] == "FS") @@ -5187,10 +5189,10 @@ what they are, and not by what they are not. The most notorious such case is so-called "comma-separated values" (CSV) data. Many spreadsheet programs, for example, can export their data into text files, where each record is terminated with a newline, -and fields are separated by commas. If only commas separated the data, +and fields are separated by commas. If commas only separated the data, there wouldn't be an issue. The problem comes when one of the fields contains an _embedded_ comma. In such cases, most programs embed the -field in double quotes.(1) So we might have data like this: +field in double quotes.(1) So, we might have data like this: Robbins,Arnold,"1234 A Pretty Street, NE",MyTown,MyState,12345-6789,USA @@ -5257,9 +5259,9 @@ being used. provides an elegant solution for the majority of cases, and the `gawk' developers are satisfied with that. - As written, the regexp used for `FPAT' requires that each field have -a least one character. A straightforward modification (changing -changed the first `+' to `*') allows fields to be empty: + As written, the regexp used for `FPAT' requires that each field +contain at least one character. A straightforward modification +(changing the first `+' to `*') allows fields to be empty: FPAT = "([^,]*)|(\"[^\"]+\")" @@ -5267,9 +5269,8 @@ changed the first `+' to `*') allows fields to be empty: available for splitting regular strings (*note String Functions::). To recap, `gawk' provides three independent methods to split input -records into fields. `gawk' uses whichever mechanism was last chosen -based on which of the three variables--`FS', `FIELDWIDTHS', and -`FPAT'--was last assigned to. +records into fields. The mechanism used is based on which of the three +variables--`FS', `FIELDWIDTHS', or `FPAT'--was last assigned to. ---------- Footnotes ---------- @@ -5307,7 +5308,7 @@ empty; lines that contain only whitespace do not count.) `"\n\n+"' to `RS'. This regexp matches the newline at the end of the record and one or more blank lines after the record. In addition, a regular expression always matches the longest possible sequence when -there is a choice (*note Leftmost Longest::). So the next record +there is a choice (*note Leftmost Longest::). So, the next record doesn't start until the first nonblank line that follows--no matter how many blank lines appear in a row, they are considered one record separator. @@ -5319,12 +5320,12 @@ last record, the final newline is removed from the record. In the second case, this special processing is not done. (d.c.) Now that the input is separated into records, the second step is to -separate the fields in the record. One way to do this is to divide each -of the lines into fields in the normal manner. This happens by default -as the result of a special feature. When `RS' is set to the empty -string, _and_ `FS' is set to a single character, the newline character -_always_ acts as a field separator. This is in addition to whatever -field separations result from `FS'.(1) +separate the fields in the records. One way to do this is to divide +each of the lines into fields in the normal manner. This happens by +default as the result of a special feature. When `RS' is set to the +empty string _and_ `FS' is set to a single character, the newline +character _always_ acts as a field separator. This is in addition to +whatever field separations result from `FS'.(1) The original motivation for this special exception was probably to provide useful behavior in the default case (i.e., `FS' is equal to @@ -5332,17 +5333,17 @@ provide useful behavior in the default case (i.e., `FS' is equal to newline character to separate fields, because there is no way to prevent it. However, you can work around this by using the `split()' function to break up the record manually (*note String Functions::). -If you have a single character field separator, you can work around the +If you have a single-character field separator, you can work around the special feature in a different way, by making `FS' into a regexp for that single character. For example, if the field separator is a percent character, instead of `FS = "%"', use `FS = "[%]"'. Another way to separate fields is to put each field on a separate line: to do this, just set the variable `FS' to the string `"\n"'. -(This single character separator matches a single newline.) A +(This single-character separator matches a single newline.) A practical example of a data file organized this way might be a mailing -list, where each entry is separated by blank lines. Consider a mailing -list in a file named `addresses', which looks like this: +list, where blank lines separate the entries. Consider a mailing list +in a file named `addresses', which looks like this: Jane Doe 123 Main Street @@ -5425,7 +5426,7 @@ File: gawk.info, Node: Getline, Next: Read Timeout, Prev: Multiple Line, Up: So far we have been getting our input data from `awk''s main input stream--either the standard input (usually your keyboard, sometimes the -output from another program) or from the files specified on the command +output from another program) or the files specified on the command line. The `awk' language has a special built-in command called `getline' that can be used to read input under your explicit control. @@ -5563,7 +5564,7 @@ and produces these results: free The `getline' command used in this way sets only the variables `NR', -`FNR', and `RT' (and of course, VAR). The record is not split into +`FNR', and `RT' (and, of course, VAR). The record is not split into fields, so the values of the fields (including `$0') and the value of `NF' do not change. @@ -5573,8 +5574,8 @@ File: gawk.info, Node: Getline/File, Next: Getline/Variable/File, Prev: Getli 4.9.3 Using `getline' from a File --------------------------------- -Use `getline < FILE' to read the next record from FILE. Here FILE is a -string-valued expression that specifies the file name. `< FILE' is +Use `getline < FILE' to read the next record from FILE. Here, FILE is +a string-valued expression that specifies the file name. `< FILE' is called a "redirection" because it directs input to come from a different place. For example, the following program reads its input record from the file `secondary.input' when it encounters a first field @@ -5710,8 +5711,8 @@ all `awk' implementations. treatment of a construct like `"echo " "date" | getline'. Most versions, including the current version, treat it at as `("echo " "date") | getline'. (This is also how BWK `awk' behaves.) Some - versions changed and treated it as `"echo " ("date" | getline)'. - (This is how `mawk' behaves.) In short, _always_ use explicit + versions instead treat it as `"echo " ("date" | getline)'. (This + is how `mawk' behaves.) In short, _always_ use explicit parentheses, and then you won't have to worry. @@ -5747,15 +5748,16 @@ File: gawk.info, Node: Getline/Coprocess, Next: Getline/Variable/Coprocess, P 4.9.7 Using `getline' from a Coprocess -------------------------------------- -Input into `getline' from a pipe is a one-way operation. The command -that is started with `COMMAND | getline' only sends data _to_ your -`awk' program. +Reading input into `getline' from a pipe is a one-way operation. The +command that is started with `COMMAND | getline' only sends data _to_ +your `awk' program. On occasion, you might want to send data to another program for processing and then read the results back. `gawk' allows you to start a "coprocess", with which two-way communications are possible. This is done with the `|&' operator. Typically, you write data to the -coprocess first and then read results back, as shown in the following: +coprocess first and then read the results back, as shown in the +following: print "SOME QUERY" |& "db_server" "db_server" |& getline @@ -5817,7 +5819,7 @@ in mind: files. (d.c.) (See *note BEGIN/END::; also *note Auto-set::.) * Using `FILENAME' with `getline' (`getline < FILENAME') is likely - to be a source for confusion. `awk' opens a separate input stream + to be a source of confusion. `awk' opens a separate input stream from the current input file. However, by not using a variable, `$0' and `NF' are still updated. If you're doing this, it's probably by accident, and you should reconsider what it is you're @@ -5825,15 +5827,15 @@ in mind: * *note Getline Summary::, presents a table summarizing the `getline' variants and which variables they can affect. It is - worth noting that those variants which do not use redirection can + worth noting that those variants that do not use redirection can cause `FILENAME' to be updated if they cause `awk' to start reading a new input file. * If the variable being assigned is an expression with side effects, different versions of `awk' behave differently upon encountering end-of-file. Some versions don't evaluate the expression; many - versions (including `gawk') do. Here is an example, due to Duncan - Moore: + versions (including `gawk') do. Here is an example, courtesy of + Duncan Moore: BEGIN { system("echo 1 > f") @@ -5841,8 +5843,8 @@ in mind: print c } - Here, the side effect is the `++c'. Is `c' incremented if end of - file is encountered, before the element in `a' is assigned? + Here, the side effect is the `++c'. Is `c' incremented if + end-of-file is encountered before the element in `a' is assigned? `gawk' treats `getline' like a function call, and evaluates the expression `a[++c]' before attempting to read from `f'. However, @@ -5886,8 +5888,8 @@ This minor node describes a feature that is specific to `gawk'. You may specify a timeout in milliseconds for reading input from the keyboard, a pipe, or two-way communication, including TCP/IP sockets. -This can be done on a per input, command, or connection basis, by -setting a special element in the `PROCINFO' array (*note Auto-set::): +This can be done on a per-input, per-command, or per-connection basis, +by setting a special element in the `PROCINFO' array (*note Auto-set::): PROCINFO["input_name", "READ_TIMEOUT"] = TIMEOUT IN MILLISECONDS @@ -5911,7 +5913,7 @@ for more than five seconds: print $0 `gawk' terminates the read operation if input does not arrive after -waiting for the timeout period, returns failure and sets `ERRNO' to an +waiting for the timeout period, returns failure, and sets `ERRNO' to an appropriate string value. A negative or zero value for the timeout is the same as specifying no timeout at all. @@ -5919,7 +5921,7 @@ the same as specifying no timeout at all. implicit loop that reads input records and matches them against patterns, like so: - $ gawk 'BEGIN { PROCINFO["-", "READ_TIMEOUT"] = 5000 } + $ gawk 'BEGIN { PROCINFO["-", "READ_TIMEOUT"] = 5000 } > { print "You entered: " $0 }' gawk -| You entered: gawk @@ -5951,7 +5953,7 @@ input to arrive: environment variable exists, `gawk' uses its value to initialize the timeout value. The exclusive use of the environment variable to specify timeout has the disadvantage of not being able to control it on -a per command or connection basis. +a per-command or per-connection basis. `gawk' considers a timeout event to be an error even though the attempt to read from the underlying device may succeed in a later @@ -6019,7 +6021,7 @@ File: gawk.info, Node: Input Summary, Next: Input Exercises, Prev: Command-li * `gawk' sets `RT' to the text matched by `RS'. * After splitting the input into records, `awk' further splits the - record into individual fields, named `$1', `$2', and so on. `$0' + records into individual fields, named `$1', `$2', and so on. `$0' is the whole record, and `NF' indicates how many fields there are. The default way to split fields is between whitespace characters. @@ -6033,19 +6035,21 @@ File: gawk.info, Node: Input Summary, Next: Input Exercises, Prev: Command-li * Field splitting is more complicated than record splitting: - Field separator value Fields are split ... `awk' / - `gawk' + Field separator value Fields are split ... `awk' / + `gawk' ---------------------------------------------------------------------- - `FS == " "' On runs of whitespace `awk' - `FS == ANY SINGLE On that character `awk' - CHARACTER' - `FS == REGEXP' On text matching the regexp `awk' - `FS == ""' Each individual character is `gawk' - a separate field - `FIELDWIDTHS == LIST OF Based on character position `gawk' - COLUMNS' - `FPAT == REGEXP' On the text surrounding text `gawk' - matching the regexp + `FS == " "' On runs of whitespace `awk' + `FS == ANY SINGLE On that character `awk' + CHARACTER' + `FS == REGEXP' On text matching the `awk' + regexp + `FS == ""' Such that each individual `gawk' + character is a separate + field + `FIELDWIDTHS == LIST OF Based on character `gawk' + COLUMNS' position + `FPAT == REGEXP' On the text surrounding `gawk' + text matching the regexp * Using `FS = "\n"' causes the entire record to be a single field (assuming that newlines separate records). @@ -6055,12 +6059,11 @@ File: gawk.info, Node: Input Summary, Next: Input Exercises, Prev: Command-li * Use `PROCINFO["FS"]' to see how fields are being split. - * Use `getline' in its various forms to read additional records, - from the default input stream, from a file, or from a pipe or - coprocess. + * Use `getline' in its various forms to read additional records from + the default input stream, from a file, or from a pipe or coprocess. - * Use `PROCINFO[FILE, "READ_TIMEOUT"]' to cause reads to timeout for - FILE. + * Use `PROCINFO[FILE, "READ_TIMEOUT"]' to cause reads to time out + for FILE. * Directories on the command line are fatal for standard `awk'; `gawk' ignores them if not in POSIX mode. @@ -6155,7 +6158,7 @@ you will probably get an error. Keep in mind that a space is printed between any two items. Note that the `print' statement is a statement and not an -expression--you can't use it in the pattern part of a PATTERN-ACTION +expression--you can't use it in the pattern part of a pattern-action statement, for example. @@ -6303,7 +6306,7 @@ File: gawk.info, Node: OFMT, Next: Printf, Prev: Output Separators, Up: Prin =========================================== When printing numeric values with the `print' statement, `awk' -internally converts the number to a string of characters and prints +internally converts each number to a string of characters and prints that string. `awk' uses the `sprintf()' function to do this conversion (*note String Functions::). For now, it suffices to say that the `sprintf()' function accepts a "format specification" that tells it how @@ -6358,7 +6361,7 @@ A simple `printf' statement looks like this: As for `print', the entire list of arguments may optionally be enclosed in parentheses. Here too, the parentheses are necessary if any of the -item expressions use the `>' relational operator; otherwise, it can be +item expressions uses the `>' relational operator; otherwise, it can be confused with an output redirection (*note Redirection::). The difference between `printf' and `print' is the FORMAT argument. @@ -6385,7 +6388,7 @@ statements. For example: > }' -| Don't Panic! -Here, neither the `+' nor the `OUCH!' appear in the output message. +Here, neither the `+' nor the `OUCH!' appears in the output message. File: gawk.info, Node: Control Letters, Next: Format Modifiers, Prev: Basic Printf, Up: Printf @@ -6424,7 +6427,7 @@ width. Here is a list of the format-control letters: (The `%i' specification is for compatibility with ISO C.) `%e', `%E' - Print a number in scientific (exponential) notation; for example: + Print a number in scientific (exponential) notation. For example: printf "%4.3e\n", 1950 @@ -6449,7 +6452,7 @@ width. Here is a list of the format-control letters: Math Definitions::). `%F' - Like `%f' but the infinity and "not a number" values are spelled + Like `%f', but the infinity and "not a number" values are spelled using uppercase letters. The `%F' format is a POSIX extension to ISO C; not all systems @@ -6643,7 +6646,7 @@ string, like so: s = "abcdefg" printf "%" w "." p "s\n", s -This is not particularly easy to read but it does work. +This is not particularly easy to read, but it does work. C programmers may be used to supplying additional modifiers (`h', `j', `l', `L', `t', and `z') in `printf' format strings. These are not @@ -6682,7 +6685,7 @@ an aligned two-column table of names and phone numbers, as shown here: -| Jean-Paul 555-2127 In this case, the phone numbers had to be printed as strings because -the numbers are separated by a dash. Printing the phone numbers as +the numbers are separated by dashes. Printing the phone numbers as numbers would have produced just the first three digits: `555'. This would have been pretty confusing. @@ -6730,7 +6733,7 @@ output, usually the screen. Both `print' and `printf' can also send their output to other places. This is called "redirection". NOTE: When `--sandbox' is specified (*note Options::), redirecting - output to files, pipes and coprocesses is disabled. + output to files, pipes, and coprocesses is disabled. A redirection appears after the `print' or `printf' statement. Redirections in `awk' are written just like redirections in shell @@ -6770,7 +6773,7 @@ work identically for `printf': Each output file contains one name or number per line. `print ITEMS >> OUTPUT-FILE' - This redirection prints the items into the pre-existing output file + This redirection prints the items into the preexisting output file named OUTPUT-FILE. The difference between this and the single-`>' redirection is that the old contents (if any) of OUTPUT-FILE are not erased. Instead, the `awk' output is appended to the file. @@ -6818,8 +6821,8 @@ work identically for `printf': `print ITEMS |& COMMAND' This redirection prints the items to the input of COMMAND. The difference between this and the single-`|' redirection is that the - output from COMMAND can be read with `getline'. Thus COMMAND is a - "coprocess", which works together with, but subsidiary to, the + output from COMMAND can be read with `getline'. Thus, COMMAND is + a "coprocess", which works together with but is subsidiary to the `awk' program. This feature is a `gawk' extension, and is not available in POSIX @@ -6843,7 +6846,7 @@ a file, and then to use `>>' for subsequent output: This is indeed how redirections must be used from the shell. But in `awk', it isn't necessary. In this kind of case, a program should use `>' for all the `print' statements, because the output file is only -opened once. (It happens that if you mix `>' and `>>' that output is +opened once. (It happens that if you mix `>' and `>>' output is produced in the expected order. However, mixing the operators for the same file is definitely poor style, and is confusing to readers of your program.) @@ -6876,14 +6879,14 @@ command lines to be fed to the shell. File: gawk.info, Node: Special FD, Next: Special Files, Prev: Redirection, Up: Printing -5.7 Special Files for Standard Pre-Opened Data Streams -====================================================== +5.7 Special Files for Standard Preopened Data Streams +===================================================== Running programs conventionally have three input and output streams already available to them for reading and writing. These are known as the "standard input", "standard output", and "standard error output". -These open streams (and any other open file or pipe) are often referred -to by the technical term "file descriptors". +These open streams (and any other open files or pipes) are often +referred to by the technical term "file descriptors". These streams are, by default, connected to your keyboard and screen, but they are often redirected with the shell, via the `<', `<<', @@ -6908,7 +6911,7 @@ error messages to the screen, like this: (`/dev/tty' is a special file supplied by the operating system that is connected to your keyboard and screen. It represents the "terminal,"(1) which on modern systems is a keyboard and screen, not a serial console.) -This generally has the same effect but not always: although the +This generally has the same effect, but not always: although the standard error stream is usually the screen, it can be redirected; when that happens, writing to the screen is not correct. In fact, if `awk' is run from a background job, it may not have a terminal at all. Then @@ -6935,7 +6938,7 @@ becomes: print "Serious error detected!" > "/dev/stderr" - Note the use of quotes around the file name. Like any other + Note the use of quotes around the file name. Like with any other redirection, the value must be a string. It is a common error to omit the quotes, which leads to confusing results. @@ -6968,7 +6971,7 @@ there are special file names reserved for TCP/IP networking. File: gawk.info, Node: Other Inherited Files, Next: Special Network, Up: Special Files -5.8.1 Accessing Other Open Files With `gawk' +5.8.1 Accessing Other Open Files with `gawk' -------------------------------------------- Besides the `/dev/stdin', `/dev/stdout', and `/dev/stderr' special file @@ -7018,7 +7021,7 @@ File: gawk.info, Node: Special Caveats, Prev: Special Network, Up: Special Fi Here are some things to bear in mind when using the special file names that `gawk' provides: - * Recognition of the file names for the three standard pre-opened + * Recognition of the file names for the three standard preopened files is disabled only in POSIX mode. * Recognition of the other special file names is disabled if `gawk' @@ -7027,7 +7030,7 @@ that `gawk' provides: * `gawk' _always_ interprets these special file names. For example, using `/dev/fd/4' for output actually writes on file descriptor 4, - and not on a new file descriptor that is `dup()''ed from file + and not on a new file descriptor that is `dup()'ed from file descriptor 4. Most of the time this does not matter; however, it is important to _not_ close any of the files related to file descriptors 0, 1, and 2. Doing so results in unpredictable @@ -7187,8 +7190,8 @@ closing input or output files, respectively. This value is zero if the close succeeds, or -1 if it fails. The POSIX standard is very vague; it says that `close()' returns -zero on success and nonzero otherwise. In general, different -implementations vary in what they report when closing pipes; thus the +zero on success and a nonzero value otherwise. In general, different +implementations vary in what they report when closing pipes; thus, the return value cannot be used portably. (d.c.) In POSIX mode (*note Options::), `gawk' just returns zero when closing a pipe. @@ -7266,8 +7269,8 @@ File: gawk.info, Node: Output Summary, Next: Output Exercises, Prev: Nonfatal numeric values for the `print' statement. * The `printf' statement provides finer-grained control over output, - with format control letters for different data types and various - flags that modify the behavior of the format control letters. + with format-control letters for different data types and various + flags that modify the behavior of the format-control letters. * Output from both `print' and `printf' may be redirected to files, pipes, and coprocesses. @@ -7323,9 +7326,9 @@ value to a variable or a field by using an assignment operator. An expression can serve as a pattern or action statement on its own. Most other kinds of statements contain one or more expressions that specify the data on which to operate. As in other languages, -expressions in `awk' include variables, array references, constants, -and function calls, as well as combinations of these with various -operators. +expressions in `awk' can include variables, array references, +constants, and function calls, as well as combinations of these with +various operators. * Menu: @@ -7344,8 +7347,8 @@ File: gawk.info, Node: Values, Next: All Operators, Up: Expressions ========================================= Expressions are built up from values and the operations performed upon -them. This minor node describes the elementary objects which provide -the values used in expressions. +them. This minor node describes the elementary objects that provide the +values used in expressions. * Menu: @@ -7390,14 +7393,14 @@ the same value: 1.05e+2 1050e-1 - A string constant consists of a sequence of characters enclosed in + A "string constant" consists of a sequence of characters enclosed in double quotation marks. For example: "parrot" represents the string whose contents are `parrot'. Strings in `gawk' can be of any length, and they can contain any of the possible -eight-bit ASCII characters including ASCII NUL (character code zero). +eight-bit ASCII characters, including ASCII NUL (character code zero). Other `awk' implementations may have difficulty with some character codes. @@ -7417,14 +7420,14 @@ File: gawk.info, Node: Nondecimal-numbers, Next: Regexp Constants, Prev: Scal In `awk', all numbers are in decimal (i.e., base 10). Many other programming languages allow you to specify numbers in other bases, often octal (base 8) and hexadecimal (base 16). In octal, the numbers go 0, -1, 2, 3, 4, 5, 6, 7, 10, 11, 12, and so on. Just as `11', in decimal, -is 1 times 10 plus 1, so `11', in octal, is 1 times 8, plus 1. This -equals 9 in decimal. In hexadecimal, there are 16 digits. Because the -everyday decimal number system only has ten digits (`0'-`9'), the -letters `a' through `f' are used to represent the rest. (Case in the -letters is usually irrelevant; hexadecimal `a' and `A' have the same -value.) Thus, `11', in hexadecimal, is 1 times 16 plus 1, which equals -17 in decimal. +1, 2, 3, 4, 5, 6, 7, 10, 11, 12, and so on. Just as `11' in decimal is +1 times 10 plus 1, so `11' in octal is 1 times 8 plus 1. This equals 9 +in decimal. In hexadecimal, there are 16 digits. Because the everyday +decimal number system only has ten digits (`0'-`9'), the letters `a' +through `f' are used to represent the rest. (Case in the letters is +usually irrelevant; hexadecimal `a' and `A' have the same value.) +Thus, `11' in hexadecimal is 1 times 16 plus 1, which equals 17 in +decimal. Just by looking at plain `11', you can't tell what base it's in. So, in C, C++, and other languages derived from C, there is a special @@ -7432,13 +7435,13 @@ notation to signify the base. Octal numbers start with a leading `0', and hexadecimal numbers start with a leading `0x' or `0X': `11' - Decimal value 11. + Decimal value 11 `011' - Octal 11, decimal value 9. + Octal 11, decimal value 9 `0x11' - Hexadecimal 11, decimal value 17. + Hexadecimal 11, decimal value 17 This example shows the difference: @@ -7457,11 +7460,11 @@ really need to do this, use the `--non-decimal-data' command-line option; *note Nondecimal Data::.) If you have octal or hexadecimal data, you can use the `strtonum()' function (*note String Functions::) to convert the data into a number. Most of the time, you will want to -use octal or hexadecimal constants when working with the built-in bit -manipulation functions; see *note Bitwise Functions::, for more +use octal or hexadecimal constants when working with the built-in +bit-manipulation functions; see *note Bitwise Functions::, for more information. - Unlike some early C implementations, `8' and `9' are not valid in + Unlike in some early C implementations, `8' and `9' are not valid in octal constants. For example, `gawk' treats `018' as decimal 18: $ gawk 'BEGIN { print "021 is", 021 ; print 018 }' @@ -7488,12 +7491,12 @@ File: gawk.info, Node: Regexp Constants, Prev: Nondecimal-numbers, Up: Consta 6.1.1.3 Regular Expression Constants .................................... -A regexp constant is a regular expression description enclosed in +A "regexp constant" is a regular expression description enclosed in slashes, such as `/^beginning and end$/'. Most regexps used in `awk' programs are constant, but the `~' and `!~' matching operators can also match computed or dynamic regexps (which are typically just ordinary -strings or variables that contain a regexp, but could be a more complex -expression). +strings or variables that contain a regexp, but could be more complex +expressions). File: gawk.info, Node: Using Constant Regexps, Next: Variables, Prev: Constants, Up: Values @@ -7545,7 +7548,7 @@ and `patsplit()' functions (*note String Functions::). Modern implementations of `awk', including `gawk', allow the third argument of `split()' to be a regexp constant, but some older implementations do not. (d.c.) Because some built-in functions accept regexp constants -as arguments, it can be confusing when attempting to use regexp +as arguments, confusion can arise when attempting to use regexp constants as arguments to user-defined functions (*note User-defined::). For example: @@ -7568,10 +7571,11 @@ User-defined::). For example: In this example, the programmer wants to pass a regexp constant to the user-defined function `mysub()', which in turn passes it on to either `sub()' or `gsub()'. However, what really happens is that the -`pat' parameter is either one or zero, depending upon whether or not -`$0' matches `/hi/'. `gawk' issues a warning when it sees a regexp -constant used as a parameter to a user-defined function, because -passing a truth value in this way is probably not what was intended. +`pat' parameter is assigned a value of either one or zero, depending +upon whether or not `$0' matches `/hi/'. `gawk' issues a warning when +it sees a regexp constant used as a parameter to a user-defined +function, because passing a truth value in this way is probably not +what was intended. File: gawk.info, Node: Variables, Next: Conversion, Prev: Using Constant Regexps, Up: Values @@ -7579,7 +7583,7 @@ File: gawk.info, Node: Variables, Next: Conversion, Prev: Using Constant Rege 6.1.3 Variables --------------- -Variables are ways of storing values at one point in your program for +"Variables" are ways of storing values at one point in your program for use later in another part of your program. They can be manipulated entirely within the program text, and they can also be assigned values on the `awk' command line. @@ -7608,14 +7612,14 @@ variables. A variable name is a valid expression by itself; it represents the variable's current value. Variables are given new values with -"assignment operators", "increment operators", and "decrement -operators". *Note Assignment Ops::. In addition, the `sub()' and -`gsub()' functions can change a variable's value, and the `match()', -`split()', and `patsplit()' functions can change the contents of their -array parameters. *Note String Functions::. +"assignment operators", "increment operators", and "decrement operators" +(*note Assignment Ops::). In addition, the `sub()' and `gsub()' +functions can change a variable's value, and the `match()', `split()', +and `patsplit()' functions can change the contents of their array +parameters (*note String Functions::). A few variables have special built-in meanings, such as `FS' (the -field separator), and `NF' (the number of fields in the current input +field separator) and `NF' (the number of fields in the current input record). *Note Built-in Variables::, for a list of the predefined variables. These predefined variables can be used and assigned just like all other variables, but their values are also used or changed @@ -7812,7 +7816,7 @@ point, so the default behavior was restored to use a period as the decimal point character. You can use the `--use-lc-numeric' option (*note Options::) to force `gawk' to use the locale's decimal point character. (`gawk' also uses the locale's decimal point character when -in POSIX mode, either via `--posix', or the `POSIXLY_CORRECT' +in POSIX mode, either via `--posix' or the `POSIXLY_CORRECT' environment variable, as shown previously.) *note table-locale-affects:: describes the cases in which the @@ -7828,10 +7832,10 @@ Input Use period Use locale Table 6.1: Locale decimal point versus a period - Finally, modern day formal standards and IEEE standard floating-point -representation can have an unusual but important effect on the way -`gawk' converts some special string values to numbers. The details are -presented in *note POSIX Floating Point Problems::. + Finally, modern-day formal standards and the IEEE standard +floating-point representation can have an unusual but important effect +on the way `gawk' converts some special string values to numbers. The +details are presented in *note POSIX Floating Point Problems::. File: gawk.info, Node: All Operators, Next: Truth Values and Conditions, Prev: Values, Up: Expressions @@ -7839,7 +7843,7 @@ File: gawk.info, Node: All Operators, Next: Truth Values and Conditions, Prev 6.2 Operators: Doing Something with Values ========================================== -This minor node introduces the "operators" which make use of the values +This minor node introduces the "operators" that make use of the values provided by constants and variables. * Menu: @@ -8020,7 +8024,7 @@ you'll get. ---------- Footnotes ---------- - (1) It happens that BWK `awk', `gawk' and `mawk' all "get it right," + (1) It happens that BWK `awk', `gawk', and `mawk' all "get it right," but you should not rely on this. @@ -8137,7 +8141,7 @@ righthand expression. For example: The indices of `bar' are practically guaranteed to be different, because `rand()' returns different values each time it is called. (Arrays and the `rand()' function haven't been covered yet. *Note Arrays::, and -*note Numeric Functions::, for more information). This example +*note Numeric Functions::, for more information.) This example illustrates an important fact about assignment operators: the lefthand expression is only evaluated _once_. @@ -8155,14 +8159,14 @@ converted to a number. Operator Effect -------------------------------------------------------------------------- -LVALUE `+=' INCREMENT Add INCREMENT to the value of LVALUE -LVALUE `-=' DECREMENT Subtract DECREMENT from the value of LVALUE -LVALUE `*=' Multiply the value of LVALUE by COEFFICIENT +LVALUE `+=' INCREMENT Add INCREMENT to the value of LVALUE. +LVALUE `-=' DECREMENT Subtract DECREMENT from the value of LVALUE. +LVALUE `*=' Multiply the value of LVALUE by COEFFICIENT. COEFFICIENT -LVALUE `/=' DIVISOR Divide the value of LVALUE by DIVISOR -LVALUE `%=' MODULUS Set LVALUE to its remainder by MODULUS -LVALUE `^=' POWER -LVALUE `**=' POWER Raise LVALUE to the power POWER (c.e.) +LVALUE `/=' DIVISOR Divide the value of LVALUE by DIVISOR. +LVALUE `%=' MODULUS Set LVALUE to its remainder by MODULUS. +LVALUE `^=' POWER Raise LVALUE to the power POWER. +LVALUE `**=' POWER Raise LVALUE to the power POWER. (c.e.) Table 6.2: Arithmetic assignment operators @@ -8247,8 +8251,8 @@ is a summary of increment and decrement expressions: Operator Evaluation Order - Doctor, doctor! It hurts when I do this! - So don't do that! -- Groucho Marx + Doctor, it hurts when I do this! + Then don't do that! -- Groucho Marx What happens for something like the following? @@ -8263,7 +8267,7 @@ Or something even stranger? In other words, when do the various side effects prescribed by the postfix operators (`b++') take effect? When side effects happen is -"implementation defined". In other words, it is up to the particular +"implementation-defined". In other words, it is up to the particular version of `awk'. The result for the first example may be 12 or 13, and for the second, it may be 22 or 23. @@ -8278,7 +8282,7 @@ File: gawk.info, Node: Truth Values and Conditions, Next: Function Calls, Pre =============================== In certain contexts, expression values also serve as "truth values"; -(i.e., they determine what should happen next as the program runs). This +i.e., they determine what should happen next as the program runs. This minor node describes how `awk' defines "true" and "false" and how values are compared. @@ -8332,10 +8336,10 @@ File: gawk.info, Node: Typing and Comparison, Next: Boolean Ops, Prev: Truth The Guide is definitive. Reality is frequently inaccurate. -- Douglas Adams, `The Hitchhiker's Guide to the Galaxy' - Unlike other programming languages, `awk' variables do not have a -fixed type. Instead, they can be either a number or a string, depending -upon the value that is assigned to them. We look now at how variables -are typed, and how `awk' compares variables. + Unlike in other programming languages, in `awk' variables do not +have a fixed type. Instead, they can be either a number or a string, +depending upon the value that is assigned to them. We look now at how +variables are typed, and how `awk' compares variables. * Menu: @@ -8356,16 +8360,16 @@ of the variable is important because the types of two variables determine how they are compared. Variable typing follows these rules: * A numeric constant or the result of a numeric operation has the - NUMERIC attribute. + "numeric" attribute. * A string constant or the result of a string operation has the - STRING attribute. + "string" attribute. * Fields, `getline' input, `FILENAME', `ARGV' elements, `ENVIRON' elements, and the elements of an array created by `match()', `split()', and `patsplit()' that are numeric strings have the - STRNUM attribute. Otherwise, they have the STRING attribute. - Uninitialized variables also have the STRNUM attribute. + "strnum" attribute. Otherwise, they have the "string" attribute. + Uninitialized variables also have the "strnum" attribute. * Attributes propagate across assignments but are not changed by any use. @@ -8407,12 +8411,13 @@ constant, then a string comparison is performed. Otherwise, a numeric comparison is performed. This point bears additional emphasis: All user input is made of -characters, and so is first and foremost of STRING type; input strings -that look numeric are additionally given the STRNUM attribute. Thus, -the six-character input string ` +3.14' receives the STRNUM attribute. +characters, and so is first and foremost of string type; input strings +that look numeric are additionally given the strnum attribute. Thus, +the six-character input string ` +3.14' receives the strnum attribute. In contrast, the eight characters `" +3.14"' appearing in program text comprise a string constant. The following examples print `1' when the -comparison between the two different constants is true, `0' otherwise: +comparison between the two different constants is true, and `0' +otherwise: $ echo ' +3.14' | awk '{ print($0 == " +3.14") }' True -| 1 @@ -8511,7 +8516,7 @@ comparison is: -| false the result is `false' because both `$1' and `$2' are user input. They -are numeric strings--therefore both have the STRNUM attribute, +are numeric strings--therefore both have the strnum attribute, dictating a numeric comparison. The purpose of the comparison rules and the use of numeric strings is to attempt to produce the behavior that is "least surprising," while still "doing the right thing." @@ -8570,7 +8575,7 @@ is an example to illustrate the difference, in an `en_US.UTF-8' locale: ---------- Footnotes ---------- (1) Technically, string comparison is supposed to behave the same -way as if the strings are compared with the C `strcoll()' function. +way as if the strings were compared with the C `strcoll()' function. File: gawk.info, Node: Boolean Ops, Next: Conditional Exp, Prev: Typing and Comparison, Up: Truth Values and Conditions @@ -8633,7 +8638,7 @@ Boolean operators are: The `&&' and `||' operators are called "short-circuit" operators because of the way they work. Evaluation of the full expression is -"short-circuited" if the result can be determined part way through its +"short-circuited" if the result can be determined partway through its evaluation. Statements that end with `&&' or `||' can be continued simply by @@ -8686,15 +8691,15 @@ File: gawk.info, Node: Conditional Exp, Prev: Boolean Ops, Up: Truth Values a A "conditional expression" is a special kind of expression that has three operands. It allows you to use one expression's value to select -one of two other expressions. The conditional expression is the same -as in the C language, as shown here: +one of two other expressions. The conditional expression in `awk' is +the same as in the C language, as shown here: SELECTOR ? IF-TRUE-EXP : IF-FALSE-EXP There are three subexpressions. The first, SELECTOR, is always computed first. If it is "true" (not zero or not null), then -IF-TRUE-EXP is computed next and its value becomes the value of the -whole expression. Otherwise, IF-FALSE-EXP is computed next and its +IF-TRUE-EXP is computed next, and its value becomes the value of the +whole expression. Otherwise, IF-FALSE-EXP is computed next, and its value becomes the value of the whole expression. For example, the following expression produces the absolute value of `x': @@ -8728,7 +8733,7 @@ A "function" is a name for a particular calculation. This enables you to ask for it by name at any point in the program. For example, the function `sqrt()' computes the square root of a number. - A fixed set of functions are "built-in", which means they are + A fixed set of functions are "built in", which means they are available in every `awk' program. The `sqrt()' function is one of these. *Note Built-in::, for a list of built-in functions and their descriptions. In addition, you can define functions for use in your @@ -8863,7 +8868,7 @@ precedence: Increment, decrement. `^ **' - Exponentiation. These operators group right-to-left. + Exponentiation. These operators group right to left. `+ - !' Unary plus, minus, logical "not." @@ -8890,7 +8895,7 @@ String concatenation operand of another operator. As a result, it does not make sense to use a redirection operator near another operator of lower precedence without parentheses. Such combinations (e.g., `print - foo > a ? b : c'), result in syntax errors. The correct way to + foo > a ? b : c') result in syntax errors. The correct way to write this statement is `print foo > (a ? b : c)'. `~ !~' @@ -8900,16 +8905,16 @@ String concatenation Array membership. `&&' - Logical "and". + Logical "and." `||' - Logical "or". + Logical "or." `?:' - Conditional. This operator groups right-to-left. + Conditional. This operator groups right to left. `= += -= *= /= %= ^= **=' - Assignment. These operators group right-to-left. + Assignment. These operators group right to left. NOTE: The `|&', `**', and `**=' operators are not specified by POSIX. For maximum portability, do not use them. @@ -8977,24 +8982,24 @@ File: gawk.info, Node: Expressions Summary, Prev: Locales, Up: Expressions * `awk' provides the usual arithmetic operators (addition, subtraction, multiplication, division, modulus), and unary plus - and minus. It also provides comparison operators, boolean - operators, array membership testing, and regexp matching - operators. String concatenation is accomplished by placing two - expressions next to each other; there is no explicit operator. - The three-operand `?:' operator provides an "if-else" test within - expressions. + and minus. It also provides comparison operators, Boolean + operators, an array membership testing operator, and regexp + matching operators. String concatenation is accomplished by + placing two expressions next to each other; there is no explicit + operator. The three-operand `?:' operator provides an "if-else" + test within expressions. * Assignment operators provide convenient shorthands for common arithmetic operations. - * In `awk', a value is considered to be true if it is non-zero _or_ + * In `awk', a value is considered to be true if it is nonzero _or_ non-null. Otherwise, the value is false. * A variable's type is set upon each assignment and may change over its lifetime. The type determines how it behaves in comparisons (string or numeric). - * Function calls return a value which may be used as part of a larger + * Function calls return a value that may be used as part of a larger expression. Expressions used to pass parameter values are fully evaluated before the function is called. `awk' provides built-in and user-defined functions; this is described in *note Functions::. @@ -9168,7 +9173,7 @@ inside Boolean patterns. Likewise, the special patterns `BEGIN', `END', `BEGINFILE', and `ENDFILE', which never match any input record, are not expressions and cannot appear inside Boolean patterns. - The precedence of the different operators which can appear in + The precedence of the different operators that can appear in patterns is described in *note Precedence::. @@ -9188,8 +9193,8 @@ following: prints every record in `myfile' between `on'/`off' pairs, inclusive. A range pattern starts out by matching BEGPAT against every input -record. When a record matches BEGPAT, the range pattern is "turned on" -and the range pattern matches this record as well. As long as the +record. When a record matches BEGPAT, the range pattern is "turned +on", and the range pattern matches this record as well. As long as the range pattern stays turned on, it automatically matches every input record read. The range pattern also matches ENDPAT against every input record; when this succeeds, the range pattern is "turned off" again for @@ -9307,7 +9312,7 @@ for more information on using library functions. *Note Library Functions::, for a number of useful library functions. If an `awk' program has only `BEGIN' rules and no other rules, then -the program exits after the `BEGIN' rule is run.(1) However, if an +the program exits after the `BEGIN' rules are run.(1) However, if an `END' rule exists, then the input is read, even if there are no other rules in the program. This is necessary in case the `END' rule checks the `FNR' and `NR' variables. @@ -9333,7 +9338,7 @@ give `$0' a real value is to execute a `getline' command without a variable (*note Getline::). Another way is simply to assign a value to `$0'. - The second point is similar to the first but from the other + The second point is similar to the first, but from the other direction. Traditionally, due largely to implementation issues, `$0' and `NF' were _undefined_ inside an `END' rule. The POSIX standard specifies that `NF' is available in an `END' rule. It contains the @@ -9394,7 +9399,7 @@ tasks that would otherwise be difficult or impossible to perform: entirely. Otherwise, `gawk' exits with the usual fatal error. * If you have written extensions that modify the record handling (by - inserting an "input parser," *note Input Parsers::), you can invoke + inserting an "input parser"; *note Input Parsers::), you can invoke them at this point, before `gawk' has started processing the file. (This is a _very_ advanced feature, currently used only by the `gawkextlib' project (http://gawkextlib.sourceforge.net).) @@ -9404,16 +9409,15 @@ last record in an input file. For the last input file, it will be called before any `END' rules. The `ENDFILE' rule is executed even for empty input files. - Normally, when an error occurs when reading input in the normal input -processing loop, the error is fatal. However, if an `ENDFILE' rule is -present, the error becomes non-fatal, and instead `ERRNO' is set. This -makes it possible to catch and process I/O errors at the level of the -`awk' program. + Normally, when an error occurs when reading input in the normal +input-processing loop, the error is fatal. However, if an `ENDFILE' +rule is present, the error becomes non-fatal, and instead `ERRNO' is +set. This makes it possible to catch and process I/O errors at the +level of the `awk' program. The `next' statement (*note Next Statement::) is not allowed inside either a `BEGINFILE' or an `ENDFILE' rule. The `nextfile' statement is -allowed only inside a `BEGINFILE' rule, but not inside an `ENDFILE' -rule. +allowed only inside a `BEGINFILE' rule, not inside an `ENDFILE' rule. The `getline' statement (*note Getline::) is restricted inside both `BEGINFILE' and `ENDFILE': only redirected forms of `getline' are @@ -9458,11 +9462,11 @@ following program: END { print nmatches, "found" }' /path/to/data The `awk' program consists of two pieces of quoted text that are -concatenated together to form the program. The first part is double -quoted, which allows substitution of the `pattern' shell variable -inside the quotes. The second part is single quoted. +concatenated together to form the program. The first part is +double-quoted, which allows substitution of the `pattern' shell +variable inside the quotes. The second part is single-quoted. - Variable substitution via quoting works, but can be potentially + Variable substitution via quoting works, but can potentially be messy. It requires a good understanding of the shell's quoting rules (*note Quoting::), and it's often difficult to correctly match up the quotes when reading the program. @@ -9659,15 +9663,15 @@ The body of this loop is a compound statement enclosed in braces, containing two statements. The loop works in the following manner: first, the value of `i' is set to one. Then, the `while' statement tests whether `i' is less than or equal to three. This is true when -`i' equals one, so the `i'-th field is printed. Then the `i++' +`i' equals one, so the `i'th field is printed. Then the `i++' increments the value of `i' and the loop repeats. The loop terminates when `i' reaches four. A newline is not required between the condition and the body; however, using one makes the program clearer unless the body is a -compound statement or else is very simple. The newline after the -open-brace that begins the compound statement is not required either, -but the program is harder to read without it. +compound statement or else is very simple. The newline after the open +brace that begins the compound statement is not required either, but the +program is harder to read without it. File: gawk.info, Node: Do Statement, Next: For Statement, Prev: While Statement, Up: Statements @@ -9690,7 +9694,7 @@ Contrast this with the corresponding `while' statement: while (CONDITION) BODY -This statement does not execute BODY even once if the CONDITION is +This statement does not execute the BODY even once if the CONDITION is false to begin with. The following is an example of a `do' statement: { @@ -9746,7 +9750,7 @@ loop.) The same is true of the INCREMENT part. Incrementing additional variables requires separate statements at the end of the loop. The C compound expression, using C's comma operator, is useful in this -context but it is not supported in `awk'. +context, but it is not supported in `awk'. Most often, INCREMENT is an increment expression, as in the previous example. But this is not required; it can be any expression @@ -9822,7 +9826,7 @@ statement looks like this: Control flow in the `switch' statement works as it does in C. Once a match to a given case is made, the case statement bodies execute until -a `break', `continue', `next', `nextfile' or `exit' is encountered, or +a `break', `continue', `next', `nextfile', or `exit' is encountered, or the end of the `switch' statement itself. For example: while ((c = getopt(ARGC, ARGV, "aksx")) != -1) { @@ -10065,12 +10069,11 @@ listed in `ARGV'. standard. See the Austin Group website (http://austingroupbugs.net/view.php?id=607). - The current version of BWK `awk', and `mawk' also support -`nextfile'. However, they don't allow the `nextfile' statement inside -function bodies (*note User-defined::). `gawk' does; a `nextfile' -inside a function body reads the next record and starts processing it -with the first rule in the program, just as any other `nextfile' -statement. + The current version of BWK `awk' and `mawk' also support `nextfile'. +However, they don't allow the `nextfile' statement inside function +bodies (*note User-defined::). `gawk' does; a `nextfile' inside a +function body reads the next record and starts processing it with the +first rule in the program, just as any other `nextfile' statement. File: gawk.info, Node: Exit Statement, Prev: Nextfile Statement, Up: Statements @@ -10098,9 +10101,9 @@ record, skips reading any remaining input records, and executes the they do not execute. In such a case, if you don't want the `END' rule to do its job, set -a variable to nonzero before the `exit' statement and check that -variable in the `END' rule. *Note Assert Function::, for an example -that does this. +a variable to a nonzero value before the `exit' statement and check +that variable in the `END' rule. *Note Assert Function::, for an +example that does this. If an argument is supplied to `exit', its value is used as the exit status code for the `awk' process. If no argument is supplied, `exit' @@ -10158,7 +10161,7 @@ of activity. File: gawk.info, Node: User-modified, Next: Auto-set, Up: Built-in Variables -7.5.1 Built-In Variables That Control `awk' +7.5.1 Built-in Variables That Control `awk' ------------------------------------------- The following is an alphabetical list of variables that you can change @@ -10182,11 +10185,11 @@ description of each variable.) use binary I/O. Any other string value is treated the same as `"rw"', but causes `gawk' to generate a warning message. `BINMODE' is described in more detail in *note PC Using::. `mawk' - (*note Other Versions::), also supports this variable, but only + (*note Other Versions::) also supports this variable, but only using numeric values. ``CONVFMT'' - This string controls conversion of numbers to strings (*note + A string that controls the conversion of numbers to strings (*note Conversion::). It works by being passed, in effect, as the first argument to the `sprintf()' function (*note String Functions::). Its default value is `"%.6g"'. `CONVFMT' was introduced by the @@ -10233,7 +10236,7 @@ description of each variable.) `IGNORECASE #' If `IGNORECASE' is nonzero or non-null, then all string comparisons - and all regular expression matching are case independent. Thus, + and all regular expression matching are case-independent. Thus, regexp matching with `~' and `!~', as well as the `gensub()', `gsub()', `index()', `match()', `patsplit()', `split()', and `sub()' functions, record termination with `RS', and field @@ -10253,7 +10256,7 @@ description of each variable.) Assigning a false value to `LINT' turns off the lint warnings. This variable is a `gawk' extension. It is not special in other - `awk' implementations. Unlike the other special variables, + `awk' implementations. Unlike with the other special variables, changing `LINT' does affect the production of lint warnings, even if `gawk' is in compatibility mode. Much as the `--lint' and `--traditional' options independently control different aspects of @@ -10261,17 +10264,18 @@ description of each variable.) execution is independent of the flavor of `awk' being executed. `OFMT' - Controls conversion of numbers to strings (*note Conversion::) for - printing with the `print' statement. It works by being passed as - the first argument to the `sprintf()' function (*note String - Functions::). Its default value is `"%.6g"'. Earlier versions of - `awk' used `OFMT' to specify the format for converting numbers to - strings in general expressions; this is now done by `CONVFMT'. + A string that controls conversion of numbers to strings (*note + Conversion::) for printing with the `print' statement. It works + by being passed as the first argument to the `sprintf()' function + (*note String Functions::). Its default value is `"%.6g"'. + Earlier versions of `awk' used `OFMT' to specify the format for + converting numbers to strings in general expressions; this is now + done by `CONVFMT'. `OFS' - This is the output field separator (*note Output Separators::). - It is output between the fields printed by a `print' statement. - Its default value is `" "', a string consisting of a single space. + The output field separator (*note Output Separators::). It is + output between the fields printed by a `print' statement. Its + default value is `" "', a string consisting of a single space. `ORS' The output record separator. It is output at the end of every @@ -10321,7 +10325,7 @@ description of each variable.) File: gawk.info, Node: Auto-set, Next: ARGC and ARGV, Prev: User-modified, Up: Built-in Variables -7.5.2 Built-In Variables That Convey Information +7.5.2 Built-in Variables That Convey Information ------------------------------------------------ The following is an alphabetical list of variables that `awk' sets @@ -10439,14 +10443,14 @@ Options::), they are not special: `NF' The number of fields in the current input record. `NF' is set - each time a new record is read, when a new field is created or + each time a new record is read, when a new field is created, or when `$0' changes (*note Fields::). Unlike most of the variables described in this node, assigning a value to `NF' has the potential to affect `awk''s internal workings. In particular, assignments to `NF' can be used to - create or remove fields from the current record. *Note Changing - Fields::. + create fields in or remove fields from the current record. *Note + Changing Fields::. `FUNCTAB #' An array whose indices and corresponding values are the names of @@ -10481,7 +10485,7 @@ Options::), they are not special: `PROCINFO["identifiers"]' A subarray, indexed by the names of all identifiers used in - the text of the AWK program. An "identifier" is simply the + the text of the `awk' program. An "identifier" is simply the name of a variable (be it scalar or array), built-in function, user-defined function, or extension function. For each identifier, the value of the element is one of the @@ -10502,7 +10506,7 @@ Options::), they are not special: `"untyped"' The identifier is untyped (could be used as a scalar or - array, `gawk' doesn't know yet). + an array; `gawk' doesn't know yet). `"user"' The identifier is a user-defined function. @@ -10591,7 +10595,7 @@ Options::), they are not special: string, or -1 if no match is found. `RSTART' - The start-index in characters of the substring that is matched by + The start index in characters of the substring that is matched by the `match()' function (*note String Functions::). `RSTART' is set by invoking the `match()' function. Its value is the position of the string where the matched substring starts, or zero if no @@ -10641,7 +10645,7 @@ Options::), they are not special: } NOTE: In order to avoid severe time-travel paradoxes,(2) - neither `FUNCTAB' nor `SYMTAB' are available as elements + neither `FUNCTAB' nor `SYMTAB' is available as an element within the `SYMTAB' array. Changing `NR' and `FNR' @@ -10780,7 +10784,7 @@ are passed on to the `awk' program. (*Note Getopt Function::, for an When designing your program, you should choose options that don't conflict with `gawk''s, because it will process any options that it accepts before passing the rest of the command line on to your program. -Using `#!' with the `-E' option may help (*Note Executable Scripts::, +Using `#!' with the `-E' option may help (*note Executable Scripts::, and *note Options::,). @@ -10791,14 +10795,14 @@ File: gawk.info, Node: Pattern Action Summary, Prev: Built-in Variables, Up: * Pattern-action pairs make up the basic elements of an `awk' program. Patterns are either normal expressions, range - expressions, regexp constants, one of the special keywords - `BEGIN', `END', `BEGINFILE', `ENDFILE', or empty. The action + expressions, or regexp constants; one of the special keywords + `BEGIN', `END', `BEGINFILE', or `ENDFILE'; or empty. The action executes if the current record matches the pattern. Empty (missing) patterns match all records. - * I/O from `BEGIN' and `END' rules have certain constraints. This - is also true, only more so, for `BEGINFILE' and `ENDFILE' rules. - The latter two give you "hooks" into `gawk''s file processing, + * I/O from `BEGIN' and `END' rules has certain constraints. This is + also true, only more so, for `BEGINFILE' and `ENDFILE' rules. The + latter two give you "hooks" into `gawk''s file processing, allowing you to recover from a file that otherwise would cause a fatal error (such as a file that cannot be opened). @@ -10819,11 +10823,11 @@ File: gawk.info, Node: Pattern Action Summary, Prev: Built-in Variables, Up: iteration of a loop (or get out of a `switch'). * `next' and `nextfile' let you read the next record and start over - at the top of your program, or skip to the next input file and + at the top of your program or skip to the next input file and start over, respectively. * The `exit' statement terminates your program. When executed from - an action (or function body) it transfers control to the `END' + an action (or function body), it transfers control to the `END' statements. From an `END' statement body, it exits immediately. You may pass an optional numeric value to be used as `awk''s exit status. @@ -10925,9 +10929,9 @@ languages allow arbitrary starting and ending indices--e.g., `15 .. 27'--but the size of the array is still fixed when the array is declared.) - A contiguous array of four elements might look like the following -example, conceptually, if the element values are 8, `"foo"', `""', and -30 as shown in *note figure-array-elements::: + A contiguous array of four elements might look like *note +figure-array-elements::, conceptually, if the element values are eight, +`"foo"', `""', and 30. +---------+---------+--------+---------+ | 8 | "foo" | "" | 30 | @r{Value} @@ -10936,17 +10940,19 @@ example, conceptually, if the element values are 8, `"foo"', `""', and Figure 8.1: A contiguous array Only the values are stored; the indices are implicit from the order of -the values. Here, 8 is the value at index zero, because 8 appears in the -position with zero elements before it. +the values. Here, eight is the value at index zero, because eight +appears in the position with zero elements before it. Arrays in `awk' are different--they are "associative". This means that each array is a collection of pairs--an index and its corresponding array element value: - Index 3 Value 30 - Index 1 Value "foo" - Index 0 Value 8 - Index 2 Value "" + Index Value +------------------------ + `3' `30' + `1' `"foo"' + `0' `8' + `2' `""' The pairs are shown in jumbled order because their order is irrelevant.(1) @@ -10955,11 +10961,13 @@ irrelevant.(1) at any time. For example, suppose a tenth element is added to the array whose value is `"number ten"'. The result is: - Index 10 Value "number ten" - Index 3 Value 30 - Index 1 Value "foo" - Index 0 Value 8 - Index 2 Value "" + Index Value +------------------------------- + `10' `"number ten"' + `3' `30' + `1' `"foo"' + `0' `8' + `2' `""' Now the array is "sparse", which just means some indices are missing. It has elements 0-3 and 10, but doesn't have elements 4, 5, 6, 7, 8, or @@ -10970,17 +10978,19 @@ have to be positive integers. Any number, or even a string, can be an index. For example, the following is an array that translates words from English to French: - Index "dog" Value "chien" - Index "cat" Value "chat" - Index "one" Value "un" - Index 1 Value "un" + Index Value +------------------------ + `"dog"' `"chien"' + `"cat"' `"chat"' + `"one"' `"un"' + `1' `"un"' Here we decided to translate the number one in both spelled-out and numeric form--thus illustrating that a single array can have both numbers and strings as indices. (In fact, array subscripts are always strings. There are some subtleties to how numbers work when used as array subscripts; this is discussed in more detail in *note Numeric -Array Subscripts::.) Here, the number `1' isn't double quoted, because +Array Subscripts::.) Here, the number `1' isn't double-quoted, because `awk' automatically converts it to a string. The value of `IGNORECASE' has no effect upon array subscripting. @@ -11004,7 +11014,7 @@ File: gawk.info, Node: Reference to Elements, Next: Assigning Elements, Prev: ----------------------------------- The principal way to use an array is to refer to one of its elements. -An array reference is an expression as follows: +An "array reference" is an expression as follows: ARRAY[INDEX-EXPRESSION] @@ -11012,8 +11022,8 @@ Here, ARRAY is the name of an array. The expression INDEX-EXPRESSION is the index of the desired element of the array. The value of the array reference is the current value of that array -element. For example, `foo[4.3]' is an expression for the element of -array `foo' at index `4.3'. +element. For example, `foo[4.3]' is an expression referencing the +element of array `foo' at index `4.3'. A reference to an array element that has no recorded value yields a value of `""', the null string. This includes elements that have not @@ -11080,7 +11090,7 @@ File: gawk.info, Node: Array Example, Next: Scanning an Array, Prev: Assignin The following program takes a list of lines, each beginning with a line number, and prints them out in order of line number. The line numbers -are not in order when they are first read--instead they are scrambled. +are not in order when they are first read--instead, they are scrambled. This program sorts the lines by making an array using the line numbers as subscripts. The program then prints out the lines in sorted order of their numbers. It is a very simple program and gets confused upon @@ -11151,7 +11161,7 @@ has previously used, with the variable VAR set to that index. The following program uses this form of the `for' statement. The first rule scans the input records and notes which words appear (at least once) in the input, by storing a one into the array `used' with -the word as index. The second rule scans the elements of `used' to +the word as the index. The second rule scans the elements of `used' to find all the distinct words that appear in the input. It prints each word that is more than 10 characters long and also prints the number of such words. *Note String Functions::, for more information on the @@ -11234,7 +11244,7 @@ internal implementation of arrays and will vary from one version of Often, though, you may wish to do something simple, such as "traverse the array by comparing the indices in ascending order," or "traverse the array by comparing the values in descending order." -`gawk' provides two mechanisms which give you this control. +`gawk' provides two mechanisms that give you this control: * Set `PROCINFO["sorted_in"]' to one of a set of predefined values. We describe this now. @@ -11282,22 +11292,26 @@ available: which `gawk' uses internally to perform the sorting. `"@ind_str_desc"' - String indices ordered from high to low. + Like `"@ind_str_asc"', but the string indices are ordered from + high to low. `"@ind_num_desc"' - Numeric indices ordered from high to low. + Like `"@ind_num_asc"', but the numeric indices are ordered from + high to low. `"@val_type_desc"' - Element values, based on type, ordered from high to low. - Subarrays, if present, come out first. + Like `"@val_type_asc"', but the element values, based on type, are + ordered from high to low. Subarrays, if present, come out first. `"@val_str_desc"' - Element values, treated as strings, ordered from high to low. - Subarrays, if present, come out first. + Like `"@val_str_asc"', but the element values, treated as strings, + are ordered from high to low. Subarrays, if present, come out + first. `"@val_num_desc"' - Element values, treated as numbers, ordered from high to low. - Subarrays, if present, come out first. + Like `"@val_num_asc"', but the element values, treated as numbers, + are ordered from high to low. Subarrays, if present, come out + first. The array traversal order is determined before the `for' loop starts to run. Changing `PROCINFO["sorted_in"]' in the loop body does not @@ -11483,8 +11497,8 @@ deleting elements in an array: This example removes all the elements from the array `frequencies'. Once an element is deleted, a subsequent `for' statement to scan the -array does not report that element and the `in' operator to check for -the presence of that element returns zero (i.e., false): +array does not report that element and using the `in' operator to check +for the presence of that element returns zero (i.e., false): delete foo[4] if (4 in foo) @@ -11687,7 +11701,7 @@ two-element subarray at index `1' of the main array `a': This simulates a true two-dimensional array. Each subarray element can contain another subarray as a value, which in turn can hold other arrays as well. In this way, you can create arrays of three or more -dimensions. The indices can be any `awk' expression, including scalars +dimensions. The indices can be any `awk' expressions, including scalars separated by commas (i.e., a regular `awk' simulated multidimensional subscript). So the following is valid in `gawk': @@ -11696,7 +11710,7 @@ subscript). So the following is valid in `gawk': Each subarray and the main array can be of different length. In fact, the elements of an array or its subarray do not all have to have the same type. This means that the main array and any of its subarrays -can be non-rectangular, or jagged in structure. You can assign a scalar +can be nonrectangular, or jagged in structure. You can assign a scalar value to the index `4' of the main array `a', even though `a[1]' is itself an array and not a scalar: @@ -11714,8 +11728,8 @@ the element at that index: a[4][5][6][7] = "An element in a four-dimensional array" This removes the scalar value from index `4' and then inserts a -subarray of subarray of subarray containing a scalar. You can also -delete an entire subarray or subarray of subarrays: +three-level nested subarray containing a scalar. You can also delete an +entire subarray or subarray of subarrays: delete a[4][5] a[4][5] = "An element in subarray a[4]" @@ -11723,7 +11737,7 @@ delete an entire subarray or subarray of subarrays: But recall that you can not delete the main array `a' and then use it as a scalar. - The built-in functions which take array arguments can also be used + The built-in functions that take array arguments can also be used with subarrays. For example, the following code fragment uses `length()' (*note String Functions::) to determine the number of elements in the main array `a' and its subarrays: @@ -11744,7 +11758,7 @@ be nested to scan all the elements of an array of arrays if it is rectangular in structure. In order to print the contents (scalar values) of a two-dimensional array of arrays (i.e., in which each first-level element is itself an array, not necessarily of the same -length) you could use the following code: +length), you could use the following code: for (i in array) for (j in array[i]) @@ -11826,9 +11840,9 @@ File: gawk.info, Node: Arrays Summary, Prev: Arrays of Arrays, Up: Arrays of `awk'. * Standard `awk' simulates multidimensional arrays by separating - subscript values with a comma. The values are concatenated into a + subscript values with commas. The values are concatenated into a single string, separated by the value of `SUBSEP'. The fact that - such a subscript was created in this way is not retained; thus + such a subscript was created in this way is not retained; thus, changing `SUBSEP' may have unexpected consequences. You can use `(SUB1, SUB2, ...) in ARRAY' to see if such a multidimensional subscript exists in ARRAY. @@ -11836,7 +11850,7 @@ File: gawk.info, Node: Arrays Summary, Prev: Arrays of Arrays, Up: Arrays * `gawk' provides true arrays of arrays. You use a separate set of square brackets for each dimension in such an array: `data[row][col]', for example. Array elements may thus be either - scalar values (number or string) or another array. + scalar values (number or string) or other arrays. * Use the `isarray()' built-in function to determine if an array element is itself a subarray. @@ -11856,7 +11870,9 @@ internationalize and localize programs. Besides the built-in functions, `awk' has provisions for writing new functions that the rest of a program can use. The second half of this -major node describes these "user-defined" functions. +major node describes these "user-defined" functions. Finally, we +explore indirect function calls, a `gawk'-specific extension that lets +you determine at runtime what function is to be called. * Menu: @@ -11868,7 +11884,7 @@ major node describes these "user-defined" functions. File: gawk.info, Node: Built-in, Next: User-defined, Up: Functions -9.1 Built-In Functions +9.1 Built-in Functions ====================== "Built-in" functions are always available for your `awk' program to @@ -11893,7 +11909,7 @@ for your convenience. File: gawk.info, Node: Calling Built-in, Next: Numeric Functions, Up: Built-in -9.1.1 Calling Built-In Functions +9.1.1 Calling Built-in Functions -------------------------------- To call one of `awk''s built-in functions, write the name of the @@ -11930,9 +11946,10 @@ are evaluated from left to right or from right to left. For example: j = atan2(++i, i *= 2) If the order of evaluation is left to right, then `i' first becomes -6, and then 12, and `atan2()' is called with the two arguments 6 and -12. But if the order of evaluation is right to left, `i' first becomes -10, then 11, and `atan2()' is called with the two arguments 11 and 10. +six, and then 12, and `atan2()' is called with the two arguments six +and 12. But if the order of evaluation is right to left, `i' first +becomes 10, then 11, and `atan2()' is called with the two arguments 11 +and 10. File: gawk.info, Node: Numeric Functions, Next: String Functions, Prev: Calling Built-in, Up: Built-in @@ -11988,7 +12005,7 @@ brackets ([ ]): Often random integers are needed instead. Following is a user-defined function that can be used to obtain a random - non-negative integer less than N: + nonnegative integer less than N: function randint(n) { @@ -12078,7 +12095,7 @@ File: gawk.info, Node: String Functions, Next: I/O Functions, Prev: Numeric F The functions in this minor node look at or change the text of one or more strings. - `gawk' understands locales (*note Locales::), and does all string + `gawk' understands locales (*note Locales::) and does all string processing in terms of _characters_, not _bytes_. This distinction is particularly important to understand for locales where one character may be represented by multiple bytes. Thus, for example, `length()' @@ -12149,7 +12166,7 @@ Options::): a[2] = "de" a[3] = "sac" - The `asorti()' function works similarly to `asort()', however, the + The `asorti()' function works similarly to `asort()'; however, the _indices_ are sorted, instead of the values. Thus, in the previous example, starting with the same initial set of indices and values in `a', calling `asorti(a)' would yield: @@ -12237,7 +12254,7 @@ Options::): With BWK `awk' and `gawk', it is a fatal error to use a regexp constant for FIND. Other implementations allow it, simply treating the regexp constant as an expression meaning `$0 ~ - /regexp/'. (d.c.). + /regexp/'. (d.c.) `length('[STRING]`)' Return the number of characters in STRING. If STRING is a number, @@ -12281,9 +12298,9 @@ Options::): `match(STRING, REGEXP' [`, ARRAY']`)' Search STRING for the longest, leftmost substring matched by the - regular expression, REGEXP and return the character position - (index) at which that substring begins (one, if it starts at the - beginning of STRING). If no match is found, return zero. + regular expression REGEXP and return the character position (index) + at which that substring begins (one, if it starts at the beginning + of STRING). If no match is found, return zero. The REGEXP argument may be either a regexp constant (`/'...`/') or a string constant (`"'...`"'). In the latter case, the string is @@ -12291,7 +12308,7 @@ Options::): discussion of the difference between the two forms, and the implications for writing your program correctly. - The order of the first two arguments is backwards from most other + The order of the first two arguments is the opposite of most other string functions that work with regular expressions, such as `sub()' and `gsub()'. It might help to remember that for `match()', the order is the same as for the `~' operator: `STRING @@ -12358,8 +12375,8 @@ Options::): There may not be subscripts for the start and index for every parenthesized subexpression, because they may not all have matched - text; thus they should be tested for with the `in' operator (*note - Reference to Elements::). + text; thus, they should be tested for with the `in' operator + (*note Reference to Elements::). The ARRAY argument to `match()' is a `gawk' extension. In compatibility mode (*note Options::), using a third argument is a @@ -12392,19 +12409,19 @@ Options::): FIELDSEP, is a regexp describing where to split STRING (much as `FS' can be a regexp describing where to split input records). If FIELDSEP is omitted, the value of `FS' is used. `split()' returns - the number of elements created. SEPS is a `gawk' extension with + the number of elements created. SEPS is a `gawk' extension, with `SEPS[I]' being the separator string between `ARRAY[I]' and - `ARRAY[I+1]'. If FIELDSEP is a single space then any leading + `ARRAY[I+1]'. If FIELDSEP is a single space, then any leading whitespace goes into `SEPS[0]' and any trailing whitespace goes - into `SEPS[N]' where N is the return value of `split()' (i.e., the - number of elements in ARRAY). + into `SEPS[N]', where N is the return value of `split()' (i.e., + the number of elements in ARRAY). The `split()' function splits strings into pieces in a manner similar to the way input lines are split into fields. For example: split("cul-de-sac", a, "-", seps) - splits the string `cul-de-sac' into three fields using `-' as the + splits the string `"cul-de-sac"' into three fields using `-' as the separator. It sets the contents of the array `a' as follows: a[1] = "cul" @@ -12421,17 +12438,18 @@ Options::): As with input field-splitting, when the value of FIELDSEP is `" "', leading and trailing whitespace is ignored in values assigned to the elements of ARRAY but not in SEPS, and the elements - are separated by runs of whitespace. Also, as with input - field-splitting, if FIELDSEP is the null string, each individual + are separated by runs of whitespace. Also, as with input field + splitting, if FIELDSEP is the null string, each individual character in the string is split into its own array element. (c.e.) Note, however, that `RS' has no effect on the way `split()' works. - Even though `RS = ""' causes newline to also be an input field - separator, this does not affect how `split()' splits strings. + Even though `RS = ""' causes the newline character to also be an + input field separator, this does not affect how `split()' splits + strings. Modern implementations of `awk', including `gawk', allow the third - argument to be a regexp constant (`/abc/') as well as a string. + argument to be a regexp constant (`/'...`/') as well as a string. (d.c.) The POSIX standard allows this as well. *Note Computed Regexps::, for a discussion of the difference between using a string constant or a regexp constant, and the implications for @@ -12532,7 +12550,7 @@ Options::): { sub(/\|/, "\\&"); print } As mentioned, the third argument to `sub()' must be a variable, - field or array element. Some versions of `awk' allow the third + field, or array element. Some versions of `awk' allow the third argument to be an expression that is not an lvalue. In such a case, `sub()' still searches for the pattern and returns zero or one, but the result of the substitution (if any) is thrown away @@ -12657,11 +12675,11 @@ example, `"a\qb"' is treated as `"aqb"'. At the runtime level, the various functions handle sequences of `\' and `&' differently. The situation is (sadly) somewhat complex. -Historically, the `sub()' and `gsub()' functions treated the two -character sequence `\&' specially; this sequence was replaced in the -generated text with a single `&'. Any other `\' within the REPLACEMENT -string that did not precede an `&' was passed through unchanged. This -is illustrated in *note table-sub-escapes::. +Historically, the `sub()' and `gsub()' functions treated the +two-character sequence `\&' specially; this sequence was replaced in +the generated text with a single `&'. Any other `\' within the +REPLACEMENT string that did not precede an `&' was passed through +unchanged. This is illustrated in *note table-sub-escapes::. You type `sub()' sees `sub()' generates ------- --------- -------------- @@ -12676,10 +12694,10 @@ is illustrated in *note table-sub-escapes::. Table 9.1: Historical escape sequence processing for `sub()' and `gsub()' -This table shows both the lexical-level processing, where an odd number -of backslashes becomes an even number at the runtime level, as well as -the runtime processing done by `sub()'. (For the sake of simplicity, -the rest of the following tables only show the case of even numbers of +This table shows the lexical-level processing, where an odd number of +backslashes becomes an even number at the runtime level, as well as the +runtime processing done by `sub()'. (For the sake of simplicity, the +rest of the following tables only show the case of even numbers of backslashes entered at the lexical level.) The problem with the historical approach is that there is no way to @@ -12703,10 +12721,10 @@ This is shown in *note table-sub-proposed::. `\\q' `\q' A literal `\q' `\\\\' `\\' `\\' -Table 9.2: GNU `awk' rules for `sub()' and backslash +Table 9.2: `gawk' rules for `sub()' and backslash In a nutshell, at the runtime level, there are now three special -sequences of characters (`\\\&', `\\&' and `\&') whereas historically +sequences of characters (`\\\&', `\\&', and `\&') whereas historically there was only one. However, as in the historical case, any `\' that is not part of one of these three sequences is not special and appears in the output literally. @@ -12736,7 +12754,7 @@ Table 9.3: POSIX rules for `sub()' and `gsub()' `\\\\' is seen as `\\' and produces `\' instead of `\\'. Starting with version 3.1.4, `gawk' followed the POSIX rules when -`--posix' is specified (*note Options::). Otherwise, it continued to +`--posix' was specified (*note Options::). Otherwise, it continued to follow the proposed rules, as that had been its behavior for many years. When version 4.0.0 was released, the `gawk' maintainer made the @@ -12763,9 +12781,9 @@ the `\' does not, as shown in *note table-gensub-escapes::. Table 9.4: Escape sequence processing for `gensub()' - Because of the complexity of the lexical and runtime level processing -and the special cases for `sub()' and `gsub()', we recommend the use of -`gawk' and `gensub()' when you have to do substitutions. + Because of the complexity of the lexical- and runtime-level +processing and the special cases for `sub()' and `gsub()', we recommend +the use of `gawk' and `gensub()' when you have to do substitutions. ---------- Footnotes ---------- @@ -12792,10 +12810,10 @@ parameters are enclosed in square brackets ([ ]): When closing a coprocess, it is occasionally useful to first close one end of the two-way pipe and then to close the other. This is done by providing a second argument to `close()'. This second - argument should be one of the two string values `"to"' or `"from"', - indicating which end of the pipe to close. Case in the string does - not matter. *Note Two-way I/O::, which discusses this feature in - more detail and gives an example. + argument (HOW) should be one of the two string values `"to"' or + `"from"', indicating which end of the pipe to close. Case in the + string does not matter. *Note Two-way I/O::, which discusses this + feature in more detail and gives an example. Note that the second argument to `close()' is a `gawk' extension; it is not available in compatibility mode (*note Options::). @@ -12813,7 +12831,7 @@ parameters are enclosed in square brackets ([ ]): sometimes it is necessary to force a program to "flush" its buffers (i.e., write the information to its destination, even if a buffer is not full). This is the purpose of the `fflush()' - function--`gawk' also buffers its output and the `fflush()' + function--`gawk' also buffers its output, and the `fflush()' function forces `gawk' to flush its buffers. Brian Kernighan added `fflush()' to his `awk' in April 1992. For @@ -12830,16 +12848,17 @@ parameters are enclosed in square brackets ([ ]): output files and pipes if the argument was the null string. This was changed in order to be compatible with Brian Kernighan's `awk', in the hope that standardizing this - feature in POSIX would then be easier (which indeed helped). + feature in POSIX would then be easier (which indeed proved to + be the case). With `gawk', you can use `fflush("/dev/stdout")' if you wish to flush only the standard output. `fflush()' returns zero if the buffer is successfully flushed; - otherwise, it returns non-zero. (`gawk' returns -1.) In the case - where all buffers are flushed, the return value is zero only if - all buffers were flushed successfully. Otherwise, it is -1, and - `gawk' warns about the problem FILENAME. + otherwise, it returns a nonzero value. (`gawk' returns -1.) In + the case where all buffers are flushed, the return value is zero + only if all buffers were flushed successfully. Otherwise, it is + -1, and `gawk' warns about the problem FILENAME. `gawk' also issues a warning message if you attempt to flush a file or pipe that was opened for reading (such as with `getline'), @@ -12848,9 +12867,9 @@ parameters are enclosed in square brackets ([ ]): Interactive Versus Noninteractive Buffering - As a side point, buffering issues can be even more confusing, - depending upon whether your program is "interactive" (i.e., - communicating with a user sitting at a keyboard).(1) + As a side point, buffering issues can be even more confusing if + your program is "interactive" (i.e., communicating with a user + sitting at a keyboard).(1) Interactive programs generally "line buffer" their output (i.e., they write out every line). Noninteractive programs wait until @@ -12879,7 +12898,7 @@ parameters are enclosed in square brackets ([ ]): shot. `system(COMMAND)' - Execute the operating-system command COMMAND and then return to + Execute the operating system command COMMAND and then return to the `awk' program. Return COMMAND's exit status. For example, if the following fragment of code is put in your `awk' @@ -12968,14 +12987,14 @@ File: gawk.info, Node: Time Functions, Next: Bitwise Functions, Prev: I/O Fun `awk' programs are commonly used to process log files containing timestamp information, indicating when a particular log record was -written. Many programs log their timestamp in the form returned by the -`time()' system call, which is the number of seconds since a particular -epoch. On POSIX-compliant systems, it is the number of seconds since -1970-01-01 00:00:00 UTC, not counting leap seconds.(1) All known -POSIX-compliant systems support timestamps from 0 through 2^31 - 1, -which is sufficient to represent times through 2038-01-19 03:14:07 UTC. -Many systems support a wider range of timestamps, including negative -timestamps that represent times before the epoch. +written. Many programs log their timestamps in the form returned by +the `time()' system call, which is the number of seconds since a +particular epoch. On POSIX-compliant systems, it is the number of +seconds since 1970-01-01 00:00:00 UTC, not counting leap seconds.(1) +All known POSIX-compliant systems support timestamps from 0 through +2^31 - 1, which is sufficient to represent times through 2038-01-19 +03:14:07 UTC. Many systems support a wider range of timestamps, +including negative timestamps that represent times before the epoch. In order to make it easier to process such log files and to produce useful reports, `gawk' provides the following functions for working @@ -12998,9 +13017,9 @@ enclosed in square brackets ([ ]): specified; for example, an hour of -1 means 1 hour before midnight. The origin-zero Gregorian calendar is assumed, with year 0 preceding year 1 and year -1 preceding year 0. The time is - assumed to be in the local timezone. If the daylight-savings flag - is positive, the time is assumed to be daylight savings time; if - zero, the time is assumed to be standard time; and if negative + assumed to be in the local time zone. If the daylight-savings + flag is positive, the time is assumed to be daylight savings time; + if zero, the time is assumed to be standard time; and if negative (the default), `mktime()' attempts to determine whether daylight savings time is in effect for the specified time. @@ -13141,23 +13160,23 @@ the following date format specifications: The weekday as a decimal number (1-7). Monday is day one. `%U' - The week number of the year (the first Sunday as the first day of - week one) as a decimal number (00-53). + The week number of the year (with the first Sunday as the first + day of week one) as a decimal number (00-53). `%V' - The week number of the year (the first Monday as the first day of - week one) as a decimal number (01-53). The method for determining - the week number is as specified by ISO 8601. (To wit: if the week - containing January 1 has four or more days in the new year, then - it is week one; otherwise it is week 53 of the previous year and - the next week is week one.) + The week number of the year (with the first Monday as the first + day of week one) as a decimal number (01-53). The method for + determining the week number is as specified by ISO 8601. (To wit: + if the week containing January 1 has four or more days in the new + year, then it is week one; otherwise it is week 53 of the previous + year and the next week is week one.) `%w' The weekday as a decimal number (0-6). Sunday is day zero. `%W' - The week number of the year (the first Monday as the first day of - week one) as a decimal number (00-53). + The week number of the year (with the first Monday as the first + day of week one) as a decimal number (00-53). `%x' The locale's "appropriate" date representation. (This is `%A %B @@ -13174,8 +13193,8 @@ the following date format specifications: The full year as a decimal number (e.g., 2015). `%z' - The timezone offset in a +HHMM format (e.g., the format necessary - to produce RFC 822/RFC 1036 date headers). + The time zone offset in a `+HHMM' format (e.g., the format + necessary to produce RFC 822/RFC 1036 date headers). `%Z' The time zone name or abbreviation; no characters if no time zone @@ -13292,7 +13311,7 @@ each successive pair of bits in the operands. Three common operations are bitwise AND, OR, and XOR. The operations are described in *note table-bitwise-ops::. - Bit Operator + Bit operator | AND | OR | XOR |--+--+--+--+--+-- Operands | 0 | 1 | 0 | 1 | 0 | 1 @@ -13348,7 +13367,7 @@ paragraph, don't worry about it.) Here is a user-defined function (*note User-defined::) that illustrates the use of these functions: - # bits2str --- turn a byte into readable 1's and 0's + # bits2str --- turn a byte into readable ones and zeros function bits2str(bits, data, mask) { @@ -13387,13 +13406,14 @@ This program produces the following output when run: -| lshift(0x99, 2) = 0x264 = 0000001001100100 -| rshift(0x99, 2) = 0x26 = 00100110 - The `bits2str()' function turns a binary number into a string. The -number `1' represents a binary value where the rightmost bit is set to -1. Using this mask, the function repeatedly checks the rightmost bit. -ANDing the mask with the value indicates whether the rightmost bit is 1 -or not. If so, a `"1"' is concatenated onto the front of the string. -Otherwise, a `"0"' is added. The value is then shifted right by one -bit and the loop continues until there are no more 1 bits. + The `bits2str()' function turns a binary number into a string. +Initializing `mask' to one creates a binary value where the rightmost +bit is set to one. Using this mask, the function repeatedly checks the +rightmost bit. ANDing the mask with the value indicates whether the +rightmost bit is one or not. If so, a `"1"' is concatenated onto the +front of the string. Otherwise, a `"0"' is added. The value is then +shifted right by one bit and the loop continues until there are no more +one bits. If the initial value is zero, it returns a simple `"0"'. Otherwise, at the end, it pads the value with zeros to represent multiples of @@ -13406,9 +13426,9 @@ Nondecimal-numbers::), and then demonstrates the results of the ---------- Footnotes ---------- - (1) This example shows that 0's come in on the left side. For + (1) This example shows that zeros come in on the left side. For `gawk', this is always true, but in some languages, it's possible to -have the left side fill with 1's. +have the left side fill with ones. File: gawk.info, Node: Type Functions, Next: I18N Functions, Prev: Bitwise Functions, Up: Built-in @@ -13422,7 +13442,7 @@ traverses every element of an array of arrays (*note Arrays of Arrays::). `isarray(X)' - Return a true value if X is an array. Otherwise return false. + Return a true value if X is an array. Otherwise, return false. `isarray()' is meant for use in two circumstances. The first is when traversing a multidimensional array: you can test if an element is @@ -13469,8 +13489,8 @@ brackets ([ ]): Return the plural form used for NUMBER of the translation of STRING1 and STRING2 in text domain DOMAIN for locale category CATEGORY. STRING1 is the English singular variant of a message, - and STRING2 the English plural variant of the same message. The - default value for DOMAIN is the current value of `TEXTDOMAIN'. + and STRING2 is the English plural variant of the same message. + The default value for DOMAIN is the current value of `TEXTDOMAIN'. The default value for CATEGORY is `"LC_MESSAGES"'. @@ -13499,7 +13519,7 @@ File: gawk.info, Node: Definition Syntax, Next: Function Example, Up: User-de 9.2.1 Function Definition Syntax -------------------------------- - It's entirely fair to say that the `awk' syntax for local variable + It's entirely fair to say that the awk syntax for local variable definitions is appallingly awful. -- Brian Kernighan Definitions of functions can appear anywhere between the rules of an @@ -13529,17 +13549,22 @@ the argument names are used to hold the argument values given in the call. A function cannot have two parameters with the same name, nor may it -have a parameter with the same name as the function itself. In -addition, according to the POSIX standard, function parameters cannot -have the same name as one of the special predefined variables (*note -Built-in Variables::). Not all versions of `awk' enforce this -restriction. +have a parameter with the same name as the function itself. + + CAUTION: According to the POSIX standard, function parameters + cannot have the same name as one of the special predefined + variables (*note Built-in Variables::), nor may a function + parameter have the same name as another function. + + Not all versions of `awk' enforce these restrictions. `gawk' + always enforces the first restriction. With `--posix' (*note + Options::), it also enforces the second restriction. Local variables act like the empty string if referenced where a string value is required, and like zero if referenced where a numeric -value is required. This is the same as regular variables that have -never been assigned a value. (There is more to understand about local -variables; *note Dynamic Typing::.) +value is required. This is the same as the behavior of regular +variables that have never been assigned a value. (There is more to +understand about local variables; *note Dynamic Typing::.) The BODY-OF-FUNCTION consists of `awk' statements. It is the most important part of the definition, because it says what the function @@ -13568,9 +13593,9 @@ function is supposed to be used. variable values hide, or "shadow", any variables of the same names used in the rest of the program. The shadowed variables are not accessible in the function definition, because there is no way to name them while -their names have been taken away for the local variables. All other -variables used in the `awk' program can be referenced or set normally -in the function's body. +their names have been taken away for the arguments and local variables. +All other variables used in the `awk' program can be referenced or set +normally in the function's body. The arguments and local variables last only as long as the function body is executing. Once the body finishes, you can once again access @@ -13623,7 +13648,7 @@ takes a number and prints it in a specific format: printf "%6.3g\n", num } -To illustrate, here is an `awk' rule that uses our `myprint' function: +To illustrate, here is an `awk' rule that uses our `myprint()' function: $3 > 0 { myprint($3) } @@ -13652,13 +13677,13 @@ extra whitespace signifies the start of the local variable list): When working with arrays, it is often necessary to delete all the elements in an array and start over with a new list of elements (*note Delete::). Instead of having to repeat this loop everywhere that you -need to clear out an array, your program can just call `delarray'. +need to clear out an array, your program can just call `delarray()'. (This guarantees portability. The use of `delete ARRAY' to delete the contents of an entire array is a relatively recent(1) addition to the POSIX standard.) The following is an example of a recursive function. It takes a -string as an input parameter and returns the string in backwards order. +string as an input parameter and returns the string in reverse order. Recursive functions must always have a test that stops the recursion. In this case, the recursion terminates when the input string is already empty: @@ -13749,14 +13774,14 @@ File: gawk.info, Node: Variable Scope, Next: Pass By Value/Reference, Prev: C 9.2.3.2 Controlling Variable Scope .................................. -Unlike many languages, there is no way to make a variable local to a +Unlike in many languages, there is no way to make a variable local to a `{' ... `}' block in `awk', but you can make a variable local to a function. It is good practice to do so whenever a variable is needed only in that function. To make a variable local to a function, simply declare the variable as an argument after the actual function arguments (*note Definition -Syntax::). Look at the following example where variable `i' is a +Syntax::). Look at the following example, where variable `i' is a global variable used by both functions `foo()' and `bar()': function bar() @@ -13792,7 +13817,7 @@ variable instance: foo's i=3 top's i=3 - If you want `i' to be local to both `foo()' and `bar()' do as + If you want `i' to be local to both `foo()' and `bar()', do as follows (the extra space before `i' is a coding convention to indicate that `i' is a local variable, not an argument): @@ -13874,7 +13899,7 @@ explicitly whether the arguments are passed "by value" or "by reference". Instead, the passing convention is determined at runtime when the -function is called according to the following rule: if the argument is +function is called, according to the following rule: if the argument is an array variable, then it is passed by reference. Otherwise, the argument is passed by value. @@ -13932,7 +13957,7 @@ function _are_ visible outside that function. stores `"two"' in the second element of `a'. Some `awk' implementations allow you to call a function that has not -been defined. They only report a problem at runtime when the program +been defined. They only report a problem at runtime, when the program actually tries to call the function. For example: BEGIN { @@ -13977,15 +14002,15 @@ undefined, and therefore, unpredictable. In practice, though, all versions of `awk' simply return the null string, which acts like zero if used in a numeric context. - A `return' statement with no value expression is assumed at the end -of every function definition. So if control reaches the end of the -function body, then technically, the function returns an unpredictable + A `return' statement without an EXPRESSION is assumed at the end of +every function definition. So, if control reaches the end of the +function body, then technically the function returns an unpredictable value. In practice, it returns the empty string. `awk' does _not_ warn you if you use the return value of such a function. Sometimes, you want to write a function for what it does, not for what it returns. Such a function corresponds to a `void' function in -C, C++ or Java, or to a `procedure' in Ada. Thus, it may be +C, C++, or Java, or to a `procedure' in Ada. Thus, it may be appropriate to not return any value; simply bear in mind that you should not be using the return value of such a function. @@ -14091,13 +14116,13 @@ you can specify the name of the function to call as a string variable, and then call the function. Let's look at an example. Suppose you have a file with your test scores for the classes you -are taking. The first field is the class name. The following fields -are the functions to call to process the data, up to a "marker" field +are taking, and you wish to get the sum and the average of your test +scores. The first field is the class name. The following fields are +the functions to call to process the data, up to a "marker" field `data:'. Following the marker, to the end of the record, are the various numeric test scores. - Here is the initial file; you wish to get the sum and the average of -your test scores: + Here is the initial file: Biology_101 sum average data: 87.0 92.4 78.5 94.9 Chemistry_305 sum average data: 75.2 98.3 94.7 88.2 @@ -14155,9 +14180,9 @@ using indirect function calls: return ret } - These two functions expect to work on fields; thus the parameters + These two functions expect to work on fields; thus, the parameters `first' and `last' indicate where in the fields to start and end. -Otherwise they perform the expected computations and are not unusual: +Otherwise, they perform the expected computations and are not unusual: # For each record, print the class name and the requested statistics { @@ -14210,18 +14235,19 @@ to force it to be a string value.) may think at first. The C and C++ languages provide "function pointers," which are a mechanism for calling a function chosen at runtime. One of the most well-known uses of this ability is the C -`qsort()' function, which sorts an array using the famous "quick sort" +`qsort()' function, which sorts an array using the famous "quicksort" algorithm (see the Wikipedia article -(http://en.wikipedia.org/wiki/Quick_sort) for more information). To -use this function, you supply a pointer to a comparison function. This +(http://en.wikipedia.org/wiki/Quicksort) for more information). To use +this function, you supply a pointer to a comparison function. This mechanism allows you to sort arbitrary data in an arbitrary fashion. We can do something similar using `gawk', like this: # quicksort.awk --- Quicksort algorithm, with user-supplied # comparison function - # quicksort --- C.A.R. Hoare's quick sort algorithm. See Wikipedia - # or almost any algorithms or computer science text + + # quicksort --- C.A.R. Hoare's quicksort algorithm. See Wikipedia + # or almost any algorithms or computer science text. function quicksort(data, left, right, less_than, i, last) { @@ -14250,7 +14276,7 @@ mechanism allows you to sort arbitrary data in an arbitrary fashion. The `quicksort()' function receives the `data' array, the starting and ending indices to sort (`left' and `right'), and the name of a function that performs a "less than" comparison. It then implements -the quick sort algorithm. +the quicksort algorithm. To make use of the sorting function, we return to our previous example. The first thing to do is write some comparison functions: @@ -14490,7 +14516,7 @@ File: gawk.info, Node: Library Functions, Next: Sample Programs, Prev: Functi *note User-defined::, describes how to write your own `awk' functions. Writing functions is important, because it allows you to encapsulate algorithms and program tasks in a single place. It simplifies -programming, making program development more manageable, and making +programming, making program development more manageable and making programs more readable. In their seminal 1976 book, `Software Tools',(1) Brian Kernighan and @@ -14595,7 +14621,7 @@ often use variable names like these for their own purposes. The example programs shown in this major node all start the names of their private variables with an underscore (`_'). Users generally don't use leading underscores in their variable names, so this -convention immediately decreases the chances that the variable name +convention immediately decreases the chances that the variable names will be accidentally shared with the user's program. In addition, several of the library functions use a prefix that helps @@ -14608,7 +14634,7 @@ for private function names.(1) As a final note on variable naming, if a function makes global variables available for use by a main program, it is a good convention -to start that variable's name with a capital letter--for example, +to start those variables' names with a capital letter--for example, `getopt()''s `Opterr' and `Optind' variables (*note Getopt Function::). The leading capital letter indicates that it is global, while the fact that the variable name is not all capital letters indicates that the @@ -14616,7 +14642,7 @@ variable is not one of `awk''s predefined variables, such as `FS'. It is also important that _all_ variables in library functions that do not need to save state are, in fact, declared local.(2) If this is -not done, the variable could accidentally be used in the user's +not done, the variables could accidentally be used in the user's program, leading to bugs that are very difficult to track down: function lib_func(x, y, l1, l2) @@ -14794,7 +14820,7 @@ for use in printing the diagnostic message. This is not possible in `awk', so this `assert()' function also requires a string version of the condition that is being tested. Following is the function: - # assert --- assert that a condition is true. Otherwise exit. + # assert --- assert that a condition is true. Otherwise, exit. function assert(condition, string) { @@ -14815,7 +14841,7 @@ the condition that is being tested. Following is the function: false, it prints a message to standard error, using the `string' parameter to describe the failed condition. It then sets the variable `_assert_exit' to one and executes the `exit' statement. The `exit' -statement jumps to the `END' rule. If the `END' rules finds +statement jumps to the `END' rule. If the `END' rule finds `_assert_exit' to be true, it exits immediately. The purpose of the test in the `END' rule is to keep any other `END' @@ -15030,9 +15056,9 @@ the strings in an array into one long string. The following function, `join()', accomplishes this task. It is used later in several of the application programs (*note Sample Programs::). - Good function design is important; this function needs to be general -but it should also have a reasonable default behavior. It is called -with an array as well as the beginning and ending indices of the + Good function design is important; this function needs to be +general, but it should also have a reasonable default behavior. It is +called with an array as well as the beginning and ending indices of the elements in the array to be merged. This assumes that the array indices are numeric--a reasonable assumption, as the array was likely created with `split()' (*note String Functions::): @@ -15151,7 +15177,7 @@ optional timestamp value to use instead of the current time. File: gawk.info, Node: Readfile Function, Next: Shell Quoting, Prev: Getlocaltime Function, Up: General Functions -10.2.8 Reading a Whole File At Once +10.2.8 Reading a Whole File at Once ----------------------------------- Often, it is convenient to have the entire contents of a file available @@ -15193,13 +15219,13 @@ reads the entire contents of the named file in one shot: It works by setting `RS' to `^$', a regular expression that will never match if the file has contents. `gawk' reads data from the file -into `tmp' attempting to match `RS'. The match fails after each read, +into `tmp', attempting to match `RS'. The match fails after each read, but fails quickly, such that `gawk' fills `tmp' with the entire contents of the file. (*Note Records::, for information on `RT' and `RS'.) In the case that `file' is empty, the return value is the null -string. Thus calling code may use something like: +string. Thus, calling code may use something like: contents = readfile("/some/path") if (length(contents) == 0) @@ -15289,8 +15315,9 @@ File: gawk.info, Node: Filetrans Function, Next: Rewind Function, Up: Data Fi The `BEGIN' and `END' rules are each executed exactly once, at the beginning and end of your `awk' program, respectively (*note BEGIN/END::). We (the `gawk' authors) once had a user who mistakenly -thought that the `BEGIN' rule is executed at the beginning of each data -file and the `END' rule is executed at the end of each data file. +thought that the `BEGIN' rules were executed at the beginning of each +data file and the `END' rules were executed at the end of each data +file. When informed that this was not the case, the user requested that we add new special patterns to `gawk', named `BEGIN_FILE' and `END_FILE', @@ -15324,7 +15351,7 @@ does so _portably_; this works with any implementation of `awk': This file must be loaded before the user's "main" program, so that the rule it supplies is executed first. - This rule relies on `awk''s `FILENAME' variable that automatically + This rule relies on `awk''s `FILENAME' variable, which automatically changes for each new data file. The current file name is saved in a private variable, `_oldfilename'. If `FILENAME' does not equal `_oldfilename', then a new data file is being processed and it is @@ -15339,7 +15366,7 @@ correctly even for the first data file. The program also supplies an `END' rule to do the final processing for the last file. Because this `END' rule comes before any `END' rules supplied in the "main" program, `endfile()' is called first. Once -again the value of multiple `BEGIN' and `END' rules should be clear. +again, the value of multiple `BEGIN' and `END' rules should be clear. If the same data file occurs twice in a row on the command line, then `endfile()' and `beginfile()' are not executed at the end of the first @@ -15366,7 +15393,7 @@ how it simplifies writing the main program. You are probably wondering, if `beginfile()' and `endfile()' functions can do the job, why does `gawk' have `BEGINFILE' and -`ENDFILE' patterns (*note BEGINFILE/ENDFILE::)? +`ENDFILE' patterns? Good question. Normally, if `awk' cannot open a file, this causes an immediate fatal error. In this case, there is no way for a @@ -15374,7 +15401,8 @@ user-defined function to deal with the problem, as the mechanism for calling it relies on the file being open and at the first record. Thus, the main reason for `BEGINFILE' is to give you a "hook" to catch files that cannot be processed. `ENDFILE' exists for symmetry, and because -it provides an easy way to do per-file cleanup processing. +it provides an easy way to do per-file cleanup processing. For more +information, refer to *note BEGINFILE/ENDFILE::. File: gawk.info, Node: Rewind Function, Next: File Checking, Prev: Filetrans Function, Up: Data File Management @@ -15382,15 +15410,14 @@ File: gawk.info, Node: Rewind Function, Next: File Checking, Prev: Filetrans 10.3.2 Rereading the Current File --------------------------------- -Another request for a new built-in function was for a `rewind()' -function that would make it possible to reread the current file. The -requesting user didn't want to have to use `getline' (*note Getline::) -inside a loop. +Another request for a new built-in function was for a function that +would make it possible to reread the current file. The requesting user +didn't want to have to use `getline' (*note Getline::) inside a loop. However, as long as you are not in the `END' rule, it is quite easy to arrange to immediately close the current input file and then start -over with it from the top. For lack of a better name, we'll call it -`rewind()': +over with it from the top. For lack of a better name, we'll call the +function `rewind()': # rewind.awk --- rewind the current file and start over @@ -15448,7 +15475,7 @@ longer in the list). See also *note ARGC and ARGV::. Because `awk' variable names only allow the English letters, the regular expression check purposely does not use character classes such -as `[:alpha:]' and `[:alnum:]' (*note Bracket Expressions::) +as `[:alpha:]' and `[:alnum:]' (*note Bracket Expressions::). ---------- Footnotes ---------- @@ -15459,14 +15486,14 @@ opened. However, the code here provides a portable solution. File: gawk.info, Node: Empty Files, Next: Ignoring Assigns, Prev: File Checking, Up: Data File Management -10.3.4 Checking for Zero-length Files +10.3.4 Checking for Zero-Length Files ------------------------------------- All known `awk' implementations silently skip over zero-length files. This is a by-product of `awk''s implicit read-a-record-and-match-against-the-rules loop: when `awk' tries to -read a record from an empty file, it immediately receives an end of -file indication, closes the file, and proceeds on to the next +read a record from an empty file, it immediately receives an +end-of-file indication, closes the file, and proceeds on to the next command-line data file, _without_ executing any user-level `awk' program code. @@ -15516,7 +15543,7 @@ File: gawk.info, Node: Ignoring Assigns, Prev: Empty Files, Up: Data File Man Occasionally, you might not want `awk' to process command-line variable assignments (*note Assignment Options::). In particular, if you have a file name that contains an `=' character, `awk' treats the file name as -an assignment, and does not process it. +an assignment and does not process it. Some users have suggested an additional command-line option for `gawk' to disable command-line assignments. However, some simple @@ -15806,8 +15833,8 @@ which is in `ARGV[0]': } } - The rest of the `BEGIN' rule is a simple test program. Here is the -result of two sample runs of the test program: + The rest of the `BEGIN' rule is a simple test program. Here are the +results of two sample runs of the test program: $ awk -f getopt.awk -v _getopt_test=1 -- -a -cbARG bax -x -| c = <a>, Optarg = <> @@ -15853,10 +15880,10 @@ File: gawk.info, Node: Passwd Functions, Next: Group Functions, Prev: Getopt ============================== The `PROCINFO' array (*note Built-in Variables::) provides access to -the current user's real and effective user and group ID numbers, and if -available, the user's supplementary group set. However, because these -are numbers, they do not provide very useful information to the average -user. There needs to be some way to find the user information +the current user's real and effective user and group ID numbers, and, +if available, the user's supplementary group set. However, because +these are numbers, they do not provide very useful information to the +average user. There needs to be some way to find the user information associated with the user and group ID numbers. This minor node presents a suite of functions for retrieving information from the user database. *Note Group Functions::, for a similar suite that retrieves @@ -15867,7 +15894,7 @@ kept. Instead, it provides the `<pwd.h>' header file and several C language subroutines for obtaining user information. The primary function is `getpwent()', for "get password entry." The "password" comes from the original user database file, `/etc/passwd', which stores -user information, along with the encrypted passwords (hence the name). +user information along with the encrypted passwords (hence the name). Although an `awk' program could simply read `/etc/passwd' directly, this file may not contain complete information about the system's set @@ -15915,7 +15942,7 @@ Encrypted password User-ID The user's numeric user ID number. (On some systems, it's a C - `long', and not an `int'. Thus we cast it to `long' for all + `long', and not an `int'. Thus, we cast it to `long' for all cases.) Group-ID @@ -16014,8 +16041,8 @@ or on some other `awk' implementation. `PROCINFO["FS"]', is similar. The main part of the function uses a loop to read database lines, -split the line into fields, and then store the line into each array as -necessary. When the loop is done, `_pw_init()' cleans up by closing +split the lines into fields, and then store the lines into each array +as necessary. When the loop is done, `_pw_init()' cleans up by closing the pipeline, setting `_pw_inited' to one, and restoring `FS' (and `FIELDWIDTHS' or `FPAT' if necessary), `RS', and `$0'. The use of `_pw_count' is explained shortly. @@ -16143,7 +16170,7 @@ Group Password Group ID Number The group's numeric group ID number; the association of name to number must be unique within the file. (On some systems it's a C - `long', and not an `int'. Thus we cast it to `long' for all + `long', and not an `int'. Thus, we cast it to `long' for all cases.) Group Member List @@ -16233,29 +16260,30 @@ to ensure that the database is scanned no more than once. The `_gr_init()' function first saves `FS', `RS', and `$0', and then sets `FS' and `RS' to the correct values for scanning the group information. It also takes care to note whether `FIELDWIDTHS' or `FPAT' is being -used, and to restore the appropriate field splitting mechanism. +used, and to restore the appropriate field-splitting mechanism. - The group information is stored is several associative arrays. The + The group information is stored in several associative arrays. The arrays are indexed by group name (`_gr_byname'), by group ID number (`_gr_bygid'), and by position in the database (`_gr_bycount'). There is an additional array indexed by username (`_gr_groupsbyuser'), which is a space-separated list of groups to which each user belongs. - Unlike the user database, it is possible to have multiple records in -the database for the same group. This is common when a group has a + Unlike in the user database, it is possible to have multiple records +in the database for the same group. This is common when a group has a large number of members. A pair of such entries might look like the following: - tvpeople:*:101:johny,jay,arsenio + tvpeople:*:101:johnny,jay,arsenio tvpeople:*:101:david,conan,tom,joan For this reason, `_gr_init()' looks to see if a group name or group -ID number is already seen. If it is, the usernames are simply +ID number is already seen. If so, the usernames are simply concatenated onto the previous list of users.(1) Finally, `_gr_init()' closes the pipeline to `grcat', restores `FS' -(and `FIELDWIDTHS' or `FPAT' if necessary), `RS', and `$0', initializes -`_gr_count' to zero (it is used later), and makes `_gr_inited' nonzero. +(and `FIELDWIDTHS' or `FPAT', if necessary), `RS', and `$0', +initializes `_gr_count' to zero (it is used later), and makes +`_gr_inited' nonzero. The `getgrnam()' function takes a group name as its argument, and if that group exists, it is returned. Otherwise, it relies on the array @@ -16318,9 +16346,9 @@ very simple, relying on `awk''s associative arrays to do work. ---------- Footnotes ---------- - (1) There is actually a subtle problem with the code just presented. -Suppose that the first time there were no names. This code adds the -names with a leading comma. It also doesn't check that there is a `$4'. + (1) There is a subtle problem with the code just presented. Suppose +that the first time there were no names. This code adds the names with +a leading comma. It also doesn't check that there is a `$4'. File: gawk.info, Node: Walking Arrays, Next: Library Functions Summary, Prev: Group Functions, Up: Library Functions @@ -16329,11 +16357,11 @@ File: gawk.info, Node: Walking Arrays, Next: Library Functions Summary, Prev: ================================ *note Arrays of Arrays::, described how `gawk' provides arrays of -arrays. In particular, any element of an array may be either a scalar, +arrays. In particular, any element of an array may be either a scalar or another array. The `isarray()' function (*note Type Functions::) lets you distinguish an array from a scalar. The following function, -`walk_array()', recursively traverses an array, printing each element's -indices and value. You call it with the array and a string +`walk_array()', recursively traverses an array, printing the element +indices and values. You call it with the array and a string representing the name of the array: function walk_array(arr, name, i) @@ -16390,24 +16418,24 @@ File: gawk.info, Node: Library Functions Summary, Next: Library Exercises, Pr * The functions presented here fit into the following categories: General problems - Number-to-string conversion, assertions, rounding, random - number generation, converting characters to numbers, joining - strings, getting easily usable time-of-day information, and - reading a whole file in one shot. + Number-to-string conversion, testing assertions, rounding, + random number generation, converting characters to numbers, + joining strings, getting easily usable time-of-day + information, and reading a whole file in one shot Managing data files Noting data file boundaries, rereading the current file, checking for readable files, checking for zero-length files, - and treating assignments as file names. + and treating assignments as file names Processing command-line options - An `awk' version of the standard C `getopt()' function. + An `awk' version of the standard C `getopt()' function Reading the user and group databases - Two sets of routines that parallel the C library versions. + Two sets of routines that parallel the C library versions Traversing arrays of arrays - A simple function to traverse an array of arrays to any depth. + A simple function to traverse an array of arrays to any depth @@ -16502,7 +16530,7 @@ you. to replace the installed versions on your system. Nor may all of these programs be fully compliant with the most recent POSIX standard. This is not a problem; their purpose is to illustrate `awk' language -programming for "real world" tasks. +programming for "real-world" tasks. The programs are presented in alphabetical order. @@ -16528,7 +16556,7 @@ separated by TABs by default, but you may supply a command-line option to change the field "delimiter" (i.e., the field-separator character). `cut''s definition of fields is less general than `awk''s. - A common use of `cut' might be to pull out just the login name of + A common use of `cut' might be to pull out just the login names of logged-on users from the output of `who'. For example, the following pipeline generates a sorted, unique list of the logged-on users: @@ -16937,7 +16965,7 @@ unsuccessful match. If the line does not match, the `next' statement just moves on to the next record. A number of additional tests are made, but they are only done if we -are not counting lines. First, if the user only wants exit status +are not counting lines. First, if the user only wants the exit status (`no_print' is true), then it is enough to know that _one_ line in this file matched, and we can skip on to the next file with `nextfile'. Similarly, if we are only printing file names, we can print the file @@ -16971,7 +16999,7 @@ line is printed, with a leading file name and colon if necessary: } The `END' rule takes care of producing the correct exit status. If -there are no matches, the exit status is one; otherwise it is zero: +there are no matches, the exit status is one; otherwise, it is zero: END { exit (total == 0) @@ -17013,7 +17041,8 @@ a more palatable output than just individual numbers. Here is a simple version of `id' written in `awk'. It uses the user database library functions (*note Passwd Functions::) and the group -database library functions (*note Group Functions::): +database library functions (*note Group Functions::) from *note Library +Functions::. The program is fairly straightforward. All the work is done in the `BEGIN' rule. The user and group ID numbers are obtained from @@ -17110,8 +17139,8 @@ is as follows:(1) By default, the output files are named `xaa', `xab', and so on. Each file has 1,000 lines in it, with the likely exception of the last file. To change the number of lines in each file, supply a number on the -command line preceded with a minus (e.g., `-500' for files with 500 -lines in them instead of 1,000). To change the name of the output +command line preceded with a minus sign (e.g., `-500' for files with +500 lines in them instead of 1,000). To change the names of the output files to something like `myfileaa', `myfileab', and so on, supply an additional argument that specifies the file name prefix. @@ -17748,7 +17777,7 @@ checking and setting of defaults: the delay, the count, and the message to print. If the user supplied a message without the ASCII BEL character (known as the "alert" character, `"\a"'), then it is added to the message. (On many systems, printing the ASCII BEL generates an -audible alert. Thus when the alarm goes off, the system calls attention +audible alert. Thus, when the alarm goes off, the system calls attention to itself in case the user is not looking at the computer.) Just for a change, this program uses a `switch' statement (*note Switch Statement::), but the processing could be done with a series of @@ -17880,7 +17909,7 @@ the "from" list. Once upon a time, a user proposed adding a transliteration function to `gawk'. The following program was written to prove that character transliteration could be done with a user-level function. This program -is not as complete as the system `tr' utility but it does most of the +is not as complete as the system `tr' utility, but it does most of the job. The `translate' program was written long before `gawk' acquired the @@ -17890,13 +17919,13 @@ and `gsub()' built-in functions (*note String Functions::). There are two functions. The first, `stranslate()', takes three arguments: `from' - A list of characters from which to translate. + A list of characters from which to translate `to' - A list of characters to which to translate. + A list of characters to which to translate `target' - The string on which to do the translation. + The string on which to do the translation Associative arrays make the translation part fairly easy. `t_ar' holds the "to" characters, indexed by the "from" characters. Then a @@ -17904,7 +17933,7 @@ simple loop goes through `from', one character at a time. For each character in `from', if the character appears in `target', it is replaced with the corresponding `to' character. - The `translate()' function calls `stranslate()' using `$0' as the + The `translate()' function calls `stranslate()', using `$0' as the target. The main program sets two global variables, `FROM' and `TO', from the command line, and then changes `ARGV' so that `awk' reads from the standard input. @@ -17913,7 +17942,7 @@ the standard input. record: # translate.awk --- do tr-like stuff - # Bugs: does not handle things like: tr A-Z a-z, it has + # Bugs: does not handle things like tr A-Z a-z; it has # to be spelled out. However, if `to' is shorter than `from', # the last character in `to' is used for the rest of `from'. @@ -17991,13 +18020,13 @@ File: gawk.info, Node: Labels Program, Next: Word Sorting, Prev: Translate Pr 11.3.4 Printing Mailing Labels ------------------------------ -Here is a "real world"(1) program. This script reads lists of names and +Here is a "real-world"(1) program. This script reads lists of names and addresses and generates mailing labels. Each page of labels has 20 labels on it, two across and 10 down. The addresses are guaranteed to be no more than five lines of data. Each address is separated from the next by a blank line. - The basic idea is to read 20 labels worth of data. Each line of + The basic idea is to read 20 labels' worth of data. Each line of each label is stored in the `line' array. The single rule takes care of filling the `line' array and printing the page when 20 labels have been read. @@ -18009,13 +18038,13 @@ splits records at blank lines (*note Records::). It sets `MAXLINES' to Most of the work is done in the `printpage()' function. The label lines are stored sequentially in the `line' array. But they have to -print horizontally; `line[1]' next to `line[6]', `line[2]' next to +print horizontally: `line[1]' next to `line[6]', `line[2]' next to `line[7]', and so on. Two loops accomplish this. The outer loop, controlled by `i', steps through every 10 lines of data; this is each row of labels. The inner loop, controlled by `j', goes through the -lines within the row. As `j' goes from 0 to 4, `i+j' is the `j'-th -line in the row, and `i+j+5' is the entry next to it. The output ends -up looking something like this: +lines within the row. As `j' goes from 0 to 4, `i+j' is the `j'th line +in the row, and `i+j+5' is the entry next to it. The output ends up +looking something like this: line 1 line 6 line 2 line 7 @@ -18118,8 +18147,8 @@ a useful format. printf "%s\t%d\n", word, freq[word] } - The program relies on `awk''s default field splitting mechanism to -break each line up into "words," and uses an associative array named + The program relies on `awk''s default field-splitting mechanism to +break each line up into "words" and uses an associative array named `freq', indexed by each word, to count the number of times the word occurs. In the `END' rule, it prints the counts. @@ -18205,7 +18234,7 @@ File: gawk.info, Node: History Sorting, Next: Extract Program, Prev: Word Sor 11.3.6 Removing Duplicates from Unsorted Text --------------------------------------------- -The `uniq' program (*note Uniq Program::), removes duplicate lines from +The `uniq' program (*note Uniq Program::) removes duplicate lines from _sorted_ data. Suppose, however, you need to remove duplicate lines from a data @@ -18258,7 +18287,7 @@ hand. Here we present a program that can extract parts of a Texinfo input file into separate files. This Info file is written in Texinfo -(http://www.gnu.org/software/texinfo/), the GNU project's document +(http://www.gnu.org/software/texinfo/), the GNU Project's document formatting language. A single Texinfo source file can be used to produce both printed documentation, with TeX, and online documentation. (The Texinfo language is described fully, starting with *note @@ -18299,7 +18328,7 @@ them in a standard directory where `gawk' can find them. The Texinfo file looks something like this: ... - This program has a @code{BEGIN} rule, + This program has a @code{BEGIN} rule that prints a nice message: @example @@ -18324,7 +18353,7 @@ upper- and lowercase letters in the directives won't matter. given (`NF' is at least three) and also checking that the command exits with a zero exit status, signifying OK: - # extract.awk --- extract files and run programs from texinfo files + # extract.awk --- extract files and run programs from Texinfo files BEGIN { IGNORECASE = 1 } @@ -18351,11 +18380,11 @@ The variable `e' is used so that the rule fits nicely on the screen. file name is given in the directive. If the file named is not the current file, then the current file is closed. Keeping the current file open until a new file is encountered allows the use of the `>' -redirection for printing the contents, keeping open file management +redirection for printing the contents, keeping open-file management simple. The `for' loop does the work. It reads lines using `getline' (*note -Getline::). For an unexpected end of file, it calls the +Getline::). For an unexpected end-of-file, it calls the `unexpected_eof()' function. If the line is an "endfile" line, then it breaks out of the loop. If the line is an `@group' or `@end group' line, then it ignores it and goes on to the next line. Similarly, @@ -18445,10 +18474,10 @@ File: gawk.info, Node: Simple Sed, Next: Igawk Program, Prev: Extract Program 11.3.8 A Simple Stream Editor ----------------------------- -The `sed' utility is a stream editor, a program that reads a stream of -data, makes changes to it, and passes it on. It is often used to make -global changes to a large file or to a stream of data generated by a -pipeline of commands. Although `sed' is a complicated program in its +The `sed' utility is a "stream editor", a program that reads a stream +of data, makes changes to it, and passes it on. It is often used to +make global changes to a large file or to a stream of data generated by +a pipeline of commands. Although `sed' is a complicated program in its own right, its most common use is to perform global substitutions in the middle of a pipeline: @@ -18562,7 +18591,7 @@ include a library function twice. `igawk' should behave just like `gawk' externally. This means it should accept all of `gawk''s command-line arguments, including the -ability to have multiple source files specified via `-f', and the +ability to have multiple source files specified via `-f' and the ability to mix command-line and library source files. The program is written using the POSIX Shell (`sh') command @@ -18592,8 +18621,8 @@ language.(1) It works as follows: file names). This program uses shell variables extensively: for storing -command-line arguments, the text of the `awk' program that will expand -the user's program, for the user's original program, and for the +command-line arguments and the text of the `awk' program that will +expand the user's program, for the user's original program, and for the expanded program. Doing so removes some potential problems that might arise were we to use temporary files instead, at the cost of making the script somewhat more complicated. @@ -18851,7 +18880,7 @@ It's done in these steps: The last step is to call `gawk' with the expanded program, along with the original options and command-line arguments that the user -supplied. +supplied: eval gawk $opts -- '"$processed_program"' '"$@"' @@ -18914,15 +18943,15 @@ One word is an anagram of another if both words contain the same letters Column 2, Problem C, of Jon Bentley's `Programming Pearls', Second Edition, presents an elegant algorithm. The idea is to give words that are anagrams a common signature, sort all the words together by their -signature, and then print them. Dr. Bentley observes that taking the -letters in each word and sorting them produces that common signature. +signatures, and then print them. Dr. Bentley observes that taking the +letters in each word and sorting them produces those common signatures. The following program uses arrays of arrays to bring together words with the same signature and array sorting to print the words in sorted order: - # anagram.awk --- An implementation of the anagram finding algorithm - # from Jon Bentley's "Programming Pearls", 2nd edition. + # anagram.awk --- An implementation of the anagram-finding algorithm + # from Jon Bentley's "Programming Pearls," 2nd edition. # Addison Wesley, 2000, ISBN 0-201-65788-0. # Column 2, Problem C, section 2.8, pp 18-20. @@ -18942,7 +18971,7 @@ signature; the second dimension is the word itself: apart into individual letters, sorts the letters, and then joins them back together: - # word2key --- split word apart into letters, sort, joining back together + # word2key --- split word apart into letters, sort, and join back together function word2key(word, a, i, n, result) { @@ -19040,12 +19069,13 @@ File: gawk.info, Node: Programs Summary, Next: Programs Exercises, Prev: Misc characters. The ability to use `split()' with the empty string as the separator can considerably simplify such tasks. - * The library functions from *note Library Functions::, proved their - usefulness for a number of real (if small) programs. + * The examples here demonstrate the usefulness of the library + functions from *note Library Functions::, for a number of real (if + small) programs. * Besides reinventing POSIX wheels, other programs solved a - selection of interesting problems, such as finding duplicates - words in text, printing mailing labels, and finding anagrams. + selection of interesting problems, such as finding duplicate words + in text, printing mailing labels, and finding anagrams. @@ -19162,16 +19192,16 @@ File: gawk.info, Node: Advanced Features, Next: Internationalization, Prev: S This major node discusses advanced features in `gawk'. It's a bit of a "grab bag" of items that are otherwise unrelated to each other. -First, a command-line option allows `gawk' to recognize nondecimal -numbers in input data, not just in `awk' programs. Then, `gawk''s -special features for sorting arrays are presented. Next, two-way I/O, -discussed briefly in earlier parts of this Info file, is described in -full detail, along with the basics of TCP/IP networking. Finally, -`gawk' can "profile" an `awk' program, making it possible to tune it -for performance. +First, we look at a command-line option that allows `gawk' to recognize +nondecimal numbers in input data, not just in `awk' programs. Then, +`gawk''s special features for sorting arrays are presented. Next, +two-way I/O, discussed briefly in earlier parts of this Info file, is +described in full detail, along with the basics of TCP/IP networking. +Finally, we see how `gawk' can "profile" an `awk' program, making it +possible to tune it for performance. - A number of advanced features require separate major nodes of their -own: + Additional advanced features are discussed in separate major nodes +of their own: * *note Internationalization::, discusses how to internationalize your `awk' programs, so that they can speak multiple national @@ -19245,7 +19275,7 @@ File: gawk.info, Node: Array Sorting, Next: Two-way I/O, Prev: Nondecimal Dat 12.2 Controlling Array Traversal and Array Sorting ================================================== -`gawk' lets you control the order in which a `for (i in array)' loop +`gawk' lets you control the order in which a `for (INDX in ARRAY)' loop traverses an array. In addition, two built-in functions, `asort()' and `asorti()', let @@ -19264,9 +19294,9 @@ File: gawk.info, Node: Controlling Array Traversal, Next: Array Sorting Functi 12.2.1 Controlling Array Traversal ---------------------------------- -By default, the order in which a `for (i in array)' loop scans an array -is not defined; it is generally based upon the internal implementation -of arrays inside `awk'. +By default, the order in which a `for (INDX in ARRAY)' loop scans an +array is not defined; it is generally based upon the internal +implementation of arrays inside `awk'. Often, though, it is desirable to be able to loop over the elements in a particular order that you, the programmer, choose. `gawk' lets @@ -19288,21 +19318,22 @@ arguments: RETURN < 0; 0; OR > 0 } - Here, I1 and I2 are the indices, and V1 and V2 are the corresponding -values of the two elements being compared. Either V1 or V2, or both, -can be arrays if the array being traversed contains subarrays as values. -(*Note Arrays of Arrays::, for more information about subarrays.) The -three possible return values are interpreted as follows: + Here, `i1' and `i2' are the indices, and `v1' and `v2' are the +corresponding values of the two elements being compared. Either `v1' +or `v2', or both, can be arrays if the array being traversed contains +subarrays as values. (*Note Arrays of Arrays::, for more information +about subarrays.) The three possible return values are interpreted as +follows: `comp_func(i1, v1, i2, v2) < 0' - Index I1 comes before index I2 during loop traversal. + Index `i1' comes before index `i2' during loop traversal. `comp_func(i1, v1, i2, v2) == 0' - Indices I1 and I2 come together but the relative order with + Indices `i1' and `i2' come together, but the relative order with respect to each other is undefined. `comp_func(i1, v1, i2, v2) > 0' - Index I1 comes after index I2 during loop traversal. + Index `i1' comes after index `i2' during loop traversal. Our first comparison function can be used to scan an array in numerical order of the indices: @@ -19445,7 +19476,7 @@ elements compare equal. This is usually not a problem, but letting the tied elements come out in arbitrary order can be an issue, especially when comparing item values. The partial ordering of the equal elements may change the next time the array is traversed, if other elements are -added or removed from the array. One way to resolve ties when +added to or removed from the array. One way to resolve ties when comparing elements with otherwise equal values is to include the indices in the comparison rules. Note that doing this may make the loop traversal less efficient, so consider it only if necessary. The @@ -19479,14 +19510,14 @@ lowercase letters as equivalent or distinct. Another point to keep in mind is that in the case of subarrays, the element values can themselves be arrays; a production comparison -function should use the `isarray()' function (*note Type Functions::), +function should use the `isarray()' function (*note Type Functions::) to check for this, and choose a defined sorting order for subarrays. All sorting based on `PROCINFO["sorted_in"]' is disabled in POSIX mode, because the `PROCINFO' array is not special in that case. As a side note, sorting the array indices before traversing the -array has been reported to add 15% to 20% overhead to the execution +array has been reported to add a 15% to 20% overhead to the execution time of `awk' programs. For this reason, sorted array traversal is not the default. @@ -19535,8 +19566,8 @@ array is not affected. Often, what's needed is to sort on the values of the _indices_ instead of the values of the elements. To do that, use the `asorti()' function. The interface and behavior are identical to that of -`asort()', except that the index values are used for sorting, and -become the values of the result array: +`asort()', except that the index values are used for sorting and become +the values of the result array: { source[$0] = some_func($0) } @@ -19568,8 +19599,8 @@ chooses_, taking into account just the indices, just the values, or both. This is extremely powerful. Once the array is sorted, `asort()' takes the _values_ in their -final order, and uses them to fill in the result array, whereas -`asorti()' takes the _indices_ in their final order, and uses them to +final order and uses them to fill in the result array, whereas +`asorti()' takes the _indices_ in their final order and uses them to fill in the result array. NOTE: Copying array indices and elements isn't expensive in terms @@ -19767,7 +19798,7 @@ REMOTE-PORT name. NOTE: Failure in opening a two-way socket will result in a - non-fatal error being returned to the calling code. The value of + nonfatal error being returned to the calling code. The value of `ERRNO' indicates the error (*note Auto-set::). Consider the following very simple example: @@ -19848,8 +19879,8 @@ First, the `awk' program: junk Here is the `awkprof.out' that results from running the `gawk' -profiler on this program and data. (This example also illustrates that -`awk' programmers sometimes get up very early in the morning to work.) +profiler on this program and data (this example also illustrates that +`awk' programmers sometimes get up very early in the morning to work): # gawk profile, created Mon Sep 29 05:16:21 2014 @@ -19902,7 +19933,7 @@ profiler on this program and data. (This example also illustrates that output. They are as follows: * The program is printed in the order `BEGIN' rules, `BEGINFILE' - rules, pattern/action rules, `ENDFILE' rules, `END' rules and + rules, pattern-action rules, `ENDFILE' rules, `END' rules, and functions, listed alphabetically. Multiple `BEGIN' and `END' rules retain their separate identities, as do multiple `BEGINFILE' and `ENDFILE' rules. @@ -19947,13 +19978,13 @@ output. They are as follows: scalar, it gets parenthesized. * `gawk' supplies leading comments in front of the `BEGIN' and `END' - rules, the `BEGINFILE' and `ENDFILE' rules, the pattern/action + rules, the `BEGINFILE' and `ENDFILE' rules, the pattern-action rules, and the functions. The profiled version of your program may not look exactly like what you typed when you wrote it. This is because `gawk' creates the -profiled version by "pretty printing" its internal representation of +profiled version by "pretty-printing" its internal representation of the program. The advantage to this is that `gawk' can produce a standard representation. Also, things such as: @@ -20003,15 +20034,15 @@ output profile file. produces the profile and the function call trace and then exits. When `gawk' runs on MS-Windows systems, it uses the `INT' and `QUIT' -signals for producing the profile and, in the case of the `INT' signal, +signals for producing the profile, and in the case of the `INT' signal, `gawk' exits. This is because these systems don't support the `kill' command, so the only signals you can deliver to a program are those generated by the keyboard. The `INT' signal is generated by the -`Ctrl-<C>' or `Ctrl-<BREAK>' key, while the `QUIT' signal is generated -by the `Ctrl-<\>' key. +`Ctrl-c' or `Ctrl-BREAK' key, while the `QUIT' signal is generated by +the `Ctrl-\' key. Finally, `gawk' also accepts another option, `--pretty-print'. When -called this way, `gawk' "pretty prints" the program into `awkprof.out', +called this way, `gawk' "pretty-prints" the program into `awkprof.out', without any execution counts. NOTE: Once upon a time, the `--pretty-print' option would also run @@ -20063,7 +20094,7 @@ File: gawk.info, Node: Advanced Features Summary, Prev: Profiling, Up: Advanc two-way communications. * By using special file names with the `|&' operator, you can open a - TCP/IP (or UDP/IP) connection to remote hosts in the Internet. + TCP/IP (or UDP/IP) connection to remote hosts on the Internet. `gawk' supports both IPv4 and IPv6. * You can generate statement count profiles of your program. This @@ -20072,7 +20103,7 @@ File: gawk.info, Node: Advanced Features Summary, Prev: Profiling, Up: Advanc `USR1' signal while profiling causes `gawk' to dump the profile and keep going, including a function call stack. - * You can also just "pretty print" the program. This currently also + * You can also just "pretty-print" the program. This currently also runs the program, but that will change in the next major release. @@ -20116,7 +20147,7 @@ File: gawk.info, Node: I18N and L10N, Next: Explaining gettext, Up: Internati "Internationalization" means writing (or modifying) a program once, in such a way that it can use multiple languages without requiring further -source-code changes. "Localization" means providing the data necessary +source code changes. "Localization" means providing the data necessary for an internationalized program to work in a particular language. Most typically, these terms refer to features such as the language used for printing error messages, the language used to read responses, and @@ -20130,7 +20161,7 @@ File: gawk.info, Node: Explaining gettext, Next: Programmer i18n, Prev: I18N ================== `gawk' uses GNU `gettext' to provide its internationalization features. -The facilities in GNU `gettext' focus on messages; strings printed by a +The facilities in GNU `gettext' focus on messages: strings printed by a program, either directly or via formatting with `printf' or `sprintf()'.(1) @@ -20259,8 +20290,7 @@ File: gawk.info, Node: Programmer i18n, Next: Translator i18n, Prev: Explaini 13.3 Internationalizing `awk' Programs ====================================== -`gawk' provides the following variables and functions for -internationalization: +`gawk' provides the following variables for internationalization: `TEXTDOMAIN' This variable indicates the application's text domain. For @@ -20272,6 +20302,8 @@ internationalization: for translation at runtime. String constants without a leading underscore are not translated. + `gawk' provides the following functions for internationalization: + ``dcgettext(STRING' [`,' DOMAIN [`,' CATEGORY]]`)'' Return the translation of STRING in text domain DOMAIN for locale category CATEGORY. The default value for DOMAIN is the current @@ -20310,8 +20342,7 @@ internationalization: the null string (`""'), then `bindtextdomain()' returns the current binding for the given DOMAIN. - To use these facilities in your `awk' program, follow the steps -outlined in *note Explaining gettext::, like so: + To use these facilities in your `awk' program, follow these steps: 1. Set the variable `TEXTDOMAIN' to the text domain of your program. This is best done in a `BEGIN' rule (*note BEGIN/END::), or it can @@ -20533,7 +20564,7 @@ actually almost portable, requiring very little change: its value, leaving the original string constant as the result. * By defining "dummy" functions to replace `dcgettext()', - `dcngettext()' and `bindtextdomain()', the `awk' program can be + `dcngettext()', and `bindtextdomain()', the `awk' program can be made to run, but all the messages are output in the original language. For example: @@ -20668,9 +20699,9 @@ File: gawk.info, Node: Gawk I18N, Next: I18N Summary, Prev: I18N Example, Up `gawk' itself has been internationalized using the GNU `gettext' package. (GNU `gettext' is described in complete detail in *note (GNU -`gettext' utilities)Top:: gettext, GNU gettext tools.) As of this -writing, the latest version of GNU `gettext' is version 0.19.3 -(ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.3.tar.gz). +`gettext' utilities)Top:: gettext, GNU `gettext' utilities.) As of +this writing, the latest version of GNU `gettext' is version 0.19.4 +(ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.4.tar.gz). If a translation of `gawk''s messages exists, then `gawk' produces usage messages, warnings, and fatal errors in the local language. @@ -20682,7 +20713,7 @@ File: gawk.info, Node: I18N Summary, Prev: Gawk I18N, Up: Internationalizatio ============ * Internationalization means writing a program such that it can use - multiple languages without requiring source-code changes. + multiple languages without requiring source code changes. Localization means providing the data necessary for an internationalized program to work in a particular language. @@ -20696,10 +20727,10 @@ File: gawk.info, Node: I18N Summary, Prev: Gawk I18N, Up: Internationalizatio file, and the `.po' files are compiled into `.gmo' files for use at runtime. - * You can use position specifications with `sprintf()' and `printf' - to rearrange the placement of argument values in formatted strings - and output. This is useful for the translations of format control - strings. + * You can use positional specifications with `sprintf()' and + `printf' to rearrange the placement of argument values in formatted + strings and output. This is useful for the translation of format + control strings. * The internationalization features have been designed so that they can be easily worked around in a standard `awk'. @@ -20755,8 +20786,7 @@ File: gawk.info, Node: Debugging Concepts, Next: Debugging Terms, Up: Debuggi --------------------------- (If you have used debuggers in other languages, you may want to skip -ahead to the next section on the specific features of the `gawk' -debugger.) +ahead to *note Awk Debugging::.) Of course, a debugging program cannot remove bugs for you, because it has no way of knowing what you or your users consider a "bug" versus @@ -20843,11 +20873,11 @@ defines terms used throughout the rest of this major node: File: gawk.info, Node: Awk Debugging, Prev: Debugging Terms, Up: Debugging -14.1.3 Awk Debugging --------------------- +14.1.3 `awk' Debugging +---------------------- Debugging an `awk' program has some specific aspects that are not -shared with other programming languages. +shared with programs written in other languages. First of all, the fact that `awk' programs usually take input line by line from a file or files and operate on those lines using specific @@ -20865,8 +20895,8 @@ commands. File: gawk.info, Node: Sample Debugging Session, Next: List of Debugger Commands, Prev: Debugging, Up: Debugger -14.2 Sample Debugging Session -============================= +14.2 Sample `gawk' Debugging Session +==================================== In order to illustrate the use of `gawk' as a debugger, let's look at a sample debugging session. We will use the `awk' implementation of the @@ -20885,8 +20915,8 @@ File: gawk.info, Node: Debugger Invocation, Next: Finding The Bug, Up: Sample -------------------------------- Starting the debugger is almost exactly like running `gawk' normally, -except you have to pass an additional option `--debug', or the -corresponding short option `-D'. The file(s) containing the program +except you have to pass an additional option, `--debug', or the +corresponding short option, `-D'. The file(s) containing the program and any supporting code are given on the command line as arguments to one or more `-f' options. (`gawk' is not designed to debug command-line programs, only programs contained in files.) In our case, we invoke @@ -20896,7 +20926,7 @@ the debugger like this: where both `getopt.awk' and `uniq.awk' are in `$AWKPATH'. (Experienced users of GDB or similar debuggers should note that this syntax is -slightly different from what they are used to. With the `gawk' +slightly different from what you are used to. With the `gawk' debugger, you give the arguments for running the program in the command line to the debugger rather than as part of the `run' command at the debugger prompt.) The `-1' is an option to `uniq.awk'. @@ -21020,10 +21050,10 @@ typing `n' (for "next"): -| 66 if (fcount > 0) { This tells us that `gawk' is now ready to execute line 66, which -decides whether to give the lines the special "field skipping" treatment +decides whether to give the lines the special "field-skipping" treatment indicated by the `-1' command-line option. (Notice that we skipped -from where we were before at line 63 to here, because the condition in -line 63 `if (fcount == 0 && charcount == 0)' was false.) +from where we were before, at line 63, to here, because the condition +in line 63, `if (fcount == 0 && charcount == 0)', was false.) Continuing to step, we now get to the splitting of the current and last records: @@ -21081,15 +21111,15 @@ mentioned): Well, here we are at our error (sorry to spoil the suspense). What we had in mind was to join the fields starting from the second one to -make the virtual record to compare, and if the first field was numbered -zero, this would work. Let's look at what we've got: +make the virtual record to compare, and if the first field were +numbered zero, this would work. Let's look at what we've got: gawk> p cline clast -| cline = "gawk is a wonderful program!" -| clast = "awk is a wonderful program!" Hey, those look pretty familiar! They're just our original, -unaltered, input records. A little thinking (the human brain is still +unaltered input records. A little thinking (the human brain is still the best debugging tool), and we realize that we were off by one! We get out of the debugger: @@ -21126,11 +21156,11 @@ categories: * Miscellaneous Each of these are discussed in the following subsections. In the -following descriptions, commands which may be abbreviated show the +following descriptions, commands that may be abbreviated show the abbreviation on a second description line. A debugger command name may also be truncated if that partial name is unambiguous. The debugger has the built-in capability to automatically repeat the previous command -just by hitting <Enter>. This works for the commands `list', `next', +just by hitting `Enter'. This works for the commands `list', `next', `nexti', `step', `stepi', and `continue' executed without any argument. * Menu: @@ -21170,8 +21200,8 @@ The commands for controlling breakpoints are: Set a breakpoint at entry to (the first instruction of) function FUNCTION. - Each breakpoint is assigned a number which can be used to delete - it from the breakpoint list using the `delete' command. + Each breakpoint is assigned a number that can be used to delete it + from the breakpoint list using the `delete' command. With a breakpoint, you may also supply a condition. This is an `awk' expression (enclosed in double quotes) that the debugger @@ -21209,26 +21239,26 @@ The commands for controlling breakpoints are: `delete' [N1 N2 ...] [N-M] `d' [N1 N2 ...] [N-M] - Delete specified breakpoints or a range of breakpoints. Deletes - all defined breakpoints if no argument is supplied. + Delete specified breakpoints or a range of breakpoints. Delete all + defined breakpoints if no argument is supplied. `disable' [N1 N2 ... | N-M] Disable specified breakpoints or a range of breakpoints. Without - any argument, disables all breakpoints. + any argument, disable all breakpoints. `enable' [`del' | `once'] [N1 N2 ...] [N-M] `e' [`del' | `once'] [N1 N2 ...] [N-M] Enable specified breakpoints or a range of breakpoints. Without - any argument, enables all breakpoints. Optionally, you can - specify how to enable the breakpoint: + any argument, enable all breakpoints. Optionally, you can specify + how to enable the breakpoints: `del' - Enable the breakpoint(s) temporarily, then delete it when the - program stops at the breakpoint. + Enable the breakpoints temporarily, then delete each one when + the program stops at it. `once' - Enable the breakpoint(s) temporarily, then disable it when - the program stops at the breakpoint. + Enable the breakpoints temporarily, then disable each one when + the program stops at it. `ignore' N COUNT Ignore breakpoint number N the next COUNT times it is hit. @@ -21274,7 +21304,7 @@ execution of the program than we saw in our earlier example: `continue' [COUNT] `c' [COUNT] Resume program execution. If continued from a breakpoint and COUNT - is specified, ignores the breakpoint at that location the next + is specified, ignore the breakpoint at that location the next COUNT times before stopping. `finish' @@ -21309,10 +21339,10 @@ execution of the program than we saw in our earlier example: `step' [COUNT] `s' [COUNT] Continue execution until control reaches a different source line - in the current stack frame. `step' steps inside any function - called within the line. If the argument COUNT is supplied, steps - that many times before stopping, unless it encounters a breakpoint - or watchpoint. + in the current stack frame, stepping inside any function called + within the line. If the argument COUNT is supplied, steps that + many times before stopping, unless it encounters a breakpoint or + watchpoint. `stepi' [COUNT] `si' [COUNT] @@ -21393,13 +21423,13 @@ AWK STATEMENTS (`"'...`"'). You can also set special `awk' variables, such as `FS', `NF', - `NR', and son on. + `NR', and so on. `watch' VAR | `$'N [`"EXPRESSION"'] `w' VAR | `$'N [`"EXPRESSION"'] Add variable VAR (or field `$N') to the watch list. The debugger then stops whenever the value of the variable or field changes. - Each watched item is assigned a number which can be used to delete + Each watched item is assigned a number that can be used to delete it from the watch list using the `unwatch' command. With a watchpoint, you may also supply a condition. This is an @@ -21423,11 +21453,11 @@ File: gawk.info, Node: Execution Stack, Next: Debugger Info, Prev: Viewing An 14.3.4 Working with the Stack ----------------------------- -Whenever you run a program which contains any function calls, `gawk' +Whenever you run a program that contains any function calls, `gawk' maintains a stack of all of the function calls leading up to where the program is right now. You can see how you got to where you are, and also move around in the stack to see what the state of things was in the -functions which called the one you are in. The commands for doing this +functions that called the one you are in. The commands for doing this are: `backtrace' [COUNT] @@ -21447,8 +21477,8 @@ are: `frame' [N] `f' [N] Select and print stack frame N. Frame 0 is the currently - executing, or "innermost", frame (function call), frame 1 is the - frame that called the innermost one. The highest numbered frame is + executing, or "innermost", frame (function call); frame 1 is the + frame that called the innermost one. The highest-numbered frame is the one for the main program. The printed information consists of the frame number, function and argument names, source file, and the source line. @@ -21465,7 +21495,7 @@ File: gawk.info, Node: Debugger Info, Next: Miscellaneous Debugger Commands, Besides looking at the values of variables, there is often a need to get other sorts of information about the state of your program and of the -debugging environment itself. The `gawk' debugger has one command which +debugging environment itself. The `gawk' debugger has one command that provides this information, appropriately called `info'. `info' is used with one of a number of arguments that tell it exactly what you want to know: @@ -21522,11 +21552,12 @@ from a file. The commands are: option. The available options are: `history_size' - The maximum number of lines to keep in the history file + Set the maximum number of lines to keep in the history file `./.gawk_history'. The default is 100. `listsize' - The number of lines that `list' prints. The default is 15. + Specify the number of lines that `list' prints. The default + is 15. `outfile' Send `gawk' output to a file; debugger output still goes to @@ -21534,7 +21565,7 @@ from a file. The commands are: standard output. `prompt' - The debugger prompt. The default is `gawk> '. + Change the debugger prompt. The default is `gawk> '. `save_history' [`on' | `off'] Save command history to file `./.gawk_history'. The default @@ -21542,8 +21573,8 @@ from a file. The commands are: `save_options' [`on' | `off'] Save current options to file `./.gawkrc' upon exit. The - default is `on'. Options are read back in to the next - session upon startup. + default is `on'. Options are read back into the next session + upon startup. `trace' [`on' | `off'] Turn instruction tracing on or off. The default is `off'. @@ -21562,7 +21593,7 @@ from a file. The commands are: commands; however, the `gawk' debugger will not source the same file more than once in order to avoid infinite recursion. - In addition to, or instead of the `source' command, you can use + In addition to, or instead of, the `source' command, you can use the `-D FILE' or `--debug=FILE' command-line options to execute commands from a file non-interactively (*note Options::). @@ -21572,13 +21603,13 @@ File: gawk.info, Node: Miscellaneous Debugger Commands, Prev: Debugger Info, 14.3.6 Miscellaneous Commands ----------------------------- -There are a few more commands which do not fit into the previous +There are a few more commands that do not fit into the previous categories, as follows: `dump' [FILENAME] - Dump bytecode of the program to standard output or to the file + Dump byte code of the program to standard output or to the file named in FILENAME. This prints a representation of the internal - instructions which `gawk' executes to implement the `awk' commands + instructions that `gawk' executes to implement the `awk' commands in a program. This can be very enlightening, as the following partial dump of Davide Brini's obfuscated code (*note Signature Program::) demonstrates: @@ -21662,22 +21693,21 @@ categories, as follows: FILENAME. This command may change the current source file. FUNCTION - Print lines centered around beginning of the function + Print lines centered around the beginning of the function FUNCTION. This command may change the current source file. `quit' `q' Exit the debugger. Debugging is great fun, but sometimes we all have to tend to other obligations in life, and sometimes we find - the bug, and are free to go on to the next one! As we saw - earlier, if you are running a program, the debugger warns you if - you accidentally type `q' or `quit', to make sure you really want - to quit. + the bug and are free to go on to the next one! As we saw earlier, + if you are running a program, the debugger warns you when you type + `q' or `quit', to make sure you really want to quit. `trace' [`on' | `off'] - Turn on or off a continuous printing of instructions which are - about to be executed, along with printing the `awk' line which they - implement. The default is `off'. + Turn on or off continuous printing of the instructions that are + about to be executed, along with the `awk' lines they implement. + The default is `off'. It is to be hoped that most of the "opcodes" in these instructions are fairly self-explanatory, and using `stepi' and `nexti' while @@ -21690,7 +21720,7 @@ File: gawk.info, Node: Readline Support, Next: Limitations, Prev: List of Deb 14.4 Readline Support ===================== -If `gawk' is compiled with the `readline' library +If `gawk' is compiled with the GNU Readline library (http://cnswww.cns.cwru.edu/php/chet/readline/readline.html), you can take advantage of that library's command completion and history expansion features. The following types of completion are available: @@ -21720,7 +21750,7 @@ File: gawk.info, Node: Limitations, Next: Debugging Summary, Prev: Readline S We hope you find the `gawk' debugger useful and enjoyable to work with, but as with any program, especially in its early releases, it still has -some limitations. A few which are worth being aware of are: +some limitations. A few that it's worth being aware of are: * At this point, the debugger does not give a detailed explanation of what you did wrong when you type in something it doesn't like. @@ -21731,13 +21761,13 @@ some limitations. A few which are worth being aware of are: Commands:: (or if you are already familiar with `gawk' internals), you will realize that much of the internal manipulation of data in `gawk', as in many interpreters, is done on a stack. `Op_push', - `Op_pop', and the like, are the "bread and butter" of most `gawk' + `Op_pop', and the like are the "bread and butter" of most `gawk' code. Unfortunately, as of now, the `gawk' debugger does not allow you to examine the stack's contents. That is, the intermediate results of expression evaluation are on the stack, but cannot be - printed. Rather, only variables which are defined in the program + printed. Rather, only variables that are defined in the program can be printed. Of course, a workaround for this is to use more explicit variables at the debugging stage and then change back to obscure, perhaps more optimal code later. @@ -21749,12 +21779,12 @@ some limitations. A few which are worth being aware of are: * The `gawk' debugger is designed to be used by running a program (with all its parameters) on the command line, as described in *note Debugger Invocation::. There is no way (as of now) to - attach or "break in" to a running program. This seems reasonable - for a language which is used mainly for quickly executing, short + attach or "break into" a running program. This seems reasonable + for a language that is used mainly for quickly executing, short programs. - * The `gawk' debugger only accepts source supplied with the `-f' - option. + * The `gawk' debugger only accepts source code supplied with the + `-f' option. File: gawk.info, Node: Debugging Summary, Prev: Limitations, Up: Debugger @@ -21763,8 +21793,8 @@ File: gawk.info, Node: Debugging Summary, Prev: Limitations, Up: Debugger ============ * Programs rarely work correctly the first time. Finding bugs is - "debugging" and a program that helps you find bugs is a - "debugger". `gawk' has a built-in debugger that works very + called debugging, and a program that helps you find bugs is a + debugger. `gawk' has a built-in debugger that works very similarly to the GNU Debugger, GDB. * Debuggers let you step through your program one statement at a @@ -21780,8 +21810,8 @@ File: gawk.info, Node: Debugging Summary, Prev: Limitations, Up: Debugger breakpoints, execution, viewing and changing data, working with the stack, getting information, and other tasks. - * If the `readline' library is available when `gawk' is compiled, it - is used by the debugger to provide command-line history and + * If the GNU Readline library is available when `gawk' is compiled, + it is used by the debugger to provide command-line history and editing. @@ -22027,7 +22057,7 @@ so: $ gawk --version -| GNU Awk 4.1.2, API: 1.1 (GNU MPFR 3.1.0-p3, GNU MP 5.0.2) - -| Copyright (C) 1989, 1991-2014 Free Software Foundation. + -| Copyright (C) 1989, 1991-2015 Free Software Foundation. ... (You may see different version numbers than what's shown here. That's @@ -22566,7 +22596,7 @@ set: It's not that well known but it's not that obscure either. It's Euler's modification to Newton's method for calculating pi. Take a look at lines (23) - (25) here: - `http://mathworld.wolfram.com/PiFormulas.htm'. + `http://mathworld.wolfram.com/PiFormulas.html'. The algorithm I wrote simply expands the multiply by 2 and works from the innermost expression outwards. I used this to program HP @@ -28507,7 +28537,7 @@ Unix `awk' git clone git://github.com/onetrueawk/awk bwkawk - This command creates a copy of the Git (http://www.git-scm.com) + This command creates a copy of the Git (http://git-scm.com) repository in a directory named `bwkawk'. If you leave that argument off the `git' command line, the repository copy is created in a directory named `awk'. @@ -28554,7 +28584,7 @@ Unix `awk' To get `awka', go to `http://sourceforge.net/projects/awka'. The project seems to be frozen; no new code changes have been made - since approximately 2003. + since approximately 2001. `pawk' Nelson H.F. Beebe at the University of Utah has modified BWK `awk' @@ -28739,7 +28769,7 @@ released versions of `gawk'. changes, you will probably wish to work with the development version. To do so, you will need to access the `gawk' source code repository. The code is maintained using the Git distributed version control system -(http://git-scm.com/). You will need to install it if your system +(http://git-scm.com). You will need to install it if your system doesn't have it. Once you have done so, use the command: git clone git://git.savannah.gnu.org/gawk.git @@ -28794,7 +28824,7 @@ possible to include them: document describes how GNU software should be written. If you haven't read it, please do so, preferably _before_ starting to modify `gawk'. (The `GNU Coding Standards' are available from the - GNU Project's website (http://www.gnu.org/prep/standards_toc.html). + GNU Project's website (http://www.gnu.org/prep/standards/). Texinfo, Info, and DVI versions are also available.) 5. Use the `gawk' coding style. The C code for `gawk' follows the @@ -29676,6 +29706,21 @@ ANSI C++ programming languages. These standards often become international standards as well. See also "ISO." +Argument + An argument can be two different things. It can be an option or a + file name passed to a command while invoking it from the command + line, or it can be something passed to a "function" inside a + program, e.g. inside `awk'. + + In the latter case, an argument can be passed to a function in two + ways. Either it is given to the called function by value, i.e., a + copy of the value of the variable is made available to the called + function, but the original variable cannot be modified by the + function itself; or it is given by reference, i.e., a pointer to + the interested variable is passed to the function, which can then + directly modify it. In `awk' scalars are passed by value, and + arrays are passed by reference. See "Pass By Value/Reference." + Array A grouping of multiple values under the same name. Most languages just provide sequential arrays. `awk' provides associative arrays. @@ -29711,6 +29756,26 @@ Bash The GNU version of the standard shell (the Bourne-Again SHell). See also "Bourne Shell." +Binary + Base-two notation, where the digits are `0'-`1'. Since electronic + circuitry works "naturally" in base 2 (just think of Off/On), + everything inside a computer is calculated using base 2. Each digit + represents the presence (or absence) of a power of 2 and is called + a "bit". So, for example, the base-two number `10101' is the same + as decimal 21, ((1 x 16) + (1 x 4) + (1 x 1)). + + Since base-two numbers quickly become very long to read and write, + they are usually grouped by 3 (i.e., they are read as octal + numbers), or by 4 (i.e., they are read as hexadecimal numbers). + There is no direct way to insert base 2 numbers in a C program. + If need arises, such numbers are usually inserted as octal or + hexadecimal numbers. The number of base-two digits that fit into + registers used for representing integer numbers in computers is a + rough indication of the computing power of the computer itself. + Most computers nowadays use 64 bits for representing integer + numbers in their registers, but 32-bit, 16-bit and 8-bit registers + have been widely used in the past. *Note Nondecimal-numbers::. + Bit Short for "Binary Digit." All values in computer memory ultimately reduce to binary digits: values that are either zero or @@ -29739,6 +29804,19 @@ Braces The characters `{' and `}'. Braces are used in `awk' for delimiting actions, compound statements, and function bodies. +Bracket Expression + Inside a "regular expression", an expression included in square + brackets, meant to designate a single character as belonging to a + specified character class. A bracket expression can contain a list + of one or more characters, like `[abc]', a range of characters, + like `[A-Z]', or a name, delimited by `:', that designates a known + set of characters, like `[:digit:]'. The form of bracket expression + enclosed between `:' is independent of the underlying + representation of the character themselves, which could utilize + the ASCII, ECBDIC, or Unicode codesets, depending on the + architecture of the computer system, and on localization. See + also "Regular Expression." + Built-in Function The `awk' language provides built-in functions that perform various numerical, I/O-related, and string computations. Examples are @@ -29766,9 +29844,25 @@ C In general, `gawk' attempts to be as similar to the 1990 version of ISO C as makes sense. +C Shell + The C Shell (`csh' or its improved version, `tcsh') is a Unix + shell that was created by Bill Joy in the late 1970s. The C shell + was differentiated from other shells by its interactive features + and overall style, which looks more like C. The C Shell is not + backward compatible with the Bourne Shell, so special attention is + required when converting scripts written for other Unix shells to + the C shell, especially with regard to the management of shell + variables. See also "Bourne Shell." + C++ A popular object-oriented programming language derived from C. +Character Class + See "Bracket Expression." + +Character List + See "Bracket Expression." + Character Set The set of numeric codes used by a computer system to represent the characters (letters, numbers, punctuation, etc.) of a particular @@ -29783,7 +29877,7 @@ CHEM A preprocessor for `pic' that reads descriptions of molecules and produces `pic' input for drawing them. It was written in `awk' by Brian Kernighan and Jon Bentley, and is available from - `http://netlib.sandia.gov/netlib/typesetting/chem.gz'. + `http://netlib.org/typesetting/chem'. Comparison Expression A relation that is either true or false, such as `a < b'. @@ -29796,10 +29890,21 @@ Compiler machine-executable object code. The object code is then executed directly by the computer. See also "Interpreter." +Complemented Bracket Expression + The negation of a "bracket expression". All that is _not_ + described by a given bracket expression. The symbol `^' precedes + the negated bracket expression. E.g.: `[[^:digit:]' designates + whatever character is not a digit. `[^bad]' designates whatever + character is not one of the letters `b', `a', or `d'. See + "Bracket Expression." + Compound Statement A series of `awk' statements, enclosed in curly braces. Compound statements may be nested. (*Note Statements::.) +Computed Regexps + See "Dynamic Regular Expressions." + Concatenation Concatenating two strings means sticking them together, one after another, producing a new string. For example, the string `foo' @@ -29813,6 +29918,12 @@ Conditional Expression otherwise the value is EXPR3. In either case, only one of EXPR2 and EXPR3 is evaluated. (*Note Conditional Exp::.) +Control Statement + A control statement is an instruction to perform a given operation + or a set of operations inside an `awk' program, if a given + condition is true. Control statements are: `if', `for', `while', + and `do' (*note Statements::). + Cookie A peculiar goodie, token, saying or remembrance produced by or presented to a program. (With thanks to Professor Doug McIlroy.) @@ -29919,6 +30030,12 @@ Format are controlled by the format strings contained in the predefined variables `CONVFMT' and `OFMT'. (*Note Control Letters::.) +Fortran + Shorthand for FORmula TRANslator, one of the first programming + languages available for scientific calculations. It was created by + John Backus, and has been available since 1957. It is still in use + today. + Free Documentation License This document describes the terms under which this Info file is published and may be copied. (*Note GNU Free Documentation @@ -29934,9 +30051,16 @@ FSF See "Free Software Foundation." Function - A specialized group of statements used to encapsulate general or - program-specific tasks. `awk' has a number of built-in functions, - and also allows you to define your own. (*Note Functions::.) + A part of an `awk' program that can be invoked from every point of + the program, to perform a task. `awk' has several built-in + functions. Users can define their own functions in every part of + the program. Function can be recursive, i.e., they may invoke + themselves. *Note Functions::. In `gawk' it is also possible to + have functions shared among different programs, and included where + required using the `@include' directive (*note Include Files::). + In `gawk' the name of the function that should be invoked can be + generated at run time, i.e., dynamically. The `gawk' extension + API provides constructor functions (*note Constructor Functions::). `gawk' The GNU implementation of `awk'. @@ -30032,6 +30156,12 @@ Keyword `else', `exit', `for...in', `for', `function', `func', `if', `next', `nextfile', `switch', and `while'. +Korn Shell + The Korn Shell (`ksh') is a Unix shell which was developed by + David Korn at Bell Laboratories in the early 1980s. The Korn Shell + is backward-compatible with the Bourne shell and includes many + features of the C shell. See also "Bourne Shell." + Lesser General Public License This document describes the terms under which binary library archives or shared objects, and their source code may be @@ -30069,6 +30199,13 @@ Metacharacters Instead, they denote regular expression operations, such as repetition, grouping, or alternation. +Nesting + Nesting is where information is organized in layers, or where + objects contain other similar objects. In `gawk' the `@include' + directive can be nested. The "natural" nesting of arithmetic and + logical operations can be changed using parentheses (*note + Precedence::). + No-op An operation that does nothing. @@ -30088,6 +30225,11 @@ Octal are written in C using a leading `0', to indicate their base. Thus, `013' is 11 ((1 x 8) + 3). *Note Nondecimal-numbers::. +Output Record + A single chunk of data that is written out by `awk'. Usually, an + `awk' output record consists of one or more lines of text. *Note + Records::. + Pattern Patterns tell `awk' which input records are interesting to which rules. @@ -30103,6 +30245,9 @@ PEBKAC computer usage problems. (Problem Exists Between Keyboard And Chair.) +Plug-in + See "Extensions." + POSIX The name for a series of standards that specify a Portable Operating System interface. The "IX" denotes the Unix heritage of @@ -30126,6 +30271,9 @@ Range (of input lines) can specify ranges of input lines for `awk' to process or it can specify single lines. (*Note Pattern Overview::.) +Record + See "Input record" and "Output record." + Recursion When a function calls itself, either directly or indirectly. If this is clear, stop, and proceed to the next entry. Otherwise, @@ -30142,6 +30290,16 @@ Redirection using the `>', `>>', `|', and `|&' operators. (*Note Getline::, and *note Redirection::.) +Reference Counts + An internal mechanism in `gawk' to minimize the amount of memory + needed to store the value of string variables. If the value + assumed by a variable is used in more than one place, only one + copy of the value itself is kept, and the associated reference + count is increased when the same value is used by an additional + variable, and decresed when the related variable is no longer in + use. When the reference count goes to zero, the memory space used + to store the value of the variable is freed. + Regexp See "Regular Expression." @@ -30160,6 +30318,15 @@ Regular Expression Constant when you write the `awk' program and cannot be changed during its execution. (*Note Regexp Usage::.) +Regular Expression Operators + See "Metacharacters." + +Rounding + Rounding the result of an arithmetic operation can be tricky. + More than one way of rounding exists, and in `gawk' it is possible + to choose which method should be used in a program. *Note Setting + the rounding mode::. + Rule A segment of an `awk' program that specifies how to process single input records. A rule consists of a "pattern" and an "action". @@ -30221,6 +30388,11 @@ Special File handed directly to the underlying operating system--for example, `/dev/stderr'. (*Note Special Files::.) +Statement + An expression inside an `awk' program in the action part of a + pattern-action rule, or inside an `awk' function. A statement can + be a variable assignment, an array operation, a loop, etc. + Stream Editor A program that reads records from an input stream and processes them one or more at a time. This is in contrast with batch @@ -30263,10 +30435,15 @@ UTC reference time for day and date calculations. See also "Epoch" and "GMT." +Variable + A name for a value. In `awk', variables may be either scalars or + arrays. + Whitespace A sequence of space, TAB, or newline characters occurring inside an input record or a string. + File: gawk.info, Node: Copying, Next: GNU Free Documentation License, Prev: Glossary, Up: Top @@ -31499,7 +31676,7 @@ Index * ! (exclamation point), !~ operator <5>: Case-sensitivity. (line 26) * ! (exclamation point), !~ operator <6>: Computed Regexps. (line 6) * ! (exclamation point), !~ operator: Regexp Usage. (line 19) -* " (double quote), in regexp constants: Computed Regexps. (line 29) +* " (double quote), in regexp constants: Computed Regexps. (line 30) * " (double quote), in shell commands: Quoting. (line 54) * # (number sign), #! (executable scripts): Executable Scripts. (line 6) @@ -31528,7 +31705,7 @@ Index * * (asterisk), * operator, as regexp operator: Regexp Operators. (line 89) * * (asterisk), * operator, null strings, matching: String Functions. - (line 536) + (line 537) * * (asterisk), ** operator <1>: Precedence. (line 49) * * (asterisk), ** operator: Arithmetic Ops. (line 81) * * (asterisk), **= operator <1>: Precedence. (line 95) @@ -31587,7 +31764,7 @@ Index * --re-interval option: Options. (line 279) * --sandbox option: Options. (line 286) * --sandbox option, disabling system() function: I/O Functions. - (line 128) + (line 129) * --sandbox option, input redirection with getline: Getline. (line 19) * --sandbox option, output redirection with print, printf: Redirection. (line 6) @@ -31633,7 +31810,7 @@ Index * -W option: Options. (line 46) * . (period), regexp operator: Regexp Operators. (line 44) * .gmo files: Explaining gettext. (line 42) -* .gmo files, specifying directory of <1>: Programmer i18n. (line 47) +* .gmo files, specifying directory of <1>: Programmer i18n. (line 48) * .gmo files, specifying directory of: Explaining gettext. (line 54) * .mo files, converting from .po: I18N Example. (line 64) * .po files <1>: Translator i18n. (line 6) @@ -31734,7 +31911,7 @@ Index * \ (backslash), in escape sequences: Escape Sequences. (line 6) * \ (backslash), in escape sequences, POSIX and: Escape Sequences. (line 108) -* \ (backslash), in regexp constants: Computed Regexps. (line 29) +* \ (backslash), in regexp constants: Computed Regexps. (line 30) * \ (backslash), in shell commands: Quoting. (line 48) * \ (backslash), regexp operator: Regexp Operators. (line 18) * ^ (caret), ^ operator: Precedence. (line 49) @@ -31828,7 +32005,7 @@ Index * arrays: Arrays. (line 6) * arrays of arrays: Arrays of Arrays. (line 6) * arrays, an example of using: Array Example. (line 6) -* arrays, and IGNORECASE variable: Array Intro. (line 94) +* arrays, and IGNORECASE variable: Array Intro. (line 100) * arrays, as parameters to functions: Pass By Value/Reference. (line 44) * arrays, associative: Array Intro. (line 50) @@ -31855,14 +32032,14 @@ Index (line 6) * arrays, sorting, and IGNORECASE variable: Array Sorting Functions. (line 83) -* arrays, sparse: Array Intro. (line 72) +* arrays, sparse: Array Intro. (line 76) * arrays, subscripts, uninitialized variables as: Uninitialized Subscripts. (line 6) * arrays, unassigned elements: Reference to Elements. (line 18) * artificial intelligence, gawk and: Distribution contents. (line 52) -* ASCII <1>: Glossary. (line 133) +* ASCII <1>: Glossary. (line 197) * ASCII: Ordinal Functions. (line 45) * asort <1>: Array Sorting Functions. (line 6) @@ -31889,7 +32066,7 @@ Index * asterisk (*), * operator, as regexp operator: Regexp Operators. (line 89) * asterisk (*), * operator, null strings, matching: String Functions. - (line 536) + (line 537) * asterisk (*), ** operator <1>: Precedence. (line 49) * asterisk (*), ** operator: Arithmetic Ops. (line 81) * asterisk (*), **= operator <1>: Precedence. (line 95) @@ -32003,7 +32180,7 @@ Index * backslash (\), in escape sequences: Escape Sequences. (line 6) * backslash (\), in escape sequences, POSIX and: Escape Sequences. (line 108) -* backslash (\), in regexp constants: Computed Regexps. (line 29) +* backslash (\), in regexp constants: Computed Regexps. (line 30) * backslash (\), in shell commands: Quoting. (line 48) * backslash (\), regexp operator: Regexp Operators. (line 18) * backtrace debugger command: Execution Stack. (line 13) @@ -32033,13 +32210,13 @@ Index * BEGINFILE pattern: BEGINFILE/ENDFILE. (line 6) * BEGINFILE pattern, Boolean patterns and: Expression Patterns. (line 69) -* beginfile() user-defined function: Filetrans Function. (line 61) -* Bentley, Jon: Glossary. (line 143) +* beginfile() user-defined function: Filetrans Function. (line 62) +* Bentley, Jon: Glossary. (line 207) * Benzinger, Michael: Contributors. (line 97) * Berry, Karl <1>: Ranges and Locales. (line 74) * Berry, Karl: Acknowledgments. (line 33) * binary input/output: User-modified. (line 15) -* bindtextdomain <1>: Programmer i18n. (line 47) +* bindtextdomain <1>: Programmer i18n. (line 48) * bindtextdomain: I18N Functions. (line 12) * bindtextdomain() function (C library): Explaining gettext. (line 50) * bindtextdomain() function (gawk), portability and: I18N Portability. @@ -32096,7 +32273,7 @@ Index * Brennan, Michael: Foreword3. (line 84) * Brian Kernighan's awk <1>: I/O Functions. (line 43) * Brian Kernighan's awk <2>: Gory Details. (line 19) -* Brian Kernighan's awk <3>: String Functions. (line 492) +* Brian Kernighan's awk <3>: String Functions. (line 493) * Brian Kernighan's awk <4>: Delete. (line 51) * Brian Kernighan's awk <5>: Nextfile Statement. (line 47) * Brian Kernighan's awk <6>: Continue Statement. (line 44) @@ -32116,14 +32293,14 @@ Index * Brink, Jeroen: DOS Quoting. (line 10) * Broder, Alan J.: Contributors. (line 88) * Brown, Martin: Contributors. (line 82) -* BSD-based operating systems: Glossary. (line 611) +* BSD-based operating systems: Glossary. (line 753) * bt debugger command (alias for backtrace): Execution Stack. (line 13) * Buening, Andreas <1>: Bugs. (line 70) * Buening, Andreas <2>: Contributors. (line 92) * Buening, Andreas: Acknowledgments. (line 60) * buffering, input/output <1>: Two-way I/O. (line 52) -* buffering, input/output: I/O Functions. (line 140) -* buffering, interactive vs. noninteractive: I/O Functions. (line 75) +* buffering, input/output: I/O Functions. (line 141) +* buffering, interactive vs. noninteractive: I/O Functions. (line 76) * buffers, flushing: I/O Functions. (line 32) * buffers, operators for: GNU Regexp Operators. (line 48) @@ -32148,8 +32325,8 @@ Index * case keyword: Switch Statement. (line 6) * case sensitivity, and regexps: User-modified. (line 76) * case sensitivity, and string comparisons: User-modified. (line 76) -* case sensitivity, array indices and: Array Intro. (line 94) -* case sensitivity, converting case: String Functions. (line 522) +* case sensitivity, array indices and: Array Intro. (line 100) +* case sensitivity, converting case: String Functions. (line 523) * case sensitivity, example programs: Library Functions. (line 53) * case sensitivity, gawk: Case-sensitivity. (line 26) * case sensitivity, regexps and: Case-sensitivity. (line 6) @@ -32158,7 +32335,7 @@ Index (line 56) * character lists in regular expression: Bracket Expressions. (line 6) * character lists, See bracket expressions: Regexp Operators. (line 56) -* character sets (machine character encodings) <1>: Glossary. (line 133) +* character sets (machine character encodings) <1>: Glossary. (line 197) * character sets (machine character encodings): Ordinal Functions. (line 45) * character sets, See Also bracket expressions: Regexp Operators. @@ -32169,7 +32346,7 @@ Index * Chassell, Robert J.: Acknowledgments. (line 33) * chdir() extension function: Extension Sample File Functions. (line 12) -* chem utility: Glossary. (line 143) +* chem utility: Glossary. (line 207) * chr() extension function: Extension Sample Ord. (line 15) * chr() user-defined function: Ordinal Functions. (line 16) @@ -32227,7 +32404,7 @@ Index * common extensions, \x escape sequence: Escape Sequences. (line 61) * common extensions, BINMODE variable: PC Using. (line 33) * common extensions, delete to delete entire arrays: Delete. (line 39) -* common extensions, func keyword: Definition Syntax. (line 93) +* common extensions, func keyword: Definition Syntax. (line 98) * common extensions, length() applied to an array: String Functions. (line 201) * common extensions, RS as a regexp: gawk split records. (line 6) @@ -32246,7 +32423,7 @@ Index * compatibility mode (gawk), octal numbers: Nondecimal-numbers. (line 60) * compatibility mode (gawk), specifying: Options. (line 81) -* compiled programs <1>: Glossary. (line 155) +* compiled programs <1>: Glossary. (line 219) * compiled programs: Basic High Level. (line 15) * compiling gawk for Cygwin: Cygwin. (line 6) * compiling gawk for MS-DOS and MS-Windows: PC Compiling. (line 13) @@ -32278,9 +32455,9 @@ Index * control statements: Statements. (line 6) * controlling array scanning order: Controlling Scanning. (line 14) -* convert string to lower case: String Functions. (line 523) -* convert string to number: String Functions. (line 390) -* convert string to upper case: String Functions. (line 529) +* convert string to lower case: String Functions. (line 524) +* convert string to number: String Functions. (line 391) +* convert string to upper case: String Functions. (line 530) * converting integer array subscripts: Numeric Array Subscripts. (line 31) * converting, dates to timestamps: Time Functions. (line 76) @@ -32292,7 +32469,7 @@ Index * CONVFMT variable: Strings And Numbers. (line 29) * CONVFMT variable, and array subscripts: Numeric Array Subscripts. (line 6) -* cookie: Glossary. (line 177) +* cookie: Glossary. (line 258) * coprocesses <1>: Two-way I/O. (line 25) * coprocesses: Redirection. (line 96) * coprocesses, closing: Close Files And Pipes. @@ -32316,7 +32493,7 @@ Index * cut.awk program: Cut Program. (line 45) * d debugger command (alias for delete): Breakpoint Control. (line 64) * d.c., See dark corner: Conventions. (line 42) -* dark corner <1>: Glossary. (line 188) +* dark corner <1>: Glossary. (line 269) * dark corner: Conventions. (line 42) * dark corner, "0" is actually true: Truth Values. (line 24) * dark corner, /= operator vs. /=.../ regexp constant: Assignment Ops. @@ -32358,7 +32535,7 @@ Index (line 148) * dark corner, regexp constants, as arguments to user-defined functions: Using Constant Regexps. (line 43) -* dark corner, split() function: String Functions. (line 361) +* dark corner, split() function: String Functions. (line 362) * dark corner, strings, storing: gawk split records. (line 83) * dark corner, value of ARGV[0]: Auto-set. (line 39) * data, fixed-width: Constant Size. (line 6) @@ -32373,11 +32550,11 @@ Index * Davies, Stephen <1>: Contributors. (line 74) * Davies, Stephen: Acknowledgments. (line 60) * Day, Robert P.J.: Acknowledgments. (line 78) -* dcgettext <1>: Programmer i18n. (line 19) +* dcgettext <1>: Programmer i18n. (line 20) * dcgettext: I18N Functions. (line 22) * dcgettext() function (gawk), portability and: I18N Portability. (line 33) -* dcngettext <1>: Programmer i18n. (line 36) +* dcngettext <1>: Programmer i18n. (line 37) * dcngettext: I18N Functions. (line 28) * dcngettext() function (gawk), portability and: I18N Portability. (line 33) @@ -32464,7 +32641,7 @@ Index * debugger commands, t (tbreak): Breakpoint Control. (line 90) * debugger commands, tbreak: Breakpoint Control. (line 90) * debugger commands, trace: Miscellaneous Debugger Commands. - (line 108) + (line 107) * debugger commands, u (until): Debugger Execution Control. (line 83) * debugger commands, undisplay: Viewing And Changing Data. @@ -32480,12 +32657,12 @@ Index (line 67) * debugger commands, where (backtrace): Execution Stack. (line 13) * debugger default list amount: Debugger Info. (line 69) -* debugger history file: Debugger Info. (line 80) +* debugger history file: Debugger Info. (line 81) * debugger history size: Debugger Info. (line 65) * debugger options: Debugger Info. (line 57) -* debugger prompt: Debugger Info. (line 77) +* debugger prompt: Debugger Info. (line 78) * debugger, how to start: Debugger Invocation. (line 6) -* debugger, read commands from a file: Debugger Info. (line 96) +* debugger, read commands from a file: Debugger Info. (line 97) * debugging awk programs: Debugger. (line 6) * debugging gawk, bug reports: Bugs. (line 9) * decimal point character, locale specific: Options. (line 270) @@ -32575,7 +32752,7 @@ Index (line 77) * differences in awk and gawk, SYMTAB variable: Auto-set. (line 283) * differences in awk and gawk, TEXTDOMAIN variable: User-modified. - (line 151) + (line 152) * differences in awk and gawk, trunc-mod operation: Arithmetic Ops. (line 66) * directories, command-line: Command-line directories. @@ -32601,7 +32778,7 @@ Index * dollar sign ($), incrementing fields and arrays: Increment Ops. (line 30) * dollar sign ($), regexp operator: Regexp Operators. (line 35) -* double quote ("), in regexp constants: Computed Regexps. (line 29) +* double quote ("), in regexp constants: Computed Regexps. (line 30) * double quote ("), in shell commands: Quoting. (line 54) * down debugger command: Execution Stack. (line 23) * Drepper, Ulrich: Acknowledgments. (line 52) @@ -32653,9 +32830,9 @@ Index * END pattern, print statement and: I/O And BEGIN/END. (line 16) * ENDFILE pattern: BEGINFILE/ENDFILE. (line 6) * ENDFILE pattern, Boolean patterns and: Expression Patterns. (line 69) -* endfile() user-defined function: Filetrans Function. (line 61) -* endgrent() function (C library): Group Functions. (line 211) -* endgrent() user-defined function: Group Functions. (line 214) +* endfile() user-defined function: Filetrans Function. (line 62) +* endgrent() function (C library): Group Functions. (line 212) +* endgrent() user-defined function: Group Functions. (line 215) * endpwent() function (C library): Passwd Functions. (line 207) * endpwent() user-defined function: Passwd Functions. (line 210) * English, Steve: Advanced Features. (line 6) @@ -32663,7 +32840,7 @@ Index * environment variables used by gawk: Environment Variables. (line 6) * environment variables, in ENVIRON array: Auto-set. (line 60) -* epoch, definition of: Glossary. (line 234) +* epoch, definition of: Glossary. (line 315) * equals sign (=), = operator: Assignment Ops. (line 6) * equals sign (=), == operator <1>: Precedence. (line 65) * equals sign (=), == operator: Comparison Operators. @@ -32710,7 +32887,7 @@ Index * exit the debugger: Miscellaneous Debugger Commands. (line 99) * exp: Numeric Functions. (line 33) -* expand utility: Very Simple. (line 72) +* expand utility: Very Simple. (line 73) * Expat XML parser library: gawkextlib. (line 33) * exponent: Numeric Functions. (line 33) * expressions: Expressions. (line 6) @@ -32749,7 +32926,7 @@ Index * extensions, common, BINMODE variable: PC Using. (line 33) * extensions, common, delete to delete entire arrays: Delete. (line 39) * extensions, common, fflush() function: I/O Functions. (line 43) -* extensions, common, func keyword: Definition Syntax. (line 93) +* extensions, common, func keyword: Definition Syntax. (line 98) * extensions, common, length() applied to an array: String Functions. (line 201) * extensions, common, RS as a regexp: gawk split records. (line 6) @@ -32816,7 +32993,7 @@ Index * FILENAME variable, getline, setting with: Getline Notes. (line 19) * filenames, assignments as: Ignoring Assigns. (line 6) * files, .gmo: Explaining gettext. (line 42) -* files, .gmo, specifying directory of <1>: Programmer i18n. (line 47) +* files, .gmo, specifying directory of <1>: Programmer i18n. (line 48) * files, .gmo, specifying directory of: Explaining gettext. (line 54) * files, .mo, converting from .po: I18N Example. (line 64) * files, .po <1>: Translator i18n. (line 6) @@ -32843,7 +33020,7 @@ Index * files, message object, converting from portable object files: I18N Example. (line 64) * files, message object, specifying directory of <1>: Programmer i18n. - (line 47) + (line 48) * files, message object, specifying directory of: Explaining gettext. (line 54) * files, multiple passes over: Other Arguments. (line 56) @@ -32895,7 +33072,7 @@ Index * format time string: Time Functions. (line 48) * formats, numeric output: OFMT. (line 6) * formatting output: Printf. (line 6) -* formatting strings: String Functions. (line 383) +* formatting strings: String Functions. (line 384) * forward slash (/) to enclose regular expressions: Regexp. (line 10) * forward slash (/), / operator: Precedence. (line 55) * forward slash (/), /= operator <1>: Precedence. (line 95) @@ -32909,10 +33086,10 @@ Index * frame debugger command: Execution Stack. (line 27) * Free Documentation License (FDL): GNU Free Documentation License. (line 7) -* Free Software Foundation (FSF) <1>: Glossary. (line 288) +* Free Software Foundation (FSF) <1>: Glossary. (line 375) * Free Software Foundation (FSF) <2>: Getting. (line 10) * Free Software Foundation (FSF): Manual History. (line 6) -* FreeBSD: Glossary. (line 611) +* FreeBSD: Glossary. (line 753) * FS variable <1>: User-modified. (line 50) * FS variable: Field Separators. (line 15) * FS variable, --field-separator option and: Options. (line 21) @@ -32926,7 +33103,7 @@ Index * FS, containing ^: Regexp Field Splitting. (line 59) * FS, in multiline records: Multiple Line. (line 41) -* FSF (Free Software Foundation) <1>: Glossary. (line 288) +* FSF (Free Software Foundation) <1>: Glossary. (line 375) * FSF (Free Software Foundation) <2>: Getting. (line 10) * FSF (Free Software Foundation): Manual History. (line 6) * fts() extension function: Extension Sample File Functions. @@ -32966,7 +33143,7 @@ Index * functions, library, user database, reading: Passwd Functions. (line 6) * functions, names of: Definition Syntax. (line 23) -* functions, recursive: Definition Syntax. (line 83) +* functions, recursive: Definition Syntax. (line 88) * functions, string-translation: I18N Functions. (line 6) * functions, undefined: Pass By Value/Reference. (line 68) @@ -32987,7 +33164,7 @@ Index * gawk, awk and: Preface. (line 21) * gawk, bitwise operations in: Bitwise Functions. (line 40) * gawk, break statement in: Break Statement. (line 51) -* gawk, character classes and: Bracket Expressions. (line 100) +* gawk, character classes and: Bracket Expressions. (line 101) * gawk, coding style in: Adding Code. (line 38) * gawk, command-line options, and regular expressions: GNU Regexp Operators. (line 70) @@ -33022,7 +33199,7 @@ Index * gawk, IGNORECASE variable in <1>: Array Sorting Functions. (line 83) * gawk, IGNORECASE variable in <2>: String Functions. (line 58) -* gawk, IGNORECASE variable in <3>: Array Intro. (line 94) +* gawk, IGNORECASE variable in <3>: Array Intro. (line 100) * gawk, IGNORECASE variable in <4>: User-modified. (line 76) * gawk, IGNORECASE variable in: Case-sensitivity. (line 26) * gawk, implementation issues: Notes. (line 6) @@ -33064,7 +33241,7 @@ Index * gawk, splitting fields and: Constant Size. (line 87) * gawk, string-translation functions: I18N Functions. (line 6) * gawk, SYMTAB array in: Auto-set. (line 283) -* gawk, TEXTDOMAIN variable in: User-modified. (line 151) +* gawk, TEXTDOMAIN variable in: User-modified. (line 152) * gawk, timestamps: Time Functions. (line 6) * gawk, uses for: Preface. (line 34) * gawk, versions of, information about, printing: Options. (line 300) @@ -33079,7 +33256,7 @@ Index * gawkpath_append shell function: Shell Startup Files. (line 19) * gawkpath_default shell function: Shell Startup Files. (line 12) * gawkpath_prepend shell function: Shell Startup Files. (line 15) -* General Public License (GPL): Glossary. (line 305) +* General Public License (GPL): Glossary. (line 399) * General Public License, See GPL: Manual History. (line 11) * generate time values: Time Functions. (line 25) * gensub <1>: String Functions. (line 90) @@ -33089,12 +33266,12 @@ Index * getaddrinfo() function (C library): TCP/IP Networking. (line 38) * getgrent() function (C library): Group Functions. (line 6) * getgrent() user-defined function: Group Functions. (line 6) -* getgrgid() function (C library): Group Functions. (line 182) -* getgrgid() user-defined function: Group Functions. (line 185) -* getgrnam() function (C library): Group Functions. (line 171) -* getgrnam() user-defined function: Group Functions. (line 176) -* getgruser() function (C library): Group Functions. (line 191) -* getgruser() function, user-defined: Group Functions. (line 194) +* getgrgid() function (C library): Group Functions. (line 183) +* getgrgid() user-defined function: Group Functions. (line 186) +* getgrnam() function (C library): Group Functions. (line 172) +* getgrnam() user-defined function: Group Functions. (line 177) +* getgruser() function (C library): Group Functions. (line 192) +* getgruser() function, user-defined: Group Functions. (line 195) * getline command: Reading Files. (line 20) * getline command, _gr_init() user-defined function: Group Functions. (line 83) @@ -33111,7 +33288,7 @@ Index * getline from a file: Getline/File. (line 6) * getline into a variable: Getline/Variable. (line 6) * getline statement, BEGINFILE/ENDFILE patterns and: BEGINFILE/ENDFILE. - (line 54) + (line 53) * getlocaltime() user-defined function: Getlocaltime Function. (line 16) * getopt() function (C library): Getopt Function. (line 15) @@ -33137,18 +33314,18 @@ Index * GNU awk, See gawk: Preface. (line 51) * GNU Free Documentation License: GNU Free Documentation License. (line 7) -* GNU General Public License: Glossary. (line 305) -* GNU Lesser General Public License: Glossary. (line 396) +* GNU General Public License: Glossary. (line 399) +* GNU Lesser General Public License: Glossary. (line 496) * GNU long options <1>: Options. (line 6) * GNU long options: Command Line. (line 13) * GNU long options, printing list of: Options. (line 154) -* GNU Project <1>: Glossary. (line 314) +* GNU Project <1>: Glossary. (line 408) * GNU Project: Manual History. (line 11) -* GNU/Linux <1>: Glossary. (line 611) +* GNU/Linux <1>: Glossary. (line 753) * GNU/Linux <2>: I18N Example. (line 55) * GNU/Linux: Manual History. (line 28) * Gordon, Assaf: Contributors. (line 105) -* GPL (General Public License) <1>: Glossary. (line 305) +* GPL (General Public License) <1>: Glossary. (line 399) * GPL (General Public License): Manual History. (line 11) * GPL (General Public License), printing: Options. (line 88) * grcat program: Group Functions. (line 16) @@ -33160,7 +33337,7 @@ Index * gsub <1>: String Functions. (line 140) * gsub: Using Constant Regexps. (line 43) -* gsub() function, arguments of: String Functions. (line 462) +* gsub() function, arguments of: String Functions. (line 463) * gsub() function, escape processing: Gory Details. (line 6) * h debugger command (alias for help): Miscellaneous Debugger Commands. (line 66) @@ -33187,7 +33364,7 @@ Index * hyphen (-), in bracket expressions: Bracket Expressions. (line 17) * i debugger command (alias for info): Debugger Info. (line 13) * id utility: Id Program. (line 6) -* id.awk program: Id Program. (line 30) +* id.awk program: Id Program. (line 31) * if statement: If Statement. (line 6) * if statement, actions, changing: Ranges. (line 25) * if statement, use of regexps in: Regexp Usage. (line 19) @@ -33195,7 +33372,7 @@ Index * ignore breakpoint: Breakpoint Control. (line 87) * ignore debugger command: Breakpoint Control. (line 87) * IGNORECASE variable: User-modified. (line 76) -* IGNORECASE variable, and array indices: Array Intro. (line 94) +* IGNORECASE variable, and array indices: Array Intro. (line 100) * IGNORECASE variable, and array sorting functions: Array Sorting Functions. (line 83) * IGNORECASE variable, in example programs: Library Functions. @@ -33255,7 +33432,7 @@ Index * insomnia, cure for: Alarm Program. (line 6) * installation, VMS: VMS Installation. (line 6) * installing gawk: Installation. (line 6) -* instruction tracing, in debugger: Debugger Info. (line 89) +* instruction tracing, in debugger: Debugger Info. (line 90) * int: Numeric Functions. (line 38) * INT signal (MS-Windows): Profiling. (line 213) * integer array indices: Numeric Array Subscripts. @@ -33263,37 +33440,37 @@ Index * integers, arbitrary precision: Arbitrary Precision Integers. (line 6) * integers, unsigned: Computer Arithmetic. (line 41) -* interacting with other programs: I/O Functions. (line 106) +* interacting with other programs: I/O Functions. (line 107) * internationalization <1>: I18N and L10N. (line 6) * internationalization: I18N Functions. (line 6) * internationalization, localization <1>: Internationalization. (line 13) -* internationalization, localization: User-modified. (line 151) +* internationalization, localization: User-modified. (line 152) * internationalization, localization, character classes: Bracket Expressions. - (line 100) + (line 101) * internationalization, localization, gawk and: Internationalization. (line 13) * internationalization, localization, locale categories: Explaining gettext. (line 81) * internationalization, localization, marked strings: Programmer i18n. - (line 14) + (line 13) * internationalization, localization, portability and: I18N Portability. (line 6) * internationalizing a program: Explaining gettext. (line 6) -* interpreted programs <1>: Glossary. (line 356) +* interpreted programs <1>: Glossary. (line 450) * interpreted programs: Basic High Level. (line 15) * interval expressions, regexp operator: Regexp Operators. (line 116) * inventory-shipped file: Sample Data Files. (line 32) -* invoke shell command: I/O Functions. (line 106) +* invoke shell command: I/O Functions. (line 107) * isarray: Type Functions. (line 11) -* ISO: Glossary. (line 367) -* ISO 8859-1: Glossary. (line 133) -* ISO Latin-1: Glossary. (line 133) +* ISO: Glossary. (line 461) +* ISO 8859-1: Glossary. (line 197) +* ISO Latin-1: Glossary. (line 197) * Jacobs, Andrew: Passwd Functions. (line 90) * Jaegermann, Michal <1>: Contributors. (line 45) * Jaegermann, Michal: Acknowledgments. (line 60) * Java implementation of awk: Other Versions. (line 117) -* Java programming language: Glossary. (line 379) +* Java programming language: Glossary. (line 473) * jawk: Other Versions. (line 117) * Jedi knights: Undocumented. (line 6) * Johansen, Chris: Signature Program. (line 25) @@ -33302,7 +33479,7 @@ Index * Kahrs, Ju"rgen: Acknowledgments. (line 60) * Kasal, Stepan: Acknowledgments. (line 60) * Kenobi, Obi-Wan: Undocumented. (line 6) -* Kernighan, Brian <1>: Glossary. (line 143) +* Kernighan, Brian <1>: Glossary. (line 207) * Kernighan, Brian <2>: Basic Data Typing. (line 54) * Kernighan, Brian <3>: Other Versions. (line 13) * Kernighan, Brian <4>: Contributors. (line 11) @@ -33343,8 +33520,8 @@ Index * length: String Functions. (line 171) * length of input record: String Functions. (line 178) * length of string: String Functions. (line 171) -* Lesser General Public License (LGPL): Glossary. (line 396) -* LGPL (Lesser General Public License): Glossary. (line 396) +* Lesser General Public License (LGPL): Glossary. (line 496) +* LGPL (Lesser General Public License): Glossary. (line 496) * libmawk: Other Versions. (line 125) * libraries of awk functions: Library Functions. (line 6) * libraries of awk functions, assertions: Assert Function. (line 6) @@ -33389,7 +33566,7 @@ Index * lint checking, undefined functions: Pass By Value/Reference. (line 85) * LINT variable: User-modified. (line 88) -* Linux <1>: Glossary. (line 611) +* Linux <1>: Glossary. (line 753) * Linux <2>: I18N Example. (line 55) * Linux: Manual History. (line 28) * list all global variables, in debugger: Debugger Info. (line 48) @@ -33444,20 +33621,20 @@ Index * matching, expressions, See comparison expressions: Typing and Comparison. (line 9) * matching, leftmost longest: Multiple Line. (line 26) -* matching, null strings: String Functions. (line 536) +* matching, null strings: String Functions. (line 537) * mawk utility <1>: Other Versions. (line 48) * mawk utility <2>: Nextfile Statement. (line 47) * mawk utility <3>: Concatenation. (line 36) * mawk utility <4>: Getline/Pipe. (line 62) * mawk utility: Escape Sequences. (line 120) * maximum precision supported by MPFR library: Auto-set. (line 235) -* McIlroy, Doug: Glossary. (line 177) +* McIlroy, Doug: Glossary. (line 258) * McPhee, Patrick: Contributors. (line 100) * message object files: Explaining gettext. (line 42) * message object files, converting from portable object files: I18N Example. (line 64) * message object files, specifying directory of <1>: Programmer i18n. - (line 47) + (line 48) * message object files, specifying directory of: Explaining gettext. (line 54) * messages from extensions: Printing Messages. (line 6) @@ -33479,7 +33656,7 @@ Index * names, functions: Definition Syntax. (line 23) * namespace issues: Library Names. (line 6) * namespace issues, functions: Definition Syntax. (line 23) -* NetBSD: Glossary. (line 611) +* NetBSD: Glossary. (line 753) * networks, programming: TCP/IP Networking. (line 6) * networks, support for: Special Network. (line 6) * newlines <1>: Boolean Ops. (line 69) @@ -33488,8 +33665,8 @@ Index * newlines, as field separators: Default Field Splitting. (line 6) * newlines, as record separators: awk split records. (line 12) -* newlines, in dynamic regexps: Computed Regexps. (line 59) -* newlines, in regexp constants: Computed Regexps. (line 69) +* newlines, in dynamic regexps: Computed Regexps. (line 60) +* newlines, in regexp constants: Computed Regexps. (line 70) * newlines, printing: Print Examples. (line 12) * newlines, separating statements in actions <1>: Statements. (line 10) * newlines, separating statements in actions: Action Overview. @@ -33535,7 +33712,7 @@ Index (line 43) * null strings, converting numbers to strings: Strings And Numbers. (line 21) -* null strings, matching: String Functions. (line 536) +* null strings, matching: String Functions. (line 537) * number as string of bits: Bitwise Functions. (line 110) * number of array elements: String Functions. (line 201) * number sign (#), #! (executable scripts): Executable Scripts. @@ -33564,10 +33741,10 @@ Index * OFMT variable <2>: Strings And Numbers. (line 57) * OFMT variable: OFMT. (line 15) * OFMT variable, POSIX awk and: OFMT. (line 27) -* OFS variable <1>: User-modified. (line 113) +* OFS variable <1>: User-modified. (line 114) * OFS variable <2>: Output Separators. (line 6) * OFS variable: Changing Fields. (line 64) -* OpenBSD: Glossary. (line 611) +* OpenBSD: Glossary. (line 753) * OpenSolaris: Other Versions. (line 100) * operating systems, BSD-based: Manual History. (line 28) * operating systems, PC, gawk on: PC Using. (line 6) @@ -33617,7 +33794,7 @@ Index (line 12) * ord() user-defined function: Ordinal Functions. (line 16) * order of evaluation, concatenation: Concatenation. (line 41) -* ORS variable <1>: User-modified. (line 118) +* ORS variable <1>: User-modified. (line 119) * ORS variable: Output Separators. (line 21) * output field separator, See OFS variable: Changing Fields. (line 64) * output record separator, See ORS variable: Output Separators. @@ -33693,7 +33870,7 @@ Index (line 65) * portability, deleting array elements: Delete. (line 56) * portability, example programs: Library Functions. (line 42) -* portability, functions, defining: Definition Syntax. (line 109) +* portability, functions, defining: Definition Syntax. (line 114) * portability, gawk: New Ports. (line 6) * portability, gettext library and: Explaining gettext. (line 11) * portability, internationalization and: I18N Portability. (line 6) @@ -33705,7 +33882,7 @@ Index * portability, operators: Increment Ops. (line 60) * portability, operators, not in POSIX awk: Precedence. (line 98) * portability, POSIXLY_CORRECT environment variable: Options. (line 359) -* portability, substr() function: String Functions. (line 512) +* portability, substr() function: String Functions. (line 513) * portable object files <1>: Translator i18n. (line 6) * portable object files: Explaining gettext. (line 37) * portable object files, converting to message object files: I18N Example. @@ -33738,7 +33915,7 @@ Index * POSIX awk, field separators and <1>: Full Line Fields. (line 16) * POSIX awk, field separators and: Fields. (line 6) * POSIX awk, FS variable and: User-modified. (line 60) -* POSIX awk, function keyword in: Definition Syntax. (line 93) +* POSIX awk, function keyword in: Definition Syntax. (line 98) * POSIX awk, functions and, gsub()/sub(): Gory Details. (line 90) * POSIX awk, functions and, length(): String Functions. (line 180) * POSIX awk, GNU long options and: Options. (line 15) @@ -33757,7 +33934,7 @@ Index * POSIX, gawk extensions not included in: POSIX/GNU. (line 6) * POSIX, programs, implementing in awk: Clones. (line 6) * POSIXLY_CORRECT environment variable: Options. (line 339) -* PREC variable: User-modified. (line 123) +* PREC variable: User-modified. (line 124) * precedence <1>: Precedence. (line 6) * precedence: Increment Ops. (line 60) * precedence, regexp operators: Regexp Operators. (line 156) @@ -33772,7 +33949,7 @@ Index * print statement, commas, omitting: Print Examples. (line 31) * print statement, I/O operators in: Precedence. (line 71) * print statement, line continuations and: Print Examples. (line 76) -* print statement, OFMT variable and: User-modified. (line 113) +* print statement, OFMT variable and: User-modified. (line 114) * print statement, See Also redirection, of output: Redirection. (line 17) * print statement, sprintf() function and: Round Function. (line 6) @@ -33831,7 +34008,7 @@ Index * programming conventions, functions, calling: Calling Built-in. (line 10) * programming conventions, functions, writing: Definition Syntax. - (line 65) + (line 70) * programming conventions, gawk extensions: Internal File Ops. (line 45) * programming conventions, private variable names: Library Names. @@ -33840,7 +34017,7 @@ Index * programming languages, Ada: Glossary. (line 11) * programming languages, data-driven vs. procedural: Getting Started. (line 12) -* programming languages, Java: Glossary. (line 379) +* programming languages, Java: Glossary. (line 473) * programming, basic steps: Basic High Level. (line 20) * programming, concepts: Basic Concepts. (line 6) * pwcat program: Passwd Functions. (line 23) @@ -33887,7 +34064,7 @@ Index * readfile() user-defined function: Readfile Function. (line 30) * reading input files: Reading Files. (line 6) * recipe for a programming language: History. (line 6) -* record separators <1>: User-modified. (line 132) +* record separators <1>: User-modified. (line 133) * record separators: awk split records. (line 6) * record separators, changing: awk split records. (line 85) * record separators, regular expressions as: awk split records. @@ -33900,8 +34077,8 @@ Index * records, splitting input into: Records. (line 6) * records, terminating: awk split records. (line 125) * records, treating files as: gawk split records. (line 93) -* recursive functions: Definition Syntax. (line 83) -* redirect gawk output, in debugger: Debugger Info. (line 72) +* recursive functions: Definition Syntax. (line 88) +* redirect gawk output, in debugger: Debugger Info. (line 73) * redirection of input: Getline/File. (line 6) * redirection of output: Redirection. (line 6) * reference counting, sorting arrays: Array Sorting Functions. @@ -33915,8 +34092,8 @@ Index * regexp constants, as patterns: Expression Patterns. (line 34) * regexp constants, in gawk: Using Constant Regexps. (line 28) -* regexp constants, slashes vs. quotes: Computed Regexps. (line 29) -* regexp constants, vs. string constants: Computed Regexps. (line 39) +* regexp constants, slashes vs. quotes: Computed Regexps. (line 30) +* regexp constants, vs. string constants: Computed Regexps. (line 40) * register extension: Registration Functions. (line 6) * regular expressions: Regexp. (line 6) @@ -33935,7 +34112,7 @@ Index (line 57) * regular expressions, dynamic: Computed Regexps. (line 6) * regular expressions, dynamic, with embedded newlines: Computed Regexps. - (line 59) + (line 60) * regular expressions, gawk, command-line options: GNU Regexp Operators. (line 70) * regular expressions, interval expressions and: Options. (line 279) @@ -33954,7 +34131,7 @@ Index * regular expressions, searching for: Egrep Program. (line 6) * relational operators, See comparison operators: Typing and Comparison. (line 9) -* replace in string: String Functions. (line 408) +* replace in string: String Functions. (line 409) * return debugger command: Debugger Execution Control. (line 54) * return statement, user-defined functions: Return Statement. (line 6) @@ -33965,7 +34142,7 @@ Index (line 11) * revtwoway extension: Extension Sample Rev2way. (line 12) -* rewind() user-defined function: Rewind Function. (line 16) +* rewind() user-defined function: Rewind Function. (line 15) * right angle bracket (>), > operator <1>: Precedence. (line 65) * right angle bracket (>), > operator: Comparison Operators. (line 11) @@ -33999,8 +34176,8 @@ Index * round to nearest integer: Numeric Functions. (line 38) * round() user-defined function: Round Function. (line 16) * rounding numbers: Round Function. (line 6) -* ROUNDMODE variable: User-modified. (line 127) -* RS variable <1>: User-modified. (line 132) +* ROUNDMODE variable: User-modified. (line 128) +* RS variable <1>: User-modified. (line 133) * RS variable: awk split records. (line 12) * RS variable, multiline records and: Multiple Line. (line 17) * rshift: Bitwise Functions. (line 53) @@ -34020,7 +34197,7 @@ Index * sample debugging session: Sample Debugging Session. (line 6) * sandbox mode: Options. (line 286) -* save debugger options: Debugger Info. (line 84) +* save debugger options: Debugger Info. (line 85) * scalar or array: Type Functions. (line 11) * scalar values: Basic Data Typing. (line 13) * scanning arrays: Scanning an Array. (line 6) @@ -34057,19 +34234,19 @@ Index * separators, field, FIELDWIDTHS variable and: User-modified. (line 37) * separators, field, FPAT variable and: User-modified. (line 43) * separators, field, POSIX and: Fields. (line 6) -* separators, for records <1>: User-modified. (line 132) +* separators, for records <1>: User-modified. (line 133) * separators, for records: awk split records. (line 6) * separators, for records, regular expressions as: awk split records. (line 125) * separators, for statements in actions: Action Overview. (line 19) -* separators, subscript: User-modified. (line 145) +* separators, subscript: User-modified. (line 146) * set breakpoint: Breakpoint Control. (line 11) * set debugger command: Viewing And Changing Data. (line 59) * set directory of message catalogs: I18N Functions. (line 12) * set watchpoint: Viewing And Changing Data. (line 67) -* shadowing of variable values: Definition Syntax. (line 71) +* shadowing of variable values: Definition Syntax. (line 76) * shell quoting, rules for: Quoting. (line 6) * shells, piping commands into: Redirection. (line 136) * shells, quoting: Using Shell Variables. @@ -34111,14 +34288,14 @@ Index (line 14) * sidebar, Changing NR and FNR: Auto-set. (line 326) * sidebar, Controlling Output Buffering with system(): I/O Functions. - (line 138) + (line 139) * sidebar, Escape Sequences for Metacharacters: Escape Sequences. (line 137) * sidebar, FS and IGNORECASE: Field Splitting Summary. (line 38) * sidebar, Interactive Versus Noninteractive Buffering: I/O Functions. - (line 73) -* sidebar, Matching the Null String: String Functions. (line 534) + (line 74) +* sidebar, Matching the Null String: String Functions. (line 535) * sidebar, Operator Evaluation Order: Increment Ops. (line 58) * sidebar, Piping into sh: Redirection. (line 134) * sidebar, Pre-POSIX awk Used OFMT for String Conversion: Strings And Numbers. @@ -34126,13 +34303,13 @@ Index * sidebar, Recipe for a Programming Language: History. (line 6) * sidebar, RS = "\0" Is Not Portable: gawk split records. (line 63) * sidebar, So Why Does gawk Have BEGINFILE and ENDFILE?: Filetrans Function. - (line 82) + (line 83) * sidebar, Syntactic Ambiguities Between /= and Regular Expressions: Assignment Ops. (line 146) * sidebar, Understanding #!: Executable Scripts. (line 31) * sidebar, Understanding $0: Changing Fields. (line 134) * sidebar, Using \n in Bracket Expressions of Dynamic Regexps: Computed Regexps. - (line 57) + (line 58) * sidebar, Using close()'s Return Value: Close Files And Pipes. (line 131) * SIGHUP signal, for dynamic profiling: Profiling. (line 210) @@ -34185,16 +34362,16 @@ Index * source code, QuikTrim Awk: Other Versions. (line 139) * source code, Solaris awk: Other Versions. (line 100) * source files, search path for: Programs Exercises. (line 70) -* sparse arrays: Array Intro. (line 72) +* sparse arrays: Array Intro. (line 76) * Spencer, Henry: Glossary. (line 16) * split: String Functions. (line 316) * split string into array: String Functions. (line 297) * split utility: Split Program. (line 6) * split() function, array elements, deleting: Delete. (line 61) * split.awk program: Split Program. (line 30) -* sprintf <1>: String Functions. (line 383) +* sprintf <1>: String Functions. (line 384) * sprintf: OFMT. (line 15) -* sprintf() function, OFMT variable and: User-modified. (line 113) +* sprintf() function, OFMT variable and: User-modified. (line 114) * sprintf() function, print/printf statements and: Round Function. (line 6) * sqrt: Numeric Functions. (line 92) @@ -34202,7 +34379,7 @@ Index * square root: Numeric Functions. (line 92) * srand: Numeric Functions. (line 96) * stack frame: Debugging Terms. (line 10) -* Stallman, Richard <1>: Glossary. (line 288) +* Stallman, Richard <1>: Glossary. (line 375) * Stallman, Richard <2>: Contributors. (line 23) * Stallman, Richard <3>: Acknowledgments. (line 18) * Stallman, Richard: Manual History. (line 6) @@ -34226,7 +34403,7 @@ Index * stream editors: Full Line Fields. (line 22) * strftime: Time Functions. (line 48) * string constants: Scalar Constants. (line 15) -* string constants, vs. regexp constants: Computed Regexps. (line 39) +* string constants, vs. regexp constants: Computed Regexps. (line 40) * string extraction (internationalization): String Extraction. (line 6) * string length: String Functions. (line 171) @@ -34238,25 +34415,25 @@ Index * strings splitting, example: String Functions. (line 335) * strings, converting <1>: Bitwise Functions. (line 110) * strings, converting: Strings And Numbers. (line 6) -* strings, converting letter case: String Functions. (line 522) +* strings, converting letter case: String Functions. (line 523) * strings, converting, numbers to: User-modified. (line 30) * strings, empty, See null strings: awk split records. (line 115) * strings, extracting: String Extraction. (line 6) -* strings, for localization: Programmer i18n. (line 14) +* strings, for localization: Programmer i18n. (line 13) * strings, length limitations: Scalar Constants. (line 20) * strings, merging arrays into: Join Function. (line 6) * strings, null: Regexp Field Splitting. (line 43) * strings, numeric: Variable Typing. (line 6) -* strtonum: String Functions. (line 390) +* strtonum: String Functions. (line 391) * strtonum() function (gawk), --non-decimal-data option and: Nondecimal Data. (line 35) -* sub <1>: String Functions. (line 408) +* sub <1>: String Functions. (line 409) * sub: Using Constant Regexps. (line 43) -* sub() function, arguments of: String Functions. (line 462) +* sub() function, arguments of: String Functions. (line 463) * sub() function, escape processing: Gory Details. (line 6) -* subscript separators: User-modified. (line 145) +* subscript separators: User-modified. (line 146) * subscripts in arrays, multidimensional: Multidimensional. (line 10) * subscripts in arrays, multidimensional, scanning: Multiscanning. (line 11) @@ -34264,19 +34441,19 @@ Index (line 6) * subscripts in arrays, uninitialized variables as: Uninitialized Subscripts. (line 6) -* SUBSEP variable: User-modified. (line 145) +* SUBSEP variable: User-modified. (line 146) * SUBSEP variable, and multidimensional arrays: Multidimensional. (line 16) * substitute in string: String Functions. (line 90) -* substr: String Functions. (line 481) -* substring: String Functions. (line 481) +* substr: String Functions. (line 482) +* substring: String Functions. (line 482) * Sumner, Andrew: Other Versions. (line 68) * supplementary groups of gawk process: Auto-set. (line 251) * switch statement: Switch Statement. (line 6) * SYMTAB array: Auto-set. (line 283) * syntactic ambiguity: /= operator vs. /=.../ regexp constant: Assignment Ops. (line 148) -* system: I/O Functions. (line 106) +* system: I/O Functions. (line 107) * systime: Time Functions. (line 66) * t debugger command (alias for tbreak): Breakpoint Control. (line 90) * tbreak debugger command: Breakpoint Control. (line 90) @@ -34302,8 +34479,8 @@ Index (line 6) * text, printing: Print. (line 22) * text, printing, unduplicated lines of: Uniq Program. (line 6) -* TEXTDOMAIN variable <1>: Programmer i18n. (line 9) -* TEXTDOMAIN variable: User-modified. (line 151) +* TEXTDOMAIN variable <1>: Programmer i18n. (line 8) +* TEXTDOMAIN variable: User-modified. (line 152) * TEXTDOMAIN variable, BEGIN pattern and: Programmer i18n. (line 60) * TEXTDOMAIN variable, portability and: I18N Portability. (line 20) * textdomain() function (C library): Explaining gettext. (line 28) @@ -34326,11 +34503,11 @@ Index * timestamps, converting dates to: Time Functions. (line 76) * timestamps, formatted: Getlocaltime Function. (line 6) -* tolower: String Functions. (line 523) -* toupper: String Functions. (line 529) +* tolower: String Functions. (line 524) +* toupper: String Functions. (line 530) * tr utility: Translate Program. (line 6) * trace debugger command: Miscellaneous Debugger Commands. - (line 108) + (line 107) * traceback, display in debugger: Execution Stack. (line 13) * translate string: I18N Functions. (line 22) * translate.awk program: Translate Program. (line 55) @@ -34346,14 +34523,14 @@ Index (line 22) * troubleshooting, fatal errors, printf format strings: Format Modifiers. (line 158) -* troubleshooting, fflush() function: I/O Functions. (line 62) +* troubleshooting, fflush() function: I/O Functions. (line 63) * troubleshooting, function call syntax: Function Calls. (line 30) * troubleshooting, gawk: Compatibility Mode. (line 6) * troubleshooting, gawk, bug reports: Bugs. (line 9) * troubleshooting, gawk, fatal errors, function arguments: Calling Built-in. (line 16) * troubleshooting, getline function: File Checking. (line 25) -* troubleshooting, gsub()/sub() functions: String Functions. (line 472) +* troubleshooting, gsub()/sub() functions: String Functions. (line 473) * troubleshooting, match() function: String Functions. (line 292) * troubleshooting, print statement, omitting commas: Print Examples. (line 31) @@ -34361,10 +34538,10 @@ Index * troubleshooting, quotes with file names: Special FD. (line 62) * troubleshooting, readable data files: File Checking. (line 6) * troubleshooting, regexp constants vs. string constants: Computed Regexps. - (line 39) + (line 40) * troubleshooting, string concatenation: Concatenation. (line 26) -* troubleshooting, substr() function: String Functions. (line 499) -* troubleshooting, system() function: I/O Functions. (line 128) +* troubleshooting, substr() function: String Functions. (line 500) +* troubleshooting, system() function: I/O Functions. (line 129) * troubleshooting, typographical errors, global variables: Options. (line 98) * true, logical: Truth Values. (line 6) @@ -34387,14 +34564,14 @@ Index * undisplay debugger command: Viewing And Changing Data. (line 80) * undocumented features: Undocumented. (line 6) -* Unicode <1>: Glossary. (line 133) +* Unicode <1>: Glossary. (line 197) * Unicode <2>: Ranges and Locales. (line 61) * Unicode: Ordinal Functions. (line 45) * uninitialized variables, as array subscripts: Uninitialized Subscripts. (line 6) * uniq utility: Uniq Program. (line 6) * uniq.awk program: Uniq Program. (line 65) -* Unix: Glossary. (line 611) +* Unix: Glossary. (line 753) * Unix awk, backslashes in escape sequences: Escape Sequences. (line 120) * Unix awk, close() function and: Close Files And Pipes. @@ -34443,7 +34620,7 @@ Index * variables, predefined conveying information: Auto-set. (line 6) * variables, private: Library Names. (line 11) * variables, setting: Options. (line 32) -* variables, shadowing: Definition Syntax. (line 71) +* variables, shadowing: Definition Syntax. (line 76) * variables, types of: Assignment Ops. (line 40) * variables, types of, comparison expressions and: Typing and Comparison. (line 9) @@ -34544,560 +34721,560 @@ Index Tag Table: Node: Top1204 Node: Foreword342291 -Node: Foreword446733 -Node: Preface48255 -Ref: Preface-Footnote-151126 -Ref: Preface-Footnote-251233 -Ref: Preface-Footnote-351466 -Node: History51608 -Node: Names53954 -Ref: Names-Footnote-155048 -Node: This Manual55194 -Ref: This Manual-Footnote-161681 -Node: Conventions61781 -Node: Manual History64119 -Ref: Manual History-Footnote-167101 -Ref: Manual History-Footnote-267142 -Node: How To Contribute67216 -Node: Acknowledgments68345 -Node: Getting Started73150 -Node: Running gawk75583 -Node: One-shot76773 -Node: Read Terminal78021 -Node: Long80048 -Node: Executable Scripts81564 -Ref: Executable Scripts-Footnote-184353 -Node: Comments84456 -Node: Quoting86938 -Node: DOS Quoting92462 -Node: Sample Data Files93137 -Node: Very Simple95732 -Node: Two Rules100630 -Node: More Complex102516 -Node: Statements/Lines105378 -Ref: Statements/Lines-Footnote-1109833 -Node: Other Features110098 -Node: When111029 -Ref: When-Footnote-1112783 -Node: Intro Summary112848 -Node: Invoking Gawk113731 -Node: Command Line115245 -Node: Options116043 -Ref: Options-Footnote-1131847 -Ref: Options-Footnote-2132076 -Node: Other Arguments132101 -Node: Naming Standard Input135049 -Node: Environment Variables136142 -Node: AWKPATH Variable136700 -Ref: AWKPATH Variable-Footnote-1140113 -Ref: AWKPATH Variable-Footnote-2140158 -Node: AWKLIBPATH Variable140418 -Node: Other Environment Variables141674 -Node: Exit Status145162 -Node: Include Files145838 -Node: Loading Shared Libraries149435 -Node: Obsolete150862 -Node: Undocumented151559 -Node: Invoking Summary151826 -Node: Regexp153490 -Node: Regexp Usage154944 -Node: Escape Sequences156981 -Node: Regexp Operators163211 -Ref: Regexp Operators-Footnote-1170637 -Ref: Regexp Operators-Footnote-2170784 -Node: Bracket Expressions170882 -Ref: table-char-classes172897 -Node: Leftmost Longest175821 -Node: Computed Regexps177123 -Node: GNU Regexp Operators180520 -Node: Case-sensitivity184193 -Ref: Case-sensitivity-Footnote-1187078 -Ref: Case-sensitivity-Footnote-2187313 -Node: Regexp Summary187421 -Node: Reading Files188888 -Node: Records190982 -Node: awk split records191715 -Node: gawk split records196630 -Ref: gawk split records-Footnote-1201174 -Node: Fields201211 -Ref: Fields-Footnote-1203987 -Node: Nonconstant Fields204073 -Ref: Nonconstant Fields-Footnote-1206316 -Node: Changing Fields206520 -Node: Field Separators212449 -Node: Default Field Splitting215154 -Node: Regexp Field Splitting216271 -Node: Single Character Fields219621 -Node: Command Line Field Separator220680 -Node: Full Line Fields223892 -Ref: Full Line Fields-Footnote-1225409 -Ref: Full Line Fields-Footnote-2225455 -Node: Field Splitting Summary225556 -Node: Constant Size227630 -Node: Splitting By Content232219 -Ref: Splitting By Content-Footnote-1236213 -Node: Multiple Line236376 -Ref: Multiple Line-Footnote-1242262 -Node: Getline242441 -Node: Plain Getline244653 -Node: Getline/Variable247293 -Node: Getline/File248441 -Node: Getline/Variable/File249825 -Ref: Getline/Variable/File-Footnote-1251428 -Node: Getline/Pipe251515 -Node: Getline/Variable/Pipe254198 -Node: Getline/Coprocess255329 -Node: Getline/Variable/Coprocess256581 -Node: Getline Notes257320 -Node: Getline Summary260112 -Ref: table-getline-variants260524 -Node: Read Timeout261353 -Ref: Read Timeout-Footnote-1265178 -Node: Command-line directories265236 -Node: Input Summary266141 -Node: Input Exercises269442 -Node: Printing270170 -Node: Print272005 -Node: Print Examples273462 -Node: Output Separators276241 -Node: OFMT278259 -Node: Printf279613 -Node: Basic Printf280398 -Node: Control Letters281968 -Node: Format Modifiers285951 -Node: Printf Examples291960 -Node: Redirection294446 -Node: Special FD301287 -Ref: Special FD-Footnote-1304447 -Node: Special Files304521 -Node: Other Inherited Files305138 -Node: Special Network306138 -Node: Special Caveats307000 -Node: Close Files And Pipes307951 -Ref: Close Files And Pipes-Footnote-1315127 -Ref: Close Files And Pipes-Footnote-2315275 -Node: Nonfatal315425 -Node: Output Summary317348 -Node: Output Exercises318569 -Node: Expressions319249 -Node: Values320434 -Node: Constants321112 -Node: Scalar Constants321803 -Ref: Scalar Constants-Footnote-1322662 -Node: Nondecimal-numbers322912 -Node: Regexp Constants325930 -Node: Using Constant Regexps326455 -Node: Variables329598 -Node: Using Variables330253 -Node: Assignment Options332164 -Node: Conversion334039 -Node: Strings And Numbers334563 -Ref: Strings And Numbers-Footnote-1337628 -Node: Locale influences conversions337737 -Ref: table-locale-affects340484 -Node: All Operators341072 -Node: Arithmetic Ops341702 -Node: Concatenation344207 -Ref: Concatenation-Footnote-1347026 -Node: Assignment Ops347132 -Ref: table-assign-ops352111 -Node: Increment Ops353383 -Node: Truth Values and Conditions356821 -Node: Truth Values357906 -Node: Typing and Comparison358955 -Node: Variable Typing359765 -Node: Comparison Operators363418 -Ref: table-relational-ops363828 -Node: POSIX String Comparison367323 -Ref: POSIX String Comparison-Footnote-1368395 -Node: Boolean Ops368533 -Ref: Boolean Ops-Footnote-1373012 -Node: Conditional Exp373103 -Node: Function Calls374830 -Node: Precedence378710 -Node: Locales382371 -Node: Expressions Summary384003 -Node: Patterns and Actions386563 -Node: Pattern Overview387683 -Node: Regexp Patterns389362 -Node: Expression Patterns389905 -Node: Ranges393615 -Node: BEGIN/END396721 -Node: Using BEGIN/END397482 -Ref: Using BEGIN/END-Footnote-1400216 -Node: I/O And BEGIN/END400322 -Node: BEGINFILE/ENDFILE402636 -Node: Empty405537 -Node: Using Shell Variables405854 -Node: Action Overview408127 -Node: Statements410453 -Node: If Statement412301 -Node: While Statement413796 -Node: Do Statement415825 -Node: For Statement416969 -Node: Switch Statement420126 -Node: Break Statement422508 -Node: Continue Statement424549 -Node: Next Statement426376 -Node: Nextfile Statement428757 -Node: Exit Statement431387 -Node: Built-in Variables433790 -Node: User-modified434923 -Ref: User-modified-Footnote-1442604 -Node: Auto-set442666 -Ref: Auto-set-Footnote-1456358 -Ref: Auto-set-Footnote-2456563 -Node: ARGC and ARGV456619 -Node: Pattern Action Summary460837 -Node: Arrays463264 -Node: Array Basics464593 -Node: Array Intro465437 -Ref: figure-array-elements467401 -Ref: Array Intro-Footnote-1469927 -Node: Reference to Elements470055 -Node: Assigning Elements472507 -Node: Array Example472998 -Node: Scanning an Array474756 -Node: Controlling Scanning477772 -Ref: Controlling Scanning-Footnote-1482968 -Node: Numeric Array Subscripts483284 -Node: Uninitialized Subscripts485469 -Node: Delete487086 -Ref: Delete-Footnote-1489829 -Node: Multidimensional489886 -Node: Multiscanning492983 -Node: Arrays of Arrays494572 -Node: Arrays Summary499331 -Node: Functions501423 -Node: Built-in502322 -Node: Calling Built-in503400 -Node: Numeric Functions505391 -Ref: Numeric Functions-Footnote-1510210 -Ref: Numeric Functions-Footnote-2510567 -Ref: Numeric Functions-Footnote-3510615 -Node: String Functions510887 -Ref: String Functions-Footnote-1534362 -Ref: String Functions-Footnote-2534491 -Ref: String Functions-Footnote-3534739 -Node: Gory Details534826 -Ref: table-sub-escapes536607 -Ref: table-sub-proposed538127 -Ref: table-posix-sub539491 -Ref: table-gensub-escapes541027 -Ref: Gory Details-Footnote-1541859 -Node: I/O Functions542010 -Ref: I/O Functions-Footnote-1549228 -Node: Time Functions549375 -Ref: Time Functions-Footnote-1559863 -Ref: Time Functions-Footnote-2559931 -Ref: Time Functions-Footnote-3560089 -Ref: Time Functions-Footnote-4560200 -Ref: Time Functions-Footnote-5560312 -Ref: Time Functions-Footnote-6560539 -Node: Bitwise Functions560805 -Ref: table-bitwise-ops561367 -Ref: Bitwise Functions-Footnote-1565676 -Node: Type Functions565845 -Node: I18N Functions566996 -Node: User-defined568641 -Node: Definition Syntax569446 -Ref: Definition Syntax-Footnote-1574853 -Node: Function Example574924 -Ref: Function Example-Footnote-1577843 -Node: Function Caveats577865 -Node: Calling A Function578383 -Node: Variable Scope579341 -Node: Pass By Value/Reference582329 -Node: Return Statement585824 -Node: Dynamic Typing588805 -Node: Indirect Calls589734 -Ref: Indirect Calls-Footnote-1601036 -Node: Functions Summary601164 -Node: Library Functions603866 -Ref: Library Functions-Footnote-1607475 -Ref: Library Functions-Footnote-2607618 -Node: Library Names607789 -Ref: Library Names-Footnote-1611243 -Ref: Library Names-Footnote-2611466 -Node: General Functions611552 -Node: Strtonum Function612655 -Node: Assert Function615677 -Node: Round Function619001 -Node: Cliff Random Function620542 -Node: Ordinal Functions621558 -Ref: Ordinal Functions-Footnote-1624621 -Ref: Ordinal Functions-Footnote-2624873 -Node: Join Function625084 -Ref: Join Function-Footnote-1626853 -Node: Getlocaltime Function627053 -Node: Readfile Function630797 -Node: Shell Quoting632767 -Node: Data File Management634168 -Node: Filetrans Function634800 -Node: Rewind Function638856 -Node: File Checking640243 -Ref: File Checking-Footnote-1641575 -Node: Empty Files641776 -Node: Ignoring Assigns643755 -Node: Getopt Function645306 -Ref: Getopt Function-Footnote-1656768 -Node: Passwd Functions656968 -Ref: Passwd Functions-Footnote-1665805 -Node: Group Functions665893 -Ref: Group Functions-Footnote-1673787 -Node: Walking Arrays674000 -Node: Library Functions Summary675603 -Node: Library Exercises677004 -Node: Sample Programs678284 -Node: Running Examples679054 -Node: Clones679782 -Node: Cut Program681006 -Node: Egrep Program690725 -Ref: Egrep Program-Footnote-1698223 -Node: Id Program698333 -Node: Split Program701978 -Ref: Split Program-Footnote-1705426 -Node: Tee Program705554 -Node: Uniq Program708343 -Node: Wc Program715762 -Ref: Wc Program-Footnote-1720012 -Node: Miscellaneous Programs720106 -Node: Dupword Program721319 -Node: Alarm Program723350 -Node: Translate Program728154 -Ref: Translate Program-Footnote-1732719 -Node: Labels Program732989 -Ref: Labels Program-Footnote-1736340 -Node: Word Sorting736424 -Node: History Sorting740495 -Node: Extract Program742331 -Node: Simple Sed749856 -Node: Igawk Program752924 -Ref: Igawk Program-Footnote-1767248 -Ref: Igawk Program-Footnote-2767449 -Ref: Igawk Program-Footnote-3767571 -Node: Anagram Program767686 -Node: Signature Program770743 -Node: Programs Summary771990 -Node: Programs Exercises773183 -Ref: Programs Exercises-Footnote-1777314 -Node: Advanced Features777405 -Node: Nondecimal Data779353 -Node: Array Sorting780943 -Node: Controlling Array Traversal781640 -Ref: Controlling Array Traversal-Footnote-1789973 -Node: Array Sorting Functions790091 -Ref: Array Sorting Functions-Footnote-1793980 -Node: Two-way I/O794176 -Ref: Two-way I/O-Footnote-1799121 -Ref: Two-way I/O-Footnote-2799307 -Node: TCP/IP Networking799389 -Node: Profiling802262 -Node: Advanced Features Summary810539 -Node: Internationalization812472 -Node: I18N and L10N813952 -Node: Explaining gettext814638 -Ref: Explaining gettext-Footnote-1819663 -Ref: Explaining gettext-Footnote-2819847 -Node: Programmer i18n820012 -Ref: Programmer i18n-Footnote-1824878 -Node: Translator i18n824927 -Node: String Extraction825721 -Ref: String Extraction-Footnote-1826852 -Node: Printf Ordering826938 -Ref: Printf Ordering-Footnote-1829724 -Node: I18N Portability829788 -Ref: I18N Portability-Footnote-1832243 -Node: I18N Example832306 -Ref: I18N Example-Footnote-1835109 -Node: Gawk I18N835181 -Node: I18N Summary835819 -Node: Debugger837158 -Node: Debugging838180 -Node: Debugging Concepts838621 -Node: Debugging Terms840474 -Node: Awk Debugging843046 -Node: Sample Debugging Session843940 -Node: Debugger Invocation844460 -Node: Finding The Bug845844 -Node: List of Debugger Commands852319 -Node: Breakpoint Control853652 -Node: Debugger Execution Control857348 -Node: Viewing And Changing Data860712 -Node: Execution Stack864090 -Node: Debugger Info865727 -Node: Miscellaneous Debugger Commands869744 -Node: Readline Support874773 -Node: Limitations875665 -Node: Debugging Summary877779 -Node: Arbitrary Precision Arithmetic878947 -Node: Computer Arithmetic880363 -Ref: table-numeric-ranges883961 -Ref: Computer Arithmetic-Footnote-1884820 -Node: Math Definitions884877 -Ref: table-ieee-formats888165 -Ref: Math Definitions-Footnote-1888769 -Node: MPFR features888874 -Node: FP Math Caution890545 -Ref: FP Math Caution-Footnote-1891595 -Node: Inexactness of computations891964 -Node: Inexact representation892923 -Node: Comparing FP Values894280 -Node: Errors accumulate895362 -Node: Getting Accuracy896795 -Node: Try To Round899457 -Node: Setting precision900356 -Ref: table-predefined-precision-strings901040 -Node: Setting the rounding mode902829 -Ref: table-gawk-rounding-modes903193 -Ref: Setting the rounding mode-Footnote-1906648 -Node: Arbitrary Precision Integers906827 -Ref: Arbitrary Precision Integers-Footnote-1911726 -Node: POSIX Floating Point Problems911875 -Ref: POSIX Floating Point Problems-Footnote-1915748 -Node: Floating point summary915786 -Node: Dynamic Extensions917980 -Node: Extension Intro919532 -Node: Plugin License920798 -Node: Extension Mechanism Outline921595 -Ref: figure-load-extension922023 -Ref: figure-register-new-function923503 -Ref: figure-call-new-function924507 -Node: Extension API Description926493 -Node: Extension API Functions Introduction927943 -Node: General Data Types932767 -Ref: General Data Types-Footnote-1938506 -Node: Memory Allocation Functions938805 -Ref: Memory Allocation Functions-Footnote-1941644 -Node: Constructor Functions941740 -Node: Registration Functions943474 -Node: Extension Functions944159 -Node: Exit Callback Functions946456 -Node: Extension Version String947704 -Node: Input Parsers948369 -Node: Output Wrappers958248 -Node: Two-way processors962763 -Node: Printing Messages964967 -Ref: Printing Messages-Footnote-1966043 -Node: Updating `ERRNO'966195 -Node: Requesting Values966935 -Ref: table-value-types-returned967663 -Node: Accessing Parameters968620 -Node: Symbol Table Access969851 -Node: Symbol table by name970365 -Node: Symbol table by cookie972346 -Ref: Symbol table by cookie-Footnote-1976490 -Node: Cached values976553 -Ref: Cached values-Footnote-1980052 -Node: Array Manipulation980143 -Ref: Array Manipulation-Footnote-1981241 -Node: Array Data Types981278 -Ref: Array Data Types-Footnote-1983933 -Node: Array Functions984025 -Node: Flattening Arrays987879 -Node: Creating Arrays994771 -Node: Extension API Variables999542 -Node: Extension Versioning1000178 -Node: Extension API Informational Variables1002079 -Node: Extension API Boilerplate1003144 -Node: Finding Extensions1006953 -Node: Extension Example1007513 -Node: Internal File Description1008285 -Node: Internal File Ops1012352 -Ref: Internal File Ops-Footnote-11024022 -Node: Using Internal File Ops1024162 -Ref: Using Internal File Ops-Footnote-11026545 -Node: Extension Samples1026818 -Node: Extension Sample File Functions1028344 -Node: Extension Sample Fnmatch1035982 -Node: Extension Sample Fork1037473 -Node: Extension Sample Inplace1038688 -Node: Extension Sample Ord1040363 -Node: Extension Sample Readdir1041199 -Ref: table-readdir-file-types1042075 -Node: Extension Sample Revout1042886 -Node: Extension Sample Rev2way1043476 -Node: Extension Sample Read write array1044216 -Node: Extension Sample Readfile1046156 -Node: Extension Sample Time1047251 -Node: Extension Sample API Tests1048600 -Node: gawkextlib1049091 -Node: Extension summary1051749 -Node: Extension Exercises1055438 -Node: Language History1056160 -Node: V7/SVR3.11057816 -Node: SVR41059997 -Node: POSIX1061442 -Node: BTL1062831 -Node: POSIX/GNU1063565 -Node: Feature History1069446 -Node: Common Extensions1083240 -Node: Ranges and Locales1084564 -Ref: Ranges and Locales-Footnote-11089182 -Ref: Ranges and Locales-Footnote-21089209 -Ref: Ranges and Locales-Footnote-31089443 -Node: Contributors1089664 -Node: History summary1095205 -Node: Installation1096575 -Node: Gawk Distribution1097521 -Node: Getting1098005 -Node: Extracting1098828 -Node: Distribution contents1100463 -Node: Unix Installation1106528 -Node: Quick Installation1107211 -Node: Shell Startup Files1109622 -Node: Additional Configuration Options1110701 -Node: Configuration Philosophy1112440 -Node: Non-Unix Installation1114809 -Node: PC Installation1115267 -Node: PC Binary Installation1116586 -Node: PC Compiling1118434 -Ref: PC Compiling-Footnote-11121455 -Node: PC Testing1121564 -Node: PC Using1122740 -Node: Cygwin1126855 -Node: MSYS1127678 -Node: VMS Installation1128178 -Node: VMS Compilation1128970 -Ref: VMS Compilation-Footnote-11130192 -Node: VMS Dynamic Extensions1130250 -Node: VMS Installation Details1131934 -Node: VMS Running1134186 -Node: VMS GNV1137022 -Node: VMS Old Gawk1137756 -Node: Bugs1138226 -Node: Other Versions1142109 -Node: Installation summary1148537 -Node: Notes1149593 -Node: Compatibility Mode1150458 -Node: Additions1151240 -Node: Accessing The Source1152165 -Node: Adding Code1153601 -Node: New Ports1159766 -Node: Derived Files1164248 -Ref: Derived Files-Footnote-11169723 -Ref: Derived Files-Footnote-21169757 -Ref: Derived Files-Footnote-31170353 -Node: Future Extensions1170467 -Node: Implementation Limitations1171073 -Node: Extension Design1172321 -Node: Old Extension Problems1173475 -Ref: Old Extension Problems-Footnote-11174992 -Node: Extension New Mechanism Goals1175049 -Ref: Extension New Mechanism Goals-Footnote-11178409 -Node: Extension Other Design Decisions1178598 -Node: Extension Future Growth1180706 -Node: Old Extension Mechanism1181542 -Node: Notes summary1183304 -Node: Basic Concepts1184490 -Node: Basic High Level1185171 -Ref: figure-general-flow1185443 -Ref: figure-process-flow1186042 -Ref: Basic High Level-Footnote-11189271 -Node: Basic Data Typing1189456 -Node: Glossary1192784 -Node: Copying1217942 -Node: GNU Free Documentation License1255498 -Node: Index1280634 +Node: Foreword446735 +Node: Preface48266 +Ref: Preface-Footnote-151137 +Ref: Preface-Footnote-251244 +Ref: Preface-Footnote-351477 +Node: History51619 +Node: Names53970 +Ref: Names-Footnote-155063 +Node: This Manual55209 +Ref: This Manual-Footnote-161709 +Node: Conventions61809 +Node: Manual History64146 +Ref: Manual History-Footnote-167139 +Ref: Manual History-Footnote-267180 +Node: How To Contribute67254 +Node: Acknowledgments68383 +Node: Getting Started73200 +Node: Running gawk75639 +Node: One-shot76829 +Node: Read Terminal78093 +Node: Long80124 +Node: Executable Scripts81637 +Ref: Executable Scripts-Footnote-184426 +Node: Comments84529 +Node: Quoting87011 +Node: DOS Quoting92529 +Node: Sample Data Files93204 +Node: Very Simple95799 +Node: Two Rules100698 +Node: More Complex102584 +Node: Statements/Lines105446 +Ref: Statements/Lines-Footnote-1109901 +Node: Other Features110166 +Node: When111102 +Ref: When-Footnote-1112856 +Node: Intro Summary112921 +Node: Invoking Gawk113805 +Node: Command Line115319 +Node: Options116117 +Ref: Options-Footnote-1131912 +Ref: Options-Footnote-2132141 +Node: Other Arguments132166 +Node: Naming Standard Input135114 +Node: Environment Variables136207 +Node: AWKPATH Variable136765 +Ref: AWKPATH Variable-Footnote-1140172 +Ref: AWKPATH Variable-Footnote-2140217 +Node: AWKLIBPATH Variable140477 +Node: Other Environment Variables141733 +Node: Exit Status145251 +Node: Include Files145927 +Node: Loading Shared Libraries149516 +Node: Obsolete150943 +Node: Undocumented151635 +Node: Invoking Summary151902 +Node: Regexp153565 +Node: Regexp Usage155019 +Node: Escape Sequences157056 +Node: Regexp Operators163285 +Ref: Regexp Operators-Footnote-1170695 +Ref: Regexp Operators-Footnote-2170842 +Node: Bracket Expressions170940 +Ref: table-char-classes172955 +Node: Leftmost Longest175897 +Node: Computed Regexps177199 +Node: GNU Regexp Operators180628 +Node: Case-sensitivity184300 +Ref: Case-sensitivity-Footnote-1187185 +Ref: Case-sensitivity-Footnote-2187420 +Node: Regexp Summary187528 +Node: Reading Files188995 +Node: Records191088 +Node: awk split records191821 +Node: gawk split records196750 +Ref: gawk split records-Footnote-1201289 +Node: Fields201326 +Ref: Fields-Footnote-1204104 +Node: Nonconstant Fields204190 +Ref: Nonconstant Fields-Footnote-1206428 +Node: Changing Fields206631 +Node: Field Separators212562 +Node: Default Field Splitting215266 +Node: Regexp Field Splitting216383 +Node: Single Character Fields219733 +Node: Command Line Field Separator220792 +Node: Full Line Fields224009 +Ref: Full Line Fields-Footnote-1225530 +Ref: Full Line Fields-Footnote-2225576 +Node: Field Splitting Summary225677 +Node: Constant Size227751 +Node: Splitting By Content232334 +Ref: Splitting By Content-Footnote-1236299 +Node: Multiple Line236462 +Ref: Multiple Line-Footnote-1242343 +Node: Getline242522 +Node: Plain Getline244729 +Node: Getline/Variable247369 +Node: Getline/File248518 +Node: Getline/Variable/File249903 +Ref: Getline/Variable/File-Footnote-1251506 +Node: Getline/Pipe251593 +Node: Getline/Variable/Pipe254271 +Node: Getline/Coprocess255402 +Node: Getline/Variable/Coprocess256666 +Node: Getline Notes257405 +Node: Getline Summary260199 +Ref: table-getline-variants260611 +Node: Read Timeout261440 +Ref: Read Timeout-Footnote-1265277 +Node: Command-line directories265335 +Node: Input Summary266240 +Node: Input Exercises269625 +Node: Printing270353 +Node: Print272188 +Node: Print Examples273645 +Node: Output Separators276424 +Node: OFMT278442 +Node: Printf279797 +Node: Basic Printf280582 +Node: Control Letters282154 +Node: Format Modifiers286139 +Node: Printf Examples292149 +Node: Redirection294635 +Node: Special FD301473 +Ref: Special FD-Footnote-1304639 +Node: Special Files304713 +Node: Other Inherited Files305330 +Node: Special Network306330 +Node: Special Caveats307192 +Node: Close Files And Pipes308141 +Ref: Close Files And Pipes-Footnote-1315326 +Ref: Close Files And Pipes-Footnote-2315474 +Node: Nonfatal315624 +Node: Output Summary317547 +Node: Output Exercises318768 +Node: Expressions319448 +Node: Values320637 +Node: Constants321314 +Node: Scalar Constants322005 +Ref: Scalar Constants-Footnote-1322867 +Node: Nondecimal-numbers323117 +Node: Regexp Constants326127 +Node: Using Constant Regexps326653 +Node: Variables329816 +Node: Using Variables330473 +Node: Assignment Options332384 +Node: Conversion334259 +Node: Strings And Numbers334783 +Ref: Strings And Numbers-Footnote-1337848 +Node: Locale influences conversions337957 +Ref: table-locale-affects340703 +Node: All Operators341295 +Node: Arithmetic Ops341924 +Node: Concatenation344429 +Ref: Concatenation-Footnote-1347248 +Node: Assignment Ops347355 +Ref: table-assign-ops352334 +Node: Increment Ops353644 +Node: Truth Values and Conditions357075 +Node: Truth Values358158 +Node: Typing and Comparison359207 +Node: Variable Typing360023 +Node: Comparison Operators363690 +Ref: table-relational-ops364100 +Node: POSIX String Comparison367595 +Ref: POSIX String Comparison-Footnote-1368667 +Node: Boolean Ops368806 +Ref: Boolean Ops-Footnote-1373284 +Node: Conditional Exp373375 +Node: Function Calls375113 +Node: Precedence378993 +Node: Locales382653 +Node: Expressions Summary384285 +Node: Patterns and Actions386856 +Node: Pattern Overview387976 +Node: Regexp Patterns389655 +Node: Expression Patterns390198 +Node: Ranges393907 +Node: BEGIN/END397014 +Node: Using BEGIN/END397775 +Ref: Using BEGIN/END-Footnote-1400511 +Node: I/O And BEGIN/END400617 +Node: BEGINFILE/ENDFILE402932 +Node: Empty405829 +Node: Using Shell Variables406146 +Node: Action Overview408419 +Node: Statements410745 +Node: If Statement412593 +Node: While Statement414088 +Node: Do Statement416116 +Node: For Statement417264 +Node: Switch Statement420422 +Node: Break Statement422804 +Node: Continue Statement424845 +Node: Next Statement426672 +Node: Nextfile Statement429053 +Node: Exit Statement431681 +Node: Built-in Variables434092 +Node: User-modified435225 +Ref: User-modified-Footnote-1442928 +Node: Auto-set442990 +Ref: Auto-set-Footnote-1456699 +Ref: Auto-set-Footnote-2456904 +Node: ARGC and ARGV456960 +Node: Pattern Action Summary461178 +Node: Arrays463611 +Node: Array Basics464940 +Node: Array Intro465784 +Ref: figure-array-elements467718 +Ref: Array Intro-Footnote-1470338 +Node: Reference to Elements470466 +Node: Assigning Elements472928 +Node: Array Example473419 +Node: Scanning an Array475178 +Node: Controlling Scanning478198 +Ref: Controlling Scanning-Footnote-1483592 +Node: Numeric Array Subscripts483908 +Node: Uninitialized Subscripts486093 +Node: Delete487710 +Ref: Delete-Footnote-1490459 +Node: Multidimensional490516 +Node: Multiscanning493613 +Node: Arrays of Arrays495202 +Node: Arrays Summary499956 +Node: Functions502047 +Node: Built-in503086 +Node: Calling Built-in504164 +Node: Numeric Functions506159 +Ref: Numeric Functions-Footnote-1510977 +Ref: Numeric Functions-Footnote-2511334 +Ref: Numeric Functions-Footnote-3511382 +Node: String Functions511654 +Ref: String Functions-Footnote-1535155 +Ref: String Functions-Footnote-2535284 +Ref: String Functions-Footnote-3535532 +Node: Gory Details535619 +Ref: table-sub-escapes537400 +Ref: table-sub-proposed538915 +Ref: table-posix-sub540277 +Ref: table-gensub-escapes541814 +Ref: Gory Details-Footnote-1542647 +Node: I/O Functions542798 +Ref: I/O Functions-Footnote-1550034 +Node: Time Functions550181 +Ref: Time Functions-Footnote-1560690 +Ref: Time Functions-Footnote-2560758 +Ref: Time Functions-Footnote-3560916 +Ref: Time Functions-Footnote-4561027 +Ref: Time Functions-Footnote-5561139 +Ref: Time Functions-Footnote-6561366 +Node: Bitwise Functions561632 +Ref: table-bitwise-ops562194 +Ref: Bitwise Functions-Footnote-1566522 +Node: Type Functions566694 +Node: I18N Functions567846 +Node: User-defined569493 +Node: Definition Syntax570298 +Ref: Definition Syntax-Footnote-1575957 +Node: Function Example576028 +Ref: Function Example-Footnote-1578949 +Node: Function Caveats578971 +Node: Calling A Function579489 +Node: Variable Scope580447 +Node: Pass By Value/Reference583440 +Node: Return Statement586937 +Node: Dynamic Typing589916 +Node: Indirect Calls590845 +Ref: Indirect Calls-Footnote-1602151 +Node: Functions Summary602279 +Node: Library Functions604981 +Ref: Library Functions-Footnote-1608589 +Ref: Library Functions-Footnote-2608732 +Node: Library Names608903 +Ref: Library Names-Footnote-1612361 +Ref: Library Names-Footnote-2612584 +Node: General Functions612670 +Node: Strtonum Function613773 +Node: Assert Function616795 +Node: Round Function620119 +Node: Cliff Random Function621660 +Node: Ordinal Functions622676 +Ref: Ordinal Functions-Footnote-1625739 +Ref: Ordinal Functions-Footnote-2625991 +Node: Join Function626202 +Ref: Join Function-Footnote-1627972 +Node: Getlocaltime Function628172 +Node: Readfile Function631916 +Node: Shell Quoting633888 +Node: Data File Management635289 +Node: Filetrans Function635921 +Node: Rewind Function640017 +Node: File Checking641403 +Ref: File Checking-Footnote-1642736 +Node: Empty Files642937 +Node: Ignoring Assigns644916 +Node: Getopt Function646466 +Ref: Getopt Function-Footnote-1657930 +Node: Passwd Functions658130 +Ref: Passwd Functions-Footnote-1666970 +Node: Group Functions667058 +Ref: Group Functions-Footnote-1674955 +Node: Walking Arrays675160 +Node: Library Functions Summary676760 +Node: Library Exercises678164 +Node: Sample Programs679444 +Node: Running Examples680214 +Node: Clones680942 +Node: Cut Program682166 +Node: Egrep Program691886 +Ref: Egrep Program-Footnote-1699389 +Node: Id Program699499 +Node: Split Program703175 +Ref: Split Program-Footnote-1706629 +Node: Tee Program706757 +Node: Uniq Program709546 +Node: Wc Program716965 +Ref: Wc Program-Footnote-1721215 +Node: Miscellaneous Programs721309 +Node: Dupword Program722522 +Node: Alarm Program724553 +Node: Translate Program729358 +Ref: Translate Program-Footnote-1733921 +Node: Labels Program734191 +Ref: Labels Program-Footnote-1737542 +Node: Word Sorting737626 +Node: History Sorting741696 +Node: Extract Program743531 +Node: Simple Sed751055 +Node: Igawk Program754125 +Ref: Igawk Program-Footnote-1768451 +Ref: Igawk Program-Footnote-2768652 +Ref: Igawk Program-Footnote-3768774 +Node: Anagram Program768889 +Node: Signature Program771950 +Node: Programs Summary773197 +Node: Programs Exercises774418 +Ref: Programs Exercises-Footnote-1778549 +Node: Advanced Features778640 +Node: Nondecimal Data780622 +Node: Array Sorting782212 +Node: Controlling Array Traversal782912 +Ref: Controlling Array Traversal-Footnote-1791278 +Node: Array Sorting Functions791396 +Ref: Array Sorting Functions-Footnote-1795282 +Node: Two-way I/O795478 +Ref: Two-way I/O-Footnote-1800423 +Ref: Two-way I/O-Footnote-2800609 +Node: TCP/IP Networking800691 +Node: Profiling803563 +Node: Advanced Features Summary811834 +Node: Internationalization813767 +Node: I18N and L10N815247 +Node: Explaining gettext815933 +Ref: Explaining gettext-Footnote-1820958 +Ref: Explaining gettext-Footnote-2821142 +Node: Programmer i18n821307 +Ref: Programmer i18n-Footnote-1826183 +Node: Translator i18n826232 +Node: String Extraction827026 +Ref: String Extraction-Footnote-1828157 +Node: Printf Ordering828243 +Ref: Printf Ordering-Footnote-1831029 +Node: I18N Portability831093 +Ref: I18N Portability-Footnote-1833549 +Node: I18N Example833612 +Ref: I18N Example-Footnote-1836415 +Node: Gawk I18N836487 +Node: I18N Summary837131 +Node: Debugger838471 +Node: Debugging839493 +Node: Debugging Concepts839934 +Node: Debugging Terms841744 +Node: Awk Debugging844316 +Node: Sample Debugging Session845222 +Node: Debugger Invocation845756 +Node: Finding The Bug847141 +Node: List of Debugger Commands853620 +Node: Breakpoint Control854952 +Node: Debugger Execution Control858629 +Node: Viewing And Changing Data861988 +Node: Execution Stack865364 +Node: Debugger Info866999 +Node: Miscellaneous Debugger Commands871044 +Node: Readline Support876045 +Node: Limitations876939 +Node: Debugging Summary879054 +Node: Arbitrary Precision Arithmetic880228 +Node: Computer Arithmetic881644 +Ref: table-numeric-ranges885242 +Ref: Computer Arithmetic-Footnote-1886101 +Node: Math Definitions886158 +Ref: table-ieee-formats889446 +Ref: Math Definitions-Footnote-1890050 +Node: MPFR features890155 +Node: FP Math Caution891826 +Ref: FP Math Caution-Footnote-1892876 +Node: Inexactness of computations893245 +Node: Inexact representation894204 +Node: Comparing FP Values895561 +Node: Errors accumulate896643 +Node: Getting Accuracy898076 +Node: Try To Round900738 +Node: Setting precision901637 +Ref: table-predefined-precision-strings902321 +Node: Setting the rounding mode904110 +Ref: table-gawk-rounding-modes904474 +Ref: Setting the rounding mode-Footnote-1907929 +Node: Arbitrary Precision Integers908108 +Ref: Arbitrary Precision Integers-Footnote-1913008 +Node: POSIX Floating Point Problems913157 +Ref: POSIX Floating Point Problems-Footnote-1917030 +Node: Floating point summary917068 +Node: Dynamic Extensions919262 +Node: Extension Intro920814 +Node: Plugin License922080 +Node: Extension Mechanism Outline922877 +Ref: figure-load-extension923305 +Ref: figure-register-new-function924785 +Ref: figure-call-new-function925789 +Node: Extension API Description927775 +Node: Extension API Functions Introduction929225 +Node: General Data Types934049 +Ref: General Data Types-Footnote-1939788 +Node: Memory Allocation Functions940087 +Ref: Memory Allocation Functions-Footnote-1942926 +Node: Constructor Functions943022 +Node: Registration Functions944756 +Node: Extension Functions945441 +Node: Exit Callback Functions947738 +Node: Extension Version String948986 +Node: Input Parsers949651 +Node: Output Wrappers959530 +Node: Two-way processors964045 +Node: Printing Messages966249 +Ref: Printing Messages-Footnote-1967325 +Node: Updating `ERRNO'967477 +Node: Requesting Values968217 +Ref: table-value-types-returned968945 +Node: Accessing Parameters969902 +Node: Symbol Table Access971133 +Node: Symbol table by name971647 +Node: Symbol table by cookie973628 +Ref: Symbol table by cookie-Footnote-1977772 +Node: Cached values977835 +Ref: Cached values-Footnote-1981334 +Node: Array Manipulation981425 +Ref: Array Manipulation-Footnote-1982523 +Node: Array Data Types982560 +Ref: Array Data Types-Footnote-1985215 +Node: Array Functions985307 +Node: Flattening Arrays989161 +Node: Creating Arrays996053 +Node: Extension API Variables1000824 +Node: Extension Versioning1001460 +Node: Extension API Informational Variables1003361 +Node: Extension API Boilerplate1004426 +Node: Finding Extensions1008235 +Node: Extension Example1008795 +Node: Internal File Description1009567 +Node: Internal File Ops1013634 +Ref: Internal File Ops-Footnote-11025304 +Node: Using Internal File Ops1025444 +Ref: Using Internal File Ops-Footnote-11027827 +Node: Extension Samples1028100 +Node: Extension Sample File Functions1029626 +Node: Extension Sample Fnmatch1037264 +Node: Extension Sample Fork1038755 +Node: Extension Sample Inplace1039970 +Node: Extension Sample Ord1041645 +Node: Extension Sample Readdir1042481 +Ref: table-readdir-file-types1043357 +Node: Extension Sample Revout1044168 +Node: Extension Sample Rev2way1044758 +Node: Extension Sample Read write array1045498 +Node: Extension Sample Readfile1047438 +Node: Extension Sample Time1048533 +Node: Extension Sample API Tests1049882 +Node: gawkextlib1050373 +Node: Extension summary1053031 +Node: Extension Exercises1056720 +Node: Language History1057442 +Node: V7/SVR3.11059098 +Node: SVR41061279 +Node: POSIX1062724 +Node: BTL1064113 +Node: POSIX/GNU1064847 +Node: Feature History1070728 +Node: Common Extensions1084522 +Node: Ranges and Locales1085846 +Ref: Ranges and Locales-Footnote-11090464 +Ref: Ranges and Locales-Footnote-21090491 +Ref: Ranges and Locales-Footnote-31090725 +Node: Contributors1090946 +Node: History summary1096487 +Node: Installation1097857 +Node: Gawk Distribution1098803 +Node: Getting1099287 +Node: Extracting1100110 +Node: Distribution contents1101745 +Node: Unix Installation1107810 +Node: Quick Installation1108493 +Node: Shell Startup Files1110904 +Node: Additional Configuration Options1111983 +Node: Configuration Philosophy1113722 +Node: Non-Unix Installation1116091 +Node: PC Installation1116549 +Node: PC Binary Installation1117868 +Node: PC Compiling1119716 +Ref: PC Compiling-Footnote-11122737 +Node: PC Testing1122846 +Node: PC Using1124022 +Node: Cygwin1128137 +Node: MSYS1128960 +Node: VMS Installation1129460 +Node: VMS Compilation1130252 +Ref: VMS Compilation-Footnote-11131474 +Node: VMS Dynamic Extensions1131532 +Node: VMS Installation Details1133216 +Node: VMS Running1135468 +Node: VMS GNV1138304 +Node: VMS Old Gawk1139038 +Node: Bugs1139508 +Node: Other Versions1143391 +Node: Installation summary1149815 +Node: Notes1150871 +Node: Compatibility Mode1151736 +Node: Additions1152518 +Node: Accessing The Source1153443 +Node: Adding Code1154878 +Node: New Ports1161035 +Node: Derived Files1165517 +Ref: Derived Files-Footnote-11170992 +Ref: Derived Files-Footnote-21171026 +Ref: Derived Files-Footnote-31171622 +Node: Future Extensions1171736 +Node: Implementation Limitations1172342 +Node: Extension Design1173590 +Node: Old Extension Problems1174744 +Ref: Old Extension Problems-Footnote-11176261 +Node: Extension New Mechanism Goals1176318 +Ref: Extension New Mechanism Goals-Footnote-11179678 +Node: Extension Other Design Decisions1179867 +Node: Extension Future Growth1181975 +Node: Old Extension Mechanism1182811 +Node: Notes summary1184573 +Node: Basic Concepts1185759 +Node: Basic High Level1186440 +Ref: figure-general-flow1186712 +Ref: figure-process-flow1187311 +Ref: Basic High Level-Footnote-11190540 +Node: Basic Data Typing1190725 +Node: Glossary1194053 +Node: Copying1225982 +Node: GNU Free Documentation License1263538 +Node: Index1288674 End Tag Table diff --git a/doc/gawk.texi b/doc/gawk.texi index e0023245..81568fe7 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -55,8 +55,9 @@ @set VERSION 4.1 @set PATCHLEVEL 2 +@set GAWKINETTITLE TCP/IP Internetworking with @command{gawk} @ifset FOR_PRINT -@set TITLE Effective Awk Programming +@set TITLE Effective awk Programming @end ifset @ifclear FOR_PRINT @set TITLE GAWK: Effective AWK Programming @@ -207,7 +208,7 @@ @set FFN Filename @set DF datafile @set DDF Datafile -@set PVERSION Version +@set PVERSION version @end ifset @c For HTML, spell out email addresses, to avoid problems with @@ -304,7 +305,7 @@ All Rights Reserved.</literallayout> @end docbook @ifnotdocbook -Copyright @copyright{} 1989, 1991, 1992, 1993, 1996--2005, 2007, 2009--2014 @* +Copyright @copyright{} 1989, 1991, 1992, 1993, 1996--2005, 2007, 2009--2015 @* Free Software Foundation, Inc. @end ifnotdocbook @sp 2 @@ -472,7 +473,7 @@ particular records in a file and perform operations upon them. @command{gawk}. * Internationalization:: Getting @command{gawk} to speak your language. -* Debugger:: The @code{gawk} debugger. +* Debugger:: The @command{gawk} debugger. * Arbitrary Precision Arithmetic:: Arbitrary precision arithmetic with @command{gawk}. * Dynamic Extensions:: Adding new built-in functions to @@ -956,7 +957,7 @@ particular records in a file and perform operations upon them. * Internal File Ops:: The code for internal file operations. * Using Internal File Ops:: How to use an external extension. * Extension Samples:: The sample extensions that ship with - @code{gawk}. + @command{gawk}. * Extension Sample File Functions:: The file functions sample. * Extension Sample Fnmatch:: An interface to @code{fnmatch()}. * Extension Sample Fork:: An interface to @code{fork()} and @@ -1171,7 +1172,7 @@ interface to network protocols via special @file{/inet} files. The programs in this book make clear that an AWK program is typically much smaller and faster to develop than a counterpart written in C. -Consequently, there is often a payoff to prototype an +Consequently, there is often a payoff to prototyping an algorithm or design in AWK to get it running quickly and expose problems early. Often, the interpreted performance is adequate and the AWK prototype becomes the product. @@ -1248,15 +1249,15 @@ March 2001 Some things don't change. Thirteen years ago I wrote: ``If you use AWK or want to learn how, then read this book.'' -True then and still true today. +True then, and still true today. -Learning to use a programming language is more than mastering the +Learning to use a programming language is about more than mastering the syntax. One needs to acquire an understanding of how to use the features of the language to solve practical programming problems. A focus of this book is many examples that show how to use AWK. Some things do change. Our computers are much faster and have more memory. -Consequently, speed and storage inefficiencies of a high level language +Consequently, speed and storage inefficiencies of a high-level language matter less. Prototyping in AWK and then rewriting in C for performance reasons happens less, because more often the prototype is fast enough. @@ -1264,12 +1265,12 @@ Of course, there are computing operations that are best done in C or C++. With @command{gawk} 4.1 and later, you do not have to choose between writing your program in AWK or in C/C++. You can write most of your program in AWK and the aspects that require C/C++ capabilities can be written -in C/C++ and then the pieces glued together when the @command{gawk} module loads +in C/C++, and then the pieces glued together when the @command{gawk} module loads the C/C++ module as a dynamic plug-in. @c Chapter 16 @ref{Dynamic Extensions}, has all the -details, and as expected, many examples to help you learn the ins and outs. +details, and, as expected, many examples to help you learn the ins and outs. I enjoy programming in AWK and had fun (re)reading this book. I think you will too. @@ -1344,7 +1345,7 @@ Generate reports Validate data @item -Produce indexes and perform other document preparation tasks +Produce indexes and perform other document-preparation tasks @item Experiment with algorithms that you can adapt later to other computer @@ -1491,23 +1492,23 @@ help from me, thoroughly reworked @command{gawk} for compatibility with the newer @command{awk}. Circa 1994, I became the primary maintainer. Current development focuses on bug fixes, -performance improvements, standards compliance and, occasionally, new features. +performance improvements, standards compliance, and, occasionally, new features. In May 1997, J@"urgen Kahrs felt the need for network access from @command{awk}, and with a little help from me, set about adding features to do this for @command{gawk}. At that time, he also wrote the bulk of -@cite{TCP/IP Internetworking with @command{gawk}} +@cite{@value{GAWKINETTITLE}} (a separate document, available as part of the @command{gawk} distribution). His code finally became part of the main @command{gawk} distribution with @command{gawk} @value{PVERSION} 3.1. John Haque rewrote the @command{gawk} internals, in the process providing an @command{awk}-level debugger. This version became available as -@command{gawk} @value{PVERSION} 4.0, in 2011. +@command{gawk} @value{PVERSION} 4.0 in 2011. @DBXREF{Contributors} -for a full list of those who made important contributions to @command{gawk}. +for a full list of those who have made important contributions to @command{gawk}. @node Names @unnumberedsec A Rose by Any Other Name @@ -1520,7 +1521,7 @@ is often referred to as ``new @command{awk}.'' By analogy, the original version of @command{awk} is referred to as ``old @command{awk}.'' -Today, on most systems, when you run the @command{awk} utility, +Today, on most systems, when you run the @command{awk} utility you get some version of new @command{awk}.@footnote{Only Solaris systems still use an old @command{awk} for the default @command{awk} utility. A more modern @command{awk} lives in @@ -1580,7 +1581,9 @@ the POSIX standard for @command{awk}. This @value{DOCUMENT} has the difficult task of being both a tutorial and a reference. If you are a novice, feel free to skip over details that seem too complex. You should also ignore the many cross-references; they are for the -expert user and for the online Info and HTML versions of the @value{DOCUMENT}. +expert user and for the Info and +@uref{http://www.gnu.org/software/gawk/manual/, HTML} +versions of the @value{DOCUMENT}. @end ifnotinfo There are sidebars @@ -1613,7 +1616,7 @@ This @value{DOCUMENT} is split into several parts, as follows: @itemize @value{BULLET} @item -Part I describes the @command{awk} language and @command{gawk} program in detail. +Part I describes the @command{awk} language and the @command{gawk} program in detail. It starts with the basics, and continues through all of the features of @command{awk}. It contains the following chapters: @@ -1660,10 +1663,10 @@ doing something when a record is matched, and the predefined variables @item @ref{Arrays}, -covers @command{awk}'s one-and-only data structure: associative arrays. -Deleting array elements and whole arrays is also described, as well as -sorting arrays in @command{gawk}. It also describes how @command{gawk} -provides arrays of arrays. +covers @command{awk}'s one-and-only data structure: the associative array. +Deleting array elements and whole arrays is described, as well as +sorting arrays in @command{gawk}. The @value{CHAPTER} also describes how +@command{gawk} provides arrays of arrays. @item @ref{Functions}, @@ -1675,17 +1678,17 @@ as well as how to define your own functions. It also discusses how @item Part II shows how to use @command{awk} and @command{gawk} for problem solving. There is lots of code here for you to read and learn from. -It contains the following chapters: +This part contains the following chapters: @c nested @itemize @value{MINUS} @item -@ref{Library Functions}, which provides a number of functions meant to +@ref{Library Functions}, provides a number of functions meant to be used from main @command{awk} programs. @item @ref{Sample Programs}, -which provides many sample @command{awk} programs. +provides many sample @command{awk} programs. @end itemize Reading these two chapters allows you to see @command{awk} @@ -1738,7 +1741,7 @@ including the GNU General Public License: @item @ref{Language History}, describes how the @command{awk} language has evolved since -its first release to present. It also describes how @command{gawk} +its first release to the present. It also describes how @command{gawk} has acquired features over time. @item @@ -1781,7 +1784,7 @@ are completely unfamiliar with computer programming. @item @uref{http://www.gnu.org/software/gawk/manual/html_node/Glossary.html, The Glossary} -defines most, if not all of, the significant terms used +defines most, if not all, of the significant terms used throughout the @value{DOCUMENT}. If you find terms that you aren't familiar with, try looking them up here. @@ -1808,7 +1811,7 @@ and some possible future directions for @command{gawk} development. provides some very cursory background material for those who are completely unfamiliar with computer programming. -The @ref{Glossary}, defines most, if not all of, the significant terms used +The @ref{Glossary}, defines most, if not all, of the significant terms used throughout the @value{DOCUMENT}. If you find terms that you aren't familiar with, try looking them up here. @@ -1851,7 +1854,7 @@ This typically represents the command's standard output. Output from the command, usually its standard output, appears @code{like this}. @end ifset -Error messages, and other output on the command's standard error, are preceded +Error messages and other output on the command's standard error are preceded by the glyph ``@error{}''. For example: @example @@ -1878,7 +1881,7 @@ there are special characters called ``control characters.'' These are characters that you type by holding down both the @kbd{CONTROL} key and another key, at the same time. For example, a @kbd{Ctrl-d} is typed by first pressing and holding the @kbd{CONTROL} key, next -pressing the @kbd{d} key and finally releasing both keys. +pressing the @kbd{d} key, and finally releasing both keys. For the sake of brevity, throughout this @value{DOCUMENT}, we refer to Brian Kernighan's version of @command{awk} as ``BWK @command{awk}.'' @@ -1914,7 +1917,7 @@ the picture of a flashlight in the margin, as shown here. @value{DARKCORNER} @end iftex @ifnottex -``(d.c.)''. +``(d.c.).'' @end ifnottex @ifclear FOR_PRINT They also appear in the index under the heading ``dark corner.'' @@ -1949,12 +1952,12 @@ Emacs editor. GNU Emacs is the most widely used version of Emacs today. @cindex GPL (General Public License) @cindex General Public License, See GPL @cindex documentation, online -The GNU@footnote{GNU stands for ``GNU's not Unix.''} +The GNU@footnote{GNU stands for ``GNU's Not Unix.''} Project is an ongoing effort on the part of the Free Software Foundation to create a complete, freely distributable, POSIX-compliant computing environment. -The FSF uses the ``GNU General Public License'' (GPL) to ensure that -their software's +The FSF uses the GNU General Public License (GPL) to ensure that +its software's source code is always available to the end user. @ifclear FOR_PRINT A copy of the GPL is included @@ -2014,7 +2017,7 @@ version of @command{awk}. I started working with that version in the fall of 1988. As work on it progressed, the FSF published several preliminary versions (numbered 0.@var{x}). -In 1996, Edition 1.0 was released with @command{gawk} 3.0.0. +In 1996, edition 1.0 was released with @command{gawk} 3.0.0. The FSF published the first two editions under the title @cite{The GNU Awk User's Guide}. @ifset FOR_PRINT @@ -2026,7 +2029,7 @@ the third edition in 2001. This edition maintains the basic structure of the previous editions. For FSF edition 4.0, the content was thoroughly reviewed and updated. All references to @command{gawk} versions prior to 4.0 were removed. -Of significant note for that edition was @ref{Debugger}. +Of significant note for that edition was the addition of @ref{Debugger}. For FSF edition @ifclear FOR_PRINT @@ -2041,7 +2044,7 @@ and the major new additions are @ref{Arbitrary Precision Arithmetic}, and @ref{Dynamic Extensions}. This @value{DOCUMENT} will undoubtedly continue to evolve. If you -find an error in this @value{DOCUMENT}, please report it! @DBXREF{Bugs} +find an error in the @value{DOCUMENT}, please report it! @DBXREF{Bugs} for information on submitting problem reports electronically. @ifset FOR_PRINT @@ -2051,7 +2054,7 @@ for information on submitting problem reports electronically. You may have a newer version of @command{gawk} than the one described here. To find out what has changed, you should first look at the @file{NEWS} file in the @command{gawk} -distribution, which provides a high-level summary of what changed in +distribution, which provides a high-level summary of the changes in each release. You can then look at the @uref{http://www.gnu.org/software/gawk/manual/, @@ -2105,7 +2108,7 @@ The initial draft of @cite{The GAWK Manual} had the following acknowledgments: Many people need to be thanked for their assistance in producing this manual. Jay Fenlason contributed many ideas and sample programs. Richard Mlynarik and Robert Chassell gave helpful comments on drafts of this -manual. The paper @cite{A Supplemental Document for @command{awk}} by John W.@: +manual. The paper @cite{A Supplemental Document for AWK} by John W.@: Pierce of the Chemistry Department at UC San Diego, pinpointed several issues relevant both to @command{awk} implementation and to this manual, that would otherwise have escaped us. @@ -2116,12 +2119,18 @@ I would like to acknowledge Richard M.@: Stallman, for his vision of a better world and for his courage in founding the FSF and starting the GNU Project. +@ifclear FOR_PRINT Earlier editions of this @value{DOCUMENT} had the following acknowledgements: +@end ifclear +@ifset FOR_PRINT +The previous edition of this @value{DOCUMENT} had +the following acknowledgements: +@end ifset @quotation The following people (in alphabetical order) provided helpful comments on various -versions of this book, +versions of this book: Rick Adams, Dr.@: Nelson H.F. Beebe, Karl Berry, @@ -2149,7 +2158,7 @@ Robert J.@: Chassell provided much valuable advice on the use of Texinfo. He also deserves special thanks for convincing me @emph{not} to title this @value{DOCUMENT} -@cite{How To Gawk Politely}. +@cite{How to Gawk Politely}. Karl Berry helped significantly with the @TeX{} part of Texinfo. @cindex Hartholz, Marshall @@ -2233,9 +2242,9 @@ a number of people. @DBXREF{Contributors} for the full list. @ifset FOR_PRINT @cindex Oram, Andy -Thanks to Andy Oram, of O'Reilly Media, for initiating +Thanks to Andy Oram of O'Reilly Media for initiating the fourth edition and for his support during the work. -Thanks to Jasmine Kwityn for her copy-editing work. +Thanks to Jasmine Kwityn for her copyediting work. @end ifset Thanks to Michael Brennan for the Forewords. @@ -2243,7 +2252,7 @@ Thanks to Michael Brennan for the Forewords. @cindex Duman, Patrice @cindex Berry, Karl Thanks to Patrice Dumas for the new @command{makeinfo} program. -Thanks to Karl Berry who continues to work to keep +Thanks to Karl Berry, who continues to work to keep the Texinfo markup language sane. @cindex Kernighan, Brian @@ -2253,8 +2262,8 @@ Robert P.J.@: Day, Michael Brennan, and Brian Kernighan kindly acted as reviewers for the 2015 edition of this @value{DOCUMENT}. Their feedback helped improve the final work. -I would like to thank Brian Kernighan for invaluable assistance during the -testing and debugging of @command{gawk}, and for ongoing +I would also like to thank Brian Kernighan for his invaluable assistance during the +testing and debugging of @command{gawk}, and for his ongoing help and advice in clarifying numerous points about the language. We could not have done nearly as good a job on either @command{gawk} or its documentation without his help. @@ -2365,9 +2374,9 @@ an advanced feature that we will ignore for now; pattern to search for and one action to perform upon finding the pattern. -Syntactically, a rule consists of a pattern followed by an action. The -action is enclosed in braces to separate it from the pattern. -Newlines usually separate rules. Therefore, an @command{awk} +Syntactically, a rule consists of a @dfn{pattern} followed by an +@dfn{action}. The action is enclosed in braces to separate it from the +pattern. Newlines usually separate rules. Therefore, an @command{awk} program looks like this: @example @@ -2441,8 +2450,8 @@ awk '@var{program}' @var{input-file1} @var{input-file2} @dots{} @end example @noindent -where @var{program} consists of a series of @var{patterns} and -@var{actions}, as described earlier. +where @var{program} consists of a series of patterns and +actions, as described earlier. @cindex single quote (@code{'}) @cindex @code{'} (single quote) @@ -2461,12 +2470,12 @@ programs from shell scripts, because it avoids the need for a separate file for the @command{awk} program. A self-contained shell script is more reliable because there are no other files to misplace. -Later in this chapter, +Later in this chapter, in @ifdocbook the section @end ifdocbook @ref{Very Simple}, -presents several short, +we'll see examples of several short, self-contained programs. @node Read Terminal @@ -2487,10 +2496,10 @@ awk '@var{program}' which usually means whatever you type on the keyboard. This continues until you indicate end-of-file by typing @kbd{Ctrl-d}. @ifset FOR_PRINT -(On other operating systems, the end-of-file character may be different.) +(On non-POSIX operating systems, the end-of-file character may be different.) @end ifset @ifclear FOR_PRINT -(On other operating systems, the end-of-file character may be different. +(On non-POSIX operating systems, the end-of-file character may be different. For example, on OS/2, it is @kbd{Ctrl-z}.) @end ifclear @@ -2590,11 +2599,9 @@ for programs that are provided on the @command{awk} command line. (Also, placing the program in a file allows us to use a literal single quote in the program text, instead of the magic @samp{\47}.) -@c STARTOFRANGE sq1x @cindex single quote (@code{'}) in @command{gawk} command lines -@c STARTOFRANGE qs2x @cindex @code{'} (single quote) in @command{gawk} command lines -If you want to clearly identify your @command{awk} program files as such, +If you want to clearly identify an @command{awk} program file as such, you can add the extension @file{.awk} to the @value{FN}. This doesn't affect the execution of the @command{awk} program but it does make ``housekeeping'' easier. @@ -2808,7 +2815,7 @@ The next @value{SUBSECTION} describes the shell's quoting rules. @end quotation @node Quoting -@subsection Shell-Quoting Issues +@subsection Shell Quoting Issues @cindex shell quoting, rules for @menu @@ -2945,7 +2952,7 @@ $ @kbd{awk 'BEGIN @{ print "Here is a single quote <'"'"'>" @}'} @noindent This program consists of three concatenated quoted strings. The first and the -third are single quoted, the second is double quoted. +third are single-quoted, and the second is double-quoted. This can be ``simplified'' to: @@ -2966,8 +2973,6 @@ $ @kbd{awk "BEGIN @{ print \"Here is a single quote <'>\" @}"} @end example @noindent -@c ENDOFRANGE sq1x -@c ENDOFRANGE qs2x This option is also painful, because double quotes, backslashes, and dollar signs are very common in more advanced @command{awk} programs. @@ -2984,7 +2989,7 @@ $ @kbd{awk 'BEGIN @{ print "Here is a double quote <\42>" @}'} @end example @noindent -This works nicely, except that you should comment clearly what the +This works nicely, but you should comment clearly what the escapes mean. A fourth option is to use command-line variable assignment, like this: @@ -2995,11 +3000,11 @@ $ @kbd{awk -v sq="'" 'BEGIN @{ print "Here is a single quote <" sq ">" @}'} @end example (Here, the two string constants and the value of @code{sq} are concatenated -into a single string which is printed by @code{print}.) +into a single string that is printed by @code{print}.) If you really need both single and double quotes in your @command{awk} program, it is probably best to move it into a separate file, where -the shell won't be part of the picture, and you can say what you mean. +the shell won't be part of the picture and you can say what you mean. @node DOS Quoting @subsubsection Quoting in MS-Windows Batch Files @@ -3098,7 +3103,7 @@ of green crates shipped, the number of red boxes shipped, the number of orange bags shipped, and the number of blue packages shipped, respectively. There are 16 entries, covering the 12 months of last year and the first four months of the current year. -An empty line separates the data for the two years. +An empty line separates the data for the two years: @example @c file eg/data/inventory-shipped @@ -3132,7 +3137,7 @@ The following command runs a simple @command{awk} program that searches the input file @file{mail-list} for the character string @samp{li} (a grouping of characters is usually called a @dfn{string}; the term @dfn{string} is based on similar usage in English, such -as ``a string of pearls,'' or ``a string of cars in a train''): +as ``a string of pearls'' or ``a string of cars in a train''): @example awk '/li/ @{ print $0 @}' mail-list @@ -3179,7 +3184,7 @@ omitting the @code{print} statement but retaining the braces makes an empty action that does nothing (i.e., no lines are printed). @cindex @command{awk} programs, one-line examples -Many practical @command{awk} programs are just a line or two. Following is a +Many practical @command{awk} programs are just a line or two long. Following is a collection of useful, short programs to get you started. Some of these programs contain constructs that haven't been covered yet. (The description of the program will give you a good idea of what is going on, but you'll @@ -3200,7 +3205,7 @@ Print every line that is longer than 80 characters: awk 'length($0) > 80' data @end example -The sole rule has a relational expression as its pattern and it has no +The sole rule has a relational expression as its pattern and has no action---so it uses the default action, printing the record. @item @@ -3287,7 +3292,7 @@ Print the even-numbered lines in the @value{DF}: awk 'NR % 2 == 0' data @end example -If you use the expression @samp{NR % 2 == 1} instead, +If you used the expression @samp{NR % 2 == 1} instead, the program would print the odd-numbered lines. @end itemize @@ -3303,8 +3308,13 @@ no actions run. After processing all the rules that match the line (and perhaps there are none), @command{awk} reads the next line. (However, -@pxref{Next Statement}, +@DBPXREF{Next Statement} +@ifdocbook +and @DBREF{Nextfile Statement}.) +@end ifdocbook +@ifnotdocbook and also @pxref{Nextfile Statement}.) +@end ifnotdocbook This continues until the program reaches the end of the file. For example, the following @command{awk} program contains two rules: @@ -3569,7 +3579,7 @@ performing bit manipulation, for runtime string translation (internationalizatio determining the type of a variable, and array sorting. -As we develop our presentation of the @command{awk} language, we introduce +As we develop our presentation of the @command{awk} language, we will introduce most of the variables and many of the functions. They are described systematically in @DBREF{Built-in Variables} and in @ref{Built-in}. @@ -3623,7 +3633,7 @@ and Perl.} @c FIXME: Review this chapter for summary of builtin functions called. @itemize @value{BULLET} @item -Programs in @command{awk} consist of @var{pattern}-@var{action} pairs. +Programs in @command{awk} consist of @var{pattern}--@var{action} pairs. @item An @var{action} without a @var{pattern} always runs. The default @@ -3652,7 +3662,7 @@ part of a larger shell script (or MS-Windows batch file). You may use backslash continuation to continue a source line. Lines are automatically continued after a comma, open brace, question mark, colon, -@samp{||}, @samp{&&}, @code{do} and @code{else}. +@samp{||}, @samp{&&}, @code{do}, and @code{else}. @end itemize @node Invoking Gawk @@ -3727,20 +3737,16 @@ warning that the program is empty. @node Options @section Command-Line Options -@c STARTOFRANGE ocl @cindex options, command-line -@c STARTOFRANGE clo @cindex command line, options -@c STARTOFRANGE gnulo @cindex GNU long options -@c STARTOFRANGE longo @cindex options, long Options begin with a dash and consist of a single character. GNU-style long options consist of two dashes and a keyword. The keyword can be abbreviated, as long as the abbreviation allows the option -to be uniquely identified. If the option takes an argument, then the -keyword is either immediately followed by an equals sign (@samp{=}) and the +to be uniquely identified. If the option takes an argument, either the +keyword is immediately followed by an equals sign (@samp{=}) and the argument's value, or the keyword and the argument's value are separated by whitespace. If a particular option with a value is given more than once, it is the @@ -3767,7 +3773,7 @@ Set the @code{FS} variable to @var{fs} @cindex @option{-f} option @cindex @option{--file} option @cindex @command{awk} programs, location of -Read @command{awk} program source from @var{source-file} +Read the @command{awk} program source from @var{source-file} instead of in the first nonoption argument. This option may be given multiple times; the @command{awk} program consists of the concatenation of the contents of @@ -3822,8 +3828,6 @@ by the user that could start with @samp{-}. It is also useful for passing options on to the @command{awk} program; see @ref{Getopt Function}. @end table -@c ENDOFRANGE gnulo -@c ENDOFRANGE longo The following list describes @command{gawk}-specific options: @@ -3835,14 +3839,14 @@ The following list describes @command{gawk}-specific options: @cindex @option{--characters-as-bytes} option Cause @command{gawk} to treat all input data as single-byte characters. In addition, all output written with @code{print} or @code{printf} -are treated as single-byte characters. +is treated as single-byte characters. Normally, @command{gawk} follows the POSIX standard and attempts to process its input data according to the current locale (@pxref{Locales}). This can often involve converting multibyte characters into wide characters (internally), and can lead to problems or confusion if the input data does not contain valid -multibyte characters. This option is an easy way to tell @command{gawk}: -``hands off my data!''. +multibyte characters. This option is an easy way to tell @command{gawk}, +``Hands off my data!'' @item @option{-c} @itemx @option{--traditional} @@ -3899,7 +3903,7 @@ Enable debugging of @command{awk} programs By default, the debugger reads commands interactively from the keyboard (standard input). The optional @var{file} argument allows you to specify a file with a list -of commands for the debugger to execute non-interactively. +of commands for the debugger to execute noninteractively. No space is allowed between the @option{-D} and @var{file}, if @var{file} is supplied. @@ -3959,7 +3963,7 @@ with @samp{#!} scripts (@pxref{Executable Scripts}), like so: @cindex portable object files, generating @cindex files, portable object, generating Analyze the source program and -generate a GNU @command{gettext} Portable Object Template file on standard +generate a GNU @command{gettext} portable object template file on standard output for all string constants that have been marked for translation. @xref{Internationalization}, for information about this option. @@ -3971,7 +3975,7 @@ for information about this option. @cindex GNU long options, printing list of @cindex options, printing list of @cindex printing, list of options -Print a ``usage'' message summarizing the short and long style options +Print a ``usage'' message summarizing the short- and long-style options that @command{gawk} accepts and then exit. @item @option{-i} @var{source-file} @@ -3981,7 +3985,7 @@ that @command{gawk} accepts and then exit. @cindex @command{awk} programs, location of Read an @command{awk} source library from @var{source-file}. This option is completely equivalent to using the @code{@@include} directive inside -your program. This option is very similar to the @option{-f} option, +your program. It is very similar to the @option{-f} option, but there are two important differences. First, when @option{-i} is used, the program source is not loaded if it has been previously loaded, whereas with @option{-f}, @command{gawk} always loads the file. @@ -4066,7 +4070,7 @@ when parsing numeric input data (@pxref{Locales}). @cindex @option{-o} option @cindex @option{--pretty-print} option Enable pretty-printing of @command{awk} programs. -By default, output program is created in a file named @file{awkprof.out} +By default, the output program is created in a file named @file{awkprof.out} (@pxref{Profiling}). The optional @var{file} argument allows you to specify a different @value{FN} for the output. @@ -4110,7 +4114,7 @@ in the left margin, and function call counts for each function. Operate in strict POSIX mode. This disables all @command{gawk} extensions (just like @option{--traditional}) and disables all extensions not allowed by POSIX. -@xref{Common Extensions}, for a summary of the extensions +@DBXREF{Common Extensions} for a summary of the extensions in @command{gawk} that are disabled by this option. Also, the following additional @@ -4231,7 +4235,7 @@ source of data.) Because it is clumsy using the standard @command{awk} mechanisms to mix source file and command-line @command{awk} programs, @command{gawk} provides the @option{-e} option. This does not require you to -pre-empt the standard input for your source code; it allows you to easily +preempt the standard input for your source code; it allows you to easily mix command-line and library source code (@pxref{AWKPATH Variable}). As with @option{-f}, the @option{-e} and @option{-i} options may also be used multiple times on the command line. @@ -4277,8 +4281,6 @@ setenv POSIXLY_CORRECT true Having @env{POSIXLY_CORRECT} set is not recommended for daily use, but it is good for testing the portability of your programs to other environments. -@c ENDOFRANGE ocl -@c ENDOFRANGE clo @node Other Arguments @section Other Command-Line Arguments @@ -4421,7 +4423,7 @@ file, unless the file is in the current directory. But with @command{gawk}, if the @value{FN} supplied to the @option{-f} or @option{-i} options does not contain a directory separator @samp{/}, then @command{gawk} searches a list of -directories (called the @dfn{search path}), one by one, looking for a +directories (called the @dfn{search path}) one by one, looking for a file with the specified name. The search path is a string consisting of directory names @@ -4462,9 +4464,9 @@ as an entry in the path or write a null entry in the path. Different past versions of @command{gawk} would also look explicitly in the current directory, either before or after the path search. As of -@value{PVERSION} 4.1.2, this no longer happens, and if you wish to look +@value{PVERSION} 4.1.2, this no longer happens; if you wish to look in the current directory, you must include @file{.} either as a separate -entry, or as a null entry in the search path. +entry or as a null entry in the search path. @end quotation The default value for @env{AWKPATH} is @@ -4580,7 +4582,7 @@ If this variable exists, @command{gawk} includes the @value{FN} and line number within the @command{gawk} source code from which warning and/or fatal messages are generated. Its purpose is to help isolate the source of a -message, as there are multiple places which produce the +message, as there are multiple places that produce the same warning or error message. @item GAWK_NO_DFA @@ -4596,16 +4598,16 @@ This specifies the amount by which @command{gawk} should grow its internal evaluation stack, when needed. @item INT_CHAIN_MAX -The intended maximum number of items @command{gawk} will maintain on a +This specifies intended maximum number of items @command{gawk} will maintain on a hash chain for managing arrays indexed by integers. @item STR_CHAIN_MAX -The intended maximum number of items @command{gawk} will maintain on a +This specifies intended maximum number of items @command{gawk} will maintain on a hash chain for managing arrays indexed by strings. @item TIDYMEM If this variable exists, @command{gawk} uses the @code{mtrace()} library -calls from GNU LIBC to help track down possible memory leaks. +calls from the GNU C library to help track down possible memory leaks. @end table @node Exit Status @@ -4642,7 +4644,7 @@ The @code{@@include} keyword can be used to read external @command{awk} source files. This gives you the ability to split large @command{awk} source files into smaller, more manageable pieces, and also lets you reuse common @command{awk} code from various @command{awk} scripts. In other words, you can group -together @command{awk} functions, used to carry out specific tasks, +together @command{awk} functions used to carry out specific tasks into external files. These files can be used just like function libraries, using the @code{@@include} keyword in conjunction with the @env{AWKPATH} environment variable. Note that source files may also be included @@ -4677,7 +4679,7 @@ $ @kbd{gawk -f test2} @print{} This is script test2. @end example -@code{gawk} runs the @file{test2} script, which includes @file{test1} +@command{gawk} runs the @file{test2} script, which includes @file{test1} using the @code{@@include} keyword. So, to include external @command{awk} source files, you just use @code{@@include} followed by the name of the file to be included, @@ -4732,11 +4734,12 @@ of the @env{AWKPATH} variable in command-line file searches This is very helpful in constructing @command{gawk} function libraries. If you have a large script with useful, general-purpose @command{awk} functions, you can break it down into library files and put those files -in a special directory. You can then include those ``libraries,'' using -either the full pathnames of the files, or by setting the @env{AWKPATH} +in a special directory. You can then include those ``libraries,'' +either by using the full pathnames of the files, or by setting the @env{AWKPATH} environment variable accordingly and then using @code{@@include} with -just the file part of the full pathname. Of course, you can have more -than one directory to keep library files; the more complex the working +just the file part of the full pathname. Of course, +you can keep library files in more than one directory; +the more complex the working environment is, the more directories you may need to organize the files to be included. @@ -4749,8 +4752,8 @@ In particular, @code{@@include} is very useful for writing CGI scripts to be run from web pages. As mentioned in @ref{AWKPATH Variable}, the current directory is always -searched first for source files, before searching in @env{AWKPATH}, -and this also applies to files named with @code{@@include}. +searched first for source files, before searching in @env{AWKPATH}; +this also applies to files named with @code{@@include}. @node Loading Shared Libraries @section Loading Dynamic Extensions into Your Program @@ -4804,8 +4807,8 @@ It also describes the @code{ordchr} extension. @cindex features, deprecated @cindex obsolete features This @value{SECTION} describes features and/or command-line options from -previous releases of @command{gawk} that are either not available in the -current version or that are still supported but deprecated (meaning that +previous releases of @command{gawk} that either are not available in the +current version or are still supported but deprecated (meaning that they will @emph{not} be in the next release). The process-related special files @file{/dev/pid}, @file{/dev/ppid}, @@ -4885,7 +4888,7 @@ This seems to have been a long-undocumented feature in Unix @command{awk}. Similarly, you may use @code{print} or @code{printf} statements in the @var{init} and @var{increment} parts of a @code{for} loop. This is another -long-undocumented ``feature'' of Unix @code{awk}. +long-undocumented ``feature'' of Unix @command{awk}. @end ignore @@ -4902,7 +4905,7 @@ to run @command{awk}. @item The three standard options for all versions of @command{awk} are -@option{-f}, @option{-F} and @option{-v}. @command{gawk} supplies these +@option{-f}, @option{-F}, and @option{-v}. @command{gawk} supplies these and many others, as well as corresponding GNU-style long options. @item @@ -4939,13 +4942,12 @@ and @option{-f} command-line options. @item @command{gawk} allows you to load additional functions written in C or C++ using the @code{@@load} statement and/or the @option{-l} option. -(This advanced feature is described later on in @ref{Dynamic Extensions}.) +(This advanced feature is described later, in @ref{Dynamic Extensions}.) @end itemize @node Regexp @chapter Regular Expressions @cindex regexp -@c STARTOFRANGE regexp @cindex regular expressions A @dfn{regular expression}, or @dfn{regexp}, is a way of describing a @@ -5152,7 +5154,7 @@ Horizontal TAB, @kbd{Ctrl-i}, ASCII code 9 (HT). @cindex @code{\} (backslash), @code{\v} escape sequence @cindex backslash (@code{\}), @code{\v} escape sequence @item \v -Vertical tab, @kbd{Ctrl-k}, ASCII code 11 (VT). +Vertical TAB, @kbd{Ctrl-k}, ASCII code 11 (VT). @cindex @code{\} (backslash), @code{\}@var{nnn} escape sequence @cindex backslash (@code{\}), @code{\}@var{nnn} escape sequence @@ -5226,7 +5228,7 @@ characters @samp{a+b}. @cindex @code{\} (backslash), in escape sequences @cindex portability For complete portability, do not use a backslash before any character not -shown in the previous list and that is not an operator. +shown in the previous list or that is not an operator. @c 11/2014: Moved so as to not stack sidebars @cindex sidebar, Backslash Before Regular Characters @@ -5388,7 +5390,6 @@ escape sequences literally when used in regexp constants. Thus, @node Regexp Operators @section Regular Expression Operators -@c STARTOFRANGE regexpo @cindex regular expressions, operators @cindex metacharacters in regular expressions @@ -5406,7 +5407,7 @@ are recognized and converted into corresponding real characters as the very first step in processing regexps. Here is a list of metacharacters. All characters that are not escape -sequences and that are not listed in the following stand for themselves: +sequences and that are not listed here stand for themselves: @c Use @asis so the docbook comes out ok. Sigh. @table @asis @@ -5529,7 +5530,7 @@ just @samp{p} if no @samp{h}s are present. There are two subtle points to understand about how @samp{*} works. First, the @samp{*} applies only to the single preceding regular expression component (e.g., in @samp{ph*}, it applies just to the @samp{h}). -To cause @samp{*} to apply to a larger sub-expression, use parentheses: +To cause @samp{*} to apply to a larger subexpression, use parentheses: @samp{(ph)*} matches @samp{ph}, @samp{phph}, @samp{phphph}, and so on. Second, @samp{*} finds as many repetitions as possible. If the text @@ -5568,10 +5569,10 @@ is repeated at least @var{n} times: Matches @samp{whhhy}, but not @samp{why} or @samp{whhhhy}. @item wh@{3,5@}y -Matches @samp{whhhy}, @samp{whhhhy}, or @samp{whhhhhy}, only. +Matches @samp{whhhy}, @samp{whhhhy}, or @samp{whhhhhy} only. @item wh@{2,@}y -Matches @samp{whhy} or @samp{whhhy}, and so on. +Matches @samp{whhy}, @samp{whhhy}, and so on. @end table @cindex POSIX @command{awk}, interval expressions in @@ -5620,11 +5621,9 @@ usage as a syntax error. If @command{gawk} is in compatibility mode (@pxref{Options}), interval expressions are not available in regular expressions. -@c ENDOFRANGE regexpo @node Bracket Expressions @section Using Bracket Expressions -@c STARTOFRANGE charlist @cindex bracket expressions @cindex bracket expressions, range expressions @cindex range expressions (regexps) @@ -5700,7 +5699,7 @@ POSIX standard. (a space is printable but not visible, whereas an @samp{a} is both) @item @code{[:lower:]} @tab Lowercase alphabetic characters @item @code{[:print:]} @tab Printable characters (characters that are not control characters) -@item @code{[:punct:]} @tab Punctuation characters (characters that are not letters, digits +@item @code{[:punct:]} @tab Punctuation characters (characters that are not letters, digits, control characters, or space characters) @item @code{[:space:]} @tab Space characters (such as space, TAB, and formfeed, to name a few) @item @code{[:upper:]} @tab Uppercase alphabetic characters @@ -5720,11 +5719,11 @@ and numeric characters in your character set. @c Date: Tue, 01 Jul 2014 07:39:51 +0200 @c From: Hermann Peifer <peifer@gmx.eu> Some utilities that match regular expressions provide a nonstandard -@code{[:ascii:]} character class; @command{awk} does not. However, you -can simulate such a construct using @code{[\x00-\x7F]}. This matches +@samp{[:ascii:]} character class; @command{awk} does not. However, you +can simulate such a construct using @samp{[\x00-\x7F]}. This matches all values numerically between zero and 127, which is the defined range of the ASCII character set. Use a complemented character list -(@code{[^\x00-\x7F]}) to match any single-byte characters that are not +(@samp{[^\x00-\x7F]}) to match any single-byte characters that are not in the ASCII range. @cindex bracket expressions, collating elements @@ -5753,8 +5752,8 @@ Locale-specific names for a list of characters that are equal. The name is enclosed between @samp{[=} and @samp{=]}. For example, the name @samp{e} might be used to represent all of -``e,'' ``@`e,'' and ``@'e.'' In this case, @samp{[[=e=]]} is a regexp -that matches any of @samp{e}, @samp{@'e}, or @samp{@`e}. +``e,'' ``@^e,'' ``@`e,'' and ``@'e.'' In this case, @samp{[[=e=]]} is a regexp +that matches any of @samp{e}, @samp{@^e}, @samp{@'e}, or @samp{@`e}. @end table These features are very valuable in non-English-speaking locales. @@ -5768,7 +5767,6 @@ expression matching currently recognize only POSIX character classes; they do not recognize collating symbols or equivalence classes. @end quotation @c maybe one day ... -@c ENDOFRANGE charlist @node Leftmost Longest @section How Much Text Matches? @@ -5784,7 +5782,7 @@ echo aaaabcd | awk '@{ sub(/a+/, "<A>"); print @}' This example uses the @code{sub()} function to make a change to the input record. (@code{sub()} replaces the first instance of any text matched by the first argument with the string provided as the second argument; -@pxref{String Functions}). Here, the regexp @code{/a+/} indicates ``one +@pxref{String Functions}.) Here, the regexp @code{/a+/} indicates ``one or more @samp{a} characters,'' and the replacement text is @samp{<A>}. The input contains four @samp{a} characters. @@ -5812,9 +5810,7 @@ and also @pxref{Field Separators}). @node Computed Regexps @section Using Dynamic Regexps -@c STARTOFRANGE dregexp @cindex regular expressions, computed -@c STARTOFRANGE regexpd @cindex regular expressions, dynamic @cindex @code{~} (tilde), @code{~} operator @cindex tilde (@code{~}), @code{~} operator @@ -5840,14 +5836,14 @@ and tests whether the input record matches this regexp. @quotation NOTE When using the @samp{~} and @samp{!~} -operators, there is a difference between a regexp constant +operators, be aware that there is a difference between a regexp constant enclosed in slashes and a string constant enclosed in double quotes. If you are going to use a string constant, you have to understand that the string is, in essence, scanned @emph{twice}: the first time when @command{awk} reads your program, and the second time when it goes to match the string on the lefthand side of the operator with the pattern on the right. This is true of any string-valued expression (such as -@code{digits_regexp}, shown previously), not just string constants. +@code{digits_regexp}, shown in the previous example), not just string constants. @end quotation @cindex regexp constants, slashes vs.@: quotes @@ -5965,17 +5961,13 @@ $ @kbd{awk '$0 ~ /[ \t\n]/'} occur often in practice, but it's worth noting for future reference. @end cartouche @end ifnotdocbook -@c ENDOFRANGE dregexp -@c ENDOFRANGE regexpd @node GNU Regexp Operators @section @command{gawk}-Specific Regexp Operators @c This section adapted (long ago) from the regex-0.12 manual -@c STARTOFRANGE regexpg @cindex regular expressions, operators, @command{gawk} -@c STARTOFRANGE gregexp @cindex @command{gawk}, regular expressions, operators @cindex operators, GNU-specific @cindex regular expressions, operators, for words @@ -6051,7 +6043,7 @@ matches either @samp{ball} or @samp{balls}, as a separate word. @item \B Matches the empty string that occurs between two word-constituent characters. For example, -@code{/\Brat\B/} matches @samp{crate} but it does not match @samp{dirty rat}. +@code{/\Brat\B/} matches @samp{crate}, but it does not match @samp{dirty rat}. @samp{\B} is essentially the opposite of @samp{\y}. @end table @@ -6070,14 +6062,14 @@ The operators are: @cindex backslash (@code{\}), @code{\`} operator (@command{gawk}) @cindex @code{\} (backslash), @code{\`} operator (@command{gawk}) Matches the empty string at the -beginning of a buffer (string). +beginning of a buffer (string) @c @cindex operators, @code{\'} (@command{gawk}) @cindex backslash (@code{\}), @code{\'} operator (@command{gawk}) @cindex @code{\} (backslash), @code{\'} operator (@command{gawk}) @item \' Matches the empty string at the -end of a buffer (string). +end of a buffer (string) @end table @cindex @code{^} (caret), regexp operator @@ -6140,15 +6132,11 @@ Allow interval expressions in regexps, if @option{--traditional} has been provided. Otherwise, interval expressions are available by default. @end table -@c ENDOFRANGE gregexp -@c ENDOFRANGE regexpg @node Case-sensitivity @section Case Sensitivity in Matching -@c STARTOFRANGE regexpcs @cindex regular expressions, case sensitivity -@c STARTOFRANGE csregexp @cindex case sensitivity, regexps and Case is normally significant in regular expressions, both when matching ordinary characters (i.e., not metacharacters) and inside bracket @@ -6240,8 +6228,6 @@ the right thing.} The value of @code{IGNORECASE} has no effect if @command{gawk} is in compatibility mode (@pxref{Options}). Case is always significant in compatibility mode. -@c ENDOFRANGE csregexp -@c ENDOFRANGE regexpcs @node Regexp Summary @section Summary @@ -6288,12 +6274,10 @@ versions, use @code{tolower()} or @code{toupper()}. @end itemize -@c ENDOFRANGE regexp @node Reading Files @chapter Reading Input Files -@c STARTOFRANGE infir @cindex reading input files @cindex input files, reading @cindex input files @@ -6318,7 +6302,7 @@ This makes it more convenient for programs to work on the parts of a record. @cindex @code{getline} command On rare occasions, you may need to use the @code{getline} command. -The @code{getline} command is valuable, both because it +The @code{getline} command is valuable both because it can do explicit input from any number of files, and because the files used with it do not have to be named on the @command{awk} command line (@pxref{Getline}). @@ -6344,9 +6328,7 @@ used with it do not have to be named on the @command{awk} command line @node Records @section How Input Is Split into Records -@c STARTOFRANGE inspl @cindex input, splitting into records -@c STARTOFRANGE recspl @cindex records, splitting input into @cindex @code{NR} variable @cindex @code{FNR} variable @@ -6371,8 +6353,8 @@ never automatically reset to zero. Records are separated by a character called the @dfn{record separator}. By default, the record separator is the newline character. This is why records are, by default, single lines. -A different character can be used for the record separator by -assigning the character to the predefined variable @code{RS}. +To use a different character for the record separator, +simply assign that character to the predefined variable @code{RS}. @cindex newlines, as record separators @cindex @code{RS} variable @@ -6395,8 +6377,8 @@ awk 'BEGIN @{ RS = "u" @} @noindent changes the value of @code{RS} to @samp{u}, before reading any input. -This is a string whose first character is the letter ``u''; as a result, records -are separated by the letter ``u.'' Then the input file is read, and the second +The new value is a string whose first character is the letter ``u''; as a result, records +are separated by the letter ``u''. Then the input file is read, and the second rule in the @command{awk} program (the action with no pattern) prints each record. Because each @code{print} statement adds a newline at the end of its output, this @command{awk} program copies the input @@ -6457,8 +6439,8 @@ Bill 555-1675 bill.drowning@@hotmail.com A @end example @noindent -It contains no @samp{u} so there is no reason to split the record, -unlike the others which have one or more occurrences of the @samp{u}. +It contains no @samp{u}, so there is no reason to split the record, +unlike the others, which each have one or more occurrences of the @samp{u}. In fact, this record is treated as part of the previous record; the newline separating them in the output is the original newline in the @value{DF}, not the one added by @@ -6553,7 +6535,7 @@ contains the same single character. However, when @code{RS} is a regular expression, @code{RT} contains the actual input text that matched the regular expression. -If the input file ended without any text that matches @code{RS}, +If the input file ends without any text matching @code{RS}, @command{gawk} sets @code{RT} to the null string. The following example illustrates both of these features. @@ -6703,8 +6685,6 @@ whole files. If you are using @command{gawk}, see @DBREF{Extension Sample Readfile} for another option. @end cartouche @end ifnotdocbook -@c ENDOFRANGE inspl -@c ENDOFRANGE recspl @node Fields @section Examining Fields @@ -6712,7 +6692,6 @@ Readfile} for another option. @cindex examining fields @cindex fields @cindex accessing fields -@c STARTOFRANGE fiex @cindex fields, examining @cindex POSIX @command{awk}, field separators and @cindex field separators, POSIX and @@ -6737,11 +6716,11 @@ simple @command{awk} programs so powerful. @cindex @code{$} (dollar sign), @code{$} field operator @cindex dollar sign (@code{$}), @code{$} field operator @cindex field operators@comma{} dollar sign as -You use a dollar-sign (@samp{$}) +You use a dollar sign (@samp{$}) to refer to a field in an @command{awk} program, followed by the number of the field you want. Thus, @code{$1} refers to the first field, @code{$2} to the second, and so on. -(Unlike the Unix shells, the field numbers are not limited to single digits. +(Unlike in the Unix shells, the field numbers are not limited to single digits. @code{$127} is the 127th field in the record.) For example, suppose the following is a line of input: @@ -6767,7 +6746,7 @@ If you try to reference a field beyond the last one (such as @code{$8} when the record has only seven fields), you get the empty string. (If used in a numeric operation, you get zero.) -The use of @code{$0}, which looks like a reference to the ``zero-th'' field, is +The use of @code{$0}, which looks like a reference to the ``zeroth'' field, is a special case: it represents the whole input record. Use it when you are not interested in specific fields. Here are some more examples: @@ -6793,7 +6772,6 @@ $ @kbd{awk '/li/ @{ print $1, $NF @}' mail-list} @print{} Julie F @print{} Samuel A @end example -@c ENDOFRANGE fiex @node Nonconstant Fields @section Nonconstant Field Numbers @@ -6823,13 +6801,13 @@ awk '@{ print $(2*2) @}' mail-list @end example @command{awk} evaluates the expression @samp{(2*2)} and uses -its value as the number of the field to print. The @samp{*} sign +its value as the number of the field to print. The @samp{*} represents multiplication, so the expression @samp{2*2} evaluates to four. The parentheses are used so that the multiplication is done before the @samp{$} operation; they are necessary whenever there is a binary operator@footnote{A @dfn{binary operator}, such as @samp{*} for multiplication, is one that takes two operands. The distinction -is required, because @command{awk} also has unary (one-operand) +is required because @command{awk} also has unary (one-operand) and ternary (three-operand) operators.} in the field-number expression. This example, then, prints the type of relationship (the fourth field) for every line of the file @@ -6854,7 +6832,6 @@ evaluating @code{NF} and using its value as a field number. @node Changing Fields @section Changing the Contents of a Field -@c STARTOFRANGE ficon @cindex fields, changing contents of The contents of a field, as seen by @command{awk}, can be changed within an @command{awk} program; this changes what @command{awk} perceives as the @@ -7010,7 +6987,7 @@ rebuild @code{$0} when @code{NF} is decremented. Finally, there are times when it is convenient to force @command{awk} to rebuild the entire record, using the current -value of the fields and @code{OFS}. To do this, use the +values of the fields and @code{OFS}. To do this, use the seemingly innocuous assignment: @example @@ -7039,7 +7016,7 @@ such as @code{sub()} and @code{gsub()} It is important to remember that @code{$0} is the @emph{full} record, exactly as it was read from the input. This includes any leading or trailing whitespace, and the exact whitespace (or other -characters) that separate the fields. +characters) that separates the fields. It is a common error to try to change the field separators in a record simply by setting @code{FS} and @code{OFS}, and then @@ -7064,7 +7041,7 @@ with a statement such as @samp{$1 = $1}, as described earlier. It is important to remember that @code{$0} is the @emph{full} record, exactly as it was read from the input. This includes any leading or trailing whitespace, and the exact whitespace (or other -characters) that separate the fields. +characters) that separates the fields. It is a common error to try to change the field separators in a record simply by setting @code{FS} and @code{OFS}, and then @@ -7077,7 +7054,6 @@ with a statement such as @samp{$1 = $1}, as described earlier. @end cartouche @end ifnotdocbook -@c ENDOFRANGE ficon @node Field Separators @section Specifying How Fields Are Separated @@ -7093,9 +7069,7 @@ with a statement such as @samp{$1 = $1}, as described earlier. @cindex @code{FS} variable @cindex fields, separating -@c STARTOFRANGE fisepr @cindex field separators -@c STARTOFRANGE fisepg @cindex fields, separating The @dfn{field separator}, which is either a single character or a regular expression, controls the way @command{awk} splits an input record into fields. @@ -7161,7 +7135,7 @@ John Q. Smith, LXIX, 29 Oak St., Walamazoo, MI 42139 @end example @noindent -The same program would extract @samp{@bullet{}LXIX}, instead of +The same program would extract @samp{@bullet{}LXIX} instead of @samp{@bullet{}29@bullet{}Oak@bullet{}St.}. If you were expecting the program to print the address, you would be surprised. The moral is to choose your data layout and @@ -7195,9 +7169,7 @@ rules. @node Regexp Field Splitting @subsection Using Regular Expressions to Separate Fields -@c STARTOFRANGE regexpfs @cindex regular expressions, as field separators -@c STARTOFRANGE fsregexp @cindex field separators, regular expressions as The previous @value{SUBSECTION} discussed the use of single characters or simple strings as the @@ -7301,8 +7273,6 @@ $ @kbd{echo 'xxAA xxBxx C' |} @print{} -->xxBxx<-- @print{} -->C<-- @end example -@c ENDOFRANGE regexpfs -@c ENDOFRANGE fsregexp @node Single Character Fields @subsection Making Each Character a Separate Field @@ -7426,7 +7396,7 @@ choosing your field and record separators. @cindex Unix @command{awk}, password files@comma{} field separators and Perhaps the most common use of a single character as the field separator occurs when processing the Unix system password file. On many Unix -systems, each user has a separate entry in the system password file, one +systems, each user has a separate entry in the system password file, with one line per user. The information in these lines is separated by colons. The first field is the user's login name and the second is the user's encrypted or shadow password. (A shadow password is indicated by the @@ -7472,7 +7442,7 @@ When you do this, @code{$1} is the same as @code{$0}. According to the POSIX standard, @command{awk} is supposed to behave as if each record is split into fields at the time it is read. In particular, this means that if you change the value of @code{FS} -after a record is read, the value of the fields (i.e., how they were split) +after a record is read, the values of the fields (i.e., how they were split) should reflect the old value of @code{FS}, not the new one. @cindex dark corner, field separators @@ -7485,10 +7455,7 @@ using the @emph{current} value of @code{FS}! @value{DARKCORNER} This behavior can be difficult to diagnose. The following example illustrates the difference -between the two methods. -(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' -Its behavior is also defined by the POSIX standard.} -command prints just the first line of @file{/etc/passwd}.) +between the two methods: @example sed 1q /etc/passwd | awk '@{ FS = ":" ; print $1 @}' @@ -7509,6 +7476,10 @@ prints the full first line of the file, something like: root:x:0:0:Root:/: @end example +(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' +Its behavior is also defined by the POSIX standard.} +command prints just the first line of @file{/etc/passwd}.) + @docbook </sidebar> @end docbook @@ -7525,7 +7496,7 @@ root:x:0:0:Root:/: According to the POSIX standard, @command{awk} is supposed to behave as if each record is split into fields at the time it is read. In particular, this means that if you change the value of @code{FS} -after a record is read, the value of the fields (i.e., how they were split) +after a record is read, the values of the fields (i.e., how they were split) should reflect the old value of @code{FS}, not the new one. @cindex dark corner, field separators @@ -7538,10 +7509,7 @@ using the @emph{current} value of @code{FS}! @value{DARKCORNER} This behavior can be difficult to diagnose. The following example illustrates the difference -between the two methods. -(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' -Its behavior is also defined by the POSIX standard.} -command prints just the first line of @file{/etc/passwd}.) +between the two methods: @example sed 1q /etc/passwd | awk '@{ FS = ":" ; print $1 @}' @@ -7561,6 +7529,10 @@ prints the full first line of the file, something like: @example root:x:0:0:Root:/: @end example + +(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' +Its behavior is also defined by the POSIX standard.} +command prints just the first line of @file{/etc/passwd}.) @end cartouche @end ifnotdocbook @@ -7658,8 +7630,6 @@ will take effect. @end cartouche @end ifnotdocbook -@c ENDOFRANGE fisepr -@c ENDOFRANGE fisepg @node Constant Size @section Reading Fixed-Width Data @@ -7774,7 +7744,7 @@ In order to tell which kind of field splitting is in effect, use @code{PROCINFO["FS"]} (@pxref{Auto-set}). The value is @code{"FS"} if regular field splitting is being used, -or it is @code{"FIELDWIDTHS"} if fixed-width field splitting is being used: +or @code{"FIELDWIDTHS"} if fixed-width field splitting is being used: @example if (PROCINFO["FS"] == "FS") @@ -7810,14 +7780,14 @@ what they are, and not by what they are not. The most notorious such case is so-called @dfn{comma-separated values} (CSV) data. Many spreadsheet programs, for example, can export their data into text files, where each record is -terminated with a newline, and fields are separated by commas. If only -commas separated the data, there wouldn't be an issue. The problem comes when +terminated with a newline, and fields are separated by commas. If +commas only separated the data, there wouldn't be an issue. The problem comes when one of the fields contains an @emph{embedded} comma. In such cases, most programs embed the field in double quotes.@footnote{The CSV format lacked a formal standard definition for many years. @uref{http://www.ietf.org/rfc/rfc4180.txt, RFC 4180} standardizes the most common practices.} -So we might have data like this: +So, we might have data like this: @example @c file eg/misc/addresses.csv @@ -7903,8 +7873,8 @@ of cases, and the @command{gawk} developers are satisfied with that. @end quotation As written, the regexp used for @code{FPAT} requires that each field -have a least one character. A straightforward modification -(changing changed the first @samp{+} to @samp{*}) allows fields to be empty: +contain at least one character. A straightforward modification +(changing the first @samp{+} to @samp{*}) allows fields to be empty: @example FPAT = "([^,]*)|(\"[^\"]+\")" @@ -7914,20 +7884,17 @@ Finally, the @code{patsplit()} function makes the same functionality available for splitting regular strings (@pxref{String Functions}). To recap, @command{gawk} provides three independent methods -to split input records into fields. @command{gawk} uses whichever -mechanism was last chosen based on which of the three -variables---@code{FS}, @code{FIELDWIDTHS}, and @code{FPAT}---was +to split input records into fields. +The mechanism used is based on which of the three +variables---@code{FS}, @code{FIELDWIDTHS}, or @code{FPAT}---was last assigned to. @node Multiple Line @section Multiple-Line Records @cindex multiple-line records -@c STARTOFRANGE recm @cindex records, multiline -@c STARTOFRANGE imr @cindex input, multiline records -@c STARTOFRANGE frm @cindex files, reading, multiline records @cindex input, files, See input files In some databases, a single line cannot conveniently hold all the @@ -7962,7 +7929,7 @@ at the end of the record and one or more blank lines after the record. In addition, a regular expression always matches the longest possible sequence when there is a choice (@pxref{Leftmost Longest}). -So the next record doesn't start until +So, the next record doesn't start until the first nonblank line that follows---no matter how many blank lines appear in a row, they are considered one record separator. @@ -7977,10 +7944,10 @@ In the second case, this special processing is not done. @cindex field separator, in multiline records @cindex @code{FS}, in multiline records Now that the input is separated into records, the second step is to -separate the fields in the record. One way to do this is to divide each +separate the fields in the records. One way to do this is to divide each of the lines into fields in the normal manner. This happens by default as the result of a special feature. When @code{RS} is set to the empty -string, @emph{and} @code{FS} is set to a single character, +string @emph{and} @code{FS} is set to a single character, the newline character @emph{always} acts as a field separator. This is in addition to whatever field separations result from @code{FS}.@footnote{When @code{FS} is the null string (@code{""}) @@ -7995,7 +7962,7 @@ want the newline character to separate fields, because there is no way to prevent it. However, you can work around this by using the @code{split()} function to break up the record manually (@pxref{String Functions}). -If you have a single character field separator, you can work around +If you have a single-character field separator, you can work around the special feature in a different way, by making @code{FS} into a regexp for that single character. For example, if the field separator is a percent character, instead of @@ -8003,10 +7970,10 @@ separator is a percent character, instead of Another way to separate fields is to put each field on a separate line: to do this, just set the -variable @code{FS} to the string @code{"\n"}. (This single -character separator matches a single newline.) +variable @code{FS} to the string @code{"\n"}. +(This single-character separator matches a single newline.) A practical example of a @value{DF} organized this way might be a mailing -list, where each entry is separated by blank lines. Consider a mailing +list, where blank lines separate the entries. Consider a mailing list in a file named @file{addresses}, which looks like this: @example @@ -8094,20 +8061,15 @@ If not in compatibility mode (@pxref{Options}), @command{gawk} sets @code{RT} to the input text that matched the value specified by @code{RS}. But if the input file ended without any text that matches @code{RS}, then @command{gawk} sets @code{RT} to the null string. -@c ENDOFRANGE recm -@c ENDOFRANGE imr -@c ENDOFRANGE frm @node Getline @section Explicit Input with @code{getline} -@c STARTOFRANGE getl @cindex @code{getline} command, explicit input with -@c STARTOFRANGE inex @cindex input, explicit So far we have been getting our input data from @command{awk}'s main input stream---either the standard input (usually your keyboard, sometimes -the output from another program) or from the +the output from another program) or the files specified on the command line. The @command{awk} language has a special built-in command called @code{getline} that can be used to read input under your explicit control. @@ -8291,7 +8253,7 @@ free @end example The @code{getline} command used in this way sets only the variables -@code{NR}, @code{FNR}, and @code{RT} (and of course, @var{var}). +@code{NR}, @code{FNR}, and @code{RT} (and, of course, @var{var}). The record is not split into fields, so the values of the fields (including @code{$0}) and the value of @code{NF} do not change. @@ -8306,7 +8268,7 @@ the value of @code{NF} do not change. @cindex left angle bracket (@code{<}), @code{<} operator (I/O) @cindex operators, input/output Use @samp{getline < @var{file}} to read the next record from @var{file}. -Here @var{file} is a string-valued expression that +Here, @var{file} is a string-valued expression that specifies the @value{FN}. @samp{< @var{file}} is called a @dfn{redirection} because it directs input to come from a different place. For example, the following @@ -8484,7 +8446,7 @@ of a construct like @samp{@w{"echo "} "date" | getline}. Most versions, including the current version, treat it at as @samp{@w{("echo "} "date") | getline}. (This is also how BWK @command{awk} behaves.) -Some versions changed and treated it as +Some versions instead treat it as @samp{@w{"echo "} ("date" | getline)}. (This is how @command{mawk} behaves.) In short, @emph{always} use explicit parentheses, and then you won't @@ -8532,7 +8494,7 @@ program to be portable to other @command{awk} implementations. @cindex operators, input/output @cindex differences in @command{awk} and @command{gawk}, input/output operators -Input into @code{getline} from a pipe is a one-way operation. +Reading input into @code{getline} from a pipe is a one-way operation. The command that is started with @samp{@var{command} | getline} only sends data @emph{to} your @command{awk} program. @@ -8542,7 +8504,7 @@ for processing and then read the results back. communications are possible. This is done with the @samp{|&} operator. Typically, you write data to the coprocess first and then -read results back, as shown in the following: +read the results back, as shown in the following: @example print "@var{some query}" |& "db_server" @@ -8625,7 +8587,7 @@ also @pxref{Auto-set}.) @item Using @code{FILENAME} with @code{getline} (@samp{getline < FILENAME}) -is likely to be a source for +is likely to be a source of confusion. @command{awk} opens a separate input stream from the current input file. However, by not using a variable, @code{$0} and @code{NF} are still updated. If you're doing this, it's @@ -8633,9 +8595,15 @@ probably by accident, and you should reconsider what it is you're trying to accomplish. @item -@DBREF{Getline Summary} presents a table summarizing the +@ifdocbook +The next section +@end ifdocbook +@ifnotdocbook +@ref{Getline Summary}, +@end ifnotdocbook +presents a table summarizing the @code{getline} variants and which variables they can affect. -It is worth noting that those variants which do not use redirection +It is worth noting that those variants that do not use redirection can cause @code{FILENAME} to be updated if they cause @command{awk} to start reading a new input file. @@ -8644,7 +8612,7 @@ can cause @code{FILENAME} to be updated if they cause If the variable being assigned is an expression with side effects, different versions of @command{awk} behave differently upon encountering end-of-file. Some versions don't evaluate the expression; many versions -(including @command{gawk}) do. Here is an example, due to Duncan Moore: +(including @command{gawk}) do. Here is an example, courtesy of Duncan Moore: @ignore Date: Sun, 01 Apr 2012 11:49:33 +0100 @@ -8661,7 +8629,7 @@ BEGIN @{ @noindent Here, the side effect is the @samp{++c}. Is @code{c} incremented if -end of file is encountered, before the element in @code{a} is assigned? +end-of-file is encountered before the element in @code{a} is assigned? @command{gawk} treats @code{getline} like a function call, and evaluates the expression @samp{a[++c]} before attempting to read from @file{f}. @@ -8693,9 +8661,6 @@ Note: for each variant, @command{gawk} sets the @code{RT} predefined variable. @item @var{command} @code{|& getline} @var{var} @tab Sets @var{var} and @code{RT} @tab @command{gawk} @end multitable @end float -@c ENDOFRANGE getl -@c ENDOFRANGE inex -@c ENDOFRANGE infir @node Read Timeout @section Reading Input with a Timeout @@ -8706,8 +8671,8 @@ This @value{SECTION} describes a feature that is specific to @command{gawk}. You may specify a timeout in milliseconds for reading input from the keyboard, a pipe, or two-way communication, including TCP/IP sockets. This can be done -on a per input, command, or connection basis, by setting a special element -in the @code{PROCINFO} array (@pxref{Auto-set}): +on a per-input, per-command, or per-connection basis, by setting a special +element in the @code{PROCINFO} array (@pxref{Auto-set}): @example PROCINFO["input_name", "READ_TIMEOUT"] = @var{timeout in milliseconds} @@ -8738,7 +8703,7 @@ while ((getline < "/dev/stdin") > 0) @end example @command{gawk} terminates the read operation if input does not -arrive after waiting for the timeout period, returns failure +arrive after waiting for the timeout period, returns failure, and sets @code{ERRNO} to an appropriate string value. A negative or zero value for the timeout is the same as specifying no timeout at all. @@ -8748,7 +8713,7 @@ loop that reads input records and matches them against patterns, like so: @example -$ @kbd{ gawk 'BEGIN @{ PROCINFO["-", "READ_TIMEOUT"] = 5000 @}} +$ @kbd{gawk 'BEGIN @{ PROCINFO["-", "READ_TIMEOUT"] = 5000 @}} > @kbd{@{ print "You entered: " $0 @}'} @kbd{gawk} @print{} You entered: gawk @@ -8788,7 +8753,7 @@ If the @code{PROCINFO} element is not present and the @command{gawk} uses its value to initialize the timeout value. The exclusive use of the environment variable to specify timeout has the disadvantage of not being able to control it -on a per command or connection basis. +on a per-command or per-connection basis. @command{gawk} considers a timeout event to be an error even though the attempt to read from the underlying device may @@ -8854,7 +8819,7 @@ The possibilities are as follows: @item After splitting the input into records, @command{awk} further splits -the record into individual fields, named @code{$1}, @code{$2}, and so +the records into individual fields, named @code{$1}, @code{$2}, and so on. @code{$0} is the whole record, and @code{NF} indicates how many fields there are. The default way to split fields is between whitespace characters. @@ -8870,12 +8835,12 @@ thing. Decrementing @code{NF} throws away fields and rebuilds the record. @item Field splitting is more complicated than record splitting: -@multitable @columnfractions .40 .45 .15 +@multitable @columnfractions .40 .40 .20 @headitem Field separator value @tab Fields are split @dots{} @tab @command{awk} / @command{gawk} @item @code{FS == " "} @tab On runs of whitespace @tab @command{awk} @item @code{FS == @var{any single character}} @tab On that character @tab @command{awk} @item @code{FS == @var{regexp}} @tab On text matching the regexp @tab @command{awk} -@item @code{FS == ""} @tab Each individual character is a separate field @tab @command{gawk} +@item @code{FS == ""} @tab Such that each individual character is a separate field @tab @command{gawk} @item @code{FIELDWIDTHS == @var{list of columns}} @tab Based on character position @tab @command{gawk} @item @code{FPAT == @var{regexp}} @tab On the text surrounding text matching the regexp @tab @command{gawk} @end multitable @@ -8892,11 +8857,11 @@ This can also be done using command-line variable assignment. Use @code{PROCINFO["FS"]} to see how fields are being split. @item -Use @code{getline} in its various forms to read additional records, +Use @code{getline} in its various forms to read additional records from the default input stream, from a file, or from a pipe or coprocess. @item -Use @code{PROCINFO[@var{file}, "READ_TIMEOUT"]} to cause reads to timeout +Use @code{PROCINFO[@var{file}, "READ_TIMEOUT"]} to cause reads to time out for @var{file}. @item @@ -8930,7 +8895,6 @@ That can be fixed by making one simple change. What is it? @node Printing @chapter Printing Output -@c STARTOFRANGE prnt @cindex printing @cindex output, printing, See printing One of the most common programming actions is to @dfn{print}, or output, @@ -8946,7 +8910,6 @@ columns, whether to use exponential notation or not, and so on. For printing with specifications, you need the @code{printf} statement (@pxref{Printf}). -@c STARTOFRANGE prnts @cindex @code{print} statement @cindex @code{printf} statement Besides basic and formatted printing, this @value{CHAPTER} @@ -9008,7 +8971,7 @@ space is printed between any two items. Note that the @code{print} statement is a statement and not an expression---you can't use it in the pattern part of a -@var{pattern}-@var{action} statement, for example. +pattern--action statement, for example. @node Print Examples @section @code{print} Statement Examples @@ -9127,7 +9090,6 @@ You can continue either a @code{print} or @code{printf} statement simply by putting a newline after any comma (@pxref{Statements/Lines}). @end quotation -@c ENDOFRANGE prnts @node Output Separators @section Output Separators @@ -9200,7 +9162,7 @@ runs together on a single line. @cindex numeric, output format @cindex formats@comma{} numeric output When printing numeric values with the @code{print} statement, -@command{awk} internally converts the number to a string of characters +@command{awk} internally converts each number to a string of characters and prints that string. @command{awk} uses the @code{sprintf()} function to do this conversion (@pxref{String Functions}). @@ -9240,7 +9202,6 @@ if @code{OFMT} contains anything but a floating-point conversion specification. @node Printf @section Using @code{printf} Statements for Fancier Printing -@c STARTOFRANGE printfs @cindex @code{printf} statement @cindex output, formatted @cindex formatting output @@ -9272,7 +9233,7 @@ printf @var{format}, @var{item1}, @var{item2}, @dots{} @noindent As for @code{print}, the entire list of arguments may optionally be enclosed in parentheses. Here too, the parentheses are necessary if any -of the item expressions use the @samp{>} relational operator; otherwise, +of the item expressions uses the @samp{>} relational operator; otherwise, it can be confused with an output redirection (@pxref{Redirection}). @cindex format specifiers @@ -9303,7 +9264,7 @@ $ @kbd{awk 'BEGIN @{} @end example @noindent -Here, neither the @samp{+} nor the @samp{OUCH!} appear in +Here, neither the @samp{+} nor the @samp{OUCH!} appears in the output message. @node Control Letters @@ -9350,8 +9311,8 @@ The two control letters are equivalent. (The @samp{%i} specification is for compatibility with ISO C.) @item @code{%e}, @code{%E} -Print a number in scientific (exponential) notation; -for example: +Print a number in scientific (exponential) notation. +For example: @example printf "%4.3e\n", 1950 @@ -9388,7 +9349,7 @@ The special ``not a number'' value formats as @samp{-nan} or @samp{nan} (@pxref{Math Definitions}). @item @code{%F} -Like @samp{%f} but the infinity and ``not a number'' values are spelled +Like @samp{%f}, but the infinity and ``not a number'' values are spelled using uppercase letters. The @samp{%F} format is a POSIX extension to ISO C; not all systems @@ -9438,7 +9399,6 @@ values or do something else entirely. @node Format Modifiers @subsection Modifiers for @code{printf} Formats -@c STARTOFRANGE pfm @cindex @code{printf} statement, modifiers @cindex modifiers@comma{} in format specifiers A format specification can also include @dfn{modifiers} that can control @@ -9477,7 +9437,7 @@ messages at runtime. which describes how and why to use positional specifiers. For now, we ignore them. -@item - (Minus) +@item - @r{(Minus)} The minus sign, used before the width modifier (see later on in this list), says to left-justify @@ -9633,7 +9593,7 @@ printf "%" w "." p "s\n", s @end example @noindent -This is not particularly easy to read but it does work. +This is not particularly easy to read, but it does work. @c @cindex lint checks @cindex troubleshooting, fatal errors, @code{printf} format strings @@ -9644,7 +9604,6 @@ format strings. These are not valid in @command{awk}. Most @command{awk} implementations silently ignore them. If @option{--lint} is provided on the command line (@pxref{Options}), @command{gawk} warns about their use. If @option{--posix} is supplied, their use is a fatal error. -@c ENDOFRANGE pfm @node Printf Examples @subsection Examples Using @code{printf} @@ -9680,7 +9639,7 @@ $ @kbd{awk '@{ printf "%-10s %s\n", $1, $2 @}' mail-list} @end example In this case, the phone numbers had to be printed as strings because -the numbers are separated by a dash. Printing the phone numbers as +the numbers are separated by dashes. Printing the phone numbers as numbers would have produced just the first three digits: @samp{555}. This would have been pretty confusing. @@ -9725,14 +9684,11 @@ awk 'BEGIN @{ format = "%-10s %s\n" @{ printf format, $1, $2 @}' mail-list @end example -@c ENDOFRANGE printfs @node Redirection @section Redirecting Output of @code{print} and @code{printf} -@c STARTOFRANGE outre @cindex output redirection -@c STARTOFRANGE reout @cindex redirection of output @cindex @option{--sandbox} option, output redirection with @code{print}, @code{printf} So far, the output from @code{print} and @code{printf} has gone @@ -9743,7 +9699,7 @@ This is called @dfn{redirection}. @quotation NOTE When @option{--sandbox} is specified (@pxref{Options}), -redirecting output to files, pipes and coprocesses is disabled. +redirecting output to files, pipes, and coprocesses is disabled. @end quotation A redirection appears after the @code{print} or @code{printf} statement. @@ -9796,7 +9752,7 @@ Each output file contains one name or number per line. @cindex @code{>} (right angle bracket), @code{>>} operator (I/O) @cindex right angle bracket (@code{>}), @code{>>} operator (I/O) @item print @var{items} >> @var{output-file} -This redirection prints the items into the pre-existing output file +This redirection prints the items into the preexisting output file named @var{output-file}. The difference between this and the single-@samp{>} redirection is that the old contents (if any) of @var{output-file} are not erased. Instead, the @command{awk} output is @@ -9835,7 +9791,7 @@ The unsorted list is written with an ordinary redirection, while the sorted list is written by piping through the @command{sort} utility. The next example uses redirection to mail a message to the mailing -list @samp{bug-system}. This might be useful when trouble is encountered +list @code{bug-system}. This might be useful when trouble is encountered in an @command{awk} script run periodically for system maintenance: @example @@ -9866,15 +9822,23 @@ This redirection prints the items to the input of @var{command}. The difference between this and the single-@samp{|} redirection is that the output from @var{command} can be read with @code{getline}. -Thus @var{command} is a @dfn{coprocess}, which works together with, -but subsidiary to, the @command{awk} program. +Thus, @var{command} is a @dfn{coprocess}, which works together with +but is subsidiary to the @command{awk} program. This feature is a @command{gawk} extension, and is not available in POSIX @command{awk}. -@DBXREF{Getline/Coprocess} +@ifnotdocbook +@xref{Getline/Coprocess}, for a brief discussion. -@DBXREF{Two-way I/O} +@xref{Two-way I/O}, +for a more complete discussion. +@end ifnotdocbook +@ifdocbook +@DBXREF{Getline/Coprocess} +for a brief discussion and +@DBREF{Two-way I/O} for a more complete discussion. +@end ifdocbook @end table Redirecting output using @samp{>}, @samp{>>}, @samp{|}, or @samp{|&} @@ -9899,7 +9863,7 @@ This is indeed how redirections must be used from the shell. But in @command{awk}, it isn't necessary. In this kind of case, a program should use @samp{>} for all the @code{print} statements, because the output file is only opened once. (It happens that if you mix @samp{>} and @samp{>>} -that output is produced in the expected order. However, mixing the operators +output is produced in the expected order. However, mixing the operators for the same file is definitely poor style, and is confusing to readers of your program.) @@ -9990,11 +9954,9 @@ It then sends the list to the shell for execution. command lines to be fed to the shell. @end cartouche @end ifnotdocbook -@c ENDOFRANGE outre -@c ENDOFRANGE reout @node Special FD -@section Special Files for Standard Pre-Opened Data Streams +@section Special Files for Standard Preopened Data Streams @cindex standard input @cindex input, standard @cindex standard output @@ -10007,7 +9969,7 @@ command lines to be fed to the shell. Running programs conventionally have three input and output streams already available to them for reading and writing. These are known as the @dfn{standard input}, @dfn{standard output}, and @dfn{standard -error output}. These open streams (and any other open file or pipe) +error output}. These open streams (and any other open files or pipes) are often referred to by the technical term @dfn{file descriptors}. These streams are, by default, connected to your keyboard and screen, but @@ -10045,7 +10007,7 @@ that is connected to your keyboard and screen. It represents the ``terminal,''@footnote{The ``tty'' in @file{/dev/tty} stands for ``Teletype,'' a serial terminal.} which on modern systems is a keyboard and screen, not a serial console.) -This generally has the same effect but not always: although the +This generally has the same effect, but not always: although the standard error stream is usually the screen, it can be redirected; when that happens, writing to the screen is not correct. In fact, if @command{awk} is run from a background job, it may not have a @@ -10090,7 +10052,7 @@ print "Serious error detected!" > "/dev/stderr" @cindex troubleshooting, quotes with file names Note the use of quotes around the @value{FN}. -Like any other redirection, the value must be a string. +Like with any other redirection, the value must be a string. It is a common error to omit the quotes, which leads to confusing results. @@ -10101,7 +10063,6 @@ invoked with the @option{--traditional} option (@pxref{Options}). @node Special Files @section Special @value{FFN}s in @command{gawk} -@c STARTOFRANGE gfn @cindex @command{gawk}, file names in Besides access to standard input, standard output, and standard error, @@ -10117,7 +10078,7 @@ TCP/IP networking. @end menu @node Other Inherited Files -@subsection Accessing Other Open Files With @command{gawk} +@subsection Accessing Other Open Files with @command{gawk} Besides the @code{/dev/stdin}, @code{/dev/stdout}, and @code{/dev/stderr} special @value{FN}s mentioned earlier, @command{gawk} provides syntax @@ -10174,7 +10135,7 @@ special @value{FN}s that @command{gawk} provides: @cindex compatibility mode (@command{gawk}), file names @cindex file names, in compatibility mode @item -Recognition of the @value{FN}s for the three standard pre-opened +Recognition of the @value{FN}s for the three standard preopened files is disabled only in POSIX mode. @item @@ -10187,23 +10148,18 @@ compatibility mode (either @option{--traditional} or @option{--posix}; interprets these special @value{FN}s. For example, using @samp{/dev/fd/4} for output actually writes on file descriptor 4, and not on a new -file descriptor that is @code{dup()}'ed from file descriptor 4. Most of +file descriptor that is @code{dup()}ed from file descriptor 4. Most of the time this does not matter; however, it is important to @emph{not} close any of the files related to file descriptors 0, 1, and 2. Doing so results in unpredictable behavior. @end itemize -@c ENDOFRANGE gfn @node Close Files And Pipes @section Closing Input and Output Redirections @cindex files, output, See output files -@c STARTOFRANGE ifc @cindex input files, closing -@c STARTOFRANGE ofc @cindex output, files@comma{} closing -@c STARTOFRANGE pc @cindex pipe, closing -@c STARTOFRANGE cc @cindex coprocesses, closing @cindex @code{getline} command, coprocesses@comma{} using from @@ -10414,9 +10370,9 @@ This value is zero if the close succeeds, or @minus{}1 if it fails. The POSIX standard is very vague; it says that @code{close()} -returns zero on success and nonzero otherwise. In general, +returns zero on success and a nonzero value otherwise. In general, different implementations vary in what they report when closing -pipes; thus the return value cannot be used portably. +pipes; thus, the return value cannot be used portably. @value{DARKCORNER} In POSIX mode (@pxref{Options}), @command{gawk} just returns zero when closing a pipe. @@ -10471,19 +10427,15 @@ This value is zero if the close succeeds, or @minus{}1 if it fails. The POSIX standard is very vague; it says that @code{close()} -returns zero on success and nonzero otherwise. In general, +returns zero on success and a nonzero value otherwise. In general, different implementations vary in what they report when closing -pipes; thus the return value cannot be used portably. +pipes; thus, the return value cannot be used portably. @value{DARKCORNER} In POSIX mode (@pxref{Options}), @command{gawk} just returns zero when closing a pipe. @end cartouche @end ifnotdocbook -@c ENDOFRANGE ifc -@c ENDOFRANGE ofc -@c ENDOFRANGE pc -@c ENDOFRANGE cc @node Nonfatal @section Enabling Nonfatal Output @@ -10554,8 +10506,8 @@ for numeric values for the @code{print} statement. @item The @code{printf} statement provides finer-grained control over output, -with format control letters for different data types and various flags -that modify the behavior of the format control letters. +with format-control letters for different data types and various flags +that modify the behavior of the format-control letters. @item Output from both @code{print} and @code{printf} may be redirected to @@ -10610,11 +10562,9 @@ BEGIN @{ print "Serious error detected!" > /dev/stderr @} @end enumerate @c EXCLUDE END -@c ENDOFRANGE prnt @node Expressions @chapter Expressions -@c STARTOFRANGE exps @cindex expressions Expressions are the basic building blocks of @command{awk} patterns @@ -10625,7 +10575,7 @@ can assign a new value to a variable or a field by using an assignment operator. An expression can serve as a pattern or action statement on its own. Most other kinds of statements contain one or more expressions that specify the data on which to -operate. As in other languages, expressions in @command{awk} include +operate. As in other languages, expressions in @command{awk} can include variables, array references, constants, and function calls, as well as combinations of these with various operators. @@ -10644,7 +10594,7 @@ combinations of these with various operators. Expressions are built up from values and the operations performed upon them. This @value{SECTION} describes the elementary objects -which provide the values used in expressions. +that provide the values used in expressions. @menu * Constants:: String, numeric and regexp constants. @@ -10657,7 +10607,6 @@ which provide the values used in expressions. @node Constants @subsection Constant Expressions -@c STARTOFRANGE cnst @cindex constants, types of The simplest type of expression is the @dfn{constant}, which always has @@ -10695,7 +10644,7 @@ have the same value: @end example @cindex string constants -A string constant consists of a sequence of characters enclosed in +A @dfn{string constant} consists of a sequence of characters enclosed in double quotation marks. For example: @example @@ -10707,7 +10656,7 @@ double quotation marks. For example: @cindex strings, length limitations represents the string whose contents are @samp{parrot}. Strings in @command{gawk} can be of any length, and they can contain any of the possible -eight-bit ASCII characters including ASCII @sc{nul} (character code zero). +eight-bit ASCII characters, including ASCII @sc{nul} (character code zero). Other @command{awk} implementations may have difficulty with some character codes. @@ -10722,15 +10671,15 @@ In @command{awk}, all numbers are in decimal (i.e., base 10). Many other programming languages allow you to specify numbers in other bases, often octal (base 8) and hexadecimal (base 16). In octal, the numbers go 0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, and so on. -Just as @samp{11}, in decimal, is 1 times 10 plus 1, so -@samp{11}, in octal, is 1 times 8, plus 1. This equals 9 in decimal. +Just as @samp{11} in decimal is 1 times 10 plus 1, so +@samp{11} in octal is 1 times 8 plus 1. This equals 9 in decimal. In hexadecimal, there are 16 digits. Because the everyday decimal number system only has ten digits (@samp{0}--@samp{9}), the letters @samp{a} through @samp{f} are used to represent the rest. (Case in the letters is usually irrelevant; hexadecimal @samp{a} and @samp{A} have the same value.) -Thus, @samp{11}, in -hexadecimal, is 1 times 16 plus 1, which equals 17 in decimal. +Thus, @samp{11} in +hexadecimal is 1 times 16 plus 1, which equals 17 in decimal. Just by looking at plain @samp{11}, you can't tell what base it's in. So, in C, C++, and other languages derived from C, @@ -10741,13 +10690,13 @@ and hexadecimal numbers start with a leading @samp{0x} or @samp{0X}: @table @code @item 11 -Decimal value 11. +Decimal value 11 @item 011 -Octal 11, decimal value 9. +Octal 11, decimal value 9 @item 0x11 -Hexadecimal 11, decimal value 17. +Hexadecimal 11, decimal value 17 @end table This example shows the difference: @@ -10775,11 +10724,11 @@ you can use the @code{strtonum()} function (@pxref{String Functions}) to convert the data into a number. Most of the time, you will want to use octal or hexadecimal constants -when working with the built-in bit manipulation functions; +when working with the built-in bit-manipulation functions; see @DBREF{Bitwise Functions} for more information. -Unlike some early C implementations, @samp{8} and @samp{9} are not +Unlike in some early C implementations, @samp{8} and @samp{9} are not valid in octal constants. For example, @command{gawk} treats @samp{018} as decimal 18: @@ -10843,19 +10792,17 @@ $ @kbd{gawk 'BEGIN @{ printf "0x11 is <%s>\n", 0x11 @}'} @node Regexp Constants @subsubsection Regular Expression Constants -@c STARTOFRANGE rec @cindex regexp constants @cindex @code{~} (tilde), @code{~} operator @cindex tilde (@code{~}), @code{~} operator @cindex @code{!} (exclamation point), @code{!~} operator @cindex exclamation point (@code{!}), @code{!~} operator -A regexp constant is a regular expression description enclosed in +A @dfn{regexp constant} is a regular expression description enclosed in slashes, such as @code{@w{/^beginning and end$/}}. Most regexps used in @command{awk} programs are constant, but the @samp{~} and @samp{!~} matching operators can also match computed or dynamic regexps (which are typically just ordinary strings or variables that contain a regexp, -but could be a more complex expression). -@c ENDOFRANGE cnst +but could be more complex expressions). @node Using Constant Regexps @subsection Using Regular Expression Constants @@ -10935,7 +10882,7 @@ the third argument of @code{split()} to be a regexp constant, but some older implementations do not. @value{DARKCORNER} Because some built-in functions accept regexp constants as arguments, -it can be confusing when attempting to use regexp constants as arguments +confusion can arise when attempting to use regexp constants as arguments to user-defined functions (@pxref{User-defined}). For example: @example @@ -10961,19 +10908,18 @@ function mysub(pat, repl, str, global) In this example, the programmer wants to pass a regexp constant to the user-defined function @code{mysub()}, which in turn passes it on to either @code{sub()} or @code{gsub()}. However, what really happens is that -the @code{pat} parameter is either one or zero, depending upon whether +the @code{pat} parameter is assigned a value of either one or zero, depending upon whether or not @code{$0} matches @code{/hi/}. @command{gawk} issues a warning when it sees a regexp constant used as a parameter to a user-defined function, because passing a truth value in this way is probably not what was intended. -@c ENDOFRANGE rec @node Variables @subsection Variables @cindex variables, user-defined @cindex user-defined, variables -Variables are ways of storing values at one point in your program for +@dfn{Variables} are ways of storing values at one point in your program for use later in another part of your program. They can be manipulated entirely within the program text, and they can also be assigned values on the @command{awk} command line. @@ -11001,17 +10947,17 @@ are distinct variables. A variable name is a valid expression by itself; it represents the variable's current value. Variables are given new values with @dfn{assignment operators}, @dfn{increment operators}, and -@dfn{decrement operators}. -@xref{Assignment Ops}. +@dfn{decrement operators} +(@pxref{Assignment Ops}). In addition, the @code{sub()} and @code{gsub()} functions can change a variable's value, and the @code{match()}, @code{split()}, and @code{patsplit()} functions can change the contents of their -array parameters. @xref{String Functions}. +array parameters (@pxref{String Functions}). @cindex variables, built-in @cindex variables, initializing A few variables have special built-in meanings, such as @code{FS} (the -field separator), and @code{NF} (the number of fields in the current input +field separator) and @code{NF} (the number of fields in the current input record). @DBXREF{Built-in Variables} for a list of the predefined variables. These predefined variables can be used and assigned just like all other variables, but their values are also used or changed automatically by @@ -11268,7 +11214,7 @@ point, so the default behavior was restored to use a period as the decimal point character. You can use the @option{--use-lc-numeric} option (@pxref{Options}) to force @command{gawk} to use the locale's decimal point character. (@command{gawk} also uses the locale's decimal -point character when in POSIX mode, either via @option{--posix}, or the +point character when in POSIX mode, either via @option{--posix} or the @env{POSIXLY_CORRECT} environment variable, as shown previously.) @ref{table-locale-affects} describes the cases in which the locale's decimal @@ -11286,7 +11232,7 @@ features have not been described yet. @end multitable @end float -Finally, modern day formal standards and IEEE standard floating-point +Finally, modern-day formal standards and the IEEE standard floating-point representation can have an unusual but important effect on the way @command{gawk} converts some special string values to numbers. The details are presented in @ref{POSIX Floating Point Problems}. @@ -11294,7 +11240,7 @@ are presented in @ref{POSIX Floating Point Problems}. @node All Operators @section Operators: Doing Something with Values -This @value{SECTION} introduces the @dfn{operators} which make use +This @value{SECTION} introduces the @dfn{operators} that make use of the values provided by constants and variables. @menu @@ -11472,7 +11418,7 @@ print "something meaningful" > file name @noindent This produces a syntax error with some versions of Unix @command{awk}.@footnote{It happens that BWK -@command{awk}, @command{gawk} and @command{mawk} all ``get it right,'' +@command{awk}, @command{gawk}, and @command{mawk} all ``get it right,'' but you should not rely on this.} It is necessary to use the following: @@ -11561,11 +11507,8 @@ you're never quite sure what you'll get. @node Assignment Ops @subsection Assignment Expressions -@c STARTOFRANGE asop @cindex assignment operators -@c STARTOFRANGE opas @cindex operators, assignment -@c STARTOFRANGE exas @cindex expressions, assignment @cindex @code{=} (equals sign), @code{=} operator @cindex equals sign (@code{=}), @code{=} operator @@ -11725,7 +11668,7 @@ and @ifdocbook @DBREF{Numeric Functions} @end ifdocbook -for more information). +for more information.) This example illustrates an important fact about assignment operators: the lefthand expression is only evaluated @emph{once}. @@ -11761,17 +11704,17 @@ to a number. @caption{Arithmetic assignment operators} @multitable @columnfractions .30 .70 @headitem Operator @tab Effect -@item @var{lvalue} @code{+=} @var{increment} @tab Add @var{increment} to the value of @var{lvalue} -@item @var{lvalue} @code{-=} @var{decrement} @tab Subtract @var{decrement} from the value of @var{lvalue} -@item @var{lvalue} @code{*=} @var{coefficient} @tab Multiply the value of @var{lvalue} by @var{coefficient} -@item @var{lvalue} @code{/=} @var{divisor} @tab Divide the value of @var{lvalue} by @var{divisor} -@item @var{lvalue} @code{%=} @var{modulus} @tab Set @var{lvalue} to its remainder by @var{modulus} +@item @var{lvalue} @code{+=} @var{increment} @tab Add @var{increment} to the value of @var{lvalue}. +@item @var{lvalue} @code{-=} @var{decrement} @tab Subtract @var{decrement} from the value of @var{lvalue}. +@item @var{lvalue} @code{*=} @var{coefficient} @tab Multiply the value of @var{lvalue} by @var{coefficient}. +@item @var{lvalue} @code{/=} @var{divisor} @tab Divide the value of @var{lvalue} by @var{divisor}. +@item @var{lvalue} @code{%=} @var{modulus} @tab Set @var{lvalue} to its remainder by @var{modulus}. @cindex common extensions, @code{**=} operator @cindex extensions, common@comma{} @code{**=} operator @cindex @command{awk} language, POSIX version @cindex POSIX @command{awk} -@item @var{lvalue} @code{^=} @var{power} @tab -@item @var{lvalue} @code{**=} @var{power} @tab Raise @var{lvalue} to the power @var{power} @value{COMMONEXT} +@item @var{lvalue} @code{^=} @var{power} @tab Raise @var{lvalue} to the power @var{power}. +@item @var{lvalue} @code{**=} @var{power} @tab Raise @var{lvalue} to the power @var{power}. @value{COMMONEXT} @end multitable @end float @@ -11871,16 +11814,11 @@ awk '/[=]=/' /dev/null and @command{mawk} also do not. @end cartouche @end ifnotdocbook -@c ENDOFRANGE exas -@c ENDOFRANGE opas -@c ENDOFRANGE asop @node Increment Ops @subsection Increment and Decrement Operators -@c STARTOFRANGE inop @cindex increment operators -@c STARTOFRANGE opde @cindex operators, decrement/increment @dfn{Increment} and @dfn{decrement operators} increase or decrease the value of a variable by one. An assignment operator can do the same thing, so @@ -11928,7 +11866,6 @@ just like variables. (Use @samp{$(i++)} when you want to do a field reference and a variable increment at the same time. The parentheses are necessary because of the precedence of the field reference operator @samp{$}.) -@c STARTOFRANGE deop @cindex decrement operators The decrement operator @samp{--} works just like @samp{++}, except that it subtracts one instead of adding it. As with @samp{++}, it can be used before @@ -11973,8 +11910,8 @@ like @samp{@var{lvalue}++}, but instead of adding, it subtracts.) @cindex evaluation order @cindex Marx, Groucho @quotation -@i{Doctor, doctor! It hurts when I do this!@* -So don't do that!} +@i{Doctor, it hurts when I do this!@* +Then don't do that!} @author Groucho Marx @end quotation @@ -11998,7 +11935,7 @@ print b @cindex side effects In other words, when do the various side effects prescribed by the postfix operators (@samp{b++}) take effect? -When side effects happen is @dfn{implementation defined}. +When side effects happen is @dfn{implementation-defined}. In other words, it is up to the particular version of @command{awk}. The result for the first example may be 12 or 13, and for the second, it may be 22 or 23. @@ -12025,8 +11962,8 @@ You should avoid such things in your own programs. @cindex evaluation order @cindex Marx, Groucho @quotation -@i{Doctor, doctor! It hurts when I do this!@* -So don't do that!} +@i{Doctor, it hurts when I do this!@* +Then don't do that!} @author Groucho Marx @end quotation @@ -12050,7 +11987,7 @@ print b @cindex side effects In other words, when do the various side effects prescribed by the postfix operators (@samp{b++}) take effect? -When side effects happen is @dfn{implementation defined}. +When side effects happen is @dfn{implementation-defined}. In other words, it is up to the particular version of @command{awk}. The result for the first example may be 12 or 13, and for the second, it may be 22 or 23. @@ -12062,15 +11999,12 @@ You should avoid such things in your own programs. @c in the mirror in the morning. @end cartouche @end ifnotdocbook -@c ENDOFRANGE inop -@c ENDOFRANGE opde -@c ENDOFRANGE deop @node Truth Values and Conditions @section Truth Values and Conditions -In certain contexts, expression values also serve as ``truth values''; (i.e., -they determine what should happen next as the program runs). This +In certain contexts, expression values also serve as ``truth values''; i.e., +they determine what should happen next as the program runs. This @value{SECTION} describes how @command{awk} defines ``true'' and ``false'' and how values are compared. @@ -12129,19 +12063,15 @@ the string constant @code{"0"} is actually true, because it is non-null. @author Douglas Adams, @cite{The Hitchhiker's Guide to the Galaxy} @end quotation -@c STARTOFRANGE comex @cindex comparison expressions -@c STARTOFRANGE excom @cindex expressions, comparison @cindex expressions, matching, See comparison expressions @cindex matching, expressions, See comparison expressions @cindex relational operators, See comparison operators @cindex operators, relational, See operators@comma{} comparison -@c STARTOFRANGE varting @cindex variable typing -@c STARTOFRANGE vartypc @cindex variables, types of, comparison expressions and -Unlike other programming languages, @command{awk} variables do not have a +Unlike in other programming languages, in @command{awk} variables do not have a fixed type. Instead, they can be either a number or a string, depending upon the value that is assigned to them. We look now at how variables are typed, and how @command{awk} @@ -12170,20 +12100,20 @@ Variable typing follows these rules: @itemize @value{BULLET} @item -A numeric constant or the result of a numeric operation has the @var{numeric} +A numeric constant or the result of a numeric operation has the @dfn{numeric} attribute. @item -A string constant or the result of a string operation has the @var{string} +A string constant or the result of a string operation has the @dfn{string} attribute. @item Fields, @code{getline} input, @code{FILENAME}, @code{ARGV} elements, @code{ENVIRON} elements, and the elements of an array created by @code{match()}, @code{split()}, and @code{patsplit()} that are numeric -strings have the @var{strnum} attribute. Otherwise, they have -the @var{string} attribute. Uninitialized variables also have the -@var{strnum} attribute. +strings have the @dfn{strnum} attribute. Otherwise, they have +the @dfn{string} attribute. Uninitialized variables also have the +@dfn{strnum} attribute. @item Attributes propagate across assignments but are not changed by @@ -12327,13 +12257,13 @@ constant, then a string comparison is performed. Otherwise, a numeric comparison is performed. This point bears additional emphasis: All user input is made of characters, -and so is first and foremost of @var{string} type; input strings -that look numeric are additionally given the @var{strnum} attribute. +and so is first and foremost of string type; input strings +that look numeric are additionally given the strnum attribute. Thus, the six-character input string @w{@samp{ +3.14}} receives the -@var{strnum} attribute. In contrast, the eight characters +strnum attribute. In contrast, the eight characters @w{@code{" +3.14"}} appearing in program text comprise a string constant. The following examples print @samp{1} when the comparison between -the two different constants is true, @samp{0} otherwise: +the two different constants is true, and @samp{0} otherwise: @c 22.9.2014: Tested with mawk and BWK awk, got same results. @example @@ -12463,7 +12393,7 @@ $ @kbd{echo 1e2 3 | awk '@{ print ($1 < $2) ? "true" : "false" @}'} @noindent the result is @samp{false} because both @code{$1} and @code{$2} are user input. They are numeric strings---therefore both have -the @var{strnum} attribute, dictating a numeric comparison. +the strnum attribute, dictating a numeric comparison. The purpose of the comparison rules and the use of numeric strings is to attempt to produce the behavior that is ``least surprising,'' while still ``doing the right thing.'' @@ -12522,7 +12452,7 @@ characters sort, as defined by the locale (for more discussion, @pxref{Locales}). This order is usually very different from the results obtained when doing straight character-by-character comparison.@footnote{Technically, string comparison is supposed -to behave the same way as if the strings are compared with the C +to behave the same way as if the strings were compared with the C @code{strcoll()} function.} Because this behavior differs considerably from existing practice, @@ -12539,19 +12469,13 @@ $ @kbd{gawk --posix 'BEGIN @{ printf("ABC < abc = %s\n",} @print{} ABC < abc = FALSE @end example -@c ENDOFRANGE comex -@c ENDOFRANGE excom -@c ENDOFRANGE vartypc -@c ENDOFRANGE varting @node Boolean Ops @subsection Boolean Expressions @cindex and Boolean-logic operator @cindex or Boolean-logic operator @cindex not Boolean-logic operator -@c STARTOFRANGE exbo @cindex expressions, Boolean -@c STARTOFRANGE boex @cindex Boolean expressions @cindex operators, Boolean, See Boolean expressions @cindex Boolean operators, See Boolean expressions @@ -12635,7 +12559,7 @@ BEGIN @{ if (! ("HOME" in ENVIRON)) @cindex vertical bar (@code{|}), @code{||} operator The @samp{&&} and @samp{||} operators are called @dfn{short-circuit} operators because of the way they work. Evaluation of the full expression -is ``short-circuited'' if the result can be determined part way through +is ``short-circuited'' if the result can be determined partway through its evaluation. @cindex line continuations @@ -12697,8 +12621,6 @@ next record, and start processing the rules over again at the top. The reason it's there is to avoid printing the bracketing @samp{START} and @samp{END} lines. @end quotation -@c ENDOFRANGE exbo -@c ENDOFRANGE boex @node Conditional Exp @subsection Conditional Expressions @@ -12709,8 +12631,8 @@ The reason it's there is to avoid printing the bracketing A @dfn{conditional expression} is a special kind of expression that has three operands. It allows you to use one expression's value to select one of two other expressions. -The conditional expression is the same as in the C language, -as shown here: +The conditional expression in @command{awk} is the same as in the C +language, as shown here: @example @var{selector} ? @var{if-true-exp} : @var{if-false-exp} @@ -12719,8 +12641,8 @@ as shown here: @noindent There are three subexpressions. The first, @var{selector}, is always computed first. If it is ``true'' (not zero or not null), then -@var{if-true-exp} is computed next and its value becomes the value of -the whole expression. Otherwise, @var{if-false-exp} is computed next +@var{if-true-exp} is computed next, and its value becomes the value of +the whole expression. Otherwise, @var{if-false-exp} is computed next, and its value becomes the value of the whole expression. For example, the following expression produces the absolute value of @code{x}: @@ -12768,7 +12690,7 @@ ask for it by name at any point in the program. For example, the function @code{sqrt()} computes the square root of a number. @cindex functions, built-in -A fixed set of functions are @dfn{built-in}, which means they are +A fixed set of functions are @dfn{built in}, which means they are available in every @command{awk} program. The @code{sqrt()} function is one of these. @DBXREF{Built-in} for a list of built-in functions and their descriptions. In addition, you can define @@ -12877,9 +12799,7 @@ $ @kbd{awk -f matchit.awk} @node Precedence @section Operator Precedence (How Operators Nest) -@c STARTOFRANGE prec @cindex precedence -@c STARTOFRANGE oppr @cindex operators, precedence @dfn{Operator precedence} determines how operators are grouped when @@ -12944,7 +12864,7 @@ Increment, decrement. @cindex @code{*} (asterisk), @code{**} operator @cindex asterisk (@code{*}), @code{**} operator @item @code{^ **} -Exponentiation. These operators group right-to-left. +Exponentiation. These operators group right to left. @cindex @code{+} (plus sign), @code{+} operator @cindex plus sign (@code{+}), @code{+} operator @@ -13010,7 +12930,7 @@ statements belong to the statement level, not to expressions. The redirection does not produce an expression that could be the operand of another operator. As a result, it does not make sense to use a redirection operator near another operator of lower precedence without -parentheses. Such combinations (e.g., @samp{print foo > a ? b : c}), +parentheses. Such combinations (e.g., @samp{print foo > a ? b : c}) result in syntax errors. The correct way to write this statement is @samp{print foo > (a ? b : c)}. @@ -13028,17 +12948,17 @@ Array membership. @cindex @code{&} (ampersand), @code{&&} operator @cindex ampersand (@code{&}), @code{&&} operator @item @code{&&} -Logical ``and''. +Logical ``and.'' @cindex @code{|} (vertical bar), @code{||} operator @cindex vertical bar (@code{|}), @code{||} operator @item @code{||} -Logical ``or''. +Logical ``or.'' @cindex @code{?} (question mark), @code{?:} operator @cindex question mark (@code{?}), @code{?:} operator @item @code{?:} -Conditional. This operator groups right-to-left. +Conditional. This operator groups right to left. @cindex @code{+} (plus sign), @code{+=} operator @cindex plus sign (@code{+}), @code{+=} operator @@ -13055,7 +12975,7 @@ Conditional. This operator groups right-to-left. @cindex @code{^} (caret), @code{^=} operator @cindex caret (@code{^}), @code{^=} operator @item @code{= += -= *= /= %= ^= **=} -Assignment. These operators group right-to-left. +Assignment. These operators group right to left. @end table @cindex POSIX @command{awk}, @code{**} operator and @@ -13064,8 +12984,6 @@ Assignment. These operators group right-to-left. The @samp{|&}, @samp{**}, and @samp{**=} operators are not specified by POSIX. For maximum portability, do not use them. @end quotation -@c ENDOFRANGE prec -@c ENDOFRANGE oppr @node Locales @section Where You Are Makes a Difference @@ -13131,8 +13049,8 @@ Locales can influence the conversions. @item @command{awk} provides the usual arithmetic operators (addition, subtraction, multiplication, division, modulus), and unary plus and minus. -It also provides comparison operators, boolean operators, array membership -testing, and regexp +It also provides comparison operators, Boolean operators, an array membership +testing operator, and regexp matching operators. String concatenation is accomplished by placing two expressions next to each other; there is no explicit operator. The three-operand @samp{?:} operator provides an ``if-else'' test within @@ -13143,7 +13061,7 @@ Assignment operators provide convenient shorthands for common arithmetic operations. @item -In @command{awk}, a value is considered to be true if it is non-zero +In @command{awk}, a value is considered to be true if it is nonzero @emph{or} non-null. Otherwise, the value is false. @item @@ -13152,7 +13070,7 @@ lifetime. The type determines how it behaves in comparisons (string or numeric). @item -Function calls return a value which may be used as part of a larger +Function calls return a value that may be used as part of a larger expression. Expressions used to pass parameter values are fully evaluated before the function is called. @command{awk} provides built-in and user-defined functions; this is described in @@ -13169,11 +13087,9 @@ program, and occasionally the format for data read as input. @end itemize -@c ENDOFRANGE exps @node Patterns and Actions @chapter Patterns, Actions, and Variables -@c STARTOFRANGE pat @cindex patterns As you have already seen, each @command{awk} statement consists of @@ -13181,7 +13097,7 @@ a pattern with an associated action. This @value{CHAPTER} describes how you build patterns and actions, what kinds of things you can do within actions, and @command{awk}'s predefined variables. -The pattern-action rules and the statements available for use +The pattern--action rules and the statements available for use within actions form the core of @command{awk} programming. In a sense, everything covered up to here has been the foundation @@ -13372,7 +13288,7 @@ patterns. Likewise, the special patterns @code{BEGIN}, @code{END}, which never match any input record, are not expressions and cannot appear inside Boolean patterns. -The precedence of the different operators which can appear in +The precedence of the different operators that can appear in patterns is described in @ref{Precedence}. @node Ranges @@ -13398,7 +13314,7 @@ prints every record in @file{myfile} between @samp{on}/@samp{off} pairs, inclusi A range pattern starts out by matching @var{begpat} against every input record. When a record matches @var{begpat}, the range pattern is -@dfn{turned on} and the range pattern matches this record as well. As long as +@dfn{turned on}, and the range pattern matches this record as well. As long as the range pattern stays turned on, it automatically matches every input record read. The range pattern also matches @var{endpat} against every input record; when this succeeds, the range pattern is @dfn{turned off} again @@ -13469,9 +13385,7 @@ a range pattern. @value{DARKCORNER} @node BEGIN/END @subsection The @code{BEGIN} and @code{END} Special Patterns -@c STARTOFRANGE beg @cindex @code{BEGIN} pattern -@c STARTOFRANGE end @cindex @code{END} pattern All the patterns described so far are for matching input records. The @code{BEGIN} and @code{END} special patterns are different. @@ -13544,7 +13458,7 @@ using library functions. for a number of useful library functions. If an @command{awk} program has only @code{BEGIN} rules and no -other rules, then the program exits after the @code{BEGIN} rule is +other rules, then the program exits after the @code{BEGIN} rules are run.@footnote{The original version of @command{awk} kept reading and ignoring input until the end of the file was seen.} However, if an @code{END} rule exists, then the input is read, even if there are @@ -13572,7 +13486,7 @@ Another way is simply to assign a value to @code{$0}. @cindex @code{print} statement, @code{BEGIN}/@code{END} patterns and @cindex @code{BEGIN} pattern, @code{print} statement and @cindex @code{END} pattern, @code{print} statement and -The second point is similar to the first but from the other direction. +The second point is similar to the first, but from the other direction. Traditionally, due largely to implementation issues, @code{$0} and @code{NF} were @emph{undefined} inside an @code{END} rule. The POSIX standard specifies that @code{NF} is available in an @code{END} @@ -13609,8 +13523,6 @@ are not valid in an @code{END} rule, because all the input has been read. @ifdocbook @DBREF{Nextfile Statement}.) @end ifdocbook -@c ENDOFRANGE beg -@c ENDOFRANGE end @node BEGINFILE/ENDFILE @subsection The @code{BEGINFILE} and @code{ENDFILE} Special Patterns @@ -13663,7 +13575,7 @@ fatal error. @item If you have written extensions that modify the record handling (by -inserting an ``input parser,'' @pxref{Input Parsers}), you can invoke +inserting an ``input parser''; @pxref{Input Parsers}), you can invoke them at this point, before @command{gawk} has started processing the file. (This is a @emph{very} advanced feature, currently used only by the @uref{http://gawkextlib.sourceforge.net, @code{gawkextlib} project}.) @@ -13674,8 +13586,8 @@ the last record in an input file. For the last input file, it will be called before any @code{END} rules. The @code{ENDFILE} rule is executed even for empty input files. -Normally, when an error occurs when reading input in the normal input -processing loop, the error is fatal. However, if an @code{ENDFILE} +Normally, when an error occurs when reading input in the normal +input-processing loop, the error is fatal. However, if an @code{ENDFILE} rule is present, the error becomes non-fatal, and instead @code{ERRNO} is set. This makes it possible to catch and process I/O errors at the level of the @command{awk} program. @@ -13684,7 +13596,7 @@ level of the @command{awk} program. The @code{next} statement (@pxref{Next Statement}) is not allowed inside either a @code{BEGINFILE} or an @code{ENDFILE} rule. The @code{nextfile} statement is allowed only inside a -@code{BEGINFILE} rule, but not inside an @code{ENDFILE} rule. +@code{BEGINFILE} rule, not inside an @code{ENDFILE} rule. @cindex @code{getline} statement, @code{BEGINFILE}/@code{ENDFILE} patterns and The @code{getline} statement (@pxref{Getline}) is restricted inside @@ -13731,7 +13643,6 @@ awk '@{ print $1 @}' mail-list @noindent prints the first field of every record. -@c ENDOFRANGE pat @node Using Shell Variables @section Using Shell Variables in Programs @@ -13761,11 +13672,11 @@ awk "/$pattern/ "'@{ nmatches++ @} @noindent The @command{awk} program consists of two pieces of quoted text that are concatenated together to form the program. -The first part is double quoted, which allows substitution of +The first part is double-quoted, which allows substitution of the @code{pattern} shell variable inside the quotes. -The second part is single quoted. +The second part is single-quoted. -Variable substitution via quoting works, but can be potentially +Variable substitution via quoting works, but can potentially be messy. It requires a good understanding of the shell's quoting rules (@pxref{Quoting}), and it's often difficult to correctly @@ -13880,11 +13791,8 @@ For deleting array elements. @node Statements @section Control Statements in Actions -@c STARTOFRANGE csta @cindex control statements -@c STARTOFRANGE acs @cindex statements, control, in actions -@c STARTOFRANGE accs @cindex actions, control statements in @dfn{Control statements}, such as @code{if}, @code{while}, and so on, @@ -14027,13 +13935,13 @@ The body of this loop is a compound statement enclosed in braces, containing two statements. The loop works in the following manner: first, the value of @code{i} is set to one. Then, the @code{while} statement tests whether @code{i} is less than or equal to -three. This is true when @code{i} equals one, so the @code{i}-th +three. This is true when @code{i} equals one, so the @code{i}th field is printed. Then the @samp{i++} increments the value of @code{i} and the loop repeats. The loop terminates when @code{i} reaches four. A newline is not required between the condition and the body; however, using one makes the program clearer unless the body is a -compound statement or else is very simple. The newline after the open-brace +compound statement or else is very simple. The newline after the open brace that begins the compound statement is not required either, but the program is harder to read without it. @@ -14063,9 +13971,9 @@ while (@var{condition}) @end example @noindent -This statement does not execute @var{body} even once if the @var{condition} -is false to begin with. -The following is an example of a @code{do} statement: +This statement does not execute the @var{body} even once if the +@var{condition} is false to begin with. The following is an example of +a @code{do} statement: @example @{ @@ -14132,7 +14040,7 @@ their assignments as separate statements preceding the @code{for} loop.) The same is true of the @var{increment} part. Incrementing additional variables requires separate statements at the end of the loop. The C compound expression, using C's comma operator, is useful in -this context but it is not supported in @command{awk}. +this context, but it is not supported in @command{awk}. Most often, @var{increment} is an increment expression, as in the previous example. But this is not required; it can be any expression @@ -14223,7 +14131,7 @@ default: Control flow in the @code{switch} statement works as it does in C. Once a match to a given case is made, the case statement bodies execute until a @code{break}, -@code{continue}, @code{next}, @code{nextfile} or @code{exit} is encountered, +@code{continue}, @code{next}, @code{nextfile}, or @code{exit} is encountered, or the end of the @code{switch} statement itself. For example: @example @@ -14397,7 +14305,12 @@ body of a loop. Historical versions of @command{awk} treated a @code{continue} statement outside a loop the same way they treated a @code{break} statement outside a loop: as if it were a @code{next} statement +@ifset FOR_PRINT +(discussed in the following section). +@end ifset +@ifclear FOR_PRINT (@pxref{Next Statement}). +@end ifclear @value{DARKCORNER} Recent versions of BWK @command{awk} no longer work this way, nor does @command{gawk}. @@ -14525,7 +14438,7 @@ See @uref{http://austingroupbugs.net/view.php?id=607, the Austin Group website}. @cindex @code{nextfile} statement, user-defined functions and @cindex Brian Kernighan's @command{awk} @cindex @command{mawk} utility -The current version of BWK @command{awk}, and @command{mawk} +The current version of BWK @command{awk} and @command{mawk} also support @code{nextfile}. However, they don't allow the @code{nextfile} statement inside function bodies (@pxref{User-defined}). @command{gawk} does; a @code{nextfile} inside a function body reads the @@ -14563,7 +14476,7 @@ any @code{ENDFILE} rules; they do not execute. In such a case, if you don't want the @code{END} rule to do its job, set a variable -to nonzero before the @code{exit} statement and check that variable in +to a nonzero value before the @code{exit} statement and check that variable in the @code{END} rule. @DBXREF{Assert Function} for an example that does this. @@ -14602,15 +14515,10 @@ Negative values, and values of 127 or greater, may not produce consistent results across different operating systems. @end quotation -@c ENDOFRANGE csta -@c ENDOFRANGE acs -@c ENDOFRANGE accs @node Built-in Variables @section Predefined Variables -@c STARTOFRANGE bvar @cindex predefined variables -@c STARTOFRANGE varb @cindex variables, predefined Most @command{awk} variables are available to use for your own @@ -14636,10 +14544,8 @@ their areas of activity. @end menu @node User-modified -@subsection Built-In Variables That Control @command{awk} -@c STARTOFRANGE bvaru +@subsection Built-in Variables That Control @command{awk} @cindex predefined variables, user-modifiable -@c STARTOFRANGE nmbv @cindex user-modifiable variables The following is an alphabetical list of variables that you can change to @@ -14667,7 +14573,7 @@ respectively, should use binary I/O. A string value of @code{"rw"} or @code{"wr"} indicates that all files should use binary I/O. Any other string value is treated the same as @code{"rw"}, but causes @command{gawk} to generate a warning message. @code{BINMODE} is described in more -detail in @ref{PC Using}. @command{mawk} (@pxref{Other Versions}), +detail in @ref{PC Using}. @command{mawk} (@pxref{Other Versions}) also supports this variable, but only using numeric values. @cindex @code{CONVFMT} variable @@ -14675,7 +14581,7 @@ also supports this variable, but only using numeric values. @cindex numbers, converting, to strings @cindex strings, converting, numbers to @item @code{CONVFMT} -This string controls conversion of numbers to +A string that controls the conversion of numbers to strings (@pxref{Conversion}). It works by being passed, in effect, as the first argument to the @code{sprintf()} function @@ -14750,7 +14656,7 @@ is to simply say @samp{FS = FS}, perhaps with an explanatory comment. @cindex regular expressions, case sensitivity @item IGNORECASE # If @code{IGNORECASE} is nonzero or non-null, then all string comparisons -and all regular expression matching are case independent. Thus, regexp +and all regular expression matching are case-independent. Thus, regexp matching with @samp{~} and @samp{!~}, as well as the @code{gensub()}, @code{gsub()}, @code{index()}, @code{match()}, @code{patsplit()}, @code{split()}, and @code{sub()} @@ -14776,7 +14682,7 @@ Any other true value prints nonfatal warnings. Assigning a false value to @code{LINT} turns off the lint warnings. This variable is a @command{gawk} extension. It is not special -in other @command{awk} implementations. Unlike the other special variables, +in other @command{awk} implementations. Unlike with the other special variables, changing @code{LINT} does affect the production of lint warnings, even if @command{gawk} is in compatibility mode. Much as the @option{--lint} and @option{--traditional} options independently @@ -14788,7 +14694,7 @@ of @command{awk} being executed. @cindex numbers, converting, to strings @cindex strings, converting, numbers to @item OFMT -Controls conversion of numbers to +A string that controls conversion of numbers to strings (@pxref{Conversion}) for printing with the @code{print} statement. It works by being passed as the first argument to the @code{sprintf()} function @@ -14803,7 +14709,7 @@ strings in general expressions; this is now done by @code{CONVFMT}. @cindex separators, field @cindex field separators @item OFS -This is the output field separator (@pxref{Output Separators}). It is +The output field separator (@pxref{Output Separators}). It is output between the fields printed by a @code{print} statement. Its default value is @w{@code{" "}}, a string consisting of a single space. @@ -14821,7 +14727,7 @@ The working precision of arbitrary-precision floating-point numbers, @cindex @code{ROUNDMODE} variable @item ROUNDMODE # The rounding mode to use for arbitrary-precision arithmetic on -numbers, by default @code{"N"} (@samp{roundTiesToEven} in +numbers, by default @code{"N"} (@code{roundTiesToEven} in the IEEE 754 standard; @pxref{Setting the rounding mode}). @cindex @code{RS} variable @@ -14850,7 +14756,7 @@ just the first character of @code{RS}'s value is used. @item @code{SUBSEP} The subscript separator. It has the default value of @code{"\034"} and is used to separate the parts of the indices of a -multidimensional array. Thus, the expression @code{@w{foo["A", "B"]}} +multidimensional array. Thus, the expression @samp{@w{foo["A", "B"]}} really accesses @code{foo["A\034B"]} (@pxref{Multidimensional}). @@ -14866,17 +14772,11 @@ marked string constants in the source text, as well as for the (@pxref{Internationalization}). The default value of @code{TEXTDOMAIN} is @code{"messages"}. @end table -@c ENDOFRANGE bvar -@c ENDOFRANGE varb -@c ENDOFRANGE bvaru -@c ENDOFRANGE nmbv @node Auto-set -@subsection Built-In Variables That Convey Information +@subsection Built-in Variables That Convey Information -@c STARTOFRANGE bvconi @cindex predefined variables, conveying information -@c STARTOFRANGE vbconi @cindex variables, predefined conveying information The following is an alphabetical list of variables that @command{awk} sets automatically on certain occasions in order to provide @@ -15032,12 +14932,12 @@ input file. @item @code{NF} The number of fields in the current input record. @code{NF} is set each time a new record is read, when a new field is -created or when @code{$0} changes (@pxref{Fields}). +created, or when @code{$0} changes (@pxref{Fields}). Unlike most of the variables described in this @value{SUBSECTION}, assigning a value to @code{NF} has the potential to affect @command{awk}'s internal workings. In particular, assignments -to @code{NF} can be used to create or remove fields from the +to @code{NF} can be used to create fields in or remove fields from the current record. @xref{Changing Fields}. @cindex @code{FUNCTAB} array @@ -15087,7 +14987,7 @@ or @code{"FPAT"} if field matching with @code{FPAT} is in effect. @item PROCINFO["identifiers"] @cindex program identifiers A subarray, indexed by the names of all identifiers used in the text of -the AWK program. An @dfn{identifier} is simply the name of a variable +the @command{awk} program. An @dfn{identifier} is simply the name of a variable (be it scalar or array), built-in function, user-defined function, or extension function. For each identifier, the value of the element is one of the following: @@ -15107,7 +15007,7 @@ The identifier is an extension function loaded via The identifier is a scalar. @item "untyped" -The identifier is untyped (could be used as a scalar or array, +The identifier is untyped (could be used as a scalar or an array; @command{gawk} doesn't know yet). @item "user" @@ -15228,7 +15128,7 @@ is the length of the matched string, or @minus{}1 if no match is found. @cindex @code{RSTART} variable @item @code{RSTART} -The start-index in characters of the substring that is matched by the +The start index in characters of the substring that is matched by the @code{match()} function (@pxref{String Functions}). @code{RSTART} is set by invoking the @code{match()} function. Its value @@ -15295,11 +15195,9 @@ function multiply(variable, amount) @quotation NOTE In order to avoid severe time-travel paradoxes,@footnote{Not to mention difficult implementation issues.} neither @code{FUNCTAB} nor @code{SYMTAB} -are available as elements within the @code{SYMTAB} array. +is available as an element within the @code{SYMTAB} array. @end quotation @end table -@c ENDOFRANGE bvconi -@c ENDOFRANGE vbconi @cindex sidebar, Changing @code{NR} and @code{FNR} @ifdocbook @@ -15517,7 +15415,7 @@ When designing your program, you should choose options that don't conflict with @command{gawk}'s, because it will process any options that it accepts before passing the rest of the command line on to your program. Using @samp{#!} with the @option{-E} option may help -(@DBXREF{Executable Scripts} +(@DBPXREF{Executable Scripts} and @ifnotdocbook @DBPXREF{Options}). @@ -15531,15 +15429,15 @@ and @itemize @value{BULLET} @item -Pattern-action pairs make up the basic elements of an @command{awk} +Pattern--action pairs make up the basic elements of an @command{awk} program. Patterns are either normal expressions, range expressions, -regexp constants, one of the special keywords @code{BEGIN}, @code{END}, -@code{BEGINFILE}, @code{ENDFILE}, or empty. The action executes if +or regexp constants; one of the special keywords @code{BEGIN}, @code{END}, +@code{BEGINFILE}, or @code{ENDFILE}; or empty. The action executes if the current record matches the pattern. Empty (missing) patterns match all records. @item -I/O from @code{BEGIN} and @code{END} rules have certain constraints. +I/O from @code{BEGIN} and @code{END} rules has certain constraints. This is also true, only more so, for @code{BEGINFILE} and @code{ENDFILE} rules. The latter two give you ``hooks'' into @command{gawk}'s file processing, allowing you to recover from a file that otherwise would @@ -15569,12 +15467,12 @@ iteration of a loop (or get out of a @code{switch}). @item @code{next} and @code{nextfile} let you read the next record and start -over at the top of your program, or skip to the next input file and +over at the top of your program or skip to the next input file and start over, respectively. @item The @code{exit} statement terminates your program. When executed -from an action (or function body) it transfers control to the +from an action (or function body), it transfers control to the @code{END} statements. From an @code{END} statement body, it exits immediately. You may pass an optional numeric value to be used as @command{awk}'s exit status. @@ -15592,7 +15490,6 @@ control how @command{awk} will process the provided @value{DF}s. @node Arrays @chapter Arrays in @command{awk} -@c STARTOFRANGE arrs @cindex arrays An @dfn{array} is a table of values called @dfn{elements}. The @@ -15678,15 +15575,17 @@ the declaration. indices---e.g., @samp{15 .. 27}---but the size of the array is still fixed when the array is declared.) -A contiguous array of four elements might look like the following example, -conceptually, if the element values are 8, @code{"foo"}, -@code{""}, and 30 +@c 1/2015: Do not put the numeric values into @code. Array element +@c values are no different than scalar variable values. +A contiguous array of four elements might look like @ifnotdocbook -as shown in @ref{figure-array-elements}: +@ref{figure-array-elements}, @end ifnotdocbook @ifdocbook -as shown in @inlineraw{docbook, <xref linkend="figure-array-elements"/>}: +@inlineraw{docbook, <xref linkend="figure-array-elements"/>}, @end ifdocbook +conceptually, if the element values are eight, @code{"foo"}, +@code{""}, and 30. @ifnotdocbook @float Figure,figure-array-elements @@ -15711,12 +15610,10 @@ as shown in @inlineraw{docbook, <xref linkend="figure-array-elements"/>}: @noindent Only the values are stored; the indices are implicit from the order of -the values. Here, 8 is the value at index zero, because 8 appears in the +the values. Here, eight is the value at index zero, because eight appears in the position with zero elements before it. -@c STARTOFRANGE arrin @cindex arrays, indexing -@c STARTOFRANGE inarr @cindex indexing arrays @cindex associative arrays @cindex arrays, associative @@ -15725,19 +15622,21 @@ that each array is a collection of pairs---an index and its corresponding array element value: @ifnotdocbook -@example -@r{Index} 3 @r{Value} 30 -@r{Index} 1 @r{Value} "foo" -@r{Index} 0 @r{Value} 8 -@r{Index} 2 @r{Value} "" -@end example +@c extra empty column to indent it right +@multitable @columnfractions .1 .1 .1 +@headitem @tab Index @tab Value +@item @tab @code{3} @tab @code{30} +@item @tab @code{1} @tab @code{"foo"} +@item @tab @code{0} @tab @code{8} +@item @tab @code{2} @tab @code{""} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15783,20 +15682,22 @@ at any time. For example, suppose a tenth element is added to the array whose value is @w{@code{"number ten"}}. The result is: @ifnotdocbook -@example -@r{Index} 10 @r{Value} "number ten" -@r{Index} 3 @r{Value} 30 -@r{Index} 1 @r{Value} "foo" -@r{Index} 0 @r{Value} 8 -@r{Index} 2 @r{Value} "" -@end example +@c extra empty column to indent it right +@multitable @columnfractions .1 .1 .2 +@headitem @tab Index @tab Value +@item @tab @code{10} @tab @code{"number ten"} +@item @tab @code{3} @tab @code{30} +@item @tab @code{1} @tab @code{"foo"} +@item @tab @code{0} @tab @code{8} +@item @tab @code{2} @tab @code{""} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15848,19 +15749,20 @@ an index. For example, the following is an array that translates words from English to French: @ifnotdocbook -@example -@r{Index} "dog" @r{Value} "chien" -@r{Index} "cat" @r{Value} "chat" -@r{Index} "one" @r{Value} "un" -@r{Index} 1 @r{Value} "un" -@end example +@multitable @columnfractions .1 .1 .1 +@headitem @tab Index @tab Value +@item @tab @code{"dog"} @tab @code{"chien"} +@item @tab @code{"cat"} @tab @code{"chat"} +@item @tab @code{"one"} @tab @code{"un"} +@item @tab @code{1} @tab @code{"un"} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15902,7 +15804,7 @@ numbers and strings as indices. There are some subtleties to how numbers work when used as array subscripts; this is discussed in more detail in @ref{Numeric Array Subscripts}.) -Here, the number @code{1} isn't double quoted, because @command{awk} +Here, the number @code{1} isn't double-quoted, because @command{awk} automatically converts it to a string. @cindex @command{gawk}, @code{IGNORECASE} variable in @@ -15919,8 +15821,6 @@ that array's indices are consecutive integers starting at one. @command{awk}'s arrays are efficient---the time to access an element is independent of the number of elements in the array. -@c ENDOFRANGE arrin -@c ENDOFRANGE inarr @node Reference to Elements @subsection Referring to an Array Element @@ -15929,7 +15829,7 @@ is independent of the number of elements in the array. @cindex elements of arrays The principal way to use an array is to refer to one of its elements. -An array reference is an expression as follows: +An @dfn{array reference} is an expression as follows: @example @var{array}[@var{index-expression}] @@ -15939,8 +15839,11 @@ An array reference is an expression as follows: Here, @var{array} is the name of an array. The expression @var{index-expression} is the index of the desired element of the array. +@c 1/2015: Having the 4.3 in @samp is a little iffy. It's essentially +@c an expression though, so leave be. It's to early in the discussion +@c to mention that it's really a string. The value of the array reference is the current value of that array -element. For example, @code{foo[4.3]} is an expression for the element +element. For example, @code{foo[4.3]} is an expression referencing the element of array @code{foo} at index @samp{4.3}. @cindex arrays, unassigned elements @@ -16032,7 +15935,7 @@ assign to that element of the array. The following program takes a list of lines, each beginning with a line number, and prints them out in order of line number. The line numbers -are not in order when they are first read---instead they +are not in order when they are first read---instead, they are scrambled. This program sorts the lines by making an array using the line numbers as subscripts. The program then prints out the lines in sorted order of their numbers. It is a very simple program and gets @@ -16126,7 +16029,7 @@ program has previously used, with the variable @var{var} set to that index. The following program uses this form of the @code{for} statement. The first rule scans the input records and notes which words appear (at least once) in the input, by storing a one into the array @code{used} with -the word as index. The second rule scans the elements of @code{used} to +the word as the index. The second rule scans the elements of @code{used} to find all the distinct words that appear in the input. It prints each word that is more than 10 characters long and also prints the number of such words. @@ -16223,7 +16126,7 @@ and will vary from one version of @command{awk} to the next. Often, though, you may wish to do something simple, such as ``traverse the array by comparing the indices in ascending order,'' or ``traverse the array by comparing the values in descending order.'' -@command{gawk} provides two mechanisms which give you this control. +@command{gawk} provides two mechanisms that give you this control: @itemize @value{BULLET} @item @@ -16280,21 +16183,26 @@ across different environments.} which @command{gawk} uses internally to perform the sorting. @item "@@ind_str_desc" -String indices ordered from high to low. +Like @code{"@@ind_str_asc"}, but the +string indices are ordered from high to low. @item "@@ind_num_desc" -Numeric indices ordered from high to low. +Like @code{"@@ind_num_asc"}, but the +numeric indices are ordered from high to low. @item "@@val_type_desc" -Element values, based on type, ordered from high to low. +Like @code{"@@val_type_asc"}, but the +element values, based on type, are ordered from high to low. Subarrays, if present, come out first. @item "@@val_str_desc" -Element values, treated as strings, ordered from high to low. +Like @code{"@@val_str_asc"}, but the +element values, treated as strings, are ordered from high to low. Subarrays, if present, come out first. @item "@@val_num_desc" -Element values, treated as numbers, ordered from high to low. +Like @code{"@@val_num_asc"}, but the +element values, treated as numbers, are ordered from high to low. Subarrays, if present, come out first. @end table @@ -16517,7 +16425,7 @@ for (i in frequencies) @noindent This example removes all the elements from the array @code{frequencies}. Once an element is deleted, a subsequent @code{for} statement to scan the array -does not report that element and the @code{in} operator to check for +does not report that element and using the @code{in} operator to check for the presence of that element returns zero (i.e., false): @example @@ -16777,7 +16685,7 @@ a[1][2] = 2 This simulates a true two-dimensional array. Each subarray element can contain another subarray as a value, which in turn can hold other arrays as well. In this way, you can create arrays of three or more dimensions. -The indices can be any @command{awk} expression, including scalars +The indices can be any @command{awk} expressions, including scalars separated by commas (i.e., a regular @command{awk} simulated multidimensional subscript). So the following is valid in @command{gawk}: @@ -16789,7 +16697,7 @@ a[1][3][1, "name"] = "barney" Each subarray and the main array can be of different length. In fact, the elements of an array or its subarray do not all have to have the same type. This means that the main array and any of its subarrays can be -non-rectangular, or jagged in structure. You can assign a scalar value to +nonrectangular, or jagged in structure. You can assign a scalar value to the index @code{4} of the main array @code{a}, even though @code{a[1]} is itself an array and not a scalar: @@ -16813,7 +16721,8 @@ a[4][5][6][7] = "An element in a four-dimensional array" @noindent This removes the scalar value from index @code{4} and then inserts a -subarray of subarray of subarray containing a scalar. You can also +three-level nested subarray +containing a scalar. You can also delete an entire subarray or subarray of subarrays: @example @@ -16824,7 +16733,7 @@ a[4][5] = "An element in subarray a[4]" But recall that you can not delete the main array @code{a} and then use it as a scalar. -The built-in functions which take array arguments can also be used +The built-in functions that take array arguments can also be used with subarrays. For example, the following code fragment uses @code{length()} (@pxref{String Functions}) to determine the number of elements in the main array @code{a} and @@ -16854,7 +16763,7 @@ can be nested to scan all the elements of an array of arrays if it is rectangular in structure. In order to print the contents (scalar values) of a two-dimensional array of arrays (i.e., in which each first-level element is itself an -array, not necessarily of the same length) +array, not necessarily of the same length), you could use the following code: @example @@ -16954,9 +16863,9 @@ versions of @command{awk}. @item Standard @command{awk} simulates multidimensional arrays by separating -subscript values with a comma. The values are concatenated into a +subscript values with commas. The values are concatenated into a single string, separated by the value of @code{SUBSEP}. The fact -that such a subscript was created in this way is not retained; thus +that such a subscript was created in this way is not retained; thus, changing @code{SUBSEP} may have unexpected consequences. You can use @samp{(@var{sub1}, @var{sub2}, @dots{}) in @var{array}} to see if such a multidimensional subscript exists in @var{array}. @@ -16965,7 +16874,7 @@ a multidimensional subscript exists in @var{array}. @command{gawk} provides true arrays of arrays. You use a separate set of square brackets for each dimension in such an array: @code{data[row][col]}, for example. Array elements may thus be either -scalar values (number or string) or another array. +scalar values (number or string) or other arrays. @item Use the @code{isarray()} built-in function to determine if an array @@ -16973,14 +16882,11 @@ element is itself a subarray. @end itemize -@c ENDOFRANGE arrs @node Functions @chapter Functions -@c STARTOFRANGE funcbi @cindex functions, built-in -@c STARTOFRANGE bifunc @cindex built-in functions This @value{CHAPTER} describes @command{awk}'s built-in functions, which fall into three categories: numeric, string, and I/O. @@ -16993,6 +16899,9 @@ Besides the built-in functions, @command{awk} has provisions for writing new functions that the rest of a program can use. The second half of this @value{CHAPTER} describes these @dfn{user-defined} functions. +Finally, we explore indirect function calls, a @command{gawk}-specific +extension that lets you determine at runtime what function is to +be called. @menu * Built-in:: Summarizes the built-in functions. @@ -17002,7 +16911,7 @@ The second half of this @value{CHAPTER} describes these @end menu @node Built-in -@section Built-In Functions +@section Built-in Functions @dfn{Built-in} functions are always available for your @command{awk} program to call. This @value{SECTION} defines all @@ -17025,7 +16934,7 @@ but are summarized here for your convenience. @end menu @node Calling Built-in -@subsection Calling Built-In Functions +@subsection Calling Built-in Functions To call one of @command{awk}'s built-in functions, write the name of the function followed @@ -17076,7 +16985,7 @@ j = atan2(++i, i *= 2) @end example If the order of evaluation is left to right, then @code{i} first becomes -6, and then 12, and @code{atan2()} is called with the two arguments 6 +six, and then 12, and @code{atan2()} is called with the two arguments six and 12. But if the order of evaluation is right to left, @code{i} first becomes 10, then 11, and @code{atan2()} is called with the two arguments 11 and 10. @@ -17157,7 +17066,7 @@ In fact, @command{gawk} uses the BSD @code{random()} function, which is considerably better than @code{rand()}, to produce random numbers.} Often random integers are needed instead. Following is a user-defined function -that can be used to obtain a random non-negative integer less than @var{n}: +that can be used to obtain a random nonnegative integer less than @var{n}: @example function randint(n) @@ -17252,7 +17161,7 @@ implementations. The functions in this @value{SECTION} look at or change the text of one or more strings. -@code{gawk} understands locales (@pxref{Locales}), and does all +@command{gawk} understands locales (@pxref{Locales}) and does all string processing in terms of @emph{characters}, not @emph{bytes}. This distinction is particularly important to understand for locales where one character may be represented by multiple bytes. Thus, for @@ -17341,7 +17250,7 @@ a[2] = "de" a[3] = "sac" @end example -The @code{asorti()} function works similarly to @code{asort()}, however, +The @code{asorti()} function works similarly to @code{asort()}; however, the @emph{indices} are sorted, instead of the values. Thus, in the previous example, starting with the same initial set of indices and values in @code{a}, calling @samp{asorti(a)} would yield: @@ -17456,7 +17365,7 @@ If @var{find} is not found, @code{index()} returns zero. With BWK @command{awk} and @command{gawk}, it is a fatal error to use a regexp constant for @var{find}. Other implementations allow it, simply treating the regexp -constant as an expression meaning @samp{$0 ~ /regexp/}. @value{DARKCORNER}. +constant as an expression meaning @samp{$0 ~ /regexp/}. @value{DARKCORNER} @item @code{length(}[@var{string}]@code{)} @cindexawkfunc{length} @@ -17539,7 +17448,7 @@ If @option{--posix} is supplied, using an array argument is a fatal error @cindex string, regular expression match @cindex match regexp in string Search @var{string} for the -longest, leftmost substring matched by the regular expression, +longest, leftmost substring matched by the regular expression @var{regexp} and return the character position (index) at which that substring begins (one, if it starts at the beginning of @var{string}). If no match is found, return zero. @@ -17551,7 +17460,7 @@ In the latter case, the string is treated as a regexp to be matched. discussion of the difference between the two forms, and the implications for writing your program correctly. -The order of the first two arguments is backwards from most other string +The order of the first two arguments is the opposite of most other string functions that work with regular expressions, such as @code{sub()} and @code{gsub()}. It might help to remember that for @code{match()}, the order is the same as for the @samp{~} operator: @@ -17640,7 +17549,7 @@ $ @kbd{echo foooobazbarrrrr |} @end example There may not be subscripts for the start and index for every parenthesized -subexpression, because they may not all have matched text; thus they +subexpression, because they may not all have matched text; thus, they should be tested for with the @code{in} operator (@pxref{Reference to Elements}). @@ -17687,13 +17596,13 @@ a regexp describing where to split @var{string} (much as @code{FS} can be a regexp describing where to split input records). If @var{fieldsep} is omitted, the value of @code{FS} is used. @code{split()} returns the number of elements created. -@var{seps} is a @command{gawk} extension with @code{@var{seps}[@var{i}]} +@var{seps} is a @command{gawk} extension, with @code{@var{seps}[@var{i}]} being the separator string between @code{@var{array}[@var{i}]} and @code{@var{array}[@var{i}+1]}. If @var{fieldsep} is a single -space then any leading whitespace goes into @code{@var{seps}[0]} and +space, then any leading whitespace goes into @code{@var{seps}[0]} and any trailing -whitespace goes into @code{@var{seps}[@var{n}]} where @var{n} is the +whitespace goes into @code{@var{seps}[@var{n}]}, where @var{n} is the return value of @code{split()} (i.e., the number of elements in @var{array}). @@ -17706,7 +17615,7 @@ split("cul-de-sac", a, "-", seps) @noindent @cindex strings splitting, example -splits the string @samp{cul-de-sac} into three fields using @samp{-} as the +splits the string @code{"cul-de-sac"} into three fields using @samp{-} as the separator. It sets the contents of the array @code{a} as follows: @example @@ -17731,19 +17640,18 @@ As with input field-splitting, when the value of @var{fieldsep} is the elements of @var{array} but not in @var{seps}, and the elements are separated by runs of whitespace. -Also, as with input field-splitting, if @var{fieldsep} is the null string, each +Also, as with input field splitting, if @var{fieldsep} is the null string, each individual character in the string is split into its own array element. @value{COMMONEXT} Note, however, that @code{RS} has no effect on the way @code{split()} -works. Even though @samp{RS = ""} causes newline to also be an input +works. Even though @samp{RS = ""} causes the newline character to also be an input field separator, this does not affect how @code{split()} splits strings. @cindex dark corner, @code{split()} function Modern implementations of @command{awk}, including @command{gawk}, allow -the third argument to be a regexp constant (@code{/abc/}) as well as a -string. -@value{DARKCORNER} +the third argument to be a regexp constant (@w{@code{/}@dots{}@code{/}}) +as well as a string. @value{DARKCORNER} The POSIX standard allows this as well. @DBXREF{Computed Regexps} for a discussion of the difference between using a string constant or a regexp constant, @@ -17880,7 +17788,7 @@ an @samp{&}: @cindex @code{sub()} function, arguments of @cindex @code{gsub()} function, arguments of As mentioned, the third argument to @code{sub()} must -be a variable, field or array element. +be a variable, field, or array element. Some versions of @command{awk} allow the third argument to be an expression that is not an lvalue. In such a case, @code{sub()} still searches for the pattern and returns zero or one, but the result of @@ -18072,8 +17980,8 @@ example, @code{"a\qb"} is treated as @code{"aqb"}. At the runtime level, the various functions handle sequences of @samp{\} and @samp{&} differently. The situation is (sadly) somewhat complex. -Historically, the @code{sub()} and @code{gsub()} functions treated the two -character sequence @samp{\&} specially; this sequence was replaced in +Historically, the @code{sub()} and @code{gsub()} functions treated the +two-character sequence @samp{\&} specially; this sequence was replaced in the generated text with a single @samp{&}. Any other @samp{\} within the @var{replacement} string that did not precede an @samp{&} was passed through unchanged. This is illustrated in @ref{table-sub-escapes}. @@ -18131,7 +18039,7 @@ _bigskip} @end float @noindent -This table shows both the lexical-level processing, where +This table shows the lexical-level processing, where an odd number of backslashes becomes an even number at the runtime level, as well as the runtime processing done by @code{sub()}. (For the sake of simplicity, the rest of the following tables only show the @@ -18152,7 +18060,7 @@ This is shown in @ref{table-sub-proposed}. @float Table,table-sub-proposed -@caption{GNU @command{awk} rules for @code{sub()} and backslash} +@caption{@command{gawk} rules for @code{sub()} and backslash} @tex \vbox{\bigskip % We need more characters for escape and tab ... @@ -18197,7 +18105,7 @@ _bigskip} @end float In a nutshell, at the runtime level, there are now three special sequences -of characters (@samp{\\\&}, @samp{\\&} and @samp{\&}) whereas historically +of characters (@samp{\\\&}, @samp{\\&}, and @samp{\&}) whereas historically there was only one. However, as in the historical case, any @samp{\} that is not part of one of these three sequences is not special and appears in the output literally. @@ -18263,7 +18171,7 @@ The only case where the difference is noticeable is the last one: @samp{\\\\} is seen as @samp{\\} and produces @samp{\} instead of @samp{\\}. Starting with @value{PVERSION} 3.1.4, @command{gawk} followed the POSIX rules -when @option{--posix} is specified (@pxref{Options}). Otherwise, +when @option{--posix} was specified (@pxref{Options}). Otherwise, it continued to follow the proposed rules, as that had been its behavior for many years. @@ -18331,7 +18239,7 @@ _bigskip} @end ifnottex @end float -Because of the complexity of the lexical and runtime level processing +Because of the complexity of the lexical- and runtime-level processing and the special cases for @code{sub()} and @code{gsub()}, we recommend the use of @command{gawk} and @code{gensub()} when you have to do substitutions. @@ -18357,6 +18265,7 @@ for more information. When closing a coprocess, it is occasionally useful to first close one end of the two-way pipe and then to close the other. This is done by providing a second argument to @code{close()}. This second argument +(@var{how}) should be one of the two string values @code{"to"} or @code{"from"}, indicating which end of the pipe to close. Case in the string does not matter. @@ -18383,7 +18292,7 @@ every little bit of information as soon as it is ready. However, sometimes it is necessary to force a program to @dfn{flush} its buffers (i.e., write the information to its destination, even if a buffer is not full). This is the purpose of the @code{fflush()} function---@command{gawk} also -buffers its output and the @code{fflush()} function forces +buffers its output, and the @code{fflush()} function forces @command{gawk} to flush its buffers. @cindex extensions, common@comma{} @code{fflush()} function @@ -18404,7 +18313,7 @@ would flush only the standard output if there was no argument, and flush all output files and pipes if the argument was the null string. This was changed in order to be compatible with Brian Kernighan's @command{awk}, in the hope that standardizing this -feature in POSIX would then be easier (which indeed helped). +feature in POSIX would then be easier (which indeed proved to be the case). With @command{gawk}, you can use @samp{fflush("/dev/stdout")} if you wish to flush @@ -18415,7 +18324,7 @@ only the standard output. @c @cindex warnings, automatic @cindex troubleshooting, @code{fflush()} function @code{fflush()} returns zero if the buffer is successfully flushed; -otherwise, it returns non-zero. (@command{gawk} returns @minus{}1.) +otherwise, it returns a nonzero value. (@command{gawk} returns @minus{}1.) In the case where all buffers are flushed, the return value is zero only if all buffers were flushed successfully. Otherwise, it is @minus{}1, and @command{gawk} warns about the problem @var{filename}. @@ -18433,8 +18342,8 @@ In such a case, @code{fflush()} returns @minus{}1, as well. @cindex buffering, interactive vs.@: noninteractive -As a side point, buffering issues can be even more confusing, depending -upon whether your program is @dfn{interactive} (i.e., communicating +As a side point, buffering issues can be even more confusing if +your program is @dfn{interactive} (i.e., communicating with a user sitting at a keyboard).@footnote{A program is interactive if the standard output is connected to a terminal device. On modern systems, this means your keyboard and screen.} @@ -18484,8 +18393,8 @@ it is all buffered and sent down the pipe to @command{cat} in one shot. @cindex buffering, interactive vs.@: noninteractive -As a side point, buffering issues can be even more confusing, depending -upon whether your program is @dfn{interactive} (i.e., communicating +As a side point, buffering issues can be even more confusing if +your program is @dfn{interactive} (i.e., communicating with a user sitting at a keyboard).@footnote{A program is interactive if the standard output is connected to a terminal device. On modern systems, this means your keyboard and screen.} @@ -18529,7 +18438,7 @@ it is all buffered and sent down the pipe to @command{cat} in one shot. @cindexawkfunc{system} @cindex invoke shell command @cindex interacting with other programs -Execute the operating-system +Execute the operating system command @var{command} and then return to the @command{awk} program. Return @var{command}'s exit status. @@ -18704,18 +18613,14 @@ you would see the latter (undesirable) output. @subsection Time Functions @cindex time functions -@c STARTOFRANGE tst @cindex timestamps -@c STARTOFRANGE logftst @cindex log files, timestamps in -@c STARTOFRANGE filogtst @cindex files, log@comma{} timestamps in -@c STARTOFRANGE gawtst @cindex @command{gawk}, timestamps @cindex POSIX @command{awk}, timestamps and -@code{awk} programs are commonly used to process log files +@command{awk} programs are commonly used to process log files containing timestamp information, indicating when a -particular log record was written. Many programs log their timestamp +particular log record was written. Many programs log their timestamps in the form returned by the @code{time()} system call, which is the number of seconds since a particular epoch. On POSIX-compliant systems, it is the number of seconds since @@ -18776,7 +18681,7 @@ The values of these numbers need not be within the ranges specified; for example, an hour of @minus{}1 means 1 hour before midnight. The origin-zero Gregorian calendar is assumed, with year 0 preceding year 1 and year @minus{}1 preceding year 0. -The time is assumed to be in the local timezone. +The time is assumed to be in the local time zone. If the daylight-savings flag is positive, the time is assumed to be daylight savings time; if zero, the time is assumed to be standard time; and if negative (the default), @code{mktime()} attempts to determine @@ -18788,7 +18693,6 @@ is out of range, @code{mktime()} returns @minus{}1. @cindex @command{gawk}, @code{PROCINFO} array in @cindex @code{PROCINFO} array @item @code{strftime(}[@var{format} [@code{,} @var{timestamp} [@code{,} @var{utc-flag}] ] ]@code{)} -@c STARTOFRANGE strf @cindexgawkfunc{strftime} @cindex format time string Format the time specified by @var{timestamp} @@ -18937,12 +18841,12 @@ Equivalent to specifying @samp{%H:%M:%S}. The weekday as a decimal number (1--7). Monday is day one. @item %U -The week number of the year (the first Sunday as the first day of week one) +The week number of the year (with the first Sunday as the first day of week one) as a decimal number (00--53). @c @cindex ISO 8601 @item %V -The week number of the year (the first Monday as the first +The week number of the year (with the first Monday as the first day of week one) as a decimal number (01--53). The method for determining the week number is as specified by ISO 8601. (To wit: if the week containing January 1 has four or more days in the @@ -18953,7 +18857,7 @@ and the next week is week one.) The weekday as a decimal number (0--6). Sunday is day zero. @item %W -The week number of the year (the first Monday as the first day of week one) +The week number of the year (with the first Monday as the first day of week one) as a decimal number (00--53). @item %x @@ -18973,8 +18877,8 @@ The full year as a decimal number (e.g., 2015). @c @cindex RFC 822 @c @cindex RFC 1036 @item %z -The timezone offset in a +HHMM format (e.g., the format necessary to -produce RFC 822/RFC 1036 date headers). +The time zone offset in a @samp{+@var{HHMM}} format (e.g., the format +necessary to produce RFC 822/RFC 1036 date headers). @item %Z The time zone name or abbreviation; no characters if @@ -19037,7 +18941,6 @@ The time as a decimal timestamp in seconds since the epoch. The date in VMS format (e.g., @samp{20-JUN-1991}). @end ignore @end table -@c ENDOFRANGE strf Additionally, the alternative representations are recognized but their normal representations are used. @@ -19088,23 +18991,14 @@ gawk 'BEGIN @{ exit exitval @}' "$@@" @end example -@c ENDOFRANGE tst -@c ENDOFRANGE logftst -@c ENDOFRANGE filogtst -@c ENDOFRANGE gawtst @node Bitwise Functions @subsection Bit-Manipulation Functions @cindex bit-manipulation functions -@c STARTOFRANGE bit @cindex bitwise, operations -@c STARTOFRANGE and @cindex AND bitwise operation -@c STARTOFRANGE oro @cindex OR bitwise operation -@c STARTOFRANGE xor @cindex XOR bitwise operation -@c STARTOFRANGE opbit @cindex operations, bitwise @quotation @i{I can explain it for you, but I can't understand it for you.} @@ -19124,7 +19018,7 @@ The operations are described in @ref{table-bitwise-ops}. @ifnottex @ifnotdocbook @display - Bit Operator + Bit operator | AND | OR | XOR |---+---+---+---+---+--- Operands | 0 | 1 | 0 | 1 | 0 | 1 @@ -19182,7 +19076,7 @@ Operands | 0 | 1 | 0 | 1 | 0 | 1 <tbody> <row> <entry colsep="0"></entry> -<entry spanname="optitle"><emphasis role="bold">Bit Operator</emphasis></entry> +<entry spanname="optitle"><emphasis role="bold">Bit operator</emphasis></entry> </row> <row rowsep="1"> @@ -19246,10 +19140,9 @@ of a given value. Finally, two other common operations are to shift the bits left or right. For example, if you have a bit string @samp{10111001} and you shift it right by three bits, you end up with @samp{00010111}.@footnote{This example -shows that 0's come in on the left side. For @command{gawk}, this is +shows that zeros come in on the left side. For @command{gawk}, this is always true, but in some languages, it's possible to have the left side -fill with 1's.} -@c Purposely decided to use 0's and 1's here. 2/2001. +fill with ones.} If you start over again with @samp{10111001} and shift it left by three bits, you end up with @samp{11001000}. The following list describes @command{gawk}'s built-in functions that implement the bitwise operations. @@ -19303,7 +19196,7 @@ that illustrates the use of these functions: @example @group @c file eg/lib/bits2str.awk -# bits2str --- turn a byte into readable 1's and 0's +# bits2str --- turn a byte into readable ones and zeros function bits2str(bits, data, mask) @{ @@ -19377,15 +19270,16 @@ $ @kbd{gawk -f testbits.awk} @cindex converting, numbers to strings @cindex number as string of bits The @code{bits2str()} function turns a binary number into a string. -The number @code{1} represents a binary value where the rightmost bit -is set to 1. Using this mask, +Initializing @code{mask} to one creates +a binary value where the rightmost bit +is set to one. Using this mask, the function repeatedly checks the rightmost bit. ANDing the mask with the value indicates whether the -rightmost bit is 1 or not. If so, a @code{"1"} is concatenated onto the front +rightmost bit is one or not. If so, a @code{"1"} is concatenated onto the front of the string. Otherwise, a @code{"0"} is added. The value is then shifted right by one bit and the loop continues -until there are no more 1 bits. +until there are no more one bits. If the initial value is zero, it returns a simple @code{"0"}. Otherwise, at the end, it pads the value with zeros to represent multiples @@ -19396,11 +19290,6 @@ decimal and octal values for the same numbers (@pxref{Nondecimal-numbers}), and then demonstrates the results of the @code{compl()}, @code{lshift()}, and @code{rshift()} functions. -@c ENDOFRANGE bit -@c ENDOFRANGE and -@c ENDOFRANGE oro -@c ENDOFRANGE xor -@c ENDOFRANGE opbit @node Type Functions @subsection Getting Type Information @@ -19414,7 +19303,7 @@ that traverses every element of an array of arrays @cindexgawkfunc{isarray} @cindex scalar or array @item isarray(@var{x}) -Return a true value if @var{x} is an array. Otherwise return false. +Return a true value if @var{x} is an array. Otherwise, return false. @end table @code{isarray()} is meant for use in two circumstances. The first is when @@ -19475,20 +19364,16 @@ The default value for @var{category} is @code{"LC_MESSAGES"}. Return the plural form used for @var{number} of the translation of @var{string1} and @var{string2} in text domain @var{domain} for locale category @var{category}. @var{string1} is the -English singular variant of a message, and @var{string2} the English plural +English singular variant of a message, and @var{string2} is the English plural variant of the same message. The default value for @var{domain} is the current value of @code{TEXTDOMAIN}. The default value for @var{category} is @code{"LC_MESSAGES"}. @end table -@c ENDOFRANGE funcbi -@c ENDOFRANGE bifunc @node User-defined @section User-Defined Functions -@c STARTOFRANGE udfunc @cindex user-defined functions -@c STARTOFRANGE funcud @cindex functions, user-defined Complicated @command{awk} programs can often be simplified by defining your own functions. User-defined functions can be called just like @@ -19508,12 +19393,11 @@ them (i.e., to tell @command{awk} what they should do). @subsection Function Definition Syntax @quotation -@i{It's entirely fair to say that the @command{awk} syntax for local +@i{It's entirely fair to say that the awk syntax for local variable definitions is appallingly awful.} @author Brian Kernighan @end quotation -@c STARTOFRANGE fdef @cindex functions, defining Definitions of functions can appear anywhere between the rules of an @command{awk} program. Thus, the general form of an @command{awk} program is @@ -19551,14 +19435,23 @@ the call. A function cannot have two parameters with the same name, nor may it have a parameter with the same name as the function itself. -In addition, according to the POSIX standard, function parameters + +@quotation CAUTION +According to the POSIX standard, function parameters cannot have the same name as one of the special predefined variables -(@pxref{Built-in Variables}). Not all versions of @command{awk} enforce -this restriction. +(@pxref{Built-in Variables}), nor may a function parameter have the +same name as another function. + +Not all versions of @command{awk} enforce +these restrictions. +@command{gawk} always enforces the first restriction. +With @option{--posix} (@pxref{Options}), +it also enforces the second restriction. +@end quotation Local variables act like the empty string if referenced where a string value is required, and like zero if referenced where a numeric value -is required. This is the same as regular variables that have never been +is required. This is the same as the behavior of regular variables that have never been assigned a value. (There is more to understand about local variables; @pxref{Dynamic Typing}.) @@ -19592,7 +19485,7 @@ During execution of the function body, the arguments and local variable values hide, or @dfn{shadow}, any variables of the same names used in the rest of the program. The shadowed variables are not accessible in the function definition, because there is no way to name them while their -names have been taken away for the local variables. All other variables +names have been taken away for the arguments and local variables. All other variables used in the @command{awk} program can be referenced or set normally in the function's body. @@ -19659,7 +19552,7 @@ function myprint(num) @end example @noindent -To illustrate, here is an @command{awk} rule that uses our @code{myprint} +To illustrate, here is an @command{awk} rule that uses our @code{myprint()} function: @example @@ -19700,13 +19593,13 @@ in an array and start over with a new list of elements (@pxref{Delete}). Instead of having to repeat this loop everywhere that you need to clear out -an array, your program can just call @code{delarray}. +an array, your program can just call @code{delarray()}. (This guarantees portability. The use of @samp{delete @var{array}} to delete the contents of an entire array is a relatively recent@footnote{Late in 2012.} addition to the POSIX standard.) The following is an example of a recursive function. It takes a string -as an input parameter and returns the string in backwards order. +as an input parameter and returns the string in reverse order. Recursive functions must always have a test that stops the recursion. In this case, the recursion terminates when the input string is already empty: @@ -19760,12 +19653,10 @@ You might think that @code{ctime()} could use @code{PROCINFO["strftime"]} for its format string. That would be a mistake, because @code{ctime()} is supposed to return the time formatted in a standard fashion, and user-level code could have changed @code{PROCINFO["strftime"]}. -@c ENDOFRANGE fdef @node Function Caveats @subsection Calling User-Defined Functions -@c STARTOFRANGE fudc @cindex functions, user-defined, calling @dfn{Calling a function} means causing the function to run and do its job. A function call is an expression and its value is the value returned by @@ -19805,7 +19696,7 @@ an error. @cindex local variables, in a function @cindex variables, local to a function -Unlike many languages, +Unlike in many languages, there is no way to make a variable local to a @code{@{} @dots{} @code{@}} block in @command{awk}, but you can make a variable local to a function. It is good practice to do so whenever a variable is needed only in that @@ -19814,7 +19705,7 @@ function. To make a variable local to a function, simply declare the variable as an argument after the actual function arguments (@pxref{Definition Syntax}). -Look at the following example where variable +Look at the following example, where variable @code{i} is a global variable used by both functions @code{foo()} and @code{bar()}: @@ -19855,7 +19746,7 @@ foo's i=3 top's i=3 @end example -If you want @code{i} to be local to both @code{foo()} and @code{bar()} do as +If you want @code{i} to be local to both @code{foo()} and @code{bar()}, do as follows (the extra space before @code{i} is a coding convention to indicate that @code{i} is a local variable, not an argument): @@ -19943,7 +19834,7 @@ declare explicitly whether the arguments are passed @dfn{by value} or @dfn{by reference}. Instead, the passing convention is determined at runtime when -the function is called according to the following rule: +the function is called, according to the following rule: if the argument is an array variable, then it is passed by reference. Otherwise, the argument is passed by value. @@ -20020,7 +19911,7 @@ prints @samp{a[1] = 1, a[2] = two, a[3] = 3}, because @cindex undefined functions @cindex functions, undefined Some @command{awk} implementations allow you to call a function that -has not been defined. They only report a problem at runtime when the +has not been defined. They only report a problem at runtime, when the program actually tries to call the function. For example: @example @@ -20057,7 +19948,6 @@ or the @code{nextfile} statement @end ifnotdocbook inside a user-defined function. @command{gawk} does not have this limitation. -@c ENDOFRANGE fudc @node Return Statement @subsection The @code{return} Statement @@ -20080,15 +19970,15 @@ makes the returned value undefined, and therefore, unpredictable. In practice, though, all versions of @command{awk} simply return the null string, which acts like zero if used in a numeric context. -A @code{return} statement with no value expression is assumed at the end of -every function definition. So if control reaches the end of the function -body, then technically, the function returns an unpredictable value. +A @code{return} statement without an @var{expression} is assumed at the end of +every function definition. So, if control reaches the end of the function +body, then technically the function returns an unpredictable value. In practice, it returns the empty string. @command{awk} does @emph{not} warn you if you use the return value of such a function. Sometimes, you want to write a function for what it does, not for what it returns. Such a function corresponds to a @code{void} function -in C, C++ or Java, or to a @code{procedure} in Ada. Thus, it may be appropriate to not +in C, C++, or Java, or to a @code{procedure} in Ada. Thus, it may be appropriate to not return any value; simply bear in mind that you should not be using the return value of such a function. @@ -20185,7 +20075,6 @@ does report the second error. Usually, such things aren't a big issue, but it's worth being aware of them. -@c ENDOFRANGE udfunc @node Indirect Calls @section Indirect Function Calls @@ -20208,13 +20097,15 @@ function calls, you can specify the name of the function to call as a string variable, and then call the function. Let's look at an example. Suppose you have a file with your test scores for the classes you -are taking. The first field is the class name. The following fields +are taking, and +you wish to get the sum and the average of +your test scores. +The first field is the class name. The following fields are the functions to call to process the data, up to a ``marker'' field @samp{data:}. Following the marker, to the end of the record, are the various numeric test scores. -Here is the initial file; you wish to get the sum and the average of -your test scores: +Here is the initial file: @example @c file eg/data/class_data1 @@ -20297,9 +20188,9 @@ function sum(first, last, ret, i) @c endfile @end example -These two functions expect to work on fields; thus the parameters +These two functions expect to work on fields; thus, the parameters @code{first} and @code{last} indicate where in the fields to start and end. -Otherwise they perform the expected computations and are not unusual: +Otherwise, they perform the expected computations and are not unusual: @example @c file eg/prog/indirectcall.awk @@ -20358,8 +20249,8 @@ The ability to use indirect function calls is more powerful than you may think at first. The C and C++ languages provide ``function pointers,'' which are a mechanism for calling a function chosen at runtime. One of the most well-known uses of this ability is the C @code{qsort()} function, which sorts -an array using the famous ``quick sort'' algorithm -(see @uref{http://en.wikipedia.org/wiki/Quick_sort, the Wikipedia article} +an array using the famous ``quicksort'' algorithm +(see @uref{http://en.wikipedia.org/wiki/Quicksort, the Wikipedia article} for more information). To use this function, you supply a pointer to a comparison function. This mechanism allows you to sort arbitrary data in an arbitrary fashion. @@ -20378,11 +20269,11 @@ We can do something similar using @command{gawk}, like this: # January 2009 @c endfile - @end ignore @c file eg/lib/quicksort.awk -# quicksort --- C.A.R. Hoare's quick sort algorithm. See Wikipedia -# or almost any algorithms or computer science text + +# quicksort --- C.A.R. Hoare's quicksort algorithm. See Wikipedia +# or almost any algorithms or computer science text. @c endfile @ignore @c file eg/lib/quicksort.awk @@ -20420,7 +20311,7 @@ function quicksort_swap(data, i, j, temp) The @code{quicksort()} function receives the @code{data} array, the starting and ending indices to sort (@code{left} and @code{right}), and the name of a function that -performs a ``less than'' comparison. It then implements the quick sort algorithm. +performs a ``less than'' comparison. It then implements the quicksort algorithm. To make use of the sorting function, we return to our previous example. The first thing to do is write some comparison functions: @@ -20611,7 +20502,7 @@ for (i = 1; i <= n; i++) @end example @noindent -@code{gawk} looks up the actual function to call only once. +@command{gawk} looks up the actual function to call only once. @node Functions Summary @section Summary @@ -20678,7 +20569,6 @@ program. This is equivalent to function pointers in C and C++. @end itemize -@c ENDOFRANGE funcud @ifnotinfo @part @value{PART2}Problem Solving with @command{awk} @@ -20700,18 +20590,15 @@ It contains the following chapters: @node Library Functions @chapter A Library of @command{awk} Functions -@c STARTOFRANGE libf @cindex libraries of @command{awk} functions -@c STARTOFRANGE flib @cindex functions, library -@c STARTOFRANGE fudlib @cindex functions, user-defined, library of @DBREF{User-defined} describes how to write your own @command{awk} functions. Writing functions is important, because it allows you to encapsulate algorithms and program tasks in a single place. It simplifies programming, making program development more -manageable, and making programs more readable. +manageable and making programs more readable. @cindex Kernighan, Brian @cindex Plauger, P.J.@: @@ -20840,7 +20727,7 @@ often use variable names like these for their own purposes. The example programs shown in this @value{CHAPTER} all start the names of their private variables with an underscore (@samp{_}). Users generally don't use leading underscores in their variable names, so this convention immediately -decreases the chances that the variable name will be accidentally shared +decreases the chances that the variable names will be accidentally shared with the user's program. @cindex @code{_} (underscore), in names of private variables @@ -20858,8 +20745,8 @@ show how our own @command{awk} programming style has evolved and to provide some basis for this discussion.} As a final note on variable naming, if a function makes global variables -available for use by a main program, it is a good convention to start that -variable's name with a capital letter---for +available for use by a main program, it is a good convention to start those +variables' names with a capital letter---for example, @code{getopt()}'s @code{Opterr} and @code{Optind} variables (@pxref{Getopt Function}). The leading capital letter indicates that it is global, while the fact that @@ -20870,7 +20757,7 @@ not one of @command{awk}'s predefined variables, such as @code{FS}. It is also important that @emph{all} variables in library functions that do not need to save state are, in fact, declared local.@footnote{@command{gawk}'s @option{--dump-variables} command-line -option is useful for verifying this.} If this is not done, the variable +option is useful for verifying this.} If this is not done, the variables could accidentally be used in the user's program, leading to bugs that are very difficult to track down: @@ -21027,13 +20914,9 @@ be tested with @command{gawk} and the results compared to the built-in @node Assert Function @subsection Assertions -@c STARTOFRANGE asse @cindex assertions -@c STARTOFRANGE assef @cindex @code{assert()} function (C library) -@c STARTOFRANGE libfass @cindex libraries of @command{awk} functions, assertions -@c STARTOFRANGE flibass @cindex functions, library, assertions @cindex @command{awk} programs, lengthy, assertions When writing large programs, it is often useful to know @@ -21072,7 +20955,7 @@ Following is the function: @example @c file eg/lib/assert.awk -# assert --- assert that a condition is true. Otherwise exit. +# assert --- assert that a condition is true. Otherwise, exit. @c endfile @ignore @@ -21108,7 +20991,7 @@ is false, it prints a message to standard error, using the @code{string} parameter to describe the failed condition. It then sets the variable @code{_assert_exit} to one and executes the @code{exit} statement. The @code{exit} statement jumps to the @code{END} rule. If the @code{END} -rules finds @code{_assert_exit} to be true, it exits immediately. +rule finds @code{_assert_exit} to be true, it exits immediately. The purpose of the test in the @code{END} rule is to keep any other @code{END} rules from running. When an assertion fails, the @@ -21149,10 +21032,6 @@ most likely causing the program to hang as it waits for input. There is a simple workaround to this: make sure that such a @code{BEGIN} rule always ends with an @code{exit} statement. -@c ENDOFRANGE asse -@c ENDOFRANGE assef -@c ENDOFRANGE flibass -@c ENDOFRANGE libfass @node Round Function @subsection Rounding Numbers @@ -21404,7 +21283,7 @@ all the strings in an array into one long string. The following function, the application programs (@pxref{Sample Programs}). -Good function design is important; this function needs to be general but it +Good function design is important; this function needs to be general, but it should also have a reasonable default behavior. It is called with an array as well as the beginning and ending indices of the elements in the array to be merged. This assumes that the array indices are numeric---a reasonable @@ -21552,7 +21431,7 @@ allowed the user to supply an optional timestamp value to use instead of the current time. @node Readfile Function -@subsection Reading a Whole File At Once +@subsection Reading a Whole File at Once Often, it is convenient to have the entire contents of a file available in memory as a single string. A straightforward but naive way to @@ -21609,13 +21488,13 @@ function readfile(file, tmp, save_rs) It works by setting @code{RS} to @samp{^$}, a regular expression that will never match if the file has contents. @command{gawk} reads data from -the file into @code{tmp} attempting to match @code{RS}. The match fails +the file into @code{tmp}, attempting to match @code{RS}. The match fails after each read, but fails quickly, such that @command{gawk} fills @code{tmp} with the entire contents of the file. (@DBXREF{Records} for information on @code{RT} and @code{RS}.) In the case that @code{file} is empty, the return value is the null -string. Thus calling code may use something like: +string. Thus, calling code may use something like: @example contents = readfile("/some/path") @@ -21626,7 +21505,7 @@ if (length(contents) == 0) This tests the result to see if it is empty or not. An equivalent test would be @samp{contents == ""}. -@xref{Extension Sample Readfile}, for an extension function that +@DBXREF{Extension Sample Readfile} for an extension function that also reads an entire file into memory. @node Shell Quoting @@ -21710,11 +21589,8 @@ function shell_quote(s, # parameter @node Data File Management @section @value{DDF} Management -@c STARTOFRANGE dataf @cindex files, managing -@c STARTOFRANGE libfdataf @cindex libraries of @command{awk} functions, managing, data files -@c STARTOFRANGE flibdataf @cindex functions, library, managing data files This @value{SECTION} presents functions that are useful for managing command-line @value{DF}s. @@ -21736,8 +21612,8 @@ The @code{BEGIN} and @code{END} rules are each executed exactly once, at the beginning and end of your @command{awk} program, respectively (@pxref{BEGIN/END}). We (the @command{gawk} authors) once had a user who mistakenly thought that the -@code{BEGIN} rule is executed at the beginning of each @value{DF} and the -@code{END} rule is executed at the end of each @value{DF}. +@code{BEGIN} rules were executed at the beginning of each @value{DF} and the +@code{END} rules were executed at the end of each @value{DF}. When informed that this was not the case, the user requested that we add new special @@ -21777,7 +21653,7 @@ END @{ endfile(FILENAME) @} This file must be loaded before the user's ``main'' program, so that the rule it supplies is executed first. -This rule relies on @command{awk}'s @code{FILENAME} variable that +This rule relies on @command{awk}'s @code{FILENAME} variable, which automatically changes for each new @value{DF}. The current @value{FN} is saved in a private variable, @code{_oldfilename}. If @code{FILENAME} does not equal @code{_oldfilename}, then a new @value{DF} is being processed and @@ -21793,7 +21669,7 @@ first @value{DF}. The program also supplies an @code{END} rule to do the final processing for the last file. Because this @code{END} rule comes before any @code{END} rules supplied in the ``main'' program, @code{endfile()} is called first. Once -again the value of multiple @code{BEGIN} and @code{END} rules should be clear. +again, the value of multiple @code{BEGIN} and @code{END} rules should be clear. @cindex @code{beginfile()} user-defined function @cindex @code{endfile()} user-defined function @@ -21841,7 +21717,7 @@ how it simplifies writing the main program. You are probably wondering, if @code{beginfile()} and @code{endfile()} functions can do the job, why does @command{gawk} have -@code{BEGINFILE} and @code{ENDFILE} patterns (@pxref{BEGINFILE/ENDFILE})? +@code{BEGINFILE} and @code{ENDFILE} patterns? Good question. Normally, if @command{awk} cannot open a file, this causes an immediate fatal error. In this case, there is no way for a @@ -21850,6 +21726,7 @@ calling it relies on the file being open and at the first record. Thus, the main reason for @code{BEGINFILE} is to give you a ``hook'' to catch files that cannot be processed. @code{ENDFILE} exists for symmetry, and because it provides an easy way to do per-file cleanup processing. +For more information, refer to @ref{BEGINFILE/ENDFILE}. @docbook </sidebar> @@ -21864,7 +21741,7 @@ and because it provides an easy way to do per-file cleanup processing. You are probably wondering, if @code{beginfile()} and @code{endfile()} functions can do the job, why does @command{gawk} have -@code{BEGINFILE} and @code{ENDFILE} patterns (@pxref{BEGINFILE/ENDFILE})? +@code{BEGINFILE} and @code{ENDFILE} patterns? Good question. Normally, if @command{awk} cannot open a file, this causes an immediate fatal error. In this case, there is no way for a @@ -21873,6 +21750,7 @@ calling it relies on the file being open and at the first record. Thus, the main reason for @code{BEGINFILE} is to give you a ``hook'' to catch files that cannot be processed. @code{ENDFILE} exists for symmetry, and because it provides an easy way to do per-file cleanup processing. +For more information, refer to @ref{BEGINFILE/ENDFILE}. @end cartouche @end ifnotdocbook @@ -21880,7 +21758,7 @@ and because it provides an easy way to do per-file cleanup processing. @subsection Rereading the Current File @cindex files, reading -Another request for a new built-in function was for a @code{rewind()} +Another request for a new built-in function was for a function that would make it possible to reread the current file. The requesting user didn't want to have to use @code{getline} (@pxref{Getline}) @@ -21889,7 +21767,7 @@ inside a loop. However, as long as you are not in the @code{END} rule, it is quite easy to arrange to immediately close the current input file and then start over with it from the top. -For lack of a better name, we'll call it @code{rewind()}: +For lack of a better name, we'll call the function @code{rewind()}: @cindex @code{rewind()} user-defined function @example @@ -21982,16 +21860,16 @@ See also @ref{ARGC and ARGV}. Because @command{awk} variable names only allow the English letters, the regular expression check purposely does not use character classes such as @samp{[:alpha:]} and @samp{[:alnum:]} -(@pxref{Bracket Expressions}) +(@pxref{Bracket Expressions}). @node Empty Files -@subsection Checking for Zero-length Files +@subsection Checking for Zero-Length Files All known @command{awk} implementations silently skip over zero-length files. This is a by-product of @command{awk}'s implicit read-a-record-and-match-against-the-rules loop: when @command{awk} tries to read a record from an empty file, it immediately receives an -end of file indication, closes the file, and proceeds on to the next +end-of-file indication, closes the file, and proceeds on to the next command-line @value{DF}, @emph{without} executing any user-level @command{awk} program code. @@ -22056,7 +21934,7 @@ Occasionally, you might not want @command{awk} to process command-line variable assignments (@pxref{Assignment Options}). In particular, if you have a @value{FN} that contains an @samp{=} character, -@command{awk} treats the @value{FN} as an assignment, and does not process it. +@command{awk} treats the @value{FN} as an assignment and does not process it. Some users have suggested an additional command-line option for @command{gawk} to disable command-line assignments. However, some simple programming with @@ -22106,22 +21984,14 @@ The use of @code{No_command_assign} allows you to disable command-line assignments at invocation time, by giving the variable a true value. When not set, it is initially zero (i.e., false), so the command-line arguments are left alone. -@c ENDOFRANGE dataf -@c ENDOFRANGE flibdataf -@c ENDOFRANGE libfdataf @node Getopt Function @section Processing Command-Line Options -@c STARTOFRANGE libfclo @cindex libraries of @command{awk} functions, command-line options -@c STARTOFRANGE flibclo @cindex functions, library, command-line options -@c STARTOFRANGE clop @cindex command-line options, processing -@c STARTOFRANGE oclp @cindex options, command-line, processing -@c STARTOFRANGE clibf @cindex functions, library, C library @cindex arguments, processing Most utilities on POSIX-compatible systems take options on @@ -22426,8 +22296,8 @@ BEGIN @{ @c endfile @end example -The rest of the @code{BEGIN} rule is a simple test program. Here is the -result of two sample runs of the test program: +The rest of the @code{BEGIN} rule is a simple test program. Here are the +results of two sample runs of the test program: @example $ @kbd{awk -f getopt.awk -v _getopt_test=1 -- -a -cbARG bax -x} @@ -22473,27 +22343,19 @@ further options Several of the sample programs presented in @ref{Sample Programs}, use @code{getopt()} to process their arguments. -@c ENDOFRANGE libfclo -@c ENDOFRANGE flibclo -@c ENDOFRANGE clop -@c ENDOFRANGE oclp @node Passwd Functions @section Reading the User Database -@c STARTOFRANGE libfudata @cindex libraries of @command{awk} functions, user database, reading -@c STARTOFRANGE flibudata @cindex functions, library, user database@comma{} reading -@c STARTOFRANGE udatar @cindex user database@comma{} reading -@c STARTOFRANGE dataur @cindex database, users@comma{} reading @cindex @code{PROCINFO} array The @code{PROCINFO} array (@pxref{Built-in Variables}) provides access to the current user's real and effective user and group ID -numbers, and if available, the user's supplementary group set. +numbers, and, if available, the user's supplementary group set. However, because these are numbers, they do not provide very useful information to the average user. There needs to be some way to find the user information associated with the user and group ID numbers. This @@ -22513,7 +22375,7 @@ kept. Instead, it provides the @code{<pwd.h>} header file and several C language subroutines for obtaining user information. The primary function is @code{getpwent()}, for ``get password entry.'' The ``password'' comes from the original user database file, -@file{/etc/passwd}, which stores user information, along with the +@file{/etc/passwd}, which stores user information along with the encrypted passwords (hence the name). @cindex @command{pwcat} program @@ -22612,7 +22474,7 @@ The user's encrypted password. This may not be available on some systems. @item User-ID The user's numeric user ID number. -(On some systems, it's a C @code{long}, and not an @code{int}. Thus +(On some systems, it's a C @code{long}, and not an @code{int}. Thus, we cast it to @code{long} for all cases.) @item Group-ID @@ -22739,7 +22601,7 @@ The code that checks for using @code{FPAT}, using @code{using_fpat} and @code{PROCINFO["FS"]}, is similar. The main part of the function uses a loop to read database lines, split -the line into fields, and then store the line into each array as necessary. +the lines into fields, and then store the lines into each array as necessary. When the loop is done, @code{@w{_pw_init()}} cleans up by closing the pipeline, setting @code{@w{_pw_inited}} to one, and restoring @code{FS} (and @code{FIELDWIDTHS} or @code{FPAT} @@ -22834,21 +22696,13 @@ and such a change would clutter up the code. The @command{id} program in @DBREF{Id Program} uses these functions. -@c ENDOFRANGE libfudata -@c ENDOFRANGE flibudata -@c ENDOFRANGE udatar -@c ENDOFRANGE dataur @node Group Functions @section Reading the Group Database -@c STARTOFRANGE libfgdata @cindex libraries of @command{awk} functions, group database, reading -@c STARTOFRANGE flibgdata @cindex functions, library, group database@comma{} reading -@c STARTOFRANGE gdatar @cindex group database, reading -@c STARTOFRANGE datagr @cindex database, group, reading @cindex @code{PROCINFO} array, and group membership @cindex @code{getgrent()} function (C library) @@ -22964,7 +22818,7 @@ it is usually empty or set to @samp{*}. @item Group ID Number The group's numeric group ID number; the association of name to number must be unique within the file. -(On some systems it's a C @code{long}, and not an @code{int}. Thus +(On some systems it's a C @code{long}, and not an @code{int}. Thus, we cast it to @code{long} for all cases.) @item Group Member List @@ -23078,32 +22932,32 @@ The @code{@w{_gr_init()}} function first saves @code{FS}, @code{$0}, and then sets @code{FS} and @code{RS} to the correct values for scanning the group information. It also takes care to note whether @code{FIELDWIDTHS} or @code{FPAT} -is being used, and to restore the appropriate field splitting mechanism. +is being used, and to restore the appropriate field-splitting mechanism. -The group information is stored is several associative arrays. +The group information is stored in several associative arrays. The arrays are indexed by group name (@code{@w{_gr_byname}}), by group ID number (@code{@w{_gr_bygid}}), and by position in the database (@code{@w{_gr_bycount}}). There is an additional array indexed by username (@code{@w{_gr_groupsbyuser}}), which is a space-separated list of groups to which each user belongs. -Unlike the user database, it is possible to have multiple records in the +Unlike in the user database, it is possible to have multiple records in the database for the same group. This is common when a group has a large number of members. A pair of such entries might look like the following: @example -tvpeople:*:101:johny,jay,arsenio +tvpeople:*:101:johnny,jay,arsenio tvpeople:*:101:david,conan,tom,joan @end example For this reason, @code{_gr_init()} looks to see if a group name or -group ID number is already seen. If it is, the usernames are -simply concatenated onto the previous list of users.@footnote{There is actually a +group ID number is already seen. If so, the usernames are +simply concatenated onto the previous list of users.@footnote{There is a subtle problem with the code just presented. Suppose that the first time there were no names. This code adds the names with a leading comma. It also doesn't check that there is a @code{$4}.} Finally, @code{_gr_init()} closes the pipeline to @command{grcat}, restores -@code{FS} (and @code{FIELDWIDTHS} or @code{FPAT} if necessary), @code{RS}, and @code{$0}, +@code{FS} (and @code{FIELDWIDTHS} or @code{FPAT}, if necessary), @code{RS}, and @code{$0}, initializes @code{_gr_count} to zero (it is used later), and makes @code{_gr_inited} nonzero. @@ -23171,7 +23025,6 @@ function getgrent() @} @c endfile @end example -@c ENDOFRANGE clibf @cindex @code{endgrent()} function (C library) The @code{endgrent()} function resets @code{_gr_count} to zero so that @code{getgrent()} can @@ -23204,12 +23057,12 @@ uses these functions. @DBREF{Arrays of Arrays} described how @command{gawk} provides arrays of arrays. In particular, any element of -an array may be either a scalar, or another array. The +an array may be either a scalar or another array. The @code{isarray()} function (@pxref{Type Functions}) lets you distinguish an array from a scalar. The following function, @code{walk_array()}, recursively traverses -an array, printing each element's indices and value. +an array, printing the element indices and values. You call it with the array and a string representing the name of the array: @@ -23260,10 +23113,6 @@ $ @kbd{gawk -f walk_array.awk} @print{} a[4][2] = 42 @end example -@c ENDOFRANGE libfgdata -@c ENDOFRANGE flibgdata -@c ENDOFRANGE gdatar -@c ENDOFRANGE libf @node Library Functions Summary @section Summary @@ -23285,24 +23134,24 @@ The functions presented here fit into the following categories: @c nested list @table @asis @item General problems -Number-to-string conversion, assertions, rounding, random number +Number-to-string conversion, testing assertions, rounding, random number generation, converting characters to numbers, joining strings, getting easily usable time-of-day information, and reading a whole file in -one shot. +one shot @item Managing @value{DF}s Noting @value{DF} boundaries, rereading the current file, checking for readable files, checking for zero-length files, and treating assignments -as @value{FN}s. +as @value{FN}s @item Processing command-line options -An @command{awk} version of the standard C @code{getopt()} function. +An @command{awk} version of the standard C @code{getopt()} function @item Reading the user and group databases -Two sets of routines that parallel the C library versions. +Two sets of routines that parallel the C library versions @item Traversing arrays of arrays -A simple function to traverse an array of arrays to any depth. +A simple function to traverse an array of arrays to any depth @end table @c end nested list @@ -23377,13 +23226,9 @@ output identical to that of the original version. @end enumerate @c EXCLUDE END -@c ENDOFRANGE flib -@c ENDOFRANGE fudlib -@c ENDOFRANGE datagr @node Sample Programs @chapter Practical @command{awk} Programs -@c STARTOFRANGE awkpex @cindex @command{awk} programs, examples of @c FULLXREF ON @@ -23401,10 +23246,10 @@ in this @value{CHAPTER}. The second presents @command{awk} versions of several common POSIX utilities. These are programs that you are hopefully already familiar with, -and therefore, whose problems are understood. +and therefore whose problems are understood. By reimplementing these programs in @command{awk}, you can focus on the @command{awk}-related aspects of solving -the programming problem. +the programming problems. The third is a grab bag of interesting programs. These solve a number of different data-manipulation and management @@ -23453,7 +23298,6 @@ cut.awk -- -c1-8 myfiles > results @node Clones @section Reinventing Wheels for Fun and Profit -@c STARTOFRANGE posimawk @cindex POSIX, programs@comma{} implementing in @command{awk} This @value{SECTION} presents a number of POSIX utilities implemented in @@ -23465,7 +23309,7 @@ It should be noted that these programs are not necessarily intended to replace the installed versions on your system. Nor may all of these programs be fully compliant with the most recent POSIX standard. This is not a problem; their -purpose is to illustrate @command{awk} language programming for ``real world'' +purpose is to illustrate @command{awk} language programming for ``real-world'' tasks. The programs are presented in alphabetical order. @@ -23484,11 +23328,8 @@ The programs are presented in alphabetical order. @subsection Cutting Out Fields and Columns @cindex @command{cut} utility -@c STARTOFRANGE cut @cindex @command{cut} utility -@c STARTOFRANGE ficut @cindex fields, cutting -@c STARTOFRANGE colcut @cindex columns, cutting The @command{cut} utility selects, or ``cuts,'' characters or fields from its standard input and sends them to its standard output. @@ -23497,7 +23338,7 @@ but you may supply a command-line option to change the field @dfn{delimiter} (i.e., the field-separator character). @command{cut}'s definition of fields is less general than @command{awk}'s. -A common use of @command{cut} might be to pull out just the login name of +A common use of @command{cut} might be to pull out just the login names of logged-on users from the output of @command{who}. For example, the following pipeline generates a sorted, unique list of the logged-on users: @@ -23796,21 +23637,14 @@ other @command{awk} implementations to use @code{substr()} it is also extremely painful. The @code{FIELDWIDTHS} variable supplies an elegant solution to the problem of picking the input line apart by characters. -@c ENDOFRANGE cut -@c ENDOFRANGE ficut -@c ENDOFRANGE colcut @node Egrep Program @subsection Searching for Regular Expressions in Files -@c STARTOFRANGE regexps @cindex regular expressions, searching for -@c STARTOFRANGE sfregexp @cindex searching, files for regular expressions -@c STARTOFRANGE fsregexp @cindex files, searching for regular expressions -@c STARTOFRANGE egrep @cindex @command{egrep} utility The @command{egrep} utility searches files for patterns. It uses regular expressions that are almost identical to those available in @command{awk} @@ -24013,7 +23847,7 @@ successful or unsuccessful match. If the line does not match, the @code{next} statement just moves on to the next record. A number of additional tests are made, but they are only done if we -are not counting lines. First, if the user only wants exit status +are not counting lines. First, if the user only wants the exit status (@code{no_print} is true), then it is enough to know that @emph{one} line in this file matched, and we can skip on to the next file with @code{nextfile}. Similarly, if we are only printing @value{FN}s, we can @@ -24054,7 +23888,7 @@ if necessary: @end example The @code{END} rule takes care of producing the correct exit status. If -there are no matches, the exit status is one; otherwise it is zero: +there are no matches, the exit status is one; otherwise, it is zero: @example @c file eg/prog/egrep.awk @@ -24078,17 +23912,12 @@ function usage() @c endfile @end example -@c ENDOFRANGE regexps -@c ENDOFRANGE sfregexp -@c ENDOFRANGE fsregexp -@c ENDOFRANGE egrep @node Id Program @subsection Printing Out User Information @cindex printing, user information @cindex users, information about, printing -@c STARTOFRANGE id @cindex @command{id} utility The @command{id} utility lists a user's real and effective user ID numbers, real and effective group ID numbers, and the user's group set, if any. @@ -24111,7 +23940,8 @@ Here is a simple version of @command{id} written in @command{awk}. It uses the user database library functions (@pxref{Passwd Functions}) and the group database library functions -(@pxref{Group Functions}): +(@pxref{Group Functions}) +from @ref{Library Functions}. The program is fairly straightforward. All the work is done in the @code{BEGIN} rule. The user and group ID numbers are obtained from @@ -24217,16 +24047,13 @@ code that is used repeatedly, making the whole program shorter and cleaner. In particular, moving the check for the empty string into this function saves several lines of code. -@c ENDOFRANGE id @node Split Program @subsection Splitting a Large File into Pieces @c FIXME: One day, update to current POSIX version of split -@c STARTOFRANGE filspl @cindex files, splitting -@c STARTOFRANGE split @cindex @code{split} utility The @command{split} program splits large text files into smaller pieces. Usage is as follows:@footnote{This is the traditional usage. The @@ -24241,8 +24068,8 @@ By default, the output files are named @file{xaa}, @file{xab}, and so on. Each file has 1,000 lines in it, with the likely exception of the last file. To change the number of lines in each file, supply a number on the command line -preceded with a minus (e.g., @samp{-500} for files with 500 lines in them -instead of 1,000). To change the name of the output files to something like +preceded with a minus sign (e.g., @samp{-500} for files with 500 lines in them +instead of 1,000). To change the names of the output files to something like @file{myfileaa}, @file{myfileab}, and so on, supply an additional argument that specifies the @value{FN} prefix. @@ -24361,15 +24188,12 @@ You might want to consider how to eliminate the use of way as to solve the EBCDIC issue as well. @end ifset -@c ENDOFRANGE filspl -@c ENDOFRANGE split @node Tee Program @subsection Duplicating Output into Multiple Files @cindex files, multiple@comma{} duplicating output into @cindex output, duplicating into files -@c STARTOFRANGE tee @cindex @code{tee} utility The @code{tee} program is known as a ``pipe fitting.'' @code{tee} copies its standard input to its standard output and also duplicates it to the @@ -24482,18 +24306,14 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE tee @node Uniq Program @subsection Printing Nonduplicated Lines of Text @c FIXME: One day, update to current POSIX version of uniq -@c STARTOFRANGE prunt @cindex printing, unduplicated lines of text -@c STARTOFRANGE tpul @cindex text@comma{} printing, unduplicated lines of -@c STARTOFRANGE uniq @cindex @command{uniq} utility The @command{uniq} utility reads sorted lines of data on its standard input, and by default removes duplicate lines. In other words, it only @@ -24762,26 +24582,17 @@ suggestion. @end ifset -@c ENDOFRANGE prunt -@c ENDOFRANGE tpul -@c ENDOFRANGE uniq @node Wc Program @subsection Counting Things @c FIXME: One day, update to current POSIX version of wc -@c STARTOFRANGE count @cindex counting -@c STARTOFRANGE infco @cindex input files, counting elements in -@c STARTOFRANGE woco @cindex words, counting -@c STARTOFRANGE chco @cindex characters, counting -@c STARTOFRANGE lico @cindex lines, counting -@c STARTOFRANGE wc @cindex @command{wc} utility The @command{wc} (word count) utility counts lines, words, and characters in one or more input files. Its usage is as follows: @@ -24951,13 +24762,6 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE count -@c ENDOFRANGE infco -@c ENDOFRANGE lico -@c ENDOFRANGE woco -@c ENDOFRANGE chco -@c ENDOFRANGE wc -@c ENDOFRANGE posimawk @node Miscellaneous Programs @section A Grab Bag of @command{awk} Programs @@ -25088,9 +24892,7 @@ Aharon Robbins <arnold@skeeve.com> wrote: @author Erik Quanstrom @end quotation -@c STARTOFRANGE tialarm @cindex time, alarm clock example program -@c STARTOFRANGE alaex @cindex alarm clock example program The following program is a simple ``alarm clock'' program. You give it a time of day and an optional message. At the specified time, @@ -25106,7 +24908,7 @@ checking and setting of defaults: the delay, the count, and the message to print. If the user supplied a message without the ASCII BEL character (known as the ``alert'' character, @code{"\a"}), then it is added to the message. (On many systems, printing the ASCII BEL generates an -audible alert. Thus when the alarm goes off, the system calls attention +audible alert. Thus, when the alarm goes off, the system calls attention to itself in case the user is not looking at the computer.) Just for a change, this program uses a @code{switch} statement (@pxref{Switch Statement}), but the processing could be done with a series of @@ -25242,15 +25044,11 @@ seconds are necessary: @} @c endfile @end example -@c ENDOFRANGE tialarm -@c ENDOFRANGE alaex @node Translate Program @subsection Transliterating Characters -@c STARTOFRANGE chtra @cindex characters, transliterating -@c STARTOFRANGE tr @cindex @command{tr} utility The system @command{tr} utility transliterates characters. For example, it is often used to map uppercase letters into lowercase for further processing: @@ -25279,7 +25077,7 @@ to @command{gawk}. @c at least theoretically The following program was written to prove that character transliteration could be done with a user-level -function. This program is not as complete as the system @command{tr} utility +function. This program is not as complete as the system @command{tr} utility, but it does most of the job. The @command{translate} program was written long before @command{gawk} @@ -25291,13 +25089,13 @@ takes three arguments: @table @code @item from -A list of characters from which to translate. +A list of characters from which to translate @item to -A list of characters to which to translate. +A list of characters to which to translate @item target -The string on which to do the translation. +The string on which to do the translation @end table Associative arrays make the translation part fairly easy. @code{t_ar} holds @@ -25306,7 +25104,7 @@ loop goes through @code{from}, one character at a time. For each character in @code{from}, if the character appears in @code{target}, it is replaced with the corresponding @code{to} character. -The @code{translate()} function calls @code{stranslate()} using @code{$0} +The @code{translate()} function calls @code{stranslate()}, using @code{$0} as the target. The main program sets two global variables, @code{FROM} and @code{TO}, from the command line, and then changes @code{ARGV} so that @command{awk} reads from the standard input. @@ -25328,7 +25126,7 @@ Finally, the processing rule simply calls @code{translate()} for each record: @c endfile @end ignore @c file eg/prog/translate.awk -# Bugs: does not handle things like: tr A-Z a-z, it has +# Bugs: does not handle things like tr A-Z a-z; it has # to be spelled out. However, if `to' is shorter than `from', # the last character in `to' is used for the rest of `from'. @@ -25398,17 +25196,13 @@ such as @samp{a-z}, as allowed by the @command{tr} utility. Look at the code for @file{cut.awk} (@pxref{Cut Program}) for inspiration. -@c ENDOFRANGE chtra -@c ENDOFRANGE tr @node Labels Program @subsection Printing Mailing Labels -@c STARTOFRANGE prml @cindex printing, mailing labels -@c STARTOFRANGE mlprint @cindex mailing labels@comma{} printing -Here is a ``real world''@footnote{``Real world'' is defined as +Here is a ``real-world''@footnote{``Real world'' is defined as ``a program actually used to get something done.''} program. This script reads lists of names and @@ -25417,7 +25211,7 @@ on it, two across and 10 down. The addresses are guaranteed to be no more than five lines of data. Each address is separated from the next by a blank line. -The basic idea is to read 20 labels worth of data. Each line of each label +The basic idea is to read 20 labels' worth of data. Each line of each label is stored in the @code{line} array. The single rule takes care of filling the @code{line} array and printing the page when 20 labels have been read. @@ -25440,12 +25234,12 @@ of lines on the page Most of the work is done in the @code{printpage()} function. The label lines are stored sequentially in the @code{line} array. But they -have to print horizontally; @code{line[1]} next to @code{line[6]}, +have to print horizontally: @code{line[1]} next to @code{line[6]}, @code{line[2]} next to @code{line[7]}, and so on. Two loops accomplish this. The outer loop, controlled by @code{i}, steps through every 10 lines of data; this is each row of labels. The inner loop, controlled by @code{j}, goes through the lines within the row. -As @code{j} goes from 0 to 4, @samp{i+j} is the @code{j}-th line in +As @code{j} goes from 0 to 4, @samp{i+j} is the @code{j}th line in the row, and @samp{i+j+5} is the entry next to it. The output ends up looking something like this: @@ -25470,7 +25264,6 @@ that there are two blank lines at the top and two blank lines at the bottom. The @code{END} rule arranges to flush the final page of labels; there may not have been an even multiple of 20 labels in the data: -@c STARTOFRANGE labels @cindex @code{labels.awk} program @example @c file eg/prog/labels.awk @@ -25535,14 +25328,10 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE prml -@c ENDOFRANGE mlprint -@c ENDOFRANGE labels @node Word Sorting @subsection Generating Word-Usage Counts -@c STARTOFRANGE worus @cindex words, usage counts@comma{} generating When working with large amounts of text, it can be interesting to know @@ -25568,8 +25357,8 @@ END @{ @} @end example -The program relies on @command{awk}'s default field splitting -mechanism to break each line up into ``words,'' and uses an +The program relies on @command{awk}'s default field-splitting +mechanism to break each line up into ``words'' and uses an associative array named @code{freq}, indexed by each word, to count the number of times the word occurs. In the @code{END} rule, it prints the counts. @@ -25604,7 +25393,6 @@ to remove punctuation characters. Finally, we solve the third problem by using the system @command{sort} utility to process the output of the @command{awk} script. Here is the new version of the program: -@c STARTOFRANGE wordfreq @cindex @code{wordfreq.awk} program @example @c file eg/prog/wordfreq.awk @@ -25669,16 +25457,13 @@ This way of sorting must be used on systems that do not have true pipes at the command-line (or batch-file) level. See the general operating system documentation for more information on how to use the @command{sort} program. -@c ENDOFRANGE worus -@c ENDOFRANGE wordfreq @node History Sorting @subsection Removing Duplicates from Unsorted Text -@c STARTOFRANGE lidu @cindex lines, duplicate@comma{} removing The @command{uniq} program -(@pxref{Uniq Program}), +(@pxref{Uniq Program}) removes duplicate lines from @emph{sorted} data. Suppose, however, you need to remove duplicate lines from a @value{DF} but @@ -25700,7 +25485,6 @@ Each element of @code{lines} is a unique command, and the indices of The @code{END} rule simply prints out the lines, in order: @cindex Rakitzis, Byron -@c STARTOFRANGE histsort @cindex @code{histsort.awk} program @example @c file eg/prog/histsort.awk @@ -25743,15 +25527,11 @@ print data[lines[i]], lines[i] @noindent This works because @code{data[$0]} is incremented each time a line is seen. -@c ENDOFRANGE lidu -@c ENDOFRANGE histsort @node Extract Program @subsection Extracting Programs from Texinfo Source Files -@c STARTOFRANGE texse @cindex Texinfo, extracting programs from source files -@c STARTOFRANGE fitex @cindex files, Texinfo@comma{} extracting programs from @ifnotinfo Both this chapter and the previous chapter @@ -25770,7 +25550,7 @@ Texinfo input file into separate files. @cindex Texinfo This @value{DOCUMENT} is written in @uref{http://www.gnu.org/software/texinfo/, Texinfo}, -the GNU project's document formatting language. +the GNU Project's document formatting language. A single Texinfo source file can be used to produce both printed documentation, with @TeX{}, and online documentation. @ifnotinfo @@ -25829,7 +25609,7 @@ The Texinfo file looks something like this: @example @dots{} -This program has a @@code@{BEGIN@} rule, +This program has a @@code@{BEGIN@} rule that prints a nice message: @@example @@ -25855,11 +25635,10 @@ The first rule handles calling @code{system()}, checking that a command is given (@code{NF} is at least three) and also checking that the command exits with a zero exit status, signifying OK: -@c STARTOFRANGE extract @cindex @code{extract.awk} program @example @c file eg/prog/extract.awk -# extract.awk --- extract files and run programs from texinfo files +# extract.awk --- extract files and run programs from Texinfo files @c endfile @ignore @c file eg/prog/extract.awk @@ -25900,12 +25679,12 @@ The second rule handles moving data into files. It verifies that a @value{FN} is given in the directive. If the file named is not the current file, then the current file is closed. Keeping the current file open until a new file is encountered allows the use of the @samp{>} -redirection for printing the contents, keeping open file management +redirection for printing the contents, keeping open-file management simple. The @code{for} loop does the work. It reads lines using @code{getline} (@pxref{Getline}). -For an unexpected end of file, it calls the @code{@w{unexpected_eof()}} +For an unexpected end-of-file, it calls the @code{@w{unexpected_eof()}} function. If the line is an ``endfile'' line, then it breaks out of the loop. If the line is an @samp{@@group} or @samp{@@end group} line, then it @@ -26001,16 +25780,13 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE texse -@c ENDOFRANGE fitex -@c ENDOFRANGE extract @node Simple Sed @subsection A Simple Stream Editor @cindex @command{sed} utility @cindex stream editors -The @command{sed} utility is a stream editor, a program that reads a +The @command{sed} utility is a @dfn{stream editor}, a program that reads a stream of data, makes changes to it, and passes it on. It is often used to make global changes to a large file or to a stream of data generated by a pipeline of commands. @@ -26033,7 +25809,6 @@ additional arguments are treated as @value{DF} names to process. If none are provided, the standard input is used: @cindex Brennan, Michael -@c STARTOFRANGE awksed @cindex @command{awksed.awk} program @c @cindex simple stream editor @c @cindex stream editor, simple @@ -26110,14 +25885,11 @@ The @code{usage()} function prints an error message and exits. Finally, the single rule handles the printing scheme outlined earlier, using @code{print} or @code{printf} as appropriate, depending upon the value of @code{RT}. -@c ENDOFRANGE awksed @node Igawk Program @subsection An Easy Way to Use Library Functions -@c STARTOFRANGE libfex @cindex libraries of @command{awk} functions, example program for using -@c STARTOFRANGE flibex @cindex functions, library, example program for using In @ref{Include Files}, we saw how @command{gawk} provides a built-in file-inclusion capability. However, this is a @command{gawk} extension. @@ -26159,7 +25931,7 @@ includes don't accidentally include a library function twice. @command{igawk} should behave just like @command{gawk} externally. This means it should accept all of @command{gawk}'s command-line arguments, including the ability to have multiple source files specified via -@option{-f}, and the ability to mix command-line and library source files. +@option{-f} and the ability to mix command-line and library source files. The program is written using the POSIX Shell (@command{sh}) command language.@footnote{Fully explaining the @command{sh} language is beyond @@ -26198,7 +25970,7 @@ Run the expanded program with @command{gawk} and any other original command-line arguments that the user supplied (such as the @value{DF} names). @end enumerate -This program uses shell variables extensively: for storing command-line arguments, +This program uses shell variables extensively: for storing command-line arguments and the text of the @command{awk} program that will expand the user's program, for the user's original program, and for the expanded program. Doing so removes some potential problems that might arise were we to use temporary files instead, @@ -26256,7 +26028,6 @@ program. The program is as follows: -@c STARTOFRANGE igawk @cindex @code{igawk.sh} program @example @c file eg/prog/igawk.sh @@ -26516,22 +26287,7 @@ Save the results of this processing in the shell variable The last step is to call @command{gawk} with the expanded program, along with the original -options and command-line arguments that the user supplied. - -@c this causes more problems than it solves, so leave it out. -@ignore -The special file @file{/dev/null} is passed as a @value{DF} to @command{gawk} -to handle an interesting case. Suppose that the user's program only has -a @code{BEGIN} rule and there are no @value{DF}s to read. -The program should exit without reading any @value{DF}s. -However, suppose that an included library file defines an @code{END} -rule of its own. In this case, @command{gawk} will hang, reading standard -input. In order to avoid this, @file{/dev/null} is explicitly added to the -command line. Reading from @file{/dev/null} always returns an immediate -end of file indication. - -@c Hmm. Add /dev/null if $# is 0? Still messes up ARGV. Sigh. -@end ignore +options and command-line arguments that the user supplied: @example @c file eg/prog/igawk.sh @@ -26581,10 +26337,6 @@ features to a program; they can often be layered on top.@footnote{@command{gawk} does @code{@@include} processing itself in order to support the use of @command{awk} programs as Web CGI scripts.} -@c ENDOFRANGE libfex -@c ENDOFRANGE flibex -@c ENDOFRANGE awkpex -@c ENDOFRANGE igawk @node Anagram Program @subsection Finding Anagrams from a Dictionary @@ -26601,19 +26353,18 @@ the same letters Column 2, Problem C, of Jon Bentley's @cite{Programming Pearls}, Second Edition, presents an elegant algorithm. The idea is to give words that are anagrams a common signature, sort all the words together by their -signature, and then print them. Dr.@: Bentley observes that taking the -letters in each word and sorting them produces that common signature. +signatures, and then print them. Dr.@: Bentley observes that taking the +letters in each word and sorting them produces those common signatures. The following program uses arrays of arrays to bring together words with the same signature and array sorting to print the words in sorted order: -@c STARTOFRANGE anagram @cindex @code{anagram.awk} program @example @c file eg/prog/anagram.awk -# anagram.awk --- An implementation of the anagram finding algorithm -# from Jon Bentley's "Programming Pearls", 2nd edition. +# anagram.awk --- An implementation of the anagram-finding algorithm +# from Jon Bentley's "Programming Pearls," 2nd edition. # Addison Wesley, 2000, ISBN 0-201-65788-0. # Column 2, Problem C, section 2.8, pp 18-20. @c endfile @@ -26661,7 +26412,7 @@ sorts the letters, and then joins them back together: @example @c file eg/prog/anagram.awk -# word2key --- split word apart into letters, sort, joining back together +# word2key --- split word apart into letters, sort, and join back together function word2key(word, a, i, n, result) @{ @@ -26717,7 +26468,6 @@ babery yabber @dots{} @end example -@c ENDOFRANGE anagram @node Signature Program @subsection And Now for Something Completely Different @@ -26857,12 +26607,13 @@ characters. The ability to use @code{split()} with the empty string as the separator can considerably simplify such tasks. @item -The library functions from @ref{Library Functions}, proved their -usefulness for a number of real (if small) programs. +The examples here demonstrate the usefulness of the library +functions from @DBREF{Library Functions} +for a number of real (if small) programs. @item Besides reinventing POSIX wheels, other programs solved a selection of -interesting problems, such as finding duplicates words in text, printing +interesting problems, such as finding duplicate words in text, printing mailing labels, and finding anagrams. @end itemize @@ -27037,9 +26788,7 @@ It contains the following chapters: @node Advanced Features @chapter Advanced Features of @command{gawk} -@c STARTOFRANGE gawadv @cindex @command{gawk}, features, advanced -@c STARTOFRANGE advgaw @cindex advanced features, @command{gawk} @ignore Contributed by: Peter Langston <pud!psl@bellcore.bellcore.com> @@ -27060,18 +26809,18 @@ a violent psychopath who knows where you live.} This @value{CHAPTER} discusses advanced features in @command{gawk}. It's a bit of a ``grab bag'' of items that are otherwise unrelated to each other. -First, a command-line option allows @command{gawk} to recognize +First, we look at a command-line option that allows @command{gawk} to recognize nondecimal numbers in input data, not just in @command{awk} programs. Then, @command{gawk}'s special features for sorting arrays are presented. Next, two-way I/O, discussed briefly in earlier parts of this @value{DOCUMENT}, is described in full detail, along with the basics -of TCP/IP networking. Finally, @command{gawk} +of TCP/IP networking. Finally, we see how @command{gawk} can @dfn{profile} an @command{awk} program, making it possible to tune it for performance. @c FULLXREF ON -A number of advanced features require separate @value{CHAPTER}s of their +Additional advanced features are discussed in separate @value{CHAPTER}s of their own: @itemize @value{BULLET} @@ -27165,7 +26914,8 @@ This option may disappear in a future version of @command{gawk}. @node Array Sorting @section Controlling Array Traversal and Array Sorting -@command{gawk} lets you control the order in which a @samp{for (i in array)} +@command{gawk} lets you control the order in which a +@samp{for (@var{indx} in @var{array})} loop traverses an array. In addition, two built-in functions, @code{asort()} and @code{asorti()}, @@ -27181,7 +26931,7 @@ to order the elements during sorting. @node Controlling Array Traversal @subsection Controlling Array Traversal -By default, the order in which a @samp{for (i in array)} loop +By default, the order in which a @samp{for (@var{indx} in @var{array})} loop scans an array is not defined; it is generally based upon the internal implementation of arrays inside @command{awk}. @@ -27210,23 +26960,23 @@ function comp_func(i1, v1, i2, v2) @} @end example -Here, @var{i1} and @var{i2} are the indices, and @var{v1} and @var{v2} +Here, @code{i1} and @code{i2} are the indices, and @code{v1} and @code{v2} are the corresponding values of the two elements being compared. -Either @var{v1} or @var{v2}, or both, can be arrays if the array being +Either @code{v1} or @code{v2}, or both, can be arrays if the array being traversed contains subarrays as values. (@DBXREF{Arrays of Arrays} for more information about subarrays.) The three possible return values are interpreted as follows: @table @code @item comp_func(i1, v1, i2, v2) < 0 -Index @var{i1} comes before index @var{i2} during loop traversal. +Index @code{i1} comes before index @code{i2} during loop traversal. @item comp_func(i1, v1, i2, v2) == 0 -Indices @var{i1} and @var{i2} -come together but the relative order with respect to each other is undefined. +Indices @code{i1} and @code{i2} +come together, but the relative order with respect to each other is undefined. @item comp_func(i1, v1, i2, v2) > 0 -Index @var{i1} comes after index @var{i2} during loop traversal. +Index @code{i1} comes after index @code{i2} during loop traversal. @end table Our first comparison function can be used to scan an array in @@ -27387,7 +27137,7 @@ As already mentioned, the order of the indices is arbitrary if two elements compare equal. This is usually not a problem, but letting the tied elements come out in arbitrary order can be an issue, especially when comparing item values. The partial ordering of the equal elements -may change the next time the array is traversed, if other elements are added or +may change the next time the array is traversed, if other elements are added to or removed from the array. One way to resolve ties when comparing elements with otherwise equal values is to include the indices in the comparison rules. Note that doing this may make the loop traversal less efficient, @@ -27430,7 +27180,7 @@ equivalent or distinct. Another point to keep in mind is that in the case of subarrays, the element values can themselves be arrays; a production comparison function should use the @code{isarray()} function -(@pxref{Type Functions}), +(@pxref{Type Functions}) to check for this, and choose a defined sorting order for subarrays. All sorting based on @code{PROCINFO["sorted_in"]} @@ -27438,7 +27188,7 @@ is disabled in POSIX mode, because the @code{PROCINFO} array is not special in that case. As a side note, sorting the array indices before traversing -the array has been reported to add 15% to 20% overhead to the +the array has been reported to add a 15% to 20% overhead to the execution time of @command{awk} programs. For this reason, sorted array traversal is not the default. @@ -27497,7 +27247,7 @@ However, the @code{source} array is not affected. Often, what's needed is to sort on the values of the @emph{indices} instead of the values of the elements. To do that, use the @code{asorti()} function. The interface and behavior are identical to -that of @code{asort()}, except that the index values are used for sorting, +that of @code{asort()}, except that the index values are used for sorting and become the values of the result array: @example @@ -27532,8 +27282,8 @@ it chooses}, taking into account just the indices, just the values, or both. This is extremely powerful. Once the array is sorted, @code{asort()} takes the @emph{values} in -their final order, and uses them to fill in the result array, whereas -@code{asorti()} takes the @emph{indices} in their final order, and uses +their final order and uses them to fill in the result array, whereas +@code{asorti()} takes the @emph{indices} in their final order and uses them to fill in the result array. @cindex reference counting, sorting arrays @@ -27749,7 +27499,6 @@ using regular pipes. @section Using @command{gawk} for Network Programming @cindex advanced features, network programming @cindex networks, programming -@c STARTOFRANGE tcpip @cindex TCP/IP @cindex @code{/inet/@dots{}} special files (@command{gawk}) @cindex files, @code{/inet/@dots{}} (@command{gawk}) @@ -27831,7 +27580,7 @@ service name. @cindex @command{gawk}, @code{ERRNO} variable in @cindex @code{ERRNO} variable @quotation NOTE -Failure in opening a two-way socket will result in a non-fatal error +Failure in opening a two-way socket will result in a nonfatal error being returned to the calling code. The value of @code{ERRNO} indicates the error (@pxref{Auto-set}). @end quotation @@ -27848,31 +27597,28 @@ BEGIN @{ @end example This program reads the current date and time from the local system's -TCP @samp{daytime} server. +TCP @code{daytime} server. It then prints the results and closes the connection. Because this topic is extensive, the use of @command{gawk} for TCP/IP programming is documented separately. @ifinfo See -@inforef{Top, , General Introduction, gawkinet, TCP/IP Internetworking with @command{gawk}}, +@inforef{Top, , General Introduction, gawkinet, @value{GAWKINETTITLE}}, @end ifinfo @ifnotinfo See @uref{http://www.gnu.org/software/gawk/manual/gawkinet/, -@cite{TCP/IP Internetworking with @command{gawk}}}, +@cite{@value{GAWKINETTITLE}}}, which comes as part of the @command{gawk} distribution, @end ifnotinfo for a much more complete introduction and discussion, as well as extensive examples. -@c ENDOFRANGE tcpip @node Profiling @section Profiling Your @command{awk} Programs -@c STARTOFRANGE awkp @cindex @command{awk} programs, profiling -@c STARTOFRANGE proawk @cindex profiling @command{awk} programs @cindex @code{awkprof.out} file @cindex files, @code{awkprof.out} @@ -27939,9 +27685,9 @@ junk @end example Here is the @file{awkprof.out} that results from running the -@command{gawk} profiler on this program and data. (This example also +@command{gawk} profiler on this program and data (this example also illustrates that @command{awk} programmers sometimes get up very early -in the morning to work.) +in the morning to work): @cindex @code{BEGIN} pattern, and profiling @cindex @code{END} pattern, and profiling @@ -28001,8 +27747,8 @@ They are as follows: @item The program is printed in the order @code{BEGIN} rules, @code{BEGINFILE} rules, -pattern/action rules, -@code{ENDFILE} rules, @code{END} rules and functions, listed +pattern--action rules, +@code{ENDFILE} rules, @code{END} rules, and functions, listed alphabetically. Multiple @code{BEGIN} and @code{END} rules retain their separate identities, as do @@ -28010,7 +27756,7 @@ multiple @code{BEGINFILE} and @code{ENDFILE} rules. @cindex patterns, counts, in a profile @item -Pattern-action rules have two counts. +Pattern--action rules have two counts. The first count, to the left of the rule, shows how many times the rule's pattern was @emph{tested}. The second count, to the right of the rule's opening left brace @@ -28077,13 +27823,13 @@ the target of a redirection isn't a scalar, it gets parenthesized. @command{gawk} supplies leading comments in front of the @code{BEGIN} and @code{END} rules, the @code{BEGINFILE} and @code{ENDFILE} rules, -the pattern/action rules, and the functions. +the pattern--action rules, and the functions. @end itemize The profiled version of your program may not look exactly like what you typed when you wrote it. This is because @command{gawk} creates the -profiled version by ``pretty printing'' its internal representation of +profiled version by ``pretty-printing'' its internal representation of the program. The advantage to this is that @command{gawk} can produce a standard representation. Also, things such as: @@ -28166,16 +27912,16 @@ If you use the @code{HUP} signal instead of the @code{USR1} signal, @cindex @code{SIGQUIT} signal (MS-Windows) @cindex signals, @code{QUIT}/@code{SIGQUIT} (MS-Windows) When @command{gawk} runs on MS-Windows systems, it uses the -@code{INT} and @code{QUIT} signals for producing the profile and, in +@code{INT} and @code{QUIT} signals for producing the profile, and in the case of the @code{INT} signal, @command{gawk} exits. This is because these systems don't support the @command{kill} command, so the only signals you can deliver to a program are those generated by the keyboard. The @code{INT} signal is generated by the -@kbd{Ctrl-@key{C}} or @kbd{Ctrl-@key{BREAK}} key, while the -@code{QUIT} signal is generated by the @kbd{Ctrl-@key{\}} key. +@kbd{Ctrl-c} or @kbd{Ctrl-BREAK} key, while the +@code{QUIT} signal is generated by the @kbd{Ctrl-\} key. Finally, @command{gawk} also accepts another option, @option{--pretty-print}. -When called this way, @command{gawk} ``pretty prints'' the program into +When called this way, @command{gawk} ``pretty-prints'' the program into @file{awkprof.out}, without any execution counts. @quotation NOTE @@ -28199,9 +27945,6 @@ that the profiling output does. This makes it easy to pretty-print your code once development is completed, and then use the result as the final version of your program. -@c ENDOFRANGE awkp -@c ENDOFRANGE proawk - @node Advanced Features Summary @section Summary @@ -28232,7 +27975,7 @@ optionally, close off one side of the two-way communications. @item By using special @value{FN}s with the @samp{|&} operator, you can open a -TCP/IP (or UDP/IP) connection to remote hosts in the Internet. @command{gawk} +TCP/IP (or UDP/IP) connection to remote hosts on the Internet. @command{gawk} supports both IPv4 and IPv6. @item @@ -28242,13 +27985,11 @@ you tune them more easily. Sending the @code{USR1} signal while profiling cause @command{gawk} to dump the profile and keep going, including a function call stack. @item -You can also just ``pretty print'' the program. This currently also runs +You can also just ``pretty-print'' the program. This currently also runs the program, but that will change in the next major release. @end itemize -@c ENDOFRANGE advgaw -@c ENDOFRANGE gawadv @node Internationalization @chapter Internationalization with @command{gawk} @@ -28261,7 +28002,6 @@ countries, they were able to sell more systems. As a result, internationalization and localization of programs and software systems became a common practice. -@c STARTOFRANGE inloc @cindex internationalization, localization @cindex @command{gawk}, internationalization and, See internationalization @cindex internationalization, localization, @command{gawk} and @@ -28294,7 +28034,7 @@ a requirement. @cindex localization @dfn{Internationalization} means writing (or modifying) a program once, in such a way that it can use multiple languages without requiring -further source-code changes. +further source code changes. @dfn{Localization} means providing the data necessary for an internationalized program to work in a particular language. Most typically, these terms refer to features such as the language @@ -28306,11 +28046,10 @@ monetary values are printed and read. @section GNU @command{gettext} @cindex internationalizing a program -@c STARTOFRANGE gettex @cindex @command{gettext} library @command{gawk} uses GNU @command{gettext} to provide its internationalization features. -The facilities in GNU @command{gettext} focus on messages; strings printed +The facilities in GNU @command{gettext} focus on messages: strings printed by a program, either directly or via formatting with @code{printf} or @code{sprintf()}.@footnote{For some operating systems, the @command{gawk} port doesn't support GNU @command{gettext}. @@ -28358,7 +28097,6 @@ lookup of the translations. @cindex @code{.po} files @cindex files, @code{.po} -@c STARTOFRANGE portobfi @cindex portable object files @cindex files, portable object @item @@ -28370,7 +28108,6 @@ For example, there might be a @file{fr.po} for a French translation. @cindex @code{.gmo} files @cindex files, @code{.gmo} @cindex message object files -@c STARTOFRANGE portmsgfi @cindex files, message object @item Each language's @file{.po} file is converted into a binary @@ -28498,14 +28235,12 @@ before or after the day in a date, local month abbreviations, and so on. @item LC_ALL All of the above. (Not too useful in the context of @command{gettext}.) @end table -@c ENDOFRANGE gettex @node Programmer i18n @section Internationalizing @command{awk} Programs -@c STARTOFRANGE inap @cindex @command{awk} programs, internationalizing -@command{gawk} provides the following variables and functions for +@command{gawk} provides the following variables for internationalization: @table @code @@ -28521,7 +28256,12 @@ value is @code{"messages"}. String constants marked with a leading underscore are candidates for translation at runtime. String constants without a leading underscore are not translated. +@end table + +@command{gawk} provides the following functions for +internationalization: +@table @code @cindexgawkfunc{dcgettext} @item @code{dcgettext(@var{string}} [@code{,} @var{domain} [@code{,} @var{category}]]@code{)} Return the translation of @var{string} in @@ -28578,15 +28318,7 @@ If @var{directory} is the null string (@code{""}), then given @var{domain}. @end table -To use these facilities in your @command{awk} program, follow the steps -outlined in -@ifnotinfo -the previous @value{SECTION}, -@end ifnotinfo -@ifinfo -@ref{Explaining gettext}, -@end ifinfo -like so: +To use these facilities in your @command{awk} program, follow these steps: @enumerate @cindex @code{BEGIN} pattern, @code{TEXTDOMAIN} variable and @@ -28735,8 +28467,6 @@ to provide you translations that you can also then distribute. @DBXREF{I18N Example} for the full list of steps to go through to create and test translations for @command{guide}. -@c ENDOFRANGE portobfi -@c ENDOFRANGE portmsgfi @node Printf Ordering @subsection Rearranging @code{printf} Arguments @@ -28871,7 +28601,7 @@ the null string (@code{""}) as its value, leaving the original string constant a the result. @item -By defining ``dummy'' functions to replace @code{dcgettext()}, @code{dcngettext()} +By defining ``dummy'' functions to replace @code{dcgettext()}, @code{dcngettext()}, and @code{bindtextdomain()}, the @command{awk} program can be made to run, but all the messages are output in the original language. For example: @@ -28912,7 +28642,6 @@ However, because the positional specifications are primarily for use in @emph{translated} format strings, and because non-GNU @command{awk}s never retrieve the translated string, this should not be a problem in practice. @end itemize -@c ENDOFRANGE inap @node I18N Example @section A Simple Internationalization Example @@ -29056,15 +28785,15 @@ using the GNU @command{gettext} package. (GNU @command{gettext} is described in complete detail in @ifinfo -@inforef{Top, , GNU @command{gettext} utilities, gettext, GNU gettext tools}.) +@inforef{Top, , GNU @command{gettext} utilities, gettext, GNU @command{gettext} utilities}.) @end ifinfo @ifnotinfo @uref{http://www.gnu.org/software/gettext/manual/, -@cite{GNU gettext tools}}.) +@cite{GNU @command{gettext} utilities}}.) @end ifnotinfo As of this writing, the latest version of GNU @command{gettext} is -@uref{ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.3.tar.gz, -@value{PVERSION} 0.19.3}. +@uref{ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.4.tar.gz, +@value{PVERSION} 0.19.4}. If a translation of @command{gawk}'s messages exists, then @command{gawk} produces usage messages, warnings, @@ -29076,7 +28805,7 @@ and fatal errors in the local language. @itemize @value{BULLET} @item Internationalization means writing a program such that it can use multiple -languages without requiring source-code changes. Localization means +languages without requiring source code changes. Localization means providing the data necessary for an internationalized program to work in a particular language. @@ -29093,9 +28822,9 @@ file, and the @file{.po} files are compiled into @file{.gmo} files for use at runtime. @item -You can use position specifications with @code{sprintf()} and +You can use positional specifications with @code{sprintf()} and @code{printf} to rearrange the placement of argument values in formatted -strings and output. This is useful for the translations of format +strings and output. This is useful for the translation of format control strings. @item @@ -29108,7 +28837,6 @@ a number of translations for its messages. @end itemize -@c ENDOFRANGE inloc @node Debugger @chapter Debugging @command{awk} Programs @@ -29152,8 +28880,7 @@ the discussion of debugging in @command{gawk}. @subsection Debugging in General (If you have used debuggers in other languages, you may want to skip -ahead to the next section on the specific features of the @command{gawk} -debugger.) +ahead to @ref{Awk Debugging}.) Of course, a debugging program cannot remove bugs for you, because it has no way of knowing what you or your users consider a ``bug'' versus a @@ -29244,10 +28971,10 @@ and usually find the errant code quite quickly. @end table @node Awk Debugging -@subsection Awk Debugging +@subsection @command{awk} Debugging Debugging an @command{awk} program has some specific aspects that are -not shared with other programming languages. +not shared with programs written in other languages. First of all, the fact that @command{awk} programs usually take input line by line from a file or files and operate on those lines using specific @@ -29263,7 +28990,7 @@ to look at the individual primitive instructions carried out by the higher-level @command{awk} commands. @node Sample Debugging Session -@section Sample Debugging Session +@section Sample @command{gawk} Debugging Session @cindex sample debugging session In order to illustrate the use of @command{gawk} as a debugger, let's look at a sample @@ -29282,8 +29009,8 @@ as our example. @cindex debugger, how to start Starting the debugger is almost exactly like running @command{gawk} normally, -except you have to pass an additional option @option{--debug}, or the -corresponding short option @option{-D}. The file(s) containing the +except you have to pass an additional option, @option{--debug}, or the +corresponding short option, @option{-D}. The file(s) containing the program and any supporting code are given on the command line as arguments to one or more @option{-f} options. (@command{gawk} is not designed to debug command-line programs, only programs contained in files.) @@ -29296,7 +29023,7 @@ $ @kbd{gawk -D -f getopt.awk -f join.awk -f uniq.awk -1 inputfile} @noindent where both @file{getopt.awk} and @file{uniq.awk} are in @env{$AWKPATH}. (Experienced users of GDB or similar debuggers should note that -this syntax is slightly different from what they are used to. +this syntax is slightly different from what you are used to. With the @command{gawk} debugger, you give the arguments for running the program in the command line to the debugger rather than as part of the @code{run} command at the debugger prompt.) @@ -29450,10 +29177,10 @@ gawk> @kbd{n} @end example This tells us that @command{gawk} is now ready to execute line 66, which -decides whether to give the lines the special ``field skipping'' treatment +decides whether to give the lines the special ``field-skipping'' treatment indicated by the @option{-1} command-line option. (Notice that we skipped -from where we were before at line 63 to here, because the condition in line 63 -@samp{if (fcount == 0 && charcount == 0)} was false.) +from where we were before, at line 63, to here, because the condition +in line 63, @samp{if (fcount == 0 && charcount == 0)}, was false.) Continuing to step, we now get to the splitting of the current and last records: @@ -29527,7 +29254,7 @@ gawk> @kbd{n} Well, here we are at our error (sorry to spoil the suspense). What we had in mind was to join the fields starting from the second one to make -the virtual record to compare, and if the first field was numbered zero, +the virtual record to compare, and if the first field were numbered zero, this would work. Let's look at what we've got: @example @@ -29536,7 +29263,7 @@ gawk> @kbd{p cline clast} @print{} clast = "awk is a wonderful program!" @end example -Hey, those look pretty familiar! They're just our original, unaltered, +Hey, those look pretty familiar! They're just our original, unaltered input records. A little thinking (the human brain is still the best debugging tool), and we realize that we were off by one! @@ -29586,11 +29313,11 @@ Miscellaneous @end itemize Each of these are discussed in the following subsections. -In the following descriptions, commands which may be abbreviated +In the following descriptions, commands that may be abbreviated show the abbreviation on a second description line. A debugger command name may also be truncated if that partial name is unambiguous. The debugger has the built-in capability to -automatically repeat the previous command just by hitting @key{Enter}. +automatically repeat the previous command just by hitting @kbd{Enter}. This works for the commands @code{list}, @code{next}, @code{nexti}, @code{step}, @code{stepi}, and @code{continue} executed without any argument. @@ -29640,7 +29367,7 @@ Set a breakpoint at entry to (the first instruction of) function @var{function}. @end table -Each breakpoint is assigned a number which can be used to delete it from +Each breakpoint is assigned a number that can be used to delete it from the breakpoint list using the @code{delete} command. With a breakpoint, you may also supply a condition. This is an @@ -29692,7 +29419,7 @@ watchpoint is made unconditional). @cindex breakpoint, delete by number @item @code{delete} [@var{n1 n2} @dots{}] [@var{n}--@var{m}] @itemx @code{d} [@var{n1 n2} @dots{}] [@var{n}--@var{m}] -Delete specified breakpoints or a range of breakpoints. Deletes +Delete specified breakpoints or a range of breakpoints. Delete all defined breakpoints if no argument is supplied. @cindex debugger commands, @code{disable} @@ -29701,7 +29428,7 @@ all defined breakpoints if no argument is supplied. @cindex breakpoint, how to disable or enable @item @code{disable} [@var{n1 n2} @dots{} | @var{n}--@var{m}] Disable specified breakpoints or a range of breakpoints. Without -any argument, disables all breakpoints. +any argument, disable all breakpoints. @cindex debugger commands, @code{e} (@code{enable}) @cindex debugger commands, @code{enable} @@ -29711,18 +29438,18 @@ any argument, disables all breakpoints. @item @code{enable} [@code{del} | @code{once}] [@var{n1 n2} @dots{}] [@var{n}--@var{m}] @itemx @code{e} [@code{del} | @code{once}] [@var{n1 n2} @dots{}] [@var{n}--@var{m}] Enable specified breakpoints or a range of breakpoints. Without -any argument, enables all breakpoints. -Optionally, you can specify how to enable the breakpoint: +any argument, enable all breakpoints. +Optionally, you can specify how to enable the breakpoints: @c nested table @table @code @item del -Enable the breakpoint(s) temporarily, then delete it when -the program stops at the breakpoint. +Enable the breakpoints temporarily, then delete each one when +the program stops at it. @item once -Enable the breakpoint(s) temporarily, then disable it when -the program stops at the breakpoint. +Enable the breakpoints temporarily, then disable each one when +the program stops at it. @end table @cindex debugger commands, @code{ignore} @@ -29790,7 +29517,7 @@ gawk> @item @code{continue} [@var{count}] @itemx @code{c} [@var{count}] Resume program execution. If continued from a breakpoint and @var{count} is -specified, ignores the breakpoint at that location the next @var{count} times +specified, ignore the breakpoint at that location the next @var{count} times before stopping. @cindex debugger commands, @code{finish} @@ -29844,7 +29571,7 @@ automatic display variables, and debugger options. @item @code{step} [@var{count}] @itemx @code{s} [@var{count}] Continue execution until control reaches a different source line in the -current stack frame. @code{step} steps inside any function called within +current stack frame, stepping inside any function called within the line. If the argument @var{count} is supplied, steps that many times before stopping, unless it encounters a breakpoint or watchpoint. @@ -29957,7 +29684,7 @@ or field. String values must be enclosed between double quotes (@code{"}@dots{}@code{"}). You can also set special @command{awk} variables, such as @code{FS}, -@code{NF}, @code{NR}, and son on. +@code{NF}, @code{NR}, and so on. @cindex debugger commands, @code{w} (@code{watch}) @cindex debugger commands, @code{watch} @@ -29969,7 +29696,7 @@ You can also set special @command{awk} variables, such as @code{FS}, Add variable @var{var} (or field @code{$@var{n}}) to the watch list. The debugger then stops whenever the value of the variable or field changes. Each watched item is assigned a -number which can be used to delete it from the watch list using the +number that can be used to delete it from the watch list using the @code{unwatch} command. With a watchpoint, you may also supply a condition. This is an @@ -29997,11 +29724,11 @@ watch list. @node Execution Stack @subsection Working with the Stack -Whenever you run a program which contains any function calls, +Whenever you run a program that contains any function calls, @command{gawk} maintains a stack of all of the function calls leading up to where the program is right now. You can see how you got to where you are, and also move around in the stack to see what the state of things was in the -functions which called the one you are in. The commands for doing this are: +functions that called the one you are in. The commands for doing this are: @table @asis @cindex debugger commands, @code{bt} (@code{backtrace}) @@ -30036,8 +29763,8 @@ Then select and print the frame. @item @code{frame} [@var{n}] @itemx @code{f} [@var{n}] Select and print stack frame @var{n}. Frame 0 is the currently executing, -or @dfn{innermost}, frame (function call), frame 1 is the frame that -called the innermost one. The highest numbered frame is the one for the +or @dfn{innermost}, frame (function call); frame 1 is the frame that +called the innermost one. The highest-numbered frame is the one for the main program. The printed information consists of the frame number, function and argument names, source file, and the source line. @@ -30053,7 +29780,7 @@ Then select and print the frame. Besides looking at the values of variables, there is often a need to get other sorts of information about the state of your program and of the -debugging environment itself. The @command{gawk} debugger has one command which +debugging environment itself. The @command{gawk} debugger has one command that provides this information, appropriately called @code{info}. @code{info} is used with one of a number of arguments that tell it exactly what you want to know: @@ -30141,12 +29868,12 @@ The available options are: @table @asis @item @code{history_size} @cindex debugger history size -The maximum number of lines to keep in the history file @file{./.gawk_history}. -The default is 100. +Set the maximum number of lines to keep in the history file +@file{./.gawk_history}. The default is 100. @item @code{listsize} @cindex debugger default list amount -The number of lines that @code{list} prints. The default is 15. +Specify the number of lines that @code{list} prints. The default is 15. @item @code{outfile} @cindex redirect @command{gawk} output, in debugger @@ -30156,7 +29883,7 @@ standard output. @item @code{prompt} @cindex debugger prompt -The debugger prompt. The default is @samp{@w{gawk> }}. +Change the debugger prompt. The default is @samp{@w{gawk> }}. @item @code{save_history} [@code{on} | @code{off}] @cindex debugger history file @@ -30167,7 +29894,7 @@ The default is @code{on}. @cindex save debugger options Save current options to file @file{./.gawkrc} upon exit. The default is @code{on}. -Options are read back in to the next session upon startup. +Options are read back into the next session upon startup. @item @code{trace} [@code{on} | @code{off}] @cindex instruction tracing, in debugger @@ -30190,7 +29917,7 @@ command in the file. Also, the list of commands may include additional @code{source} commands; however, the @command{gawk} debugger will not source the same file more than once in order to avoid infinite recursion. -In addition to, or instead of the @code{source} command, you can use +In addition to, or instead of, the @code{source} command, you can use the @option{-D @var{file}} or @option{--debug=@var{file}} command-line options to execute commands from a file non-interactively (@pxref{Options}). @@ -30199,16 +29926,16 @@ options to execute commands from a file non-interactively @node Miscellaneous Debugger Commands @subsection Miscellaneous Commands -There are a few more commands which do not fit into the +There are a few more commands that do not fit into the previous categories, as follows: @table @asis @cindex debugger commands, @code{dump} @cindex @code{dump} debugger command @item @code{dump} [@var{filename}] -Dump bytecode of the program to standard output or to the file +Dump byte code of the program to standard output or to the file named in @var{filename}. This prints a representation of the internal -instructions which @command{gawk} executes to implement the @command{awk} +instructions that @command{gawk} executes to implement the @command{awk} commands in a program. This can be very enlightening, as the following partial dump of Davide Brini's obfuscated code (@pxref{Signature Program}) demonstrates: @@ -30305,7 +30032,7 @@ Print lines centered around line number @var{n} in source file @var{filename}. This command may change the current source file. @item @var{function} -Print lines centered around beginning of the +Print lines centered around the beginning of the function @var{function}. This command may change the current source file. @end table @@ -30317,16 +30044,16 @@ function @var{function}. This command may change the current source file. @item @code{quit} @itemx @code{q} Exit the debugger. Debugging is great fun, but sometimes we all have -to tend to other obligations in life, and sometimes we find the bug, +to tend to other obligations in life, and sometimes we find the bug and are free to go on to the next one! As we saw earlier, if you are -running a program, the debugger warns you if you accidentally type +running a program, the debugger warns you when you type @samp{q} or @samp{quit}, to make sure you really want to quit. @cindex debugger commands, @code{trace} @cindex @code{trace} debugger command @item @code{trace} [@code{on} | @code{off}] -Turn on or off a continuous printing of instructions which are about to -be executed, along with printing the @command{awk} line which they +Turn on or off continuous printing of the instructions that are about to +be executed, along with the @command{awk} lines they implement. The default is @code{off}. It is to be hoped that most of the ``opcodes'' in these instructions are @@ -30342,7 +30069,7 @@ fairly self-explanatory, and using @code{stepi} and @code{nexti} while If @command{gawk} is compiled with @uref{http://cnswww.cns.cwru.edu/php/chet/readline/readline.html, -the @code{readline} library}, you can take advantage of that library's +the GNU Readline library}, you can take advantage of that library's command completion and history expansion features. The following types of completion are available: @@ -30379,7 +30106,7 @@ and We hope you find the @command{gawk} debugger useful and enjoyable to work with, but as with any program, especially in its early releases, it still has -some limitations. A few which are worth being aware of are: +some limitations. A few that it's worth being aware of are: @itemize @value{BULLET} @item @@ -30395,13 +30122,13 @@ If you perused the dump of opcodes in @ref{Miscellaneous Debugger Commands} (or if you are already familiar with @command{gawk} internals), you will realize that much of the internal manipulation of data in @command{gawk}, as in many interpreters, is done on a stack. -@code{Op_push}, @code{Op_pop}, and the like, are the ``bread and butter'' of +@code{Op_push}, @code{Op_pop}, and the like are the ``bread and butter'' of most @command{gawk} code. Unfortunately, as of now, the @command{gawk} debugger does not allow you to examine the stack's contents. That is, the intermediate results of expression evaluation are on the -stack, but cannot be printed. Rather, only variables which are defined +stack, but cannot be printed. Rather, only variables that are defined in the program can be printed. Of course, a workaround for this is to use more explicit variables at the debugging stage and then change back to obscure, perhaps more optimal code later. @@ -30415,12 +30142,12 @@ programmer, you are expected to know the meaning of @item The @command{gawk} debugger is designed to be used by running a program (with all its parameters) on the command line, as described in @ref{Debugger Invocation}. -There is no way (as of now) to attach or ``break in'' to a running program. -This seems reasonable for a language which is used mainly for quickly +There is no way (as of now) to attach or ``break into'' a running program. +This seems reasonable for a language that is used mainly for quickly executing, short programs. @item -The @command{gawk} debugger only accepts source supplied with the @option{-f} option. +The @command{gawk} debugger only accepts source code supplied with the @option{-f} option. @end itemize @ignore @@ -30434,8 +30161,8 @@ be added, and of course feel free to try to add them yourself! @itemize @value{BULLET} @item Programs rarely work correctly the first time. Finding bugs -is @dfn{debugging} and a program that helps you find bugs is a -@dfn{debugger}. @command{gawk} has a built-in debugger that works very +is called debugging, and a program that helps you find bugs is a +debugger. @command{gawk} has a built-in debugger that works very similarly to the GNU Debugger, GDB. @item @@ -30455,7 +30182,7 @@ breakpoints, execution, viewing and changing data, working with the stack, getting information, and other tasks. @item -If the @code{readline} library is available when @command{gawk} is +If the GNU Readline library is available when @command{gawk} is compiled, it is used by the debugger to provide command-line history and editing. @@ -30712,7 +30439,7 @@ is available like so: @example $ @kbd{gawk --version} @print{} GNU Awk 4.1.2, API: 1.1 (GNU MPFR 3.1.0-p3, GNU MP 5.0.2) -@print{} Copyright (C) 1989, 1991-2014 Free Software Foundation. +@print{} Copyright (C) 1989, 1991-2015 Free Software Foundation. @dots{} @end example @@ -31366,7 +31093,7 @@ When asked about the algorithm used, Katie replied: @quotation It's not that well known but it's not that obscure either. It's Euler's modification to Newton's method for calculating pi. -Take a look at lines (23) - (25) here: @uref{http://mathworld.wolfram.com/PiFormulas.htm}. +Take a look at lines (23) - (25) here: @uref{http://mathworld.wolfram.com/PiFormulas.html}. The algorithm I wrote simply expands the multiply by 2 and works from the innermost expression outwards. I used this to program HP calculators @@ -31416,7 +31143,7 @@ Allowing completely alphabetic strings to have valid numeric values is also a very severe departure from historical practice. @end itemize -The second problem is that the @code{gawk} maintainer feels that this +The second problem is that the @command{gawk} maintainer feels that this interpretation of the standard, which requires a certain amount of ``language lawyering'' to arrive at in the first place, was not even intended by the standard developers. In other words, ``we see how you @@ -31575,7 +31302,7 @@ When @option{--sandbox} is specified, extensions are disabled * Finding Extensions:: How @command{gawk} finds compiled extensions. * Extension Example:: Example C code for an extension. * Extension Samples:: The sample extensions that ship with - @code{gawk}. + @command{gawk}. * gawkextlib:: The @code{gawkextlib} project. * Extension summary:: Extension summary. * Extension Exercises:: Exercises. @@ -32539,7 +32266,7 @@ If the concept of a ``record terminator'' makes sense, then @code{*rt_start} should be set to point to the data to be used for @code{RT}, and @code{*rt_len} should be set to the length of the data. Otherwise, @code{*rt_len} should be set to zero. -@code{gawk} makes its own copy of this data, so the +@command{gawk} makes its own copy of this data, so the extension must manage this storage. @end table @@ -32585,7 +32312,7 @@ When writing an input parser, you should think about (and document) how it is expected to interact with @command{awk} code. You may want it to always be called, and take effect as appropriate (as the @code{readdir} extension does). Or you may want it to take effect -based upon the value of an @code{awk} variable, as the XML extension +based upon the value of an @command{awk} variable, as the XML extension from the @code{gawkextlib} project does (@pxref{gawkextlib}). In the latter case, code in a @code{BEGINFILE} section can look at @code{FILENAME} and @code{ERRNO} to decide whether or @@ -33368,7 +33095,7 @@ converts it to a string. Using non-integral values is possible, but requires that you understand how such values are converted to strings (@pxref{Conversion}); thus using integral values is safest. -As with @emph{all} strings passed into @code{gawk} from an extension, +As with @emph{all} strings passed into @command{gawk} from an extension, the string value of @code{index} must come from @code{gawk_malloc()}, @code{gawk_calloc()} or @code{gawk_realloc()}, and @command{gawk} releases the storage. @@ -35654,9 +35381,7 @@ online documentation}. @node V7/SVR3.1 @appendixsec Major Changes Between V7 and SVR3.1 -@c STARTOFRANGE gawkv @cindex @command{awk}, versions of -@c STARTOFRANGE gawkv1 @cindex @command{awk}, versions of, changes between V7 and SVR3.1 The @command{awk} language evolved considerably between the release of @@ -35743,7 +35468,6 @@ Multiple @code{BEGIN} and @code{END} rules Multidimensional arrays (@pxref{Multidimensional}). @end itemize -@c ENDOFRANGE gawkv1 @node SVR4 @appendixsec Changes Between SVR3.1 and SVR4 @@ -35858,7 +35582,6 @@ not permitted by the POSIX standard. The 2008 POSIX standard can be found online at @url{http://www.opengroup.org/onlinepubs/9699919799/}. -@c ENDOFRANGE gawkv @node BTL @appendixsec Extensions in Brian Kernighan's @command{awk} @@ -35904,11 +35627,8 @@ available in his @command{awk}. @node POSIX/GNU @appendixsec Extensions in @command{gawk} Not in POSIX @command{awk} -@c STARTOFRANGE fripls @cindex compatibility mode (@command{gawk}), extensions -@c STARTOFRANGE exgnot @cindex extensions, in @command{gawk}, not in POSIX @command{awk} -@c STARTOFRANGE posnot @cindex POSIX, @command{gawk} extensions not included in The GNU implementation, @command{gawk}, adds a large number of features. They can all be disabled with either the @option{--traditional} or @@ -36237,9 +35957,6 @@ MirBSD @c XXX ADD MORE STUFF HERE -@c ENDOFRANGE fripls -@c ENDOFRANGE exgnot -@c ENDOFRANGE posnot @c This does not need to be in the formal book. @ifclear FOR_PRINT @@ -37326,9 +37043,7 @@ the appropriate credit where credit is due. @c last two commas are part of see also @cindex operating systems, See Also GNU/Linux@comma{} PC operating systems@comma{} Unix -@c STARTOFRANGE gligawk @cindex @command{gawk}, installing -@c STARTOFRANGE ingawk @cindex installing @command{gawk} This appendix provides instructions for installing @command{gawk} on the various platforms that are supported by the developers. The primary @@ -37438,7 +37153,6 @@ a local expert. @node Distribution contents @appendixsubsec Contents of the @command{gawk} Distribution -@c STARTOFRANGE gawdis @cindex @command{gawk}, distribution The @command{gawk} distribution has a number of C source files, @@ -37536,10 +37250,10 @@ The generated Info file for this @value{DOCUMENT}. @item doc/gawkinet.texi The Texinfo source file for @ifinfo -@inforef{Top, , General Introduction, gawkinet, TCP/IP Internetworking with @command{gawk}}. +@inforef{Top, , General Introduction, gawkinet, @value{GAWKINETTITLE}}. @end ifinfo @ifnotinfo -@cite{TCP/IP Internetworking with @command{gawk}}. +@cite{@value{GAWKINETTITLE}}. @end ifnotinfo It should be processed with @TeX{} (via @command{texi2dvi} or @command{texi2pdf}) @@ -37548,7 +37262,7 @@ with @command{makeinfo} to produce an Info or HTML file. @item doc/gawkinet.info The generated Info file for -@cite{TCP/IP Internetworking with @command{gawk}}. +@cite{@value{GAWKINETTITLE}}. @item doc/igawk.1 The @command{troff} source for a manual page describing the @command{igawk} @@ -37637,7 +37351,6 @@ directory to run your version of @command{gawk} against the test suite. If @command{gawk} successfully passes @samp{make check}, then you can be confident of a successful port. @end table -@c ENDOFRANGE gawdis @node Unix Installation @appendixsec Compiling and Installing @command{gawk} on Unix-Like Systems @@ -37788,7 +37501,7 @@ can be configured and compiled. @cindex @option{--disable-lint} configuration option @cindex configuration option, @code{--disable-lint} @item --disable-lint -Disable all lint checking within @code{gawk}. The +Disable all lint checking within @command{gawk}. The @option{--lint} and @option{--lint-old} options (@pxref{Options}) are accepted, but silently do nothing. @@ -38102,9 +37815,7 @@ multibyte functionality is not available. @node PC Using @appendixsubsubsec Using @command{gawk} on PC Operating Systems -@c STARTOFRANGE opgawx @cindex operating systems, PC, @command{gawk} on -@c STARTOFRANGE pcgawon @cindex PC operating systems, @command{gawk} on Under MS-DOS and MS-Windows, the Cygwin and MinGW environments support @@ -38612,8 +38323,6 @@ $ @kbd{gawk :== $sys$common:[syshlp.examples.tcpip.snmp]gawk.exe} This is apparently @value{PVERSION} 2.15.6, which is extremely old. We recommend compiling and using the current version. -@c ENDOFRANGE opgawx -@c ENDOFRANGE pcgawon @node Bugs @appendixsec Reporting Problems and Bugs @@ -38624,9 +38333,7 @@ recommend compiling and using the current version. @end quotation @c the radio show, not the book. :-) -@c STARTOFRANGE dbugg @cindex debugging @command{gawk}, bug reports -@c STARTOFRANGE tblgawb @cindex troubleshooting, @command{gawk}, bug reports If you have problems with @command{gawk} or think that you have found a bug, report it to the developers; we cannot promise to do anything @@ -38723,12 +38430,9 @@ The people maintaining the various @command{gawk} ports are: If your bug is also reproducible under Unix, send a copy of your report to the @EMAIL{bug-gawk@@gnu.org,bug-gawk at gnu dot org} email list as well. -@c ENDOFRANGE dbugg -@c ENDOFRANGE tblgawb @node Other Versions @appendixsec Other Freely Available @command{awk} Implementations -@c STARTOFRANGE awkim @cindex @command{awk}, implementations @ignore From: emory!amc.com!brennan (Michael Brennan) @@ -38788,7 +38492,7 @@ git clone git://github.com/onetrueawk/awk bwkawk @end example @noindent -This command creates a copy of the @uref{http://www.git-scm.com, Git} +This command creates a copy of the @uref{http://git-scm.com, Git} repository in a directory named @file{bwkawk}. If you leave that argument off the @command{git} command line, the repository copy is created in a directory named @file{awk}. @@ -38853,7 +38557,7 @@ To get @command{awka}, go to @url{http://sourceforge.net/projects/awka}. @c andrewsumner@@yahoo.net The project seems to be frozen; no new code changes have been made -since approximately 2003. +since approximately 2001. @cindex Beebe, Nelson H.F.@: @cindex @command{pawk} (profiling version of Brian Kernighan's @command{awk}) @@ -38949,7 +38653,6 @@ See also the ``Versions and implementations'' section of the Wikipedia article} for information on additional versions. @end table -@c ENDOFRANGE awkim @node Installation summary @appendixsec Summary @@ -38987,15 +38690,11 @@ implementations. Many are POSIX compliant; others are less so. @end itemize -@c ENDOFRANGE gligawk -@c ENDOFRANGE ingawk @ifclear FOR_PRINT @node Notes @appendix Implementation Notes -@c STARTOFRANGE gawii @cindex @command{gawk}, implementation issues -@c STARTOFRANGE impis @cindex implementation issues, @command{gawk} This appendix contains information mainly of interest to implementers and @@ -39071,7 +38770,7 @@ However, if you want to modify @command{gawk} and contribute back your changes, you will probably wish to work with the development version. To do so, you will need to access the @command{gawk} source code repository. The code is maintained using the -@uref{http://git-scm.com/, Git distributed version control system}. +@uref{http://git-scm.com, Git distributed version control system}. You will need to install it if your system doesn't have it. Once you have done so, use the command: @@ -39100,11 +38799,8 @@ that has a Git plug-in for working with Git repositories. @node Adding Code @appendixsubsec Adding New Features -@c STARTOFRANGE adfgaw @cindex adding, features to @command{gawk} -@c STARTOFRANGE fadgaw @cindex features, adding to @command{gawk} -@c STARTOFRANGE gawadf @cindex @command{gawk}, features, adding You are free to add any new features you like to @command{gawk}. However, if you want your changes to be incorporated into the @command{gawk} @@ -39139,7 +38835,7 @@ for information on getting the latest version of @command{gawk}.) @item @ifnotinfo -Follow the @uref{http://www.gnu.org/prep/standards/, @cite{GNU Coding Standards}}. +Follow the @cite{GNU Coding Standards}. @end ifnotinfo @ifinfo See @inforef{Top, , Version, standards, GNU Coding Standards}. @@ -39148,7 +38844,7 @@ This document describes how GNU software should be written. If you haven't read it, please do so, preferably @emph{before} starting to modify @command{gawk}. (The @cite{GNU Coding Standards} are available from the GNU Project's -@uref{http://www.gnu.org/prep/standards_toc.html, website}. +@uref{http://www.gnu.org/prep/standards/, website}. Texinfo, Info, and DVI versions are also available.) @cindex @command{gawk}, coding style in @@ -39271,9 +38967,6 @@ Although this sounds like a lot of work, please remember that while you may write the new code, I have to maintain it and support it. If it isn't possible for me to do that with a minimum of extra work, then I probably will not. -@c ENDOFRANGE adfgaw -@c ENDOFRANGE gawadf -@c ENDOFRANGE fadgaw @node New Ports @appendixsubsec Porting @command{gawk} to a New Operating System @@ -39407,7 +39100,6 @@ coding style and brace layout that suits your taste. @node Derived Files @appendixsubsec Why Generated Files Are Kept In Git -@c STARTOFRANGE gawkgit @cindex Git, use of for @command{gawk} source code @c From emails written March 22, 2012, to the gawk developers list. @@ -39596,7 +39288,6 @@ wget http://git.savannah.gnu.org/cgit/gawk.git/snapshot/gawk-@var{branchname}.ta @noindent to retrieve a snapshot of the given branch. -@c ENDOFRANGE gawkgit @node Future Extensions @appendixsec Probable Future Extensions @@ -39977,13 +39668,10 @@ of @command{gawk}, but it @emph{will} be removed in the next major release. @end itemize -@c ENDOFRANGE impis -@c ENDOFRANGE gawii @node Basic Concepts @appendix Basic Programming Concepts @cindex programming, concepts -@c STARTOFRANGE procon @cindex programming, concepts This @value{APPENDIX} attempts to define some of the basic concepts @@ -40221,7 +39909,6 @@ standard for C. This standard became an ISO standard in 1990. In 1999, a revised ISO C standard was approved and released. Where it makes sense, POSIX @command{awk} is compatible with 1999 ISO C. -@c ENDOFRANGE procon @node Glossary @unnumbered Glossary @@ -40272,6 +39959,21 @@ languages. These standards often become international standards as well. See also ``ISO.'' +@item Argument +An argument can be two different things. It can be an option or a +@value{FN} passed to a command while invoking it from the command line, or +it can be something passed to a @dfn{function} inside a program, e.g. +inside @command{awk}. + +In the latter case, an argument can be passed to a function in two ways. +Either it is given to the called function by value, i.e., a copy of the +value of the variable is made available to the called function, but the +original variable cannot be modified by the function itself; or it is +given by reference, i.e., a pointer to the interested variable is passed to +the function, which can then directly modify it. In @command{awk} +scalars are passed by value, and arrays are passed by reference. +See ``Pass By Value/Reference.'' + @item Array A grouping of multiple values under the same name. Most languages just provide sequential arrays. @@ -40313,6 +40015,25 @@ The GNU version of the standard shell @end ifinfo See also ``Bourne Shell.'' +@item Binary +Base-two notation, where the digits are @code{0}--@code{1}. Since +electronic circuitry works ``naturally'' in base 2 (just think of Off/On), +everything inside a computer is calculated using base 2. Each digit +represents the presence (or absence) of a power of 2 and is called a +@dfn{bit}. So, for example, the base-two number @code{10101} is +the same as decimal 21, ((1 x 16) + (1 x 4) + (1 x 1)). + +Since base-two numbers quickly become +very long to read and write, they are usually grouped by 3 (i.e., they are +read as octal numbers), or by 4 (i.e., they are read as hexadecimal +numbers). There is no direct way to insert base 2 numbers in a C program. +If need arises, such numbers are usually inserted as octal or hexadecimal +numbers. The number of base-two digits that fit into registers used for +representing integer numbers in computers is a rough indication of the +computing power of the computer itself. Most computers nowadays use 64 +bits for representing integer numbers in their registers, but 32-bit, +16-bit and 8-bit registers have been widely used in the past. +@xref{Nondecimal-numbers}. @item Bit Short for ``Binary Digit.'' All values in computer memory ultimately reduce to binary digits: values @@ -40344,6 +40065,19 @@ The characters @samp{@{} and @samp{@}}. Braces are used in @command{awk} for delimiting actions, compound statements, and function bodies. +@item Bracket Expression +Inside a @dfn{regular expression}, an expression included in square +brackets, meant to designate a single character as belonging to a +specified character class. A bracket expression can contain a list of one +or more characters, like @samp{[abc]}, a range of characters, like +@samp{[A-Z]}, or a name, delimited by @samp{:}, that designates a known set +of characters, like @samp{[:digit:]}. The form of bracket expression +enclosed between @samp{:} is independent of the underlying representation +of the character themselves, which could utilize the ASCII, ECBDIC, or +Unicode codesets, depending on the architecture of the computer system, and on +localization. +See also ``Regular Expression.'' + @item Built-in Function The @command{awk} language provides built-in functions that perform various numerical, I/O-related, and string computations. Examples are @@ -40397,9 +40131,25 @@ points out similarities between @command{awk} and C when appropriate. In general, @command{gawk} attempts to be as similar to the 1990 version of ISO C as makes sense. +@item C Shell +The C Shell (@command{csh} or its improved version, @command{tcsh}) is a Unix shell that was +created by Bill Joy in the late 1970s. The C shell was differentiated from +other shells by its interactive features and overall style, which +looks more like C. The C Shell is not backward compatible with the Bourne +Shell, so special attention is required when converting scripts +written for other Unix shells to the C shell, especially with regard to the management of +shell variables. +See also ``Bourne Shell.'' + @item C++ A popular object-oriented programming language derived from C. +@item Character Class +See ``Bracket Expression.'' + +@item Character List +See ``Bracket Expression.'' + @cindex ASCII @cindex ISO 8859-1 @cindex ISO Latin-1 @@ -40423,7 +40173,7 @@ A preprocessor for @command{pic} that reads descriptions of molecules and produces @command{pic} input for drawing them. It was written in @command{awk} by Brian Kernighan and Jon Bentley, and is available from -@uref{http://netlib.sandia.gov/netlib/typesetting/chem.gz}. +@uref{http://netlib.org/typesetting/chem}. @item Comparison Expression A relation that is either true or false, such as @samp{a < b}. @@ -40439,11 +40189,23 @@ machine-executable object code. The object code is then executed directly by the computer. See also ``Interpreter.'' +@item Complemented Bracket Expression +The negation of a @dfn{bracket expression}. All that is @emph{not} +described by a given bracket expression. The symbol @samp{^} precedes +the negated bracket expression. E.g.: @samp{[[^:digit:]} +designates whatever character is not a digit. @samp{[^bad]} +designates whatever character is not one of the letters @samp{b}, @samp{a}, +or @samp{d}. +See ``Bracket Expression.'' + @item Compound Statement A series of @command{awk} statements, enclosed in curly braces. Compound statements may be nested. (@xref{Statements}.) +@item Computed Regexps +See ``Dynamic Regular Expressions.'' + @item Concatenation Concatenating two strings means sticking them together, one after another, producing a new string. For example, the string @samp{foo} concatenated with @@ -40458,6 +40220,13 @@ expression is the value of @var{expr2}; otherwise the value is @var{expr3}. In either case, only one of @var{expr2} and @var{expr3} is evaluated. (@xref{Conditional Exp}.) +@item Control Statement +A control statement is an instruction to perform a given operation or a set +of operations inside an @command{awk} program, if a given condition is +true. Control statements are: @code{if}, @code{for}, @code{while}, and +@code{do} +(@pxref{Statements}). + @cindex McIlroy, Doug @cindex cookie @item Cookie @@ -40612,6 +40381,11 @@ Format strings control the appearance of output in the are controlled by the format strings contained in the predefined variables @code{CONVFMT} and @code{OFMT}. (@xref{Control Letters}.) +@item Fortran +Shorthand for FORmula TRANslator, one of the first programming languages +available for scientific calculations. It was created by John Backus, +and has been available since 1957. It is still in use today. + @item Free Documentation License This document describes the terms under which this @value{DOCUMENT} is published and may be copied. (@xref{GNU Free Documentation License}.) @@ -40629,10 +40403,21 @@ Emacs editor. GNU Emacs is the most widely used version of Emacs today. See ``Free Software Foundation.'' @item Function -A specialized group of statements used to encapsulate general -or program-specific tasks. @command{awk} has a number of built-in -functions, and also allows you to define your own. -(@xref{Functions}.) +A part of an @command{awk} program that can be invoked from every point of +the program, to perform a task. @command{awk} has several built-in +functions. +Users can define their own functions in every part of the program. +Function can be recursive, i.e., they may invoke themselves. +@xref{Functions}. +In @command{gawk} it is also possible to have functions shared +among different programs, and included where required using the +@code{@@include} directive +(@pxref{Include Files}). +In @command{gawk} the name of the function that should be invoked +can be generated at run time, i.e., dynamically. +The @command{gawk} extension API provides constructor functions +(@pxref{Constructor Functions}). + @item @command{gawk} The GNU implementation of @command{awk}. @@ -40756,6 +40541,12 @@ meaning. Keywords are reserved and may not be used as variable names. and @code{while}. +@item Korn Shell +The Korn Shell (@command{ksh}) is a Unix shell which was developed by David Korn at Bell +Laboratories in the early 1980s. The Korn Shell is backward-compatible with the Bourne +shell and includes many features of the C shell. +See also ``Bourne Shell.'' + @cindex LGPL (Lesser General Public License) @cindex Lesser General Public License (LGPL) @cindex GNU Lesser General Public License @@ -40795,6 +40586,14 @@ Characters used within a regexp that do not stand for themselves. Instead, they denote regular expression operations, such as repetition, grouping, or alternation. +@item Nesting +Nesting is where information is organized in layers, or where objects +contain other similar objects. +In @command{gawk} the @code{@@include} +directive can be nested. The ``natural'' nesting of arithmetic and +logical operations can be changed using parentheses +(@pxref{Precedence}). + @item No-op An operation that does nothing. @@ -40815,6 +40614,11 @@ Octal numbers are written in C using a leading @samp{0}, to indicate their base. Thus, @code{013} is 11 ((1 x 8) + 3). @xref{Nondecimal-numbers}. +@item Output Record +A single chunk of data that is written out by @command{awk}. Usually, an +@command{awk} output record consists of one or more lines of text. +@xref{Records}. + @item Pattern Patterns tell @command{awk} which input records are interesting to which rules. @@ -40829,6 +40633,9 @@ An acronym describing what is possibly the most frequent source of computer usage problems. (Problem Exists Between Keyboard And Chair.) +@item Plug-in +See ``Extensions.'' + @item POSIX The name for a series of standards that specify a Portable Operating System interface. The ``IX'' denotes @@ -40853,6 +40660,9 @@ A sequence of consecutive lines from the input file(s). A pattern can specify ranges of input lines for @command{awk} to process or it can specify single lines. (@xref{Pattern Overview}.) +@item Record +See ``Input record'' and ``Output record.'' + @item Recursion When a function calls itself, either directly or indirectly. If this is clear, stop, and proceed to the next entry. @@ -40870,6 +40680,15 @@ operators. (@xref{Getline}, and @ref{Redirection}.) +@item Reference Counts +An internal mechanism in @command{gawk} to minimize the amount of memory +needed to store the value of string variables. If the value assumed by +a variable is used in more than one place, only one copy of the value +itself is kept, and the associated reference count is increased when the +same value is used by an additional variable, and decresed when the related +variable is no longer in use. When the reference count goes to zero, +the memory space used to store the value of the variable is freed. + @item Regexp See ``Regular Expression.'' @@ -40887,6 +40706,15 @@ slashes, such as @code{/foo/}. This regular expression is chosen when you write the @command{awk} program and cannot be changed during its execution. (@xref{Regexp Usage}.) +@item Regular Expression Operators +See ``Metacharacters.'' + +@item Rounding +Rounding the result of an arithmetic operation can be tricky. +More than one way of rounding exists, and in @command{gawk} +it is possible to choose which method should be used in a program. +@xref{Setting the rounding mode}. + @item Rule A segment of an @command{awk} program that specifies how to process single input records. A rule consists of a @dfn{pattern} and an @dfn{action}. @@ -40946,6 +40774,12 @@ A @value{FN} interpreted internally by @command{gawk}, instead of being handed directly to the underlying operating system---for example, @file{/dev/stderr}. (@xref{Special Files}.) +@item Statement +An expression inside an @command{awk} program in the action part +of a pattern--action rule, or inside an +@command{awk} function. A statement can be a variable assignment, +an array operation, a loop, etc. + @item Stream Editor A program that reads records from an input stream and processes them one or more at a time. This is in contrast with batch programs, which may @@ -40996,9 +40830,14 @@ This is standard time in Greenwich, England, which is used as a reference time for day and date calculations. See also ``Epoch'' and ``GMT.'' +@item Variable +A name for a value. In @command{awk}, variables may be either scalars +or arrays. + @item Whitespace A sequence of space, TAB, or newline characters occurring inside an input record or a string. + @end table @end ifclear diff --git a/doc/gawkinet.info b/doc/gawkinet.info index 0a0d69d8..d726be0b 100644 --- a/doc/gawkinet.info +++ b/doc/gawkinet.info @@ -6,7 +6,7 @@ START-INFO-DIR-ENTRY * Gawkinet: (gawkinet). TCP/IP Internetworking With `gawk'. END-INFO-DIR-ENTRY - This is Edition 1.3 of `TCP/IP Internetworking With `gawk'', for the + This is Edition 1.3 of `TCP/IP Internetworking with `gawk'', for the 4.0.0 (or later) version of the GNU implementation of AWK. @@ -30,7 +30,7 @@ texts being (a) (see below), and with the Back-Cover Texts being (b) This file documents the networking features in GNU `awk'. - This is Edition 1.3 of `TCP/IP Internetworking With `gawk'', for the + This is Edition 1.3 of `TCP/IP Internetworking with `gawk'', for the 4.0.0 (or later) version of the GNU implementation of AWK. @@ -61,7 +61,7 @@ General Introduction This file documents the networking features in GNU Awk (`gawk') version 4.0 and later. - This is Edition 1.3 of `TCP/IP Internetworking With `gawk'', for the + This is Edition 1.3 of `TCP/IP Internetworking with `gawk'', for the 4.0.0 (or later) version of the GNU implementation of AWK. diff --git a/doc/gawkinet.texi b/doc/gawkinet.texi index 40198e1d..10223239 100644 --- a/doc/gawkinet.texi +++ b/doc/gawkinet.texi @@ -60,7 +60,7 @@ @c fit into that chapter, thus this separate document. At over 50 @c pages, I think this is the right decision. ADR. -@set TITLE TCP/IP Internetworking With @command{gawk} +@set TITLE TCP/IP Internetworking with @command{gawk} @set EDITION 1.3 @set UPDATE-MONTH December, 2010 @c gawk versions: diff --git a/doc/gawktexi.in b/doc/gawktexi.in index 87fa41ca..e127f428 100644 --- a/doc/gawktexi.in +++ b/doc/gawktexi.in @@ -50,8 +50,9 @@ @set VERSION 4.1 @set PATCHLEVEL 2 +@set GAWKINETTITLE TCP/IP Internetworking with @command{gawk} @ifset FOR_PRINT -@set TITLE Effective Awk Programming +@set TITLE Effective awk Programming @end ifset @ifclear FOR_PRINT @set TITLE GAWK: Effective AWK Programming @@ -202,7 +203,7 @@ @set FFN Filename @set DF datafile @set DDF Datafile -@set PVERSION Version +@set PVERSION version @end ifset @c For HTML, spell out email addresses, to avoid problems with @@ -299,7 +300,7 @@ All Rights Reserved.</literallayout> @end docbook @ifnotdocbook -Copyright @copyright{} 1989, 1991, 1992, 1993, 1996--2005, 2007, 2009--2014 @* +Copyright @copyright{} 1989, 1991, 1992, 1993, 1996--2005, 2007, 2009--2015 @* Free Software Foundation, Inc. @end ifnotdocbook @sp 2 @@ -467,7 +468,7 @@ particular records in a file and perform operations upon them. @command{gawk}. * Internationalization:: Getting @command{gawk} to speak your language. -* Debugger:: The @code{gawk} debugger. +* Debugger:: The @command{gawk} debugger. * Arbitrary Precision Arithmetic:: Arbitrary precision arithmetic with @command{gawk}. * Dynamic Extensions:: Adding new built-in functions to @@ -951,7 +952,7 @@ particular records in a file and perform operations upon them. * Internal File Ops:: The code for internal file operations. * Using Internal File Ops:: How to use an external extension. * Extension Samples:: The sample extensions that ship with - @code{gawk}. + @command{gawk}. * Extension Sample File Functions:: The file functions sample. * Extension Sample Fnmatch:: An interface to @code{fnmatch()}. * Extension Sample Fork:: An interface to @code{fork()} and @@ -1166,7 +1167,7 @@ interface to network protocols via special @file{/inet} files. The programs in this book make clear that an AWK program is typically much smaller and faster to develop than a counterpart written in C. -Consequently, there is often a payoff to prototype an +Consequently, there is often a payoff to prototyping an algorithm or design in AWK to get it running quickly and expose problems early. Often, the interpreted performance is adequate and the AWK prototype becomes the product. @@ -1243,15 +1244,15 @@ March 2001 Some things don't change. Thirteen years ago I wrote: ``If you use AWK or want to learn how, then read this book.'' -True then and still true today. +True then, and still true today. -Learning to use a programming language is more than mastering the +Learning to use a programming language is about more than mastering the syntax. One needs to acquire an understanding of how to use the features of the language to solve practical programming problems. A focus of this book is many examples that show how to use AWK. Some things do change. Our computers are much faster and have more memory. -Consequently, speed and storage inefficiencies of a high level language +Consequently, speed and storage inefficiencies of a high-level language matter less. Prototyping in AWK and then rewriting in C for performance reasons happens less, because more often the prototype is fast enough. @@ -1259,12 +1260,12 @@ Of course, there are computing operations that are best done in C or C++. With @command{gawk} 4.1 and later, you do not have to choose between writing your program in AWK or in C/C++. You can write most of your program in AWK and the aspects that require C/C++ capabilities can be written -in C/C++ and then the pieces glued together when the @command{gawk} module loads +in C/C++, and then the pieces glued together when the @command{gawk} module loads the C/C++ module as a dynamic plug-in. @c Chapter 16 @ref{Dynamic Extensions}, has all the -details, and as expected, many examples to help you learn the ins and outs. +details, and, as expected, many examples to help you learn the ins and outs. I enjoy programming in AWK and had fun (re)reading this book. I think you will too. @@ -1339,7 +1340,7 @@ Generate reports Validate data @item -Produce indexes and perform other document preparation tasks +Produce indexes and perform other document-preparation tasks @item Experiment with algorithms that you can adapt later to other computer @@ -1458,23 +1459,23 @@ help from me, thoroughly reworked @command{gawk} for compatibility with the newer @command{awk}. Circa 1994, I became the primary maintainer. Current development focuses on bug fixes, -performance improvements, standards compliance and, occasionally, new features. +performance improvements, standards compliance, and, occasionally, new features. In May 1997, J@"urgen Kahrs felt the need for network access from @command{awk}, and with a little help from me, set about adding features to do this for @command{gawk}. At that time, he also wrote the bulk of -@cite{TCP/IP Internetworking with @command{gawk}} +@cite{@value{GAWKINETTITLE}} (a separate document, available as part of the @command{gawk} distribution). His code finally became part of the main @command{gawk} distribution with @command{gawk} @value{PVERSION} 3.1. John Haque rewrote the @command{gawk} internals, in the process providing an @command{awk}-level debugger. This version became available as -@command{gawk} @value{PVERSION} 4.0, in 2011. +@command{gawk} @value{PVERSION} 4.0 in 2011. @DBXREF{Contributors} -for a full list of those who made important contributions to @command{gawk}. +for a full list of those who have made important contributions to @command{gawk}. @node Names @unnumberedsec A Rose by Any Other Name @@ -1487,7 +1488,7 @@ is often referred to as ``new @command{awk}.'' By analogy, the original version of @command{awk} is referred to as ``old @command{awk}.'' -Today, on most systems, when you run the @command{awk} utility, +Today, on most systems, when you run the @command{awk} utility you get some version of new @command{awk}.@footnote{Only Solaris systems still use an old @command{awk} for the default @command{awk} utility. A more modern @command{awk} lives in @@ -1547,7 +1548,9 @@ the POSIX standard for @command{awk}. This @value{DOCUMENT} has the difficult task of being both a tutorial and a reference. If you are a novice, feel free to skip over details that seem too complex. You should also ignore the many cross-references; they are for the -expert user and for the online Info and HTML versions of the @value{DOCUMENT}. +expert user and for the Info and +@uref{http://www.gnu.org/software/gawk/manual/, HTML} +versions of the @value{DOCUMENT}. @end ifnotinfo There are sidebars @@ -1580,7 +1583,7 @@ This @value{DOCUMENT} is split into several parts, as follows: @itemize @value{BULLET} @item -Part I describes the @command{awk} language and @command{gawk} program in detail. +Part I describes the @command{awk} language and the @command{gawk} program in detail. It starts with the basics, and continues through all of the features of @command{awk}. It contains the following chapters: @@ -1627,10 +1630,10 @@ doing something when a record is matched, and the predefined variables @item @ref{Arrays}, -covers @command{awk}'s one-and-only data structure: associative arrays. -Deleting array elements and whole arrays is also described, as well as -sorting arrays in @command{gawk}. It also describes how @command{gawk} -provides arrays of arrays. +covers @command{awk}'s one-and-only data structure: the associative array. +Deleting array elements and whole arrays is described, as well as +sorting arrays in @command{gawk}. The @value{CHAPTER} also describes how +@command{gawk} provides arrays of arrays. @item @ref{Functions}, @@ -1642,17 +1645,17 @@ as well as how to define your own functions. It also discusses how @item Part II shows how to use @command{awk} and @command{gawk} for problem solving. There is lots of code here for you to read and learn from. -It contains the following chapters: +This part contains the following chapters: @c nested @itemize @value{MINUS} @item -@ref{Library Functions}, which provides a number of functions meant to +@ref{Library Functions}, provides a number of functions meant to be used from main @command{awk} programs. @item @ref{Sample Programs}, -which provides many sample @command{awk} programs. +provides many sample @command{awk} programs. @end itemize Reading these two chapters allows you to see @command{awk} @@ -1705,7 +1708,7 @@ including the GNU General Public License: @item @ref{Language History}, describes how the @command{awk} language has evolved since -its first release to present. It also describes how @command{gawk} +its first release to the present. It also describes how @command{gawk} has acquired features over time. @item @@ -1748,7 +1751,7 @@ are completely unfamiliar with computer programming. @item @uref{http://www.gnu.org/software/gawk/manual/html_node/Glossary.html, The Glossary} -defines most, if not all of, the significant terms used +defines most, if not all, of the significant terms used throughout the @value{DOCUMENT}. If you find terms that you aren't familiar with, try looking them up here. @@ -1775,7 +1778,7 @@ and some possible future directions for @command{gawk} development. provides some very cursory background material for those who are completely unfamiliar with computer programming. -The @ref{Glossary}, defines most, if not all of, the significant terms used +The @ref{Glossary}, defines most, if not all, of the significant terms used throughout the @value{DOCUMENT}. If you find terms that you aren't familiar with, try looking them up here. @@ -1818,7 +1821,7 @@ This typically represents the command's standard output. Output from the command, usually its standard output, appears @code{like this}. @end ifset -Error messages, and other output on the command's standard error, are preceded +Error messages and other output on the command's standard error are preceded by the glyph ``@error{}''. For example: @example @@ -1845,7 +1848,7 @@ there are special characters called ``control characters.'' These are characters that you type by holding down both the @kbd{CONTROL} key and another key, at the same time. For example, a @kbd{Ctrl-d} is typed by first pressing and holding the @kbd{CONTROL} key, next -pressing the @kbd{d} key and finally releasing both keys. +pressing the @kbd{d} key, and finally releasing both keys. For the sake of brevity, throughout this @value{DOCUMENT}, we refer to Brian Kernighan's version of @command{awk} as ``BWK @command{awk}.'' @@ -1881,7 +1884,7 @@ the picture of a flashlight in the margin, as shown here. @value{DARKCORNER} @end iftex @ifnottex -``(d.c.)''. +``(d.c.).'' @end ifnottex @ifclear FOR_PRINT They also appear in the index under the heading ``dark corner.'' @@ -1916,12 +1919,12 @@ Emacs editor. GNU Emacs is the most widely used version of Emacs today. @cindex GPL (General Public License) @cindex General Public License, See GPL @cindex documentation, online -The GNU@footnote{GNU stands for ``GNU's not Unix.''} +The GNU@footnote{GNU stands for ``GNU's Not Unix.''} Project is an ongoing effort on the part of the Free Software Foundation to create a complete, freely distributable, POSIX-compliant computing environment. -The FSF uses the ``GNU General Public License'' (GPL) to ensure that -their software's +The FSF uses the GNU General Public License (GPL) to ensure that +its software's source code is always available to the end user. @ifclear FOR_PRINT A copy of the GPL is included @@ -1981,7 +1984,7 @@ version of @command{awk}. I started working with that version in the fall of 1988. As work on it progressed, the FSF published several preliminary versions (numbered 0.@var{x}). -In 1996, Edition 1.0 was released with @command{gawk} 3.0.0. +In 1996, edition 1.0 was released with @command{gawk} 3.0.0. The FSF published the first two editions under the title @cite{The GNU Awk User's Guide}. @ifset FOR_PRINT @@ -1993,7 +1996,7 @@ the third edition in 2001. This edition maintains the basic structure of the previous editions. For FSF edition 4.0, the content was thoroughly reviewed and updated. All references to @command{gawk} versions prior to 4.0 were removed. -Of significant note for that edition was @ref{Debugger}. +Of significant note for that edition was the addition of @ref{Debugger}. For FSF edition @ifclear FOR_PRINT @@ -2008,7 +2011,7 @@ and the major new additions are @ref{Arbitrary Precision Arithmetic}, and @ref{Dynamic Extensions}. This @value{DOCUMENT} will undoubtedly continue to evolve. If you -find an error in this @value{DOCUMENT}, please report it! @DBXREF{Bugs} +find an error in the @value{DOCUMENT}, please report it! @DBXREF{Bugs} for information on submitting problem reports electronically. @ifset FOR_PRINT @@ -2018,7 +2021,7 @@ for information on submitting problem reports electronically. You may have a newer version of @command{gawk} than the one described here. To find out what has changed, you should first look at the @file{NEWS} file in the @command{gawk} -distribution, which provides a high-level summary of what changed in +distribution, which provides a high-level summary of the changes in each release. You can then look at the @uref{http://www.gnu.org/software/gawk/manual/, @@ -2072,7 +2075,7 @@ The initial draft of @cite{The GAWK Manual} had the following acknowledgments: Many people need to be thanked for their assistance in producing this manual. Jay Fenlason contributed many ideas and sample programs. Richard Mlynarik and Robert Chassell gave helpful comments on drafts of this -manual. The paper @cite{A Supplemental Document for @command{awk}} by John W.@: +manual. The paper @cite{A Supplemental Document for AWK} by John W.@: Pierce of the Chemistry Department at UC San Diego, pinpointed several issues relevant both to @command{awk} implementation and to this manual, that would otherwise have escaped us. @@ -2083,12 +2086,18 @@ I would like to acknowledge Richard M.@: Stallman, for his vision of a better world and for his courage in founding the FSF and starting the GNU Project. +@ifclear FOR_PRINT Earlier editions of this @value{DOCUMENT} had the following acknowledgements: +@end ifclear +@ifset FOR_PRINT +The previous edition of this @value{DOCUMENT} had +the following acknowledgements: +@end ifset @quotation The following people (in alphabetical order) provided helpful comments on various -versions of this book, +versions of this book: Rick Adams, Dr.@: Nelson H.F. Beebe, Karl Berry, @@ -2116,7 +2125,7 @@ Robert J.@: Chassell provided much valuable advice on the use of Texinfo. He also deserves special thanks for convincing me @emph{not} to title this @value{DOCUMENT} -@cite{How To Gawk Politely}. +@cite{How to Gawk Politely}. Karl Berry helped significantly with the @TeX{} part of Texinfo. @cindex Hartholz, Marshall @@ -2200,9 +2209,9 @@ a number of people. @DBXREF{Contributors} for the full list. @ifset FOR_PRINT @cindex Oram, Andy -Thanks to Andy Oram, of O'Reilly Media, for initiating +Thanks to Andy Oram of O'Reilly Media for initiating the fourth edition and for his support during the work. -Thanks to Jasmine Kwityn for her copy-editing work. +Thanks to Jasmine Kwityn for her copyediting work. @end ifset Thanks to Michael Brennan for the Forewords. @@ -2210,7 +2219,7 @@ Thanks to Michael Brennan for the Forewords. @cindex Duman, Patrice @cindex Berry, Karl Thanks to Patrice Dumas for the new @command{makeinfo} program. -Thanks to Karl Berry who continues to work to keep +Thanks to Karl Berry, who continues to work to keep the Texinfo markup language sane. @cindex Kernighan, Brian @@ -2220,8 +2229,8 @@ Robert P.J.@: Day, Michael Brennan, and Brian Kernighan kindly acted as reviewers for the 2015 edition of this @value{DOCUMENT}. Their feedback helped improve the final work. -I would like to thank Brian Kernighan for invaluable assistance during the -testing and debugging of @command{gawk}, and for ongoing +I would also like to thank Brian Kernighan for his invaluable assistance during the +testing and debugging of @command{gawk}, and for his ongoing help and advice in clarifying numerous points about the language. We could not have done nearly as good a job on either @command{gawk} or its documentation without his help. @@ -2332,9 +2341,9 @@ an advanced feature that we will ignore for now; pattern to search for and one action to perform upon finding the pattern. -Syntactically, a rule consists of a pattern followed by an action. The -action is enclosed in braces to separate it from the pattern. -Newlines usually separate rules. Therefore, an @command{awk} +Syntactically, a rule consists of a @dfn{pattern} followed by an +@dfn{action}. The action is enclosed in braces to separate it from the +pattern. Newlines usually separate rules. Therefore, an @command{awk} program looks like this: @example @@ -2408,8 +2417,8 @@ awk '@var{program}' @var{input-file1} @var{input-file2} @dots{} @end example @noindent -where @var{program} consists of a series of @var{patterns} and -@var{actions}, as described earlier. +where @var{program} consists of a series of patterns and +actions, as described earlier. @cindex single quote (@code{'}) @cindex @code{'} (single quote) @@ -2428,12 +2437,12 @@ programs from shell scripts, because it avoids the need for a separate file for the @command{awk} program. A self-contained shell script is more reliable because there are no other files to misplace. -Later in this chapter, +Later in this chapter, in @ifdocbook the section @end ifdocbook @ref{Very Simple}, -presents several short, +we'll see examples of several short, self-contained programs. @node Read Terminal @@ -2454,10 +2463,10 @@ awk '@var{program}' which usually means whatever you type on the keyboard. This continues until you indicate end-of-file by typing @kbd{Ctrl-d}. @ifset FOR_PRINT -(On other operating systems, the end-of-file character may be different.) +(On non-POSIX operating systems, the end-of-file character may be different.) @end ifset @ifclear FOR_PRINT -(On other operating systems, the end-of-file character may be different. +(On non-POSIX operating systems, the end-of-file character may be different. For example, on OS/2, it is @kbd{Ctrl-z}.) @end ifclear @@ -2557,11 +2566,9 @@ for programs that are provided on the @command{awk} command line. (Also, placing the program in a file allows us to use a literal single quote in the program text, instead of the magic @samp{\47}.) -@c STARTOFRANGE sq1x @cindex single quote (@code{'}) in @command{gawk} command lines -@c STARTOFRANGE qs2x @cindex @code{'} (single quote) in @command{gawk} command lines -If you want to clearly identify your @command{awk} program files as such, +If you want to clearly identify an @command{awk} program file as such, you can add the extension @file{.awk} to the @value{FN}. This doesn't affect the execution of the @command{awk} program but it does make ``housekeeping'' easier. @@ -2719,7 +2726,7 @@ The next @value{SUBSECTION} describes the shell's quoting rules. @end quotation @node Quoting -@subsection Shell-Quoting Issues +@subsection Shell Quoting Issues @cindex shell quoting, rules for @menu @@ -2856,7 +2863,7 @@ $ @kbd{awk 'BEGIN @{ print "Here is a single quote <'"'"'>" @}'} @noindent This program consists of three concatenated quoted strings. The first and the -third are single quoted, the second is double quoted. +third are single-quoted, and the second is double-quoted. This can be ``simplified'' to: @@ -2877,8 +2884,6 @@ $ @kbd{awk "BEGIN @{ print \"Here is a single quote <'>\" @}"} @end example @noindent -@c ENDOFRANGE sq1x -@c ENDOFRANGE qs2x This option is also painful, because double quotes, backslashes, and dollar signs are very common in more advanced @command{awk} programs. @@ -2895,7 +2900,7 @@ $ @kbd{awk 'BEGIN @{ print "Here is a double quote <\42>" @}'} @end example @noindent -This works nicely, except that you should comment clearly what the +This works nicely, but you should comment clearly what the escapes mean. A fourth option is to use command-line variable assignment, like this: @@ -2906,11 +2911,11 @@ $ @kbd{awk -v sq="'" 'BEGIN @{ print "Here is a single quote <" sq ">" @}'} @end example (Here, the two string constants and the value of @code{sq} are concatenated -into a single string which is printed by @code{print}.) +into a single string that is printed by @code{print}.) If you really need both single and double quotes in your @command{awk} program, it is probably best to move it into a separate file, where -the shell won't be part of the picture, and you can say what you mean. +the shell won't be part of the picture and you can say what you mean. @node DOS Quoting @subsubsection Quoting in MS-Windows Batch Files @@ -3009,7 +3014,7 @@ of green crates shipped, the number of red boxes shipped, the number of orange bags shipped, and the number of blue packages shipped, respectively. There are 16 entries, covering the 12 months of last year and the first four months of the current year. -An empty line separates the data for the two years. +An empty line separates the data for the two years: @example @c file eg/data/inventory-shipped @@ -3043,7 +3048,7 @@ The following command runs a simple @command{awk} program that searches the input file @file{mail-list} for the character string @samp{li} (a grouping of characters is usually called a @dfn{string}; the term @dfn{string} is based on similar usage in English, such -as ``a string of pearls,'' or ``a string of cars in a train''): +as ``a string of pearls'' or ``a string of cars in a train''): @example awk '/li/ @{ print $0 @}' mail-list @@ -3090,7 +3095,7 @@ omitting the @code{print} statement but retaining the braces makes an empty action that does nothing (i.e., no lines are printed). @cindex @command{awk} programs, one-line examples -Many practical @command{awk} programs are just a line or two. Following is a +Many practical @command{awk} programs are just a line or two long. Following is a collection of useful, short programs to get you started. Some of these programs contain constructs that haven't been covered yet. (The description of the program will give you a good idea of what is going on, but you'll @@ -3111,7 +3116,7 @@ Print every line that is longer than 80 characters: awk 'length($0) > 80' data @end example -The sole rule has a relational expression as its pattern and it has no +The sole rule has a relational expression as its pattern and has no action---so it uses the default action, printing the record. @item @@ -3198,7 +3203,7 @@ Print the even-numbered lines in the @value{DF}: awk 'NR % 2 == 0' data @end example -If you use the expression @samp{NR % 2 == 1} instead, +If you used the expression @samp{NR % 2 == 1} instead, the program would print the odd-numbered lines. @end itemize @@ -3214,8 +3219,13 @@ no actions run. After processing all the rules that match the line (and perhaps there are none), @command{awk} reads the next line. (However, -@pxref{Next Statement}, +@DBPXREF{Next Statement} +@ifdocbook +and @DBREF{Nextfile Statement}.) +@end ifdocbook +@ifnotdocbook and also @pxref{Nextfile Statement}.) +@end ifnotdocbook This continues until the program reaches the end of the file. For example, the following @command{awk} program contains two rules: @@ -3480,7 +3490,7 @@ performing bit manipulation, for runtime string translation (internationalizatio determining the type of a variable, and array sorting. -As we develop our presentation of the @command{awk} language, we introduce +As we develop our presentation of the @command{awk} language, we will introduce most of the variables and many of the functions. They are described systematically in @DBREF{Built-in Variables} and in @ref{Built-in}. @@ -3534,7 +3544,7 @@ and Perl.} @c FIXME: Review this chapter for summary of builtin functions called. @itemize @value{BULLET} @item -Programs in @command{awk} consist of @var{pattern}-@var{action} pairs. +Programs in @command{awk} consist of @var{pattern}--@var{action} pairs. @item An @var{action} without a @var{pattern} always runs. The default @@ -3563,7 +3573,7 @@ part of a larger shell script (or MS-Windows batch file). You may use backslash continuation to continue a source line. Lines are automatically continued after a comma, open brace, question mark, colon, -@samp{||}, @samp{&&}, @code{do} and @code{else}. +@samp{||}, @samp{&&}, @code{do}, and @code{else}. @end itemize @node Invoking Gawk @@ -3638,20 +3648,16 @@ warning that the program is empty. @node Options @section Command-Line Options -@c STARTOFRANGE ocl @cindex options, command-line -@c STARTOFRANGE clo @cindex command line, options -@c STARTOFRANGE gnulo @cindex GNU long options -@c STARTOFRANGE longo @cindex options, long Options begin with a dash and consist of a single character. GNU-style long options consist of two dashes and a keyword. The keyword can be abbreviated, as long as the abbreviation allows the option -to be uniquely identified. If the option takes an argument, then the -keyword is either immediately followed by an equals sign (@samp{=}) and the +to be uniquely identified. If the option takes an argument, either the +keyword is immediately followed by an equals sign (@samp{=}) and the argument's value, or the keyword and the argument's value are separated by whitespace. If a particular option with a value is given more than once, it is the @@ -3678,7 +3684,7 @@ Set the @code{FS} variable to @var{fs} @cindex @option{-f} option @cindex @option{--file} option @cindex @command{awk} programs, location of -Read @command{awk} program source from @var{source-file} +Read the @command{awk} program source from @var{source-file} instead of in the first nonoption argument. This option may be given multiple times; the @command{awk} program consists of the concatenation of the contents of @@ -3733,8 +3739,6 @@ by the user that could start with @samp{-}. It is also useful for passing options on to the @command{awk} program; see @ref{Getopt Function}. @end table -@c ENDOFRANGE gnulo -@c ENDOFRANGE longo The following list describes @command{gawk}-specific options: @@ -3746,14 +3750,14 @@ The following list describes @command{gawk}-specific options: @cindex @option{--characters-as-bytes} option Cause @command{gawk} to treat all input data as single-byte characters. In addition, all output written with @code{print} or @code{printf} -are treated as single-byte characters. +is treated as single-byte characters. Normally, @command{gawk} follows the POSIX standard and attempts to process its input data according to the current locale (@pxref{Locales}). This can often involve converting multibyte characters into wide characters (internally), and can lead to problems or confusion if the input data does not contain valid -multibyte characters. This option is an easy way to tell @command{gawk}: -``hands off my data!''. +multibyte characters. This option is an easy way to tell @command{gawk}, +``Hands off my data!'' @item @option{-c} @itemx @option{--traditional} @@ -3810,7 +3814,7 @@ Enable debugging of @command{awk} programs By default, the debugger reads commands interactively from the keyboard (standard input). The optional @var{file} argument allows you to specify a file with a list -of commands for the debugger to execute non-interactively. +of commands for the debugger to execute noninteractively. No space is allowed between the @option{-D} and @var{file}, if @var{file} is supplied. @@ -3870,7 +3874,7 @@ with @samp{#!} scripts (@pxref{Executable Scripts}), like so: @cindex portable object files, generating @cindex files, portable object, generating Analyze the source program and -generate a GNU @command{gettext} Portable Object Template file on standard +generate a GNU @command{gettext} portable object template file on standard output for all string constants that have been marked for translation. @xref{Internationalization}, for information about this option. @@ -3882,7 +3886,7 @@ for information about this option. @cindex GNU long options, printing list of @cindex options, printing list of @cindex printing, list of options -Print a ``usage'' message summarizing the short and long style options +Print a ``usage'' message summarizing the short- and long-style options that @command{gawk} accepts and then exit. @item @option{-i} @var{source-file} @@ -3892,7 +3896,7 @@ that @command{gawk} accepts and then exit. @cindex @command{awk} programs, location of Read an @command{awk} source library from @var{source-file}. This option is completely equivalent to using the @code{@@include} directive inside -your program. This option is very similar to the @option{-f} option, +your program. It is very similar to the @option{-f} option, but there are two important differences. First, when @option{-i} is used, the program source is not loaded if it has been previously loaded, whereas with @option{-f}, @command{gawk} always loads the file. @@ -3977,7 +3981,7 @@ when parsing numeric input data (@pxref{Locales}). @cindex @option{-o} option @cindex @option{--pretty-print} option Enable pretty-printing of @command{awk} programs. -By default, output program is created in a file named @file{awkprof.out} +By default, the output program is created in a file named @file{awkprof.out} (@pxref{Profiling}). The optional @var{file} argument allows you to specify a different @value{FN} for the output. @@ -4021,7 +4025,7 @@ in the left margin, and function call counts for each function. Operate in strict POSIX mode. This disables all @command{gawk} extensions (just like @option{--traditional}) and disables all extensions not allowed by POSIX. -@xref{Common Extensions}, for a summary of the extensions +@DBXREF{Common Extensions} for a summary of the extensions in @command{gawk} that are disabled by this option. Also, the following additional @@ -4142,7 +4146,7 @@ source of data.) Because it is clumsy using the standard @command{awk} mechanisms to mix source file and command-line @command{awk} programs, @command{gawk} provides the @option{-e} option. This does not require you to -pre-empt the standard input for your source code; it allows you to easily +preempt the standard input for your source code; it allows you to easily mix command-line and library source code (@pxref{AWKPATH Variable}). As with @option{-f}, the @option{-e} and @option{-i} options may also be used multiple times on the command line. @@ -4188,8 +4192,6 @@ setenv POSIXLY_CORRECT true Having @env{POSIXLY_CORRECT} set is not recommended for daily use, but it is good for testing the portability of your programs to other environments. -@c ENDOFRANGE ocl -@c ENDOFRANGE clo @node Other Arguments @section Other Command-Line Arguments @@ -4332,7 +4334,7 @@ file, unless the file is in the current directory. But with @command{gawk}, if the @value{FN} supplied to the @option{-f} or @option{-i} options does not contain a directory separator @samp{/}, then @command{gawk} searches a list of -directories (called the @dfn{search path}), one by one, looking for a +directories (called the @dfn{search path}) one by one, looking for a file with the specified name. The search path is a string consisting of directory names @@ -4373,9 +4375,9 @@ as an entry in the path or write a null entry in the path. Different past versions of @command{gawk} would also look explicitly in the current directory, either before or after the path search. As of -@value{PVERSION} 4.1.2, this no longer happens, and if you wish to look +@value{PVERSION} 4.1.2, this no longer happens; if you wish to look in the current directory, you must include @file{.} either as a separate -entry, or as a null entry in the search path. +entry or as a null entry in the search path. @end quotation The default value for @env{AWKPATH} is @@ -4491,7 +4493,7 @@ If this variable exists, @command{gawk} includes the @value{FN} and line number within the @command{gawk} source code from which warning and/or fatal messages are generated. Its purpose is to help isolate the source of a -message, as there are multiple places which produce the +message, as there are multiple places that produce the same warning or error message. @item GAWK_NO_DFA @@ -4507,16 +4509,16 @@ This specifies the amount by which @command{gawk} should grow its internal evaluation stack, when needed. @item INT_CHAIN_MAX -The intended maximum number of items @command{gawk} will maintain on a +This specifies intended maximum number of items @command{gawk} will maintain on a hash chain for managing arrays indexed by integers. @item STR_CHAIN_MAX -The intended maximum number of items @command{gawk} will maintain on a +This specifies intended maximum number of items @command{gawk} will maintain on a hash chain for managing arrays indexed by strings. @item TIDYMEM If this variable exists, @command{gawk} uses the @code{mtrace()} library -calls from GNU LIBC to help track down possible memory leaks. +calls from the GNU C library to help track down possible memory leaks. @end table @node Exit Status @@ -4553,7 +4555,7 @@ The @code{@@include} keyword can be used to read external @command{awk} source files. This gives you the ability to split large @command{awk} source files into smaller, more manageable pieces, and also lets you reuse common @command{awk} code from various @command{awk} scripts. In other words, you can group -together @command{awk} functions, used to carry out specific tasks, +together @command{awk} functions used to carry out specific tasks into external files. These files can be used just like function libraries, using the @code{@@include} keyword in conjunction with the @env{AWKPATH} environment variable. Note that source files may also be included @@ -4588,7 +4590,7 @@ $ @kbd{gawk -f test2} @print{} This is script test2. @end example -@code{gawk} runs the @file{test2} script, which includes @file{test1} +@command{gawk} runs the @file{test2} script, which includes @file{test1} using the @code{@@include} keyword. So, to include external @command{awk} source files, you just use @code{@@include} followed by the name of the file to be included, @@ -4643,11 +4645,12 @@ of the @env{AWKPATH} variable in command-line file searches This is very helpful in constructing @command{gawk} function libraries. If you have a large script with useful, general-purpose @command{awk} functions, you can break it down into library files and put those files -in a special directory. You can then include those ``libraries,'' using -either the full pathnames of the files, or by setting the @env{AWKPATH} +in a special directory. You can then include those ``libraries,'' +either by using the full pathnames of the files, or by setting the @env{AWKPATH} environment variable accordingly and then using @code{@@include} with -just the file part of the full pathname. Of course, you can have more -than one directory to keep library files; the more complex the working +just the file part of the full pathname. Of course, +you can keep library files in more than one directory; +the more complex the working environment is, the more directories you may need to organize the files to be included. @@ -4660,8 +4663,8 @@ In particular, @code{@@include} is very useful for writing CGI scripts to be run from web pages. As mentioned in @ref{AWKPATH Variable}, the current directory is always -searched first for source files, before searching in @env{AWKPATH}, -and this also applies to files named with @code{@@include}. +searched first for source files, before searching in @env{AWKPATH}; +this also applies to files named with @code{@@include}. @node Loading Shared Libraries @section Loading Dynamic Extensions into Your Program @@ -4715,8 +4718,8 @@ It also describes the @code{ordchr} extension. @cindex features, deprecated @cindex obsolete features This @value{SECTION} describes features and/or command-line options from -previous releases of @command{gawk} that are either not available in the -current version or that are still supported but deprecated (meaning that +previous releases of @command{gawk} that either are not available in the +current version or are still supported but deprecated (meaning that they will @emph{not} be in the next release). The process-related special files @file{/dev/pid}, @file{/dev/ppid}, @@ -4796,7 +4799,7 @@ This seems to have been a long-undocumented feature in Unix @command{awk}. Similarly, you may use @code{print} or @code{printf} statements in the @var{init} and @var{increment} parts of a @code{for} loop. This is another -long-undocumented ``feature'' of Unix @code{awk}. +long-undocumented ``feature'' of Unix @command{awk}. @end ignore @@ -4813,7 +4816,7 @@ to run @command{awk}. @item The three standard options for all versions of @command{awk} are -@option{-f}, @option{-F} and @option{-v}. @command{gawk} supplies these +@option{-f}, @option{-F}, and @option{-v}. @command{gawk} supplies these and many others, as well as corresponding GNU-style long options. @item @@ -4850,13 +4853,12 @@ and @option{-f} command-line options. @item @command{gawk} allows you to load additional functions written in C or C++ using the @code{@@load} statement and/or the @option{-l} option. -(This advanced feature is described later on in @ref{Dynamic Extensions}.) +(This advanced feature is described later, in @ref{Dynamic Extensions}.) @end itemize @node Regexp @chapter Regular Expressions @cindex regexp -@c STARTOFRANGE regexp @cindex regular expressions A @dfn{regular expression}, or @dfn{regexp}, is a way of describing a @@ -5063,7 +5065,7 @@ Horizontal TAB, @kbd{Ctrl-i}, ASCII code 9 (HT). @cindex @code{\} (backslash), @code{\v} escape sequence @cindex backslash (@code{\}), @code{\v} escape sequence @item \v -Vertical tab, @kbd{Ctrl-k}, ASCII code 11 (VT). +Vertical TAB, @kbd{Ctrl-k}, ASCII code 11 (VT). @cindex @code{\} (backslash), @code{\}@var{nnn} escape sequence @cindex backslash (@code{\}), @code{\}@var{nnn} escape sequence @@ -5137,7 +5139,7 @@ characters @samp{a+b}. @cindex @code{\} (backslash), in escape sequences @cindex portability For complete portability, do not use a backslash before any character not -shown in the previous list and that is not an operator. +shown in the previous list or that is not an operator. @c 11/2014: Moved so as to not stack sidebars @sidebar Backslash Before Regular Characters @@ -5216,7 +5218,6 @@ escape sequences literally when used in regexp constants. Thus, @node Regexp Operators @section Regular Expression Operators -@c STARTOFRANGE regexpo @cindex regular expressions, operators @cindex metacharacters in regular expressions @@ -5234,7 +5235,7 @@ are recognized and converted into corresponding real characters as the very first step in processing regexps. Here is a list of metacharacters. All characters that are not escape -sequences and that are not listed in the following stand for themselves: +sequences and that are not listed here stand for themselves: @c Use @asis so the docbook comes out ok. Sigh. @table @asis @@ -5357,7 +5358,7 @@ just @samp{p} if no @samp{h}s are present. There are two subtle points to understand about how @samp{*} works. First, the @samp{*} applies only to the single preceding regular expression component (e.g., in @samp{ph*}, it applies just to the @samp{h}). -To cause @samp{*} to apply to a larger sub-expression, use parentheses: +To cause @samp{*} to apply to a larger subexpression, use parentheses: @samp{(ph)*} matches @samp{ph}, @samp{phph}, @samp{phphph}, and so on. Second, @samp{*} finds as many repetitions as possible. If the text @@ -5396,10 +5397,10 @@ is repeated at least @var{n} times: Matches @samp{whhhy}, but not @samp{why} or @samp{whhhhy}. @item wh@{3,5@}y -Matches @samp{whhhy}, @samp{whhhhy}, or @samp{whhhhhy}, only. +Matches @samp{whhhy}, @samp{whhhhy}, or @samp{whhhhhy} only. @item wh@{2,@}y -Matches @samp{whhy} or @samp{whhhy}, and so on. +Matches @samp{whhy}, @samp{whhhy}, and so on. @end table @cindex POSIX @command{awk}, interval expressions in @@ -5448,11 +5449,9 @@ usage as a syntax error. If @command{gawk} is in compatibility mode (@pxref{Options}), interval expressions are not available in regular expressions. -@c ENDOFRANGE regexpo @node Bracket Expressions @section Using Bracket Expressions -@c STARTOFRANGE charlist @cindex bracket expressions @cindex bracket expressions, range expressions @cindex range expressions (regexps) @@ -5528,7 +5527,7 @@ POSIX standard. (a space is printable but not visible, whereas an @samp{a} is both) @item @code{[:lower:]} @tab Lowercase alphabetic characters @item @code{[:print:]} @tab Printable characters (characters that are not control characters) -@item @code{[:punct:]} @tab Punctuation characters (characters that are not letters, digits +@item @code{[:punct:]} @tab Punctuation characters (characters that are not letters, digits, control characters, or space characters) @item @code{[:space:]} @tab Space characters (such as space, TAB, and formfeed, to name a few) @item @code{[:upper:]} @tab Uppercase alphabetic characters @@ -5548,11 +5547,11 @@ and numeric characters in your character set. @c Date: Tue, 01 Jul 2014 07:39:51 +0200 @c From: Hermann Peifer <peifer@gmx.eu> Some utilities that match regular expressions provide a nonstandard -@code{[:ascii:]} character class; @command{awk} does not. However, you -can simulate such a construct using @code{[\x00-\x7F]}. This matches +@samp{[:ascii:]} character class; @command{awk} does not. However, you +can simulate such a construct using @samp{[\x00-\x7F]}. This matches all values numerically between zero and 127, which is the defined range of the ASCII character set. Use a complemented character list -(@code{[^\x00-\x7F]}) to match any single-byte characters that are not +(@samp{[^\x00-\x7F]}) to match any single-byte characters that are not in the ASCII range. @cindex bracket expressions, collating elements @@ -5581,8 +5580,8 @@ Locale-specific names for a list of characters that are equal. The name is enclosed between @samp{[=} and @samp{=]}. For example, the name @samp{e} might be used to represent all of -``e,'' ``@`e,'' and ``@'e.'' In this case, @samp{[[=e=]]} is a regexp -that matches any of @samp{e}, @samp{@'e}, or @samp{@`e}. +``e,'' ``@^e,'' ``@`e,'' and ``@'e.'' In this case, @samp{[[=e=]]} is a regexp +that matches any of @samp{e}, @samp{@^e}, @samp{@'e}, or @samp{@`e}. @end table These features are very valuable in non-English-speaking locales. @@ -5596,7 +5595,6 @@ expression matching currently recognize only POSIX character classes; they do not recognize collating symbols or equivalence classes. @end quotation @c maybe one day ... -@c ENDOFRANGE charlist @node Leftmost Longest @section How Much Text Matches? @@ -5612,7 +5610,7 @@ echo aaaabcd | awk '@{ sub(/a+/, "<A>"); print @}' This example uses the @code{sub()} function to make a change to the input record. (@code{sub()} replaces the first instance of any text matched by the first argument with the string provided as the second argument; -@pxref{String Functions}). Here, the regexp @code{/a+/} indicates ``one +@pxref{String Functions}.) Here, the regexp @code{/a+/} indicates ``one or more @samp{a} characters,'' and the replacement text is @samp{<A>}. The input contains four @samp{a} characters. @@ -5640,9 +5638,7 @@ and also @pxref{Field Separators}). @node Computed Regexps @section Using Dynamic Regexps -@c STARTOFRANGE dregexp @cindex regular expressions, computed -@c STARTOFRANGE regexpd @cindex regular expressions, dynamic @cindex @code{~} (tilde), @code{~} operator @cindex tilde (@code{~}), @code{~} operator @@ -5668,14 +5664,14 @@ and tests whether the input record matches this regexp. @quotation NOTE When using the @samp{~} and @samp{!~} -operators, there is a difference between a regexp constant +operators, be aware that there is a difference between a regexp constant enclosed in slashes and a string constant enclosed in double quotes. If you are going to use a string constant, you have to understand that the string is, in essence, scanned @emph{twice}: the first time when @command{awk} reads your program, and the second time when it goes to match the string on the lefthand side of the operator with the pattern on the right. This is true of any string-valued expression (such as -@code{digits_regexp}, shown previously), not just string constants. +@code{digits_regexp}, shown in the previous example), not just string constants. @end quotation @cindex regexp constants, slashes vs.@: quotes @@ -5749,17 +5745,13 @@ $ @kbd{awk '$0 ~ /[ \t\n]/'} @command{gawk} does not have this problem, and it isn't likely to occur often in practice, but it's worth noting for future reference. @end sidebar -@c ENDOFRANGE dregexp -@c ENDOFRANGE regexpd @node GNU Regexp Operators @section @command{gawk}-Specific Regexp Operators @c This section adapted (long ago) from the regex-0.12 manual -@c STARTOFRANGE regexpg @cindex regular expressions, operators, @command{gawk} -@c STARTOFRANGE gregexp @cindex @command{gawk}, regular expressions, operators @cindex operators, GNU-specific @cindex regular expressions, operators, for words @@ -5835,7 +5827,7 @@ matches either @samp{ball} or @samp{balls}, as a separate word. @item \B Matches the empty string that occurs between two word-constituent characters. For example, -@code{/\Brat\B/} matches @samp{crate} but it does not match @samp{dirty rat}. +@code{/\Brat\B/} matches @samp{crate}, but it does not match @samp{dirty rat}. @samp{\B} is essentially the opposite of @samp{\y}. @end table @@ -5854,14 +5846,14 @@ The operators are: @cindex backslash (@code{\}), @code{\`} operator (@command{gawk}) @cindex @code{\} (backslash), @code{\`} operator (@command{gawk}) Matches the empty string at the -beginning of a buffer (string). +beginning of a buffer (string) @c @cindex operators, @code{\'} (@command{gawk}) @cindex backslash (@code{\}), @code{\'} operator (@command{gawk}) @cindex @code{\} (backslash), @code{\'} operator (@command{gawk}) @item \' Matches the empty string at the -end of a buffer (string). +end of a buffer (string) @end table @cindex @code{^} (caret), regexp operator @@ -5924,15 +5916,11 @@ Allow interval expressions in regexps, if @option{--traditional} has been provided. Otherwise, interval expressions are available by default. @end table -@c ENDOFRANGE gregexp -@c ENDOFRANGE regexpg @node Case-sensitivity @section Case Sensitivity in Matching -@c STARTOFRANGE regexpcs @cindex regular expressions, case sensitivity -@c STARTOFRANGE csregexp @cindex case sensitivity, regexps and Case is normally significant in regular expressions, both when matching ordinary characters (i.e., not metacharacters) and inside bracket @@ -6024,8 +6012,6 @@ the right thing.} The value of @code{IGNORECASE} has no effect if @command{gawk} is in compatibility mode (@pxref{Options}). Case is always significant in compatibility mode. -@c ENDOFRANGE csregexp -@c ENDOFRANGE regexpcs @node Regexp Summary @section Summary @@ -6072,12 +6058,10 @@ versions, use @code{tolower()} or @code{toupper()}. @end itemize -@c ENDOFRANGE regexp @node Reading Files @chapter Reading Input Files -@c STARTOFRANGE infir @cindex reading input files @cindex input files, reading @cindex input files @@ -6102,7 +6086,7 @@ This makes it more convenient for programs to work on the parts of a record. @cindex @code{getline} command On rare occasions, you may need to use the @code{getline} command. -The @code{getline} command is valuable, both because it +The @code{getline} command is valuable both because it can do explicit input from any number of files, and because the files used with it do not have to be named on the @command{awk} command line (@pxref{Getline}). @@ -6128,9 +6112,7 @@ used with it do not have to be named on the @command{awk} command line @node Records @section How Input Is Split into Records -@c STARTOFRANGE inspl @cindex input, splitting into records -@c STARTOFRANGE recspl @cindex records, splitting input into @cindex @code{NR} variable @cindex @code{FNR} variable @@ -6155,8 +6137,8 @@ never automatically reset to zero. Records are separated by a character called the @dfn{record separator}. By default, the record separator is the newline character. This is why records are, by default, single lines. -A different character can be used for the record separator by -assigning the character to the predefined variable @code{RS}. +To use a different character for the record separator, +simply assign that character to the predefined variable @code{RS}. @cindex newlines, as record separators @cindex @code{RS} variable @@ -6179,8 +6161,8 @@ awk 'BEGIN @{ RS = "u" @} @noindent changes the value of @code{RS} to @samp{u}, before reading any input. -This is a string whose first character is the letter ``u''; as a result, records -are separated by the letter ``u.'' Then the input file is read, and the second +The new value is a string whose first character is the letter ``u''; as a result, records +are separated by the letter ``u''. Then the input file is read, and the second rule in the @command{awk} program (the action with no pattern) prints each record. Because each @code{print} statement adds a newline at the end of its output, this @command{awk} program copies the input @@ -6241,8 +6223,8 @@ Bill 555-1675 bill.drowning@@hotmail.com A @end example @noindent -It contains no @samp{u} so there is no reason to split the record, -unlike the others which have one or more occurrences of the @samp{u}. +It contains no @samp{u}, so there is no reason to split the record, +unlike the others, which each have one or more occurrences of the @samp{u}. In fact, this record is treated as part of the previous record; the newline separating them in the output is the original newline in the @value{DF}, not the one added by @@ -6337,7 +6319,7 @@ contains the same single character. However, when @code{RS} is a regular expression, @code{RT} contains the actual input text that matched the regular expression. -If the input file ended without any text that matches @code{RS}, +If the input file ends without any text matching @code{RS}, @command{gawk} sets @code{RT} to the null string. The following example illustrates both of these features. @@ -6430,8 +6412,6 @@ character as a record separator. However, this is a special case: whole files. If you are using @command{gawk}, see @DBREF{Extension Sample Readfile} for another option. @end sidebar -@c ENDOFRANGE inspl -@c ENDOFRANGE recspl @node Fields @section Examining Fields @@ -6439,7 +6419,6 @@ Readfile} for another option. @cindex examining fields @cindex fields @cindex accessing fields -@c STARTOFRANGE fiex @cindex fields, examining @cindex POSIX @command{awk}, field separators and @cindex field separators, POSIX and @@ -6464,11 +6443,11 @@ simple @command{awk} programs so powerful. @cindex @code{$} (dollar sign), @code{$} field operator @cindex dollar sign (@code{$}), @code{$} field operator @cindex field operators@comma{} dollar sign as -You use a dollar-sign (@samp{$}) +You use a dollar sign (@samp{$}) to refer to a field in an @command{awk} program, followed by the number of the field you want. Thus, @code{$1} refers to the first field, @code{$2} to the second, and so on. -(Unlike the Unix shells, the field numbers are not limited to single digits. +(Unlike in the Unix shells, the field numbers are not limited to single digits. @code{$127} is the 127th field in the record.) For example, suppose the following is a line of input: @@ -6494,7 +6473,7 @@ If you try to reference a field beyond the last one (such as @code{$8} when the record has only seven fields), you get the empty string. (If used in a numeric operation, you get zero.) -The use of @code{$0}, which looks like a reference to the ``zero-th'' field, is +The use of @code{$0}, which looks like a reference to the ``zeroth'' field, is a special case: it represents the whole input record. Use it when you are not interested in specific fields. Here are some more examples: @@ -6520,7 +6499,6 @@ $ @kbd{awk '/li/ @{ print $1, $NF @}' mail-list} @print{} Julie F @print{} Samuel A @end example -@c ENDOFRANGE fiex @node Nonconstant Fields @section Nonconstant Field Numbers @@ -6550,13 +6528,13 @@ awk '@{ print $(2*2) @}' mail-list @end example @command{awk} evaluates the expression @samp{(2*2)} and uses -its value as the number of the field to print. The @samp{*} sign +its value as the number of the field to print. The @samp{*} represents multiplication, so the expression @samp{2*2} evaluates to four. The parentheses are used so that the multiplication is done before the @samp{$} operation; they are necessary whenever there is a binary operator@footnote{A @dfn{binary operator}, such as @samp{*} for multiplication, is one that takes two operands. The distinction -is required, because @command{awk} also has unary (one-operand) +is required because @command{awk} also has unary (one-operand) and ternary (three-operand) operators.} in the field-number expression. This example, then, prints the type of relationship (the fourth field) for every line of the file @@ -6581,7 +6559,6 @@ evaluating @code{NF} and using its value as a field number. @node Changing Fields @section Changing the Contents of a Field -@c STARTOFRANGE ficon @cindex fields, changing contents of The contents of a field, as seen by @command{awk}, can be changed within an @command{awk} program; this changes what @command{awk} perceives as the @@ -6737,7 +6714,7 @@ rebuild @code{$0} when @code{NF} is decremented. Finally, there are times when it is convenient to force @command{awk} to rebuild the entire record, using the current -value of the fields and @code{OFS}. To do this, use the +values of the fields and @code{OFS}. To do this, use the seemingly innocuous assignment: @example @@ -6761,7 +6738,7 @@ such as @code{sub()} and @code{gsub()} It is important to remember that @code{$0} is the @emph{full} record, exactly as it was read from the input. This includes any leading or trailing whitespace, and the exact whitespace (or other -characters) that separate the fields. +characters) that separates the fields. It is a common error to try to change the field separators in a record simply by setting @code{FS} and @code{OFS}, and then @@ -6773,7 +6750,6 @@ itself. Instead, you must force the record to be rebuilt, typically with a statement such as @samp{$1 = $1}, as described earlier. @end sidebar -@c ENDOFRANGE ficon @node Field Separators @section Specifying How Fields Are Separated @@ -6789,9 +6765,7 @@ with a statement such as @samp{$1 = $1}, as described earlier. @cindex @code{FS} variable @cindex fields, separating -@c STARTOFRANGE fisepr @cindex field separators -@c STARTOFRANGE fisepg @cindex fields, separating The @dfn{field separator}, which is either a single character or a regular expression, controls the way @command{awk} splits an input record into fields. @@ -6857,7 +6831,7 @@ John Q. Smith, LXIX, 29 Oak St., Walamazoo, MI 42139 @end example @noindent -The same program would extract @samp{@bullet{}LXIX}, instead of +The same program would extract @samp{@bullet{}LXIX} instead of @samp{@bullet{}29@bullet{}Oak@bullet{}St.}. If you were expecting the program to print the address, you would be surprised. The moral is to choose your data layout and @@ -6891,9 +6865,7 @@ rules. @node Regexp Field Splitting @subsection Using Regular Expressions to Separate Fields -@c STARTOFRANGE regexpfs @cindex regular expressions, as field separators -@c STARTOFRANGE fsregexp @cindex field separators, regular expressions as The previous @value{SUBSECTION} discussed the use of single characters or simple strings as the @@ -6997,8 +6969,6 @@ $ @kbd{echo 'xxAA xxBxx C' |} @print{} -->xxBxx<-- @print{} -->C<-- @end example -@c ENDOFRANGE regexpfs -@c ENDOFRANGE fsregexp @node Single Character Fields @subsection Making Each Character a Separate Field @@ -7122,7 +7092,7 @@ choosing your field and record separators. @cindex Unix @command{awk}, password files@comma{} field separators and Perhaps the most common use of a single character as the field separator occurs when processing the Unix system password file. On many Unix -systems, each user has a separate entry in the system password file, one +systems, each user has a separate entry in the system password file, with one line per user. The information in these lines is separated by colons. The first field is the user's login name and the second is the user's encrypted or shadow password. (A shadow password is indicated by the @@ -7163,7 +7133,7 @@ When you do this, @code{$1} is the same as @code{$0}. According to the POSIX standard, @command{awk} is supposed to behave as if each record is split into fields at the time it is read. In particular, this means that if you change the value of @code{FS} -after a record is read, the value of the fields (i.e., how they were split) +after a record is read, the values of the fields (i.e., how they were split) should reflect the old value of @code{FS}, not the new one. @cindex dark corner, field separators @@ -7176,10 +7146,7 @@ using the @emph{current} value of @code{FS}! @value{DARKCORNER} This behavior can be difficult to diagnose. The following example illustrates the difference -between the two methods. -(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' -Its behavior is also defined by the POSIX standard.} -command prints just the first line of @file{/etc/passwd}.) +between the two methods: @example sed 1q /etc/passwd | awk '@{ FS = ":" ; print $1 @}' @@ -7199,6 +7166,10 @@ prints the full first line of the file, something like: @example root:x:0:0:Root:/: @end example + +(The @command{sed}@footnote{The @command{sed} utility is a ``stream editor.'' +Its behavior is also defined by the POSIX standard.} +command prints just the first line of @file{/etc/passwd}.) @end sidebar @node Field Splitting Summary @@ -7259,8 +7230,6 @@ do it for you (e.g., @samp{FS = "[c]"}). In this case, @code{IGNORECASE} will take effect. @end sidebar -@c ENDOFRANGE fisepr -@c ENDOFRANGE fisepg @node Constant Size @section Reading Fixed-Width Data @@ -7375,7 +7344,7 @@ In order to tell which kind of field splitting is in effect, use @code{PROCINFO["FS"]} (@pxref{Auto-set}). The value is @code{"FS"} if regular field splitting is being used, -or it is @code{"FIELDWIDTHS"} if fixed-width field splitting is being used: +or @code{"FIELDWIDTHS"} if fixed-width field splitting is being used: @example if (PROCINFO["FS"] == "FS") @@ -7411,14 +7380,14 @@ what they are, and not by what they are not. The most notorious such case is so-called @dfn{comma-separated values} (CSV) data. Many spreadsheet programs, for example, can export their data into text files, where each record is -terminated with a newline, and fields are separated by commas. If only -commas separated the data, there wouldn't be an issue. The problem comes when +terminated with a newline, and fields are separated by commas. If +commas only separated the data, there wouldn't be an issue. The problem comes when one of the fields contains an @emph{embedded} comma. In such cases, most programs embed the field in double quotes.@footnote{The CSV format lacked a formal standard definition for many years. @uref{http://www.ietf.org/rfc/rfc4180.txt, RFC 4180} standardizes the most common practices.} -So we might have data like this: +So, we might have data like this: @example @c file eg/misc/addresses.csv @@ -7504,8 +7473,8 @@ of cases, and the @command{gawk} developers are satisfied with that. @end quotation As written, the regexp used for @code{FPAT} requires that each field -have a least one character. A straightforward modification -(changing changed the first @samp{+} to @samp{*}) allows fields to be empty: +contain at least one character. A straightforward modification +(changing the first @samp{+} to @samp{*}) allows fields to be empty: @example FPAT = "([^,]*)|(\"[^\"]+\")" @@ -7515,20 +7484,17 @@ Finally, the @code{patsplit()} function makes the same functionality available for splitting regular strings (@pxref{String Functions}). To recap, @command{gawk} provides three independent methods -to split input records into fields. @command{gawk} uses whichever -mechanism was last chosen based on which of the three -variables---@code{FS}, @code{FIELDWIDTHS}, and @code{FPAT}---was +to split input records into fields. +The mechanism used is based on which of the three +variables---@code{FS}, @code{FIELDWIDTHS}, or @code{FPAT}---was last assigned to. @node Multiple Line @section Multiple-Line Records @cindex multiple-line records -@c STARTOFRANGE recm @cindex records, multiline -@c STARTOFRANGE imr @cindex input, multiline records -@c STARTOFRANGE frm @cindex files, reading, multiline records @cindex input, files, See input files In some databases, a single line cannot conveniently hold all the @@ -7563,7 +7529,7 @@ at the end of the record and one or more blank lines after the record. In addition, a regular expression always matches the longest possible sequence when there is a choice (@pxref{Leftmost Longest}). -So the next record doesn't start until +So, the next record doesn't start until the first nonblank line that follows---no matter how many blank lines appear in a row, they are considered one record separator. @@ -7578,10 +7544,10 @@ In the second case, this special processing is not done. @cindex field separator, in multiline records @cindex @code{FS}, in multiline records Now that the input is separated into records, the second step is to -separate the fields in the record. One way to do this is to divide each +separate the fields in the records. One way to do this is to divide each of the lines into fields in the normal manner. This happens by default as the result of a special feature. When @code{RS} is set to the empty -string, @emph{and} @code{FS} is set to a single character, +string @emph{and} @code{FS} is set to a single character, the newline character @emph{always} acts as a field separator. This is in addition to whatever field separations result from @code{FS}.@footnote{When @code{FS} is the null string (@code{""}) @@ -7596,7 +7562,7 @@ want the newline character to separate fields, because there is no way to prevent it. However, you can work around this by using the @code{split()} function to break up the record manually (@pxref{String Functions}). -If you have a single character field separator, you can work around +If you have a single-character field separator, you can work around the special feature in a different way, by making @code{FS} into a regexp for that single character. For example, if the field separator is a percent character, instead of @@ -7604,10 +7570,10 @@ separator is a percent character, instead of Another way to separate fields is to put each field on a separate line: to do this, just set the -variable @code{FS} to the string @code{"\n"}. (This single -character separator matches a single newline.) +variable @code{FS} to the string @code{"\n"}. +(This single-character separator matches a single newline.) A practical example of a @value{DF} organized this way might be a mailing -list, where each entry is separated by blank lines. Consider a mailing +list, where blank lines separate the entries. Consider a mailing list in a file named @file{addresses}, which looks like this: @example @@ -7695,20 +7661,15 @@ If not in compatibility mode (@pxref{Options}), @command{gawk} sets @code{RT} to the input text that matched the value specified by @code{RS}. But if the input file ended without any text that matches @code{RS}, then @command{gawk} sets @code{RT} to the null string. -@c ENDOFRANGE recm -@c ENDOFRANGE imr -@c ENDOFRANGE frm @node Getline @section Explicit Input with @code{getline} -@c STARTOFRANGE getl @cindex @code{getline} command, explicit input with -@c STARTOFRANGE inex @cindex input, explicit So far we have been getting our input data from @command{awk}'s main input stream---either the standard input (usually your keyboard, sometimes -the output from another program) or from the +the output from another program) or the files specified on the command line. The @command{awk} language has a special built-in command called @code{getline} that can be used to read input under your explicit control. @@ -7892,7 +7853,7 @@ free @end example The @code{getline} command used in this way sets only the variables -@code{NR}, @code{FNR}, and @code{RT} (and of course, @var{var}). +@code{NR}, @code{FNR}, and @code{RT} (and, of course, @var{var}). The record is not split into fields, so the values of the fields (including @code{$0}) and the value of @code{NF} do not change. @@ -7907,7 +7868,7 @@ the value of @code{NF} do not change. @cindex left angle bracket (@code{<}), @code{<} operator (I/O) @cindex operators, input/output Use @samp{getline < @var{file}} to read the next record from @var{file}. -Here @var{file} is a string-valued expression that +Here, @var{file} is a string-valued expression that specifies the @value{FN}. @samp{< @var{file}} is called a @dfn{redirection} because it directs input to come from a different place. For example, the following @@ -8085,7 +8046,7 @@ of a construct like @samp{@w{"echo "} "date" | getline}. Most versions, including the current version, treat it at as @samp{@w{("echo "} "date") | getline}. (This is also how BWK @command{awk} behaves.) -Some versions changed and treated it as +Some versions instead treat it as @samp{@w{"echo "} ("date" | getline)}. (This is how @command{mawk} behaves.) In short, @emph{always} use explicit parentheses, and then you won't @@ -8133,7 +8094,7 @@ program to be portable to other @command{awk} implementations. @cindex operators, input/output @cindex differences in @command{awk} and @command{gawk}, input/output operators -Input into @code{getline} from a pipe is a one-way operation. +Reading input into @code{getline} from a pipe is a one-way operation. The command that is started with @samp{@var{command} | getline} only sends data @emph{to} your @command{awk} program. @@ -8143,7 +8104,7 @@ for processing and then read the results back. communications are possible. This is done with the @samp{|&} operator. Typically, you write data to the coprocess first and then -read results back, as shown in the following: +read the results back, as shown in the following: @example print "@var{some query}" |& "db_server" @@ -8226,7 +8187,7 @@ also @pxref{Auto-set}.) @item Using @code{FILENAME} with @code{getline} (@samp{getline < FILENAME}) -is likely to be a source for +is likely to be a source of confusion. @command{awk} opens a separate input stream from the current input file. However, by not using a variable, @code{$0} and @code{NF} are still updated. If you're doing this, it's @@ -8234,9 +8195,15 @@ probably by accident, and you should reconsider what it is you're trying to accomplish. @item -@DBREF{Getline Summary} presents a table summarizing the +@ifdocbook +The next section +@end ifdocbook +@ifnotdocbook +@ref{Getline Summary}, +@end ifnotdocbook +presents a table summarizing the @code{getline} variants and which variables they can affect. -It is worth noting that those variants which do not use redirection +It is worth noting that those variants that do not use redirection can cause @code{FILENAME} to be updated if they cause @command{awk} to start reading a new input file. @@ -8245,7 +8212,7 @@ can cause @code{FILENAME} to be updated if they cause If the variable being assigned is an expression with side effects, different versions of @command{awk} behave differently upon encountering end-of-file. Some versions don't evaluate the expression; many versions -(including @command{gawk}) do. Here is an example, due to Duncan Moore: +(including @command{gawk}) do. Here is an example, courtesy of Duncan Moore: @ignore Date: Sun, 01 Apr 2012 11:49:33 +0100 @@ -8262,7 +8229,7 @@ BEGIN @{ @noindent Here, the side effect is the @samp{++c}. Is @code{c} incremented if -end of file is encountered, before the element in @code{a} is assigned? +end-of-file is encountered before the element in @code{a} is assigned? @command{gawk} treats @code{getline} like a function call, and evaluates the expression @samp{a[++c]} before attempting to read from @file{f}. @@ -8294,9 +8261,6 @@ Note: for each variant, @command{gawk} sets the @code{RT} predefined variable. @item @var{command} @code{|& getline} @var{var} @tab Sets @var{var} and @code{RT} @tab @command{gawk} @end multitable @end float -@c ENDOFRANGE getl -@c ENDOFRANGE inex -@c ENDOFRANGE infir @node Read Timeout @section Reading Input with a Timeout @@ -8307,8 +8271,8 @@ This @value{SECTION} describes a feature that is specific to @command{gawk}. You may specify a timeout in milliseconds for reading input from the keyboard, a pipe, or two-way communication, including TCP/IP sockets. This can be done -on a per input, command, or connection basis, by setting a special element -in the @code{PROCINFO} array (@pxref{Auto-set}): +on a per-input, per-command, or per-connection basis, by setting a special +element in the @code{PROCINFO} array (@pxref{Auto-set}): @example PROCINFO["input_name", "READ_TIMEOUT"] = @var{timeout in milliseconds} @@ -8339,7 +8303,7 @@ while ((getline < "/dev/stdin") > 0) @end example @command{gawk} terminates the read operation if input does not -arrive after waiting for the timeout period, returns failure +arrive after waiting for the timeout period, returns failure, and sets @code{ERRNO} to an appropriate string value. A negative or zero value for the timeout is the same as specifying no timeout at all. @@ -8349,7 +8313,7 @@ loop that reads input records and matches them against patterns, like so: @example -$ @kbd{ gawk 'BEGIN @{ PROCINFO["-", "READ_TIMEOUT"] = 5000 @}} +$ @kbd{gawk 'BEGIN @{ PROCINFO["-", "READ_TIMEOUT"] = 5000 @}} > @kbd{@{ print "You entered: " $0 @}'} @kbd{gawk} @print{} You entered: gawk @@ -8389,7 +8353,7 @@ If the @code{PROCINFO} element is not present and the @command{gawk} uses its value to initialize the timeout value. The exclusive use of the environment variable to specify timeout has the disadvantage of not being able to control it -on a per command or connection basis. +on a per-command or per-connection basis. @command{gawk} considers a timeout event to be an error even though the attempt to read from the underlying device may @@ -8455,7 +8419,7 @@ The possibilities are as follows: @item After splitting the input into records, @command{awk} further splits -the record into individual fields, named @code{$1}, @code{$2}, and so +the records into individual fields, named @code{$1}, @code{$2}, and so on. @code{$0} is the whole record, and @code{NF} indicates how many fields there are. The default way to split fields is between whitespace characters. @@ -8471,12 +8435,12 @@ thing. Decrementing @code{NF} throws away fields and rebuilds the record. @item Field splitting is more complicated than record splitting: -@multitable @columnfractions .40 .45 .15 +@multitable @columnfractions .40 .40 .20 @headitem Field separator value @tab Fields are split @dots{} @tab @command{awk} / @command{gawk} @item @code{FS == " "} @tab On runs of whitespace @tab @command{awk} @item @code{FS == @var{any single character}} @tab On that character @tab @command{awk} @item @code{FS == @var{regexp}} @tab On text matching the regexp @tab @command{awk} -@item @code{FS == ""} @tab Each individual character is a separate field @tab @command{gawk} +@item @code{FS == ""} @tab Such that each individual character is a separate field @tab @command{gawk} @item @code{FIELDWIDTHS == @var{list of columns}} @tab Based on character position @tab @command{gawk} @item @code{FPAT == @var{regexp}} @tab On the text surrounding text matching the regexp @tab @command{gawk} @end multitable @@ -8493,11 +8457,11 @@ This can also be done using command-line variable assignment. Use @code{PROCINFO["FS"]} to see how fields are being split. @item -Use @code{getline} in its various forms to read additional records, +Use @code{getline} in its various forms to read additional records from the default input stream, from a file, or from a pipe or coprocess. @item -Use @code{PROCINFO[@var{file}, "READ_TIMEOUT"]} to cause reads to timeout +Use @code{PROCINFO[@var{file}, "READ_TIMEOUT"]} to cause reads to time out for @var{file}. @item @@ -8531,7 +8495,6 @@ That can be fixed by making one simple change. What is it? @node Printing @chapter Printing Output -@c STARTOFRANGE prnt @cindex printing @cindex output, printing, See printing One of the most common programming actions is to @dfn{print}, or output, @@ -8547,7 +8510,6 @@ columns, whether to use exponential notation or not, and so on. For printing with specifications, you need the @code{printf} statement (@pxref{Printf}). -@c STARTOFRANGE prnts @cindex @code{print} statement @cindex @code{printf} statement Besides basic and formatted printing, this @value{CHAPTER} @@ -8609,7 +8571,7 @@ space is printed between any two items. Note that the @code{print} statement is a statement and not an expression---you can't use it in the pattern part of a -@var{pattern}-@var{action} statement, for example. +pattern--action statement, for example. @node Print Examples @section @code{print} Statement Examples @@ -8728,7 +8690,6 @@ You can continue either a @code{print} or @code{printf} statement simply by putting a newline after any comma (@pxref{Statements/Lines}). @end quotation -@c ENDOFRANGE prnts @node Output Separators @section Output Separators @@ -8801,7 +8762,7 @@ runs together on a single line. @cindex numeric, output format @cindex formats@comma{} numeric output When printing numeric values with the @code{print} statement, -@command{awk} internally converts the number to a string of characters +@command{awk} internally converts each number to a string of characters and prints that string. @command{awk} uses the @code{sprintf()} function to do this conversion (@pxref{String Functions}). @@ -8841,7 +8802,6 @@ if @code{OFMT} contains anything but a floating-point conversion specification. @node Printf @section Using @code{printf} Statements for Fancier Printing -@c STARTOFRANGE printfs @cindex @code{printf} statement @cindex output, formatted @cindex formatting output @@ -8873,7 +8833,7 @@ printf @var{format}, @var{item1}, @var{item2}, @dots{} @noindent As for @code{print}, the entire list of arguments may optionally be enclosed in parentheses. Here too, the parentheses are necessary if any -of the item expressions use the @samp{>} relational operator; otherwise, +of the item expressions uses the @samp{>} relational operator; otherwise, it can be confused with an output redirection (@pxref{Redirection}). @cindex format specifiers @@ -8904,7 +8864,7 @@ $ @kbd{awk 'BEGIN @{} @end example @noindent -Here, neither the @samp{+} nor the @samp{OUCH!} appear in +Here, neither the @samp{+} nor the @samp{OUCH!} appears in the output message. @node Control Letters @@ -8951,8 +8911,8 @@ The two control letters are equivalent. (The @samp{%i} specification is for compatibility with ISO C.) @item @code{%e}, @code{%E} -Print a number in scientific (exponential) notation; -for example: +Print a number in scientific (exponential) notation. +For example: @example printf "%4.3e\n", 1950 @@ -8989,7 +8949,7 @@ The special ``not a number'' value formats as @samp{-nan} or @samp{nan} (@pxref{Math Definitions}). @item @code{%F} -Like @samp{%f} but the infinity and ``not a number'' values are spelled +Like @samp{%f}, but the infinity and ``not a number'' values are spelled using uppercase letters. The @samp{%F} format is a POSIX extension to ISO C; not all systems @@ -9039,7 +8999,6 @@ values or do something else entirely. @node Format Modifiers @subsection Modifiers for @code{printf} Formats -@c STARTOFRANGE pfm @cindex @code{printf} statement, modifiers @cindex modifiers@comma{} in format specifiers A format specification can also include @dfn{modifiers} that can control @@ -9078,7 +9037,7 @@ messages at runtime. which describes how and why to use positional specifiers. For now, we ignore them. -@item - (Minus) +@item - @r{(Minus)} The minus sign, used before the width modifier (see later on in this list), says to left-justify @@ -9234,7 +9193,7 @@ printf "%" w "." p "s\n", s @end example @noindent -This is not particularly easy to read but it does work. +This is not particularly easy to read, but it does work. @c @cindex lint checks @cindex troubleshooting, fatal errors, @code{printf} format strings @@ -9245,7 +9204,6 @@ format strings. These are not valid in @command{awk}. Most @command{awk} implementations silently ignore them. If @option{--lint} is provided on the command line (@pxref{Options}), @command{gawk} warns about their use. If @option{--posix} is supplied, their use is a fatal error. -@c ENDOFRANGE pfm @node Printf Examples @subsection Examples Using @code{printf} @@ -9281,7 +9239,7 @@ $ @kbd{awk '@{ printf "%-10s %s\n", $1, $2 @}' mail-list} @end example In this case, the phone numbers had to be printed as strings because -the numbers are separated by a dash. Printing the phone numbers as +the numbers are separated by dashes. Printing the phone numbers as numbers would have produced just the first three digits: @samp{555}. This would have been pretty confusing. @@ -9326,14 +9284,11 @@ awk 'BEGIN @{ format = "%-10s %s\n" @{ printf format, $1, $2 @}' mail-list @end example -@c ENDOFRANGE printfs @node Redirection @section Redirecting Output of @code{print} and @code{printf} -@c STARTOFRANGE outre @cindex output redirection -@c STARTOFRANGE reout @cindex redirection of output @cindex @option{--sandbox} option, output redirection with @code{print}, @code{printf} So far, the output from @code{print} and @code{printf} has gone @@ -9344,7 +9299,7 @@ This is called @dfn{redirection}. @quotation NOTE When @option{--sandbox} is specified (@pxref{Options}), -redirecting output to files, pipes and coprocesses is disabled. +redirecting output to files, pipes, and coprocesses is disabled. @end quotation A redirection appears after the @code{print} or @code{printf} statement. @@ -9397,7 +9352,7 @@ Each output file contains one name or number per line. @cindex @code{>} (right angle bracket), @code{>>} operator (I/O) @cindex right angle bracket (@code{>}), @code{>>} operator (I/O) @item print @var{items} >> @var{output-file} -This redirection prints the items into the pre-existing output file +This redirection prints the items into the preexisting output file named @var{output-file}. The difference between this and the single-@samp{>} redirection is that the old contents (if any) of @var{output-file} are not erased. Instead, the @command{awk} output is @@ -9436,7 +9391,7 @@ The unsorted list is written with an ordinary redirection, while the sorted list is written by piping through the @command{sort} utility. The next example uses redirection to mail a message to the mailing -list @samp{bug-system}. This might be useful when trouble is encountered +list @code{bug-system}. This might be useful when trouble is encountered in an @command{awk} script run periodically for system maintenance: @example @@ -9467,15 +9422,23 @@ This redirection prints the items to the input of @var{command}. The difference between this and the single-@samp{|} redirection is that the output from @var{command} can be read with @code{getline}. -Thus @var{command} is a @dfn{coprocess}, which works together with, -but subsidiary to, the @command{awk} program. +Thus, @var{command} is a @dfn{coprocess}, which works together with +but is subsidiary to the @command{awk} program. This feature is a @command{gawk} extension, and is not available in POSIX @command{awk}. -@DBXREF{Getline/Coprocess} +@ifnotdocbook +@xref{Getline/Coprocess}, for a brief discussion. -@DBXREF{Two-way I/O} +@xref{Two-way I/O}, for a more complete discussion. +@end ifnotdocbook +@ifdocbook +@DBXREF{Getline/Coprocess} +for a brief discussion and +@DBREF{Two-way I/O} +for a more complete discussion. +@end ifdocbook @end table Redirecting output using @samp{>}, @samp{>>}, @samp{|}, or @samp{|&} @@ -9500,7 +9463,7 @@ This is indeed how redirections must be used from the shell. But in @command{awk}, it isn't necessary. In this kind of case, a program should use @samp{>} for all the @code{print} statements, because the output file is only opened once. (It happens that if you mix @samp{>} and @samp{>>} -that output is produced in the expected order. However, mixing the operators +output is produced in the expected order. However, mixing the operators for the same file is definitely poor style, and is confusing to readers of your program.) @@ -9550,11 +9513,9 @@ It then sends the list to the shell for execution. @DBXREF{Shell Quoting} for a function that can help in generating command lines to be fed to the shell. @end sidebar -@c ENDOFRANGE outre -@c ENDOFRANGE reout @node Special FD -@section Special Files for Standard Pre-Opened Data Streams +@section Special Files for Standard Preopened Data Streams @cindex standard input @cindex input, standard @cindex standard output @@ -9567,7 +9528,7 @@ command lines to be fed to the shell. Running programs conventionally have three input and output streams already available to them for reading and writing. These are known as the @dfn{standard input}, @dfn{standard output}, and @dfn{standard -error output}. These open streams (and any other open file or pipe) +error output}. These open streams (and any other open files or pipes) are often referred to by the technical term @dfn{file descriptors}. These streams are, by default, connected to your keyboard and screen, but @@ -9605,7 +9566,7 @@ that is connected to your keyboard and screen. It represents the ``terminal,''@footnote{The ``tty'' in @file{/dev/tty} stands for ``Teletype,'' a serial terminal.} which on modern systems is a keyboard and screen, not a serial console.) -This generally has the same effect but not always: although the +This generally has the same effect, but not always: although the standard error stream is usually the screen, it can be redirected; when that happens, writing to the screen is not correct. In fact, if @command{awk} is run from a background job, it may not have a @@ -9650,7 +9611,7 @@ print "Serious error detected!" > "/dev/stderr" @cindex troubleshooting, quotes with file names Note the use of quotes around the @value{FN}. -Like any other redirection, the value must be a string. +Like with any other redirection, the value must be a string. It is a common error to omit the quotes, which leads to confusing results. @@ -9661,7 +9622,6 @@ invoked with the @option{--traditional} option (@pxref{Options}). @node Special Files @section Special @value{FFN}s in @command{gawk} -@c STARTOFRANGE gfn @cindex @command{gawk}, file names in Besides access to standard input, standard output, and standard error, @@ -9677,7 +9637,7 @@ TCP/IP networking. @end menu @node Other Inherited Files -@subsection Accessing Other Open Files With @command{gawk} +@subsection Accessing Other Open Files with @command{gawk} Besides the @code{/dev/stdin}, @code{/dev/stdout}, and @code{/dev/stderr} special @value{FN}s mentioned earlier, @command{gawk} provides syntax @@ -9734,7 +9694,7 @@ special @value{FN}s that @command{gawk} provides: @cindex compatibility mode (@command{gawk}), file names @cindex file names, in compatibility mode @item -Recognition of the @value{FN}s for the three standard pre-opened +Recognition of the @value{FN}s for the three standard preopened files is disabled only in POSIX mode. @item @@ -9747,23 +9707,18 @@ compatibility mode (either @option{--traditional} or @option{--posix}; interprets these special @value{FN}s. For example, using @samp{/dev/fd/4} for output actually writes on file descriptor 4, and not on a new -file descriptor that is @code{dup()}'ed from file descriptor 4. Most of +file descriptor that is @code{dup()}ed from file descriptor 4. Most of the time this does not matter; however, it is important to @emph{not} close any of the files related to file descriptors 0, 1, and 2. Doing so results in unpredictable behavior. @end itemize -@c ENDOFRANGE gfn @node Close Files And Pipes @section Closing Input and Output Redirections @cindex files, output, See output files -@c STARTOFRANGE ifc @cindex input files, closing -@c STARTOFRANGE ofc @cindex output, files@comma{} closing -@c STARTOFRANGE pc @cindex pipe, closing -@c STARTOFRANGE cc @cindex coprocesses, closing @cindex @code{getline} command, coprocesses@comma{} using from @@ -9969,18 +9924,14 @@ This value is zero if the close succeeds, or @minus{}1 if it fails. The POSIX standard is very vague; it says that @code{close()} -returns zero on success and nonzero otherwise. In general, +returns zero on success and a nonzero value otherwise. In general, different implementations vary in what they report when closing -pipes; thus the return value cannot be used portably. +pipes; thus, the return value cannot be used portably. @value{DARKCORNER} In POSIX mode (@pxref{Options}), @command{gawk} just returns zero when closing a pipe. @end sidebar -@c ENDOFRANGE ifc -@c ENDOFRANGE ofc -@c ENDOFRANGE pc -@c ENDOFRANGE cc @node Nonfatal @section Enabling Nonfatal Output @@ -10051,8 +10002,8 @@ for numeric values for the @code{print} statement. @item The @code{printf} statement provides finer-grained control over output, -with format control letters for different data types and various flags -that modify the behavior of the format control letters. +with format-control letters for different data types and various flags +that modify the behavior of the format-control letters. @item Output from both @code{print} and @code{printf} may be redirected to @@ -10107,11 +10058,9 @@ BEGIN @{ print "Serious error detected!" > /dev/stderr @} @end enumerate @c EXCLUDE END -@c ENDOFRANGE prnt @node Expressions @chapter Expressions -@c STARTOFRANGE exps @cindex expressions Expressions are the basic building blocks of @command{awk} patterns @@ -10122,7 +10071,7 @@ can assign a new value to a variable or a field by using an assignment operator. An expression can serve as a pattern or action statement on its own. Most other kinds of statements contain one or more expressions that specify the data on which to -operate. As in other languages, expressions in @command{awk} include +operate. As in other languages, expressions in @command{awk} can include variables, array references, constants, and function calls, as well as combinations of these with various operators. @@ -10141,7 +10090,7 @@ combinations of these with various operators. Expressions are built up from values and the operations performed upon them. This @value{SECTION} describes the elementary objects -which provide the values used in expressions. +that provide the values used in expressions. @menu * Constants:: String, numeric and regexp constants. @@ -10154,7 +10103,6 @@ which provide the values used in expressions. @node Constants @subsection Constant Expressions -@c STARTOFRANGE cnst @cindex constants, types of The simplest type of expression is the @dfn{constant}, which always has @@ -10192,7 +10140,7 @@ have the same value: @end example @cindex string constants -A string constant consists of a sequence of characters enclosed in +A @dfn{string constant} consists of a sequence of characters enclosed in double quotation marks. For example: @example @@ -10204,7 +10152,7 @@ double quotation marks. For example: @cindex strings, length limitations represents the string whose contents are @samp{parrot}. Strings in @command{gawk} can be of any length, and they can contain any of the possible -eight-bit ASCII characters including ASCII @sc{nul} (character code zero). +eight-bit ASCII characters, including ASCII @sc{nul} (character code zero). Other @command{awk} implementations may have difficulty with some character codes. @@ -10219,15 +10167,15 @@ In @command{awk}, all numbers are in decimal (i.e., base 10). Many other programming languages allow you to specify numbers in other bases, often octal (base 8) and hexadecimal (base 16). In octal, the numbers go 0, 1, 2, 3, 4, 5, 6, 7, 10, 11, 12, and so on. -Just as @samp{11}, in decimal, is 1 times 10 plus 1, so -@samp{11}, in octal, is 1 times 8, plus 1. This equals 9 in decimal. +Just as @samp{11} in decimal is 1 times 10 plus 1, so +@samp{11} in octal is 1 times 8 plus 1. This equals 9 in decimal. In hexadecimal, there are 16 digits. Because the everyday decimal number system only has ten digits (@samp{0}--@samp{9}), the letters @samp{a} through @samp{f} are used to represent the rest. (Case in the letters is usually irrelevant; hexadecimal @samp{a} and @samp{A} have the same value.) -Thus, @samp{11}, in -hexadecimal, is 1 times 16 plus 1, which equals 17 in decimal. +Thus, @samp{11} in +hexadecimal is 1 times 16 plus 1, which equals 17 in decimal. Just by looking at plain @samp{11}, you can't tell what base it's in. So, in C, C++, and other languages derived from C, @@ -10238,13 +10186,13 @@ and hexadecimal numbers start with a leading @samp{0x} or @samp{0X}: @table @code @item 11 -Decimal value 11. +Decimal value 11 @item 011 -Octal 11, decimal value 9. +Octal 11, decimal value 9 @item 0x11 -Hexadecimal 11, decimal value 17. +Hexadecimal 11, decimal value 17 @end table This example shows the difference: @@ -10272,11 +10220,11 @@ you can use the @code{strtonum()} function (@pxref{String Functions}) to convert the data into a number. Most of the time, you will want to use octal or hexadecimal constants -when working with the built-in bit manipulation functions; +when working with the built-in bit-manipulation functions; see @DBREF{Bitwise Functions} for more information. -Unlike some early C implementations, @samp{8} and @samp{9} are not +Unlike in some early C implementations, @samp{8} and @samp{9} are not valid in octal constants. For example, @command{gawk} treats @samp{018} as decimal 18: @@ -10311,19 +10259,17 @@ $ @kbd{gawk 'BEGIN @{ printf "0x11 is <%s>\n", 0x11 @}'} @node Regexp Constants @subsubsection Regular Expression Constants -@c STARTOFRANGE rec @cindex regexp constants @cindex @code{~} (tilde), @code{~} operator @cindex tilde (@code{~}), @code{~} operator @cindex @code{!} (exclamation point), @code{!~} operator @cindex exclamation point (@code{!}), @code{!~} operator -A regexp constant is a regular expression description enclosed in +A @dfn{regexp constant} is a regular expression description enclosed in slashes, such as @code{@w{/^beginning and end$/}}. Most regexps used in @command{awk} programs are constant, but the @samp{~} and @samp{!~} matching operators can also match computed or dynamic regexps (which are typically just ordinary strings or variables that contain a regexp, -but could be a more complex expression). -@c ENDOFRANGE cnst +but could be more complex expressions). @node Using Constant Regexps @subsection Using Regular Expression Constants @@ -10403,7 +10349,7 @@ the third argument of @code{split()} to be a regexp constant, but some older implementations do not. @value{DARKCORNER} Because some built-in functions accept regexp constants as arguments, -it can be confusing when attempting to use regexp constants as arguments +confusion can arise when attempting to use regexp constants as arguments to user-defined functions (@pxref{User-defined}). For example: @example @@ -10429,19 +10375,18 @@ function mysub(pat, repl, str, global) In this example, the programmer wants to pass a regexp constant to the user-defined function @code{mysub()}, which in turn passes it on to either @code{sub()} or @code{gsub()}. However, what really happens is that -the @code{pat} parameter is either one or zero, depending upon whether +the @code{pat} parameter is assigned a value of either one or zero, depending upon whether or not @code{$0} matches @code{/hi/}. @command{gawk} issues a warning when it sees a regexp constant used as a parameter to a user-defined function, because passing a truth value in this way is probably not what was intended. -@c ENDOFRANGE rec @node Variables @subsection Variables @cindex variables, user-defined @cindex user-defined, variables -Variables are ways of storing values at one point in your program for +@dfn{Variables} are ways of storing values at one point in your program for use later in another part of your program. They can be manipulated entirely within the program text, and they can also be assigned values on the @command{awk} command line. @@ -10469,17 +10414,17 @@ are distinct variables. A variable name is a valid expression by itself; it represents the variable's current value. Variables are given new values with @dfn{assignment operators}, @dfn{increment operators}, and -@dfn{decrement operators}. -@xref{Assignment Ops}. +@dfn{decrement operators} +(@pxref{Assignment Ops}). In addition, the @code{sub()} and @code{gsub()} functions can change a variable's value, and the @code{match()}, @code{split()}, and @code{patsplit()} functions can change the contents of their -array parameters. @xref{String Functions}. +array parameters (@pxref{String Functions}). @cindex variables, built-in @cindex variables, initializing A few variables have special built-in meanings, such as @code{FS} (the -field separator), and @code{NF} (the number of fields in the current input +field separator) and @code{NF} (the number of fields in the current input record). @DBXREF{Built-in Variables} for a list of the predefined variables. These predefined variables can be used and assigned just like all other variables, but their values are also used or changed automatically by @@ -10707,7 +10652,7 @@ point, so the default behavior was restored to use a period as the decimal point character. You can use the @option{--use-lc-numeric} option (@pxref{Options}) to force @command{gawk} to use the locale's decimal point character. (@command{gawk} also uses the locale's decimal -point character when in POSIX mode, either via @option{--posix}, or the +point character when in POSIX mode, either via @option{--posix} or the @env{POSIXLY_CORRECT} environment variable, as shown previously.) @ref{table-locale-affects} describes the cases in which the locale's decimal @@ -10725,7 +10670,7 @@ features have not been described yet. @end multitable @end float -Finally, modern day formal standards and IEEE standard floating-point +Finally, modern-day formal standards and the IEEE standard floating-point representation can have an unusual but important effect on the way @command{gawk} converts some special string values to numbers. The details are presented in @ref{POSIX Floating Point Problems}. @@ -10733,7 +10678,7 @@ are presented in @ref{POSIX Floating Point Problems}. @node All Operators @section Operators: Doing Something with Values -This @value{SECTION} introduces the @dfn{operators} which make use +This @value{SECTION} introduces the @dfn{operators} that make use of the values provided by constants and variables. @menu @@ -10911,7 +10856,7 @@ print "something meaningful" > file name @noindent This produces a syntax error with some versions of Unix @command{awk}.@footnote{It happens that BWK -@command{awk}, @command{gawk} and @command{mawk} all ``get it right,'' +@command{awk}, @command{gawk}, and @command{mawk} all ``get it right,'' but you should not rely on this.} It is necessary to use the following: @@ -11000,11 +10945,8 @@ you're never quite sure what you'll get. @node Assignment Ops @subsection Assignment Expressions -@c STARTOFRANGE asop @cindex assignment operators -@c STARTOFRANGE opas @cindex operators, assignment -@c STARTOFRANGE exas @cindex expressions, assignment @cindex @code{=} (equals sign), @code{=} operator @cindex equals sign (@code{=}), @code{=} operator @@ -11164,7 +11106,7 @@ and @ifdocbook @DBREF{Numeric Functions} @end ifdocbook -for more information). +for more information.) This example illustrates an important fact about assignment operators: the lefthand expression is only evaluated @emph{once}. @@ -11200,17 +11142,17 @@ to a number. @caption{Arithmetic assignment operators} @multitable @columnfractions .30 .70 @headitem Operator @tab Effect -@item @var{lvalue} @code{+=} @var{increment} @tab Add @var{increment} to the value of @var{lvalue} -@item @var{lvalue} @code{-=} @var{decrement} @tab Subtract @var{decrement} from the value of @var{lvalue} -@item @var{lvalue} @code{*=} @var{coefficient} @tab Multiply the value of @var{lvalue} by @var{coefficient} -@item @var{lvalue} @code{/=} @var{divisor} @tab Divide the value of @var{lvalue} by @var{divisor} -@item @var{lvalue} @code{%=} @var{modulus} @tab Set @var{lvalue} to its remainder by @var{modulus} +@item @var{lvalue} @code{+=} @var{increment} @tab Add @var{increment} to the value of @var{lvalue}. +@item @var{lvalue} @code{-=} @var{decrement} @tab Subtract @var{decrement} from the value of @var{lvalue}. +@item @var{lvalue} @code{*=} @var{coefficient} @tab Multiply the value of @var{lvalue} by @var{coefficient}. +@item @var{lvalue} @code{/=} @var{divisor} @tab Divide the value of @var{lvalue} by @var{divisor}. +@item @var{lvalue} @code{%=} @var{modulus} @tab Set @var{lvalue} to its remainder by @var{modulus}. @cindex common extensions, @code{**=} operator @cindex extensions, common@comma{} @code{**=} operator @cindex @command{awk} language, POSIX version @cindex POSIX @command{awk} -@item @var{lvalue} @code{^=} @var{power} @tab -@item @var{lvalue} @code{**=} @var{power} @tab Raise @var{lvalue} to the power @var{power} @value{COMMONEXT} +@item @var{lvalue} @code{^=} @var{power} @tab Raise @var{lvalue} to the power @var{power}. +@item @var{lvalue} @code{**=} @var{power} @tab Raise @var{lvalue} to the power @var{power}. @value{COMMONEXT} @end multitable @end float @@ -11258,16 +11200,11 @@ awk '/[=]=/' /dev/null @command{gawk} does not have this problem; BWK @command{awk} and @command{mawk} also do not. @end sidebar -@c ENDOFRANGE exas -@c ENDOFRANGE opas -@c ENDOFRANGE asop @node Increment Ops @subsection Increment and Decrement Operators -@c STARTOFRANGE inop @cindex increment operators -@c STARTOFRANGE opde @cindex operators, decrement/increment @dfn{Increment} and @dfn{decrement operators} increase or decrease the value of a variable by one. An assignment operator can do the same thing, so @@ -11315,7 +11252,6 @@ just like variables. (Use @samp{$(i++)} when you want to do a field reference and a variable increment at the same time. The parentheses are necessary because of the precedence of the field reference operator @samp{$}.) -@c STARTOFRANGE deop @cindex decrement operators The decrement operator @samp{--} works just like @samp{++}, except that it subtracts one instead of adding it. As with @samp{++}, it can be used before @@ -11355,8 +11291,8 @@ like @samp{@var{lvalue}++}, but instead of adding, it subtracts.) @cindex evaluation order @cindex Marx, Groucho @quotation -@i{Doctor, doctor! It hurts when I do this!@* -So don't do that!} +@i{Doctor, it hurts when I do this!@* +Then don't do that!} @author Groucho Marx @end quotation @@ -11380,7 +11316,7 @@ print b @cindex side effects In other words, when do the various side effects prescribed by the postfix operators (@samp{b++}) take effect? -When side effects happen is @dfn{implementation defined}. +When side effects happen is @dfn{implementation-defined}. In other words, it is up to the particular version of @command{awk}. The result for the first example may be 12 or 13, and for the second, it may be 22 or 23. @@ -11391,15 +11327,12 @@ You should avoid such things in your own programs. @c You'll sleep better at night and be able to look at yourself @c in the mirror in the morning. @end sidebar -@c ENDOFRANGE inop -@c ENDOFRANGE opde -@c ENDOFRANGE deop @node Truth Values and Conditions @section Truth Values and Conditions -In certain contexts, expression values also serve as ``truth values''; (i.e., -they determine what should happen next as the program runs). This +In certain contexts, expression values also serve as ``truth values''; i.e., +they determine what should happen next as the program runs. This @value{SECTION} describes how @command{awk} defines ``true'' and ``false'' and how values are compared. @@ -11458,19 +11391,15 @@ the string constant @code{"0"} is actually true, because it is non-null. @author Douglas Adams, @cite{The Hitchhiker's Guide to the Galaxy} @end quotation -@c STARTOFRANGE comex @cindex comparison expressions -@c STARTOFRANGE excom @cindex expressions, comparison @cindex expressions, matching, See comparison expressions @cindex matching, expressions, See comparison expressions @cindex relational operators, See comparison operators @cindex operators, relational, See operators@comma{} comparison -@c STARTOFRANGE varting @cindex variable typing -@c STARTOFRANGE vartypc @cindex variables, types of, comparison expressions and -Unlike other programming languages, @command{awk} variables do not have a +Unlike in other programming languages, in @command{awk} variables do not have a fixed type. Instead, they can be either a number or a string, depending upon the value that is assigned to them. We look now at how variables are typed, and how @command{awk} @@ -11499,20 +11428,20 @@ Variable typing follows these rules: @itemize @value{BULLET} @item -A numeric constant or the result of a numeric operation has the @var{numeric} +A numeric constant or the result of a numeric operation has the @dfn{numeric} attribute. @item -A string constant or the result of a string operation has the @var{string} +A string constant or the result of a string operation has the @dfn{string} attribute. @item Fields, @code{getline} input, @code{FILENAME}, @code{ARGV} elements, @code{ENVIRON} elements, and the elements of an array created by @code{match()}, @code{split()}, and @code{patsplit()} that are numeric -strings have the @var{strnum} attribute. Otherwise, they have -the @var{string} attribute. Uninitialized variables also have the -@var{strnum} attribute. +strings have the @dfn{strnum} attribute. Otherwise, they have +the @dfn{string} attribute. Uninitialized variables also have the +@dfn{strnum} attribute. @item Attributes propagate across assignments but are not changed by @@ -11656,13 +11585,13 @@ constant, then a string comparison is performed. Otherwise, a numeric comparison is performed. This point bears additional emphasis: All user input is made of characters, -and so is first and foremost of @var{string} type; input strings -that look numeric are additionally given the @var{strnum} attribute. +and so is first and foremost of string type; input strings +that look numeric are additionally given the strnum attribute. Thus, the six-character input string @w{@samp{ +3.14}} receives the -@var{strnum} attribute. In contrast, the eight characters +strnum attribute. In contrast, the eight characters @w{@code{" +3.14"}} appearing in program text comprise a string constant. The following examples print @samp{1} when the comparison between -the two different constants is true, @samp{0} otherwise: +the two different constants is true, and @samp{0} otherwise: @c 22.9.2014: Tested with mawk and BWK awk, got same results. @example @@ -11792,7 +11721,7 @@ $ @kbd{echo 1e2 3 | awk '@{ print ($1 < $2) ? "true" : "false" @}'} @noindent the result is @samp{false} because both @code{$1} and @code{$2} are user input. They are numeric strings---therefore both have -the @var{strnum} attribute, dictating a numeric comparison. +the strnum attribute, dictating a numeric comparison. The purpose of the comparison rules and the use of numeric strings is to attempt to produce the behavior that is ``least surprising,'' while still ``doing the right thing.'' @@ -11851,7 +11780,7 @@ characters sort, as defined by the locale (for more discussion, @pxref{Locales}). This order is usually very different from the results obtained when doing straight character-by-character comparison.@footnote{Technically, string comparison is supposed -to behave the same way as if the strings are compared with the C +to behave the same way as if the strings were compared with the C @code{strcoll()} function.} Because this behavior differs considerably from existing practice, @@ -11868,19 +11797,13 @@ $ @kbd{gawk --posix 'BEGIN @{ printf("ABC < abc = %s\n",} @print{} ABC < abc = FALSE @end example -@c ENDOFRANGE comex -@c ENDOFRANGE excom -@c ENDOFRANGE vartypc -@c ENDOFRANGE varting @node Boolean Ops @subsection Boolean Expressions @cindex and Boolean-logic operator @cindex or Boolean-logic operator @cindex not Boolean-logic operator -@c STARTOFRANGE exbo @cindex expressions, Boolean -@c STARTOFRANGE boex @cindex Boolean expressions @cindex operators, Boolean, See Boolean expressions @cindex Boolean operators, See Boolean expressions @@ -11964,7 +11887,7 @@ BEGIN @{ if (! ("HOME" in ENVIRON)) @cindex vertical bar (@code{|}), @code{||} operator The @samp{&&} and @samp{||} operators are called @dfn{short-circuit} operators because of the way they work. Evaluation of the full expression -is ``short-circuited'' if the result can be determined part way through +is ``short-circuited'' if the result can be determined partway through its evaluation. @cindex line continuations @@ -12026,8 +11949,6 @@ next record, and start processing the rules over again at the top. The reason it's there is to avoid printing the bracketing @samp{START} and @samp{END} lines. @end quotation -@c ENDOFRANGE exbo -@c ENDOFRANGE boex @node Conditional Exp @subsection Conditional Expressions @@ -12038,8 +11959,8 @@ The reason it's there is to avoid printing the bracketing A @dfn{conditional expression} is a special kind of expression that has three operands. It allows you to use one expression's value to select one of two other expressions. -The conditional expression is the same as in the C language, -as shown here: +The conditional expression in @command{awk} is the same as in the C +language, as shown here: @example @var{selector} ? @var{if-true-exp} : @var{if-false-exp} @@ -12048,8 +11969,8 @@ as shown here: @noindent There are three subexpressions. The first, @var{selector}, is always computed first. If it is ``true'' (not zero or not null), then -@var{if-true-exp} is computed next and its value becomes the value of -the whole expression. Otherwise, @var{if-false-exp} is computed next +@var{if-true-exp} is computed next, and its value becomes the value of +the whole expression. Otherwise, @var{if-false-exp} is computed next, and its value becomes the value of the whole expression. For example, the following expression produces the absolute value of @code{x}: @@ -12097,7 +12018,7 @@ ask for it by name at any point in the program. For example, the function @code{sqrt()} computes the square root of a number. @cindex functions, built-in -A fixed set of functions are @dfn{built-in}, which means they are +A fixed set of functions are @dfn{built in}, which means they are available in every @command{awk} program. The @code{sqrt()} function is one of these. @DBXREF{Built-in} for a list of built-in functions and their descriptions. In addition, you can define @@ -12206,9 +12127,7 @@ $ @kbd{awk -f matchit.awk} @node Precedence @section Operator Precedence (How Operators Nest) -@c STARTOFRANGE prec @cindex precedence -@c STARTOFRANGE oppr @cindex operators, precedence @dfn{Operator precedence} determines how operators are grouped when @@ -12273,7 +12192,7 @@ Increment, decrement. @cindex @code{*} (asterisk), @code{**} operator @cindex asterisk (@code{*}), @code{**} operator @item @code{^ **} -Exponentiation. These operators group right-to-left. +Exponentiation. These operators group right to left. @cindex @code{+} (plus sign), @code{+} operator @cindex plus sign (@code{+}), @code{+} operator @@ -12339,7 +12258,7 @@ statements belong to the statement level, not to expressions. The redirection does not produce an expression that could be the operand of another operator. As a result, it does not make sense to use a redirection operator near another operator of lower precedence without -parentheses. Such combinations (e.g., @samp{print foo > a ? b : c}), +parentheses. Such combinations (e.g., @samp{print foo > a ? b : c}) result in syntax errors. The correct way to write this statement is @samp{print foo > (a ? b : c)}. @@ -12357,17 +12276,17 @@ Array membership. @cindex @code{&} (ampersand), @code{&&} operator @cindex ampersand (@code{&}), @code{&&} operator @item @code{&&} -Logical ``and''. +Logical ``and.'' @cindex @code{|} (vertical bar), @code{||} operator @cindex vertical bar (@code{|}), @code{||} operator @item @code{||} -Logical ``or''. +Logical ``or.'' @cindex @code{?} (question mark), @code{?:} operator @cindex question mark (@code{?}), @code{?:} operator @item @code{?:} -Conditional. This operator groups right-to-left. +Conditional. This operator groups right to left. @cindex @code{+} (plus sign), @code{+=} operator @cindex plus sign (@code{+}), @code{+=} operator @@ -12384,7 +12303,7 @@ Conditional. This operator groups right-to-left. @cindex @code{^} (caret), @code{^=} operator @cindex caret (@code{^}), @code{^=} operator @item @code{= += -= *= /= %= ^= **=} -Assignment. These operators group right-to-left. +Assignment. These operators group right to left. @end table @cindex POSIX @command{awk}, @code{**} operator and @@ -12393,8 +12312,6 @@ Assignment. These operators group right-to-left. The @samp{|&}, @samp{**}, and @samp{**=} operators are not specified by POSIX. For maximum portability, do not use them. @end quotation -@c ENDOFRANGE prec -@c ENDOFRANGE oppr @node Locales @section Where You Are Makes a Difference @@ -12460,8 +12377,8 @@ Locales can influence the conversions. @item @command{awk} provides the usual arithmetic operators (addition, subtraction, multiplication, division, modulus), and unary plus and minus. -It also provides comparison operators, boolean operators, array membership -testing, and regexp +It also provides comparison operators, Boolean operators, an array membership +testing operator, and regexp matching operators. String concatenation is accomplished by placing two expressions next to each other; there is no explicit operator. The three-operand @samp{?:} operator provides an ``if-else'' test within @@ -12472,7 +12389,7 @@ Assignment operators provide convenient shorthands for common arithmetic operations. @item -In @command{awk}, a value is considered to be true if it is non-zero +In @command{awk}, a value is considered to be true if it is nonzero @emph{or} non-null. Otherwise, the value is false. @item @@ -12481,7 +12398,7 @@ lifetime. The type determines how it behaves in comparisons (string or numeric). @item -Function calls return a value which may be used as part of a larger +Function calls return a value that may be used as part of a larger expression. Expressions used to pass parameter values are fully evaluated before the function is called. @command{awk} provides built-in and user-defined functions; this is described in @@ -12498,11 +12415,9 @@ program, and occasionally the format for data read as input. @end itemize -@c ENDOFRANGE exps @node Patterns and Actions @chapter Patterns, Actions, and Variables -@c STARTOFRANGE pat @cindex patterns As you have already seen, each @command{awk} statement consists of @@ -12510,7 +12425,7 @@ a pattern with an associated action. This @value{CHAPTER} describes how you build patterns and actions, what kinds of things you can do within actions, and @command{awk}'s predefined variables. -The pattern-action rules and the statements available for use +The pattern--action rules and the statements available for use within actions form the core of @command{awk} programming. In a sense, everything covered up to here has been the foundation @@ -12701,7 +12616,7 @@ patterns. Likewise, the special patterns @code{BEGIN}, @code{END}, which never match any input record, are not expressions and cannot appear inside Boolean patterns. -The precedence of the different operators which can appear in +The precedence of the different operators that can appear in patterns is described in @ref{Precedence}. @node Ranges @@ -12727,7 +12642,7 @@ prints every record in @file{myfile} between @samp{on}/@samp{off} pairs, inclusi A range pattern starts out by matching @var{begpat} against every input record. When a record matches @var{begpat}, the range pattern is -@dfn{turned on} and the range pattern matches this record as well. As long as +@dfn{turned on}, and the range pattern matches this record as well. As long as the range pattern stays turned on, it automatically matches every input record read. The range pattern also matches @var{endpat} against every input record; when this succeeds, the range pattern is @dfn{turned off} again @@ -12798,9 +12713,7 @@ a range pattern. @value{DARKCORNER} @node BEGIN/END @subsection The @code{BEGIN} and @code{END} Special Patterns -@c STARTOFRANGE beg @cindex @code{BEGIN} pattern -@c STARTOFRANGE end @cindex @code{END} pattern All the patterns described so far are for matching input records. The @code{BEGIN} and @code{END} special patterns are different. @@ -12873,7 +12786,7 @@ using library functions. for a number of useful library functions. If an @command{awk} program has only @code{BEGIN} rules and no -other rules, then the program exits after the @code{BEGIN} rule is +other rules, then the program exits after the @code{BEGIN} rules are run.@footnote{The original version of @command{awk} kept reading and ignoring input until the end of the file was seen.} However, if an @code{END} rule exists, then the input is read, even if there are @@ -12901,7 +12814,7 @@ Another way is simply to assign a value to @code{$0}. @cindex @code{print} statement, @code{BEGIN}/@code{END} patterns and @cindex @code{BEGIN} pattern, @code{print} statement and @cindex @code{END} pattern, @code{print} statement and -The second point is similar to the first but from the other direction. +The second point is similar to the first, but from the other direction. Traditionally, due largely to implementation issues, @code{$0} and @code{NF} were @emph{undefined} inside an @code{END} rule. The POSIX standard specifies that @code{NF} is available in an @code{END} @@ -12938,8 +12851,6 @@ are not valid in an @code{END} rule, because all the input has been read. @ifdocbook @DBREF{Nextfile Statement}.) @end ifdocbook -@c ENDOFRANGE beg -@c ENDOFRANGE end @node BEGINFILE/ENDFILE @subsection The @code{BEGINFILE} and @code{ENDFILE} Special Patterns @@ -12992,7 +12903,7 @@ fatal error. @item If you have written extensions that modify the record handling (by -inserting an ``input parser,'' @pxref{Input Parsers}), you can invoke +inserting an ``input parser''; @pxref{Input Parsers}), you can invoke them at this point, before @command{gawk} has started processing the file. (This is a @emph{very} advanced feature, currently used only by the @uref{http://gawkextlib.sourceforge.net, @code{gawkextlib} project}.) @@ -13003,8 +12914,8 @@ the last record in an input file. For the last input file, it will be called before any @code{END} rules. The @code{ENDFILE} rule is executed even for empty input files. -Normally, when an error occurs when reading input in the normal input -processing loop, the error is fatal. However, if an @code{ENDFILE} +Normally, when an error occurs when reading input in the normal +input-processing loop, the error is fatal. However, if an @code{ENDFILE} rule is present, the error becomes non-fatal, and instead @code{ERRNO} is set. This makes it possible to catch and process I/O errors at the level of the @command{awk} program. @@ -13013,7 +12924,7 @@ level of the @command{awk} program. The @code{next} statement (@pxref{Next Statement}) is not allowed inside either a @code{BEGINFILE} or an @code{ENDFILE} rule. The @code{nextfile} statement is allowed only inside a -@code{BEGINFILE} rule, but not inside an @code{ENDFILE} rule. +@code{BEGINFILE} rule, not inside an @code{ENDFILE} rule. @cindex @code{getline} statement, @code{BEGINFILE}/@code{ENDFILE} patterns and The @code{getline} statement (@pxref{Getline}) is restricted inside @@ -13060,7 +12971,6 @@ awk '@{ print $1 @}' mail-list @noindent prints the first field of every record. -@c ENDOFRANGE pat @node Using Shell Variables @section Using Shell Variables in Programs @@ -13090,11 +13000,11 @@ awk "/$pattern/ "'@{ nmatches++ @} @noindent The @command{awk} program consists of two pieces of quoted text that are concatenated together to form the program. -The first part is double quoted, which allows substitution of +The first part is double-quoted, which allows substitution of the @code{pattern} shell variable inside the quotes. -The second part is single quoted. +The second part is single-quoted. -Variable substitution via quoting works, but can be potentially +Variable substitution via quoting works, but can potentially be messy. It requires a good understanding of the shell's quoting rules (@pxref{Quoting}), and it's often difficult to correctly @@ -13209,11 +13119,8 @@ For deleting array elements. @node Statements @section Control Statements in Actions -@c STARTOFRANGE csta @cindex control statements -@c STARTOFRANGE acs @cindex statements, control, in actions -@c STARTOFRANGE accs @cindex actions, control statements in @dfn{Control statements}, such as @code{if}, @code{while}, and so on, @@ -13356,13 +13263,13 @@ The body of this loop is a compound statement enclosed in braces, containing two statements. The loop works in the following manner: first, the value of @code{i} is set to one. Then, the @code{while} statement tests whether @code{i} is less than or equal to -three. This is true when @code{i} equals one, so the @code{i}-th +three. This is true when @code{i} equals one, so the @code{i}th field is printed. Then the @samp{i++} increments the value of @code{i} and the loop repeats. The loop terminates when @code{i} reaches four. A newline is not required between the condition and the body; however, using one makes the program clearer unless the body is a -compound statement or else is very simple. The newline after the open-brace +compound statement or else is very simple. The newline after the open brace that begins the compound statement is not required either, but the program is harder to read without it. @@ -13392,9 +13299,9 @@ while (@var{condition}) @end example @noindent -This statement does not execute @var{body} even once if the @var{condition} -is false to begin with. -The following is an example of a @code{do} statement: +This statement does not execute the @var{body} even once if the +@var{condition} is false to begin with. The following is an example of +a @code{do} statement: @example @{ @@ -13461,7 +13368,7 @@ their assignments as separate statements preceding the @code{for} loop.) The same is true of the @var{increment} part. Incrementing additional variables requires separate statements at the end of the loop. The C compound expression, using C's comma operator, is useful in -this context but it is not supported in @command{awk}. +this context, but it is not supported in @command{awk}. Most often, @var{increment} is an increment expression, as in the previous example. But this is not required; it can be any expression @@ -13552,7 +13459,7 @@ default: Control flow in the @code{switch} statement works as it does in C. Once a match to a given case is made, the case statement bodies execute until a @code{break}, -@code{continue}, @code{next}, @code{nextfile} or @code{exit} is encountered, +@code{continue}, @code{next}, @code{nextfile}, or @code{exit} is encountered, or the end of the @code{switch} statement itself. For example: @example @@ -13726,7 +13633,12 @@ body of a loop. Historical versions of @command{awk} treated a @code{continue} statement outside a loop the same way they treated a @code{break} statement outside a loop: as if it were a @code{next} statement +@ifset FOR_PRINT +(discussed in the following section). +@end ifset +@ifclear FOR_PRINT (@pxref{Next Statement}). +@end ifclear @value{DARKCORNER} Recent versions of BWK @command{awk} no longer work this way, nor does @command{gawk}. @@ -13854,7 +13766,7 @@ See @uref{http://austingroupbugs.net/view.php?id=607, the Austin Group website}. @cindex @code{nextfile} statement, user-defined functions and @cindex Brian Kernighan's @command{awk} @cindex @command{mawk} utility -The current version of BWK @command{awk}, and @command{mawk} +The current version of BWK @command{awk} and @command{mawk} also support @code{nextfile}. However, they don't allow the @code{nextfile} statement inside function bodies (@pxref{User-defined}). @command{gawk} does; a @code{nextfile} inside a function body reads the @@ -13892,7 +13804,7 @@ any @code{ENDFILE} rules; they do not execute. In such a case, if you don't want the @code{END} rule to do its job, set a variable -to nonzero before the @code{exit} statement and check that variable in +to a nonzero value before the @code{exit} statement and check that variable in the @code{END} rule. @DBXREF{Assert Function} for an example that does this. @@ -13931,15 +13843,10 @@ Negative values, and values of 127 or greater, may not produce consistent results across different operating systems. @end quotation -@c ENDOFRANGE csta -@c ENDOFRANGE acs -@c ENDOFRANGE accs @node Built-in Variables @section Predefined Variables -@c STARTOFRANGE bvar @cindex predefined variables -@c STARTOFRANGE varb @cindex variables, predefined Most @command{awk} variables are available to use for your own @@ -13965,10 +13872,8 @@ their areas of activity. @end menu @node User-modified -@subsection Built-In Variables That Control @command{awk} -@c STARTOFRANGE bvaru +@subsection Built-in Variables That Control @command{awk} @cindex predefined variables, user-modifiable -@c STARTOFRANGE nmbv @cindex user-modifiable variables The following is an alphabetical list of variables that you can change to @@ -13996,7 +13901,7 @@ respectively, should use binary I/O. A string value of @code{"rw"} or @code{"wr"} indicates that all files should use binary I/O. Any other string value is treated the same as @code{"rw"}, but causes @command{gawk} to generate a warning message. @code{BINMODE} is described in more -detail in @ref{PC Using}. @command{mawk} (@pxref{Other Versions}), +detail in @ref{PC Using}. @command{mawk} (@pxref{Other Versions}) also supports this variable, but only using numeric values. @cindex @code{CONVFMT} variable @@ -14004,7 +13909,7 @@ also supports this variable, but only using numeric values. @cindex numbers, converting, to strings @cindex strings, converting, numbers to @item @code{CONVFMT} -This string controls conversion of numbers to +A string that controls the conversion of numbers to strings (@pxref{Conversion}). It works by being passed, in effect, as the first argument to the @code{sprintf()} function @@ -14079,7 +13984,7 @@ is to simply say @samp{FS = FS}, perhaps with an explanatory comment. @cindex regular expressions, case sensitivity @item IGNORECASE # If @code{IGNORECASE} is nonzero or non-null, then all string comparisons -and all regular expression matching are case independent. Thus, regexp +and all regular expression matching are case-independent. Thus, regexp matching with @samp{~} and @samp{!~}, as well as the @code{gensub()}, @code{gsub()}, @code{index()}, @code{match()}, @code{patsplit()}, @code{split()}, and @code{sub()} @@ -14105,7 +14010,7 @@ Any other true value prints nonfatal warnings. Assigning a false value to @code{LINT} turns off the lint warnings. This variable is a @command{gawk} extension. It is not special -in other @command{awk} implementations. Unlike the other special variables, +in other @command{awk} implementations. Unlike with the other special variables, changing @code{LINT} does affect the production of lint warnings, even if @command{gawk} is in compatibility mode. Much as the @option{--lint} and @option{--traditional} options independently @@ -14117,7 +14022,7 @@ of @command{awk} being executed. @cindex numbers, converting, to strings @cindex strings, converting, numbers to @item OFMT -Controls conversion of numbers to +A string that controls conversion of numbers to strings (@pxref{Conversion}) for printing with the @code{print} statement. It works by being passed as the first argument to the @code{sprintf()} function @@ -14132,7 +14037,7 @@ strings in general expressions; this is now done by @code{CONVFMT}. @cindex separators, field @cindex field separators @item OFS -This is the output field separator (@pxref{Output Separators}). It is +The output field separator (@pxref{Output Separators}). It is output between the fields printed by a @code{print} statement. Its default value is @w{@code{" "}}, a string consisting of a single space. @@ -14150,7 +14055,7 @@ The working precision of arbitrary-precision floating-point numbers, @cindex @code{ROUNDMODE} variable @item ROUNDMODE # The rounding mode to use for arbitrary-precision arithmetic on -numbers, by default @code{"N"} (@samp{roundTiesToEven} in +numbers, by default @code{"N"} (@code{roundTiesToEven} in the IEEE 754 standard; @pxref{Setting the rounding mode}). @cindex @code{RS} variable @@ -14179,7 +14084,7 @@ just the first character of @code{RS}'s value is used. @item @code{SUBSEP} The subscript separator. It has the default value of @code{"\034"} and is used to separate the parts of the indices of a -multidimensional array. Thus, the expression @code{@w{foo["A", "B"]}} +multidimensional array. Thus, the expression @samp{@w{foo["A", "B"]}} really accesses @code{foo["A\034B"]} (@pxref{Multidimensional}). @@ -14195,17 +14100,11 @@ marked string constants in the source text, as well as for the (@pxref{Internationalization}). The default value of @code{TEXTDOMAIN} is @code{"messages"}. @end table -@c ENDOFRANGE bvar -@c ENDOFRANGE varb -@c ENDOFRANGE bvaru -@c ENDOFRANGE nmbv @node Auto-set -@subsection Built-In Variables That Convey Information +@subsection Built-in Variables That Convey Information -@c STARTOFRANGE bvconi @cindex predefined variables, conveying information -@c STARTOFRANGE vbconi @cindex variables, predefined conveying information The following is an alphabetical list of variables that @command{awk} sets automatically on certain occasions in order to provide @@ -14361,12 +14260,12 @@ input file. @item @code{NF} The number of fields in the current input record. @code{NF} is set each time a new record is read, when a new field is -created or when @code{$0} changes (@pxref{Fields}). +created, or when @code{$0} changes (@pxref{Fields}). Unlike most of the variables described in this @value{SUBSECTION}, assigning a value to @code{NF} has the potential to affect @command{awk}'s internal workings. In particular, assignments -to @code{NF} can be used to create or remove fields from the +to @code{NF} can be used to create fields in or remove fields from the current record. @xref{Changing Fields}. @cindex @code{FUNCTAB} array @@ -14416,7 +14315,7 @@ or @code{"FPAT"} if field matching with @code{FPAT} is in effect. @item PROCINFO["identifiers"] @cindex program identifiers A subarray, indexed by the names of all identifiers used in the text of -the AWK program. An @dfn{identifier} is simply the name of a variable +the @command{awk} program. An @dfn{identifier} is simply the name of a variable (be it scalar or array), built-in function, user-defined function, or extension function. For each identifier, the value of the element is one of the following: @@ -14436,7 +14335,7 @@ The identifier is an extension function loaded via The identifier is a scalar. @item "untyped" -The identifier is untyped (could be used as a scalar or array, +The identifier is untyped (could be used as a scalar or an array; @command{gawk} doesn't know yet). @item "user" @@ -14557,7 +14456,7 @@ is the length of the matched string, or @minus{}1 if no match is found. @cindex @code{RSTART} variable @item @code{RSTART} -The start-index in characters of the substring that is matched by the +The start index in characters of the substring that is matched by the @code{match()} function (@pxref{String Functions}). @code{RSTART} is set by invoking the @code{match()} function. Its value @@ -14624,11 +14523,9 @@ function multiply(variable, amount) @quotation NOTE In order to avoid severe time-travel paradoxes,@footnote{Not to mention difficult implementation issues.} neither @code{FUNCTAB} nor @code{SYMTAB} -are available as elements within the @code{SYMTAB} array. +is available as an element within the @code{SYMTAB} array. @end quotation @end table -@c ENDOFRANGE bvconi -@c ENDOFRANGE vbconi @sidebar Changing @code{NR} and @code{FNR} @cindex @code{NR} variable, changing @@ -14800,7 +14697,7 @@ When designing your program, you should choose options that don't conflict with @command{gawk}'s, because it will process any options that it accepts before passing the rest of the command line on to your program. Using @samp{#!} with the @option{-E} option may help -(@DBXREF{Executable Scripts} +(@DBPXREF{Executable Scripts} and @ifnotdocbook @DBPXREF{Options}). @@ -14814,15 +14711,15 @@ and @itemize @value{BULLET} @item -Pattern-action pairs make up the basic elements of an @command{awk} +Pattern--action pairs make up the basic elements of an @command{awk} program. Patterns are either normal expressions, range expressions, -regexp constants, one of the special keywords @code{BEGIN}, @code{END}, -@code{BEGINFILE}, @code{ENDFILE}, or empty. The action executes if +or regexp constants; one of the special keywords @code{BEGIN}, @code{END}, +@code{BEGINFILE}, or @code{ENDFILE}; or empty. The action executes if the current record matches the pattern. Empty (missing) patterns match all records. @item -I/O from @code{BEGIN} and @code{END} rules have certain constraints. +I/O from @code{BEGIN} and @code{END} rules has certain constraints. This is also true, only more so, for @code{BEGINFILE} and @code{ENDFILE} rules. The latter two give you ``hooks'' into @command{gawk}'s file processing, allowing you to recover from a file that otherwise would @@ -14852,12 +14749,12 @@ iteration of a loop (or get out of a @code{switch}). @item @code{next} and @code{nextfile} let you read the next record and start -over at the top of your program, or skip to the next input file and +over at the top of your program or skip to the next input file and start over, respectively. @item The @code{exit} statement terminates your program. When executed -from an action (or function body) it transfers control to the +from an action (or function body), it transfers control to the @code{END} statements. From an @code{END} statement body, it exits immediately. You may pass an optional numeric value to be used as @command{awk}'s exit status. @@ -14875,7 +14772,6 @@ control how @command{awk} will process the provided @value{DF}s. @node Arrays @chapter Arrays in @command{awk} -@c STARTOFRANGE arrs @cindex arrays An @dfn{array} is a table of values called @dfn{elements}. The @@ -14961,15 +14857,17 @@ the declaration. indices---e.g., @samp{15 .. 27}---but the size of the array is still fixed when the array is declared.) -A contiguous array of four elements might look like the following example, -conceptually, if the element values are 8, @code{"foo"}, -@code{""}, and 30 +@c 1/2015: Do not put the numeric values into @code. Array element +@c values are no different than scalar variable values. +A contiguous array of four elements might look like @ifnotdocbook -as shown in @ref{figure-array-elements}: +@ref{figure-array-elements}, @end ifnotdocbook @ifdocbook -as shown in @inlineraw{docbook, <xref linkend="figure-array-elements"/>}: +@inlineraw{docbook, <xref linkend="figure-array-elements"/>}, @end ifdocbook +conceptually, if the element values are eight, @code{"foo"}, +@code{""}, and 30. @ifnotdocbook @float Figure,figure-array-elements @@ -14994,12 +14892,10 @@ as shown in @inlineraw{docbook, <xref linkend="figure-array-elements"/>}: @noindent Only the values are stored; the indices are implicit from the order of -the values. Here, 8 is the value at index zero, because 8 appears in the +the values. Here, eight is the value at index zero, because eight appears in the position with zero elements before it. -@c STARTOFRANGE arrin @cindex arrays, indexing -@c STARTOFRANGE inarr @cindex indexing arrays @cindex associative arrays @cindex arrays, associative @@ -15008,19 +14904,21 @@ that each array is a collection of pairs---an index and its corresponding array element value: @ifnotdocbook -@example -@r{Index} 3 @r{Value} 30 -@r{Index} 1 @r{Value} "foo" -@r{Index} 0 @r{Value} 8 -@r{Index} 2 @r{Value} "" -@end example +@c extra empty column to indent it right +@multitable @columnfractions .1 .1 .1 +@headitem @tab Index @tab Value +@item @tab @code{3} @tab @code{30} +@item @tab @code{1} @tab @code{"foo"} +@item @tab @code{0} @tab @code{8} +@item @tab @code{2} @tab @code{""} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15066,20 +14964,22 @@ at any time. For example, suppose a tenth element is added to the array whose value is @w{@code{"number ten"}}. The result is: @ifnotdocbook -@example -@r{Index} 10 @r{Value} "number ten" -@r{Index} 3 @r{Value} 30 -@r{Index} 1 @r{Value} "foo" -@r{Index} 0 @r{Value} 8 -@r{Index} 2 @r{Value} "" -@end example +@c extra empty column to indent it right +@multitable @columnfractions .1 .1 .2 +@headitem @tab Index @tab Value +@item @tab @code{10} @tab @code{"number ten"} +@item @tab @code{3} @tab @code{30} +@item @tab @code{1} @tab @code{"foo"} +@item @tab @code{0} @tab @code{8} +@item @tab @code{2} @tab @code{""} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15131,19 +15031,20 @@ an index. For example, the following is an array that translates words from English to French: @ifnotdocbook -@example -@r{Index} "dog" @r{Value} "chien" -@r{Index} "cat" @r{Value} "chat" -@r{Index} "one" @r{Value} "un" -@r{Index} 1 @r{Value} "un" -@end example +@multitable @columnfractions .1 .1 .1 +@headitem @tab Index @tab Value +@item @tab @code{"dog"} @tab @code{"chien"} +@item @tab @code{"cat"} @tab @code{"chat"} +@item @tab @code{"one"} @tab @code{"un"} +@item @tab @code{1} @tab @code{"un"} +@end multitable @end ifnotdocbook @docbook <informaltable> <tgroup cols="2"> -<colspec colname="1" align="center"/> -<colspec colname="2" align="center"/> +<colspec colname="1" align="left"/> +<colspec colname="2" align="left"/> <thead> <row> <entry>Index</entry> @@ -15185,7 +15086,7 @@ numbers and strings as indices. There are some subtleties to how numbers work when used as array subscripts; this is discussed in more detail in @ref{Numeric Array Subscripts}.) -Here, the number @code{1} isn't double quoted, because @command{awk} +Here, the number @code{1} isn't double-quoted, because @command{awk} automatically converts it to a string. @cindex @command{gawk}, @code{IGNORECASE} variable in @@ -15202,8 +15103,6 @@ that array's indices are consecutive integers starting at one. @command{awk}'s arrays are efficient---the time to access an element is independent of the number of elements in the array. -@c ENDOFRANGE arrin -@c ENDOFRANGE inarr @node Reference to Elements @subsection Referring to an Array Element @@ -15212,7 +15111,7 @@ is independent of the number of elements in the array. @cindex elements of arrays The principal way to use an array is to refer to one of its elements. -An array reference is an expression as follows: +An @dfn{array reference} is an expression as follows: @example @var{array}[@var{index-expression}] @@ -15222,8 +15121,11 @@ An array reference is an expression as follows: Here, @var{array} is the name of an array. The expression @var{index-expression} is the index of the desired element of the array. +@c 1/2015: Having the 4.3 in @samp is a little iffy. It's essentially +@c an expression though, so leave be. It's to early in the discussion +@c to mention that it's really a string. The value of the array reference is the current value of that array -element. For example, @code{foo[4.3]} is an expression for the element +element. For example, @code{foo[4.3]} is an expression referencing the element of array @code{foo} at index @samp{4.3}. @cindex arrays, unassigned elements @@ -15315,7 +15217,7 @@ assign to that element of the array. The following program takes a list of lines, each beginning with a line number, and prints them out in order of line number. The line numbers -are not in order when they are first read---instead they +are not in order when they are first read---instead, they are scrambled. This program sorts the lines by making an array using the line numbers as subscripts. The program then prints out the lines in sorted order of their numbers. It is a very simple program and gets @@ -15409,7 +15311,7 @@ program has previously used, with the variable @var{var} set to that index. The following program uses this form of the @code{for} statement. The first rule scans the input records and notes which words appear (at least once) in the input, by storing a one into the array @code{used} with -the word as index. The second rule scans the elements of @code{used} to +the word as the index. The second rule scans the elements of @code{used} to find all the distinct words that appear in the input. It prints each word that is more than 10 characters long and also prints the number of such words. @@ -15506,7 +15408,7 @@ and will vary from one version of @command{awk} to the next. Often, though, you may wish to do something simple, such as ``traverse the array by comparing the indices in ascending order,'' or ``traverse the array by comparing the values in descending order.'' -@command{gawk} provides two mechanisms which give you this control. +@command{gawk} provides two mechanisms that give you this control: @itemize @value{BULLET} @item @@ -15563,21 +15465,26 @@ across different environments.} which @command{gawk} uses internally to perform the sorting. @item "@@ind_str_desc" -String indices ordered from high to low. +Like @code{"@@ind_str_asc"}, but the +string indices are ordered from high to low. @item "@@ind_num_desc" -Numeric indices ordered from high to low. +Like @code{"@@ind_num_asc"}, but the +numeric indices are ordered from high to low. @item "@@val_type_desc" -Element values, based on type, ordered from high to low. +Like @code{"@@val_type_asc"}, but the +element values, based on type, are ordered from high to low. Subarrays, if present, come out first. @item "@@val_str_desc" -Element values, treated as strings, ordered from high to low. +Like @code{"@@val_str_asc"}, but the +element values, treated as strings, are ordered from high to low. Subarrays, if present, come out first. @item "@@val_num_desc" -Element values, treated as numbers, ordered from high to low. +Like @code{"@@val_num_asc"}, but the +element values, treated as numbers, are ordered from high to low. Subarrays, if present, come out first. @end table @@ -15800,7 +15707,7 @@ for (i in frequencies) @noindent This example removes all the elements from the array @code{frequencies}. Once an element is deleted, a subsequent @code{for} statement to scan the array -does not report that element and the @code{in} operator to check for +does not report that element and using the @code{in} operator to check for the presence of that element returns zero (i.e., false): @example @@ -16060,7 +15967,7 @@ a[1][2] = 2 This simulates a true two-dimensional array. Each subarray element can contain another subarray as a value, which in turn can hold other arrays as well. In this way, you can create arrays of three or more dimensions. -The indices can be any @command{awk} expression, including scalars +The indices can be any @command{awk} expressions, including scalars separated by commas (i.e., a regular @command{awk} simulated multidimensional subscript). So the following is valid in @command{gawk}: @@ -16072,7 +15979,7 @@ a[1][3][1, "name"] = "barney" Each subarray and the main array can be of different length. In fact, the elements of an array or its subarray do not all have to have the same type. This means that the main array and any of its subarrays can be -non-rectangular, or jagged in structure. You can assign a scalar value to +nonrectangular, or jagged in structure. You can assign a scalar value to the index @code{4} of the main array @code{a}, even though @code{a[1]} is itself an array and not a scalar: @@ -16096,7 +16003,8 @@ a[4][5][6][7] = "An element in a four-dimensional array" @noindent This removes the scalar value from index @code{4} and then inserts a -subarray of subarray of subarray containing a scalar. You can also +three-level nested subarray +containing a scalar. You can also delete an entire subarray or subarray of subarrays: @example @@ -16107,7 +16015,7 @@ a[4][5] = "An element in subarray a[4]" But recall that you can not delete the main array @code{a} and then use it as a scalar. -The built-in functions which take array arguments can also be used +The built-in functions that take array arguments can also be used with subarrays. For example, the following code fragment uses @code{length()} (@pxref{String Functions}) to determine the number of elements in the main array @code{a} and @@ -16137,7 +16045,7 @@ can be nested to scan all the elements of an array of arrays if it is rectangular in structure. In order to print the contents (scalar values) of a two-dimensional array of arrays (i.e., in which each first-level element is itself an -array, not necessarily of the same length) +array, not necessarily of the same length), you could use the following code: @example @@ -16237,9 +16145,9 @@ versions of @command{awk}. @item Standard @command{awk} simulates multidimensional arrays by separating -subscript values with a comma. The values are concatenated into a +subscript values with commas. The values are concatenated into a single string, separated by the value of @code{SUBSEP}. The fact -that such a subscript was created in this way is not retained; thus +that such a subscript was created in this way is not retained; thus, changing @code{SUBSEP} may have unexpected consequences. You can use @samp{(@var{sub1}, @var{sub2}, @dots{}) in @var{array}} to see if such a multidimensional subscript exists in @var{array}. @@ -16248,7 +16156,7 @@ a multidimensional subscript exists in @var{array}. @command{gawk} provides true arrays of arrays. You use a separate set of square brackets for each dimension in such an array: @code{data[row][col]}, for example. Array elements may thus be either -scalar values (number or string) or another array. +scalar values (number or string) or other arrays. @item Use the @code{isarray()} built-in function to determine if an array @@ -16256,14 +16164,11 @@ element is itself a subarray. @end itemize -@c ENDOFRANGE arrs @node Functions @chapter Functions -@c STARTOFRANGE funcbi @cindex functions, built-in -@c STARTOFRANGE bifunc @cindex built-in functions This @value{CHAPTER} describes @command{awk}'s built-in functions, which fall into three categories: numeric, string, and I/O. @@ -16276,6 +16181,9 @@ Besides the built-in functions, @command{awk} has provisions for writing new functions that the rest of a program can use. The second half of this @value{CHAPTER} describes these @dfn{user-defined} functions. +Finally, we explore indirect function calls, a @command{gawk}-specific +extension that lets you determine at runtime what function is to +be called. @menu * Built-in:: Summarizes the built-in functions. @@ -16285,7 +16193,7 @@ The second half of this @value{CHAPTER} describes these @end menu @node Built-in -@section Built-In Functions +@section Built-in Functions @dfn{Built-in} functions are always available for your @command{awk} program to call. This @value{SECTION} defines all @@ -16308,7 +16216,7 @@ but are summarized here for your convenience. @end menu @node Calling Built-in -@subsection Calling Built-In Functions +@subsection Calling Built-in Functions To call one of @command{awk}'s built-in functions, write the name of the function followed @@ -16359,7 +16267,7 @@ j = atan2(++i, i *= 2) @end example If the order of evaluation is left to right, then @code{i} first becomes -6, and then 12, and @code{atan2()} is called with the two arguments 6 +six, and then 12, and @code{atan2()} is called with the two arguments six and 12. But if the order of evaluation is right to left, @code{i} first becomes 10, then 11, and @code{atan2()} is called with the two arguments 11 and 10. @@ -16440,7 +16348,7 @@ In fact, @command{gawk} uses the BSD @code{random()} function, which is considerably better than @code{rand()}, to produce random numbers.} Often random integers are needed instead. Following is a user-defined function -that can be used to obtain a random non-negative integer less than @var{n}: +that can be used to obtain a random nonnegative integer less than @var{n}: @example function randint(n) @@ -16535,7 +16443,7 @@ implementations. The functions in this @value{SECTION} look at or change the text of one or more strings. -@code{gawk} understands locales (@pxref{Locales}), and does all +@command{gawk} understands locales (@pxref{Locales}) and does all string processing in terms of @emph{characters}, not @emph{bytes}. This distinction is particularly important to understand for locales where one character may be represented by multiple bytes. Thus, for @@ -16624,7 +16532,7 @@ a[2] = "de" a[3] = "sac" @end example -The @code{asorti()} function works similarly to @code{asort()}, however, +The @code{asorti()} function works similarly to @code{asort()}; however, the @emph{indices} are sorted, instead of the values. Thus, in the previous example, starting with the same initial set of indices and values in @code{a}, calling @samp{asorti(a)} would yield: @@ -16739,7 +16647,7 @@ If @var{find} is not found, @code{index()} returns zero. With BWK @command{awk} and @command{gawk}, it is a fatal error to use a regexp constant for @var{find}. Other implementations allow it, simply treating the regexp -constant as an expression meaning @samp{$0 ~ /regexp/}. @value{DARKCORNER}. +constant as an expression meaning @samp{$0 ~ /regexp/}. @value{DARKCORNER} @item @code{length(}[@var{string}]@code{)} @cindexawkfunc{length} @@ -16822,7 +16730,7 @@ If @option{--posix} is supplied, using an array argument is a fatal error @cindex string, regular expression match @cindex match regexp in string Search @var{string} for the -longest, leftmost substring matched by the regular expression, +longest, leftmost substring matched by the regular expression @var{regexp} and return the character position (index) at which that substring begins (one, if it starts at the beginning of @var{string}). If no match is found, return zero. @@ -16834,7 +16742,7 @@ In the latter case, the string is treated as a regexp to be matched. discussion of the difference between the two forms, and the implications for writing your program correctly. -The order of the first two arguments is backwards from most other string +The order of the first two arguments is the opposite of most other string functions that work with regular expressions, such as @code{sub()} and @code{gsub()}. It might help to remember that for @code{match()}, the order is the same as for the @samp{~} operator: @@ -16923,7 +16831,7 @@ $ @kbd{echo foooobazbarrrrr |} @end example There may not be subscripts for the start and index for every parenthesized -subexpression, because they may not all have matched text; thus they +subexpression, because they may not all have matched text; thus, they should be tested for with the @code{in} operator (@pxref{Reference to Elements}). @@ -16970,13 +16878,13 @@ a regexp describing where to split @var{string} (much as @code{FS} can be a regexp describing where to split input records). If @var{fieldsep} is omitted, the value of @code{FS} is used. @code{split()} returns the number of elements created. -@var{seps} is a @command{gawk} extension with @code{@var{seps}[@var{i}]} +@var{seps} is a @command{gawk} extension, with @code{@var{seps}[@var{i}]} being the separator string between @code{@var{array}[@var{i}]} and @code{@var{array}[@var{i}+1]}. If @var{fieldsep} is a single -space then any leading whitespace goes into @code{@var{seps}[0]} and +space, then any leading whitespace goes into @code{@var{seps}[0]} and any trailing -whitespace goes into @code{@var{seps}[@var{n}]} where @var{n} is the +whitespace goes into @code{@var{seps}[@var{n}]}, where @var{n} is the return value of @code{split()} (i.e., the number of elements in @var{array}). @@ -16989,7 +16897,7 @@ split("cul-de-sac", a, "-", seps) @noindent @cindex strings splitting, example -splits the string @samp{cul-de-sac} into three fields using @samp{-} as the +splits the string @code{"cul-de-sac"} into three fields using @samp{-} as the separator. It sets the contents of the array @code{a} as follows: @example @@ -17014,19 +16922,18 @@ As with input field-splitting, when the value of @var{fieldsep} is the elements of @var{array} but not in @var{seps}, and the elements are separated by runs of whitespace. -Also, as with input field-splitting, if @var{fieldsep} is the null string, each +Also, as with input field splitting, if @var{fieldsep} is the null string, each individual character in the string is split into its own array element. @value{COMMONEXT} Note, however, that @code{RS} has no effect on the way @code{split()} -works. Even though @samp{RS = ""} causes newline to also be an input +works. Even though @samp{RS = ""} causes the newline character to also be an input field separator, this does not affect how @code{split()} splits strings. @cindex dark corner, @code{split()} function Modern implementations of @command{awk}, including @command{gawk}, allow -the third argument to be a regexp constant (@code{/abc/}) as well as a -string. -@value{DARKCORNER} +the third argument to be a regexp constant (@w{@code{/}@dots{}@code{/}}) +as well as a string. @value{DARKCORNER} The POSIX standard allows this as well. @DBXREF{Computed Regexps} for a discussion of the difference between using a string constant or a regexp constant, @@ -17163,7 +17070,7 @@ an @samp{&}: @cindex @code{sub()} function, arguments of @cindex @code{gsub()} function, arguments of As mentioned, the third argument to @code{sub()} must -be a variable, field or array element. +be a variable, field, or array element. Some versions of @command{awk} allow the third argument to be an expression that is not an lvalue. In such a case, @code{sub()} still searches for the pattern and returns zero or one, but the result of @@ -17322,8 +17229,8 @@ example, @code{"a\qb"} is treated as @code{"aqb"}. At the runtime level, the various functions handle sequences of @samp{\} and @samp{&} differently. The situation is (sadly) somewhat complex. -Historically, the @code{sub()} and @code{gsub()} functions treated the two -character sequence @samp{\&} specially; this sequence was replaced in +Historically, the @code{sub()} and @code{gsub()} functions treated the +two-character sequence @samp{\&} specially; this sequence was replaced in the generated text with a single @samp{&}. Any other @samp{\} within the @var{replacement} string that did not precede an @samp{&} was passed through unchanged. This is illustrated in @ref{table-sub-escapes}. @@ -17381,7 +17288,7 @@ _bigskip} @end float @noindent -This table shows both the lexical-level processing, where +This table shows the lexical-level processing, where an odd number of backslashes becomes an even number at the runtime level, as well as the runtime processing done by @code{sub()}. (For the sake of simplicity, the rest of the following tables only show the @@ -17402,7 +17309,7 @@ This is shown in @ref{table-sub-proposed}. @float Table,table-sub-proposed -@caption{GNU @command{awk} rules for @code{sub()} and backslash} +@caption{@command{gawk} rules for @code{sub()} and backslash} @tex \vbox{\bigskip % We need more characters for escape and tab ... @@ -17447,7 +17354,7 @@ _bigskip} @end float In a nutshell, at the runtime level, there are now three special sequences -of characters (@samp{\\\&}, @samp{\\&} and @samp{\&}) whereas historically +of characters (@samp{\\\&}, @samp{\\&}, and @samp{\&}) whereas historically there was only one. However, as in the historical case, any @samp{\} that is not part of one of these three sequences is not special and appears in the output literally. @@ -17513,7 +17420,7 @@ The only case where the difference is noticeable is the last one: @samp{\\\\} is seen as @samp{\\} and produces @samp{\} instead of @samp{\\}. Starting with @value{PVERSION} 3.1.4, @command{gawk} followed the POSIX rules -when @option{--posix} is specified (@pxref{Options}). Otherwise, +when @option{--posix} was specified (@pxref{Options}). Otherwise, it continued to follow the proposed rules, as that had been its behavior for many years. @@ -17581,7 +17488,7 @@ _bigskip} @end ifnottex @end float -Because of the complexity of the lexical and runtime level processing +Because of the complexity of the lexical- and runtime-level processing and the special cases for @code{sub()} and @code{gsub()}, we recommend the use of @command{gawk} and @code{gensub()} when you have to do substitutions. @@ -17607,6 +17514,7 @@ for more information. When closing a coprocess, it is occasionally useful to first close one end of the two-way pipe and then to close the other. This is done by providing a second argument to @code{close()}. This second argument +(@var{how}) should be one of the two string values @code{"to"} or @code{"from"}, indicating which end of the pipe to close. Case in the string does not matter. @@ -17633,7 +17541,7 @@ every little bit of information as soon as it is ready. However, sometimes it is necessary to force a program to @dfn{flush} its buffers (i.e., write the information to its destination, even if a buffer is not full). This is the purpose of the @code{fflush()} function---@command{gawk} also -buffers its output and the @code{fflush()} function forces +buffers its output, and the @code{fflush()} function forces @command{gawk} to flush its buffers. @cindex extensions, common@comma{} @code{fflush()} function @@ -17654,7 +17562,7 @@ would flush only the standard output if there was no argument, and flush all output files and pipes if the argument was the null string. This was changed in order to be compatible with Brian Kernighan's @command{awk}, in the hope that standardizing this -feature in POSIX would then be easier (which indeed helped). +feature in POSIX would then be easier (which indeed proved to be the case). With @command{gawk}, you can use @samp{fflush("/dev/stdout")} if you wish to flush @@ -17665,7 +17573,7 @@ only the standard output. @c @cindex warnings, automatic @cindex troubleshooting, @code{fflush()} function @code{fflush()} returns zero if the buffer is successfully flushed; -otherwise, it returns non-zero. (@command{gawk} returns @minus{}1.) +otherwise, it returns a nonzero value. (@command{gawk} returns @minus{}1.) In the case where all buffers are flushed, the return value is zero only if all buffers were flushed successfully. Otherwise, it is @minus{}1, and @command{gawk} warns about the problem @var{filename}. @@ -17678,8 +17586,8 @@ In such a case, @code{fflush()} returns @minus{}1, as well. @sidebar Interactive Versus Noninteractive Buffering @cindex buffering, interactive vs.@: noninteractive -As a side point, buffering issues can be even more confusing, depending -upon whether your program is @dfn{interactive} (i.e., communicating +As a side point, buffering issues can be even more confusing if +your program is @dfn{interactive} (i.e., communicating with a user sitting at a keyboard).@footnote{A program is interactive if the standard output is connected to a terminal device. On modern systems, this means your keyboard and screen.} @@ -17722,7 +17630,7 @@ it is all buffered and sent down the pipe to @command{cat} in one shot. @cindexawkfunc{system} @cindex invoke shell command @cindex interacting with other programs -Execute the operating-system +Execute the operating system command @var{command} and then return to the @command{awk} program. Return @var{command}'s exit status. @@ -17826,18 +17734,14 @@ you would see the latter (undesirable) output. @subsection Time Functions @cindex time functions -@c STARTOFRANGE tst @cindex timestamps -@c STARTOFRANGE logftst @cindex log files, timestamps in -@c STARTOFRANGE filogtst @cindex files, log@comma{} timestamps in -@c STARTOFRANGE gawtst @cindex @command{gawk}, timestamps @cindex POSIX @command{awk}, timestamps and -@code{awk} programs are commonly used to process log files +@command{awk} programs are commonly used to process log files containing timestamp information, indicating when a -particular log record was written. Many programs log their timestamp +particular log record was written. Many programs log their timestamps in the form returned by the @code{time()} system call, which is the number of seconds since a particular epoch. On POSIX-compliant systems, it is the number of seconds since @@ -17898,7 +17802,7 @@ The values of these numbers need not be within the ranges specified; for example, an hour of @minus{}1 means 1 hour before midnight. The origin-zero Gregorian calendar is assumed, with year 0 preceding year 1 and year @minus{}1 preceding year 0. -The time is assumed to be in the local timezone. +The time is assumed to be in the local time zone. If the daylight-savings flag is positive, the time is assumed to be daylight savings time; if zero, the time is assumed to be standard time; and if negative (the default), @code{mktime()} attempts to determine @@ -17910,7 +17814,6 @@ is out of range, @code{mktime()} returns @minus{}1. @cindex @command{gawk}, @code{PROCINFO} array in @cindex @code{PROCINFO} array @item @code{strftime(}[@var{format} [@code{,} @var{timestamp} [@code{,} @var{utc-flag}] ] ]@code{)} -@c STARTOFRANGE strf @cindexgawkfunc{strftime} @cindex format time string Format the time specified by @var{timestamp} @@ -18059,12 +17962,12 @@ Equivalent to specifying @samp{%H:%M:%S}. The weekday as a decimal number (1--7). Monday is day one. @item %U -The week number of the year (the first Sunday as the first day of week one) +The week number of the year (with the first Sunday as the first day of week one) as a decimal number (00--53). @c @cindex ISO 8601 @item %V -The week number of the year (the first Monday as the first +The week number of the year (with the first Monday as the first day of week one) as a decimal number (01--53). The method for determining the week number is as specified by ISO 8601. (To wit: if the week containing January 1 has four or more days in the @@ -18075,7 +17978,7 @@ and the next week is week one.) The weekday as a decimal number (0--6). Sunday is day zero. @item %W -The week number of the year (the first Monday as the first day of week one) +The week number of the year (with the first Monday as the first day of week one) as a decimal number (00--53). @item %x @@ -18095,8 +17998,8 @@ The full year as a decimal number (e.g., 2015). @c @cindex RFC 822 @c @cindex RFC 1036 @item %z -The timezone offset in a +HHMM format (e.g., the format necessary to -produce RFC 822/RFC 1036 date headers). +The time zone offset in a @samp{+@var{HHMM}} format (e.g., the format +necessary to produce RFC 822/RFC 1036 date headers). @item %Z The time zone name or abbreviation; no characters if @@ -18159,7 +18062,6 @@ The time as a decimal timestamp in seconds since the epoch. The date in VMS format (e.g., @samp{20-JUN-1991}). @end ignore @end table -@c ENDOFRANGE strf Additionally, the alternative representations are recognized but their normal representations are used. @@ -18210,23 +18112,14 @@ gawk 'BEGIN @{ exit exitval @}' "$@@" @end example -@c ENDOFRANGE tst -@c ENDOFRANGE logftst -@c ENDOFRANGE filogtst -@c ENDOFRANGE gawtst @node Bitwise Functions @subsection Bit-Manipulation Functions @cindex bit-manipulation functions -@c STARTOFRANGE bit @cindex bitwise, operations -@c STARTOFRANGE and @cindex AND bitwise operation -@c STARTOFRANGE oro @cindex OR bitwise operation -@c STARTOFRANGE xor @cindex XOR bitwise operation -@c STARTOFRANGE opbit @cindex operations, bitwise @quotation @i{I can explain it for you, but I can't understand it for you.} @@ -18246,7 +18139,7 @@ The operations are described in @ref{table-bitwise-ops}. @ifnottex @ifnotdocbook @display - Bit Operator + Bit operator | AND | OR | XOR |---+---+---+---+---+--- Operands | 0 | 1 | 0 | 1 | 0 | 1 @@ -18304,7 +18197,7 @@ Operands | 0 | 1 | 0 | 1 | 0 | 1 <tbody> <row> <entry colsep="0"></entry> -<entry spanname="optitle"><emphasis role="bold">Bit Operator</emphasis></entry> +<entry spanname="optitle"><emphasis role="bold">Bit operator</emphasis></entry> </row> <row rowsep="1"> @@ -18368,10 +18261,9 @@ of a given value. Finally, two other common operations are to shift the bits left or right. For example, if you have a bit string @samp{10111001} and you shift it right by three bits, you end up with @samp{00010111}.@footnote{This example -shows that 0's come in on the left side. For @command{gawk}, this is +shows that zeros come in on the left side. For @command{gawk}, this is always true, but in some languages, it's possible to have the left side -fill with 1's.} -@c Purposely decided to use 0's and 1's here. 2/2001. +fill with ones.} If you start over again with @samp{10111001} and shift it left by three bits, you end up with @samp{11001000}. The following list describes @command{gawk}'s built-in functions that implement the bitwise operations. @@ -18425,7 +18317,7 @@ that illustrates the use of these functions: @example @group @c file eg/lib/bits2str.awk -# bits2str --- turn a byte into readable 1's and 0's +# bits2str --- turn a byte into readable ones and zeros function bits2str(bits, data, mask) @{ @@ -18499,15 +18391,16 @@ $ @kbd{gawk -f testbits.awk} @cindex converting, numbers to strings @cindex number as string of bits The @code{bits2str()} function turns a binary number into a string. -The number @code{1} represents a binary value where the rightmost bit -is set to 1. Using this mask, +Initializing @code{mask} to one creates +a binary value where the rightmost bit +is set to one. Using this mask, the function repeatedly checks the rightmost bit. ANDing the mask with the value indicates whether the -rightmost bit is 1 or not. If so, a @code{"1"} is concatenated onto the front +rightmost bit is one or not. If so, a @code{"1"} is concatenated onto the front of the string. Otherwise, a @code{"0"} is added. The value is then shifted right by one bit and the loop continues -until there are no more 1 bits. +until there are no more one bits. If the initial value is zero, it returns a simple @code{"0"}. Otherwise, at the end, it pads the value with zeros to represent multiples @@ -18518,11 +18411,6 @@ decimal and octal values for the same numbers (@pxref{Nondecimal-numbers}), and then demonstrates the results of the @code{compl()}, @code{lshift()}, and @code{rshift()} functions. -@c ENDOFRANGE bit -@c ENDOFRANGE and -@c ENDOFRANGE oro -@c ENDOFRANGE xor -@c ENDOFRANGE opbit @node Type Functions @subsection Getting Type Information @@ -18536,7 +18424,7 @@ that traverses every element of an array of arrays @cindexgawkfunc{isarray} @cindex scalar or array @item isarray(@var{x}) -Return a true value if @var{x} is an array. Otherwise return false. +Return a true value if @var{x} is an array. Otherwise, return false. @end table @code{isarray()} is meant for use in two circumstances. The first is when @@ -18597,20 +18485,16 @@ The default value for @var{category} is @code{"LC_MESSAGES"}. Return the plural form used for @var{number} of the translation of @var{string1} and @var{string2} in text domain @var{domain} for locale category @var{category}. @var{string1} is the -English singular variant of a message, and @var{string2} the English plural +English singular variant of a message, and @var{string2} is the English plural variant of the same message. The default value for @var{domain} is the current value of @code{TEXTDOMAIN}. The default value for @var{category} is @code{"LC_MESSAGES"}. @end table -@c ENDOFRANGE funcbi -@c ENDOFRANGE bifunc @node User-defined @section User-Defined Functions -@c STARTOFRANGE udfunc @cindex user-defined functions -@c STARTOFRANGE funcud @cindex functions, user-defined Complicated @command{awk} programs can often be simplified by defining your own functions. User-defined functions can be called just like @@ -18630,12 +18514,11 @@ them (i.e., to tell @command{awk} what they should do). @subsection Function Definition Syntax @quotation -@i{It's entirely fair to say that the @command{awk} syntax for local +@i{It's entirely fair to say that the awk syntax for local variable definitions is appallingly awful.} @author Brian Kernighan @end quotation -@c STARTOFRANGE fdef @cindex functions, defining Definitions of functions can appear anywhere between the rules of an @command{awk} program. Thus, the general form of an @command{awk} program is @@ -18673,14 +18556,23 @@ the call. A function cannot have two parameters with the same name, nor may it have a parameter with the same name as the function itself. -In addition, according to the POSIX standard, function parameters + +@quotation CAUTION +According to the POSIX standard, function parameters cannot have the same name as one of the special predefined variables -(@pxref{Built-in Variables}). Not all versions of @command{awk} enforce -this restriction. +(@pxref{Built-in Variables}), nor may a function parameter have the +same name as another function. + +Not all versions of @command{awk} enforce +these restrictions. +@command{gawk} always enforces the first restriction. +With @option{--posix} (@pxref{Options}), +it also enforces the second restriction. +@end quotation Local variables act like the empty string if referenced where a string value is required, and like zero if referenced where a numeric value -is required. This is the same as regular variables that have never been +is required. This is the same as the behavior of regular variables that have never been assigned a value. (There is more to understand about local variables; @pxref{Dynamic Typing}.) @@ -18714,7 +18606,7 @@ During execution of the function body, the arguments and local variable values hide, or @dfn{shadow}, any variables of the same names used in the rest of the program. The shadowed variables are not accessible in the function definition, because there is no way to name them while their -names have been taken away for the local variables. All other variables +names have been taken away for the arguments and local variables. All other variables used in the @command{awk} program can be referenced or set normally in the function's body. @@ -18781,7 +18673,7 @@ function myprint(num) @end example @noindent -To illustrate, here is an @command{awk} rule that uses our @code{myprint} +To illustrate, here is an @command{awk} rule that uses our @code{myprint()} function: @example @@ -18822,13 +18714,13 @@ in an array and start over with a new list of elements (@pxref{Delete}). Instead of having to repeat this loop everywhere that you need to clear out -an array, your program can just call @code{delarray}. +an array, your program can just call @code{delarray()}. (This guarantees portability. The use of @samp{delete @var{array}} to delete the contents of an entire array is a relatively recent@footnote{Late in 2012.} addition to the POSIX standard.) The following is an example of a recursive function. It takes a string -as an input parameter and returns the string in backwards order. +as an input parameter and returns the string in reverse order. Recursive functions must always have a test that stops the recursion. In this case, the recursion terminates when the input string is already empty: @@ -18882,12 +18774,10 @@ You might think that @code{ctime()} could use @code{PROCINFO["strftime"]} for its format string. That would be a mistake, because @code{ctime()} is supposed to return the time formatted in a standard fashion, and user-level code could have changed @code{PROCINFO["strftime"]}. -@c ENDOFRANGE fdef @node Function Caveats @subsection Calling User-Defined Functions -@c STARTOFRANGE fudc @cindex functions, user-defined, calling @dfn{Calling a function} means causing the function to run and do its job. A function call is an expression and its value is the value returned by @@ -18927,7 +18817,7 @@ an error. @cindex local variables, in a function @cindex variables, local to a function -Unlike many languages, +Unlike in many languages, there is no way to make a variable local to a @code{@{} @dots{} @code{@}} block in @command{awk}, but you can make a variable local to a function. It is good practice to do so whenever a variable is needed only in that @@ -18936,7 +18826,7 @@ function. To make a variable local to a function, simply declare the variable as an argument after the actual function arguments (@pxref{Definition Syntax}). -Look at the following example where variable +Look at the following example, where variable @code{i} is a global variable used by both functions @code{foo()} and @code{bar()}: @@ -18977,7 +18867,7 @@ foo's i=3 top's i=3 @end example -If you want @code{i} to be local to both @code{foo()} and @code{bar()} do as +If you want @code{i} to be local to both @code{foo()} and @code{bar()}, do as follows (the extra space before @code{i} is a coding convention to indicate that @code{i} is a local variable, not an argument): @@ -19065,7 +18955,7 @@ declare explicitly whether the arguments are passed @dfn{by value} or @dfn{by reference}. Instead, the passing convention is determined at runtime when -the function is called according to the following rule: +the function is called, according to the following rule: if the argument is an array variable, then it is passed by reference. Otherwise, the argument is passed by value. @@ -19142,7 +19032,7 @@ prints @samp{a[1] = 1, a[2] = two, a[3] = 3}, because @cindex undefined functions @cindex functions, undefined Some @command{awk} implementations allow you to call a function that -has not been defined. They only report a problem at runtime when the +has not been defined. They only report a problem at runtime, when the program actually tries to call the function. For example: @example @@ -19179,7 +19069,6 @@ or the @code{nextfile} statement @end ifnotdocbook inside a user-defined function. @command{gawk} does not have this limitation. -@c ENDOFRANGE fudc @node Return Statement @subsection The @code{return} Statement @@ -19202,15 +19091,15 @@ makes the returned value undefined, and therefore, unpredictable. In practice, though, all versions of @command{awk} simply return the null string, which acts like zero if used in a numeric context. -A @code{return} statement with no value expression is assumed at the end of -every function definition. So if control reaches the end of the function -body, then technically, the function returns an unpredictable value. +A @code{return} statement without an @var{expression} is assumed at the end of +every function definition. So, if control reaches the end of the function +body, then technically the function returns an unpredictable value. In practice, it returns the empty string. @command{awk} does @emph{not} warn you if you use the return value of such a function. Sometimes, you want to write a function for what it does, not for what it returns. Such a function corresponds to a @code{void} function -in C, C++ or Java, or to a @code{procedure} in Ada. Thus, it may be appropriate to not +in C, C++, or Java, or to a @code{procedure} in Ada. Thus, it may be appropriate to not return any value; simply bear in mind that you should not be using the return value of such a function. @@ -19307,7 +19196,6 @@ does report the second error. Usually, such things aren't a big issue, but it's worth being aware of them. -@c ENDOFRANGE udfunc @node Indirect Calls @section Indirect Function Calls @@ -19330,13 +19218,15 @@ function calls, you can specify the name of the function to call as a string variable, and then call the function. Let's look at an example. Suppose you have a file with your test scores for the classes you -are taking. The first field is the class name. The following fields +are taking, and +you wish to get the sum and the average of +your test scores. +The first field is the class name. The following fields are the functions to call to process the data, up to a ``marker'' field @samp{data:}. Following the marker, to the end of the record, are the various numeric test scores. -Here is the initial file; you wish to get the sum and the average of -your test scores: +Here is the initial file: @example @c file eg/data/class_data1 @@ -19419,9 +19309,9 @@ function sum(first, last, ret, i) @c endfile @end example -These two functions expect to work on fields; thus the parameters +These two functions expect to work on fields; thus, the parameters @code{first} and @code{last} indicate where in the fields to start and end. -Otherwise they perform the expected computations and are not unusual: +Otherwise, they perform the expected computations and are not unusual: @example @c file eg/prog/indirectcall.awk @@ -19480,8 +19370,8 @@ The ability to use indirect function calls is more powerful than you may think at first. The C and C++ languages provide ``function pointers,'' which are a mechanism for calling a function chosen at runtime. One of the most well-known uses of this ability is the C @code{qsort()} function, which sorts -an array using the famous ``quick sort'' algorithm -(see @uref{http://en.wikipedia.org/wiki/Quick_sort, the Wikipedia article} +an array using the famous ``quicksort'' algorithm +(see @uref{http://en.wikipedia.org/wiki/Quicksort, the Wikipedia article} for more information). To use this function, you supply a pointer to a comparison function. This mechanism allows you to sort arbitrary data in an arbitrary fashion. @@ -19500,11 +19390,11 @@ We can do something similar using @command{gawk}, like this: # January 2009 @c endfile - @end ignore @c file eg/lib/quicksort.awk -# quicksort --- C.A.R. Hoare's quick sort algorithm. See Wikipedia -# or almost any algorithms or computer science text + +# quicksort --- C.A.R. Hoare's quicksort algorithm. See Wikipedia +# or almost any algorithms or computer science text. @c endfile @ignore @c file eg/lib/quicksort.awk @@ -19542,7 +19432,7 @@ function quicksort_swap(data, i, j, temp) The @code{quicksort()} function receives the @code{data} array, the starting and ending indices to sort (@code{left} and @code{right}), and the name of a function that -performs a ``less than'' comparison. It then implements the quick sort algorithm. +performs a ``less than'' comparison. It then implements the quicksort algorithm. To make use of the sorting function, we return to our previous example. The first thing to do is write some comparison functions: @@ -19733,7 +19623,7 @@ for (i = 1; i <= n; i++) @end example @noindent -@code{gawk} looks up the actual function to call only once. +@command{gawk} looks up the actual function to call only once. @node Functions Summary @section Summary @@ -19800,7 +19690,6 @@ program. This is equivalent to function pointers in C and C++. @end itemize -@c ENDOFRANGE funcud @ifnotinfo @part @value{PART2}Problem Solving with @command{awk} @@ -19822,18 +19711,15 @@ It contains the following chapters: @node Library Functions @chapter A Library of @command{awk} Functions -@c STARTOFRANGE libf @cindex libraries of @command{awk} functions -@c STARTOFRANGE flib @cindex functions, library -@c STARTOFRANGE fudlib @cindex functions, user-defined, library of @DBREF{User-defined} describes how to write your own @command{awk} functions. Writing functions is important, because it allows you to encapsulate algorithms and program tasks in a single place. It simplifies programming, making program development more -manageable, and making programs more readable. +manageable and making programs more readable. @cindex Kernighan, Brian @cindex Plauger, P.J.@: @@ -19962,7 +19848,7 @@ often use variable names like these for their own purposes. The example programs shown in this @value{CHAPTER} all start the names of their private variables with an underscore (@samp{_}). Users generally don't use leading underscores in their variable names, so this convention immediately -decreases the chances that the variable name will be accidentally shared +decreases the chances that the variable names will be accidentally shared with the user's program. @cindex @code{_} (underscore), in names of private variables @@ -19980,8 +19866,8 @@ show how our own @command{awk} programming style has evolved and to provide some basis for this discussion.} As a final note on variable naming, if a function makes global variables -available for use by a main program, it is a good convention to start that -variable's name with a capital letter---for +available for use by a main program, it is a good convention to start those +variables' names with a capital letter---for example, @code{getopt()}'s @code{Opterr} and @code{Optind} variables (@pxref{Getopt Function}). The leading capital letter indicates that it is global, while the fact that @@ -19992,7 +19878,7 @@ not one of @command{awk}'s predefined variables, such as @code{FS}. It is also important that @emph{all} variables in library functions that do not need to save state are, in fact, declared local.@footnote{@command{gawk}'s @option{--dump-variables} command-line -option is useful for verifying this.} If this is not done, the variable +option is useful for verifying this.} If this is not done, the variables could accidentally be used in the user's program, leading to bugs that are very difficult to track down: @@ -20149,13 +20035,9 @@ be tested with @command{gawk} and the results compared to the built-in @node Assert Function @subsection Assertions -@c STARTOFRANGE asse @cindex assertions -@c STARTOFRANGE assef @cindex @code{assert()} function (C library) -@c STARTOFRANGE libfass @cindex libraries of @command{awk} functions, assertions -@c STARTOFRANGE flibass @cindex functions, library, assertions @cindex @command{awk} programs, lengthy, assertions When writing large programs, it is often useful to know @@ -20194,7 +20076,7 @@ Following is the function: @example @c file eg/lib/assert.awk -# assert --- assert that a condition is true. Otherwise exit. +# assert --- assert that a condition is true. Otherwise, exit. @c endfile @ignore @@ -20230,7 +20112,7 @@ is false, it prints a message to standard error, using the @code{string} parameter to describe the failed condition. It then sets the variable @code{_assert_exit} to one and executes the @code{exit} statement. The @code{exit} statement jumps to the @code{END} rule. If the @code{END} -rules finds @code{_assert_exit} to be true, it exits immediately. +rule finds @code{_assert_exit} to be true, it exits immediately. The purpose of the test in the @code{END} rule is to keep any other @code{END} rules from running. When an assertion fails, the @@ -20271,10 +20153,6 @@ most likely causing the program to hang as it waits for input. There is a simple workaround to this: make sure that such a @code{BEGIN} rule always ends with an @code{exit} statement. -@c ENDOFRANGE asse -@c ENDOFRANGE assef -@c ENDOFRANGE flibass -@c ENDOFRANGE libfass @node Round Function @subsection Rounding Numbers @@ -20526,7 +20404,7 @@ all the strings in an array into one long string. The following function, the application programs (@pxref{Sample Programs}). -Good function design is important; this function needs to be general but it +Good function design is important; this function needs to be general, but it should also have a reasonable default behavior. It is called with an array as well as the beginning and ending indices of the elements in the array to be merged. This assumes that the array indices are numeric---a reasonable @@ -20674,7 +20552,7 @@ allowed the user to supply an optional timestamp value to use instead of the current time. @node Readfile Function -@subsection Reading a Whole File At Once +@subsection Reading a Whole File at Once Often, it is convenient to have the entire contents of a file available in memory as a single string. A straightforward but naive way to @@ -20731,13 +20609,13 @@ function readfile(file, tmp, save_rs) It works by setting @code{RS} to @samp{^$}, a regular expression that will never match if the file has contents. @command{gawk} reads data from -the file into @code{tmp} attempting to match @code{RS}. The match fails +the file into @code{tmp}, attempting to match @code{RS}. The match fails after each read, but fails quickly, such that @command{gawk} fills @code{tmp} with the entire contents of the file. (@DBXREF{Records} for information on @code{RT} and @code{RS}.) In the case that @code{file} is empty, the return value is the null -string. Thus calling code may use something like: +string. Thus, calling code may use something like: @example contents = readfile("/some/path") @@ -20748,7 +20626,7 @@ if (length(contents) == 0) This tests the result to see if it is empty or not. An equivalent test would be @samp{contents == ""}. -@xref{Extension Sample Readfile}, for an extension function that +@DBXREF{Extension Sample Readfile} for an extension function that also reads an entire file into memory. @node Shell Quoting @@ -20832,11 +20710,8 @@ function shell_quote(s, # parameter @node Data File Management @section @value{DDF} Management -@c STARTOFRANGE dataf @cindex files, managing -@c STARTOFRANGE libfdataf @cindex libraries of @command{awk} functions, managing, data files -@c STARTOFRANGE flibdataf @cindex functions, library, managing data files This @value{SECTION} presents functions that are useful for managing command-line @value{DF}s. @@ -20858,8 +20733,8 @@ The @code{BEGIN} and @code{END} rules are each executed exactly once, at the beginning and end of your @command{awk} program, respectively (@pxref{BEGIN/END}). We (the @command{gawk} authors) once had a user who mistakenly thought that the -@code{BEGIN} rule is executed at the beginning of each @value{DF} and the -@code{END} rule is executed at the end of each @value{DF}. +@code{BEGIN} rules were executed at the beginning of each @value{DF} and the +@code{END} rules were executed at the end of each @value{DF}. When informed that this was not the case, the user requested that we add new special @@ -20899,7 +20774,7 @@ END @{ endfile(FILENAME) @} This file must be loaded before the user's ``main'' program, so that the rule it supplies is executed first. -This rule relies on @command{awk}'s @code{FILENAME} variable that +This rule relies on @command{awk}'s @code{FILENAME} variable, which automatically changes for each new @value{DF}. The current @value{FN} is saved in a private variable, @code{_oldfilename}. If @code{FILENAME} does not equal @code{_oldfilename}, then a new @value{DF} is being processed and @@ -20915,7 +20790,7 @@ first @value{DF}. The program also supplies an @code{END} rule to do the final processing for the last file. Because this @code{END} rule comes before any @code{END} rules supplied in the ``main'' program, @code{endfile()} is called first. Once -again the value of multiple @code{BEGIN} and @code{END} rules should be clear. +again, the value of multiple @code{BEGIN} and @code{END} rules should be clear. @cindex @code{beginfile()} user-defined function @cindex @code{endfile()} user-defined function @@ -20958,7 +20833,7 @@ how it simplifies writing the main program. You are probably wondering, if @code{beginfile()} and @code{endfile()} functions can do the job, why does @command{gawk} have -@code{BEGINFILE} and @code{ENDFILE} patterns (@pxref{BEGINFILE/ENDFILE})? +@code{BEGINFILE} and @code{ENDFILE} patterns? Good question. Normally, if @command{awk} cannot open a file, this causes an immediate fatal error. In this case, there is no way for a @@ -20967,13 +20842,14 @@ calling it relies on the file being open and at the first record. Thus, the main reason for @code{BEGINFILE} is to give you a ``hook'' to catch files that cannot be processed. @code{ENDFILE} exists for symmetry, and because it provides an easy way to do per-file cleanup processing. +For more information, refer to @ref{BEGINFILE/ENDFILE}. @end sidebar @node Rewind Function @subsection Rereading the Current File @cindex files, reading -Another request for a new built-in function was for a @code{rewind()} +Another request for a new built-in function was for a function that would make it possible to reread the current file. The requesting user didn't want to have to use @code{getline} (@pxref{Getline}) @@ -20982,7 +20858,7 @@ inside a loop. However, as long as you are not in the @code{END} rule, it is quite easy to arrange to immediately close the current input file and then start over with it from the top. -For lack of a better name, we'll call it @code{rewind()}: +For lack of a better name, we'll call the function @code{rewind()}: @cindex @code{rewind()} user-defined function @example @@ -21075,16 +20951,16 @@ See also @ref{ARGC and ARGV}. Because @command{awk} variable names only allow the English letters, the regular expression check purposely does not use character classes such as @samp{[:alpha:]} and @samp{[:alnum:]} -(@pxref{Bracket Expressions}) +(@pxref{Bracket Expressions}). @node Empty Files -@subsection Checking for Zero-length Files +@subsection Checking for Zero-Length Files All known @command{awk} implementations silently skip over zero-length files. This is a by-product of @command{awk}'s implicit read-a-record-and-match-against-the-rules loop: when @command{awk} tries to read a record from an empty file, it immediately receives an -end of file indication, closes the file, and proceeds on to the next +end-of-file indication, closes the file, and proceeds on to the next command-line @value{DF}, @emph{without} executing any user-level @command{awk} program code. @@ -21149,7 +21025,7 @@ Occasionally, you might not want @command{awk} to process command-line variable assignments (@pxref{Assignment Options}). In particular, if you have a @value{FN} that contains an @samp{=} character, -@command{awk} treats the @value{FN} as an assignment, and does not process it. +@command{awk} treats the @value{FN} as an assignment and does not process it. Some users have suggested an additional command-line option for @command{gawk} to disable command-line assignments. However, some simple programming with @@ -21199,22 +21075,14 @@ The use of @code{No_command_assign} allows you to disable command-line assignments at invocation time, by giving the variable a true value. When not set, it is initially zero (i.e., false), so the command-line arguments are left alone. -@c ENDOFRANGE dataf -@c ENDOFRANGE flibdataf -@c ENDOFRANGE libfdataf @node Getopt Function @section Processing Command-Line Options -@c STARTOFRANGE libfclo @cindex libraries of @command{awk} functions, command-line options -@c STARTOFRANGE flibclo @cindex functions, library, command-line options -@c STARTOFRANGE clop @cindex command-line options, processing -@c STARTOFRANGE oclp @cindex options, command-line, processing -@c STARTOFRANGE clibf @cindex functions, library, C library @cindex arguments, processing Most utilities on POSIX-compatible systems take options on @@ -21519,8 +21387,8 @@ BEGIN @{ @c endfile @end example -The rest of the @code{BEGIN} rule is a simple test program. Here is the -result of two sample runs of the test program: +The rest of the @code{BEGIN} rule is a simple test program. Here are the +results of two sample runs of the test program: @example $ @kbd{awk -f getopt.awk -v _getopt_test=1 -- -a -cbARG bax -x} @@ -21566,27 +21434,19 @@ further options Several of the sample programs presented in @ref{Sample Programs}, use @code{getopt()} to process their arguments. -@c ENDOFRANGE libfclo -@c ENDOFRANGE flibclo -@c ENDOFRANGE clop -@c ENDOFRANGE oclp @node Passwd Functions @section Reading the User Database -@c STARTOFRANGE libfudata @cindex libraries of @command{awk} functions, user database, reading -@c STARTOFRANGE flibudata @cindex functions, library, user database@comma{} reading -@c STARTOFRANGE udatar @cindex user database@comma{} reading -@c STARTOFRANGE dataur @cindex database, users@comma{} reading @cindex @code{PROCINFO} array The @code{PROCINFO} array (@pxref{Built-in Variables}) provides access to the current user's real and effective user and group ID -numbers, and if available, the user's supplementary group set. +numbers, and, if available, the user's supplementary group set. However, because these are numbers, they do not provide very useful information to the average user. There needs to be some way to find the user information associated with the user and group ID numbers. This @@ -21606,7 +21466,7 @@ kept. Instead, it provides the @code{<pwd.h>} header file and several C language subroutines for obtaining user information. The primary function is @code{getpwent()}, for ``get password entry.'' The ``password'' comes from the original user database file, -@file{/etc/passwd}, which stores user information, along with the +@file{/etc/passwd}, which stores user information along with the encrypted passwords (hence the name). @cindex @command{pwcat} program @@ -21705,7 +21565,7 @@ The user's encrypted password. This may not be available on some systems. @item User-ID The user's numeric user ID number. -(On some systems, it's a C @code{long}, and not an @code{int}. Thus +(On some systems, it's a C @code{long}, and not an @code{int}. Thus, we cast it to @code{long} for all cases.) @item Group-ID @@ -21832,7 +21692,7 @@ The code that checks for using @code{FPAT}, using @code{using_fpat} and @code{PROCINFO["FS"]}, is similar. The main part of the function uses a loop to read database lines, split -the line into fields, and then store the line into each array as necessary. +the lines into fields, and then store the lines into each array as necessary. When the loop is done, @code{@w{_pw_init()}} cleans up by closing the pipeline, setting @code{@w{_pw_inited}} to one, and restoring @code{FS} (and @code{FIELDWIDTHS} or @code{FPAT} @@ -21927,21 +21787,13 @@ and such a change would clutter up the code. The @command{id} program in @DBREF{Id Program} uses these functions. -@c ENDOFRANGE libfudata -@c ENDOFRANGE flibudata -@c ENDOFRANGE udatar -@c ENDOFRANGE dataur @node Group Functions @section Reading the Group Database -@c STARTOFRANGE libfgdata @cindex libraries of @command{awk} functions, group database, reading -@c STARTOFRANGE flibgdata @cindex functions, library, group database@comma{} reading -@c STARTOFRANGE gdatar @cindex group database, reading -@c STARTOFRANGE datagr @cindex database, group, reading @cindex @code{PROCINFO} array, and group membership @cindex @code{getgrent()} function (C library) @@ -22057,7 +21909,7 @@ it is usually empty or set to @samp{*}. @item Group ID Number The group's numeric group ID number; the association of name to number must be unique within the file. -(On some systems it's a C @code{long}, and not an @code{int}. Thus +(On some systems it's a C @code{long}, and not an @code{int}. Thus, we cast it to @code{long} for all cases.) @item Group Member List @@ -22171,32 +22023,32 @@ The @code{@w{_gr_init()}} function first saves @code{FS}, @code{$0}, and then sets @code{FS} and @code{RS} to the correct values for scanning the group information. It also takes care to note whether @code{FIELDWIDTHS} or @code{FPAT} -is being used, and to restore the appropriate field splitting mechanism. +is being used, and to restore the appropriate field-splitting mechanism. -The group information is stored is several associative arrays. +The group information is stored in several associative arrays. The arrays are indexed by group name (@code{@w{_gr_byname}}), by group ID number (@code{@w{_gr_bygid}}), and by position in the database (@code{@w{_gr_bycount}}). There is an additional array indexed by username (@code{@w{_gr_groupsbyuser}}), which is a space-separated list of groups to which each user belongs. -Unlike the user database, it is possible to have multiple records in the +Unlike in the user database, it is possible to have multiple records in the database for the same group. This is common when a group has a large number of members. A pair of such entries might look like the following: @example -tvpeople:*:101:johny,jay,arsenio +tvpeople:*:101:johnny,jay,arsenio tvpeople:*:101:david,conan,tom,joan @end example For this reason, @code{_gr_init()} looks to see if a group name or -group ID number is already seen. If it is, the usernames are -simply concatenated onto the previous list of users.@footnote{There is actually a +group ID number is already seen. If so, the usernames are +simply concatenated onto the previous list of users.@footnote{There is a subtle problem with the code just presented. Suppose that the first time there were no names. This code adds the names with a leading comma. It also doesn't check that there is a @code{$4}.} Finally, @code{_gr_init()} closes the pipeline to @command{grcat}, restores -@code{FS} (and @code{FIELDWIDTHS} or @code{FPAT} if necessary), @code{RS}, and @code{$0}, +@code{FS} (and @code{FIELDWIDTHS} or @code{FPAT}, if necessary), @code{RS}, and @code{$0}, initializes @code{_gr_count} to zero (it is used later), and makes @code{_gr_inited} nonzero. @@ -22264,7 +22116,6 @@ function getgrent() @} @c endfile @end example -@c ENDOFRANGE clibf @cindex @code{endgrent()} function (C library) The @code{endgrent()} function resets @code{_gr_count} to zero so that @code{getgrent()} can @@ -22297,12 +22148,12 @@ uses these functions. @DBREF{Arrays of Arrays} described how @command{gawk} provides arrays of arrays. In particular, any element of -an array may be either a scalar, or another array. The +an array may be either a scalar or another array. The @code{isarray()} function (@pxref{Type Functions}) lets you distinguish an array from a scalar. The following function, @code{walk_array()}, recursively traverses -an array, printing each element's indices and value. +an array, printing the element indices and values. You call it with the array and a string representing the name of the array: @@ -22353,10 +22204,6 @@ $ @kbd{gawk -f walk_array.awk} @print{} a[4][2] = 42 @end example -@c ENDOFRANGE libfgdata -@c ENDOFRANGE flibgdata -@c ENDOFRANGE gdatar -@c ENDOFRANGE libf @node Library Functions Summary @section Summary @@ -22378,24 +22225,24 @@ The functions presented here fit into the following categories: @c nested list @table @asis @item General problems -Number-to-string conversion, assertions, rounding, random number +Number-to-string conversion, testing assertions, rounding, random number generation, converting characters to numbers, joining strings, getting easily usable time-of-day information, and reading a whole file in -one shot. +one shot @item Managing @value{DF}s Noting @value{DF} boundaries, rereading the current file, checking for readable files, checking for zero-length files, and treating assignments -as @value{FN}s. +as @value{FN}s @item Processing command-line options -An @command{awk} version of the standard C @code{getopt()} function. +An @command{awk} version of the standard C @code{getopt()} function @item Reading the user and group databases -Two sets of routines that parallel the C library versions. +Two sets of routines that parallel the C library versions @item Traversing arrays of arrays -A simple function to traverse an array of arrays to any depth. +A simple function to traverse an array of arrays to any depth @end table @c end nested list @@ -22470,13 +22317,9 @@ output identical to that of the original version. @end enumerate @c EXCLUDE END -@c ENDOFRANGE flib -@c ENDOFRANGE fudlib -@c ENDOFRANGE datagr @node Sample Programs @chapter Practical @command{awk} Programs -@c STARTOFRANGE awkpex @cindex @command{awk} programs, examples of @c FULLXREF ON @@ -22494,10 +22337,10 @@ in this @value{CHAPTER}. The second presents @command{awk} versions of several common POSIX utilities. These are programs that you are hopefully already familiar with, -and therefore, whose problems are understood. +and therefore whose problems are understood. By reimplementing these programs in @command{awk}, you can focus on the @command{awk}-related aspects of solving -the programming problem. +the programming problems. The third is a grab bag of interesting programs. These solve a number of different data-manipulation and management @@ -22546,7 +22389,6 @@ cut.awk -- -c1-8 myfiles > results @node Clones @section Reinventing Wheels for Fun and Profit -@c STARTOFRANGE posimawk @cindex POSIX, programs@comma{} implementing in @command{awk} This @value{SECTION} presents a number of POSIX utilities implemented in @@ -22558,7 +22400,7 @@ It should be noted that these programs are not necessarily intended to replace the installed versions on your system. Nor may all of these programs be fully compliant with the most recent POSIX standard. This is not a problem; their -purpose is to illustrate @command{awk} language programming for ``real world'' +purpose is to illustrate @command{awk} language programming for ``real-world'' tasks. The programs are presented in alphabetical order. @@ -22577,11 +22419,8 @@ The programs are presented in alphabetical order. @subsection Cutting Out Fields and Columns @cindex @command{cut} utility -@c STARTOFRANGE cut @cindex @command{cut} utility -@c STARTOFRANGE ficut @cindex fields, cutting -@c STARTOFRANGE colcut @cindex columns, cutting The @command{cut} utility selects, or ``cuts,'' characters or fields from its standard input and sends them to its standard output. @@ -22590,7 +22429,7 @@ but you may supply a command-line option to change the field @dfn{delimiter} (i.e., the field-separator character). @command{cut}'s definition of fields is less general than @command{awk}'s. -A common use of @command{cut} might be to pull out just the login name of +A common use of @command{cut} might be to pull out just the login names of logged-on users from the output of @command{who}. For example, the following pipeline generates a sorted, unique list of the logged-on users: @@ -22889,21 +22728,14 @@ other @command{awk} implementations to use @code{substr()} it is also extremely painful. The @code{FIELDWIDTHS} variable supplies an elegant solution to the problem of picking the input line apart by characters. -@c ENDOFRANGE cut -@c ENDOFRANGE ficut -@c ENDOFRANGE colcut @node Egrep Program @subsection Searching for Regular Expressions in Files -@c STARTOFRANGE regexps @cindex regular expressions, searching for -@c STARTOFRANGE sfregexp @cindex searching, files for regular expressions -@c STARTOFRANGE fsregexp @cindex files, searching for regular expressions -@c STARTOFRANGE egrep @cindex @command{egrep} utility The @command{egrep} utility searches files for patterns. It uses regular expressions that are almost identical to those available in @command{awk} @@ -23106,7 +22938,7 @@ successful or unsuccessful match. If the line does not match, the @code{next} statement just moves on to the next record. A number of additional tests are made, but they are only done if we -are not counting lines. First, if the user only wants exit status +are not counting lines. First, if the user only wants the exit status (@code{no_print} is true), then it is enough to know that @emph{one} line in this file matched, and we can skip on to the next file with @code{nextfile}. Similarly, if we are only printing @value{FN}s, we can @@ -23147,7 +22979,7 @@ if necessary: @end example The @code{END} rule takes care of producing the correct exit status. If -there are no matches, the exit status is one; otherwise it is zero: +there are no matches, the exit status is one; otherwise, it is zero: @example @c file eg/prog/egrep.awk @@ -23171,17 +23003,12 @@ function usage() @c endfile @end example -@c ENDOFRANGE regexps -@c ENDOFRANGE sfregexp -@c ENDOFRANGE fsregexp -@c ENDOFRANGE egrep @node Id Program @subsection Printing Out User Information @cindex printing, user information @cindex users, information about, printing -@c STARTOFRANGE id @cindex @command{id} utility The @command{id} utility lists a user's real and effective user ID numbers, real and effective group ID numbers, and the user's group set, if any. @@ -23204,7 +23031,8 @@ Here is a simple version of @command{id} written in @command{awk}. It uses the user database library functions (@pxref{Passwd Functions}) and the group database library functions -(@pxref{Group Functions}): +(@pxref{Group Functions}) +from @ref{Library Functions}. The program is fairly straightforward. All the work is done in the @code{BEGIN} rule. The user and group ID numbers are obtained from @@ -23310,16 +23138,13 @@ code that is used repeatedly, making the whole program shorter and cleaner. In particular, moving the check for the empty string into this function saves several lines of code. -@c ENDOFRANGE id @node Split Program @subsection Splitting a Large File into Pieces @c FIXME: One day, update to current POSIX version of split -@c STARTOFRANGE filspl @cindex files, splitting -@c STARTOFRANGE split @cindex @code{split} utility The @command{split} program splits large text files into smaller pieces. Usage is as follows:@footnote{This is the traditional usage. The @@ -23334,8 +23159,8 @@ By default, the output files are named @file{xaa}, @file{xab}, and so on. Each file has 1,000 lines in it, with the likely exception of the last file. To change the number of lines in each file, supply a number on the command line -preceded with a minus (e.g., @samp{-500} for files with 500 lines in them -instead of 1,000). To change the name of the output files to something like +preceded with a minus sign (e.g., @samp{-500} for files with 500 lines in them +instead of 1,000). To change the names of the output files to something like @file{myfileaa}, @file{myfileab}, and so on, supply an additional argument that specifies the @value{FN} prefix. @@ -23454,15 +23279,12 @@ You might want to consider how to eliminate the use of way as to solve the EBCDIC issue as well. @end ifset -@c ENDOFRANGE filspl -@c ENDOFRANGE split @node Tee Program @subsection Duplicating Output into Multiple Files @cindex files, multiple@comma{} duplicating output into @cindex output, duplicating into files -@c STARTOFRANGE tee @cindex @code{tee} utility The @code{tee} program is known as a ``pipe fitting.'' @code{tee} copies its standard input to its standard output and also duplicates it to the @@ -23575,18 +23397,14 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE tee @node Uniq Program @subsection Printing Nonduplicated Lines of Text @c FIXME: One day, update to current POSIX version of uniq -@c STARTOFRANGE prunt @cindex printing, unduplicated lines of text -@c STARTOFRANGE tpul @cindex text@comma{} printing, unduplicated lines of -@c STARTOFRANGE uniq @cindex @command{uniq} utility The @command{uniq} utility reads sorted lines of data on its standard input, and by default removes duplicate lines. In other words, it only @@ -23855,26 +23673,17 @@ suggestion. @end ifset -@c ENDOFRANGE prunt -@c ENDOFRANGE tpul -@c ENDOFRANGE uniq @node Wc Program @subsection Counting Things @c FIXME: One day, update to current POSIX version of wc -@c STARTOFRANGE count @cindex counting -@c STARTOFRANGE infco @cindex input files, counting elements in -@c STARTOFRANGE woco @cindex words, counting -@c STARTOFRANGE chco @cindex characters, counting -@c STARTOFRANGE lico @cindex lines, counting -@c STARTOFRANGE wc @cindex @command{wc} utility The @command{wc} (word count) utility counts lines, words, and characters in one or more input files. Its usage is as follows: @@ -24044,13 +23853,6 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE count -@c ENDOFRANGE infco -@c ENDOFRANGE lico -@c ENDOFRANGE woco -@c ENDOFRANGE chco -@c ENDOFRANGE wc -@c ENDOFRANGE posimawk @node Miscellaneous Programs @section A Grab Bag of @command{awk} Programs @@ -24181,9 +23983,7 @@ Aharon Robbins <arnold@skeeve.com> wrote: @author Erik Quanstrom @end quotation -@c STARTOFRANGE tialarm @cindex time, alarm clock example program -@c STARTOFRANGE alaex @cindex alarm clock example program The following program is a simple ``alarm clock'' program. You give it a time of day and an optional message. At the specified time, @@ -24199,7 +23999,7 @@ checking and setting of defaults: the delay, the count, and the message to print. If the user supplied a message without the ASCII BEL character (known as the ``alert'' character, @code{"\a"}), then it is added to the message. (On many systems, printing the ASCII BEL generates an -audible alert. Thus when the alarm goes off, the system calls attention +audible alert. Thus, when the alarm goes off, the system calls attention to itself in case the user is not looking at the computer.) Just for a change, this program uses a @code{switch} statement (@pxref{Switch Statement}), but the processing could be done with a series of @@ -24335,15 +24135,11 @@ seconds are necessary: @} @c endfile @end example -@c ENDOFRANGE tialarm -@c ENDOFRANGE alaex @node Translate Program @subsection Transliterating Characters -@c STARTOFRANGE chtra @cindex characters, transliterating -@c STARTOFRANGE tr @cindex @command{tr} utility The system @command{tr} utility transliterates characters. For example, it is often used to map uppercase letters into lowercase for further processing: @@ -24372,7 +24168,7 @@ to @command{gawk}. @c at least theoretically The following program was written to prove that character transliteration could be done with a user-level -function. This program is not as complete as the system @command{tr} utility +function. This program is not as complete as the system @command{tr} utility, but it does most of the job. The @command{translate} program was written long before @command{gawk} @@ -24384,13 +24180,13 @@ takes three arguments: @table @code @item from -A list of characters from which to translate. +A list of characters from which to translate @item to -A list of characters to which to translate. +A list of characters to which to translate @item target -The string on which to do the translation. +The string on which to do the translation @end table Associative arrays make the translation part fairly easy. @code{t_ar} holds @@ -24399,7 +24195,7 @@ loop goes through @code{from}, one character at a time. For each character in @code{from}, if the character appears in @code{target}, it is replaced with the corresponding @code{to} character. -The @code{translate()} function calls @code{stranslate()} using @code{$0} +The @code{translate()} function calls @code{stranslate()}, using @code{$0} as the target. The main program sets two global variables, @code{FROM} and @code{TO}, from the command line, and then changes @code{ARGV} so that @command{awk} reads from the standard input. @@ -24421,7 +24217,7 @@ Finally, the processing rule simply calls @code{translate()} for each record: @c endfile @end ignore @c file eg/prog/translate.awk -# Bugs: does not handle things like: tr A-Z a-z, it has +# Bugs: does not handle things like tr A-Z a-z; it has # to be spelled out. However, if `to' is shorter than `from', # the last character in `to' is used for the rest of `from'. @@ -24491,17 +24287,13 @@ such as @samp{a-z}, as allowed by the @command{tr} utility. Look at the code for @file{cut.awk} (@pxref{Cut Program}) for inspiration. -@c ENDOFRANGE chtra -@c ENDOFRANGE tr @node Labels Program @subsection Printing Mailing Labels -@c STARTOFRANGE prml @cindex printing, mailing labels -@c STARTOFRANGE mlprint @cindex mailing labels@comma{} printing -Here is a ``real world''@footnote{``Real world'' is defined as +Here is a ``real-world''@footnote{``Real world'' is defined as ``a program actually used to get something done.''} program. This script reads lists of names and @@ -24510,7 +24302,7 @@ on it, two across and 10 down. The addresses are guaranteed to be no more than five lines of data. Each address is separated from the next by a blank line. -The basic idea is to read 20 labels worth of data. Each line of each label +The basic idea is to read 20 labels' worth of data. Each line of each label is stored in the @code{line} array. The single rule takes care of filling the @code{line} array and printing the page when 20 labels have been read. @@ -24533,12 +24325,12 @@ of lines on the page Most of the work is done in the @code{printpage()} function. The label lines are stored sequentially in the @code{line} array. But they -have to print horizontally; @code{line[1]} next to @code{line[6]}, +have to print horizontally: @code{line[1]} next to @code{line[6]}, @code{line[2]} next to @code{line[7]}, and so on. Two loops accomplish this. The outer loop, controlled by @code{i}, steps through every 10 lines of data; this is each row of labels. The inner loop, controlled by @code{j}, goes through the lines within the row. -As @code{j} goes from 0 to 4, @samp{i+j} is the @code{j}-th line in +As @code{j} goes from 0 to 4, @samp{i+j} is the @code{j}th line in the row, and @samp{i+j+5} is the entry next to it. The output ends up looking something like this: @@ -24563,7 +24355,6 @@ that there are two blank lines at the top and two blank lines at the bottom. The @code{END} rule arranges to flush the final page of labels; there may not have been an even multiple of 20 labels in the data: -@c STARTOFRANGE labels @cindex @code{labels.awk} program @example @c file eg/prog/labels.awk @@ -24628,14 +24419,10 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE prml -@c ENDOFRANGE mlprint -@c ENDOFRANGE labels @node Word Sorting @subsection Generating Word-Usage Counts -@c STARTOFRANGE worus @cindex words, usage counts@comma{} generating When working with large amounts of text, it can be interesting to know @@ -24661,8 +24448,8 @@ END @{ @} @end example -The program relies on @command{awk}'s default field splitting -mechanism to break each line up into ``words,'' and uses an +The program relies on @command{awk}'s default field-splitting +mechanism to break each line up into ``words'' and uses an associative array named @code{freq}, indexed by each word, to count the number of times the word occurs. In the @code{END} rule, it prints the counts. @@ -24697,7 +24484,6 @@ to remove punctuation characters. Finally, we solve the third problem by using the system @command{sort} utility to process the output of the @command{awk} script. Here is the new version of the program: -@c STARTOFRANGE wordfreq @cindex @code{wordfreq.awk} program @example @c file eg/prog/wordfreq.awk @@ -24762,16 +24548,13 @@ This way of sorting must be used on systems that do not have true pipes at the command-line (or batch-file) level. See the general operating system documentation for more information on how to use the @command{sort} program. -@c ENDOFRANGE worus -@c ENDOFRANGE wordfreq @node History Sorting @subsection Removing Duplicates from Unsorted Text -@c STARTOFRANGE lidu @cindex lines, duplicate@comma{} removing The @command{uniq} program -(@pxref{Uniq Program}), +(@pxref{Uniq Program}) removes duplicate lines from @emph{sorted} data. Suppose, however, you need to remove duplicate lines from a @value{DF} but @@ -24793,7 +24576,6 @@ Each element of @code{lines} is a unique command, and the indices of The @code{END} rule simply prints out the lines, in order: @cindex Rakitzis, Byron -@c STARTOFRANGE histsort @cindex @code{histsort.awk} program @example @c file eg/prog/histsort.awk @@ -24836,15 +24618,11 @@ print data[lines[i]], lines[i] @noindent This works because @code{data[$0]} is incremented each time a line is seen. -@c ENDOFRANGE lidu -@c ENDOFRANGE histsort @node Extract Program @subsection Extracting Programs from Texinfo Source Files -@c STARTOFRANGE texse @cindex Texinfo, extracting programs from source files -@c STARTOFRANGE fitex @cindex files, Texinfo@comma{} extracting programs from @ifnotinfo Both this chapter and the previous chapter @@ -24863,7 +24641,7 @@ Texinfo input file into separate files. @cindex Texinfo This @value{DOCUMENT} is written in @uref{http://www.gnu.org/software/texinfo/, Texinfo}, -the GNU project's document formatting language. +the GNU Project's document formatting language. A single Texinfo source file can be used to produce both printed documentation, with @TeX{}, and online documentation. @ifnotinfo @@ -24922,7 +24700,7 @@ The Texinfo file looks something like this: @example @dots{} -This program has a @@code@{BEGIN@} rule, +This program has a @@code@{BEGIN@} rule that prints a nice message: @@example @@ -24948,11 +24726,10 @@ The first rule handles calling @code{system()}, checking that a command is given (@code{NF} is at least three) and also checking that the command exits with a zero exit status, signifying OK: -@c STARTOFRANGE extract @cindex @code{extract.awk} program @example @c file eg/prog/extract.awk -# extract.awk --- extract files and run programs from texinfo files +# extract.awk --- extract files and run programs from Texinfo files @c endfile @ignore @c file eg/prog/extract.awk @@ -24993,12 +24770,12 @@ The second rule handles moving data into files. It verifies that a @value{FN} is given in the directive. If the file named is not the current file, then the current file is closed. Keeping the current file open until a new file is encountered allows the use of the @samp{>} -redirection for printing the contents, keeping open file management +redirection for printing the contents, keeping open-file management simple. The @code{for} loop does the work. It reads lines using @code{getline} (@pxref{Getline}). -For an unexpected end of file, it calls the @code{@w{unexpected_eof()}} +For an unexpected end-of-file, it calls the @code{@w{unexpected_eof()}} function. If the line is an ``endfile'' line, then it breaks out of the loop. If the line is an @samp{@@group} or @samp{@@end group} line, then it @@ -25094,16 +24871,13 @@ END @{ @} @c endfile @end example -@c ENDOFRANGE texse -@c ENDOFRANGE fitex -@c ENDOFRANGE extract @node Simple Sed @subsection A Simple Stream Editor @cindex @command{sed} utility @cindex stream editors -The @command{sed} utility is a stream editor, a program that reads a +The @command{sed} utility is a @dfn{stream editor}, a program that reads a stream of data, makes changes to it, and passes it on. It is often used to make global changes to a large file or to a stream of data generated by a pipeline of commands. @@ -25126,7 +24900,6 @@ additional arguments are treated as @value{DF} names to process. If none are provided, the standard input is used: @cindex Brennan, Michael -@c STARTOFRANGE awksed @cindex @command{awksed.awk} program @c @cindex simple stream editor @c @cindex stream editor, simple @@ -25203,14 +24976,11 @@ The @code{usage()} function prints an error message and exits. Finally, the single rule handles the printing scheme outlined earlier, using @code{print} or @code{printf} as appropriate, depending upon the value of @code{RT}. -@c ENDOFRANGE awksed @node Igawk Program @subsection An Easy Way to Use Library Functions -@c STARTOFRANGE libfex @cindex libraries of @command{awk} functions, example program for using -@c STARTOFRANGE flibex @cindex functions, library, example program for using In @ref{Include Files}, we saw how @command{gawk} provides a built-in file-inclusion capability. However, this is a @command{gawk} extension. @@ -25252,7 +25022,7 @@ includes don't accidentally include a library function twice. @command{igawk} should behave just like @command{gawk} externally. This means it should accept all of @command{gawk}'s command-line arguments, including the ability to have multiple source files specified via -@option{-f}, and the ability to mix command-line and library source files. +@option{-f} and the ability to mix command-line and library source files. The program is written using the POSIX Shell (@command{sh}) command language.@footnote{Fully explaining the @command{sh} language is beyond @@ -25291,7 +25061,7 @@ Run the expanded program with @command{gawk} and any other original command-line arguments that the user supplied (such as the @value{DF} names). @end enumerate -This program uses shell variables extensively: for storing command-line arguments, +This program uses shell variables extensively: for storing command-line arguments and the text of the @command{awk} program that will expand the user's program, for the user's original program, and for the expanded program. Doing so removes some potential problems that might arise were we to use temporary files instead, @@ -25349,7 +25119,6 @@ program. The program is as follows: -@c STARTOFRANGE igawk @cindex @code{igawk.sh} program @example @c file eg/prog/igawk.sh @@ -25609,22 +25378,7 @@ Save the results of this processing in the shell variable The last step is to call @command{gawk} with the expanded program, along with the original -options and command-line arguments that the user supplied. - -@c this causes more problems than it solves, so leave it out. -@ignore -The special file @file{/dev/null} is passed as a @value{DF} to @command{gawk} -to handle an interesting case. Suppose that the user's program only has -a @code{BEGIN} rule and there are no @value{DF}s to read. -The program should exit without reading any @value{DF}s. -However, suppose that an included library file defines an @code{END} -rule of its own. In this case, @command{gawk} will hang, reading standard -input. In order to avoid this, @file{/dev/null} is explicitly added to the -command line. Reading from @file{/dev/null} always returns an immediate -end of file indication. - -@c Hmm. Add /dev/null if $# is 0? Still messes up ARGV. Sigh. -@end ignore +options and command-line arguments that the user supplied: @example @c file eg/prog/igawk.sh @@ -25674,10 +25428,6 @@ features to a program; they can often be layered on top.@footnote{@command{gawk} does @code{@@include} processing itself in order to support the use of @command{awk} programs as Web CGI scripts.} -@c ENDOFRANGE libfex -@c ENDOFRANGE flibex -@c ENDOFRANGE awkpex -@c ENDOFRANGE igawk @node Anagram Program @subsection Finding Anagrams from a Dictionary @@ -25694,19 +25444,18 @@ the same letters Column 2, Problem C, of Jon Bentley's @cite{Programming Pearls}, Second Edition, presents an elegant algorithm. The idea is to give words that are anagrams a common signature, sort all the words together by their -signature, and then print them. Dr.@: Bentley observes that taking the -letters in each word and sorting them produces that common signature. +signatures, and then print them. Dr.@: Bentley observes that taking the +letters in each word and sorting them produces those common signatures. The following program uses arrays of arrays to bring together words with the same signature and array sorting to print the words in sorted order: -@c STARTOFRANGE anagram @cindex @code{anagram.awk} program @example @c file eg/prog/anagram.awk -# anagram.awk --- An implementation of the anagram finding algorithm -# from Jon Bentley's "Programming Pearls", 2nd edition. +# anagram.awk --- An implementation of the anagram-finding algorithm +# from Jon Bentley's "Programming Pearls," 2nd edition. # Addison Wesley, 2000, ISBN 0-201-65788-0. # Column 2, Problem C, section 2.8, pp 18-20. @c endfile @@ -25754,7 +25503,7 @@ sorts the letters, and then joins them back together: @example @c file eg/prog/anagram.awk -# word2key --- split word apart into letters, sort, joining back together +# word2key --- split word apart into letters, sort, and join back together function word2key(word, a, i, n, result) @{ @@ -25810,7 +25559,6 @@ babery yabber @dots{} @end example -@c ENDOFRANGE anagram @node Signature Program @subsection And Now for Something Completely Different @@ -25950,12 +25698,13 @@ characters. The ability to use @code{split()} with the empty string as the separator can considerably simplify such tasks. @item -The library functions from @ref{Library Functions}, proved their -usefulness for a number of real (if small) programs. +The examples here demonstrate the usefulness of the library +functions from @DBREF{Library Functions} +for a number of real (if small) programs. @item Besides reinventing POSIX wheels, other programs solved a selection of -interesting problems, such as finding duplicates words in text, printing +interesting problems, such as finding duplicate words in text, printing mailing labels, and finding anagrams. @end itemize @@ -26130,9 +25879,7 @@ It contains the following chapters: @node Advanced Features @chapter Advanced Features of @command{gawk} -@c STARTOFRANGE gawadv @cindex @command{gawk}, features, advanced -@c STARTOFRANGE advgaw @cindex advanced features, @command{gawk} @ignore Contributed by: Peter Langston <pud!psl@bellcore.bellcore.com> @@ -26153,18 +25900,18 @@ a violent psychopath who knows where you live.} This @value{CHAPTER} discusses advanced features in @command{gawk}. It's a bit of a ``grab bag'' of items that are otherwise unrelated to each other. -First, a command-line option allows @command{gawk} to recognize +First, we look at a command-line option that allows @command{gawk} to recognize nondecimal numbers in input data, not just in @command{awk} programs. Then, @command{gawk}'s special features for sorting arrays are presented. Next, two-way I/O, discussed briefly in earlier parts of this @value{DOCUMENT}, is described in full detail, along with the basics -of TCP/IP networking. Finally, @command{gawk} +of TCP/IP networking. Finally, we see how @command{gawk} can @dfn{profile} an @command{awk} program, making it possible to tune it for performance. @c FULLXREF ON -A number of advanced features require separate @value{CHAPTER}s of their +Additional advanced features are discussed in separate @value{CHAPTER}s of their own: @itemize @value{BULLET} @@ -26258,7 +26005,8 @@ This option may disappear in a future version of @command{gawk}. @node Array Sorting @section Controlling Array Traversal and Array Sorting -@command{gawk} lets you control the order in which a @samp{for (i in array)} +@command{gawk} lets you control the order in which a +@samp{for (@var{indx} in @var{array})} loop traverses an array. In addition, two built-in functions, @code{asort()} and @code{asorti()}, @@ -26274,7 +26022,7 @@ to order the elements during sorting. @node Controlling Array Traversal @subsection Controlling Array Traversal -By default, the order in which a @samp{for (i in array)} loop +By default, the order in which a @samp{for (@var{indx} in @var{array})} loop scans an array is not defined; it is generally based upon the internal implementation of arrays inside @command{awk}. @@ -26303,23 +26051,23 @@ function comp_func(i1, v1, i2, v2) @} @end example -Here, @var{i1} and @var{i2} are the indices, and @var{v1} and @var{v2} +Here, @code{i1} and @code{i2} are the indices, and @code{v1} and @code{v2} are the corresponding values of the two elements being compared. -Either @var{v1} or @var{v2}, or both, can be arrays if the array being +Either @code{v1} or @code{v2}, or both, can be arrays if the array being traversed contains subarrays as values. (@DBXREF{Arrays of Arrays} for more information about subarrays.) The three possible return values are interpreted as follows: @table @code @item comp_func(i1, v1, i2, v2) < 0 -Index @var{i1} comes before index @var{i2} during loop traversal. +Index @code{i1} comes before index @code{i2} during loop traversal. @item comp_func(i1, v1, i2, v2) == 0 -Indices @var{i1} and @var{i2} -come together but the relative order with respect to each other is undefined. +Indices @code{i1} and @code{i2} +come together, but the relative order with respect to each other is undefined. @item comp_func(i1, v1, i2, v2) > 0 -Index @var{i1} comes after index @var{i2} during loop traversal. +Index @code{i1} comes after index @code{i2} during loop traversal. @end table Our first comparison function can be used to scan an array in @@ -26480,7 +26228,7 @@ As already mentioned, the order of the indices is arbitrary if two elements compare equal. This is usually not a problem, but letting the tied elements come out in arbitrary order can be an issue, especially when comparing item values. The partial ordering of the equal elements -may change the next time the array is traversed, if other elements are added or +may change the next time the array is traversed, if other elements are added to or removed from the array. One way to resolve ties when comparing elements with otherwise equal values is to include the indices in the comparison rules. Note that doing this may make the loop traversal less efficient, @@ -26523,7 +26271,7 @@ equivalent or distinct. Another point to keep in mind is that in the case of subarrays, the element values can themselves be arrays; a production comparison function should use the @code{isarray()} function -(@pxref{Type Functions}), +(@pxref{Type Functions}) to check for this, and choose a defined sorting order for subarrays. All sorting based on @code{PROCINFO["sorted_in"]} @@ -26531,7 +26279,7 @@ is disabled in POSIX mode, because the @code{PROCINFO} array is not special in that case. As a side note, sorting the array indices before traversing -the array has been reported to add 15% to 20% overhead to the +the array has been reported to add a 15% to 20% overhead to the execution time of @command{awk} programs. For this reason, sorted array traversal is not the default. @@ -26590,7 +26338,7 @@ However, the @code{source} array is not affected. Often, what's needed is to sort on the values of the @emph{indices} instead of the values of the elements. To do that, use the @code{asorti()} function. The interface and behavior are identical to -that of @code{asort()}, except that the index values are used for sorting, +that of @code{asort()}, except that the index values are used for sorting and become the values of the result array: @example @@ -26625,8 +26373,8 @@ it chooses}, taking into account just the indices, just the values, or both. This is extremely powerful. Once the array is sorted, @code{asort()} takes the @emph{values} in -their final order, and uses them to fill in the result array, whereas -@code{asorti()} takes the @emph{indices} in their final order, and uses +their final order and uses them to fill in the result array, whereas +@code{asorti()} takes the @emph{indices} in their final order and uses them to fill in the result array. @cindex reference counting, sorting arrays @@ -26842,7 +26590,6 @@ using regular pipes. @section Using @command{gawk} for Network Programming @cindex advanced features, network programming @cindex networks, programming -@c STARTOFRANGE tcpip @cindex TCP/IP @cindex @code{/inet/@dots{}} special files (@command{gawk}) @cindex files, @code{/inet/@dots{}} (@command{gawk}) @@ -26924,7 +26671,7 @@ service name. @cindex @command{gawk}, @code{ERRNO} variable in @cindex @code{ERRNO} variable @quotation NOTE -Failure in opening a two-way socket will result in a non-fatal error +Failure in opening a two-way socket will result in a nonfatal error being returned to the calling code. The value of @code{ERRNO} indicates the error (@pxref{Auto-set}). @end quotation @@ -26941,31 +26688,28 @@ BEGIN @{ @end example This program reads the current date and time from the local system's -TCP @samp{daytime} server. +TCP @code{daytime} server. It then prints the results and closes the connection. Because this topic is extensive, the use of @command{gawk} for TCP/IP programming is documented separately. @ifinfo See -@inforef{Top, , General Introduction, gawkinet, TCP/IP Internetworking with @command{gawk}}, +@inforef{Top, , General Introduction, gawkinet, @value{GAWKINETTITLE}}, @end ifinfo @ifnotinfo See @uref{http://www.gnu.org/software/gawk/manual/gawkinet/, -@cite{TCP/IP Internetworking with @command{gawk}}}, +@cite{@value{GAWKINETTITLE}}}, which comes as part of the @command{gawk} distribution, @end ifnotinfo for a much more complete introduction and discussion, as well as extensive examples. -@c ENDOFRANGE tcpip @node Profiling @section Profiling Your @command{awk} Programs -@c STARTOFRANGE awkp @cindex @command{awk} programs, profiling -@c STARTOFRANGE proawk @cindex profiling @command{awk} programs @cindex @code{awkprof.out} file @cindex files, @code{awkprof.out} @@ -27032,9 +26776,9 @@ junk @end example Here is the @file{awkprof.out} that results from running the -@command{gawk} profiler on this program and data. (This example also +@command{gawk} profiler on this program and data (this example also illustrates that @command{awk} programmers sometimes get up very early -in the morning to work.) +in the morning to work): @cindex @code{BEGIN} pattern, and profiling @cindex @code{END} pattern, and profiling @@ -27094,8 +26838,8 @@ They are as follows: @item The program is printed in the order @code{BEGIN} rules, @code{BEGINFILE} rules, -pattern/action rules, -@code{ENDFILE} rules, @code{END} rules and functions, listed +pattern--action rules, +@code{ENDFILE} rules, @code{END} rules, and functions, listed alphabetically. Multiple @code{BEGIN} and @code{END} rules retain their separate identities, as do @@ -27103,7 +26847,7 @@ multiple @code{BEGINFILE} and @code{ENDFILE} rules. @cindex patterns, counts, in a profile @item -Pattern-action rules have two counts. +Pattern--action rules have two counts. The first count, to the left of the rule, shows how many times the rule's pattern was @emph{tested}. The second count, to the right of the rule's opening left brace @@ -27170,13 +26914,13 @@ the target of a redirection isn't a scalar, it gets parenthesized. @command{gawk} supplies leading comments in front of the @code{BEGIN} and @code{END} rules, the @code{BEGINFILE} and @code{ENDFILE} rules, -the pattern/action rules, and the functions. +the pattern--action rules, and the functions. @end itemize The profiled version of your program may not look exactly like what you typed when you wrote it. This is because @command{gawk} creates the -profiled version by ``pretty printing'' its internal representation of +profiled version by ``pretty-printing'' its internal representation of the program. The advantage to this is that @command{gawk} can produce a standard representation. Also, things such as: @@ -27259,16 +27003,16 @@ If you use the @code{HUP} signal instead of the @code{USR1} signal, @cindex @code{SIGQUIT} signal (MS-Windows) @cindex signals, @code{QUIT}/@code{SIGQUIT} (MS-Windows) When @command{gawk} runs on MS-Windows systems, it uses the -@code{INT} and @code{QUIT} signals for producing the profile and, in +@code{INT} and @code{QUIT} signals for producing the profile, and in the case of the @code{INT} signal, @command{gawk} exits. This is because these systems don't support the @command{kill} command, so the only signals you can deliver to a program are those generated by the keyboard. The @code{INT} signal is generated by the -@kbd{Ctrl-@key{C}} or @kbd{Ctrl-@key{BREAK}} key, while the -@code{QUIT} signal is generated by the @kbd{Ctrl-@key{\}} key. +@kbd{Ctrl-c} or @kbd{Ctrl-BREAK} key, while the +@code{QUIT} signal is generated by the @kbd{Ctrl-\} key. Finally, @command{gawk} also accepts another option, @option{--pretty-print}. -When called this way, @command{gawk} ``pretty prints'' the program into +When called this way, @command{gawk} ``pretty-prints'' the program into @file{awkprof.out}, without any execution counts. @quotation NOTE @@ -27292,9 +27036,6 @@ that the profiling output does. This makes it easy to pretty-print your code once development is completed, and then use the result as the final version of your program. -@c ENDOFRANGE awkp -@c ENDOFRANGE proawk - @node Advanced Features Summary @section Summary @@ -27325,7 +27066,7 @@ optionally, close off one side of the two-way communications. @item By using special @value{FN}s with the @samp{|&} operator, you can open a -TCP/IP (or UDP/IP) connection to remote hosts in the Internet. @command{gawk} +TCP/IP (or UDP/IP) connection to remote hosts on the Internet. @command{gawk} supports both IPv4 and IPv6. @item @@ -27335,13 +27076,11 @@ you tune them more easily. Sending the @code{USR1} signal while profiling cause @command{gawk} to dump the profile and keep going, including a function call stack. @item -You can also just ``pretty print'' the program. This currently also runs +You can also just ``pretty-print'' the program. This currently also runs the program, but that will change in the next major release. @end itemize -@c ENDOFRANGE advgaw -@c ENDOFRANGE gawadv @node Internationalization @chapter Internationalization with @command{gawk} @@ -27354,7 +27093,6 @@ countries, they were able to sell more systems. As a result, internationalization and localization of programs and software systems became a common practice. -@c STARTOFRANGE inloc @cindex internationalization, localization @cindex @command{gawk}, internationalization and, See internationalization @cindex internationalization, localization, @command{gawk} and @@ -27387,7 +27125,7 @@ a requirement. @cindex localization @dfn{Internationalization} means writing (or modifying) a program once, in such a way that it can use multiple languages without requiring -further source-code changes. +further source code changes. @dfn{Localization} means providing the data necessary for an internationalized program to work in a particular language. Most typically, these terms refer to features such as the language @@ -27399,11 +27137,10 @@ monetary values are printed and read. @section GNU @command{gettext} @cindex internationalizing a program -@c STARTOFRANGE gettex @cindex @command{gettext} library @command{gawk} uses GNU @command{gettext} to provide its internationalization features. -The facilities in GNU @command{gettext} focus on messages; strings printed +The facilities in GNU @command{gettext} focus on messages: strings printed by a program, either directly or via formatting with @code{printf} or @code{sprintf()}.@footnote{For some operating systems, the @command{gawk} port doesn't support GNU @command{gettext}. @@ -27451,7 +27188,6 @@ lookup of the translations. @cindex @code{.po} files @cindex files, @code{.po} -@c STARTOFRANGE portobfi @cindex portable object files @cindex files, portable object @item @@ -27463,7 +27199,6 @@ For example, there might be a @file{fr.po} for a French translation. @cindex @code{.gmo} files @cindex files, @code{.gmo} @cindex message object files -@c STARTOFRANGE portmsgfi @cindex files, message object @item Each language's @file{.po} file is converted into a binary @@ -27591,14 +27326,12 @@ before or after the day in a date, local month abbreviations, and so on. @item LC_ALL All of the above. (Not too useful in the context of @command{gettext}.) @end table -@c ENDOFRANGE gettex @node Programmer i18n @section Internationalizing @command{awk} Programs -@c STARTOFRANGE inap @cindex @command{awk} programs, internationalizing -@command{gawk} provides the following variables and functions for +@command{gawk} provides the following variables for internationalization: @table @code @@ -27614,7 +27347,12 @@ value is @code{"messages"}. String constants marked with a leading underscore are candidates for translation at runtime. String constants without a leading underscore are not translated. +@end table +@command{gawk} provides the following functions for +internationalization: + +@table @code @cindexgawkfunc{dcgettext} @item @code{dcgettext(@var{string}} [@code{,} @var{domain} [@code{,} @var{category}]]@code{)} Return the translation of @var{string} in @@ -27671,15 +27409,7 @@ If @var{directory} is the null string (@code{""}), then given @var{domain}. @end table -To use these facilities in your @command{awk} program, follow the steps -outlined in -@ifnotinfo -the previous @value{SECTION}, -@end ifnotinfo -@ifinfo -@ref{Explaining gettext}, -@end ifinfo -like so: +To use these facilities in your @command{awk} program, follow these steps: @enumerate @cindex @code{BEGIN} pattern, @code{TEXTDOMAIN} variable and @@ -27828,8 +27558,6 @@ to provide you translations that you can also then distribute. @DBXREF{I18N Example} for the full list of steps to go through to create and test translations for @command{guide}. -@c ENDOFRANGE portobfi -@c ENDOFRANGE portmsgfi @node Printf Ordering @subsection Rearranging @code{printf} Arguments @@ -27964,7 +27692,7 @@ the null string (@code{""}) as its value, leaving the original string constant a the result. @item -By defining ``dummy'' functions to replace @code{dcgettext()}, @code{dcngettext()} +By defining ``dummy'' functions to replace @code{dcgettext()}, @code{dcngettext()}, and @code{bindtextdomain()}, the @command{awk} program can be made to run, but all the messages are output in the original language. For example: @@ -28005,7 +27733,6 @@ However, because the positional specifications are primarily for use in @emph{translated} format strings, and because non-GNU @command{awk}s never retrieve the translated string, this should not be a problem in practice. @end itemize -@c ENDOFRANGE inap @node I18N Example @section A Simple Internationalization Example @@ -28149,15 +27876,15 @@ using the GNU @command{gettext} package. (GNU @command{gettext} is described in complete detail in @ifinfo -@inforef{Top, , GNU @command{gettext} utilities, gettext, GNU gettext tools}.) +@inforef{Top, , GNU @command{gettext} utilities, gettext, GNU @command{gettext} utilities}.) @end ifinfo @ifnotinfo @uref{http://www.gnu.org/software/gettext/manual/, -@cite{GNU gettext tools}}.) +@cite{GNU @command{gettext} utilities}}.) @end ifnotinfo As of this writing, the latest version of GNU @command{gettext} is -@uref{ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.3.tar.gz, -@value{PVERSION} 0.19.3}. +@uref{ftp://ftp.gnu.org/gnu/gettext/gettext-0.19.4.tar.gz, +@value{PVERSION} 0.19.4}. If a translation of @command{gawk}'s messages exists, then @command{gawk} produces usage messages, warnings, @@ -28169,7 +27896,7 @@ and fatal errors in the local language. @itemize @value{BULLET} @item Internationalization means writing a program such that it can use multiple -languages without requiring source-code changes. Localization means +languages without requiring source code changes. Localization means providing the data necessary for an internationalized program to work in a particular language. @@ -28186,9 +27913,9 @@ file, and the @file{.po} files are compiled into @file{.gmo} files for use at runtime. @item -You can use position specifications with @code{sprintf()} and +You can use positional specifications with @code{sprintf()} and @code{printf} to rearrange the placement of argument values in formatted -strings and output. This is useful for the translations of format +strings and output. This is useful for the translation of format control strings. @item @@ -28201,7 +27928,6 @@ a number of translations for its messages. @end itemize -@c ENDOFRANGE inloc @node Debugger @chapter Debugging @command{awk} Programs @@ -28245,8 +27971,7 @@ the discussion of debugging in @command{gawk}. @subsection Debugging in General (If you have used debuggers in other languages, you may want to skip -ahead to the next section on the specific features of the @command{gawk} -debugger.) +ahead to @ref{Awk Debugging}.) Of course, a debugging program cannot remove bugs for you, because it has no way of knowing what you or your users consider a ``bug'' versus a @@ -28337,10 +28062,10 @@ and usually find the errant code quite quickly. @end table @node Awk Debugging -@subsection Awk Debugging +@subsection @command{awk} Debugging Debugging an @command{awk} program has some specific aspects that are -not shared with other programming languages. +not shared with programs written in other languages. First of all, the fact that @command{awk} programs usually take input line by line from a file or files and operate on those lines using specific @@ -28356,7 +28081,7 @@ to look at the individual primitive instructions carried out by the higher-level @command{awk} commands. @node Sample Debugging Session -@section Sample Debugging Session +@section Sample @command{gawk} Debugging Session @cindex sample debugging session In order to illustrate the use of @command{gawk} as a debugger, let's look at a sample @@ -28375,8 +28100,8 @@ as our example. @cindex debugger, how to start Starting the debugger is almost exactly like running @command{gawk} normally, -except you have to pass an additional option @option{--debug}, or the -corresponding short option @option{-D}. The file(s) containing the +except you have to pass an additional option, @option{--debug}, or the +corresponding short option, @option{-D}. The file(s) containing the program and any supporting code are given on the command line as arguments to one or more @option{-f} options. (@command{gawk} is not designed to debug command-line programs, only programs contained in files.) @@ -28389,7 +28114,7 @@ $ @kbd{gawk -D -f getopt.awk -f join.awk -f uniq.awk -1 inputfile} @noindent where both @file{getopt.awk} and @file{uniq.awk} are in @env{$AWKPATH}. (Experienced users of GDB or similar debuggers should note that -this syntax is slightly different from what they are used to. +this syntax is slightly different from what you are used to. With the @command{gawk} debugger, you give the arguments for running the program in the command line to the debugger rather than as part of the @code{run} command at the debugger prompt.) @@ -28543,10 +28268,10 @@ gawk> @kbd{n} @end example This tells us that @command{gawk} is now ready to execute line 66, which -decides whether to give the lines the special ``field skipping'' treatment +decides whether to give the lines the special ``field-skipping'' treatment indicated by the @option{-1} command-line option. (Notice that we skipped -from where we were before at line 63 to here, because the condition in line 63 -@samp{if (fcount == 0 && charcount == 0)} was false.) +from where we were before, at line 63, to here, because the condition +in line 63, @samp{if (fcount == 0 && charcount == 0)}, was false.) Continuing to step, we now get to the splitting of the current and last records: @@ -28620,7 +28345,7 @@ gawk> @kbd{n} Well, here we are at our error (sorry to spoil the suspense). What we had in mind was to join the fields starting from the second one to make -the virtual record to compare, and if the first field was numbered zero, +the virtual record to compare, and if the first field were numbered zero, this would work. Let's look at what we've got: @example @@ -28629,7 +28354,7 @@ gawk> @kbd{p cline clast} @print{} clast = "awk is a wonderful program!" @end example -Hey, those look pretty familiar! They're just our original, unaltered, +Hey, those look pretty familiar! They're just our original, unaltered input records. A little thinking (the human brain is still the best debugging tool), and we realize that we were off by one! @@ -28679,11 +28404,11 @@ Miscellaneous @end itemize Each of these are discussed in the following subsections. -In the following descriptions, commands which may be abbreviated +In the following descriptions, commands that may be abbreviated show the abbreviation on a second description line. A debugger command name may also be truncated if that partial name is unambiguous. The debugger has the built-in capability to -automatically repeat the previous command just by hitting @key{Enter}. +automatically repeat the previous command just by hitting @kbd{Enter}. This works for the commands @code{list}, @code{next}, @code{nexti}, @code{step}, @code{stepi}, and @code{continue} executed without any argument. @@ -28733,7 +28458,7 @@ Set a breakpoint at entry to (the first instruction of) function @var{function}. @end table -Each breakpoint is assigned a number which can be used to delete it from +Each breakpoint is assigned a number that can be used to delete it from the breakpoint list using the @code{delete} command. With a breakpoint, you may also supply a condition. This is an @@ -28785,7 +28510,7 @@ watchpoint is made unconditional). @cindex breakpoint, delete by number @item @code{delete} [@var{n1 n2} @dots{}] [@var{n}--@var{m}] @itemx @code{d} [@var{n1 n2} @dots{}] [@var{n}--@var{m}] -Delete specified breakpoints or a range of breakpoints. Deletes +Delete specified breakpoints or a range of breakpoints. Delete all defined breakpoints if no argument is supplied. @cindex debugger commands, @code{disable} @@ -28794,7 +28519,7 @@ all defined breakpoints if no argument is supplied. @cindex breakpoint, how to disable or enable @item @code{disable} [@var{n1 n2} @dots{} | @var{n}--@var{m}] Disable specified breakpoints or a range of breakpoints. Without -any argument, disables all breakpoints. +any argument, disable all breakpoints. @cindex debugger commands, @code{e} (@code{enable}) @cindex debugger commands, @code{enable} @@ -28804,18 +28529,18 @@ any argument, disables all breakpoints. @item @code{enable} [@code{del} | @code{once}] [@var{n1 n2} @dots{}] [@var{n}--@var{m}] @itemx @code{e} [@code{del} | @code{once}] [@var{n1 n2} @dots{}] [@var{n}--@var{m}] Enable specified breakpoints or a range of breakpoints. Without -any argument, enables all breakpoints. -Optionally, you can specify how to enable the breakpoint: +any argument, enable all breakpoints. +Optionally, you can specify how to enable the breakpoints: @c nested table @table @code @item del -Enable the breakpoint(s) temporarily, then delete it when -the program stops at the breakpoint. +Enable the breakpoints temporarily, then delete each one when +the program stops at it. @item once -Enable the breakpoint(s) temporarily, then disable it when -the program stops at the breakpoint. +Enable the breakpoints temporarily, then disable each one when +the program stops at it. @end table @cindex debugger commands, @code{ignore} @@ -28883,7 +28608,7 @@ gawk> @item @code{continue} [@var{count}] @itemx @code{c} [@var{count}] Resume program execution. If continued from a breakpoint and @var{count} is -specified, ignores the breakpoint at that location the next @var{count} times +specified, ignore the breakpoint at that location the next @var{count} times before stopping. @cindex debugger commands, @code{finish} @@ -28937,7 +28662,7 @@ automatic display variables, and debugger options. @item @code{step} [@var{count}] @itemx @code{s} [@var{count}] Continue execution until control reaches a different source line in the -current stack frame. @code{step} steps inside any function called within +current stack frame, stepping inside any function called within the line. If the argument @var{count} is supplied, steps that many times before stopping, unless it encounters a breakpoint or watchpoint. @@ -29050,7 +28775,7 @@ or field. String values must be enclosed between double quotes (@code{"}@dots{}@code{"}). You can also set special @command{awk} variables, such as @code{FS}, -@code{NF}, @code{NR}, and son on. +@code{NF}, @code{NR}, and so on. @cindex debugger commands, @code{w} (@code{watch}) @cindex debugger commands, @code{watch} @@ -29062,7 +28787,7 @@ You can also set special @command{awk} variables, such as @code{FS}, Add variable @var{var} (or field @code{$@var{n}}) to the watch list. The debugger then stops whenever the value of the variable or field changes. Each watched item is assigned a -number which can be used to delete it from the watch list using the +number that can be used to delete it from the watch list using the @code{unwatch} command. With a watchpoint, you may also supply a condition. This is an @@ -29090,11 +28815,11 @@ watch list. @node Execution Stack @subsection Working with the Stack -Whenever you run a program which contains any function calls, +Whenever you run a program that contains any function calls, @command{gawk} maintains a stack of all of the function calls leading up to where the program is right now. You can see how you got to where you are, and also move around in the stack to see what the state of things was in the -functions which called the one you are in. The commands for doing this are: +functions that called the one you are in. The commands for doing this are: @table @asis @cindex debugger commands, @code{bt} (@code{backtrace}) @@ -29129,8 +28854,8 @@ Then select and print the frame. @item @code{frame} [@var{n}] @itemx @code{f} [@var{n}] Select and print stack frame @var{n}. Frame 0 is the currently executing, -or @dfn{innermost}, frame (function call), frame 1 is the frame that -called the innermost one. The highest numbered frame is the one for the +or @dfn{innermost}, frame (function call); frame 1 is the frame that +called the innermost one. The highest-numbered frame is the one for the main program. The printed information consists of the frame number, function and argument names, source file, and the source line. @@ -29146,7 +28871,7 @@ Then select and print the frame. Besides looking at the values of variables, there is often a need to get other sorts of information about the state of your program and of the -debugging environment itself. The @command{gawk} debugger has one command which +debugging environment itself. The @command{gawk} debugger has one command that provides this information, appropriately called @code{info}. @code{info} is used with one of a number of arguments that tell it exactly what you want to know: @@ -29234,12 +28959,12 @@ The available options are: @table @asis @item @code{history_size} @cindex debugger history size -The maximum number of lines to keep in the history file @file{./.gawk_history}. -The default is 100. +Set the maximum number of lines to keep in the history file +@file{./.gawk_history}. The default is 100. @item @code{listsize} @cindex debugger default list amount -The number of lines that @code{list} prints. The default is 15. +Specify the number of lines that @code{list} prints. The default is 15. @item @code{outfile} @cindex redirect @command{gawk} output, in debugger @@ -29249,7 +28974,7 @@ standard output. @item @code{prompt} @cindex debugger prompt -The debugger prompt. The default is @samp{@w{gawk> }}. +Change the debugger prompt. The default is @samp{@w{gawk> }}. @item @code{save_history} [@code{on} | @code{off}] @cindex debugger history file @@ -29260,7 +28985,7 @@ The default is @code{on}. @cindex save debugger options Save current options to file @file{./.gawkrc} upon exit. The default is @code{on}. -Options are read back in to the next session upon startup. +Options are read back into the next session upon startup. @item @code{trace} [@code{on} | @code{off}] @cindex instruction tracing, in debugger @@ -29283,7 +29008,7 @@ command in the file. Also, the list of commands may include additional @code{source} commands; however, the @command{gawk} debugger will not source the same file more than once in order to avoid infinite recursion. -In addition to, or instead of the @code{source} command, you can use +In addition to, or instead of, the @code{source} command, you can use the @option{-D @var{file}} or @option{--debug=@var{file}} command-line options to execute commands from a file non-interactively (@pxref{Options}). @@ -29292,16 +29017,16 @@ options to execute commands from a file non-interactively @node Miscellaneous Debugger Commands @subsection Miscellaneous Commands -There are a few more commands which do not fit into the +There are a few more commands that do not fit into the previous categories, as follows: @table @asis @cindex debugger commands, @code{dump} @cindex @code{dump} debugger command @item @code{dump} [@var{filename}] -Dump bytecode of the program to standard output or to the file +Dump byte code of the program to standard output or to the file named in @var{filename}. This prints a representation of the internal -instructions which @command{gawk} executes to implement the @command{awk} +instructions that @command{gawk} executes to implement the @command{awk} commands in a program. This can be very enlightening, as the following partial dump of Davide Brini's obfuscated code (@pxref{Signature Program}) demonstrates: @@ -29398,7 +29123,7 @@ Print lines centered around line number @var{n} in source file @var{filename}. This command may change the current source file. @item @var{function} -Print lines centered around beginning of the +Print lines centered around the beginning of the function @var{function}. This command may change the current source file. @end table @@ -29410,16 +29135,16 @@ function @var{function}. This command may change the current source file. @item @code{quit} @itemx @code{q} Exit the debugger. Debugging is great fun, but sometimes we all have -to tend to other obligations in life, and sometimes we find the bug, +to tend to other obligations in life, and sometimes we find the bug and are free to go on to the next one! As we saw earlier, if you are -running a program, the debugger warns you if you accidentally type +running a program, the debugger warns you when you type @samp{q} or @samp{quit}, to make sure you really want to quit. @cindex debugger commands, @code{trace} @cindex @code{trace} debugger command @item @code{trace} [@code{on} | @code{off}] -Turn on or off a continuous printing of instructions which are about to -be executed, along with printing the @command{awk} line which they +Turn on or off continuous printing of the instructions that are about to +be executed, along with the @command{awk} lines they implement. The default is @code{off}. It is to be hoped that most of the ``opcodes'' in these instructions are @@ -29435,7 +29160,7 @@ fairly self-explanatory, and using @code{stepi} and @code{nexti} while If @command{gawk} is compiled with @uref{http://cnswww.cns.cwru.edu/php/chet/readline/readline.html, -the @code{readline} library}, you can take advantage of that library's +the GNU Readline library}, you can take advantage of that library's command completion and history expansion features. The following types of completion are available: @@ -29472,7 +29197,7 @@ and We hope you find the @command{gawk} debugger useful and enjoyable to work with, but as with any program, especially in its early releases, it still has -some limitations. A few which are worth being aware of are: +some limitations. A few that it's worth being aware of are: @itemize @value{BULLET} @item @@ -29488,13 +29213,13 @@ If you perused the dump of opcodes in @ref{Miscellaneous Debugger Commands} (or if you are already familiar with @command{gawk} internals), you will realize that much of the internal manipulation of data in @command{gawk}, as in many interpreters, is done on a stack. -@code{Op_push}, @code{Op_pop}, and the like, are the ``bread and butter'' of +@code{Op_push}, @code{Op_pop}, and the like are the ``bread and butter'' of most @command{gawk} code. Unfortunately, as of now, the @command{gawk} debugger does not allow you to examine the stack's contents. That is, the intermediate results of expression evaluation are on the -stack, but cannot be printed. Rather, only variables which are defined +stack, but cannot be printed. Rather, only variables that are defined in the program can be printed. Of course, a workaround for this is to use more explicit variables at the debugging stage and then change back to obscure, perhaps more optimal code later. @@ -29508,12 +29233,12 @@ programmer, you are expected to know the meaning of @item The @command{gawk} debugger is designed to be used by running a program (with all its parameters) on the command line, as described in @ref{Debugger Invocation}. -There is no way (as of now) to attach or ``break in'' to a running program. -This seems reasonable for a language which is used mainly for quickly +There is no way (as of now) to attach or ``break into'' a running program. +This seems reasonable for a language that is used mainly for quickly executing, short programs. @item -The @command{gawk} debugger only accepts source supplied with the @option{-f} option. +The @command{gawk} debugger only accepts source code supplied with the @option{-f} option. @end itemize @ignore @@ -29527,8 +29252,8 @@ be added, and of course feel free to try to add them yourself! @itemize @value{BULLET} @item Programs rarely work correctly the first time. Finding bugs -is @dfn{debugging} and a program that helps you find bugs is a -@dfn{debugger}. @command{gawk} has a built-in debugger that works very +is called debugging, and a program that helps you find bugs is a +debugger. @command{gawk} has a built-in debugger that works very similarly to the GNU Debugger, GDB. @item @@ -29548,7 +29273,7 @@ breakpoints, execution, viewing and changing data, working with the stack, getting information, and other tasks. @item -If the @code{readline} library is available when @command{gawk} is +If the GNU Readline library is available when @command{gawk} is compiled, it is used by the debugger to provide command-line history and editing. @@ -29805,7 +29530,7 @@ is available like so: @example $ @kbd{gawk --version} @print{} GNU Awk 4.1.2, API: 1.1 (GNU MPFR 3.1.0-p3, GNU MP 5.0.2) -@print{} Copyright (C) 1989, 1991-2014 Free Software Foundation. +@print{} Copyright (C) 1989, 1991-2015 Free Software Foundation. @dots{} @end example @@ -30459,7 +30184,7 @@ When asked about the algorithm used, Katie replied: @quotation It's not that well known but it's not that obscure either. It's Euler's modification to Newton's method for calculating pi. -Take a look at lines (23) - (25) here: @uref{http://mathworld.wolfram.com/PiFormulas.htm}. +Take a look at lines (23) - (25) here: @uref{http://mathworld.wolfram.com/PiFormulas.html}. The algorithm I wrote simply expands the multiply by 2 and works from the innermost expression outwards. I used this to program HP calculators @@ -30509,7 +30234,7 @@ Allowing completely alphabetic strings to have valid numeric values is also a very severe departure from historical practice. @end itemize -The second problem is that the @code{gawk} maintainer feels that this +The second problem is that the @command{gawk} maintainer feels that this interpretation of the standard, which requires a certain amount of ``language lawyering'' to arrive at in the first place, was not even intended by the standard developers. In other words, ``we see how you @@ -30668,7 +30393,7 @@ When @option{--sandbox} is specified, extensions are disabled * Finding Extensions:: How @command{gawk} finds compiled extensions. * Extension Example:: Example C code for an extension. * Extension Samples:: The sample extensions that ship with - @code{gawk}. + @command{gawk}. * gawkextlib:: The @code{gawkextlib} project. * Extension summary:: Extension summary. * Extension Exercises:: Exercises. @@ -31632,7 +31357,7 @@ If the concept of a ``record terminator'' makes sense, then @code{*rt_start} should be set to point to the data to be used for @code{RT}, and @code{*rt_len} should be set to the length of the data. Otherwise, @code{*rt_len} should be set to zero. -@code{gawk} makes its own copy of this data, so the +@command{gawk} makes its own copy of this data, so the extension must manage this storage. @end table @@ -31678,7 +31403,7 @@ When writing an input parser, you should think about (and document) how it is expected to interact with @command{awk} code. You may want it to always be called, and take effect as appropriate (as the @code{readdir} extension does). Or you may want it to take effect -based upon the value of an @code{awk} variable, as the XML extension +based upon the value of an @command{awk} variable, as the XML extension from the @code{gawkextlib} project does (@pxref{gawkextlib}). In the latter case, code in a @code{BEGINFILE} section can look at @code{FILENAME} and @code{ERRNO} to decide whether or @@ -32461,7 +32186,7 @@ converts it to a string. Using non-integral values is possible, but requires that you understand how such values are converted to strings (@pxref{Conversion}); thus using integral values is safest. -As with @emph{all} strings passed into @code{gawk} from an extension, +As with @emph{all} strings passed into @command{gawk} from an extension, the string value of @code{index} must come from @code{gawk_malloc()}, @code{gawk_calloc()} or @code{gawk_realloc()}, and @command{gawk} releases the storage. @@ -34747,9 +34472,7 @@ online documentation}. @node V7/SVR3.1 @appendixsec Major Changes Between V7 and SVR3.1 -@c STARTOFRANGE gawkv @cindex @command{awk}, versions of -@c STARTOFRANGE gawkv1 @cindex @command{awk}, versions of, changes between V7 and SVR3.1 The @command{awk} language evolved considerably between the release of @@ -34836,7 +34559,6 @@ Multiple @code{BEGIN} and @code{END} rules Multidimensional arrays (@pxref{Multidimensional}). @end itemize -@c ENDOFRANGE gawkv1 @node SVR4 @appendixsec Changes Between SVR3.1 and SVR4 @@ -34951,7 +34673,6 @@ not permitted by the POSIX standard. The 2008 POSIX standard can be found online at @url{http://www.opengroup.org/onlinepubs/9699919799/}. -@c ENDOFRANGE gawkv @node BTL @appendixsec Extensions in Brian Kernighan's @command{awk} @@ -34997,11 +34718,8 @@ available in his @command{awk}. @node POSIX/GNU @appendixsec Extensions in @command{gawk} Not in POSIX @command{awk} -@c STARTOFRANGE fripls @cindex compatibility mode (@command{gawk}), extensions -@c STARTOFRANGE exgnot @cindex extensions, in @command{gawk}, not in POSIX @command{awk} -@c STARTOFRANGE posnot @cindex POSIX, @command{gawk} extensions not included in The GNU implementation, @command{gawk}, adds a large number of features. They can all be disabled with either the @option{--traditional} or @@ -35330,9 +35048,6 @@ MirBSD @c XXX ADD MORE STUFF HERE -@c ENDOFRANGE fripls -@c ENDOFRANGE exgnot -@c ENDOFRANGE posnot @c This does not need to be in the formal book. @ifclear FOR_PRINT @@ -36419,9 +36134,7 @@ the appropriate credit where credit is due. @c last two commas are part of see also @cindex operating systems, See Also GNU/Linux@comma{} PC operating systems@comma{} Unix -@c STARTOFRANGE gligawk @cindex @command{gawk}, installing -@c STARTOFRANGE ingawk @cindex installing @command{gawk} This appendix provides instructions for installing @command{gawk} on the various platforms that are supported by the developers. The primary @@ -36531,7 +36244,6 @@ a local expert. @node Distribution contents @appendixsubsec Contents of the @command{gawk} Distribution -@c STARTOFRANGE gawdis @cindex @command{gawk}, distribution The @command{gawk} distribution has a number of C source files, @@ -36629,10 +36341,10 @@ The generated Info file for this @value{DOCUMENT}. @item doc/gawkinet.texi The Texinfo source file for @ifinfo -@inforef{Top, , General Introduction, gawkinet, TCP/IP Internetworking with @command{gawk}}. +@inforef{Top, , General Introduction, gawkinet, @value{GAWKINETTITLE}}. @end ifinfo @ifnotinfo -@cite{TCP/IP Internetworking with @command{gawk}}. +@cite{@value{GAWKINETTITLE}}. @end ifnotinfo It should be processed with @TeX{} (via @command{texi2dvi} or @command{texi2pdf}) @@ -36641,7 +36353,7 @@ with @command{makeinfo} to produce an Info or HTML file. @item doc/gawkinet.info The generated Info file for -@cite{TCP/IP Internetworking with @command{gawk}}. +@cite{@value{GAWKINETTITLE}}. @item doc/igawk.1 The @command{troff} source for a manual page describing the @command{igawk} @@ -36730,7 +36442,6 @@ directory to run your version of @command{gawk} against the test suite. If @command{gawk} successfully passes @samp{make check}, then you can be confident of a successful port. @end table -@c ENDOFRANGE gawdis @node Unix Installation @appendixsec Compiling and Installing @command{gawk} on Unix-Like Systems @@ -36881,7 +36592,7 @@ can be configured and compiled. @cindex @option{--disable-lint} configuration option @cindex configuration option, @code{--disable-lint} @item --disable-lint -Disable all lint checking within @code{gawk}. The +Disable all lint checking within @command{gawk}. The @option{--lint} and @option{--lint-old} options (@pxref{Options}) are accepted, but silently do nothing. @@ -37195,9 +36906,7 @@ multibyte functionality is not available. @node PC Using @appendixsubsubsec Using @command{gawk} on PC Operating Systems -@c STARTOFRANGE opgawx @cindex operating systems, PC, @command{gawk} on -@c STARTOFRANGE pcgawon @cindex PC operating systems, @command{gawk} on Under MS-DOS and MS-Windows, the Cygwin and MinGW environments support @@ -37705,8 +37414,6 @@ $ @kbd{gawk :== $sys$common:[syshlp.examples.tcpip.snmp]gawk.exe} This is apparently @value{PVERSION} 2.15.6, which is extremely old. We recommend compiling and using the current version. -@c ENDOFRANGE opgawx -@c ENDOFRANGE pcgawon @node Bugs @appendixsec Reporting Problems and Bugs @@ -37717,9 +37424,7 @@ recommend compiling and using the current version. @end quotation @c the radio show, not the book. :-) -@c STARTOFRANGE dbugg @cindex debugging @command{gawk}, bug reports -@c STARTOFRANGE tblgawb @cindex troubleshooting, @command{gawk}, bug reports If you have problems with @command{gawk} or think that you have found a bug, report it to the developers; we cannot promise to do anything @@ -37816,12 +37521,9 @@ The people maintaining the various @command{gawk} ports are: If your bug is also reproducible under Unix, send a copy of your report to the @EMAIL{bug-gawk@@gnu.org,bug-gawk at gnu dot org} email list as well. -@c ENDOFRANGE dbugg -@c ENDOFRANGE tblgawb @node Other Versions @appendixsec Other Freely Available @command{awk} Implementations -@c STARTOFRANGE awkim @cindex @command{awk}, implementations @ignore From: emory!amc.com!brennan (Michael Brennan) @@ -37881,7 +37583,7 @@ git clone git://github.com/onetrueawk/awk bwkawk @end example @noindent -This command creates a copy of the @uref{http://www.git-scm.com, Git} +This command creates a copy of the @uref{http://git-scm.com, Git} repository in a directory named @file{bwkawk}. If you leave that argument off the @command{git} command line, the repository copy is created in a directory named @file{awk}. @@ -37946,7 +37648,7 @@ To get @command{awka}, go to @url{http://sourceforge.net/projects/awka}. @c andrewsumner@@yahoo.net The project seems to be frozen; no new code changes have been made -since approximately 2003. +since approximately 2001. @cindex Beebe, Nelson H.F.@: @cindex @command{pawk} (profiling version of Brian Kernighan's @command{awk}) @@ -38042,7 +37744,6 @@ See also the ``Versions and implementations'' section of the Wikipedia article} for information on additional versions. @end table -@c ENDOFRANGE awkim @node Installation summary @appendixsec Summary @@ -38080,15 +37781,11 @@ implementations. Many are POSIX compliant; others are less so. @end itemize -@c ENDOFRANGE gligawk -@c ENDOFRANGE ingawk @ifclear FOR_PRINT @node Notes @appendix Implementation Notes -@c STARTOFRANGE gawii @cindex @command{gawk}, implementation issues -@c STARTOFRANGE impis @cindex implementation issues, @command{gawk} This appendix contains information mainly of interest to implementers and @@ -38164,7 +37861,7 @@ However, if you want to modify @command{gawk} and contribute back your changes, you will probably wish to work with the development version. To do so, you will need to access the @command{gawk} source code repository. The code is maintained using the -@uref{http://git-scm.com/, Git distributed version control system}. +@uref{http://git-scm.com, Git distributed version control system}. You will need to install it if your system doesn't have it. Once you have done so, use the command: @@ -38193,11 +37890,8 @@ that has a Git plug-in for working with Git repositories. @node Adding Code @appendixsubsec Adding New Features -@c STARTOFRANGE adfgaw @cindex adding, features to @command{gawk} -@c STARTOFRANGE fadgaw @cindex features, adding to @command{gawk} -@c STARTOFRANGE gawadf @cindex @command{gawk}, features, adding You are free to add any new features you like to @command{gawk}. However, if you want your changes to be incorporated into the @command{gawk} @@ -38232,7 +37926,7 @@ for information on getting the latest version of @command{gawk}.) @item @ifnotinfo -Follow the @uref{http://www.gnu.org/prep/standards/, @cite{GNU Coding Standards}}. +Follow the @cite{GNU Coding Standards}. @end ifnotinfo @ifinfo See @inforef{Top, , Version, standards, GNU Coding Standards}. @@ -38241,7 +37935,7 @@ This document describes how GNU software should be written. If you haven't read it, please do so, preferably @emph{before} starting to modify @command{gawk}. (The @cite{GNU Coding Standards} are available from the GNU Project's -@uref{http://www.gnu.org/prep/standards_toc.html, website}. +@uref{http://www.gnu.org/prep/standards/, website}. Texinfo, Info, and DVI versions are also available.) @cindex @command{gawk}, coding style in @@ -38364,9 +38058,6 @@ Although this sounds like a lot of work, please remember that while you may write the new code, I have to maintain it and support it. If it isn't possible for me to do that with a minimum of extra work, then I probably will not. -@c ENDOFRANGE adfgaw -@c ENDOFRANGE gawadf -@c ENDOFRANGE fadgaw @node New Ports @appendixsubsec Porting @command{gawk} to a New Operating System @@ -38500,7 +38191,6 @@ coding style and brace layout that suits your taste. @node Derived Files @appendixsubsec Why Generated Files Are Kept In Git -@c STARTOFRANGE gawkgit @cindex Git, use of for @command{gawk} source code @c From emails written March 22, 2012, to the gawk developers list. @@ -38689,7 +38379,6 @@ wget http://git.savannah.gnu.org/cgit/gawk.git/snapshot/gawk-@var{branchname}.ta @noindent to retrieve a snapshot of the given branch. -@c ENDOFRANGE gawkgit @node Future Extensions @appendixsec Probable Future Extensions @@ -39070,13 +38759,10 @@ of @command{gawk}, but it @emph{will} be removed in the next major release. @end itemize -@c ENDOFRANGE impis -@c ENDOFRANGE gawii @node Basic Concepts @appendix Basic Programming Concepts @cindex programming, concepts -@c STARTOFRANGE procon @cindex programming, concepts This @value{APPENDIX} attempts to define some of the basic concepts @@ -39314,7 +39000,6 @@ standard for C. This standard became an ISO standard in 1990. In 1999, a revised ISO C standard was approved and released. Where it makes sense, POSIX @command{awk} is compatible with 1999 ISO C. -@c ENDOFRANGE procon @node Glossary @unnumbered Glossary @@ -39365,6 +39050,21 @@ languages. These standards often become international standards as well. See also ``ISO.'' +@item Argument +An argument can be two different things. It can be an option or a +@value{FN} passed to a command while invoking it from the command line, or +it can be something passed to a @dfn{function} inside a program, e.g. +inside @command{awk}. + +In the latter case, an argument can be passed to a function in two ways. +Either it is given to the called function by value, i.e., a copy of the +value of the variable is made available to the called function, but the +original variable cannot be modified by the function itself; or it is +given by reference, i.e., a pointer to the interested variable is passed to +the function, which can then directly modify it. In @command{awk} +scalars are passed by value, and arrays are passed by reference. +See ``Pass By Value/Reference.'' + @item Array A grouping of multiple values under the same name. Most languages just provide sequential arrays. @@ -39406,6 +39106,25 @@ The GNU version of the standard shell @end ifinfo See also ``Bourne Shell.'' +@item Binary +Base-two notation, where the digits are @code{0}--@code{1}. Since +electronic circuitry works ``naturally'' in base 2 (just think of Off/On), +everything inside a computer is calculated using base 2. Each digit +represents the presence (or absence) of a power of 2 and is called a +@dfn{bit}. So, for example, the base-two number @code{10101} is +the same as decimal 21, ((1 x 16) + (1 x 4) + (1 x 1)). + +Since base-two numbers quickly become +very long to read and write, they are usually grouped by 3 (i.e., they are +read as octal numbers), or by 4 (i.e., they are read as hexadecimal +numbers). There is no direct way to insert base 2 numbers in a C program. +If need arises, such numbers are usually inserted as octal or hexadecimal +numbers. The number of base-two digits that fit into registers used for +representing integer numbers in computers is a rough indication of the +computing power of the computer itself. Most computers nowadays use 64 +bits for representing integer numbers in their registers, but 32-bit, +16-bit and 8-bit registers have been widely used in the past. +@xref{Nondecimal-numbers}. @item Bit Short for ``Binary Digit.'' All values in computer memory ultimately reduce to binary digits: values @@ -39437,6 +39156,19 @@ The characters @samp{@{} and @samp{@}}. Braces are used in @command{awk} for delimiting actions, compound statements, and function bodies. +@item Bracket Expression +Inside a @dfn{regular expression}, an expression included in square +brackets, meant to designate a single character as belonging to a +specified character class. A bracket expression can contain a list of one +or more characters, like @samp{[abc]}, a range of characters, like +@samp{[A-Z]}, or a name, delimited by @samp{:}, that designates a known set +of characters, like @samp{[:digit:]}. The form of bracket expression +enclosed between @samp{:} is independent of the underlying representation +of the character themselves, which could utilize the ASCII, ECBDIC, or +Unicode codesets, depending on the architecture of the computer system, and on +localization. +See also ``Regular Expression.'' + @item Built-in Function The @command{awk} language provides built-in functions that perform various numerical, I/O-related, and string computations. Examples are @@ -39490,9 +39222,25 @@ points out similarities between @command{awk} and C when appropriate. In general, @command{gawk} attempts to be as similar to the 1990 version of ISO C as makes sense. +@item C Shell +The C Shell (@command{csh} or its improved version, @command{tcsh}) is a Unix shell that was +created by Bill Joy in the late 1970s. The C shell was differentiated from +other shells by its interactive features and overall style, which +looks more like C. The C Shell is not backward compatible with the Bourne +Shell, so special attention is required when converting scripts +written for other Unix shells to the C shell, especially with regard to the management of +shell variables. +See also ``Bourne Shell.'' + @item C++ A popular object-oriented programming language derived from C. +@item Character Class +See ``Bracket Expression.'' + +@item Character List +See ``Bracket Expression.'' + @cindex ASCII @cindex ISO 8859-1 @cindex ISO Latin-1 @@ -39516,7 +39264,7 @@ A preprocessor for @command{pic} that reads descriptions of molecules and produces @command{pic} input for drawing them. It was written in @command{awk} by Brian Kernighan and Jon Bentley, and is available from -@uref{http://netlib.sandia.gov/netlib/typesetting/chem.gz}. +@uref{http://netlib.org/typesetting/chem}. @item Comparison Expression A relation that is either true or false, such as @samp{a < b}. @@ -39532,11 +39280,23 @@ machine-executable object code. The object code is then executed directly by the computer. See also ``Interpreter.'' +@item Complemented Bracket Expression +The negation of a @dfn{bracket expression}. All that is @emph{not} +described by a given bracket expression. The symbol @samp{^} precedes +the negated bracket expression. E.g.: @samp{[[^:digit:]} +designates whatever character is not a digit. @samp{[^bad]} +designates whatever character is not one of the letters @samp{b}, @samp{a}, +or @samp{d}. +See ``Bracket Expression.'' + @item Compound Statement A series of @command{awk} statements, enclosed in curly braces. Compound statements may be nested. (@xref{Statements}.) +@item Computed Regexps +See ``Dynamic Regular Expressions.'' + @item Concatenation Concatenating two strings means sticking them together, one after another, producing a new string. For example, the string @samp{foo} concatenated with @@ -39551,6 +39311,13 @@ expression is the value of @var{expr2}; otherwise the value is @var{expr3}. In either case, only one of @var{expr2} and @var{expr3} is evaluated. (@xref{Conditional Exp}.) +@item Control Statement +A control statement is an instruction to perform a given operation or a set +of operations inside an @command{awk} program, if a given condition is +true. Control statements are: @code{if}, @code{for}, @code{while}, and +@code{do} +(@pxref{Statements}). + @cindex McIlroy, Doug @cindex cookie @item Cookie @@ -39705,6 +39472,11 @@ Format strings control the appearance of output in the are controlled by the format strings contained in the predefined variables @code{CONVFMT} and @code{OFMT}. (@xref{Control Letters}.) +@item Fortran +Shorthand for FORmula TRANslator, one of the first programming languages +available for scientific calculations. It was created by John Backus, +and has been available since 1957. It is still in use today. + @item Free Documentation License This document describes the terms under which this @value{DOCUMENT} is published and may be copied. (@xref{GNU Free Documentation License}.) @@ -39722,10 +39494,21 @@ Emacs editor. GNU Emacs is the most widely used version of Emacs today. See ``Free Software Foundation.'' @item Function -A specialized group of statements used to encapsulate general -or program-specific tasks. @command{awk} has a number of built-in -functions, and also allows you to define your own. -(@xref{Functions}.) +A part of an @command{awk} program that can be invoked from every point of +the program, to perform a task. @command{awk} has several built-in +functions. +Users can define their own functions in every part of the program. +Function can be recursive, i.e., they may invoke themselves. +@xref{Functions}. +In @command{gawk} it is also possible to have functions shared +among different programs, and included where required using the +@code{@@include} directive +(@pxref{Include Files}). +In @command{gawk} the name of the function that should be invoked +can be generated at run time, i.e., dynamically. +The @command{gawk} extension API provides constructor functions +(@pxref{Constructor Functions}). + @item @command{gawk} The GNU implementation of @command{awk}. @@ -39849,6 +39632,12 @@ meaning. Keywords are reserved and may not be used as variable names. and @code{while}. +@item Korn Shell +The Korn Shell (@command{ksh}) is a Unix shell which was developed by David Korn at Bell +Laboratories in the early 1980s. The Korn Shell is backward-compatible with the Bourne +shell and includes many features of the C shell. +See also ``Bourne Shell.'' + @cindex LGPL (Lesser General Public License) @cindex Lesser General Public License (LGPL) @cindex GNU Lesser General Public License @@ -39888,6 +39677,14 @@ Characters used within a regexp that do not stand for themselves. Instead, they denote regular expression operations, such as repetition, grouping, or alternation. +@item Nesting +Nesting is where information is organized in layers, or where objects +contain other similar objects. +In @command{gawk} the @code{@@include} +directive can be nested. The ``natural'' nesting of arithmetic and +logical operations can be changed using parentheses +(@pxref{Precedence}). + @item No-op An operation that does nothing. @@ -39908,6 +39705,11 @@ Octal numbers are written in C using a leading @samp{0}, to indicate their base. Thus, @code{013} is 11 ((1 x 8) + 3). @xref{Nondecimal-numbers}. +@item Output Record +A single chunk of data that is written out by @command{awk}. Usually, an +@command{awk} output record consists of one or more lines of text. +@xref{Records}. + @item Pattern Patterns tell @command{awk} which input records are interesting to which rules. @@ -39922,6 +39724,9 @@ An acronym describing what is possibly the most frequent source of computer usage problems. (Problem Exists Between Keyboard And Chair.) +@item Plug-in +See ``Extensions.'' + @item POSIX The name for a series of standards that specify a Portable Operating System interface. The ``IX'' denotes @@ -39946,6 +39751,9 @@ A sequence of consecutive lines from the input file(s). A pattern can specify ranges of input lines for @command{awk} to process or it can specify single lines. (@xref{Pattern Overview}.) +@item Record +See ``Input record'' and ``Output record.'' + @item Recursion When a function calls itself, either directly or indirectly. If this is clear, stop, and proceed to the next entry. @@ -39963,6 +39771,15 @@ operators. (@xref{Getline}, and @ref{Redirection}.) +@item Reference Counts +An internal mechanism in @command{gawk} to minimize the amount of memory +needed to store the value of string variables. If the value assumed by +a variable is used in more than one place, only one copy of the value +itself is kept, and the associated reference count is increased when the +same value is used by an additional variable, and decresed when the related +variable is no longer in use. When the reference count goes to zero, +the memory space used to store the value of the variable is freed. + @item Regexp See ``Regular Expression.'' @@ -39980,6 +39797,15 @@ slashes, such as @code{/foo/}. This regular expression is chosen when you write the @command{awk} program and cannot be changed during its execution. (@xref{Regexp Usage}.) +@item Regular Expression Operators +See ``Metacharacters.'' + +@item Rounding +Rounding the result of an arithmetic operation can be tricky. +More than one way of rounding exists, and in @command{gawk} +it is possible to choose which method should be used in a program. +@xref{Setting the rounding mode}. + @item Rule A segment of an @command{awk} program that specifies how to process single input records. A rule consists of a @dfn{pattern} and an @dfn{action}. @@ -40039,6 +39865,12 @@ A @value{FN} interpreted internally by @command{gawk}, instead of being handed directly to the underlying operating system---for example, @file{/dev/stderr}. (@xref{Special Files}.) +@item Statement +An expression inside an @command{awk} program in the action part +of a pattern--action rule, or inside an +@command{awk} function. A statement can be a variable assignment, +an array operation, a loop, etc. + @item Stream Editor A program that reads records from an input stream and processes them one or more at a time. This is in contrast with batch programs, which may @@ -40089,9 +39921,14 @@ This is standard time in Greenwich, England, which is used as a reference time for day and date calculations. See also ``Epoch'' and ``GMT.'' +@item Variable +A name for a value. In @command{awk}, variables may be either scalars +or arrays. + @item Whitespace A sequence of space, TAB, or newline characters occurring inside an input record or a string. + @end table @end ifclear @@ -708,6 +708,8 @@ set_IGNORECASE() load_casetable(); if (do_traditional) IGNORECASE = false; + else if ((n->flags & (NUMCUR|NUMBER)) != 0) + IGNORECASE = ! iszero(n); else if ((n->flags & (STRING|STRCUR)) != 0) { if ((n->flags & MAYBE_NUM) == 0) { (void) force_string(n); @@ -716,9 +718,7 @@ set_IGNORECASE() (void) force_number(n); IGNORECASE = ! iszero(n); } - } else if ((n->flags & (NUMCUR|NUMBER)) != 0) - IGNORECASE = ! iszero(n); - else + } else IGNORECASE = false; /* shouldn't happen */ set_RS(); /* set_RS() calls set_FS() if need be, for us */ diff --git a/extension/ChangeLog b/extension/ChangeLog index 41c8a0e4..e30ad593 100644 --- a/extension/ChangeLog +++ b/extension/ChangeLog @@ -1,3 +1,15 @@ +2015-01-24 Arnold D. Robbins <arnold@skeeve.com> + + Infrastructure updates. + + Automake 1.15. Libtool 2.4.5. + + * configure.ac: Remove gettext macros. + +2015-01-07 Arnold D. Robbins <arnold@skeeve.com> + + * testext.c (var_test): Adjust for PROCINFO now being there. + 2014-11-23 Arnold D. Robbins <arnold@skeeve.com> * inplace.c (do_inplace_begin): Jump through hoops to silence diff --git a/extension/INSTALL b/extension/INSTALL index 6e90e07d..20998407 100644 --- a/extension/INSTALL +++ b/extension/INSTALL @@ -1,7 +1,7 @@ Installation Instructions ************************* -Copyright (C) 1994-1996, 1999-2002, 2004-2012 Free Software Foundation, +Copyright (C) 1994-1996, 1999-2002, 2004-2013 Free Software Foundation, Inc. Copying and distribution of this file, with or without modification, @@ -12,8 +12,8 @@ without warranty of any kind. Basic Installation ================== - Briefly, the shell commands `./configure; make; make install' should -configure, build, and install this package. The following + Briefly, the shell command `./configure && make && make install' +should configure, build, and install this package. The following more-detailed instructions are generic; see the `README' file for instructions specific to this package. Some packages provide this `INSTALL' file but do not implement all of the features documented diff --git a/extension/Makefile.in b/extension/Makefile.in index 2596d282..2a6ef5e0 100644 --- a/extension/Makefile.in +++ b/extension/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -38,7 +38,17 @@ # VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -102,33 +112,15 @@ POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ subdir = . -DIST_COMMON = INSTALL NEWS README AUTHORS ChangeLog \ - $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ - $(top_srcdir)/configure $(am__configure_deps) \ - $(srcdir)/configh.in ABOUT-NLS $(top_srcdir)/build-aux/depcomp \ - $(dist_man_MANS) COPYING build-aux/ChangeLog build-aux/ar-lib \ - build-aux/compile build-aux/config.guess \ - build-aux/config.rpath build-aux/config.sub build-aux/depcomp \ - build-aux/install-sh build-aux/missing build-aux/ltmain.sh \ - $(top_srcdir)/build-aux/ar-lib $(top_srcdir)/build-aux/compile \ - $(top_srcdir)/build-aux/config.guess \ - $(top_srcdir)/build-aux/config.rpath \ - $(top_srcdir)/build-aux/config.sub \ - $(top_srcdir)/build-aux/install-sh \ - $(top_srcdir)/build-aux/ltmain.sh \ - $(top_srcdir)/build-aux/missing ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/dirfd.m4 \ - $(top_srcdir)/m4/gettext.m4 $(top_srcdir)/m4/iconv.m4 \ - $(top_srcdir)/m4/intlmacosx.m4 $(top_srcdir)/m4/lib-ld.m4 \ - $(top_srcdir)/m4/lib-link.m4 $(top_srcdir)/m4/lib-prefix.m4 \ $(top_srcdir)/m4/libtool.m4 $(top_srcdir)/m4/ltoptions.m4 \ $(top_srcdir)/m4/ltsugar.m4 $(top_srcdir)/m4/ltversion.m4 \ - $(top_srcdir)/m4/lt~obsolete.m4 $(top_srcdir)/m4/nls.m4 \ - $(top_srcdir)/m4/po.m4 $(top_srcdir)/m4/progtest.m4 \ - $(top_srcdir)/configure.ac + $(top_srcdir)/m4/lt~obsolete.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(top_srcdir)/configure \ + $(am__configure_deps) $(am__DIST_COMMON) am__CONFIG_DISTCLEAN_FILES = config.status config.cache config.log \ configure.lineno config.status.lineno mkinstalldirs = $(install_sh) -d @@ -166,8 +158,7 @@ am__installdirs = "$(DESTDIR)$(pkgextensiondir)" \ "$(DESTDIR)$(man3dir)" LTLIBRARIES = $(pkgextension_LTLIBRARIES) am__DEPENDENCIES_1 = -am__DEPENDENCIES_2 = $(am__DEPENDENCIES_1) -filefuncs_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +filefuncs_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_filefuncs_la_OBJECTS = filefuncs.lo stack.lo gawkfts.lo filefuncs_la_OBJECTS = $(am_filefuncs_la_OBJECTS) AM_V_lt = $(am__v_lt_@AM_V@) @@ -177,67 +168,67 @@ am__v_lt_1 = filefuncs_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(filefuncs_la_LDFLAGS) $(LDFLAGS) -o $@ -fnmatch_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +fnmatch_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_fnmatch_la_OBJECTS = fnmatch.lo fnmatch_la_OBJECTS = $(am_fnmatch_la_OBJECTS) fnmatch_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(fnmatch_la_LDFLAGS) $(LDFLAGS) -o $@ -fork_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +fork_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_fork_la_OBJECTS = fork.lo fork_la_OBJECTS = $(am_fork_la_OBJECTS) fork_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(fork_la_LDFLAGS) $(LDFLAGS) -o $@ -inplace_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +inplace_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_inplace_la_OBJECTS = inplace.lo inplace_la_OBJECTS = $(am_inplace_la_OBJECTS) inplace_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(inplace_la_LDFLAGS) $(LDFLAGS) -o $@ -ordchr_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +ordchr_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_ordchr_la_OBJECTS = ordchr.lo ordchr_la_OBJECTS = $(am_ordchr_la_OBJECTS) ordchr_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(ordchr_la_LDFLAGS) $(LDFLAGS) -o $@ -readdir_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +readdir_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_readdir_la_OBJECTS = readdir.lo readdir_la_OBJECTS = $(am_readdir_la_OBJECTS) readdir_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(readdir_la_LDFLAGS) $(LDFLAGS) -o $@ -readfile_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +readfile_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_readfile_la_OBJECTS = readfile.lo readfile_la_OBJECTS = $(am_readfile_la_OBJECTS) readfile_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(readfile_la_LDFLAGS) $(LDFLAGS) -o $@ -revoutput_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +revoutput_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_revoutput_la_OBJECTS = revoutput.lo revoutput_la_OBJECTS = $(am_revoutput_la_OBJECTS) revoutput_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(revoutput_la_LDFLAGS) $(LDFLAGS) -o $@ -revtwoway_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +revtwoway_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_revtwoway_la_OBJECTS = revtwoway.lo revtwoway_la_OBJECTS = $(am_revtwoway_la_OBJECTS) revtwoway_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(revtwoway_la_LDFLAGS) $(LDFLAGS) -o $@ -rwarray_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +rwarray_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_rwarray_la_OBJECTS = rwarray.lo rwarray_la_OBJECTS = $(am_rwarray_la_OBJECTS) rwarray_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(rwarray_la_LDFLAGS) $(LDFLAGS) -o $@ -testext_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +testext_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_testext_la_OBJECTS = testext.lo testext_la_OBJECTS = $(am_testext_la_OBJECTS) testext_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ $(LIBTOOLFLAGS) --mode=link $(CCLD) $(AM_CFLAGS) $(CFLAGS) \ $(testext_la_LDFLAGS) $(LDFLAGS) -o $@ -time_la_DEPENDENCIES = $(am__DEPENDENCIES_2) +time_la_DEPENDENCIES = $(am__DEPENDENCIES_1) am_time_la_OBJECTS = time.lo time_la_OBJECTS = $(am_time_la_OBJECTS) time_la_LINK = $(LIBTOOL) $(AM_V_lt) --tag=CC $(AM_LIBTOOLFLAGS) \ @@ -333,6 +324,19 @@ ETAGS = etags CTAGS = ctags CSCOPE = cscope DIST_SUBDIRS = $(SUBDIRS) +am__DIST_COMMON = $(dist_man_MANS) $(srcdir)/Makefile.in \ + $(srcdir)/configh.in $(top_srcdir)/build-aux/ar-lib \ + $(top_srcdir)/build-aux/compile \ + $(top_srcdir)/build-aux/config.guess \ + $(top_srcdir)/build-aux/config.sub \ + $(top_srcdir)/build-aux/depcomp \ + $(top_srcdir)/build-aux/install-sh \ + $(top_srcdir)/build-aux/ltmain.sh \ + $(top_srcdir)/build-aux/missing ABOUT-NLS AUTHORS COPYING \ + ChangeLog INSTALL NEWS README build-aux/ChangeLog \ + build-aux/ar-lib build-aux/compile build-aux/config.guess \ + build-aux/config.rpath build-aux/config.sub build-aux/depcomp \ + build-aux/install-sh build-aux/ltmain.sh build-aux/missing DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) distdir = $(PACKAGE)-$(VERSION) top_distdir = $(distdir) @@ -400,35 +404,24 @@ ECHO_T = @ECHO_T@ EGREP = @EGREP@ EXEEXT = @EXEEXT@ FGREP = @FGREP@ -GETTEXT_MACRO_VERSION = @GETTEXT_MACRO_VERSION@ -GMSGFMT = @GMSGFMT@ -GMSGFMT_015 = @GMSGFMT_015@ GREP = @GREP@ INSTALL = @INSTALL@ INSTALL_DATA = @INSTALL_DATA@ INSTALL_PROGRAM = @INSTALL_PROGRAM@ INSTALL_SCRIPT = @INSTALL_SCRIPT@ INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@ -INTLLIBS = @INTLLIBS@ -INTL_MACOSX_LIBS = @INTL_MACOSX_LIBS@ LD = @LD@ LDFLAGS = @LDFLAGS@ -LIBICONV = @LIBICONV@ -LIBINTL = @LIBINTL@ LIBOBJS = @LIBOBJS@ LIBS = @LIBS@ LIBTOOL = @LIBTOOL@ LIPO = @LIPO@ LN_S = @LN_S@ -LTLIBICONV = @LTLIBICONV@ -LTLIBINTL = @LTLIBINTL@ LTLIBOBJS = @LTLIBOBJS@ +LT_SYS_LIBRARY_PATH = @LT_SYS_LIBRARY_PATH@ MAKEINFO = @MAKEINFO@ MANIFEST_TOOL = @MANIFEST_TOOL@ MKDIR_P = @MKDIR_P@ -MSGFMT = @MSGFMT@ -MSGFMT_015 = @MSGFMT_015@ -MSGMERGE = @MSGMERGE@ NM = @NM@ NMEDIT = @NMEDIT@ OBJDUMP = @OBJDUMP@ @@ -443,17 +436,12 @@ PACKAGE_TARNAME = @PACKAGE_TARNAME@ PACKAGE_URL = @PACKAGE_URL@ PACKAGE_VERSION = @PACKAGE_VERSION@ PATH_SEPARATOR = @PATH_SEPARATOR@ -POSUB = @POSUB@ RANLIB = @RANLIB@ SED = @SED@ SET_MAKE = @SET_MAKE@ SHELL = @SHELL@ STRIP = @STRIP@ -USE_NLS = @USE_NLS@ VERSION = @VERSION@ -XGETTEXT = @XGETTEXT@ -XGETTEXT_015 = @XGETTEXT_015@ -XGETTEXT_EXTRA_OPTIONS = @XGETTEXT_EXTRA_OPTIONS@ abs_builddir = @abs_builddir@ abs_srcdir = @abs_srcdir@ abs_top_builddir = @abs_top_builddir@ @@ -606,7 +594,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -993,15 +980,15 @@ dist-xz: distdir $(am__post_remove_distdir) dist-tarZ: distdir - @echo WARNING: "Support for shar distribution archives is" \ - "deprecated." >&2 + @echo WARNING: "Support for distribution archives compressed with" \ + "legacy program 'compress' is deprecated." >&2 @echo WARNING: "It will be removed altogether in Automake 2.0" >&2 tardir=$(distdir) && $(am__tar) | compress -c >$(distdir).tar.Z $(am__post_remove_distdir) dist-shar: distdir - @echo WARNING: "Support for distribution archives compressed with" \ - "legacy program 'compress' is deprecated." >&2 + @echo WARNING: "Support for shar distribution archives is" \ + "deprecated." >&2 @echo WARNING: "It will be removed altogether in Automake 2.0" >&2 shar $(distdir) | GZIP=$(GZIP_ENV) gzip -c >$(distdir).shar.gz $(am__post_remove_distdir) @@ -1037,17 +1024,17 @@ distcheck: dist esac chmod -R a-w $(distdir) chmod u+w $(distdir) - mkdir $(distdir)/_build $(distdir)/_inst + mkdir $(distdir)/_build $(distdir)/_build/sub $(distdir)/_inst chmod a-w $(distdir) test -d $(distdir)/_build || exit 0; \ dc_install_base=`$(am__cd) $(distdir)/_inst && pwd | sed -e 's,^[^:\\/]:[\\/],/,'` \ && dc_destdir="$${TMPDIR-/tmp}/am-dc-$$$$/" \ && am__cwd=`pwd` \ - && $(am__cd) $(distdir)/_build \ - && ../configure \ + && $(am__cd) $(distdir)/_build/sub \ + && ../../configure \ $(AM_DISTCHECK_CONFIGURE_FLAGS) \ $(DISTCHECK_CONFIGURE_FLAGS) \ - --srcdir=.. --prefix="$$dc_install_base" \ + --srcdir=../.. --prefix="$$dc_install_base" \ && $(MAKE) $(AM_MAKEFLAGS) \ && $(MAKE) $(AM_MAKEFLAGS) dvi \ && $(MAKE) $(AM_MAKEFLAGS) check \ @@ -1238,6 +1225,8 @@ uninstall-man: uninstall-man3 tags tags-am uninstall uninstall-am uninstall-man \ uninstall-man3 uninstall-pkgextensionLTLIBRARIES +.PRECIOUS: Makefile + install-data-hook: for i in $(pkgextension_LTLIBRARIES) ; do \ diff --git a/extension/aclocal.m4 b/extension/aclocal.m4 index cd7f9c16..d2e755e4 100644 --- a/extension/aclocal.m4 +++ b/extension/aclocal.m4 @@ -1,6 +1,6 @@ -# generated automatically by aclocal 1.14.1 -*- Autoconf -*- +# generated automatically by aclocal 1.15 -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -20,7 +20,7 @@ You have another version of autoconf. It may work, but is not guaranteed to. If you have problems, you may need to regenerate the build system entirely. To do so, use the procedure documented by the package, typically 'autoreconf'.])]) -# Copyright (C) 2002-2013 Free Software Foundation, Inc. +# Copyright (C) 2002-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -32,10 +32,10 @@ To do so, use the procedure documented by the package, typically 'autoreconf'.]) # generated from the m4 files accompanying Automake X.Y. # (This private macro should not be called outside this file.) AC_DEFUN([AM_AUTOMAKE_VERSION], -[am__api_version='1.14' +[am__api_version='1.15' dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to dnl require some minimum version. Point them to the right macro. -m4_if([$1], [1.14.1], [], +m4_if([$1], [1.15], [], [AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl ]) @@ -51,12 +51,12 @@ m4_define([_AM_AUTOCONF_VERSION], []) # Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced. # This function is AC_REQUIREd by AM_INIT_AUTOMAKE. AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION], -[AM_AUTOMAKE_VERSION([1.14.1])dnl +[AM_AUTOMAKE_VERSION([1.15])dnl m4_ifndef([AC_AUTOCONF_VERSION], [m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl _AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))]) -# Copyright (C) 2011-2013 Free Software Foundation, Inc. +# Copyright (C) 2011-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -118,7 +118,7 @@ AC_SUBST([AR])dnl # AM_AUX_DIR_EXPAND -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -163,15 +163,14 @@ AC_SUBST([AR])dnl # configured tree to be moved without reconfiguration. AC_DEFUN([AM_AUX_DIR_EXPAND], -[dnl Rely on autoconf to set up CDPATH properly. -AC_PREREQ([2.50])dnl -# expand $ac_aux_dir to an absolute path -am_aux_dir=`cd $ac_aux_dir && pwd` +[AC_REQUIRE([AC_CONFIG_AUX_DIR_DEFAULT])dnl +# Expand $ac_aux_dir to an absolute path. +am_aux_dir=`cd "$ac_aux_dir" && pwd` ]) # AM_CONDITIONAL -*- Autoconf -*- -# Copyright (C) 1997-2013 Free Software Foundation, Inc. +# Copyright (C) 1997-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -202,7 +201,7 @@ AC_CONFIG_COMMANDS_PRE( Usually this means the macro was only invoked conditionally.]]) fi])]) -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -393,7 +392,7 @@ _AM_SUBST_NOTMAKE([am__nodep])dnl # Generate code to set up dependency tracking. -*- Autoconf -*- -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -469,7 +468,7 @@ AC_DEFUN([AM_OUTPUT_DEPENDENCY_COMMANDS], # Do all the work for Automake. -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -559,8 +558,8 @@ AC_REQUIRE([AC_PROG_MKDIR_P])dnl # <http://lists.gnu.org/archive/html/automake/2012-07/msg00001.html> # <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html> AC_SUBST([mkdir_p], ['$(MKDIR_P)']) -# We need awk for the "check" target. The system "awk" is bad on -# some platforms. +# We need awk for the "check" target (and possibly the TAP driver). The +# system "awk" is bad on some platforms. AC_REQUIRE([AC_PROG_AWK])dnl AC_REQUIRE([AC_PROG_MAKE_SET])dnl AC_REQUIRE([AM_SET_LEADING_DOT])dnl @@ -633,7 +632,11 @@ to "yes", and re-run configure. END AC_MSG_ERROR([Your 'rm' program is bad, sorry.]) fi -fi]) +fi +dnl The trailing newline in this macro's definition is deliberate, for +dnl backward compatibility and to allow trailing 'dnl'-style comments +dnl after the AM_INIT_AUTOMAKE invocation. See automake bug#16841. +]) dnl Hook into '_AC_COMPILER_EXEEXT' early to learn its expansion. Do not dnl add the conditional right here, as _AC_COMPILER_EXEEXT may be further @@ -662,7 +665,7 @@ for _am_header in $config_headers :; do done echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_count]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -673,7 +676,7 @@ echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_co # Define $install_sh. AC_DEFUN([AM_PROG_INSTALL_SH], [AC_REQUIRE([AM_AUX_DIR_EXPAND])dnl -if test x"${install_sh}" != xset; then +if test x"${install_sh+set}" != xset; then case $am_aux_dir in *\ * | *\ *) install_sh="\${SHELL} '$am_aux_dir/install-sh'" ;; @@ -683,7 +686,7 @@ if test x"${install_sh}" != xset; then fi AC_SUBST([install_sh])]) -# Copyright (C) 2003-2013 Free Software Foundation, Inc. +# Copyright (C) 2003-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -704,7 +707,7 @@ AC_SUBST([am__leading_dot])]) # Check to see how 'make' treats includes. -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -754,7 +757,7 @@ rm -f confinc confmf # Fake the existence of programs that GNU maintainers use. -*- Autoconf -*- -# Copyright (C) 1997-2013 Free Software Foundation, Inc. +# Copyright (C) 1997-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -793,7 +796,7 @@ fi # Helper functions for option handling. -*- Autoconf -*- -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -822,7 +825,7 @@ AC_DEFUN([_AM_SET_OPTIONS], AC_DEFUN([_AM_IF_OPTION], [m4_ifset(_AM_MANGLE_OPTION([$1]), [$2], [$3])]) -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -869,7 +872,7 @@ AC_LANG_POP([C])]) # For backward compatibility. AC_DEFUN_ONCE([AM_PROG_CC_C_O], [AC_REQUIRE([AC_PROG_CC])]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -888,7 +891,7 @@ AC_DEFUN([AM_RUN_LOG], # Check to make sure that the build environment is sane. -*- Autoconf -*- -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -969,7 +972,7 @@ AC_CONFIG_COMMANDS_PRE( rm -f conftest.file ]) -# Copyright (C) 2009-2013 Free Software Foundation, Inc. +# Copyright (C) 2009-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -1029,7 +1032,7 @@ AC_SUBST([AM_BACKSLASH])dnl _AM_SUBST_NOTMAKE([AM_BACKSLASH])dnl ]) -# Copyright (C) 2001-2013 Free Software Foundation, Inc. +# Copyright (C) 2001-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -1057,7 +1060,7 @@ fi INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s" AC_SUBST([INSTALL_STRIP_PROGRAM])]) -# Copyright (C) 2006-2013 Free Software Foundation, Inc. +# Copyright (C) 2006-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -1076,7 +1079,7 @@ AC_DEFUN([AM_SUBST_NOTMAKE], [_AM_SUBST_NOTMAKE($@)]) # Check how to create a tarball. -*- Autoconf -*- -# Copyright (C) 2004-2013 Free Software Foundation, Inc. +# Copyright (C) 2004-2014 Free Software Foundation, Inc. # # This file is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -1208,17 +1211,8 @@ AC_SUBST([am__untar]) ]) # _AM_PROG_TAR m4_include([m4/dirfd.m4]) -m4_include([m4/gettext.m4]) -m4_include([m4/iconv.m4]) -m4_include([m4/intlmacosx.m4]) -m4_include([m4/lib-ld.m4]) -m4_include([m4/lib-link.m4]) -m4_include([m4/lib-prefix.m4]) m4_include([m4/libtool.m4]) m4_include([m4/ltoptions.m4]) m4_include([m4/ltsugar.m4]) m4_include([m4/ltversion.m4]) m4_include([m4/lt~obsolete.m4]) -m4_include([m4/nls.m4]) -m4_include([m4/po.m4]) -m4_include([m4/progtest.m4]) diff --git a/extension/build-aux/ar-lib b/extension/build-aux/ar-lib index 67f5f36f..463b9ec0 100755 --- a/extension/build-aux/ar-lib +++ b/extension/build-aux/ar-lib @@ -4,7 +4,7 @@ me=ar-lib scriptversion=2012-03-01.08; # UTC -# Copyright (C) 2010-2012 Free Software Foundation, Inc. +# Copyright (C) 2010-2014 Free Software Foundation, Inc. # Written by Peter Rosin <peda@lysator.liu.se>. # # This program is free software; you can redistribute it and/or modify diff --git a/extension/build-aux/compile b/extension/build-aux/compile index 531136b0..a85b723c 100755 --- a/extension/build-aux/compile +++ b/extension/build-aux/compile @@ -3,7 +3,7 @@ scriptversion=2012-10-14.11; # UTC -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # Written by Tom Tromey <tromey@cygnus.com>. # # This program is free software; you can redistribute it and/or modify diff --git a/extension/build-aux/config.guess b/extension/build-aux/config.guess index 4438cd70..6c32c864 100755 --- a/extension/build-aux/config.guess +++ b/extension/build-aux/config.guess @@ -2,7 +2,7 @@ # Attempt to guess a canonical system name. # Copyright 1992-2014 Free Software Foundation, Inc. -timestamp='2014-01-01' +timestamp='2014-11-04' # This file is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by @@ -24,12 +24,12 @@ timestamp='2014-01-01' # program. This Exception is an additional permission under section 7 # of the GNU General Public License, version 3 ("GPLv3"). # -# Originally written by Per Bothner. +# Originally written by Per Bothner; maintained since 2000 by Ben Elliston. # # You can get the latest version of this script from: # http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD # -# Please send patches with a ChangeLog entry to config-patches@gnu.org. +# Please send patches to <config-patches@gnu.org>. me=`echo "$0" | sed -e 's,.*/,,'` @@ -149,7 +149,7 @@ Linux|GNU|GNU/*) LIBC=gnu #endif EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^LIBC'` + eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^LIBC' | sed 's, ,,g'` ;; esac @@ -579,8 +579,9 @@ EOF else IBM_ARCH=powerpc fi - if [ -x /usr/bin/oslevel ] ; then - IBM_REV=`/usr/bin/oslevel` + if [ -x /usr/bin/lslpp ] ; then + IBM_REV=`/usr/bin/lslpp -Lqc bos.rte.libc | + awk -F: '{ print $3 }' | sed s/[0-9]*$/0/` else IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} fi @@ -826,7 +827,7 @@ EOF *:MINGW*:*) echo ${UNAME_MACHINE}-pc-mingw32 exit ;; - i*:MSYS*:*) + *:MSYS*:*) echo ${UNAME_MACHINE}-pc-msys exit ;; i*:windows32*:*) @@ -969,10 +970,10 @@ EOF eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^CPU'` test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; } ;; - or1k:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-${LIBC} + openrisc*:Linux:*:*) + echo or1k-unknown-linux-${LIBC} exit ;; - or32:Linux:*:*) + or32:Linux:*:* | or1k*:Linux:*:*) echo ${UNAME_MACHINE}-unknown-linux-${LIBC} exit ;; padre:Linux:*:*) @@ -1371,154 +1372,6 @@ EOF exit ;; esac -eval $set_cc_for_build -cat >$dummy.c <<EOF -#ifdef _SEQUENT_ -# include <sys/types.h> -# include <sys/utsname.h> -#endif -main () -{ -#if defined (sony) -#if defined (MIPSEB) - /* BFD wants "bsd" instead of "newsos". Perhaps BFD should be changed, - I don't know.... */ - printf ("mips-sony-bsd\n"); exit (0); -#else -#include <sys/param.h> - printf ("m68k-sony-newsos%s\n", -#ifdef NEWSOS4 - "4" -#else - "" -#endif - ); exit (0); -#endif -#endif - -#if defined (__arm) && defined (__acorn) && defined (__unix) - printf ("arm-acorn-riscix\n"); exit (0); -#endif - -#if defined (hp300) && !defined (hpux) - printf ("m68k-hp-bsd\n"); exit (0); -#endif - -#if defined (NeXT) -#if !defined (__ARCHITECTURE__) -#define __ARCHITECTURE__ "m68k" -#endif - int version; - version=`(hostinfo | sed -n 's/.*NeXT Mach \([0-9]*\).*/\1/p') 2>/dev/null`; - if (version < 4) - printf ("%s-next-nextstep%d\n", __ARCHITECTURE__, version); - else - printf ("%s-next-openstep%d\n", __ARCHITECTURE__, version); - exit (0); -#endif - -#if defined (MULTIMAX) || defined (n16) -#if defined (UMAXV) - printf ("ns32k-encore-sysv\n"); exit (0); -#else -#if defined (CMU) - printf ("ns32k-encore-mach\n"); exit (0); -#else - printf ("ns32k-encore-bsd\n"); exit (0); -#endif -#endif -#endif - -#if defined (__386BSD__) - printf ("i386-pc-bsd\n"); exit (0); -#endif - -#if defined (sequent) -#if defined (i386) - printf ("i386-sequent-dynix\n"); exit (0); -#endif -#if defined (ns32000) - printf ("ns32k-sequent-dynix\n"); exit (0); -#endif -#endif - -#if defined (_SEQUENT_) - struct utsname un; - - uname(&un); - - if (strncmp(un.version, "V2", 2) == 0) { - printf ("i386-sequent-ptx2\n"); exit (0); - } - if (strncmp(un.version, "V1", 2) == 0) { /* XXX is V1 correct? */ - printf ("i386-sequent-ptx1\n"); exit (0); - } - printf ("i386-sequent-ptx\n"); exit (0); - -#endif - -#if defined (vax) -# if !defined (ultrix) -# include <sys/param.h> -# if defined (BSD) -# if BSD == 43 - printf ("vax-dec-bsd4.3\n"); exit (0); -# else -# if BSD == 199006 - printf ("vax-dec-bsd4.3reno\n"); exit (0); -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# endif -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# else - printf ("vax-dec-ultrix\n"); exit (0); -# endif -#endif - -#if defined (alliant) && defined (i860) - printf ("i860-alliant-bsd\n"); exit (0); -#endif - - exit (1); -} -EOF - -$CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null && SYSTEM_NAME=`$dummy` && - { echo "$SYSTEM_NAME"; exit; } - -# Apollos put the system type in the environment. - -test -d /usr/apollo && { echo ${ISP}-apollo-${SYSTYPE}; exit; } - -# Convex versions that predate uname can use getsysinfo(1) - -if [ -x /usr/convex/getsysinfo ] -then - case `getsysinfo -f cpu_type` in - c1*) - echo c1-convex-bsd - exit ;; - c2*) - if getsysinfo -f scalar_acc - then echo c32-convex-bsd - else echo c2-convex-bsd - fi - exit ;; - c34*) - echo c34-convex-bsd - exit ;; - c38*) - echo c38-convex-bsd - exit ;; - c4*) - echo c4-convex-bsd - exit ;; - esac -fi - cat >&2 <<EOF $0: unable to guess system type diff --git a/extension/build-aux/config.sub b/extension/build-aux/config.sub index 092cff00..7ffe3737 100755 --- a/extension/build-aux/config.sub +++ b/extension/build-aux/config.sub @@ -2,7 +2,7 @@ # Configuration validation subroutine script. # Copyright 1992-2014 Free Software Foundation, Inc. -timestamp='2014-01-01' +timestamp='2014-12-03' # This file is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by @@ -25,7 +25,7 @@ timestamp='2014-01-01' # of the GNU General Public License, version 3 ("GPLv3"). -# Please send patches with a ChangeLog entry to config-patches@gnu.org. +# Please send patches to <config-patches@gnu.org>. # # Configuration subroutine to validate and canonicalize a configuration type. # Supply the specified configuration type as an argument. @@ -283,8 +283,10 @@ case $basic_machine in | mips64vr5900 | mips64vr5900el \ | mipsisa32 | mipsisa32el \ | mipsisa32r2 | mipsisa32r2el \ + | mipsisa32r6 | mipsisa32r6el \ | mipsisa64 | mipsisa64el \ | mipsisa64r2 | mipsisa64r2el \ + | mipsisa64r6 | mipsisa64r6el \ | mipsisa64sb1 | mipsisa64sb1el \ | mipsisa64sr71k | mipsisa64sr71kel \ | mipsr5900 | mipsr5900el \ @@ -296,11 +298,11 @@ case $basic_machine in | nds32 | nds32le | nds32be \ | nios | nios2 | nios2eb | nios2el \ | ns16k | ns32k \ - | open8 \ - | or1k | or32 \ + | open8 | or1k | or1knd | or32 \ | pdp10 | pdp11 | pj | pjl \ | powerpc | powerpc64 | powerpc64le | powerpcle \ | pyramid \ + | riscv32 | riscv64 \ | rl78 | rx \ | score \ | sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \ @@ -311,6 +313,7 @@ case $basic_machine in | tahoe | tic4x | tic54x | tic55x | tic6x | tic80 | tron \ | ubicom32 \ | v850 | v850e | v850e1 | v850e2 | v850es | v850e2v3 \ + | visium \ | we32k \ | x86 | xc16x | xstormy16 | xtensa \ | z8k | z80) @@ -325,6 +328,9 @@ case $basic_machine in c6x) basic_machine=tic6x-unknown ;; + leon|leon[3-9]) + basic_machine=sparc-$basic_machine + ;; m6811 | m68hc11 | m6812 | m68hc12 | m68hcs12x | nvptx | picochip) basic_machine=$basic_machine-unknown os=-none @@ -402,8 +408,10 @@ case $basic_machine in | mips64vr5900-* | mips64vr5900el-* \ | mipsisa32-* | mipsisa32el-* \ | mipsisa32r2-* | mipsisa32r2el-* \ + | mipsisa32r6-* | mipsisa32r6el-* \ | mipsisa64-* | mipsisa64el-* \ | mipsisa64r2-* | mipsisa64r2el-* \ + | mipsisa64r6-* | mipsisa64r6el-* \ | mipsisa64sb1-* | mipsisa64sb1el-* \ | mipsisa64sr71k-* | mipsisa64sr71kel-* \ | mipsr5900-* | mipsr5900el-* \ @@ -415,6 +423,7 @@ case $basic_machine in | nios-* | nios2-* | nios2eb-* | nios2el-* \ | none-* | np1-* | ns16k-* | ns32k-* \ | open8-* \ + | or1k*-* \ | orion-* \ | pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \ | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* \ @@ -432,6 +441,7 @@ case $basic_machine in | ubicom32-* \ | v850-* | v850e-* | v850e1-* | v850es-* | v850e2-* | v850e2v3-* \ | vax-* \ + | visium-* \ | we32k-* \ | x86-* | x86_64-* | xc16x-* | xps100-* \ | xstormy16-* | xtensa*-* \ @@ -769,6 +779,9 @@ case $basic_machine in basic_machine=m68k-isi os=-sysv ;; + leon-*|leon[3-9]-*) + basic_machine=sparc-`echo $basic_machine | sed 's/-.*//'` + ;; m68knommu) basic_machine=m68k-unknown os=-linux @@ -824,6 +837,10 @@ case $basic_machine in basic_machine=powerpc-unknown os=-morphos ;; + moxiebox) + basic_machine=moxie-unknown + os=-moxiebox + ;; msdos) basic_machine=i386-pc os=-msdos @@ -1369,14 +1386,14 @@ case $os in | -cygwin* | -msys* | -pe* | -psos* | -moss* | -proelf* | -rtems* \ | -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \ | -linux-newlib* | -linux-musl* | -linux-uclibc* \ - | -uxpv* | -beos* | -mpeix* | -udk* \ + | -uxpv* | -beos* | -mpeix* | -udk* | -moxiebox* \ | -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \ | -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \ | -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \ | -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \ | -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \ | -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \ - | -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es*) + | -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* | -tirtos*) # Remember, each alternative MUST END IN *, to match a version number. ;; -qnx*) @@ -1594,9 +1611,6 @@ case $basic_machine in mips*-*) os=-elf ;; - or1k-*) - os=-elf - ;; or32-*) os=-coff ;; diff --git a/extension/build-aux/depcomp b/extension/build-aux/depcomp index 31788017..fc98710e 100755 --- a/extension/build-aux/depcomp +++ b/extension/build-aux/depcomp @@ -3,7 +3,7 @@ scriptversion=2013-05-30.07; # UTC -# Copyright (C) 1999-2013 Free Software Foundation, Inc. +# Copyright (C) 1999-2014 Free Software Foundation, Inc. # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -251,6 +251,41 @@ hp) exit 1 ;; +sgi) + if test "$libtool" = yes; then + "$@" "-Wp,-MDupdate,$tmpdepfile" + else + "$@" -MDupdate "$tmpdepfile" + fi + stat=$? + if test $stat -ne 0; then + rm -f "$tmpdepfile" + exit $stat + fi + rm -f "$depfile" + + if test -f "$tmpdepfile"; then # yes, the sourcefile depend on other files + echo "$object : \\" > "$depfile" + # Clip off the initial element (the dependent). Don't try to be + # clever and replace this with sed code, as IRIX sed won't handle + # lines with more than a fixed number of characters (4096 in + # IRIX 6.2 sed, 8192 in IRIX 6.5). We also remove comment lines; + # the IRIX cc adds comments like '#:fec' to the end of the + # dependency line. + tr ' ' "$nl" < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' \ + | tr "$nl" ' ' >> "$depfile" + echo >> "$depfile" + # The second pass generates a dummy entry for each header file. + tr ' ' "$nl" < "$tmpdepfile" \ + | sed -e 's/^.*\.o://' -e 's/#.*$//' -e '/^$/ d' -e 's/$/:/' \ + >> "$depfile" + else + make_dummy_depfile + fi + rm -f "$tmpdepfile" + ;; + xlc) # This case exists only to let depend.m4 do its work. It works by # looking at the text of this script. This case will never be run, diff --git a/extension/build-aux/install-sh b/extension/build-aux/install-sh index 04367377..0b0fdcbb 100755 --- a/extension/build-aux/install-sh +++ b/extension/build-aux/install-sh @@ -1,7 +1,7 @@ #!/bin/sh # install - install a program, script, or datafile -scriptversion=2013-10-30.23; # UTC +scriptversion=2013-12-25.23; # UTC # This originates from X11R5 (mit/util/scripts/install.sh), which was # later released in X11R6 (xc/config/util/install.sh) with the @@ -82,7 +82,7 @@ dir_arg= dst_arg= copy_on_change=false -no_target_directory= +is_target_a_directory=possibly usage="\ Usage: $0 [OPTION]... [-T] SRCFILE DSTFILE @@ -139,14 +139,16 @@ while test $# -ne 0; do -s) stripcmd=$stripprog;; - -t) dst_arg=$2 + -t) + is_target_a_directory=always + dst_arg=$2 # Protect names problematic for 'test' and other utilities. case $dst_arg in -* | [=\(\)!]) dst_arg=./$dst_arg;; esac shift;; - -T) no_target_directory=true;; + -T) is_target_a_directory=never;; --version) echo "$0 $scriptversion"; exit $?;; @@ -161,6 +163,16 @@ while test $# -ne 0; do shift done +# We allow the use of options -d and -T together, by making -d +# take the precedence; this is for compatibility with GNU install. + +if test -n "$dir_arg"; then + if test -n "$dst_arg"; then + echo "$0: target directory not allowed when installing a directory." >&2 + exit 1 + fi +fi + if test $# -ne 0 && test -z "$dir_arg$dst_arg"; then # When -d is used, all remaining arguments are directories to create. # When -t is used, the destination is already specified. @@ -192,6 +204,15 @@ if test $# -eq 0; then fi if test -z "$dir_arg"; then + if test $# -gt 1 || test "$is_target_a_directory" = always; then + if test ! -d "$dst_arg"; then + echo "$0: $dst_arg: Is not a directory." >&2 + exit 1 + fi + fi +fi + +if test -z "$dir_arg"; then do_exit='(exit $ret); exit $ret' trap "ret=129; $do_exit" 1 trap "ret=130; $do_exit" 2 @@ -253,7 +274,7 @@ do # If destination is a directory, append the input filename; won't work # if double slashes aren't ignored. if test -d "$dst"; then - if test -n "$no_target_directory"; then + if test "$is_target_a_directory" = never; then echo "$0: $dst_arg: Is a directory" >&2 exit 1 fi diff --git a/extension/build-aux/ltmain.sh b/extension/build-aux/ltmain.sh index 555b7637..b8915268 100644 --- a/extension/build-aux/ltmain.sh +++ b/extension/build-aux/ltmain.sh @@ -2,11 +2,11 @@ ## DO NOT EDIT - This file generated from ./build-aux/ltmain.in ## by inline-source v2014-01-03.01 -# libtool (GNU libtool) 2.4.3 +# libtool (GNU libtool) 2.4.5 # Provide generalized library-building support services. # Written by Gordon Matzigkeit <gord@gnu.ai.mit.edu>, 1996 -# Copyright (C) 1996-2014 Free Software Foundation, Inc. +# Copyright (C) 1996-2015 Free Software Foundation, Inc. # This is free software; see the source for copying conditions. There is NO # warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. @@ -31,8 +31,8 @@ PROGRAM=libtool PACKAGE=libtool -VERSION=2.4.3 -package_revision=2.4.3 +VERSION=2.4.5 +package_revision=2.4.5 ## ------ ## @@ -69,7 +69,7 @@ scriptversion=2014-01-03.01; # UTC # General shell script boiler plate, and helper functions. # Written by Gary V. Vaughan, 2004 -# Copyright (C) 2004-2014 Free Software Foundation, Inc. +# Copyright (C) 2004-2015 Free Software Foundation, Inc. # This is free software; see the source for copying conditions. There is NO # warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. @@ -1375,7 +1375,7 @@ scriptversion=2014-01-07.03; # UTC # A portable, pluggable option parser for Bourne shell. # Written by Gary V. Vaughan, 2010 -# Copyright (C) 2010-2014 Free Software Foundation, Inc. +# Copyright (C) 2010-2015 Free Software Foundation, Inc. # This is free software; see the source for copying conditions. There is NO # warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. @@ -1977,7 +1977,7 @@ func_version () # End: # Set a version string. -scriptversion='(GNU libtool) 2.4.3' +scriptversion='(GNU libtool) 2.4.5' # func_echo ARG... @@ -2063,7 +2063,7 @@ include the following information: compiler: $LTCC compiler flags: $LTCFLAGS linker: $LD (gnu? $with_gnu_ld) - version: $progname (GNU libtool) 2.4.3 + version: $progname (GNU libtool) 2.4.5 automake: `($AUTOMAKE --version) 2>/dev/null |$SED 1q` autoconf: `($AUTOCONF --version) 2>/dev/null |$SED 1q` @@ -2411,7 +2411,7 @@ libtool_validate_options () case $host in # Solaris2 added to fix http://debbugs.gnu.org/cgi/bugreport.cgi?bug=16452 # see also: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59788 - *cygwin* | *mingw* | *pw32* | *cegcc* | *solaris2*) + *cygwin* | *mingw* | *pw32* | *cegcc* | *solaris2* | *os2*) # don't eliminate duplications in $postdeps and $predeps opt_duplicate_compiler_generated_deps=: ;; @@ -3730,7 +3730,8 @@ The following components of LINK-COMMAND are treated specially: -no-install link a not-installable executable -no-undefined declare that a library does not refer to external symbols -o OUTPUT-FILE create OUTPUT-FILE from the specified objects - -objectlist FILE Use a list of object files found in FILE to specify objects + -objectlist FILE use a list of object files found in FILE to specify objects + -os2dllname NAME force a short DLL name on OS/2 (no effect on other OSes) -precious-files-regex REGEX don't remove output files matching REGEX -release RELEASE specify package release information @@ -4312,6 +4313,13 @@ func_mode_install () ;; esac ;; + os2*) + case $realname in + *_dll.a) + tstripme= + ;; + esac + ;; esac if test -n "$tstripme" && test -n "$striplib"; then func_show_eval "$striplib $destdir/$realname" 'exit $?' @@ -5153,7 +5161,7 @@ func_extract_archives () $RM "unfat-$$/$darwin_base_archive-$darwin_arch/$darwin_base_archive" done # $darwin_arches ## Okay now we've a bunch of thin objects, gotta fatten them up :) - darwin_filelist=`find unfat-$$ -type f -name \*.o -print -o -name \*.lo -print | $SED -e "$basename" | sort -u` + darwin_filelist=`find unfat-$$ -type f -name \*.o -print -o -name \*.lo -print | $SED -e "$sed_basename" | sort -u` darwin_file= darwin_files= for darwin_file in $darwin_filelist; do @@ -6453,6 +6461,24 @@ func_win32_import_lib_p () esac } +# func_suncc_cstd_abi +# !!ONLY CALL THIS FOR SUN CC AFTER $compile_command IS FULLY EXPANDED!! +# Several compiler flags select an ABI that is incompatible with the +# Cstd library. Avoid specifying it if any are in CXXFLAGS. +func_suncc_cstd_abi () +{ + $debug_cmd + + case " $compile_command " in + *" -compat=g "*|*\ -std=c++[0-9][0-9]\ *|*" -library=stdcxx4 "*|*" -library=stlport4 "*) + suncc_use_cstd_abi=no + ;; + *) + suncc_use_cstd_abi=yes + ;; + esac +} + # func_mode_link arg... func_mode_link () { @@ -6511,6 +6537,7 @@ func_mode_link () module=no no_install=no objs= + os2dllname= non_pic_objects= precious_files_regex= prefer_static_libs=no @@ -6768,6 +6795,11 @@ func_mode_link () prev= continue ;; + os2dllname) + os2dllname=$arg + prev= + continue + ;; precious_regex) precious_files_regex=$arg prev= @@ -7077,6 +7109,11 @@ func_mode_link () continue ;; + -os2dllname) + prev=os2dllname + continue + ;; + -o) prev=output ;; -precious-files-regex) @@ -7240,6 +7277,25 @@ func_mode_link () continue ;; + -Z*) + if test os2 = "`expr $host : '.*\(os2\)'`"; then + # OS/2 uses -Zxxx to specify OS/2-specific options + compiler_flags="$compiler_flags $arg" + func_append compile_command " $arg" + func_append finalize_command " $arg" + case $arg in + -Zlinker | -Zstack) + prev=xcompiler + ;; + esac + continue + else + # Otherwise treat like 'Some other compiler flag' below + func_quote_for_eval "$arg" + arg=$func_quote_for_eval_result + fi + ;; + # Some other compiler flag. -* | +*) func_quote_for_eval "$arg" @@ -7399,6 +7455,9 @@ func_mode_link () eval sys_lib_search_path=\"$sys_lib_search_path_spec\" eval sys_lib_dlsearch_path=\"$sys_lib_dlsearch_path_spec\" + # Definition is injected by LT_CONFIG during libtool generation. + func_munge_path_list sys_lib_dlsearch_path "$LT_SYS_LIBRARY_PATH" + func_dirname "$output" "/" "" output_objdir=$func_dirname_result$objdir func_to_tool_file "$output_objdir/" @@ -8066,7 +8125,7 @@ func_mode_link () if test -n "$library_names" && { test no = "$use_static_libs" || test -z "$old_library"; }; then case $host in - *cygwin* | *mingw* | *cegcc*) + *cygwin* | *mingw* | *cegcc* | *os2*) # No point in relinking DLLs because paths are not encoded func_append notinst_deplibs " $lib" need_relink=no @@ -8136,7 +8195,7 @@ func_mode_link () elif test -n "$soname_spec"; then # bleh windows case $host in - *cygwin* | mingw* | *cegcc*) + *cygwin* | mingw* | *cegcc* | *os2*) func_arith $current - $age major=$func_arith_result versuffix=-$major @@ -8561,6 +8620,37 @@ func_mode_link () eval $var=\"$tmp_libs\" done # for var fi + + # Add Sun CC postdeps if required: + test CXX = "$tagname" && { + case $host_os in + linux*) + case `$CC -V 2>&1 | sed 5q` in + *Sun\ C*) # Sun C++ 5.9 + func_suncc_cstd_abi + + if test no != "$suncc_use_cstd_abi"; then + func_append postdeps ' -library=Cstd -library=Crun' + fi + ;; + esac + ;; + + solaris*) + func_cc_basename "$CC" + case $func_cc_basename_result in + CC* | sunCC*) + func_suncc_cstd_abi + + if test no != "$suncc_use_cstd_abi"; then + func_append postdeps ' -library=Cstd -library=Crun' + fi + ;; + esac + ;; + esac + } + # Last step: remove runtime libs from dependency_libs # (they stay in deplibs) tmp_libs= @@ -8708,13 +8798,13 @@ func_mode_link () # case $version_type in # correct linux to gnu/linux during the next big refactor - darwin|linux|osf|windows|none) + darwin|freebsd-elf|linux|osf|windows|none) func_arith $number_major + $number_minor current=$func_arith_result age=$number_minor revision=$number_revision ;; - freebsd-aout|freebsd-elf|qnx|sunos) + freebsd-aout|qnx|sunos) current=$number_major revision=$number_minor age=0 @@ -8800,8 +8890,9 @@ func_mode_link () ;; freebsd-elf) - major=.$current - versuffix=.$current + func_arith $current - $age + major=.$func_arith_result + versuffix=$major.$age.$revision ;; irix | nonstopux) @@ -8864,6 +8955,11 @@ func_mode_link () versuffix=.$current ;; + sco) + major=.$current + versuffix=.$current + ;; + sunos) major=.$current versuffix=.$current.$revision diff --git a/extension/build-aux/missing b/extension/build-aux/missing index cdea5149..f62bbae3 100755 --- a/extension/build-aux/missing +++ b/extension/build-aux/missing @@ -1,9 +1,9 @@ #! /bin/sh # Common wrapper for a few potentially missing GNU programs. -scriptversion=2012-06-26.16; # UTC +scriptversion=2013-10-28.13; # UTC -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # Originally written by Fran,cois Pinard <pinard@iro.umontreal.ca>, 1996. # This program is free software; you can redistribute it and/or modify @@ -160,7 +160,7 @@ give_advice () ;; autom4te*) echo "You might have modified some maintainer files that require" - echo "the 'automa4te' program to be rebuilt." + echo "the 'autom4te' program to be rebuilt." program_details 'autom4te' ;; bison*|yacc*) diff --git a/extension/configh.in b/extension/configh.in index 5842f2f4..d3f7361e 100644 --- a/extension/configh.in +++ b/extension/configh.in @@ -10,22 +10,6 @@ #endif -/* Define to 1 if translation of program messages to the user's native - language is requested. */ -#undef ENABLE_NLS - -/* Define to 1 if you have the MacOS X function CFLocaleCopyCurrent in the - CoreFoundation framework. */ -#undef HAVE_CFLOCALECOPYCURRENT - -/* Define to 1 if you have the MacOS X function CFPreferencesCopyAppValue in - the CoreFoundation framework. */ -#undef HAVE_CFPREFERENCESCOPYAPPVALUE - -/* Define if the GNU dcgettext() function is already present or preinstalled. - */ -#undef HAVE_DCGETTEXT - /* Define to 1 if you have the declaration of `dirfd', and to 0 if you don't. */ #undef HAVE_DECL_DIRFD @@ -55,15 +39,9 @@ /* Define to 1 if you have the `GetSystemTimeAsFileTime' function. */ #undef HAVE_GETSYSTEMTIMEASFILETIME -/* Define if the GNU gettext() function is already present or preinstalled. */ -#undef HAVE_GETTEXT - /* Define to 1 if you have the `gettimeofday' function. */ #undef HAVE_GETTIMEOFDAY -/* Define if you have the iconv() function and it works. */ -#undef HAVE_ICONV - /* Define to 1 if you have the <inttypes.h> header file. */ #undef HAVE_INTTYPES_H diff --git a/extension/configure b/extension/configure index 7ee9c0df..6818958b 100755 --- a/extension/configure +++ b/extension/configure @@ -631,12 +631,12 @@ ac_includes_default="\ # include <unistd.h> #endif" -gt_needs= ac_subst_vars='am__EXEEXT_FALSE am__EXEEXT_TRUE LTLIBOBJS LIBOBJS pkgextensiondir +LT_SYS_LIBRARY_PATH OTOOL64 OTOOL LIPO @@ -653,16 +653,6 @@ DUMPBIN LD FGREP SED -LIBTOOL -ac_ct_AR -AR -POSUB -LTLIBINTL -LIBINTL -INTLLIBS -LTLIBICONV -LIBICONV -INTL_MACOSX_LIBS host_os host_vendor host_cpu @@ -671,16 +661,9 @@ build_os build_vendor build_cpu build -XGETTEXT_EXTRA_OPTIONS -MSGMERGE -XGETTEXT_015 -XGETTEXT -GMSGFMT_015 -MSGFMT_015 -GMSGFMT -MSGFMT -GETTEXT_MACRO_VERSION -USE_NLS +LIBTOOL +ac_ct_AR +AR AM_BACKSLASH AM_DEFAULT_VERBOSITY AM_DEFAULT_V @@ -771,16 +754,13 @@ ac_user_opts=' enable_option_checking enable_dependency_tracking enable_silent_rules -enable_nls -with_gnu_ld -enable_rpath -with_libiconv_prefix -with_libintl_prefix enable_largefile enable_static enable_shared with_pic enable_fast_install +with_aix_soname +with_gnu_ld with_sysroot enable_libtool_lock ' @@ -792,7 +772,8 @@ CFLAGS LDFLAGS LIBS CPPFLAGS -CPP' +CPP +LT_SYS_LIBRARY_PATH' # Initialize some variables set by options. @@ -1417,8 +1398,6 @@ Optional Features: speeds up one-time build --enable-silent-rules less verbose build output (undo: "make V=1") --disable-silent-rules verbose build output (undo: "make V=0") - --disable-nls do not use Native Language Support - --disable-rpath do not hardcode runtime library paths --disable-largefile omit support for large files --enable-static[=PKGS] build static libraries [default=no] --enable-shared[=PKGS] build shared libraries [default=yes] @@ -1429,13 +1408,11 @@ Optional Features: Optional Packages: --with-PACKAGE[=ARG] use PACKAGE [ARG=yes] --without-PACKAGE do not use PACKAGE (same as --with-PACKAGE=no) - --with-gnu-ld assume the C compiler uses GNU ld default=no - --with-libiconv-prefix[=DIR] search for libiconv in DIR/include and DIR/lib - --without-libiconv-prefix don't search for libiconv in includedir and libdir - --with-libintl-prefix[=DIR] search for libintl in DIR/include and DIR/lib - --without-libintl-prefix don't search for libintl in includedir and libdir --with-pic[=PKGS] try to use only PIC/non-PIC objects [default=use both] + --with-aix-soname=aix|svr4|both + shared library versioning (aka "SONAME") variant to + provide on AIX, [default=aix]. --with-gnu-ld assume the C compiler uses GNU ld [default=no] --with-sysroot[=DIR] Search for dependent libraries within DIR (or the compiler's sysroot if not specified). @@ -1449,6 +1426,8 @@ Some influential environment variables: CPPFLAGS (Objective) C/C++ preprocessor flags, e.g. -I<include dir> if you have headers in a nonstandard directory <include dir> CPP C preprocessor + LT_SYS_LIBRARY_PATH + User-defined run-time library search path. Use these variables to override the choices made by `configure' or to help it to find libraries and programs with nonstandard names/locations. @@ -1771,52 +1750,6 @@ $as_echo "$ac_res" >&6; } } # ac_fn_c_check_header_compile -# ac_fn_c_try_link LINENO -# ----------------------- -# Try to link conftest.$ac_ext, and return whether this succeeded. -ac_fn_c_try_link () -{ - as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack - rm -f conftest.$ac_objext conftest$ac_exeext - if { { ac_try="$ac_link" -case "(($ac_try" in - *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; - *) ac_try_echo=$ac_try;; -esac -eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" -$as_echo "$ac_try_echo"; } >&5 - (eval "$ac_link") 2>conftest.err - ac_status=$? - if test -s conftest.err; then - grep -v '^ *+' conftest.err >conftest.er1 - cat conftest.er1 >&5 - mv -f conftest.er1 conftest.err - fi - $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 - test $ac_status = 0; } && { - test -z "$ac_c_werror_flag" || - test ! -s conftest.err - } && test -s conftest$ac_exeext && { - test "$cross_compiling" = yes || - test -x conftest$ac_exeext - }; then : - ac_retval=0 -else - $as_echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - ac_retval=1 -fi - # Delete the IPA/IPO (Inter Procedural Analysis/Optimization) information - # created by the PGI compiler (conftest_ipa8_conftest.oo), as it would - # interfere with the next link command; also delete a directory that is - # left behind by Apple's compiler. We do this before executing the actions. - rm -rf conftest.dSYM conftest_ipa8_conftest.oo - eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno - as_fn_set_status $ac_retval - -} # ac_fn_c_try_link - # ac_fn_c_check_member LINENO AGGR MEMBER VAR INCLUDES # ---------------------------------------------------- # Tries to find if the field MEMBER exists in type AGGR, after including @@ -1874,6 +1807,52 @@ $as_echo "$ac_res" >&6; } } # ac_fn_c_check_member +# ac_fn_c_try_link LINENO +# ----------------------- +# Try to link conftest.$ac_ext, and return whether this succeeded. +ac_fn_c_try_link () +{ + as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack + rm -f conftest.$ac_objext conftest$ac_exeext + if { { ac_try="$ac_link" +case "(($ac_try" in + *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;; + *) ac_try_echo=$ac_try;; +esac +eval ac_try_echo="\"\$as_me:${as_lineno-$LINENO}: $ac_try_echo\"" +$as_echo "$ac_try_echo"; } >&5 + (eval "$ac_link") 2>conftest.err + ac_status=$? + if test -s conftest.err; then + grep -v '^ *+' conftest.err >conftest.er1 + cat conftest.er1 >&5 + mv -f conftest.er1 conftest.err + fi + $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5 + test $ac_status = 0; } && { + test -z "$ac_c_werror_flag" || + test ! -s conftest.err + } && test -s conftest$ac_exeext && { + test "$cross_compiling" = yes || + test -x conftest$ac_exeext + }; then : + ac_retval=0 +else + $as_echo "$as_me: failed program was:" >&5 +sed 's/^/| /' conftest.$ac_ext >&5 + + ac_retval=1 +fi + # Delete the IPA/IPO (Inter Procedural Analysis/Optimization) information + # created by the PGI compiler (conftest_ipa8_conftest.oo), as it would + # interfere with the next link command; also delete a directory that is + # left behind by Apple's compiler. We do this before executing the actions. + rm -rf conftest.dSYM conftest_ipa8_conftest.oo + eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno + as_fn_set_status $ac_retval + +} # ac_fn_c_try_link + # ac_fn_c_check_func LINENO FUNC VAR # ---------------------------------- # Tests whether FUNC exists, setting the cache variable VAR accordingly @@ -2270,7 +2249,6 @@ $as_echo "$as_me: creating cache $cache_file" >&6;} >$cache_file fi -gt_needs="$gt_needs " # Check that the precious variables saved in the cache have kept the same # value. ac_cache_corrupted=false @@ -2371,8 +2349,8 @@ ac_configure="$SHELL $ac_aux_dir/configure" # Please don't use this var. -# expand $ac_aux_dir to an absolute path -am_aux_dir=`cd $ac_aux_dir && pwd` +# Expand $ac_aux_dir to an absolute path. +am_aux_dir=`cd "$ac_aux_dir" && pwd` ac_ext=c ac_cpp='$CPP $CPPFLAGS' @@ -3685,7 +3663,7 @@ $as_echo "$ac_cv_safe_to_define___extensions__" >&6; } INSTALL="$ac_aux_dir/install-sh -c" export INSTALL -am__api_version='1.14' +am__api_version='1.15' # Find a good install program. We prefer a C program (faster), # so one script is as good as another. But avoid the broken or @@ -3874,7 +3852,7 @@ else $as_echo "$as_me: WARNING: 'missing' script is too old or missing" >&2;} fi -if test x"${install_sh}" != xset; then +if test x"${install_sh+set}" != xset; then case $am_aux_dir in *\ * | *\ *) install_sh="\${SHELL} '$am_aux_dir/install-sh'" ;; @@ -4265,8 +4243,8 @@ MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"} # <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html> mkdir_p='$(MKDIR_P)' -# We need awk for the "check" target. The system "awk" is bad on -# some platforms. +# We need awk for the "check" target (and possibly the TAP driver). The +# system "awk" is bad on some platforms. # Always define AMTAR for backward compatibility. Yes, it's still used # in the wild :-( We should find a proper way to deprecate it ... AMTAR='$${TAR-tar}' @@ -4453,2097 +4431,6 @@ END fi - { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether NLS is requested" >&5 -$as_echo_n "checking whether NLS is requested... " >&6; } - # Check whether --enable-nls was given. -if test "${enable_nls+set}" = set; then : - enableval=$enable_nls; USE_NLS=$enableval -else - USE_NLS=yes -fi - - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $USE_NLS" >&5 -$as_echo "$USE_NLS" >&6; } - - - - - GETTEXT_MACRO_VERSION=0.18 - - - - -# Prepare PATH_SEPARATOR. -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi - -# Find out how to test for executable files. Don't use a zero-byte file, -# as systems may use methods other than mode bits to determine executability. -cat >conf$$.file <<_ASEOF -#! /bin/sh -exit 0 -_ASEOF -chmod +x conf$$.file -if test -x conf$$.file >/dev/null 2>&1; then - ac_executable_p="test -x" -else - ac_executable_p="test -f" -fi -rm -f conf$$.file - -# Extract the first word of "msgfmt", so it can be a program name with args. -set dummy msgfmt; ac_word=$2 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 -$as_echo_n "checking for $ac_word... " >&6; } -if ${ac_cv_path_MSGFMT+:} false; then : - $as_echo_n "(cached) " >&6 -else - case "$MSGFMT" in - [\\/]* | ?:[\\/]*) - ac_cv_path_MSGFMT="$MSGFMT" # Let the user override the test with a path. - ;; - *) - ac_save_IFS="$IFS"; IFS=$PATH_SEPARATOR - for ac_dir in $PATH; do - IFS="$ac_save_IFS" - test -z "$ac_dir" && ac_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $ac_executable_p "$ac_dir/$ac_word$ac_exec_ext"; then - echo "$as_me: trying $ac_dir/$ac_word..." >&5 - if $ac_dir/$ac_word --statistics /dev/null >&5 2>&1 && - (if $ac_dir/$ac_word --statistics /dev/null 2>&1 >/dev/null | grep usage >/dev/null; then exit 1; else exit 0; fi); then - ac_cv_path_MSGFMT="$ac_dir/$ac_word$ac_exec_ext" - break 2 - fi - fi - done - done - IFS="$ac_save_IFS" - test -z "$ac_cv_path_MSGFMT" && ac_cv_path_MSGFMT=":" - ;; -esac -fi -MSGFMT="$ac_cv_path_MSGFMT" -if test "$MSGFMT" != ":"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MSGFMT" >&5 -$as_echo "$MSGFMT" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi - - # Extract the first word of "gmsgfmt", so it can be a program name with args. -set dummy gmsgfmt; ac_word=$2 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 -$as_echo_n "checking for $ac_word... " >&6; } -if ${ac_cv_path_GMSGFMT+:} false; then : - $as_echo_n "(cached) " >&6 -else - case $GMSGFMT in - [\\/]* | ?:[\\/]*) - ac_cv_path_GMSGFMT="$GMSGFMT" # Let the user override the test with a path. - ;; - *) - as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_path_GMSGFMT="$as_dir/$ac_word$ac_exec_ext" - $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done - done -IFS=$as_save_IFS - - test -z "$ac_cv_path_GMSGFMT" && ac_cv_path_GMSGFMT="$MSGFMT" - ;; -esac -fi -GMSGFMT=$ac_cv_path_GMSGFMT -if test -n "$GMSGFMT"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $GMSGFMT" >&5 -$as_echo "$GMSGFMT" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi - - - - case `$MSGFMT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) MSGFMT_015=: ;; - *) MSGFMT_015=$MSGFMT ;; - esac - - case `$GMSGFMT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) GMSGFMT_015=: ;; - *) GMSGFMT_015=$GMSGFMT ;; - esac - - - -# Prepare PATH_SEPARATOR. -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi - -# Find out how to test for executable files. Don't use a zero-byte file, -# as systems may use methods other than mode bits to determine executability. -cat >conf$$.file <<_ASEOF -#! /bin/sh -exit 0 -_ASEOF -chmod +x conf$$.file -if test -x conf$$.file >/dev/null 2>&1; then - ac_executable_p="test -x" -else - ac_executable_p="test -f" -fi -rm -f conf$$.file - -# Extract the first word of "xgettext", so it can be a program name with args. -set dummy xgettext; ac_word=$2 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 -$as_echo_n "checking for $ac_word... " >&6; } -if ${ac_cv_path_XGETTEXT+:} false; then : - $as_echo_n "(cached) " >&6 -else - case "$XGETTEXT" in - [\\/]* | ?:[\\/]*) - ac_cv_path_XGETTEXT="$XGETTEXT" # Let the user override the test with a path. - ;; - *) - ac_save_IFS="$IFS"; IFS=$PATH_SEPARATOR - for ac_dir in $PATH; do - IFS="$ac_save_IFS" - test -z "$ac_dir" && ac_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $ac_executable_p "$ac_dir/$ac_word$ac_exec_ext"; then - echo "$as_me: trying $ac_dir/$ac_word..." >&5 - if $ac_dir/$ac_word --omit-header --copyright-holder= --msgid-bugs-address= /dev/null >&5 2>&1 && - (if $ac_dir/$ac_word --omit-header --copyright-holder= --msgid-bugs-address= /dev/null 2>&1 >/dev/null | grep usage >/dev/null; then exit 1; else exit 0; fi); then - ac_cv_path_XGETTEXT="$ac_dir/$ac_word$ac_exec_ext" - break 2 - fi - fi - done - done - IFS="$ac_save_IFS" - test -z "$ac_cv_path_XGETTEXT" && ac_cv_path_XGETTEXT=":" - ;; -esac -fi -XGETTEXT="$ac_cv_path_XGETTEXT" -if test "$XGETTEXT" != ":"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $XGETTEXT" >&5 -$as_echo "$XGETTEXT" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi - - rm -f messages.po - - case `$XGETTEXT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) XGETTEXT_015=: ;; - *) XGETTEXT_015=$XGETTEXT ;; - esac - - - -# Prepare PATH_SEPARATOR. -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi - -# Find out how to test for executable files. Don't use a zero-byte file, -# as systems may use methods other than mode bits to determine executability. -cat >conf$$.file <<_ASEOF -#! /bin/sh -exit 0 -_ASEOF -chmod +x conf$$.file -if test -x conf$$.file >/dev/null 2>&1; then - ac_executable_p="test -x" -else - ac_executable_p="test -f" -fi -rm -f conf$$.file - -# Extract the first word of "msgmerge", so it can be a program name with args. -set dummy msgmerge; ac_word=$2 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5 -$as_echo_n "checking for $ac_word... " >&6; } -if ${ac_cv_path_MSGMERGE+:} false; then : - $as_echo_n "(cached) " >&6 -else - case "$MSGMERGE" in - [\\/]* | ?:[\\/]*) - ac_cv_path_MSGMERGE="$MSGMERGE" # Let the user override the test with a path. - ;; - *) - ac_save_IFS="$IFS"; IFS=$PATH_SEPARATOR - for ac_dir in $PATH; do - IFS="$ac_save_IFS" - test -z "$ac_dir" && ac_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $ac_executable_p "$ac_dir/$ac_word$ac_exec_ext"; then - echo "$as_me: trying $ac_dir/$ac_word..." >&5 - if $ac_dir/$ac_word --update -q /dev/null /dev/null >&5 2>&1; then - ac_cv_path_MSGMERGE="$ac_dir/$ac_word$ac_exec_ext" - break 2 - fi - fi - done - done - IFS="$ac_save_IFS" - test -z "$ac_cv_path_MSGMERGE" && ac_cv_path_MSGMERGE=":" - ;; -esac -fi -MSGMERGE="$ac_cv_path_MSGMERGE" -if test "$MSGMERGE" != ":"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $MSGMERGE" >&5 -$as_echo "$MSGMERGE" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi - - - test -n "$localedir" || localedir='${datadir}/locale' - - - test -n "${XGETTEXT_EXTRA_OPTIONS+set}" || XGETTEXT_EXTRA_OPTIONS= - - - ac_config_commands="$ac_config_commands po-directories" - - - - if test "X$prefix" = "XNONE"; then - acl_final_prefix="$ac_default_prefix" - else - acl_final_prefix="$prefix" - fi - if test "X$exec_prefix" = "XNONE"; then - acl_final_exec_prefix='${prefix}' - else - acl_final_exec_prefix="$exec_prefix" - fi - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - eval acl_final_exec_prefix=\"$acl_final_exec_prefix\" - prefix="$acl_save_prefix" - -# Make sure we can run config.sub. -$SHELL "$ac_aux_dir/config.sub" sun4 >/dev/null 2>&1 || - as_fn_error $? "cannot run $SHELL $ac_aux_dir/config.sub" "$LINENO" 5 - -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking build system type" >&5 -$as_echo_n "checking build system type... " >&6; } -if ${ac_cv_build+:} false; then : - $as_echo_n "(cached) " >&6 -else - ac_build_alias=$build_alias -test "x$ac_build_alias" = x && - ac_build_alias=`$SHELL "$ac_aux_dir/config.guess"` -test "x$ac_build_alias" = x && - as_fn_error $? "cannot guess build type; you must specify one" "$LINENO" 5 -ac_cv_build=`$SHELL "$ac_aux_dir/config.sub" $ac_build_alias` || - as_fn_error $? "$SHELL $ac_aux_dir/config.sub $ac_build_alias failed" "$LINENO" 5 - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_build" >&5 -$as_echo "$ac_cv_build" >&6; } -case $ac_cv_build in -*-*-*) ;; -*) as_fn_error $? "invalid value of canonical build" "$LINENO" 5;; -esac -build=$ac_cv_build -ac_save_IFS=$IFS; IFS='-' -set x $ac_cv_build -shift -build_cpu=$1 -build_vendor=$2 -shift; shift -# Remember, the first character of IFS is used to create $*, -# except with old shells: -build_os=$* -IFS=$ac_save_IFS -case $build_os in *\ *) build_os=`echo "$build_os" | sed 's/ /-/g'`;; esac - - -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking host system type" >&5 -$as_echo_n "checking host system type... " >&6; } -if ${ac_cv_host+:} false; then : - $as_echo_n "(cached) " >&6 -else - if test "x$host_alias" = x; then - ac_cv_host=$ac_cv_build -else - ac_cv_host=`$SHELL "$ac_aux_dir/config.sub" $host_alias` || - as_fn_error $? "$SHELL $ac_aux_dir/config.sub $host_alias failed" "$LINENO" 5 -fi - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_host" >&5 -$as_echo "$ac_cv_host" >&6; } -case $ac_cv_host in -*-*-*) ;; -*) as_fn_error $? "invalid value of canonical host" "$LINENO" 5;; -esac -host=$ac_cv_host -ac_save_IFS=$IFS; IFS='-' -set x $ac_cv_host -shift -host_cpu=$1 -host_vendor=$2 -shift; shift -# Remember, the first character of IFS is used to create $*, -# except with old shells: -host_os=$* -IFS=$ac_save_IFS -case $host_os in *\ *) host_os=`echo "$host_os" | sed 's/ /-/g'`;; esac - - - -# Check whether --with-gnu-ld was given. -if test "${with_gnu_ld+set}" = set; then : - withval=$with_gnu_ld; test "$withval" = no || with_gnu_ld=yes -else - with_gnu_ld=no -fi - -# Prepare PATH_SEPARATOR. -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi -ac_prog=ld -if test "$GCC" = yes; then - # Check if gcc -print-prog-name=ld gives a path. - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for ld used by GCC" >&5 -$as_echo_n "checking for ld used by GCC... " >&6; } - case $host in - *-*-mingw*) - # gcc leaves a trailing carriage return which upsets mingw - ac_prog=`($CC -print-prog-name=ld) 2>&5 | tr -d '\015'` ;; - *) - ac_prog=`($CC -print-prog-name=ld) 2>&5` ;; - esac - case $ac_prog in - # Accept absolute paths. - [\\/]* | [A-Za-z]:[\\/]*) - re_direlt='/[^/][^/]*/\.\./' - # Canonicalize the path of ld - ac_prog=`echo $ac_prog| sed 's%\\\\%/%g'` - while echo $ac_prog | grep "$re_direlt" > /dev/null 2>&1; do - ac_prog=`echo $ac_prog| sed "s%$re_direlt%/%"` - done - test -z "$LD" && LD="$ac_prog" - ;; - "") - # If it fails, then pretend we aren't using GCC. - ac_prog=ld - ;; - *) - # If it is relative, then search for the first ld in PATH. - with_gnu_ld=unknown - ;; - esac -elif test "$with_gnu_ld" = yes; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for GNU ld" >&5 -$as_echo_n "checking for GNU ld... " >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for non-GNU ld" >&5 -$as_echo_n "checking for non-GNU ld... " >&6; } -fi -if ${acl_cv_path_LD+:} false; then : - $as_echo_n "(cached) " >&6 -else - if test -z "$LD"; then - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR-:}" - for ac_dir in $PATH; do - test -z "$ac_dir" && ac_dir=. - if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then - acl_cv_path_LD="$ac_dir/$ac_prog" - # Check to see if the program is GNU ld. I'd rather use --version, - # but apparently some GNU ld's only accept -v. - # Break only if it was the GNU/non-GNU ld that we prefer. - case `"$acl_cv_path_LD" -v 2>&1 < /dev/null` in - *GNU* | *'with BFD'*) - test "$with_gnu_ld" != no && break ;; - *) - test "$with_gnu_ld" != yes && break ;; - esac - fi - done - IFS="$ac_save_ifs" -else - acl_cv_path_LD="$LD" # Let the user override the test with a path. -fi -fi - -LD="$acl_cv_path_LD" -if test -n "$LD"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LD" >&5 -$as_echo "$LD" >&6; } -else - { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5 -$as_echo "no" >&6; } -fi -test -z "$LD" && as_fn_error $? "no acceptable ld found in \$PATH" "$LINENO" 5 -{ $as_echo "$as_me:${as_lineno-$LINENO}: checking if the linker ($LD) is GNU ld" >&5 -$as_echo_n "checking if the linker ($LD) is GNU ld... " >&6; } -if ${acl_cv_prog_gnu_ld+:} false; then : - $as_echo_n "(cached) " >&6 -else - # I'd rather use --version here, but apparently some GNU ld's only accept -v. -case `$LD -v 2>&1 </dev/null` in -*GNU* | *'with BFD'*) - acl_cv_prog_gnu_ld=yes ;; -*) - acl_cv_prog_gnu_ld=no ;; -esac -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $acl_cv_prog_gnu_ld" >&5 -$as_echo "$acl_cv_prog_gnu_ld" >&6; } -with_gnu_ld=$acl_cv_prog_gnu_ld - - - - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for shared library run path origin" >&5 -$as_echo_n "checking for shared library run path origin... " >&6; } -if ${acl_cv_rpath+:} false; then : - $as_echo_n "(cached) " >&6 -else - - CC="$CC" GCC="$GCC" LDFLAGS="$LDFLAGS" LD="$LD" with_gnu_ld="$with_gnu_ld" \ - ${CONFIG_SHELL-/bin/sh} "$ac_aux_dir/config.rpath" "$host" > conftest.sh - . ./conftest.sh - rm -f ./conftest.sh - acl_cv_rpath=done - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $acl_cv_rpath" >&5 -$as_echo "$acl_cv_rpath" >&6; } - wl="$acl_cv_wl" - acl_libext="$acl_cv_libext" - acl_shlibext="$acl_cv_shlibext" - acl_libname_spec="$acl_cv_libname_spec" - acl_library_names_spec="$acl_cv_library_names_spec" - acl_hardcode_libdir_flag_spec="$acl_cv_hardcode_libdir_flag_spec" - acl_hardcode_libdir_separator="$acl_cv_hardcode_libdir_separator" - acl_hardcode_direct="$acl_cv_hardcode_direct" - acl_hardcode_minus_L="$acl_cv_hardcode_minus_L" - # Check whether --enable-rpath was given. -if test "${enable_rpath+set}" = set; then : - enableval=$enable_rpath; : -else - enable_rpath=yes -fi - - - - - acl_libdirstem=lib - acl_libdirstem2= - case "$host_os" in - solaris*) - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for 64-bit host" >&5 -$as_echo_n "checking for 64-bit host... " >&6; } -if ${gl_cv_solaris_64bit+:} false; then : - $as_echo_n "(cached) " >&6 -else - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ - -#ifdef _LP64 -sixtyfour bits -#endif - -_ACEOF -if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | - $EGREP "sixtyfour bits" >/dev/null 2>&1; then : - gl_cv_solaris_64bit=yes -else - gl_cv_solaris_64bit=no -fi -rm -f conftest* - - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $gl_cv_solaris_64bit" >&5 -$as_echo "$gl_cv_solaris_64bit" >&6; } - if test $gl_cv_solaris_64bit = yes; then - acl_libdirstem=lib/64 - case "$host_cpu" in - sparc*) acl_libdirstem2=lib/sparcv9 ;; - i*86 | x86_64) acl_libdirstem2=lib/amd64 ;; - esac - fi - ;; - *) - searchpath=`(LC_ALL=C $CC -print-search-dirs) 2>/dev/null | sed -n -e 's,^libraries: ,,p' | sed -e 's,^=,,'` - if test -n "$searchpath"; then - acl_save_IFS="${IFS= }"; IFS=":" - for searchdir in $searchpath; do - if test -d "$searchdir"; then - case "$searchdir" in - */lib64/ | */lib64 ) acl_libdirstem=lib64 ;; - */../ | */.. ) - # Better ignore directories of this form. They are misleading. - ;; - *) searchdir=`cd "$searchdir" && pwd` - case "$searchdir" in - */lib64 ) acl_libdirstem=lib64 ;; - esac ;; - esac - fi - done - IFS="$acl_save_IFS" - fi - ;; - esac - test -n "$acl_libdirstem2" || acl_libdirstem2="$acl_libdirstem" - - - - - - - - - - - - - use_additional=yes - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - - eval additional_includedir=\"$includedir\" - eval additional_libdir=\"$libdir\" - - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - -# Check whether --with-libiconv-prefix was given. -if test "${with_libiconv_prefix+set}" = set; then : - withval=$with_libiconv_prefix; - if test "X$withval" = "Xno"; then - use_additional=no - else - if test "X$withval" = "X"; then - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - - eval additional_includedir=\"$includedir\" - eval additional_libdir=\"$libdir\" - - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - else - additional_includedir="$withval/include" - additional_libdir="$withval/$acl_libdirstem" - if test "$acl_libdirstem2" != "$acl_libdirstem" \ - && ! test -d "$withval/$acl_libdirstem"; then - additional_libdir="$withval/$acl_libdirstem2" - fi - fi - fi - -fi - - LIBICONV= - LTLIBICONV= - INCICONV= - LIBICONV_PREFIX= - HAVE_LIBICONV= - rpathdirs= - ltrpathdirs= - names_already_handled= - names_next_round='iconv ' - while test -n "$names_next_round"; do - names_this_round="$names_next_round" - names_next_round= - for name in $names_this_round; do - already_handled= - for n in $names_already_handled; do - if test "$n" = "$name"; then - already_handled=yes - break - fi - done - if test -z "$already_handled"; then - names_already_handled="$names_already_handled $name" - uppername=`echo "$name" | sed -e 'y|abcdefghijklmnopqrstuvwxyz./-|ABCDEFGHIJKLMNOPQRSTUVWXYZ___|'` - eval value=\"\$HAVE_LIB$uppername\" - if test -n "$value"; then - if test "$value" = yes; then - eval value=\"\$LIB$uppername\" - test -z "$value" || LIBICONV="${LIBICONV}${LIBICONV:+ }$value" - eval value=\"\$LTLIB$uppername\" - test -z "$value" || LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }$value" - else - : - fi - else - found_dir= - found_la= - found_so= - found_a= - eval libname=\"$acl_libname_spec\" # typically: libname=lib$name - if test -n "$acl_shlibext"; then - shrext=".$acl_shlibext" # typically: shrext=.so - else - shrext= - fi - if test $use_additional = yes; then - dir="$additional_libdir" - if test -n "$acl_shlibext"; then - if test -f "$dir/$libname$shrext"; then - found_dir="$dir" - found_so="$dir/$libname$shrext" - else - if test "$acl_library_names_spec" = '$libname$shrext$versuffix'; then - ver=`(cd "$dir" && \ - for f in "$libname$shrext".*; do echo "$f"; done \ - | sed -e "s,^$libname$shrext\\\\.,," \ - | sort -t '.' -n -r -k1,1 -k2,2 -k3,3 -k4,4 -k5,5 \ - | sed 1q ) 2>/dev/null` - if test -n "$ver" && test -f "$dir/$libname$shrext.$ver"; then - found_dir="$dir" - found_so="$dir/$libname$shrext.$ver" - fi - else - eval library_names=\"$acl_library_names_spec\" - for f in $library_names; do - if test -f "$dir/$f"; then - found_dir="$dir" - found_so="$dir/$f" - break - fi - done - fi - fi - fi - if test "X$found_dir" = "X"; then - if test -f "$dir/$libname.$acl_libext"; then - found_dir="$dir" - found_a="$dir/$libname.$acl_libext" - fi - fi - if test "X$found_dir" != "X"; then - if test -f "$dir/$libname.la"; then - found_la="$dir/$libname.la" - fi - fi - fi - if test "X$found_dir" = "X"; then - for x in $LDFLAGS $LTLIBICONV; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - case "$x" in - -L*) - dir=`echo "X$x" | sed -e 's/^X-L//'` - if test -n "$acl_shlibext"; then - if test -f "$dir/$libname$shrext"; then - found_dir="$dir" - found_so="$dir/$libname$shrext" - else - if test "$acl_library_names_spec" = '$libname$shrext$versuffix'; then - ver=`(cd "$dir" && \ - for f in "$libname$shrext".*; do echo "$f"; done \ - | sed -e "s,^$libname$shrext\\\\.,," \ - | sort -t '.' -n -r -k1,1 -k2,2 -k3,3 -k4,4 -k5,5 \ - | sed 1q ) 2>/dev/null` - if test -n "$ver" && test -f "$dir/$libname$shrext.$ver"; then - found_dir="$dir" - found_so="$dir/$libname$shrext.$ver" - fi - else - eval library_names=\"$acl_library_names_spec\" - for f in $library_names; do - if test -f "$dir/$f"; then - found_dir="$dir" - found_so="$dir/$f" - break - fi - done - fi - fi - fi - if test "X$found_dir" = "X"; then - if test -f "$dir/$libname.$acl_libext"; then - found_dir="$dir" - found_a="$dir/$libname.$acl_libext" - fi - fi - if test "X$found_dir" != "X"; then - if test -f "$dir/$libname.la"; then - found_la="$dir/$libname.la" - fi - fi - ;; - esac - if test "X$found_dir" != "X"; then - break - fi - done - fi - if test "X$found_dir" != "X"; then - LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }-L$found_dir -l$name" - if test "X$found_so" != "X"; then - if test "$enable_rpath" = no \ - || test "X$found_dir" = "X/usr/$acl_libdirstem" \ - || test "X$found_dir" = "X/usr/$acl_libdirstem2"; then - LIBICONV="${LIBICONV}${LIBICONV:+ }$found_so" - else - haveit= - for x in $ltrpathdirs; do - if test "X$x" = "X$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - ltrpathdirs="$ltrpathdirs $found_dir" - fi - if test "$acl_hardcode_direct" = yes; then - LIBICONV="${LIBICONV}${LIBICONV:+ }$found_so" - else - if test -n "$acl_hardcode_libdir_flag_spec" && test "$acl_hardcode_minus_L" = no; then - LIBICONV="${LIBICONV}${LIBICONV:+ }$found_so" - haveit= - for x in $rpathdirs; do - if test "X$x" = "X$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - rpathdirs="$rpathdirs $found_dir" - fi - else - haveit= - for x in $LDFLAGS $LIBICONV; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - LIBICONV="${LIBICONV}${LIBICONV:+ }-L$found_dir" - fi - if test "$acl_hardcode_minus_L" != no; then - LIBICONV="${LIBICONV}${LIBICONV:+ }$found_so" - else - LIBICONV="${LIBICONV}${LIBICONV:+ }-l$name" - fi - fi - fi - fi - else - if test "X$found_a" != "X"; then - LIBICONV="${LIBICONV}${LIBICONV:+ }$found_a" - else - LIBICONV="${LIBICONV}${LIBICONV:+ }-L$found_dir -l$name" - fi - fi - additional_includedir= - case "$found_dir" in - */$acl_libdirstem | */$acl_libdirstem/) - basedir=`echo "X$found_dir" | sed -e 's,^X,,' -e "s,/$acl_libdirstem/"'*$,,'` - if test "$name" = 'iconv'; then - LIBICONV_PREFIX="$basedir" - fi - additional_includedir="$basedir/include" - ;; - */$acl_libdirstem2 | */$acl_libdirstem2/) - basedir=`echo "X$found_dir" | sed -e 's,^X,,' -e "s,/$acl_libdirstem2/"'*$,,'` - if test "$name" = 'iconv'; then - LIBICONV_PREFIX="$basedir" - fi - additional_includedir="$basedir/include" - ;; - esac - if test "X$additional_includedir" != "X"; then - if test "X$additional_includedir" != "X/usr/include"; then - haveit= - if test "X$additional_includedir" = "X/usr/local/include"; then - if test -n "$GCC"; then - case $host_os in - linux* | gnu* | k*bsd*-gnu) haveit=yes;; - esac - fi - fi - if test -z "$haveit"; then - for x in $CPPFLAGS $INCICONV; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-I$additional_includedir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_includedir"; then - INCICONV="${INCICONV}${INCICONV:+ }-I$additional_includedir" - fi - fi - fi - fi - fi - if test -n "$found_la"; then - save_libdir="$libdir" - case "$found_la" in - */* | *\\*) . "$found_la" ;; - *) . "./$found_la" ;; - esac - libdir="$save_libdir" - for dep in $dependency_libs; do - case "$dep" in - -L*) - additional_libdir=`echo "X$dep" | sed -e 's/^X-L//'` - if test "X$additional_libdir" != "X/usr/$acl_libdirstem" \ - && test "X$additional_libdir" != "X/usr/$acl_libdirstem2"; then - haveit= - if test "X$additional_libdir" = "X/usr/local/$acl_libdirstem" \ - || test "X$additional_libdir" = "X/usr/local/$acl_libdirstem2"; then - if test -n "$GCC"; then - case $host_os in - linux* | gnu* | k*bsd*-gnu) haveit=yes;; - esac - fi - fi - if test -z "$haveit"; then - haveit= - for x in $LDFLAGS $LIBICONV; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$additional_libdir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_libdir"; then - LIBICONV="${LIBICONV}${LIBICONV:+ }-L$additional_libdir" - fi - fi - haveit= - for x in $LDFLAGS $LTLIBICONV; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$additional_libdir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_libdir"; then - LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }-L$additional_libdir" - fi - fi - fi - fi - ;; - -R*) - dir=`echo "X$dep" | sed -e 's/^X-R//'` - if test "$enable_rpath" != no; then - haveit= - for x in $rpathdirs; do - if test "X$x" = "X$dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - rpathdirs="$rpathdirs $dir" - fi - haveit= - for x in $ltrpathdirs; do - if test "X$x" = "X$dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - ltrpathdirs="$ltrpathdirs $dir" - fi - fi - ;; - -l*) - names_next_round="$names_next_round "`echo "X$dep" | sed -e 's/^X-l//'` - ;; - *.la) - names_next_round="$names_next_round "`echo "X$dep" | sed -e 's,^X.*/,,' -e 's,^lib,,' -e 's,\.la$,,'` - ;; - *) - LIBICONV="${LIBICONV}${LIBICONV:+ }$dep" - LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }$dep" - ;; - esac - done - fi - else - LIBICONV="${LIBICONV}${LIBICONV:+ }-l$name" - LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }-l$name" - fi - fi - fi - done - done - if test "X$rpathdirs" != "X"; then - if test -n "$acl_hardcode_libdir_separator"; then - alldirs= - for found_dir in $rpathdirs; do - alldirs="${alldirs}${alldirs:+$acl_hardcode_libdir_separator}$found_dir" - done - acl_save_libdir="$libdir" - libdir="$alldirs" - eval flag=\"$acl_hardcode_libdir_flag_spec\" - libdir="$acl_save_libdir" - LIBICONV="${LIBICONV}${LIBICONV:+ }$flag" - else - for found_dir in $rpathdirs; do - acl_save_libdir="$libdir" - libdir="$found_dir" - eval flag=\"$acl_hardcode_libdir_flag_spec\" - libdir="$acl_save_libdir" - LIBICONV="${LIBICONV}${LIBICONV:+ }$flag" - done - fi - fi - if test "X$ltrpathdirs" != "X"; then - for found_dir in $ltrpathdirs; do - LTLIBICONV="${LTLIBICONV}${LTLIBICONV:+ }-R$found_dir" - done - fi - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for CFPreferencesCopyAppValue" >&5 -$as_echo_n "checking for CFPreferencesCopyAppValue... " >&6; } -if ${gt_cv_func_CFPreferencesCopyAppValue+:} false; then : - $as_echo_n "(cached) " >&6 -else - gt_save_LIBS="$LIBS" - LIBS="$LIBS -Wl,-framework -Wl,CoreFoundation" - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <CoreFoundation/CFPreferences.h> -int -main () -{ -CFPreferencesCopyAppValue(NULL, NULL) - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - gt_cv_func_CFPreferencesCopyAppValue=yes -else - gt_cv_func_CFPreferencesCopyAppValue=no -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - LIBS="$gt_save_LIBS" -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $gt_cv_func_CFPreferencesCopyAppValue" >&5 -$as_echo "$gt_cv_func_CFPreferencesCopyAppValue" >&6; } - if test $gt_cv_func_CFPreferencesCopyAppValue = yes; then - -$as_echo "#define HAVE_CFPREFERENCESCOPYAPPVALUE 1" >>confdefs.h - - fi - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for CFLocaleCopyCurrent" >&5 -$as_echo_n "checking for CFLocaleCopyCurrent... " >&6; } -if ${gt_cv_func_CFLocaleCopyCurrent+:} false; then : - $as_echo_n "(cached) " >&6 -else - gt_save_LIBS="$LIBS" - LIBS="$LIBS -Wl,-framework -Wl,CoreFoundation" - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <CoreFoundation/CFLocale.h> -int -main () -{ -CFLocaleCopyCurrent(); - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - gt_cv_func_CFLocaleCopyCurrent=yes -else - gt_cv_func_CFLocaleCopyCurrent=no -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - LIBS="$gt_save_LIBS" -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $gt_cv_func_CFLocaleCopyCurrent" >&5 -$as_echo "$gt_cv_func_CFLocaleCopyCurrent" >&6; } - if test $gt_cv_func_CFLocaleCopyCurrent = yes; then - -$as_echo "#define HAVE_CFLOCALECOPYCURRENT 1" >>confdefs.h - - fi - INTL_MACOSX_LIBS= - if test $gt_cv_func_CFPreferencesCopyAppValue = yes || test $gt_cv_func_CFLocaleCopyCurrent = yes; then - INTL_MACOSX_LIBS="-Wl,-framework -Wl,CoreFoundation" - fi - - - - - - - LIBINTL= - LTLIBINTL= - POSUB= - - case " $gt_needs " in - *" need-formatstring-macros "*) gt_api_version=3 ;; - *" need-ngettext "*) gt_api_version=2 ;; - *) gt_api_version=1 ;; - esac - gt_func_gnugettext_libc="gt_cv_func_gnugettext${gt_api_version}_libc" - gt_func_gnugettext_libintl="gt_cv_func_gnugettext${gt_api_version}_libintl" - - if test "$USE_NLS" = "yes"; then - gt_use_preinstalled_gnugettext=no - - - if test $gt_api_version -ge 3; then - gt_revision_test_code=' -#ifndef __GNU_GETTEXT_SUPPORTED_REVISION -#define __GNU_GETTEXT_SUPPORTED_REVISION(major) ((major) == 0 ? 0 : -1) -#endif -typedef int array [2 * (__GNU_GETTEXT_SUPPORTED_REVISION(0) >= 1) - 1]; -' - else - gt_revision_test_code= - fi - if test $gt_api_version -ge 2; then - gt_expression_test_code=' + * ngettext ("", "", 0)' - else - gt_expression_test_code= - fi - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for GNU gettext in libc" >&5 -$as_echo_n "checking for GNU gettext in libc... " >&6; } -if eval \${$gt_func_gnugettext_libc+:} false; then : - $as_echo_n "(cached) " >&6 -else - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern int *_nl_domain_bindings; -int -main () -{ -bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_domain_bindings - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - eval "$gt_func_gnugettext_libc=yes" -else - eval "$gt_func_gnugettext_libc=no" -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext -fi -eval ac_res=\$$gt_func_gnugettext_libc - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 -$as_echo "$ac_res" >&6; } - - if { eval "gt_val=\$$gt_func_gnugettext_libc"; test "$gt_val" != "yes"; }; then - - - - - - am_save_CPPFLAGS="$CPPFLAGS" - - for element in $INCICONV; do - haveit= - for x in $CPPFLAGS; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X$element"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - CPPFLAGS="${CPPFLAGS}${CPPFLAGS:+ }$element" - fi - done - - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for iconv" >&5 -$as_echo_n "checking for iconv... " >&6; } -if ${am_cv_func_iconv+:} false; then : - $as_echo_n "(cached) " >&6 -else - - am_cv_func_iconv="no, consider installing GNU libiconv" - am_cv_lib_iconv=no - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <stdlib.h> -#include <iconv.h> -int -main () -{ -iconv_t cd = iconv_open("",""); - iconv(cd,NULL,NULL,NULL,NULL); - iconv_close(cd); - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - am_cv_func_iconv=yes -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - if test "$am_cv_func_iconv" != yes; then - am_save_LIBS="$LIBS" - LIBS="$LIBS $LIBICONV" - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <stdlib.h> -#include <iconv.h> -int -main () -{ -iconv_t cd = iconv_open("",""); - iconv(cd,NULL,NULL,NULL,NULL); - iconv_close(cd); - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - am_cv_lib_iconv=yes - am_cv_func_iconv=yes -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - LIBS="$am_save_LIBS" - fi - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_func_iconv" >&5 -$as_echo "$am_cv_func_iconv" >&6; } - if test "$am_cv_func_iconv" = yes; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for working iconv" >&5 -$as_echo_n "checking for working iconv... " >&6; } -if ${am_cv_func_iconv_works+:} false; then : - $as_echo_n "(cached) " >&6 -else - - am_save_LIBS="$LIBS" - if test $am_cv_lib_iconv = yes; then - LIBS="$LIBS $LIBICONV" - fi - if test "$cross_compiling" = yes; then : - case "$host_os" in - aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; - *) am_cv_func_iconv_works="guessing yes" ;; - esac -else - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ - -#include <iconv.h> -#include <string.h> -int main () -{ - /* Test against AIX 5.1 bug: Failures are not distinguishable from successful - returns. */ - { - iconv_t cd_utf8_to_88591 = iconv_open ("ISO8859-1", "UTF-8"); - if (cd_utf8_to_88591 != (iconv_t)(-1)) - { - static const char input[] = "\342\202\254"; /* EURO SIGN */ - char buf[10]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_utf8_to_88591, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if (res == 0) - return 1; - } - } - /* Test against Solaris 10 bug: Failures are not distinguishable from - successful returns. */ - { - iconv_t cd_ascii_to_88591 = iconv_open ("ISO8859-1", "646"); - if (cd_ascii_to_88591 != (iconv_t)(-1)) - { - static const char input[] = "\263"; - char buf[10]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_ascii_to_88591, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if (res == 0) - return 1; - } - } -#if 0 /* This bug could be worked around by the caller. */ - /* Test against HP-UX 11.11 bug: Positive return value instead of 0. */ - { - iconv_t cd_88591_to_utf8 = iconv_open ("utf8", "iso88591"); - if (cd_88591_to_utf8 != (iconv_t)(-1)) - { - static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; - char buf[50]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if ((int)res > 0) - return 1; - } - } -#endif - /* Test against HP-UX 11.11 bug: No converter from EUC-JP to UTF-8 is - provided. */ - if (/* Try standardized names. */ - iconv_open ("UTF-8", "EUC-JP") == (iconv_t)(-1) - /* Try IRIX, OSF/1 names. */ - && iconv_open ("UTF-8", "eucJP") == (iconv_t)(-1) - /* Try AIX names. */ - && iconv_open ("UTF-8", "IBM-eucJP") == (iconv_t)(-1) - /* Try HP-UX names. */ - && iconv_open ("utf8", "eucJP") == (iconv_t)(-1)) - return 1; - return 0; -} -_ACEOF -if ac_fn_c_try_run "$LINENO"; then : - am_cv_func_iconv_works=yes -else - am_cv_func_iconv_works=no -fi -rm -f core *.core core.conftest.* gmon.out bb.out conftest$ac_exeext \ - conftest.$ac_objext conftest.beam conftest.$ac_ext -fi - - LIBS="$am_save_LIBS" - -fi -{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $am_cv_func_iconv_works" >&5 -$as_echo "$am_cv_func_iconv_works" >&6; } - case "$am_cv_func_iconv_works" in - *no) am_func_iconv=no am_cv_lib_iconv=no ;; - *) am_func_iconv=yes ;; - esac - else - am_func_iconv=no am_cv_lib_iconv=no - fi - if test "$am_func_iconv" = yes; then - -$as_echo "#define HAVE_ICONV 1" >>confdefs.h - - fi - if test "$am_cv_lib_iconv" = yes; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking how to link with libiconv" >&5 -$as_echo_n "checking how to link with libiconv... " >&6; } - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LIBICONV" >&5 -$as_echo "$LIBICONV" >&6; } - else - CPPFLAGS="$am_save_CPPFLAGS" - LIBICONV= - LTLIBICONV= - fi - - - - - - - - - - - - use_additional=yes - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - - eval additional_includedir=\"$includedir\" - eval additional_libdir=\"$libdir\" - - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - -# Check whether --with-libintl-prefix was given. -if test "${with_libintl_prefix+set}" = set; then : - withval=$with_libintl_prefix; - if test "X$withval" = "Xno"; then - use_additional=no - else - if test "X$withval" = "X"; then - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - - eval additional_includedir=\"$includedir\" - eval additional_libdir=\"$libdir\" - - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - else - additional_includedir="$withval/include" - additional_libdir="$withval/$acl_libdirstem" - if test "$acl_libdirstem2" != "$acl_libdirstem" \ - && ! test -d "$withval/$acl_libdirstem"; then - additional_libdir="$withval/$acl_libdirstem2" - fi - fi - fi - -fi - - LIBINTL= - LTLIBINTL= - INCINTL= - LIBINTL_PREFIX= - HAVE_LIBINTL= - rpathdirs= - ltrpathdirs= - names_already_handled= - names_next_round='intl ' - while test -n "$names_next_round"; do - names_this_round="$names_next_round" - names_next_round= - for name in $names_this_round; do - already_handled= - for n in $names_already_handled; do - if test "$n" = "$name"; then - already_handled=yes - break - fi - done - if test -z "$already_handled"; then - names_already_handled="$names_already_handled $name" - uppername=`echo "$name" | sed -e 'y|abcdefghijklmnopqrstuvwxyz./-|ABCDEFGHIJKLMNOPQRSTUVWXYZ___|'` - eval value=\"\$HAVE_LIB$uppername\" - if test -n "$value"; then - if test "$value" = yes; then - eval value=\"\$LIB$uppername\" - test -z "$value" || LIBINTL="${LIBINTL}${LIBINTL:+ }$value" - eval value=\"\$LTLIB$uppername\" - test -z "$value" || LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }$value" - else - : - fi - else - found_dir= - found_la= - found_so= - found_a= - eval libname=\"$acl_libname_spec\" # typically: libname=lib$name - if test -n "$acl_shlibext"; then - shrext=".$acl_shlibext" # typically: shrext=.so - else - shrext= - fi - if test $use_additional = yes; then - dir="$additional_libdir" - if test -n "$acl_shlibext"; then - if test -f "$dir/$libname$shrext"; then - found_dir="$dir" - found_so="$dir/$libname$shrext" - else - if test "$acl_library_names_spec" = '$libname$shrext$versuffix'; then - ver=`(cd "$dir" && \ - for f in "$libname$shrext".*; do echo "$f"; done \ - | sed -e "s,^$libname$shrext\\\\.,," \ - | sort -t '.' -n -r -k1,1 -k2,2 -k3,3 -k4,4 -k5,5 \ - | sed 1q ) 2>/dev/null` - if test -n "$ver" && test -f "$dir/$libname$shrext.$ver"; then - found_dir="$dir" - found_so="$dir/$libname$shrext.$ver" - fi - else - eval library_names=\"$acl_library_names_spec\" - for f in $library_names; do - if test -f "$dir/$f"; then - found_dir="$dir" - found_so="$dir/$f" - break - fi - done - fi - fi - fi - if test "X$found_dir" = "X"; then - if test -f "$dir/$libname.$acl_libext"; then - found_dir="$dir" - found_a="$dir/$libname.$acl_libext" - fi - fi - if test "X$found_dir" != "X"; then - if test -f "$dir/$libname.la"; then - found_la="$dir/$libname.la" - fi - fi - fi - if test "X$found_dir" = "X"; then - for x in $LDFLAGS $LTLIBINTL; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - case "$x" in - -L*) - dir=`echo "X$x" | sed -e 's/^X-L//'` - if test -n "$acl_shlibext"; then - if test -f "$dir/$libname$shrext"; then - found_dir="$dir" - found_so="$dir/$libname$shrext" - else - if test "$acl_library_names_spec" = '$libname$shrext$versuffix'; then - ver=`(cd "$dir" && \ - for f in "$libname$shrext".*; do echo "$f"; done \ - | sed -e "s,^$libname$shrext\\\\.,," \ - | sort -t '.' -n -r -k1,1 -k2,2 -k3,3 -k4,4 -k5,5 \ - | sed 1q ) 2>/dev/null` - if test -n "$ver" && test -f "$dir/$libname$shrext.$ver"; then - found_dir="$dir" - found_so="$dir/$libname$shrext.$ver" - fi - else - eval library_names=\"$acl_library_names_spec\" - for f in $library_names; do - if test -f "$dir/$f"; then - found_dir="$dir" - found_so="$dir/$f" - break - fi - done - fi - fi - fi - if test "X$found_dir" = "X"; then - if test -f "$dir/$libname.$acl_libext"; then - found_dir="$dir" - found_a="$dir/$libname.$acl_libext" - fi - fi - if test "X$found_dir" != "X"; then - if test -f "$dir/$libname.la"; then - found_la="$dir/$libname.la" - fi - fi - ;; - esac - if test "X$found_dir" != "X"; then - break - fi - done - fi - if test "X$found_dir" != "X"; then - LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }-L$found_dir -l$name" - if test "X$found_so" != "X"; then - if test "$enable_rpath" = no \ - || test "X$found_dir" = "X/usr/$acl_libdirstem" \ - || test "X$found_dir" = "X/usr/$acl_libdirstem2"; then - LIBINTL="${LIBINTL}${LIBINTL:+ }$found_so" - else - haveit= - for x in $ltrpathdirs; do - if test "X$x" = "X$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - ltrpathdirs="$ltrpathdirs $found_dir" - fi - if test "$acl_hardcode_direct" = yes; then - LIBINTL="${LIBINTL}${LIBINTL:+ }$found_so" - else - if test -n "$acl_hardcode_libdir_flag_spec" && test "$acl_hardcode_minus_L" = no; then - LIBINTL="${LIBINTL}${LIBINTL:+ }$found_so" - haveit= - for x in $rpathdirs; do - if test "X$x" = "X$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - rpathdirs="$rpathdirs $found_dir" - fi - else - haveit= - for x in $LDFLAGS $LIBINTL; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$found_dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - LIBINTL="${LIBINTL}${LIBINTL:+ }-L$found_dir" - fi - if test "$acl_hardcode_minus_L" != no; then - LIBINTL="${LIBINTL}${LIBINTL:+ }$found_so" - else - LIBINTL="${LIBINTL}${LIBINTL:+ }-l$name" - fi - fi - fi - fi - else - if test "X$found_a" != "X"; then - LIBINTL="${LIBINTL}${LIBINTL:+ }$found_a" - else - LIBINTL="${LIBINTL}${LIBINTL:+ }-L$found_dir -l$name" - fi - fi - additional_includedir= - case "$found_dir" in - */$acl_libdirstem | */$acl_libdirstem/) - basedir=`echo "X$found_dir" | sed -e 's,^X,,' -e "s,/$acl_libdirstem/"'*$,,'` - if test "$name" = 'intl'; then - LIBINTL_PREFIX="$basedir" - fi - additional_includedir="$basedir/include" - ;; - */$acl_libdirstem2 | */$acl_libdirstem2/) - basedir=`echo "X$found_dir" | sed -e 's,^X,,' -e "s,/$acl_libdirstem2/"'*$,,'` - if test "$name" = 'intl'; then - LIBINTL_PREFIX="$basedir" - fi - additional_includedir="$basedir/include" - ;; - esac - if test "X$additional_includedir" != "X"; then - if test "X$additional_includedir" != "X/usr/include"; then - haveit= - if test "X$additional_includedir" = "X/usr/local/include"; then - if test -n "$GCC"; then - case $host_os in - linux* | gnu* | k*bsd*-gnu) haveit=yes;; - esac - fi - fi - if test -z "$haveit"; then - for x in $CPPFLAGS $INCINTL; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-I$additional_includedir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_includedir"; then - INCINTL="${INCINTL}${INCINTL:+ }-I$additional_includedir" - fi - fi - fi - fi - fi - if test -n "$found_la"; then - save_libdir="$libdir" - case "$found_la" in - */* | *\\*) . "$found_la" ;; - *) . "./$found_la" ;; - esac - libdir="$save_libdir" - for dep in $dependency_libs; do - case "$dep" in - -L*) - additional_libdir=`echo "X$dep" | sed -e 's/^X-L//'` - if test "X$additional_libdir" != "X/usr/$acl_libdirstem" \ - && test "X$additional_libdir" != "X/usr/$acl_libdirstem2"; then - haveit= - if test "X$additional_libdir" = "X/usr/local/$acl_libdirstem" \ - || test "X$additional_libdir" = "X/usr/local/$acl_libdirstem2"; then - if test -n "$GCC"; then - case $host_os in - linux* | gnu* | k*bsd*-gnu) haveit=yes;; - esac - fi - fi - if test -z "$haveit"; then - haveit= - for x in $LDFLAGS $LIBINTL; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$additional_libdir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_libdir"; then - LIBINTL="${LIBINTL}${LIBINTL:+ }-L$additional_libdir" - fi - fi - haveit= - for x in $LDFLAGS $LTLIBINTL; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X-L$additional_libdir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - if test -d "$additional_libdir"; then - LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }-L$additional_libdir" - fi - fi - fi - fi - ;; - -R*) - dir=`echo "X$dep" | sed -e 's/^X-R//'` - if test "$enable_rpath" != no; then - haveit= - for x in $rpathdirs; do - if test "X$x" = "X$dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - rpathdirs="$rpathdirs $dir" - fi - haveit= - for x in $ltrpathdirs; do - if test "X$x" = "X$dir"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - ltrpathdirs="$ltrpathdirs $dir" - fi - fi - ;; - -l*) - names_next_round="$names_next_round "`echo "X$dep" | sed -e 's/^X-l//'` - ;; - *.la) - names_next_round="$names_next_round "`echo "X$dep" | sed -e 's,^X.*/,,' -e 's,^lib,,' -e 's,\.la$,,'` - ;; - *) - LIBINTL="${LIBINTL}${LIBINTL:+ }$dep" - LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }$dep" - ;; - esac - done - fi - else - LIBINTL="${LIBINTL}${LIBINTL:+ }-l$name" - LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }-l$name" - fi - fi - fi - done - done - if test "X$rpathdirs" != "X"; then - if test -n "$acl_hardcode_libdir_separator"; then - alldirs= - for found_dir in $rpathdirs; do - alldirs="${alldirs}${alldirs:+$acl_hardcode_libdir_separator}$found_dir" - done - acl_save_libdir="$libdir" - libdir="$alldirs" - eval flag=\"$acl_hardcode_libdir_flag_spec\" - libdir="$acl_save_libdir" - LIBINTL="${LIBINTL}${LIBINTL:+ }$flag" - else - for found_dir in $rpathdirs; do - acl_save_libdir="$libdir" - libdir="$found_dir" - eval flag=\"$acl_hardcode_libdir_flag_spec\" - libdir="$acl_save_libdir" - LIBINTL="${LIBINTL}${LIBINTL:+ }$flag" - done - fi - fi - if test "X$ltrpathdirs" != "X"; then - for found_dir in $ltrpathdirs; do - LTLIBINTL="${LTLIBINTL}${LTLIBINTL:+ }-R$found_dir" - done - fi - - - - - - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking for GNU gettext in libintl" >&5 -$as_echo_n "checking for GNU gettext in libintl... " >&6; } -if eval \${$gt_func_gnugettext_libintl+:} false; then : - $as_echo_n "(cached) " >&6 -else - gt_save_CPPFLAGS="$CPPFLAGS" - CPPFLAGS="$CPPFLAGS $INCINTL" - gt_save_LIBS="$LIBS" - LIBS="$LIBS $LIBINTL" - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern -#ifdef __cplusplus -"C" -#endif -const char *_nl_expand_alias (const char *); -int -main () -{ -bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_expand_alias ("") - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - eval "$gt_func_gnugettext_libintl=yes" -else - eval "$gt_func_gnugettext_libintl=no" -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" != yes; } && test -n "$LIBICONV"; then - LIBS="$LIBS $LIBICONV" - cat confdefs.h - <<_ACEOF >conftest.$ac_ext -/* end confdefs.h. */ -#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern -#ifdef __cplusplus -"C" -#endif -const char *_nl_expand_alias (const char *); -int -main () -{ -bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_expand_alias ("") - ; - return 0; -} -_ACEOF -if ac_fn_c_try_link "$LINENO"; then : - LIBINTL="$LIBINTL $LIBICONV" - LTLIBINTL="$LTLIBINTL $LTLIBICONV" - eval "$gt_func_gnugettext_libintl=yes" - -fi -rm -f core conftest.err conftest.$ac_objext \ - conftest$ac_exeext conftest.$ac_ext - fi - CPPFLAGS="$gt_save_CPPFLAGS" - LIBS="$gt_save_LIBS" -fi -eval ac_res=\$$gt_func_gnugettext_libintl - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5 -$as_echo "$ac_res" >&6; } - fi - - if { eval "gt_val=\$$gt_func_gnugettext_libc"; test "$gt_val" = "yes"; } \ - || { { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; } \ - && test "$PACKAGE" != gettext-runtime \ - && test "$PACKAGE" != gettext-tools; }; then - gt_use_preinstalled_gnugettext=yes - else - LIBINTL= - LTLIBINTL= - INCINTL= - fi - - - - if test -n "$INTL_MACOSX_LIBS"; then - if test "$gt_use_preinstalled_gnugettext" = "yes" \ - || test "$nls_cv_use_gnu_gettext" = "yes"; then - LIBINTL="$LIBINTL $INTL_MACOSX_LIBS" - LTLIBINTL="$LTLIBINTL $INTL_MACOSX_LIBS" - fi - fi - - if test "$gt_use_preinstalled_gnugettext" = "yes" \ - || test "$nls_cv_use_gnu_gettext" = "yes"; then - -$as_echo "#define ENABLE_NLS 1" >>confdefs.h - - else - USE_NLS=no - fi - fi - - { $as_echo "$as_me:${as_lineno-$LINENO}: checking whether to use NLS" >&5 -$as_echo_n "checking whether to use NLS... " >&6; } - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $USE_NLS" >&5 -$as_echo "$USE_NLS" >&6; } - if test "$USE_NLS" = "yes"; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking where the gettext function comes from" >&5 -$as_echo_n "checking where the gettext function comes from... " >&6; } - if test "$gt_use_preinstalled_gnugettext" = "yes"; then - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; }; then - gt_source="external libintl" - else - gt_source="libc" - fi - else - gt_source="included intl directory" - fi - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $gt_source" >&5 -$as_echo "$gt_source" >&6; } - fi - - if test "$USE_NLS" = "yes"; then - - if test "$gt_use_preinstalled_gnugettext" = "yes"; then - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; }; then - { $as_echo "$as_me:${as_lineno-$LINENO}: checking how to link with libintl" >&5 -$as_echo_n "checking how to link with libintl... " >&6; } - { $as_echo "$as_me:${as_lineno-$LINENO}: result: $LIBINTL" >&5 -$as_echo "$LIBINTL" >&6; } - - for element in $INCINTL; do - haveit= - for x in $CPPFLAGS; do - - acl_save_prefix="$prefix" - prefix="$acl_final_prefix" - acl_save_exec_prefix="$exec_prefix" - exec_prefix="$acl_final_exec_prefix" - eval x=\"$x\" - exec_prefix="$acl_save_exec_prefix" - prefix="$acl_save_prefix" - - if test "X$x" = "X$element"; then - haveit=yes - break - fi - done - if test -z "$haveit"; then - CPPFLAGS="${CPPFLAGS}${CPPFLAGS:+ }$element" - fi - done - - fi - - -$as_echo "#define HAVE_GETTEXT 1" >>confdefs.h - - -$as_echo "#define HAVE_DCGETTEXT 1" >>confdefs.h - - fi - - POSUB=po - fi - - - - INTLLIBS="$LIBINTL" - - - - - - - - ac_fn_c_check_member "$LINENO" "struct stat" "st_blksize" "ac_cv_member_struct_stat_st_blksize" "$ac_includes_default" if test "x$ac_cv_member_struct_stat_st_blksize" = xyes; then : @@ -6965,8 +4852,8 @@ esac -macro_version='2.4.2.458.26-92994' -macro_revision='2.4.3' +macro_version='2.4.5' +macro_revision='2.4.5' @@ -6982,6 +4869,77 @@ macro_revision='2.4.3' ltmain=$ac_aux_dir/ltmain.sh +# Make sure we can run config.sub. +$SHELL "$ac_aux_dir/config.sub" sun4 >/dev/null 2>&1 || + as_fn_error $? "cannot run $SHELL $ac_aux_dir/config.sub" "$LINENO" 5 + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking build system type" >&5 +$as_echo_n "checking build system type... " >&6; } +if ${ac_cv_build+:} false; then : + $as_echo_n "(cached) " >&6 +else + ac_build_alias=$build_alias +test "x$ac_build_alias" = x && + ac_build_alias=`$SHELL "$ac_aux_dir/config.guess"` +test "x$ac_build_alias" = x && + as_fn_error $? "cannot guess build type; you must specify one" "$LINENO" 5 +ac_cv_build=`$SHELL "$ac_aux_dir/config.sub" $ac_build_alias` || + as_fn_error $? "$SHELL $ac_aux_dir/config.sub $ac_build_alias failed" "$LINENO" 5 + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_build" >&5 +$as_echo "$ac_cv_build" >&6; } +case $ac_cv_build in +*-*-*) ;; +*) as_fn_error $? "invalid value of canonical build" "$LINENO" 5;; +esac +build=$ac_cv_build +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_build +shift +build_cpu=$1 +build_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +build_os=$* +IFS=$ac_save_IFS +case $build_os in *\ *) build_os=`echo "$build_os" | sed 's/ /-/g'`;; esac + + +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking host system type" >&5 +$as_echo_n "checking host system type... " >&6; } +if ${ac_cv_host+:} false; then : + $as_echo_n "(cached) " >&6 +else + if test "x$host_alias" = x; then + ac_cv_host=$ac_cv_build +else + ac_cv_host=`$SHELL "$ac_aux_dir/config.sub" $host_alias` || + as_fn_error $? "$SHELL $ac_aux_dir/config.sub $host_alias failed" "$LINENO" 5 +fi + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_host" >&5 +$as_echo "$ac_cv_host" >&6; } +case $ac_cv_host in +*-*-*) ;; +*) as_fn_error $? "invalid value of canonical host" "$LINENO" 5;; +esac +host=$ac_cv_host +ac_save_IFS=$IFS; IFS='-' +set x $ac_cv_host +shift +host_cpu=$1 +host_vendor=$2 +shift; shift +# Remember, the first character of IFS is used to create $*, +# except with old shells: +host_os=$* +IFS=$ac_save_IFS +case $host_os in *\ *) host_os=`echo "$host_os" | sed 's/ /-/g'`;; esac + + # Backslashify metacharacters that are still active within # double-quoted strings. sed_quote_subst='s/\(["`$\\]\)/\\\1/g' @@ -8137,6 +6095,9 @@ sysv4 | sysv4.3*) tpf*) lt_cv_deplibs_check_method=pass_all ;; +os2*) + lt_cv_deplibs_check_method=pass_all + ;; esac fi @@ -9184,6 +7145,21 @@ $as_echo "$lt_cv_truncate_bin" >&6; } + +# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +func_cc_basename () +{ + for cc_temp in $*""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac + done + func_cc_basename_result=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +} + # Check whether --enable-libtool-lock was given. if test "${enable_libtool_lock+set}" = set; then : enableval=$enable_libtool_lock; @@ -10191,6 +8167,41 @@ $as_echo "$lt_cv_ld_force_load" >&6; } ;; esac +# func_munge_path_list VARIABLE PATH +# ----------------------------------- +# VARIABLE is name of variable containing _space_ separated list of +# directories to be munged by the contents of PATH, which is string +# having a format: +# "DIR[:DIR]:" +# string "DIR[ DIR]" will be prepended to VARIABLE +# ":DIR[:DIR]" +# string "DIR[ DIR]" will be appended to VARIABLE +# "DIRP[:DIRP]::[DIRA:]DIRA" +# string "DIRP[ DIRP]" will be prepended to VARIABLE and string +# "DIRA[ DIRA]" will be appended to VARIABLE +# "DIR[:DIR]" +# VARIABLE will be replaced by "DIR[ DIR]" +func_munge_path_list () +{ + case x$2 in + x) + ;; + *:) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'` \S|@1\" + ;; + x:*) + eval $1=\"\$$1 `$ECHO $2 | $SED 's/:/ /g'`\" + ;; + *::*) + eval $1=\"\$$1\ `$ECHO $2 | $SED -e 's/.*:://' -e 's/:/ /g'`\" + eval $1=\"`$ECHO $2 | $SED -e 's/::.*//' -e 's/:/ /g'`\ \$$1\" + ;; + *) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'`\" + ;; + esac +} + for ac_header in dlfcn.h do : ac_fn_c_check_header_compile "$LINENO" "dlfcn.h" "ac_cv_header_dlfcn_h" "$ac_includes_default @@ -10310,6 +8321,58 @@ fi + shared_archive_member_spec= +case $host,$enable_shared in +power*-*-aix[5-9]*,yes) + { $as_echo "$as_me:${as_lineno-$LINENO}: checking which variant of shared library versioning to provide" >&5 +$as_echo_n "checking which variant of shared library versioning to provide... " >&6; } + +# Check whether --with-aix-soname was given. +if test "${with_aix_soname+set}" = set; then : + withval=$with_aix_soname; case $withval in + aix|svr4|both) + ;; + *) + as_fn_error $? "Unknown argument to --with-aix-soname" "$LINENO" 5 + ;; + esac + lt_cv_with_aix_soname=$with_aix_soname +else + if ${lt_cv_with_aix_soname+:} false; then : + $as_echo_n "(cached) " >&6 +else + lt_cv_with_aix_soname=aix +fi + + with_aix_soname=$lt_cv_with_aix_soname +fi + + { $as_echo "$as_me:${as_lineno-$LINENO}: result: $with_aix_soname" >&5 +$as_echo "$with_aix_soname" >&6; } + if test aix != "$with_aix_soname"; then + # For the AIX way of multilib, we name the shared archive member + # based on the bitwidth used, traditionally 'shr.o' or 'shr_64.o', + # and 'shr.imp' or 'shr_64.imp', respectively, for the Import File. + # Even when GNU compilers ignore OBJECT_MODE but need '-maix64' flag, + # the AIX toolchain works better with OBJECT_MODE set (default 32). + if test 64 = "${OBJECT_MODE-32}"; then + shared_archive_member_spec=shr_64 + else + shared_archive_member_spec=shr + fi + fi + ;; +*) + with_aix_soname=aix + ;; +esac + + + + + + + @@ -10429,15 +8492,8 @@ test -z "$LTCFLAGS" && LTCFLAGS=$CFLAGS test -z "$LD" && LD=ld test -z "$ac_objext" && ac_objext=o -for cc_temp in $compiler""; do - case $cc_temp in - compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; - distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; - \-*) ;; - *) break;; - esac -done -cc_basename=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +func_cc_basename $compiler +cc_basename=$func_cc_basename_result # Only perform the check for file, if the check method requires it @@ -10748,6 +8804,11 @@ lt_prog_compiler_static= # Although the cygwin gcc ignores -fPIC, still need this for old-style # (--disable-auto-import) libraries lt_prog_compiler_pic='-DDLL_EXPORT' + case $host_os in + os2*) + lt_prog_compiler_static='$wl-static' + ;; + esac ;; darwin* | rhapsody*) @@ -10844,6 +8905,11 @@ lt_prog_compiler_static= # This hack is so that the source file can tell whether it is being # built for inclusion in a dll (and should export symbols for example). lt_prog_compiler_pic='-DDLL_EXPORT' + case $host_os in + os2*) + lt_prog_compiler_static='$wl-static' + ;; + esac ;; hpux9* | hpux10* | hpux11*) @@ -11484,6 +9550,34 @@ _LT_EOF link_all_deplibs=yes ;; + os2*) + hardcode_libdir_flag_spec='-L$libdir' + hardcode_minus_L=yes + allow_undefined_flag=unsupported + shrext_cmds=.dll + archive_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + archive_expsym_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + old_archive_From_new_cmds='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + enable_shared_with_static_runtimes=yes + ;; + interix[3-9]*) hardcode_direct=no hardcode_shlibpath_var=no @@ -11557,6 +9651,9 @@ _LT_EOF fi case $cc_basename in + tcc*) + export_dynamic_flag_spec='-rdynamic' + ;; xlf* | bgf* | bgxlf* | mpixlf*) # IBM XL Fortran 10.1 on PPC cannot create shared libs itself whole_archive_flag_spec='--whole-archive$convenience --no-whole-archive' @@ -11686,19 +9783,35 @@ _LT_EOF no_entry_flag= else # If we're using GNU nm, then we don't want the "-C" option. - # -C means demangle to AIX nm, but means don't demangle with GNU nm - # Also, AIX nm treats weak defined symbols like other global - # defined symbols, whereas GNU nm marks them as "W". + # -C means demangle to GNU nm, but means don't demangle to AIX nm. + # Without the "-l" option, or with the "-B" option, AIX nm treats + # weak defined symbols like other global defined symbols, whereas + # GNU nm marks them as "W". + # While the 'weak' keyword is ignored in the Export File, we need + # it in the Import File for the 'aix-soname' feature, so we have + # to replace the "-B" option with "-P" for AIX nm. if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then - export_symbols_cmds='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && (substr(\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + export_symbols_cmds='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && (substr(\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols' else - export_symbols_cmds='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B")) && (substr(\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + export_symbols_cmds='`func_echo_all $NM | $SED -e '\''s/B\([^B]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && (substr(\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols' fi aix_use_runtimelinking=no # Test if we are trying to use run time linking or normal # AIX style linking. If -brtl is somewhere in LDFLAGS, we - # need to do runtime linking. + # have runtime linking enabled, and use it for executables. + # For shared libraries, we enable/disable runtime linking + # depending on the kind of the shared library created - + # when "with_aix_soname,aix_use_runtimelinking" is: + # "aix,no" lib.a(lib.so.V) shared, rtl:no, for executables + # "aix,yes" lib.so shared, rtl:yes, for executables + # lib.a static archive + # "both,no" lib.so.V(shr.o) shared, rtl:yes + # lib.a(lib.so.V) shared, rtl:no, for executables + # "both,yes" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a(lib.so.V) shared, rtl:no + # "svr4,*" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a static archive case $host_os in aix4.[23]|aix4.[23].*|aix[5-9]*) for ld_flag in $LDFLAGS; do if (test x-brtl = "x$ld_flag" || test x-Wl,-brtl = "x$ld_flag"); then @@ -11706,6 +9819,13 @@ _LT_EOF break fi done + if test svr4,no = "$with_aix_soname,$aix_use_runtimelinking"; then + # With aix-soname=svr4, we create the lib.so.V shared archives only, + # so we don't have lib.a shared libs to link our executables. + # We have to force runtime linking in this case. + aix_use_runtimelinking=yes + LDFLAGS="$LDFLAGS -Wl,-brtl" + fi ;; esac @@ -11725,6 +9845,14 @@ _LT_EOF hardcode_libdir_separator=':' link_all_deplibs=yes file_list_spec='$wl-f,' + case $with_aix_soname,$aix_use_runtimelinking in + aix,*) ;; # traditional, no import file + svr4,* | *,yes) # use import file + # The Import File defines what to hardcode. + hardcode_direct=no + hardcode_direct_absolute=no + ;; + esac if test yes = "$GCC"; then case $host_os in aix4.[012]|aix4.[012].*) @@ -11752,6 +9880,11 @@ _LT_EOF if test yes = "$aix_use_runtimelinking"; then shared_flag="$shared_flag "'$wl-G' fi + # Need to ensure runtime linking is disabled for the traditional + # shared library, or the linker may eventually find shared libraries + # /with/ Import File - we do not want to mix them. + shared_flag_aix='-shared' + shared_flag_svr4='-shared $wl-G' else # not using gcc if test ia64 = "$host_cpu"; then @@ -11764,6 +9897,8 @@ _LT_EOF else shared_flag='$wl-bM:SRE' fi + shared_flag_aix='$wl-bM:SRE' + shared_flag_svr4='$wl-G' fi fi @@ -11771,7 +9906,7 @@ _LT_EOF # It seems that -bexpall does not export symbols beginning with # underscore (_), so it is better to generate a list of symbols to export. always_export_symbols=yes - if test yes = "$aix_use_runtimelinking"; then + if test aix,yes = "$with_aix_soname,$aix_use_runtimelinking"; then # Warning - without using the other runtime loading flags (-brtl), # -berok will link without error, but may produce a broken library. allow_undefined_flag='-berok' @@ -11886,8 +10021,20 @@ fi whole_archive_flag_spec='$convenience' fi archive_cmds_need_lc=yes - # This is similar to how AIX traditionally builds its shared libraries. - archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs $wl-bnoentry $compiler_flags $wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + archive_expsym_cmds='$RM -r $output_objdir/$realname.d~$MKDIR $output_objdir/$realname.d' + # -brtl affects multiple linker settings, -berok does not and is overridden later + compiler_flags_filtered='`func_echo_all "$compiler_flags " | $SED -e "s%-brtl\\([, ]\\)%-berok\\1%g"`' + if test svr4 != "$with_aix_soname"; then + # This is similar to how AIX traditionally builds its shared libraries. + archive_expsym_cmds="$archive_expsym_cmds"'~$CC '$shared_flag_aix' -o $output_objdir/$realname.d/$soname $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$realname.d/$soname' + fi + if test aix != "$with_aix_soname"; then + archive_expsym_cmds="$archive_expsym_cmds"'~$CC '$shared_flag_svr4' -o $output_objdir/$realname.d/$shared_archive_member_spec.o $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$STRIP -e $output_objdir/$realname.d/$shared_archive_member_spec.o~( func_echo_all "#! $soname($shared_archive_member_spec.o)"; if test shr_64 = "$shared_archive_member_spec"; then func_echo_all "# 64"; else func_echo_all "# 32"; fi; cat $export_symbols ) > $output_objdir/$realname.d/$shared_archive_member_spec.imp~$AR $AR_FLAGS $output_objdir/$soname $output_objdir/$realname.d/$shared_archive_member_spec.o $output_objdir/$realname.d/$shared_archive_member_spec.imp' + else + # used by -dlpreopen to get the symbols + archive_expsym_cmds="$archive_expsym_cmds"'~$MV $output_objdir/$realname.d/$soname $output_objdir' + fi + archive_expsym_cmds="$archive_expsym_cmds"'~$RM -r $output_objdir/$realname.d' fi fi ;; @@ -12206,6 +10353,16 @@ $as_echo "$lt_cv_irix_exported_symbol" >&6; } link_all_deplibs=yes ;; + linux*) + case $cc_basename in + tcc*) + # Fabrice Bellard et al's Tiny C Compiler + ld_shlibs=yes + archive_cmds='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + ;; + netbsd*) if echo __ELF__ | $CC -E - | $GREP __ELF__ >/dev/null; then archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out @@ -12251,8 +10408,28 @@ $as_echo "$lt_cv_irix_exported_symbol" >&6; } hardcode_libdir_flag_spec='-L$libdir' hardcode_minus_L=yes allow_undefined_flag=unsupported - archive_cmds='$ECHO "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~echo DATA >> $output_objdir/$libname.def~echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' - old_archive_from_new_cmds='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' + shrext_cmds=.dll + archive_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + archive_expsym_cmds='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + old_archive_From_new_cmds='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + enable_shared_with_static_runtimes=yes ;; osf3*) @@ -12775,6 +10952,8 @@ hardcode_into_libs=no # flags to be left without arguments need_version=unknown + + case $host_os in aix3*) version_type=linux # correct to gnu/linux during the next big refactor @@ -12811,20 +10990,70 @@ aix[4-9]*) fi ;; esac + # Using Import Files as archive members, it is possible to support + # filename-based versioning of shared library archives on AIX. While + # this would work for both with and without runtime linking, it will + # prevent static linking of such archives. So we do filename-based + # shared library versioning with .so extension only, which is used + # when both runtime linking and shared linking is enabled. + # Unfortunately, runtime linking may impact performance, so we do + # not want this to be the default eventually. Also, we use the + # versioned .so libs for executables only if there is the -brtl + # linker flag in LDFLAGS as well, or --with-aix-soname=svr4 only. + # To allow for filename-based versioning support, we need to create + # libNAME.so.V as an archive file, containing: + # *) an Import File, referring to the versioned filename of the + # archive as well as the shared archive member, telling the + # bitwidth (32 or 64) of that shared object, and providing the + # list of exported symbols of that shared object, eventually + # decorated with the 'weak' keyword + # *) the shared object with the F_LOADONLY flag set, to really avoid + # it being seen by the linker. + # At run time we better use the real file rather than another symlink, + # but for link time we create the symlink libNAME.so -> libNAME.so.V + + case $with_aix_soname,$aix_use_runtimelinking in # AIX (on Power*) has no versioning support, so currently we cannot hardcode correct # soname into executable. Probably we can add versioning support to # collect2, so additional links can be useful in future. - if test yes = "$aix_use_runtimelinking"; then + aix,yes) # traditional libtool + dynamic_linker='AIX unversionable lib.so' # If using run time linking (on AIX 4.2 or later) use lib<name>.so # instead of lib<name>.a to let people know that these are not # typical AIX shared libraries. library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' - else + ;; + aix,no) # traditional AIX only + dynamic_linker='AIX lib.a(lib.so.V)' # We preserve .a as extension for shared libraries through AIX4.2 # and later when we are not doing run time linking. library_names_spec='$libname$release.a $libname.a' soname_spec='$libname$release$shared_ext$major' - fi + ;; + svr4,*) # full svr4 only + dynamic_linker="AIX lib.so.V($shared_archive_member_spec.o)" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,yes) # both, prefer svr4 + dynamic_linker="AIX lib.so.V($shared_archive_member_spec.o), lib.a(lib.so.V)" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # unpreferred sharedlib libNAME.a needs extra handling + postinstall_cmds='test -n "$linkname" || linkname="$realname"~func_stripname "" ".so" "$linkname"~$install_shared_prog "$dir/$func_stripname_result.$libext" "$destdir/$func_stripname_result.$libext"~test -z "$tstripme" || test -z "$striplib" || $striplib "$destdir/$func_stripname_result.$libext"' + postuninstall_cmds='for n in $library_names $old_library; do :; done~func_stripname "" ".so" "$n"~test "$func_stripname_result" = "$n" || func_append rmfiles " $odir/$func_stripname_result.$libext"' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,no) # both, prefer aix + dynamic_linker="AIX lib.a(lib.so.V), lib.so.V($shared_archive_member_spec.o)" + library_names_spec='$libname$release.a $libname.a' + soname_spec='$libname$release$shared_ext$major' + # unpreferred sharedlib libNAME.so.V and symlink libNAME.so need extra handling + postinstall_cmds='test -z "$dlname" || $install_shared_prog $dir/$dlname $destdir/$dlname~test -z "$tstripme" || test -z "$striplib" || $striplib $destdir/$dlname~test -n "$linkname" || linkname=$realname~func_stripname "" ".a" "$linkname"~(cd "$destdir" && $LN_S -f $dlname $func_stripname_result.so)' + postuninstall_cmds='test -z "$dlname" || func_append rmfiles " $odir/$dlname"~for n in $old_library $library_names; do :; done~func_stripname "" ".a" "$n"~func_append rmfiles " $odir/$func_stripname_result.so"' + ;; + esac shlibpath_var=LIBPATH fi ;; @@ -13012,7 +11241,8 @@ freebsd* | dragonfly*) version_type=freebsd-$objformat case $version_type in freebsd-elf*) - library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext $libname$shared_ext' + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' need_version=no need_lib_prefix=no ;; @@ -13072,10 +11302,11 @@ hpux9* | hpux10* | hpux11*) soname_spec='$libname$release$shared_ext$major' if test 32 = "$HPUX_IA64_MODE"; then sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + sys_lib_dlsearch_path_spec=/usr/lib/hpux32 else sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + sys_lib_dlsearch_path_spec=/usr/lib/hpux64 fi - sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec ;; hppa*64*) shrext_cmds='.sl' @@ -13227,7 +11458,12 @@ fi # before this can be enabled. hardcode_into_libs=yes - # Append ld.so.conf contents to the search path + # Ideally, we could use ldconfig to report *all* directores which are + # searched for libraries, however this is still not possible. Aside from not + # being certain /sbin/ldconfig is available, command + # 'ldconfig -N -X -v | grep ^/' on 64bit Fedora does not report /usr/lib64, + # even though it is searched at run-time. Try to do the best guess by + # appending ld.so.conf contents (and includes) to the search path. if test -f /etc/ld.so.conf; then lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s 2>/dev/null", \$2)); skip = 1; } { if (!skip) print \$0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;/^[ ]*hwcap[ ]/d;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;s/"//g;/^$/d' | tr '\n' ' '` sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" @@ -13296,11 +11532,32 @@ openbsd* | bitrig*) os2*) libname_spec='$name' + version_type=windows shrext_cmds=.dll + need_version=no need_lib_prefix=no - library_names_spec='$libname$shared_ext $libname.a' + # OS/2 can only load a DLL with a base name of 8 characters or less. + soname_spec='`test -n "$os2dllname" && libname="$os2dllname"; + v=$($ECHO $release$versuffix | tr -d .-); + n=$($ECHO $libname | cut -b -$((8 - ${#v})) | tr . _); + $ECHO $n$v`$shared_ext' + library_names_spec='${libname}_dll.$libext' dynamic_linker='OS/2 ld.exe' - shlibpath_var=LIBPATH + shlibpath_var=BEGINLIBPATH + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + postinstall_cmds='base_file=`basename \$file`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\$base_file'\''i; $ECHO \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname~ + if test -n '\''$stripme'\'' && test -n '\''$striplib'\''; then + eval '\''$striplib \$dldir/$dlname'\'' || exit \$?; + fi' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; $ECHO \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $RM \$dlpath' ;; osf3* | osf4* | osf5*) @@ -13376,7 +11633,7 @@ sysv4*MP*) ;; sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) - version_type=freebsd-elf + version_type=sco need_lib_prefix=no need_version=no library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext $libname$shared_ext' @@ -13431,10 +11688,18 @@ fi if test set = "${lt_cv_sys_lib_search_path_spec+set}"; then sys_lib_search_path_spec=$lt_cv_sys_lib_search_path_spec fi + if test set = "${lt_cv_sys_lib_dlsearch_path_spec+set}"; then sys_lib_dlsearch_path_spec=$lt_cv_sys_lib_dlsearch_path_spec fi +# lt_cv_sys_lib... is unaugmented for libtool script decls... +lt_cv_sys_lib_dlsearch_path_spec=$sys_lib_dlsearch_path_spec + +# ..but sys_lib_... needs LT_SYS_LIBRARY_PATH munging for +# LT_SYS_DLSEARCH_PATH macro in ltdl.m4 to work with the correct paths: +func_munge_path_list sys_lib_dlsearch_path_spec "$LT_SYS_LIBRARY_PATH" + @@ -13905,7 +12170,7 @@ else # endif #endif -/* When -fvisbility=hidden is used, assume the code has been annotated +/* When -fvisibility=hidden is used, assume the code has been annotated correspondingly for the symbols needed. */ #if defined __GNUC__ && (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)) || (__GNUC__ > 3)) int fnord () __attribute__((visibility("default"))); @@ -14011,7 +12276,7 @@ else # endif #endif -/* When -fvisbility=hidden is used, assume the code has been annotated +/* When -fvisibility=hidden is used, assume the code has been annotated correspondingly for the symbols needed. */ #if defined __GNUC__ && (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)) || (__GNUC__ > 3)) int fnord () __attribute__((visibility("default"))); @@ -14160,8 +12425,12 @@ $as_echo_n "checking whether to build shared libraries... " >&6; } ;; aix[4-9]*) - if test ia64 != "$host_cpu" && test no = "$aix_use_runtimelinking"; then - test yes = "$enable_shared" && enable_static=no + if test ia64 != "$host_cpu"; then + case $enable_shared,$with_aix_soname,$aix_use_runtimelinking in + yes,aix,yes) ;; # shared object as lib.so file only + yes,svr4,*) ;; # shared object as lib.so archive member only + yes,*) enable_static=no ;; # shared object in lib.a archive as well + esac fi ;; esac @@ -15386,13 +13655,6 @@ cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1 # INIT-COMMANDS # AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir" -# Capture the value of obsolete ALL_LINGUAS because we need it to compute - # POFILES, UPDATEPOFILES, DUMMYPOFILES, GMOFILES, CATALOGS. But hide it - # from automake < 1.5. - eval 'OBSOLETE_ALL_LINGUAS''="$ALL_LINGUAS"' - # Capture the value of LINGUAS because we need it to compute CATALOGS. - LINGUAS="${LINGUAS-%UNSET%}" - # The HP-UX ksh and POSIX shell print the target directory to stdout @@ -15408,6 +13670,7 @@ macro_revision='`$ECHO "$macro_revision" | $SED "$delay_single_quote_subst"`' enable_shared='`$ECHO "$enable_shared" | $SED "$delay_single_quote_subst"`' pic_mode='`$ECHO "$pic_mode" | $SED "$delay_single_quote_subst"`' enable_fast_install='`$ECHO "$enable_fast_install" | $SED "$delay_single_quote_subst"`' +shared_archive_member_spec='`$ECHO "$shared_archive_member_spec" | $SED "$delay_single_quote_subst"`' SHELL='`$ECHO "$SHELL" | $SED "$delay_single_quote_subst"`' ECHO='`$ECHO "$ECHO" | $SED "$delay_single_quote_subst"`' PATH_SEPARATOR='`$ECHO "$PATH_SEPARATOR" | $SED "$delay_single_quote_subst"`' @@ -15528,7 +13791,7 @@ finish_cmds='`$ECHO "$finish_cmds" | $SED "$delay_single_quote_subst"`' finish_eval='`$ECHO "$finish_eval" | $SED "$delay_single_quote_subst"`' hardcode_into_libs='`$ECHO "$hardcode_into_libs" | $SED "$delay_single_quote_subst"`' sys_lib_search_path_spec='`$ECHO "$sys_lib_search_path_spec" | $SED "$delay_single_quote_subst"`' -sys_lib_dlsearch_path_spec='`$ECHO "$sys_lib_dlsearch_path_spec" | $SED "$delay_single_quote_subst"`' +lt_cv_sys_lib_dlsearch_path_spec='`$ECHO "$lt_cv_sys_lib_dlsearch_path_spec" | $SED "$delay_single_quote_subst"`' hardcode_action='`$ECHO "$hardcode_action" | $SED "$delay_single_quote_subst"`' enable_dlopen='`$ECHO "$enable_dlopen" | $SED "$delay_single_quote_subst"`' enable_dlopen_self='`$ECHO "$enable_dlopen_self" | $SED "$delay_single_quote_subst"`' @@ -15646,7 +13909,7 @@ postinstall_cmds \ postuninstall_cmds \ finish_cmds \ sys_lib_search_path_spec \ -sys_lib_dlsearch_path_spec; do +lt_cv_sys_lib_dlsearch_path_spec; do case \`eval \\\\\$ECHO \\\\""\\\\\$\$var"\\\\"\` in *[\\\\\\\`\\"\\\$]*) eval "lt_\$var=\\\\\\"\\\`\\\$ECHO \\"\\\$\$var\\" | \\\$SED -e \\"\\\$double_quote_subst\\" -e \\"\\\$sed_quote_subst\\" -e \\"\\\$delay_variable_subst\\"\\\`\\\\\\"" ## exclude from sc_prohibit_nested_quotes @@ -15683,7 +13946,6 @@ for ac_config_target in $ac_config_targets do case $ac_config_target in "depfiles") CONFIG_COMMANDS="$CONFIG_COMMANDS depfiles" ;; - "po-directories") CONFIG_COMMANDS="$CONFIG_COMMANDS po-directories" ;; "libtool") CONFIG_COMMANDS="$CONFIG_COMMANDS libtool" ;; "config.h") CONFIG_HEADERS="$CONFIG_HEADERS config.h:configh.in" ;; "Makefile") CONFIG_FILES="$CONFIG_FILES Makefile" ;; @@ -16375,119 +14637,6 @@ $as_echo X"$file" | done } ;; - "po-directories":C) - for ac_file in $CONFIG_FILES; do - # Support "outfile[:infile[:infile...]]" - case "$ac_file" in - *:*) ac_file=`echo "$ac_file"|sed 's%:.*%%'` ;; - esac - # PO directories have a Makefile.in generated from Makefile.in.in. - case "$ac_file" in */Makefile.in) - # Adjust a relative srcdir. - ac_dir=`echo "$ac_file"|sed 's%/[^/][^/]*$%%'` - ac_dir_suffix="/`echo "$ac_dir"|sed 's%^\./%%'`" - ac_dots=`echo "$ac_dir_suffix"|sed 's%/[^/]*%../%g'` - # In autoconf-2.13 it is called $ac_given_srcdir. - # In autoconf-2.50 it is called $srcdir. - test -n "$ac_given_srcdir" || ac_given_srcdir="$srcdir" - case "$ac_given_srcdir" in - .) top_srcdir=`echo $ac_dots|sed 's%/$%%'` ;; - /*) top_srcdir="$ac_given_srcdir" ;; - *) top_srcdir="$ac_dots$ac_given_srcdir" ;; - esac - # Treat a directory as a PO directory if and only if it has a - # POTFILES.in file. This allows packages to have multiple PO - # directories under different names or in different locations. - if test -f "$ac_given_srcdir/$ac_dir/POTFILES.in"; then - rm -f "$ac_dir/POTFILES" - test -n "$as_me" && echo "$as_me: creating $ac_dir/POTFILES" || echo "creating $ac_dir/POTFILES" - cat "$ac_given_srcdir/$ac_dir/POTFILES.in" | sed -e "/^#/d" -e "/^[ ]*\$/d" -e "s,.*, $top_srcdir/& \\\\," | sed -e "\$s/\(.*\) \\\\/\1/" > "$ac_dir/POTFILES" - POMAKEFILEDEPS="POTFILES.in" - # ALL_LINGUAS, POFILES, UPDATEPOFILES, DUMMYPOFILES, GMOFILES depend - # on $ac_dir but don't depend on user-specified configuration - # parameters. - if test -f "$ac_given_srcdir/$ac_dir/LINGUAS"; then - # The LINGUAS file contains the set of available languages. - if test -n "$OBSOLETE_ALL_LINGUAS"; then - test -n "$as_me" && echo "$as_me: setting ALL_LINGUAS in configure.in is obsolete" || echo "setting ALL_LINGUAS in configure.in is obsolete" - fi - ALL_LINGUAS_=`sed -e "/^#/d" -e "s/#.*//" "$ac_given_srcdir/$ac_dir/LINGUAS"` - # Hide the ALL_LINGUAS assigment from automake < 1.5. - eval 'ALL_LINGUAS''=$ALL_LINGUAS_' - POMAKEFILEDEPS="$POMAKEFILEDEPS LINGUAS" - else - # The set of available languages was given in configure.in. - # Hide the ALL_LINGUAS assigment from automake < 1.5. - eval 'ALL_LINGUAS''=$OBSOLETE_ALL_LINGUAS' - fi - # Compute POFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).po) - # Compute UPDATEPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).po-update) - # Compute DUMMYPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).nop) - # Compute GMOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).gmo) - case "$ac_given_srcdir" in - .) srcdirpre= ;; - *) srcdirpre='$(srcdir)/' ;; - esac - POFILES= - UPDATEPOFILES= - DUMMYPOFILES= - GMOFILES= - for lang in $ALL_LINGUAS; do - POFILES="$POFILES $srcdirpre$lang.po" - UPDATEPOFILES="$UPDATEPOFILES $lang.po-update" - DUMMYPOFILES="$DUMMYPOFILES $lang.nop" - GMOFILES="$GMOFILES $srcdirpre$lang.gmo" - done - # CATALOGS depends on both $ac_dir and the user's LINGUAS - # environment variable. - INST_LINGUAS= - if test -n "$ALL_LINGUAS"; then - for presentlang in $ALL_LINGUAS; do - useit=no - if test "%UNSET%" != "$LINGUAS"; then - desiredlanguages="$LINGUAS" - else - desiredlanguages="$ALL_LINGUAS" - fi - for desiredlang in $desiredlanguages; do - # Use the presentlang catalog if desiredlang is - # a. equal to presentlang, or - # b. a variant of presentlang (because in this case, - # presentlang can be used as a fallback for messages - # which are not translated in the desiredlang catalog). - case "$desiredlang" in - "$presentlang"*) useit=yes;; - esac - done - if test $useit = yes; then - INST_LINGUAS="$INST_LINGUAS $presentlang" - fi - done - fi - CATALOGS= - if test -n "$INST_LINGUAS"; then - for lang in $INST_LINGUAS; do - CATALOGS="$CATALOGS $lang.gmo" - done - fi - test -n "$as_me" && echo "$as_me: creating $ac_dir/Makefile" || echo "creating $ac_dir/Makefile" - sed -e "/^POTFILES =/r $ac_dir/POTFILES" -e "/^# Makevars/r $ac_given_srcdir/$ac_dir/Makevars" -e "s|@POFILES@|$POFILES|g" -e "s|@UPDATEPOFILES@|$UPDATEPOFILES|g" -e "s|@DUMMYPOFILES@|$DUMMYPOFILES|g" -e "s|@GMOFILES@|$GMOFILES|g" -e "s|@CATALOGS@|$CATALOGS|g" -e "s|@POMAKEFILEDEPS@|$POMAKEFILEDEPS|g" "$ac_dir/Makefile.in" > "$ac_dir/Makefile" - for f in "$ac_given_srcdir/$ac_dir"/Rules-*; do - if test -f "$f"; then - case "$f" in - *.orig | *.bak | *~) ;; - *) cat "$f" >> "$ac_dir/Makefile" ;; - esac - fi - done - fi - ;; - esac - done ;; "libtool":C) # See if we are running on zsh, and set the options that allow our @@ -16535,6 +14684,9 @@ $as_echo X"$file" | # The names of the tagged configurations supported by this script. available_tags='' +# Configured defaults for sys_lib_dlsearch_path munging. +: \${LT_SYS_LIBRARY_PATH="$LT_SYS_LIBRARY_PATH"} + # ### BEGIN LIBTOOL CONFIG # Whether or not to build static libraries. @@ -16553,6 +14705,9 @@ pic_mode=$pic_mode # Whether or not to optimize for fast installation. fast_install=$enable_fast_install +# Shared archive member basename,for filename based shared library versioning on AIX. +shared_archive_member_spec=$shared_archive_member_spec + # Shell to use when invoking shell scripts. SHELL=$lt_SHELL @@ -16782,7 +14937,7 @@ hardcode_into_libs=$hardcode_into_libs sys_lib_search_path_spec=$lt_sys_lib_search_path_spec # Run-time system search path for libraries. -sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec +sys_lib_dlsearch_path_spec=$lt_lt_cv_sys_lib_dlsearch_path_spec # Whether dlopen is supported. dlopen_support=$enable_dlopen @@ -16933,6 +15088,64 @@ hardcode_action=$hardcode_action _LT_EOF + cat <<'_LT_EOF' >> "$cfgfile" +## -------------------------------------- ## +## Shell functions shared with configure. ## +## -------------------------------------- ## + +# func_munge_path_list VARIABLE PATH +# ----------------------------------- +# VARIABLE is name of variable containing _space_ separated list of +# directories to be munged by the contents of PATH, which is string +# having a format: +# "DIR[:DIR]:" +# string "DIR[ DIR]" will be prepended to VARIABLE +# ":DIR[:DIR]" +# string "DIR[ DIR]" will be appended to VARIABLE +# "DIRP[:DIRP]::[DIRA:]DIRA" +# string "DIRP[ DIRP]" will be prepended to VARIABLE and string +# "DIRA[ DIRA]" will be appended to VARIABLE +# "DIR[:DIR]" +# VARIABLE will be replaced by "DIR[ DIR]" +func_munge_path_list () +{ + case x$2 in + x) + ;; + *:) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'` \S|@1\" + ;; + x:*) + eval $1=\"\$$1 `$ECHO $2 | $SED 's/:/ /g'`\" + ;; + *::*) + eval $1=\"\$$1\ `$ECHO $2 | $SED -e 's/.*:://' -e 's/:/ /g'`\" + eval $1=\"`$ECHO $2 | $SED -e 's/::.*//' -e 's/:/ /g'`\ \$$1\" + ;; + *) + eval $1=\"`$ECHO $2 | $SED 's/:/ /g'`\" + ;; + esac +} + + +# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +func_cc_basename () +{ + for cc_temp in $*""; do + case $cc_temp in + compile | *[\\/]compile | ccache | *[\\/]ccache ) ;; + distcc | *[\\/]distcc | purify | *[\\/]purify ) ;; + \-*) ;; + *) break;; + esac + done + func_cc_basename_result=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +} + + +_LT_EOF + case $host_os in aix3*) cat <<\_LT_EOF >> "$cfgfile" diff --git a/extension/configure.ac b/extension/configure.ac index 1f876a0e..6a516cbc 100644 --- a/extension/configure.ac +++ b/extension/configure.ac @@ -33,10 +33,7 @@ AC_USE_SYSTEM_EXTENSIONS INSTALL="$ac_aux_dir/install-sh -c" export INSTALL -AM_INIT_AUTOMAKE([-Wall -Werror]) - -AM_GNU_GETTEXT([external]) -AM_GNU_GETTEXT_VERSION([0.18.1]) +AM_INIT_AUTOMAKE([1.15 -Wall -Werror]) dnl checks for structure members AC_CHECK_MEMBERS([struct stat.st_blksize]) diff --git a/extension/m4/ChangeLog b/extension/m4/ChangeLog index 349bbcc8..f991eac3 100644 --- a/extension/m4/ChangeLog +++ b/extension/m4/ChangeLog @@ -1,3 +1,7 @@ +2015-01-24 Arnold D. Robbins <arnold@skeeve.com> + + * gettext.m4, iconv.m4, intlmacosx.m4, po.m4: Removed. + 2014-04-08 Arnold D. Robbins <arnold@skeeve.com> * 4.1.1: Release tar ball made. diff --git a/extension/m4/gettext.m4 b/extension/m4/gettext.m4 deleted file mode 100644 index f84e6a5d..00000000 --- a/extension/m4/gettext.m4 +++ /dev/null @@ -1,383 +0,0 @@ -# gettext.m4 serial 63 (gettext-0.18) -dnl Copyright (C) 1995-2010 Free Software Foundation, Inc. -dnl This file is free software; the Free Software Foundation -dnl gives unlimited permission to copy and/or distribute it, -dnl with or without modifications, as long as this notice is preserved. -dnl -dnl This file can can be used in projects which are not available under -dnl the GNU General Public License or the GNU Library General Public -dnl License but which still want to provide support for the GNU gettext -dnl functionality. -dnl Please note that the actual code of the GNU gettext library is covered -dnl by the GNU Library General Public License, and the rest of the GNU -dnl gettext package package is covered by the GNU General Public License. -dnl They are *not* in the public domain. - -dnl Authors: -dnl Ulrich Drepper <drepper@cygnus.com>, 1995-2000. -dnl Bruno Haible <haible@clisp.cons.org>, 2000-2006, 2008-2010. - -dnl Macro to add for using GNU gettext. - -dnl Usage: AM_GNU_GETTEXT([INTLSYMBOL], [NEEDSYMBOL], [INTLDIR]). -dnl INTLSYMBOL can be one of 'external', 'no-libtool', 'use-libtool'. The -dnl default (if it is not specified or empty) is 'no-libtool'. -dnl INTLSYMBOL should be 'external' for packages with no intl directory, -dnl and 'no-libtool' or 'use-libtool' for packages with an intl directory. -dnl If INTLSYMBOL is 'use-libtool', then a libtool library -dnl $(top_builddir)/intl/libintl.la will be created (shared and/or static, -dnl depending on --{enable,disable}-{shared,static} and on the presence of -dnl AM-DISABLE-SHARED). If INTLSYMBOL is 'no-libtool', a static library -dnl $(top_builddir)/intl/libintl.a will be created. -dnl If NEEDSYMBOL is specified and is 'need-ngettext', then GNU gettext -dnl implementations (in libc or libintl) without the ngettext() function -dnl will be ignored. If NEEDSYMBOL is specified and is -dnl 'need-formatstring-macros', then GNU gettext implementations that don't -dnl support the ISO C 99 <inttypes.h> formatstring macros will be ignored. -dnl INTLDIR is used to find the intl libraries. If empty, -dnl the value `$(top_builddir)/intl/' is used. -dnl -dnl The result of the configuration is one of three cases: -dnl 1) GNU gettext, as included in the intl subdirectory, will be compiled -dnl and used. -dnl Catalog format: GNU --> install in $(datadir) -dnl Catalog extension: .mo after installation, .gmo in source tree -dnl 2) GNU gettext has been found in the system's C library. -dnl Catalog format: GNU --> install in $(datadir) -dnl Catalog extension: .mo after installation, .gmo in source tree -dnl 3) No internationalization, always use English msgid. -dnl Catalog format: none -dnl Catalog extension: none -dnl If INTLSYMBOL is 'external', only cases 2 and 3 can occur. -dnl The use of .gmo is historical (it was needed to avoid overwriting the -dnl GNU format catalogs when building on a platform with an X/Open gettext), -dnl but we keep it in order not to force irrelevant filename changes on the -dnl maintainers. -dnl -AC_DEFUN([AM_GNU_GETTEXT], -[ - dnl Argument checking. - ifelse([$1], [], , [ifelse([$1], [external], , [ifelse([$1], [no-libtool], , [ifelse([$1], [use-libtool], , - [errprint([ERROR: invalid first argument to AM_GNU_GETTEXT -])])])])]) - ifelse(ifelse([$1], [], [old])[]ifelse([$1], [no-libtool], [old]), [old], - [AC_DIAGNOSE([obsolete], [Use of AM_GNU_GETTEXT without [external] argument is deprecated.])]) - ifelse([$2], [], , [ifelse([$2], [need-ngettext], , [ifelse([$2], [need-formatstring-macros], , - [errprint([ERROR: invalid second argument to AM_GNU_GETTEXT -])])])]) - define([gt_included_intl], - ifelse([$1], [external], - ifdef([AM_GNU_GETTEXT_][INTL_SUBDIR], [yes], [no]), - [yes])) - define([gt_libtool_suffix_prefix], ifelse([$1], [use-libtool], [l], [])) - gt_NEEDS_INIT - AM_GNU_GETTEXT_NEED([$2]) - - AC_REQUIRE([AM_PO_SUBDIRS])dnl - ifelse(gt_included_intl, yes, [ - AC_REQUIRE([AM_INTL_SUBDIR])dnl - ]) - - dnl Prerequisites of AC_LIB_LINKFLAGS_BODY. - AC_REQUIRE([AC_LIB_PREPARE_PREFIX]) - AC_REQUIRE([AC_LIB_RPATH]) - - dnl Sometimes libintl requires libiconv, so first search for libiconv. - dnl Ideally we would do this search only after the - dnl if test "$USE_NLS" = "yes"; then - dnl if { eval "gt_val=\$$gt_func_gnugettext_libc"; test "$gt_val" != "yes"; }; then - dnl tests. But if configure.in invokes AM_ICONV after AM_GNU_GETTEXT - dnl the configure script would need to contain the same shell code - dnl again, outside any 'if'. There are two solutions: - dnl - Invoke AM_ICONV_LINKFLAGS_BODY here, outside any 'if'. - dnl - Control the expansions in more detail using AC_PROVIDE_IFELSE. - dnl Since AC_PROVIDE_IFELSE is only in autoconf >= 2.52 and not - dnl documented, we avoid it. - ifelse(gt_included_intl, yes, , [ - AC_REQUIRE([AM_ICONV_LINKFLAGS_BODY]) - ]) - - dnl Sometimes, on MacOS X, libintl requires linking with CoreFoundation. - gt_INTL_MACOSX - - dnl Set USE_NLS. - AC_REQUIRE([AM_NLS]) - - ifelse(gt_included_intl, yes, [ - BUILD_INCLUDED_LIBINTL=no - USE_INCLUDED_LIBINTL=no - ]) - LIBINTL= - LTLIBINTL= - POSUB= - - dnl Add a version number to the cache macros. - case " $gt_needs " in - *" need-formatstring-macros "*) gt_api_version=3 ;; - *" need-ngettext "*) gt_api_version=2 ;; - *) gt_api_version=1 ;; - esac - gt_func_gnugettext_libc="gt_cv_func_gnugettext${gt_api_version}_libc" - gt_func_gnugettext_libintl="gt_cv_func_gnugettext${gt_api_version}_libintl" - - dnl If we use NLS figure out what method - if test "$USE_NLS" = "yes"; then - gt_use_preinstalled_gnugettext=no - ifelse(gt_included_intl, yes, [ - AC_MSG_CHECKING([whether included gettext is requested]) - AC_ARG_WITH([included-gettext], - [ --with-included-gettext use the GNU gettext library included here], - nls_cv_force_use_gnu_gettext=$withval, - nls_cv_force_use_gnu_gettext=no) - AC_MSG_RESULT([$nls_cv_force_use_gnu_gettext]) - - nls_cv_use_gnu_gettext="$nls_cv_force_use_gnu_gettext" - if test "$nls_cv_force_use_gnu_gettext" != "yes"; then - ]) - dnl User does not insist on using GNU NLS library. Figure out what - dnl to use. If GNU gettext is available we use this. Else we have - dnl to fall back to GNU NLS library. - - if test $gt_api_version -ge 3; then - gt_revision_test_code=' -#ifndef __GNU_GETTEXT_SUPPORTED_REVISION -#define __GNU_GETTEXT_SUPPORTED_REVISION(major) ((major) == 0 ? 0 : -1) -#endif -changequote(,)dnl -typedef int array [2 * (__GNU_GETTEXT_SUPPORTED_REVISION(0) >= 1) - 1]; -changequote([,])dnl -' - else - gt_revision_test_code= - fi - if test $gt_api_version -ge 2; then - gt_expression_test_code=' + * ngettext ("", "", 0)' - else - gt_expression_test_code= - fi - - AC_CACHE_CHECK([for GNU gettext in libc], [$gt_func_gnugettext_libc], - [AC_TRY_LINK([#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern int *_nl_domain_bindings;], - [bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_domain_bindings], - [eval "$gt_func_gnugettext_libc=yes"], - [eval "$gt_func_gnugettext_libc=no"])]) - - if { eval "gt_val=\$$gt_func_gnugettext_libc"; test "$gt_val" != "yes"; }; then - dnl Sometimes libintl requires libiconv, so first search for libiconv. - ifelse(gt_included_intl, yes, , [ - AM_ICONV_LINK - ]) - dnl Search for libintl and define LIBINTL, LTLIBINTL and INCINTL - dnl accordingly. Don't use AC_LIB_LINKFLAGS_BODY([intl],[iconv]) - dnl because that would add "-liconv" to LIBINTL and LTLIBINTL - dnl even if libiconv doesn't exist. - AC_LIB_LINKFLAGS_BODY([intl]) - AC_CACHE_CHECK([for GNU gettext in libintl], - [$gt_func_gnugettext_libintl], - [gt_save_CPPFLAGS="$CPPFLAGS" - CPPFLAGS="$CPPFLAGS $INCINTL" - gt_save_LIBS="$LIBS" - LIBS="$LIBS $LIBINTL" - dnl Now see whether libintl exists and does not depend on libiconv. - AC_TRY_LINK([#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern -#ifdef __cplusplus -"C" -#endif -const char *_nl_expand_alias (const char *);], - [bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_expand_alias ("")], - [eval "$gt_func_gnugettext_libintl=yes"], - [eval "$gt_func_gnugettext_libintl=no"]) - dnl Now see whether libintl exists and depends on libiconv. - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" != yes; } && test -n "$LIBICONV"; then - LIBS="$LIBS $LIBICONV" - AC_TRY_LINK([#include <libintl.h> -$gt_revision_test_code -extern int _nl_msg_cat_cntr; -extern -#ifdef __cplusplus -"C" -#endif -const char *_nl_expand_alias (const char *);], - [bindtextdomain ("", ""); -return * gettext ("")$gt_expression_test_code + _nl_msg_cat_cntr + *_nl_expand_alias ("")], - [LIBINTL="$LIBINTL $LIBICONV" - LTLIBINTL="$LTLIBINTL $LTLIBICONV" - eval "$gt_func_gnugettext_libintl=yes" - ]) - fi - CPPFLAGS="$gt_save_CPPFLAGS" - LIBS="$gt_save_LIBS"]) - fi - - dnl If an already present or preinstalled GNU gettext() is found, - dnl use it. But if this macro is used in GNU gettext, and GNU - dnl gettext is already preinstalled in libintl, we update this - dnl libintl. (Cf. the install rule in intl/Makefile.in.) - if { eval "gt_val=\$$gt_func_gnugettext_libc"; test "$gt_val" = "yes"; } \ - || { { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; } \ - && test "$PACKAGE" != gettext-runtime \ - && test "$PACKAGE" != gettext-tools; }; then - gt_use_preinstalled_gnugettext=yes - else - dnl Reset the values set by searching for libintl. - LIBINTL= - LTLIBINTL= - INCINTL= - fi - - ifelse(gt_included_intl, yes, [ - if test "$gt_use_preinstalled_gnugettext" != "yes"; then - dnl GNU gettext is not found in the C library. - dnl Fall back on included GNU gettext library. - nls_cv_use_gnu_gettext=yes - fi - fi - - if test "$nls_cv_use_gnu_gettext" = "yes"; then - dnl Mark actions used to generate GNU NLS library. - BUILD_INCLUDED_LIBINTL=yes - USE_INCLUDED_LIBINTL=yes - LIBINTL="ifelse([$3],[],\${top_builddir}/intl,[$3])/libintl.[]gt_libtool_suffix_prefix[]a $LIBICONV $LIBTHREAD" - LTLIBINTL="ifelse([$3],[],\${top_builddir}/intl,[$3])/libintl.[]gt_libtool_suffix_prefix[]a $LTLIBICONV $LTLIBTHREAD" - LIBS=`echo " $LIBS " | sed -e 's/ -lintl / /' -e 's/^ //' -e 's/ $//'` - fi - - CATOBJEXT= - if test "$gt_use_preinstalled_gnugettext" = "yes" \ - || test "$nls_cv_use_gnu_gettext" = "yes"; then - dnl Mark actions to use GNU gettext tools. - CATOBJEXT=.gmo - fi - ]) - - if test -n "$INTL_MACOSX_LIBS"; then - if test "$gt_use_preinstalled_gnugettext" = "yes" \ - || test "$nls_cv_use_gnu_gettext" = "yes"; then - dnl Some extra flags are needed during linking. - LIBINTL="$LIBINTL $INTL_MACOSX_LIBS" - LTLIBINTL="$LTLIBINTL $INTL_MACOSX_LIBS" - fi - fi - - if test "$gt_use_preinstalled_gnugettext" = "yes" \ - || test "$nls_cv_use_gnu_gettext" = "yes"; then - AC_DEFINE([ENABLE_NLS], [1], - [Define to 1 if translation of program messages to the user's native language - is requested.]) - else - USE_NLS=no - fi - fi - - AC_MSG_CHECKING([whether to use NLS]) - AC_MSG_RESULT([$USE_NLS]) - if test "$USE_NLS" = "yes"; then - AC_MSG_CHECKING([where the gettext function comes from]) - if test "$gt_use_preinstalled_gnugettext" = "yes"; then - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; }; then - gt_source="external libintl" - else - gt_source="libc" - fi - else - gt_source="included intl directory" - fi - AC_MSG_RESULT([$gt_source]) - fi - - if test "$USE_NLS" = "yes"; then - - if test "$gt_use_preinstalled_gnugettext" = "yes"; then - if { eval "gt_val=\$$gt_func_gnugettext_libintl"; test "$gt_val" = "yes"; }; then - AC_MSG_CHECKING([how to link with libintl]) - AC_MSG_RESULT([$LIBINTL]) - AC_LIB_APPENDTOVAR([CPPFLAGS], [$INCINTL]) - fi - - dnl For backward compatibility. Some packages may be using this. - AC_DEFINE([HAVE_GETTEXT], [1], - [Define if the GNU gettext() function is already present or preinstalled.]) - AC_DEFINE([HAVE_DCGETTEXT], [1], - [Define if the GNU dcgettext() function is already present or preinstalled.]) - fi - - dnl We need to process the po/ directory. - POSUB=po - fi - - ifelse(gt_included_intl, yes, [ - dnl If this is used in GNU gettext we have to set BUILD_INCLUDED_LIBINTL - dnl to 'yes' because some of the testsuite requires it. - if test "$PACKAGE" = gettext-runtime || test "$PACKAGE" = gettext-tools; then - BUILD_INCLUDED_LIBINTL=yes - fi - - dnl Make all variables we use known to autoconf. - AC_SUBST([BUILD_INCLUDED_LIBINTL]) - AC_SUBST([USE_INCLUDED_LIBINTL]) - AC_SUBST([CATOBJEXT]) - - dnl For backward compatibility. Some configure.ins may be using this. - nls_cv_header_intl= - nls_cv_header_libgt= - - dnl For backward compatibility. Some Makefiles may be using this. - DATADIRNAME=share - AC_SUBST([DATADIRNAME]) - - dnl For backward compatibility. Some Makefiles may be using this. - INSTOBJEXT=.mo - AC_SUBST([INSTOBJEXT]) - - dnl For backward compatibility. Some Makefiles may be using this. - GENCAT=gencat - AC_SUBST([GENCAT]) - - dnl For backward compatibility. Some Makefiles may be using this. - INTLOBJS= - if test "$USE_INCLUDED_LIBINTL" = yes; then - INTLOBJS="\$(GETTOBJS)" - fi - AC_SUBST([INTLOBJS]) - - dnl Enable libtool support if the surrounding package wishes it. - INTL_LIBTOOL_SUFFIX_PREFIX=gt_libtool_suffix_prefix - AC_SUBST([INTL_LIBTOOL_SUFFIX_PREFIX]) - ]) - - dnl For backward compatibility. Some Makefiles may be using this. - INTLLIBS="$LIBINTL" - AC_SUBST([INTLLIBS]) - - dnl Make all documented variables known to autoconf. - AC_SUBST([LIBINTL]) - AC_SUBST([LTLIBINTL]) - AC_SUBST([POSUB]) -]) - - -dnl gt_NEEDS_INIT ensures that the gt_needs variable is initialized. -m4_define([gt_NEEDS_INIT], -[ - m4_divert_text([DEFAULTS], [gt_needs=]) - m4_define([gt_NEEDS_INIT], []) -]) - - -dnl Usage: AM_GNU_GETTEXT_NEED([NEEDSYMBOL]) -AC_DEFUN([AM_GNU_GETTEXT_NEED], -[ - m4_divert_text([INIT_PREPARE], [gt_needs="$gt_needs $1"]) -]) - - -dnl Usage: AM_GNU_GETTEXT_VERSION([gettext-version]) -AC_DEFUN([AM_GNU_GETTEXT_VERSION], []) diff --git a/extension/m4/iconv.m4 b/extension/m4/iconv.m4 deleted file mode 100644 index e2041b9b..00000000 --- a/extension/m4/iconv.m4 +++ /dev/null @@ -1,214 +0,0 @@ -# iconv.m4 serial 11 (gettext-0.18.1) -dnl Copyright (C) 2000-2002, 2007-2010 Free Software Foundation, Inc. -dnl This file is free software; the Free Software Foundation -dnl gives unlimited permission to copy and/or distribute it, -dnl with or without modifications, as long as this notice is preserved. - -dnl From Bruno Haible. - -AC_DEFUN([AM_ICONV_LINKFLAGS_BODY], -[ - dnl Prerequisites of AC_LIB_LINKFLAGS_BODY. - AC_REQUIRE([AC_LIB_PREPARE_PREFIX]) - AC_REQUIRE([AC_LIB_RPATH]) - - dnl Search for libiconv and define LIBICONV, LTLIBICONV and INCICONV - dnl accordingly. - AC_LIB_LINKFLAGS_BODY([iconv]) -]) - -AC_DEFUN([AM_ICONV_LINK], -[ - dnl Some systems have iconv in libc, some have it in libiconv (OSF/1 and - dnl those with the standalone portable GNU libiconv installed). - AC_REQUIRE([AC_CANONICAL_HOST]) dnl for cross-compiles - - dnl Search for libiconv and define LIBICONV, LTLIBICONV and INCICONV - dnl accordingly. - AC_REQUIRE([AM_ICONV_LINKFLAGS_BODY]) - - dnl Add $INCICONV to CPPFLAGS before performing the following checks, - dnl because if the user has installed libiconv and not disabled its use - dnl via --without-libiconv-prefix, he wants to use it. The first - dnl AC_TRY_LINK will then fail, the second AC_TRY_LINK will succeed. - am_save_CPPFLAGS="$CPPFLAGS" - AC_LIB_APPENDTOVAR([CPPFLAGS], [$INCICONV]) - - AC_CACHE_CHECK([for iconv], [am_cv_func_iconv], [ - am_cv_func_iconv="no, consider installing GNU libiconv" - am_cv_lib_iconv=no - AC_TRY_LINK([#include <stdlib.h> -#include <iconv.h>], - [iconv_t cd = iconv_open("",""); - iconv(cd,NULL,NULL,NULL,NULL); - iconv_close(cd);], - [am_cv_func_iconv=yes]) - if test "$am_cv_func_iconv" != yes; then - am_save_LIBS="$LIBS" - LIBS="$LIBS $LIBICONV" - AC_TRY_LINK([#include <stdlib.h> -#include <iconv.h>], - [iconv_t cd = iconv_open("",""); - iconv(cd,NULL,NULL,NULL,NULL); - iconv_close(cd);], - [am_cv_lib_iconv=yes] - [am_cv_func_iconv=yes]) - LIBS="$am_save_LIBS" - fi - ]) - if test "$am_cv_func_iconv" = yes; then - AC_CACHE_CHECK([for working iconv], [am_cv_func_iconv_works], [ - dnl This tests against bugs in AIX 5.1, HP-UX 11.11, Solaris 10. - am_save_LIBS="$LIBS" - if test $am_cv_lib_iconv = yes; then - LIBS="$LIBS $LIBICONV" - fi - AC_TRY_RUN([ -#include <iconv.h> -#include <string.h> -int main () -{ - /* Test against AIX 5.1 bug: Failures are not distinguishable from successful - returns. */ - { - iconv_t cd_utf8_to_88591 = iconv_open ("ISO8859-1", "UTF-8"); - if (cd_utf8_to_88591 != (iconv_t)(-1)) - { - static const char input[] = "\342\202\254"; /* EURO SIGN */ - char buf[10]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_utf8_to_88591, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if (res == 0) - return 1; - } - } - /* Test against Solaris 10 bug: Failures are not distinguishable from - successful returns. */ - { - iconv_t cd_ascii_to_88591 = iconv_open ("ISO8859-1", "646"); - if (cd_ascii_to_88591 != (iconv_t)(-1)) - { - static const char input[] = "\263"; - char buf[10]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_ascii_to_88591, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if (res == 0) - return 1; - } - } -#if 0 /* This bug could be worked around by the caller. */ - /* Test against HP-UX 11.11 bug: Positive return value instead of 0. */ - { - iconv_t cd_88591_to_utf8 = iconv_open ("utf8", "iso88591"); - if (cd_88591_to_utf8 != (iconv_t)(-1)) - { - static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; - char buf[50]; - const char *inptr = input; - size_t inbytesleft = strlen (input); - char *outptr = buf; - size_t outbytesleft = sizeof (buf); - size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, - &outptr, &outbytesleft); - if ((int)res > 0) - return 1; - } - } -#endif - /* Test against HP-UX 11.11 bug: No converter from EUC-JP to UTF-8 is - provided. */ - if (/* Try standardized names. */ - iconv_open ("UTF-8", "EUC-JP") == (iconv_t)(-1) - /* Try IRIX, OSF/1 names. */ - && iconv_open ("UTF-8", "eucJP") == (iconv_t)(-1) - /* Try AIX names. */ - && iconv_open ("UTF-8", "IBM-eucJP") == (iconv_t)(-1) - /* Try HP-UX names. */ - && iconv_open ("utf8", "eucJP") == (iconv_t)(-1)) - return 1; - return 0; -}], [am_cv_func_iconv_works=yes], [am_cv_func_iconv_works=no], - [case "$host_os" in - aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; - *) am_cv_func_iconv_works="guessing yes" ;; - esac]) - LIBS="$am_save_LIBS" - ]) - case "$am_cv_func_iconv_works" in - *no) am_func_iconv=no am_cv_lib_iconv=no ;; - *) am_func_iconv=yes ;; - esac - else - am_func_iconv=no am_cv_lib_iconv=no - fi - if test "$am_func_iconv" = yes; then - AC_DEFINE([HAVE_ICONV], [1], - [Define if you have the iconv() function and it works.]) - fi - if test "$am_cv_lib_iconv" = yes; then - AC_MSG_CHECKING([how to link with libiconv]) - AC_MSG_RESULT([$LIBICONV]) - else - dnl If $LIBICONV didn't lead to a usable library, we don't need $INCICONV - dnl either. - CPPFLAGS="$am_save_CPPFLAGS" - LIBICONV= - LTLIBICONV= - fi - AC_SUBST([LIBICONV]) - AC_SUBST([LTLIBICONV]) -]) - -dnl Define AM_ICONV using AC_DEFUN_ONCE for Autoconf >= 2.64, in order to -dnl avoid warnings like -dnl "warning: AC_REQUIRE: `AM_ICONV' was expanded before it was required". -dnl This is tricky because of the way 'aclocal' is implemented: -dnl - It requires defining an auxiliary macro whose name ends in AC_DEFUN. -dnl Otherwise aclocal's initial scan pass would miss the macro definition. -dnl - It requires a line break inside the AC_DEFUN_ONCE and AC_DEFUN expansions. -dnl Otherwise aclocal would emit many "Use of uninitialized value $1" -dnl warnings. -m4_define([gl_iconv_AC_DEFUN], - m4_version_prereq([2.64], - [[AC_DEFUN_ONCE( - [$1], [$2])]], - [[AC_DEFUN( - [$1], [$2])]])) -gl_iconv_AC_DEFUN([AM_ICONV], -[ - AM_ICONV_LINK - if test "$am_cv_func_iconv" = yes; then - AC_MSG_CHECKING([for iconv declaration]) - AC_CACHE_VAL([am_cv_proto_iconv], [ - AC_TRY_COMPILE([ -#include <stdlib.h> -#include <iconv.h> -extern -#ifdef __cplusplus -"C" -#endif -#if defined(__STDC__) || defined(__cplusplus) -size_t iconv (iconv_t cd, char * *inbuf, size_t *inbytesleft, char * *outbuf, size_t *outbytesleft); -#else -size_t iconv(); -#endif -], [], [am_cv_proto_iconv_arg1=""], [am_cv_proto_iconv_arg1="const"]) - am_cv_proto_iconv="extern size_t iconv (iconv_t cd, $am_cv_proto_iconv_arg1 char * *inbuf, size_t *inbytesleft, char * *outbuf, size_t *outbytesleft);"]) - am_cv_proto_iconv=`echo "[$]am_cv_proto_iconv" | tr -s ' ' | sed -e 's/( /(/'` - AC_MSG_RESULT([ - $am_cv_proto_iconv]) - AC_DEFINE_UNQUOTED([ICONV_CONST], [$am_cv_proto_iconv_arg1], - [Define as const if the declaration of iconv() needs const.]) - fi -]) diff --git a/extension/m4/intlmacosx.m4 b/extension/m4/intlmacosx.m4 deleted file mode 100644 index dd910259..00000000 --- a/extension/m4/intlmacosx.m4 +++ /dev/null @@ -1,51 +0,0 @@ -# intlmacosx.m4 serial 3 (gettext-0.18) -dnl Copyright (C) 2004-2010 Free Software Foundation, Inc. -dnl This file is free software; the Free Software Foundation -dnl gives unlimited permission to copy and/or distribute it, -dnl with or without modifications, as long as this notice is preserved. -dnl -dnl This file can can be used in projects which are not available under -dnl the GNU General Public License or the GNU Library General Public -dnl License but which still want to provide support for the GNU gettext -dnl functionality. -dnl Please note that the actual code of the GNU gettext library is covered -dnl by the GNU Library General Public License, and the rest of the GNU -dnl gettext package package is covered by the GNU General Public License. -dnl They are *not* in the public domain. - -dnl Checks for special options needed on MacOS X. -dnl Defines INTL_MACOSX_LIBS. -AC_DEFUN([gt_INTL_MACOSX], -[ - dnl Check for API introduced in MacOS X 10.2. - AC_CACHE_CHECK([for CFPreferencesCopyAppValue], - [gt_cv_func_CFPreferencesCopyAppValue], - [gt_save_LIBS="$LIBS" - LIBS="$LIBS -Wl,-framework -Wl,CoreFoundation" - AC_TRY_LINK([#include <CoreFoundation/CFPreferences.h>], - [CFPreferencesCopyAppValue(NULL, NULL)], - [gt_cv_func_CFPreferencesCopyAppValue=yes], - [gt_cv_func_CFPreferencesCopyAppValue=no]) - LIBS="$gt_save_LIBS"]) - if test $gt_cv_func_CFPreferencesCopyAppValue = yes; then - AC_DEFINE([HAVE_CFPREFERENCESCOPYAPPVALUE], [1], - [Define to 1 if you have the MacOS X function CFPreferencesCopyAppValue in the CoreFoundation framework.]) - fi - dnl Check for API introduced in MacOS X 10.3. - AC_CACHE_CHECK([for CFLocaleCopyCurrent], [gt_cv_func_CFLocaleCopyCurrent], - [gt_save_LIBS="$LIBS" - LIBS="$LIBS -Wl,-framework -Wl,CoreFoundation" - AC_TRY_LINK([#include <CoreFoundation/CFLocale.h>], [CFLocaleCopyCurrent();], - [gt_cv_func_CFLocaleCopyCurrent=yes], - [gt_cv_func_CFLocaleCopyCurrent=no]) - LIBS="$gt_save_LIBS"]) - if test $gt_cv_func_CFLocaleCopyCurrent = yes; then - AC_DEFINE([HAVE_CFLOCALECOPYCURRENT], [1], - [Define to 1 if you have the MacOS X function CFLocaleCopyCurrent in the CoreFoundation framework.]) - fi - INTL_MACOSX_LIBS= - if test $gt_cv_func_CFPreferencesCopyAppValue = yes || test $gt_cv_func_CFLocaleCopyCurrent = yes; then - INTL_MACOSX_LIBS="-Wl,-framework -Wl,CoreFoundation" - fi - AC_SUBST([INTL_MACOSX_LIBS]) -]) diff --git a/extension/m4/libtool.m4 b/extension/m4/libtool.m4 index 068f0d8b..f796d7bc 100644 --- a/extension/m4/libtool.m4 +++ b/extension/m4/libtool.m4 @@ -1,6 +1,6 @@ # libtool.m4 - Configure libtool for the host system. -*-Autoconf-*- # -# Copyright (C) 1996-2001, 2003-2014 Free Software Foundation, Inc. +# Copyright (C) 1996-2001, 2003-2015 Free Software Foundation, Inc. # Written by Gordon Matzigkeit, 1996 # # This file is free software; the Free Software Foundation gives @@ -103,19 +103,36 @@ dnl AC_DEFUN([AC_PROG_LIBTOOL], []) dnl AC_DEFUN([AM_PROG_LIBTOOL], []) +# _LT_PREPARE_CC_BASENAME +# ----------------------- +m4_defun([_LT_PREPARE_CC_BASENAME], [ +# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +func_cc_basename () +{ + for cc_temp in @S|@*""; do + case $cc_temp in + compile | *[[\\/]]compile | ccache | *[[\\/]]ccache ) ;; + distcc | *[[\\/]]distcc | purify | *[[\\/]]purify ) ;; + \-*) ;; + *) break;; + esac + done + func_cc_basename_result=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +} +])# _LT_PREPARE_CC_BASENAME + + # _LT_CC_BASENAME(CC) # ------------------- -# Calculate cc_basename. Skip known compiler wrappers and cross-prefix. +# It would be clearer to call AC_REQUIREs from _LT_PREPARE_CC_BASENAME, +# but that macro is also expanded into generated libtool script, which +# arranges for $SED and $ECHO to be set by different means. m4_defun([_LT_CC_BASENAME], -[for cc_temp in $1""; do - case $cc_temp in - compile | *[[\\/]]compile | ccache | *[[\\/]]ccache ) ;; - distcc | *[[\\/]]distcc | purify | *[[\\/]]purify ) ;; - \-*) ;; - *) break;; - esac -done -cc_basename=`$ECHO "$cc_temp" | $SED "s%.*/%%; s%^$host_alias-%%"` +[m4_require([_LT_PREPARE_CC_BASENAME])dnl +AC_REQUIRE([_LT_DECL_SED])dnl +AC_REQUIRE([_LT_PROG_ECHO_BACKSLASH])dnl +func_cc_basename $1 +cc_basename=$func_cc_basename_result ]) @@ -720,6 +737,9 @@ _LT_CONFIG_SAVE_COMMANDS([ _LT_COPYING _LT_LIBTOOL_TAGS +# Configured defaults for sys_lib_dlsearch_path munging. +: \${LT_SYS_LIBRARY_PATH="$LT_SYS_LIBRARY_PATH"} + # ### BEGIN LIBTOOL CONFIG _LT_LIBTOOL_CONFIG_VARS _LT_LIBTOOL_TAG_VARS @@ -727,6 +747,16 @@ _LT_LIBTOOL_TAG_VARS _LT_EOF + cat <<'_LT_EOF' >> "$cfgfile" +## -------------------------------------- ## +## Shell functions shared with configure. ## +## -------------------------------------- ## + +_LT_PREPARE_MUNGE_PATH_LIST +_LT_PREPARE_CC_BASENAME + +_LT_EOF + case $host_os in aix3*) cat <<\_LT_EOF >> "$cfgfile" @@ -1840,7 +1870,7 @@ else # endif #endif -/* When -fvisbility=hidden is used, assume the code has been annotated +/* When -fvisibility=hidden is used, assume the code has been annotated correspondingly for the symbols needed. */ #if defined __GNUC__ && (((__GNUC__ == 3) && (__GNUC_MINOR__ >= 3)) || (__GNUC__ > 3)) int fnord () __attribute__((visibility("default"))); @@ -2202,6 +2232,47 @@ _LT_DECL([], [striplib], [1]) ])# _LT_CMD_STRIPLIB +# _LT_PREPARE_MUNGE_PATH_LIST +# --------------------------- +# Make sure func_munge_path_list() is defined correctly. +m4_defun([_LT_PREPARE_MUNGE_PATH_LIST], +[[# func_munge_path_list VARIABLE PATH +# ----------------------------------- +# VARIABLE is name of variable containing _space_ separated list of +# directories to be munged by the contents of PATH, which is string +# having a format: +# "DIR[:DIR]:" +# string "DIR[ DIR]" will be prepended to VARIABLE +# ":DIR[:DIR]" +# string "DIR[ DIR]" will be appended to VARIABLE +# "DIRP[:DIRP]::[DIRA:]DIRA" +# string "DIRP[ DIRP]" will be prepended to VARIABLE and string +# "DIRA[ DIRA]" will be appended to VARIABLE +# "DIR[:DIR]" +# VARIABLE will be replaced by "DIR[ DIR]" +func_munge_path_list () +{ + case x@S|@2 in + x) + ;; + *:) + eval @S|@1=\"`$ECHO @S|@2 | $SED 's/:/ /g'` \$@S|@1\" + ;; + x:*) + eval @S|@1=\"\@S|@@S|@1 `$ECHO @S|@2 | $SED 's/:/ /g'`\" + ;; + *::*) + eval @S|@1=\"\@S|@@S|@1\ `$ECHO @S|@2 | $SED -e 's/.*:://' -e 's/:/ /g'`\" + eval @S|@1=\"`$ECHO @S|@2 | $SED -e 's/::.*//' -e 's/:/ /g'`\ \@S|@@S|@1\" + ;; + *) + eval @S|@1=\"`$ECHO @S|@2 | $SED 's/:/ /g'`\" + ;; + esac +} +]])# _LT_PREPARE_PATH_LIST + + # _LT_SYS_DYNAMIC_LINKER([TAG]) # ----------------------------- # PORTME Fill in your ld.so characteristics @@ -2212,6 +2283,7 @@ m4_require([_LT_FILEUTILS_DEFAULTS])dnl m4_require([_LT_DECL_OBJDUMP])dnl m4_require([_LT_DECL_SED])dnl m4_require([_LT_CHECK_SHELL_FEATURES])dnl +m4_require([_LT_PREPARE_MUNGE_PATH_LIST])dnl AC_MSG_CHECKING([dynamic linker characteristics]) m4_if([$1], [], [ @@ -2306,6 +2378,9 @@ hardcode_into_libs=no # flags to be left without arguments need_version=unknown +AC_ARG_VAR([LT_SYS_LIBRARY_PATH], +[User-defined run-time library search path.]) + case $host_os in aix3*) version_type=linux # correct to gnu/linux during the next big refactor @@ -2342,20 +2417,70 @@ aix[[4-9]]*) fi ;; esac + # Using Import Files as archive members, it is possible to support + # filename-based versioning of shared library archives on AIX. While + # this would work for both with and without runtime linking, it will + # prevent static linking of such archives. So we do filename-based + # shared library versioning with .so extension only, which is used + # when both runtime linking and shared linking is enabled. + # Unfortunately, runtime linking may impact performance, so we do + # not want this to be the default eventually. Also, we use the + # versioned .so libs for executables only if there is the -brtl + # linker flag in LDFLAGS as well, or --with-aix-soname=svr4 only. + # To allow for filename-based versioning support, we need to create + # libNAME.so.V as an archive file, containing: + # *) an Import File, referring to the versioned filename of the + # archive as well as the shared archive member, telling the + # bitwidth (32 or 64) of that shared object, and providing the + # list of exported symbols of that shared object, eventually + # decorated with the 'weak' keyword + # *) the shared object with the F_LOADONLY flag set, to really avoid + # it being seen by the linker. + # At run time we better use the real file rather than another symlink, + # but for link time we create the symlink libNAME.so -> libNAME.so.V + + case $with_aix_soname,$aix_use_runtimelinking in # AIX (on Power*) has no versioning support, so currently we cannot hardcode correct # soname into executable. Probably we can add versioning support to # collect2, so additional links can be useful in future. - if test yes = "$aix_use_runtimelinking"; then + aix,yes) # traditional libtool + dynamic_linker='AIX unversionable lib.so' # If using run time linking (on AIX 4.2 or later) use lib<name>.so # instead of lib<name>.a to let people know that these are not # typical AIX shared libraries. library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' - else + ;; + aix,no) # traditional AIX only + dynamic_linker='AIX lib.a[(]lib.so.V[)]' # We preserve .a as extension for shared libraries through AIX4.2 # and later when we are not doing run time linking. library_names_spec='$libname$release.a $libname.a' soname_spec='$libname$release$shared_ext$major' - fi + ;; + svr4,*) # full svr4 only + dynamic_linker="AIX lib.so.V[(]$shared_archive_member_spec.o[)]" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,yes) # both, prefer svr4 + dynamic_linker="AIX lib.so.V[(]$shared_archive_member_spec.o[)], lib.a[(]lib.so.V[)]" + library_names_spec='$libname$release$shared_ext$major $libname$shared_ext' + # unpreferred sharedlib libNAME.a needs extra handling + postinstall_cmds='test -n "$linkname" || linkname="$realname"~func_stripname "" ".so" "$linkname"~$install_shared_prog "$dir/$func_stripname_result.$libext" "$destdir/$func_stripname_result.$libext"~test -z "$tstripme" || test -z "$striplib" || $striplib "$destdir/$func_stripname_result.$libext"' + postuninstall_cmds='for n in $library_names $old_library; do :; done~func_stripname "" ".so" "$n"~test "$func_stripname_result" = "$n" || func_append rmfiles " $odir/$func_stripname_result.$libext"' + # We do not specify a path in Import Files, so LIBPATH fires. + shlibpath_overrides_runpath=yes + ;; + *,no) # both, prefer aix + dynamic_linker="AIX lib.a[(]lib.so.V[)], lib.so.V[(]$shared_archive_member_spec.o[)]" + library_names_spec='$libname$release.a $libname.a' + soname_spec='$libname$release$shared_ext$major' + # unpreferred sharedlib libNAME.so.V and symlink libNAME.so need extra handling + postinstall_cmds='test -z "$dlname" || $install_shared_prog $dir/$dlname $destdir/$dlname~test -z "$tstripme" || test -z "$striplib" || $striplib $destdir/$dlname~test -n "$linkname" || linkname=$realname~func_stripname "" ".a" "$linkname"~(cd "$destdir" && $LN_S -f $dlname $func_stripname_result.so)' + postuninstall_cmds='test -z "$dlname" || func_append rmfiles " $odir/$dlname"~for n in $old_library $library_names; do :; done~func_stripname "" ".a" "$n"~func_append rmfiles " $odir/$func_stripname_result.so"' + ;; + esac shlibpath_var=LIBPATH fi ;; @@ -2543,7 +2668,8 @@ freebsd* | dragonfly*) version_type=freebsd-$objformat case $version_type in freebsd-elf*) - library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext $libname$shared_ext' + library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext$major $libname$shared_ext' + soname_spec='$libname$release$shared_ext$major' need_version=no need_lib_prefix=no ;; @@ -2603,10 +2729,11 @@ hpux9* | hpux10* | hpux11*) soname_spec='$libname$release$shared_ext$major' if test 32 = "$HPUX_IA64_MODE"; then sys_lib_search_path_spec="/usr/lib/hpux32 /usr/local/lib/hpux32 /usr/local/lib" + sys_lib_dlsearch_path_spec=/usr/lib/hpux32 else sys_lib_search_path_spec="/usr/lib/hpux64 /usr/local/lib/hpux64" + sys_lib_dlsearch_path_spec=/usr/lib/hpux64 fi - sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec ;; hppa*64*) shrext_cmds='.sl' @@ -2739,7 +2866,12 @@ linux* | k*bsd*-gnu | kopensolaris*-gnu | gnu*) # before this can be enabled. hardcode_into_libs=yes - # Append ld.so.conf contents to the search path + # Ideally, we could use ldconfig to report *all* directores which are + # searched for libraries, however this is still not possible. Aside from not + # being certain /sbin/ldconfig is available, command + # 'ldconfig -N -X -v | grep ^/' on 64bit Fedora does not report /usr/lib64, + # even though it is searched at run-time. Try to do the best guess by + # appending ld.so.conf contents (and includes) to the search path. if test -f /etc/ld.so.conf; then lt_ld_extra=`awk '/^include / { system(sprintf("cd /etc; cat %s 2>/dev/null", \[$]2)); skip = 1; } { if (!skip) print \[$]0; skip = 0; }' < /etc/ld.so.conf | $SED -e 's/#.*//;/^[ ]*hwcap[ ]/d;s/[:, ]/ /g;s/=[^=]*$//;s/=[^= ]* / /g;s/"//g;/^$/d' | tr '\n' ' '` sys_lib_dlsearch_path_spec="/lib /usr/lib $lt_ld_extra" @@ -2808,11 +2940,32 @@ openbsd* | bitrig*) os2*) libname_spec='$name' + version_type=windows shrext_cmds=.dll + need_version=no need_lib_prefix=no - library_names_spec='$libname$shared_ext $libname.a' + # OS/2 can only load a DLL with a base name of 8 characters or less. + soname_spec='`test -n "$os2dllname" && libname="$os2dllname"; + v=$($ECHO $release$versuffix | tr -d .-); + n=$($ECHO $libname | cut -b -$((8 - ${#v})) | tr . _); + $ECHO $n$v`$shared_ext' + library_names_spec='${libname}_dll.$libext' dynamic_linker='OS/2 ld.exe' - shlibpath_var=LIBPATH + shlibpath_var=BEGINLIBPATH + sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" + sys_lib_dlsearch_path_spec=$sys_lib_search_path_spec + postinstall_cmds='base_file=`basename \$file`~ + dlpath=`$SHELL 2>&1 -c '\''. $dir/'\''\$base_file'\''i; $ECHO \$dlname'\''`~ + dldir=$destdir/`dirname \$dlpath`~ + test -d \$dldir || mkdir -p \$dldir~ + $install_prog $dir/$dlname \$dldir/$dlname~ + chmod a+x \$dldir/$dlname~ + if test -n '\''$stripme'\'' && test -n '\''$striplib'\''; then + eval '\''$striplib \$dldir/$dlname'\'' || exit \$?; + fi' + postuninstall_cmds='dldll=`$SHELL 2>&1 -c '\''. $file; $ECHO \$dlname'\''`~ + dlpath=$dir/\$dldll~ + $RM \$dlpath' ;; osf3* | osf4* | osf5*) @@ -2888,7 +3041,7 @@ sysv4*MP*) ;; sysv5* | sco3.2v5* | sco5v6* | unixware* | OpenUNIX* | sysv4*uw2*) - version_type=freebsd-elf + version_type=sco need_lib_prefix=no need_version=no library_names_spec='$libname$release$shared_ext$versuffix $libname$release$shared_ext $libname$shared_ext' @@ -2942,10 +3095,18 @@ fi if test set = "${lt_cv_sys_lib_search_path_spec+set}"; then sys_lib_search_path_spec=$lt_cv_sys_lib_search_path_spec fi + if test set = "${lt_cv_sys_lib_dlsearch_path_spec+set}"; then sys_lib_dlsearch_path_spec=$lt_cv_sys_lib_dlsearch_path_spec fi +# lt_cv_sys_lib... is unaugmented for libtool script decls... +lt_cv_sys_lib_dlsearch_path_spec=$sys_lib_dlsearch_path_spec + +# ..but sys_lib_... needs LT_SYS_LIBRARY_PATH munging for +# LT_SYS_DLSEARCH_PATH macro in ltdl.m4 to work with the correct paths: +func_munge_path_list sys_lib_dlsearch_path_spec "$LT_SYS_LIBRARY_PATH" + _LT_DECL([], [variables_saved_for_relink], [1], [Variables whose values should be saved in libtool wrapper scripts and restored at link time]) @@ -2978,7 +3139,7 @@ _LT_DECL([], [hardcode_into_libs], [0], [Whether we should hardcode library paths into libraries]) _LT_DECL([], [sys_lib_search_path_spec], [2], [Compile-time system search path for libraries]) -_LT_DECL([], [sys_lib_dlsearch_path_spec], [2], +_LT_DECL([sys_lib_dlsearch_path_spec], [lt_cv_sys_lib_dlsearch_path_spec], [2], [Run-time system search path for libraries]) ])# _LT_SYS_DYNAMIC_LINKER @@ -3452,6 +3613,9 @@ sysv4 | sysv4.3*) tpf*) lt_cv_deplibs_check_method=pass_all ;; +os2*) + lt_cv_deplibs_check_method=pass_all + ;; esac ]) @@ -4060,6 +4224,11 @@ m4_if([$1], [CXX], [ # (--disable-auto-import) libraries m4_if([$1], [GCJ], [], [_LT_TAGVAR(lt_prog_compiler_pic, $1)='-DDLL_EXPORT']) + case $host_os in + os2*) + _LT_TAGVAR(lt_prog_compiler_static, $1)='$wl-static' + ;; + esac ;; darwin* | rhapsody*) # PIC is the default on this platform @@ -4379,6 +4548,11 @@ m4_if([$1], [CXX], [ # (--disable-auto-import) libraries m4_if([$1], [GCJ], [], [_LT_TAGVAR(lt_prog_compiler_pic, $1)='-DDLL_EXPORT']) + case $host_os in + os2*) + _LT_TAGVAR(lt_prog_compiler_static, $1)='$wl-static' + ;; + esac ;; darwin* | rhapsody*) @@ -4476,6 +4650,11 @@ m4_if([$1], [CXX], [ # built for inclusion in a dll (and should export symbols for example). m4_if([$1], [GCJ], [], [_LT_TAGVAR(lt_prog_compiler_pic, $1)='-DDLL_EXPORT']) + case $host_os in + os2*) + _LT_TAGVAR(lt_prog_compiler_static, $1)='$wl-static' + ;; + esac ;; hpux9* | hpux10* | hpux11*) @@ -4725,13 +4904,17 @@ m4_if([$1], [CXX], [ case $host_os in aix[[4-9]]*) # If we're using GNU nm, then we don't want the "-C" option. - # -C means demangle to AIX nm, but means don't demangle with GNU nm - # Also, AIX nm treats weak defined symbols like other global defined - # symbols, whereas GNU nm marks them as "W". + # -C means demangle to GNU nm, but means don't demangle to AIX nm. + # Without the "-l" option, or with the "-B" option, AIX nm treats + # weak defined symbols like other global defined symbols, whereas + # GNU nm marks them as "W". + # While the 'weak' keyword is ignored in the Export File, we need + # it in the Import File for the 'aix-soname' feature, so we have + # to replace the "-B" option with "-P" for AIX nm. if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then - _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols' else - _LT_TAGVAR(export_symbols_cmds, $1)='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B")) && ([substr](\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + _LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols' fi ;; pw32*) @@ -4942,6 +5125,34 @@ _LT_EOF _LT_TAGVAR(link_all_deplibs, $1)=yes ;; + os2*) + _LT_TAGVAR(hardcode_libdir_flag_spec, $1)='-L$libdir' + _LT_TAGVAR(hardcode_minus_L, $1)=yes + _LT_TAGVAR(allow_undefined_flag, $1)=unsupported + shrext_cmds=.dll + _LT_TAGVAR(archive_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(archive_expsym_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + _LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes + ;; + interix[[3-9]]*) _LT_TAGVAR(hardcode_direct, $1)=no _LT_TAGVAR(hardcode_shlibpath_var, $1)=no @@ -5015,6 +5226,9 @@ _LT_EOF fi case $cc_basename in + tcc*) + _LT_TAGVAR(export_dynamic_flag_spec, $1)='-rdynamic' + ;; xlf* | bgf* | bgxlf* | mpixlf*) # IBM XL Fortran 10.1 on PPC cannot create shared libs itself _LT_TAGVAR(whole_archive_flag_spec, $1)='--whole-archive$convenience --no-whole-archive' @@ -5144,19 +5358,35 @@ _LT_EOF no_entry_flag= else # If we're using GNU nm, then we don't want the "-C" option. - # -C means demangle to AIX nm, but means don't demangle with GNU nm - # Also, AIX nm treats weak defined symbols like other global - # defined symbols, whereas GNU nm marks them as "W". + # -C means demangle to GNU nm, but means don't demangle to AIX nm. + # Without the "-l" option, or with the "-B" option, AIX nm treats + # weak defined symbols like other global defined symbols, whereas + # GNU nm marks them as "W". + # While the 'weak' keyword is ignored in the Export File, we need + # it in the Import File for the 'aix-soname' feature, so we have + # to replace the "-B" option with "-P" for AIX nm. if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then - _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols' else - _LT_TAGVAR(export_symbols_cmds, $1)='$NM -BCpg $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B")) && ([substr](\$ 3,1,1) != ".")) { print \$ 3 } }'\'' | sort -u > $export_symbols' + _LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } else { print \$ 1 } } }'\'' | sort -u > $export_symbols' fi aix_use_runtimelinking=no # Test if we are trying to use run time linking or normal # AIX style linking. If -brtl is somewhere in LDFLAGS, we - # need to do runtime linking. + # have runtime linking enabled, and use it for executables. + # For shared libraries, we enable/disable runtime linking + # depending on the kind of the shared library created - + # when "with_aix_soname,aix_use_runtimelinking" is: + # "aix,no" lib.a(lib.so.V) shared, rtl:no, for executables + # "aix,yes" lib.so shared, rtl:yes, for executables + # lib.a static archive + # "both,no" lib.so.V(shr.o) shared, rtl:yes + # lib.a(lib.so.V) shared, rtl:no, for executables + # "both,yes" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a(lib.so.V) shared, rtl:no + # "svr4,*" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a static archive case $host_os in aix4.[[23]]|aix4.[[23]].*|aix[[5-9]]*) for ld_flag in $LDFLAGS; do if (test x-brtl = "x$ld_flag" || test x-Wl,-brtl = "x$ld_flag"); then @@ -5164,6 +5394,13 @@ _LT_EOF break fi done + if test svr4,no = "$with_aix_soname,$aix_use_runtimelinking"; then + # With aix-soname=svr4, we create the lib.so.V shared archives only, + # so we don't have lib.a shared libs to link our executables. + # We have to force runtime linking in this case. + aix_use_runtimelinking=yes + LDFLAGS="$LDFLAGS -Wl,-brtl" + fi ;; esac @@ -5183,6 +5420,14 @@ _LT_EOF _LT_TAGVAR(hardcode_libdir_separator, $1)=':' _LT_TAGVAR(link_all_deplibs, $1)=yes _LT_TAGVAR(file_list_spec, $1)='$wl-f,' + case $with_aix_soname,$aix_use_runtimelinking in + aix,*) ;; # traditional, no import file + svr4,* | *,yes) # use import file + # The Import File defines what to hardcode. + _LT_TAGVAR(hardcode_direct, $1)=no + _LT_TAGVAR(hardcode_direct_absolute, $1)=no + ;; + esac if test yes = "$GCC"; then case $host_os in aix4.[[012]]|aix4.[[012]].*) @@ -5210,6 +5455,11 @@ _LT_EOF if test yes = "$aix_use_runtimelinking"; then shared_flag="$shared_flag "'$wl-G' fi + # Need to ensure runtime linking is disabled for the traditional + # shared library, or the linker may eventually find shared libraries + # /with/ Import File - we do not want to mix them. + shared_flag_aix='-shared' + shared_flag_svr4='-shared $wl-G' else # not using gcc if test ia64 = "$host_cpu"; then @@ -5222,6 +5472,8 @@ _LT_EOF else shared_flag='$wl-bM:SRE' fi + shared_flag_aix='$wl-bM:SRE' + shared_flag_svr4='$wl-G' fi fi @@ -5229,7 +5481,7 @@ _LT_EOF # It seems that -bexpall does not export symbols beginning with # underscore (_), so it is better to generate a list of symbols to export. _LT_TAGVAR(always_export_symbols, $1)=yes - if test yes = "$aix_use_runtimelinking"; then + if test aix,yes = "$with_aix_soname,$aix_use_runtimelinking"; then # Warning - without using the other runtime loading flags (-brtl), # -berok will link without error, but may produce a broken library. _LT_TAGVAR(allow_undefined_flag, $1)='-berok' @@ -5260,8 +5512,20 @@ _LT_EOF _LT_TAGVAR(whole_archive_flag_spec, $1)='$convenience' fi _LT_TAGVAR(archive_cmds_need_lc, $1)=yes - # This is similar to how AIX traditionally builds its shared libraries. - _LT_TAGVAR(archive_expsym_cmds, $1)="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs $wl-bnoentry $compiler_flags $wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + _LT_TAGVAR(archive_expsym_cmds, $1)='$RM -r $output_objdir/$realname.d~$MKDIR $output_objdir/$realname.d' + # -brtl affects multiple linker settings, -berok does not and is overridden later + compiler_flags_filtered='`func_echo_all "$compiler_flags " | $SED -e "s%-brtl\\([[, ]]\\)%-berok\\1%g"`' + if test svr4 != "$with_aix_soname"; then + # This is similar to how AIX traditionally builds its shared libraries. + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$CC '$shared_flag_aix' -o $output_objdir/$realname.d/$soname $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$realname.d/$soname' + fi + if test aix != "$with_aix_soname"; then + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$CC '$shared_flag_svr4' -o $output_objdir/$realname.d/$shared_archive_member_spec.o $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$STRIP -e $output_objdir/$realname.d/$shared_archive_member_spec.o~( func_echo_all "#! $soname($shared_archive_member_spec.o)"; if test shr_64 = "$shared_archive_member_spec"; then func_echo_all "# 64"; else func_echo_all "# 32"; fi; cat $export_symbols ) > $output_objdir/$realname.d/$shared_archive_member_spec.imp~$AR $AR_FLAGS $output_objdir/$soname $output_objdir/$realname.d/$shared_archive_member_spec.o $output_objdir/$realname.d/$shared_archive_member_spec.imp' + else + # used by -dlpreopen to get the symbols + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$MV $output_objdir/$realname.d/$soname $output_objdir' + fi + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$RM -r $output_objdir/$realname.d' fi fi ;; @@ -5515,6 +5779,16 @@ _LT_EOF _LT_TAGVAR(link_all_deplibs, $1)=yes ;; + linux*) + case $cc_basename in + tcc*) + # Fabrice Bellard et al's Tiny C Compiler + _LT_TAGVAR(ld_shlibs, $1)=yes + _LT_TAGVAR(archive_cmds, $1)='$CC -shared $pic_flag -o $lib $libobjs $deplibs $compiler_flags' + ;; + esac + ;; + netbsd*) if echo __ELF__ | $CC -E - | $GREP __ELF__ >/dev/null; then _LT_TAGVAR(archive_cmds, $1)='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out @@ -5560,8 +5834,28 @@ _LT_EOF _LT_TAGVAR(hardcode_libdir_flag_spec, $1)='-L$libdir' _LT_TAGVAR(hardcode_minus_L, $1)=yes _LT_TAGVAR(allow_undefined_flag, $1)=unsupported - _LT_TAGVAR(archive_cmds, $1)='$ECHO "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~echo DATA >> $output_objdir/$libname.def~echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' - _LT_TAGVAR(old_archive_from_new_cmds, $1)='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' + shrext_cmds=.dll + _LT_TAGVAR(archive_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(archive_expsym_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + _LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes ;; osf3*) @@ -5956,8 +6250,12 @@ if test -n "$compiler"; then ;; aix[[4-9]]*) - if test ia64 != "$host_cpu" && test no = "$aix_use_runtimelinking"; then - test yes = "$enable_shared" && enable_static=no + if test ia64 != "$host_cpu"; then + case $enable_shared,$with_aix_soname,$aix_use_runtimelinking in + yes,aix,yes) ;; # shared object as lib.so file only + yes,svr4,*) ;; # shared object as lib.so archive member only + yes,*) enable_static=no ;; # shared object in lib.a archive as well + esac fi ;; esac @@ -6145,7 +6443,19 @@ if test yes != "$_lt_caught_CXX_error"; then # Test if we are trying to use run time linking or normal # AIX style linking. If -brtl is somewhere in LDFLAGS, we - # need to do runtime linking. + # have runtime linking enabled, and use it for executables. + # For shared libraries, we enable/disable runtime linking + # depending on the kind of the shared library created - + # when "with_aix_soname,aix_use_runtimelinking" is: + # "aix,no" lib.a(lib.so.V) shared, rtl:no, for executables + # "aix,yes" lib.so shared, rtl:yes, for executables + # lib.a static archive + # "both,no" lib.so.V(shr.o) shared, rtl:yes + # lib.a(lib.so.V) shared, rtl:no, for executables + # "both,yes" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a(lib.so.V) shared, rtl:no + # "svr4,*" lib.so.V(shr.o) shared, rtl:yes, for executables + # lib.a static archive case $host_os in aix4.[[23]]|aix4.[[23]].*|aix[[5-9]]*) for ld_flag in $LDFLAGS; do case $ld_flag in @@ -6155,6 +6465,13 @@ if test yes != "$_lt_caught_CXX_error"; then ;; esac done + if test svr4,no = "$with_aix_soname,$aix_use_runtimelinking"; then + # With aix-soname=svr4, we create the lib.so.V shared archives only, + # so we don't have lib.a shared libs to link our executables. + # We have to force runtime linking in this case. + aix_use_runtimelinking=yes + LDFLAGS="$LDFLAGS -Wl,-brtl" + fi ;; esac @@ -6174,6 +6491,14 @@ if test yes != "$_lt_caught_CXX_error"; then _LT_TAGVAR(hardcode_libdir_separator, $1)=':' _LT_TAGVAR(link_all_deplibs, $1)=yes _LT_TAGVAR(file_list_spec, $1)='$wl-f,' + case $with_aix_soname,$aix_use_runtimelinking in + aix,*) ;; # no import file + svr4,* | *,yes) # use import file + # The Import File defines what to hardcode. + _LT_TAGVAR(hardcode_direct, $1)=no + _LT_TAGVAR(hardcode_direct_absolute, $1)=no + ;; + esac if test yes = "$GXX"; then case $host_os in aix4.[[012]]|aix4.[[012]].*) @@ -6200,6 +6525,11 @@ if test yes != "$_lt_caught_CXX_error"; then if test yes = "$aix_use_runtimelinking"; then shared_flag=$shared_flag' $wl-G' fi + # Need to ensure runtime linking is disabled for the traditional + # shared library, or the linker may eventually find shared libraries + # /with/ Import File - we do not want to mix them. + shared_flag_aix='-shared' + shared_flag_svr4='-shared $wl-G' else # not using gcc if test ia64 = "$host_cpu"; then @@ -6212,6 +6542,8 @@ if test yes != "$_lt_caught_CXX_error"; then else shared_flag='$wl-bM:SRE' fi + shared_flag_aix='$wl-bM:SRE' + shared_flag_svr4='$wl-G' fi fi @@ -6220,10 +6552,11 @@ if test yes != "$_lt_caught_CXX_error"; then # underscore (_), so it is better to generate a list of symbols to # export. _LT_TAGVAR(always_export_symbols, $1)=yes - if test yes = "$aix_use_runtimelinking"; then + if test aix,yes = "$with_aix_soname,$aix_use_runtimelinking"; then # Warning - without using the other runtime loading flags (-brtl), # -berok will link without error, but may produce a broken library. - _LT_TAGVAR(allow_undefined_flag, $1)='-berok' + # The "-G" linker flag allows undefined symbols. + _LT_TAGVAR(no_undefined_flag, $1)='-bernotok' # Determine the default libpath from the value encoded in an empty # executable. _LT_SYS_MODULE_PATH_AIX([$1]) @@ -6252,9 +6585,21 @@ if test yes != "$_lt_caught_CXX_error"; then _LT_TAGVAR(whole_archive_flag_spec, $1)='$convenience' fi _LT_TAGVAR(archive_cmds_need_lc, $1)=yes - # This is similar to how AIX traditionally builds its shared - # libraries. - _LT_TAGVAR(archive_expsym_cmds, $1)="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs $wl-bnoentry $compiler_flags $wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$soname' + _LT_TAGVAR(archive_expsym_cmds, $1)='$RM -r $output_objdir/$realname.d~$MKDIR $output_objdir/$realname.d' + # -brtl affects multiple linker settings, -berok does not and is overridden later + compiler_flags_filtered='`func_echo_all "$compiler_flags " | $SED -e "s%-brtl\\([[, ]]\\)%-berok\\1%g"`' + if test svr4 != "$with_aix_soname"; then + # This is similar to how AIX traditionally builds its shared + # libraries. Need -bnortl late, we may have -brtl in LDFLAGS. + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$CC '$shared_flag_aix' -o $output_objdir/$realname.d/$soname $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$AR $AR_FLAGS $output_objdir/$libname$release.a $output_objdir/$realname.d/$soname' + fi + if test aix != "$with_aix_soname"; then + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$CC '$shared_flag_svr4' -o $output_objdir/$realname.d/$shared_archive_member_spec.o $libobjs $deplibs $wl-bnoentry '$compiler_flags_filtered'$wl-bE:$export_symbols$allow_undefined_flag~$STRIP -e $output_objdir/$realname.d/$shared_archive_member_spec.o~( func_echo_all "#! $soname($shared_archive_member_spec.o)"; if test shr_64 = "$shared_archive_member_spec"; then func_echo_all "# 64"; else func_echo_all "# 32"; fi; cat $export_symbols ) > $output_objdir/$realname.d/$shared_archive_member_spec.imp~$AR $AR_FLAGS $output_objdir/$soname $output_objdir/$realname.d/$shared_archive_member_spec.o $output_objdir/$realname.d/$shared_archive_member_spec.imp' + else + # used by -dlpreopen to get the symbols + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$MV $output_objdir/$realname.d/$soname $output_objdir' + fi + _LT_TAGVAR(archive_expsym_cmds, $1)="$_LT_TAGVAR(archive_expsym_cmds, $1)"'~$RM -r $output_objdir/$realname.d' fi fi ;; @@ -6354,6 +6699,34 @@ if test yes != "$_lt_caught_CXX_error"; then _LT_DARWIN_LINKER_FEATURES($1) ;; + os2*) + _LT_TAGVAR(hardcode_libdir_flag_spec, $1)='-L$libdir' + _LT_TAGVAR(hardcode_minus_L, $1)=yes + _LT_TAGVAR(allow_undefined_flag, $1)=unsupported + shrext_cmds=.dll + _LT_TAGVAR(archive_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + emxexp $libobjs | $SED /"_DLL_InitTerm"/d >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(archive_expsym_cmds, $1)='$ECHO "LIBRARY ${soname%$shared_ext} INITINSTANCE TERMINSTANCE" > $output_objdir/$libname.def~ + $ECHO "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~ + $ECHO "DATA MULTIPLE NONSHARED" >> $output_objdir/$libname.def~ + $ECHO EXPORTS >> $output_objdir/$libname.def~ + prefix_cmds="$SED"~ + if test EXPORTS = "`$SED 1q $export_symbols`"; then + prefix_cmds="$prefix_cmds -e 1d"; + fi~ + prefix_cmds="$prefix_cmds -e \"s/^\(.*\)$/_\1/g\""~ + cat $export_symbols | $prefix_cmds >> $output_objdir/$libname.def~ + $CC -Zdll -Zcrtdll -o $output_objdir/$soname $libobjs $deplibs $compiler_flags $output_objdir/$libname.def~ + emximp -o $lib $output_objdir/$libname.def' + _LT_TAGVAR(old_archive_From_new_cmds, $1)='emximp -o $output_objdir/${libname}_dll.a $output_objdir/$libname.def' + _LT_TAGVAR(enable_shared_with_static_runtimes, $1)=yes + ;; + dgux*) case $cc_basename in ec++*) @@ -7067,6 +7440,7 @@ func_stripname_cnf () } # func_stripname_cnf ])# _LT_FUNC_STRIPNAME_CNF + # _LT_SYS_HIDDEN_LIBDEPS([TAGNAME]) # --------------------------------- # Figure out "hidden" library dependencies from verbose @@ -7245,51 +7619,6 @@ interix[[3-9]]*) _LT_TAGVAR(postdep_objects,$1)= _LT_TAGVAR(postdeps,$1)= ;; - -linux*) - case `$CC -V 2>&1 | sed 5q` in - *Sun\ C*) - # Sun C++ 5.9 - - # The more standards-conforming stlport4 library is - # incompatible with the Cstd library. Avoid specifying - # it if it's in CXXFLAGS. Ignore libCrun as - # -library=stlport4 depends on it. - case " $CXX $CXXFLAGS " in - *" -library=stlport4 "*) - solaris_use_stlport4=yes - ;; - esac - - if test yes != "$solaris_use_stlport4"; then - _LT_TAGVAR(postdeps,$1)='-library=Cstd -library=Crun' - fi - ;; - esac - ;; - -solaris*) - case $cc_basename in - CC* | sunCC*) - # The more standards-conforming stlport4 library is - # incompatible with the Cstd library. Avoid specifying - # it if it's in CXXFLAGS. Ignore libCrun as - # -library=stlport4 depends on it. - case " $CXX $CXXFLAGS " in - *" -library=stlport4 "*) - solaris_use_stlport4=yes - ;; - esac - - # Adding this requires a known-good setup of shared libraries for - # Sun compiler versions before 5.6, else PIC objects from an old - # archive will be linked into the output, leading to subtle bugs. - if test yes != "$solaris_use_stlport4"; then - _LT_TAGVAR(postdeps,$1)='-library=Cstd -library=Crun' - fi - ;; - esac - ;; esac ]) @@ -7407,8 +7736,12 @@ if test yes != "$_lt_disable_F77"; then fi ;; aix[[4-9]]*) - if test ia64 != "$host_cpu" && test no = "$aix_use_runtimelinking"; then - test yes = "$enable_shared" && enable_static=no + if test ia64 != "$host_cpu"; then + case $enable_shared,$with_aix_soname,$aix_use_runtimelinking in + yes,aix,yes) ;; # shared object as lib.so file only + yes,svr4,*) ;; # shared object as lib.so archive member only + yes,*) enable_static=no ;; # shared object in lib.a archive as well + esac fi ;; esac @@ -7541,8 +7874,12 @@ if test yes != "$_lt_disable_FC"; then fi ;; aix[[4-9]]*) - if test ia64 != "$host_cpu" && test no = "$aix_use_runtimelinking"; then - test yes = "$enable_shared" && enable_static=no + if test ia64 != "$host_cpu"; then + case $enable_shared,$with_aix_soname,$aix_use_runtimelinking in + yes,aix,yes) ;; # shared object as lib.so file only + yes,svr4,*) ;; # shared object as lib.so archive member only + yes,*) enable_static=no ;; # shared object in lib.a archive as well + esac fi ;; esac diff --git a/extension/m4/ltoptions.m4 b/extension/m4/ltoptions.m4 index de6520ed..94b08297 100644 --- a/extension/m4/ltoptions.m4 +++ b/extension/m4/ltoptions.m4 @@ -1,6 +1,6 @@ # Helper functions for option handling. -*- Autoconf -*- # -# Copyright (C) 2004-2005, 2007-2009, 2011-2014 Free Software +# Copyright (C) 2004-2005, 2007-2009, 2011-2015 Free Software # Foundation, Inc. # Written by Gary V. Vaughan, 2004 # @@ -82,6 +82,8 @@ m4_if([$1],[LT_INIT],[ _LT_UNLESS_OPTIONS([LT_INIT], [pic-only no-pic], [_LT_WITH_PIC]) _LT_UNLESS_OPTIONS([LT_INIT], [fast-install disable-fast-install], [_LT_ENABLE_FAST_INSTALL]) + _LT_UNLESS_OPTIONS([LT_INIT], [aix-soname=aix aix-soname=both aix-soname=svr4], + [_LT_WITH_AIX_SONAME([aix])]) ]) ])# _LT_SET_OPTIONS @@ -319,6 +321,59 @@ dnl AC_DEFUN([AC_ENABLE_FAST_INSTALL], []) dnl AC_DEFUN([AM_DISABLE_FAST_INSTALL], []) +# _LT_WITH_AIX_SONAME([DEFAULT]) +# ---------------------------------- +# implement the --with-aix-soname flag, and support the `aix-soname=aix' +# and `aix-soname=both' and `aix-soname=svr4' LT_INIT options. DEFAULT +# is either `aix', `both' or `svr4'. If omitted, it defaults to `aix'. +m4_define([_LT_WITH_AIX_SONAME], +[m4_define([_LT_WITH_AIX_SONAME_DEFAULT], [m4_if($1, svr4, svr4, m4_if($1, both, both, aix))])dnl +shared_archive_member_spec= +case $host,$enable_shared in +power*-*-aix[[5-9]]*,yes) + AC_MSG_CHECKING([which variant of shared library versioning to provide]) + AC_ARG_WITH([aix-soname], + [AS_HELP_STRING([--with-aix-soname=aix|svr4|both], + [shared library versioning (aka "SONAME") variant to provide on AIX, @<:@default=]_LT_WITH_AIX_SONAME_DEFAULT[@:>@.])], + [case $withval in + aix|svr4|both) + ;; + *) + AC_MSG_ERROR([Unknown argument to --with-aix-soname]) + ;; + esac + lt_cv_with_aix_soname=$with_aix_soname], + [AC_CACHE_VAL([lt_cv_with_aix_soname], + [lt_cv_with_aix_soname=]_LT_WITH_AIX_SONAME_DEFAULT) + with_aix_soname=$lt_cv_with_aix_soname]) + AC_MSG_RESULT([$with_aix_soname]) + if test aix != "$with_aix_soname"; then + # For the AIX way of multilib, we name the shared archive member + # based on the bitwidth used, traditionally 'shr.o' or 'shr_64.o', + # and 'shr.imp' or 'shr_64.imp', respectively, for the Import File. + # Even when GNU compilers ignore OBJECT_MODE but need '-maix64' flag, + # the AIX toolchain works better with OBJECT_MODE set (default 32). + if test 64 = "${OBJECT_MODE-32}"; then + shared_archive_member_spec=shr_64 + else + shared_archive_member_spec=shr + fi + fi + ;; +*) + with_aix_soname=aix + ;; +esac + +_LT_DECL([], [shared_archive_member_spec], [0], + [Shared archive member basename, for filename based shared library versioning on AIX])dnl +])# _LT_WITH_AIX_SONAME + +LT_OPTION_DEFINE([LT_INIT], [aix-soname=aix], [_LT_WITH_AIX_SONAME([aix])]) +LT_OPTION_DEFINE([LT_INIT], [aix-soname=both], [_LT_WITH_AIX_SONAME([both])]) +LT_OPTION_DEFINE([LT_INIT], [aix-soname=svr4], [_LT_WITH_AIX_SONAME([svr4])]) + + # _LT_WITH_PIC([MODE]) # -------------------- # implement the --with-pic flag, and support the 'pic-only' and 'no-pic' diff --git a/extension/m4/ltsugar.m4 b/extension/m4/ltsugar.m4 index da4ac6b3..48bc9344 100644 --- a/extension/m4/ltsugar.m4 +++ b/extension/m4/ltsugar.m4 @@ -1,6 +1,6 @@ # ltsugar.m4 -- libtool m4 base layer. -*-Autoconf-*- # -# Copyright (C) 2004-2005, 2007-2008, 2011-2014 Free Software +# Copyright (C) 2004-2005, 2007-2008, 2011-2015 Free Software # Foundation, Inc. # Written by Gary V. Vaughan, 2004 # diff --git a/extension/m4/ltversion.m4 b/extension/m4/ltversion.m4 index 3535ff40..a4c5ed43 100644 --- a/extension/m4/ltversion.m4 +++ b/extension/m4/ltversion.m4 @@ -1,6 +1,6 @@ # ltversion.m4 -- version numbers -*- Autoconf -*- # -# Copyright (C) 2004, 2011-2014 Free Software Foundation, Inc. +# Copyright (C) 2004, 2011-2015 Free Software Foundation, Inc. # Written by Scott James Remnant, 2004 # # This file is free software; the Free Software Foundation gives @@ -9,15 +9,15 @@ # @configure_input@ -# serial 4105 ltversion.m4 +# serial 4171 ltversion.m4 # This file is part of GNU Libtool -m4_define([LT_PACKAGE_VERSION], [2.4.2.458.26-92994]) -m4_define([LT_PACKAGE_REVISION], [2.4.3]) +m4_define([LT_PACKAGE_VERSION], [2.4.5]) +m4_define([LT_PACKAGE_REVISION], [2.4.5]) AC_DEFUN([LTVERSION_VERSION], -[macro_version='2.4.2.458.26-92994' -macro_revision='2.4.3' +[macro_version='2.4.5' +macro_revision='2.4.5' _LT_DECL(, macro_version, 0, [Which release of libtool.m4 was used?]) _LT_DECL(, macro_revision, 0) ]) diff --git a/extension/m4/lt~obsolete.m4 b/extension/m4/lt~obsolete.m4 index 6975098b..c6b26f88 100644 --- a/extension/m4/lt~obsolete.m4 +++ b/extension/m4/lt~obsolete.m4 @@ -1,6 +1,6 @@ # lt~obsolete.m4 -- aclocal satisfying obsolete definitions. -*-Autoconf-*- # -# Copyright (C) 2004-2005, 2007, 2009, 2011-2014 Free Software +# Copyright (C) 2004-2005, 2007, 2009, 2011-2015 Free Software # Foundation, Inc. # Written by Scott James Remnant, 2004. # diff --git a/extension/m4/po.m4 b/extension/m4/po.m4 deleted file mode 100644 index 3c9884ba..00000000 --- a/extension/m4/po.m4 +++ /dev/null @@ -1,449 +0,0 @@ -# po.m4 serial 17 (gettext-0.18) -dnl Copyright (C) 1995-2010 Free Software Foundation, Inc. -dnl This file is free software; the Free Software Foundation -dnl gives unlimited permission to copy and/or distribute it, -dnl with or without modifications, as long as this notice is preserved. -dnl -dnl This file can can be used in projects which are not available under -dnl the GNU General Public License or the GNU Library General Public -dnl License but which still want to provide support for the GNU gettext -dnl functionality. -dnl Please note that the actual code of the GNU gettext library is covered -dnl by the GNU Library General Public License, and the rest of the GNU -dnl gettext package package is covered by the GNU General Public License. -dnl They are *not* in the public domain. - -dnl Authors: -dnl Ulrich Drepper <drepper@cygnus.com>, 1995-2000. -dnl Bruno Haible <haible@clisp.cons.org>, 2000-2003. - -AC_PREREQ([2.50]) - -dnl Checks for all prerequisites of the po subdirectory. -AC_DEFUN([AM_PO_SUBDIRS], -[ - AC_REQUIRE([AC_PROG_MAKE_SET])dnl - AC_REQUIRE([AC_PROG_INSTALL])dnl - AC_REQUIRE([AC_PROG_MKDIR_P])dnl defined by automake - AC_REQUIRE([AM_NLS])dnl - - dnl Release version of the gettext macros. This is used to ensure that - dnl the gettext macros and po/Makefile.in.in are in sync. - AC_SUBST([GETTEXT_MACRO_VERSION], [0.18]) - - dnl Perform the following tests also if --disable-nls has been given, - dnl because they are needed for "make dist" to work. - - dnl Search for GNU msgfmt in the PATH. - dnl The first test excludes Solaris msgfmt and early GNU msgfmt versions. - dnl The second test excludes FreeBSD msgfmt. - AM_PATH_PROG_WITH_TEST(MSGFMT, msgfmt, - [$ac_dir/$ac_word --statistics /dev/null >&]AS_MESSAGE_LOG_FD[ 2>&1 && - (if $ac_dir/$ac_word --statistics /dev/null 2>&1 >/dev/null | grep usage >/dev/null; then exit 1; else exit 0; fi)], - :) - AC_PATH_PROG([GMSGFMT], [gmsgfmt], [$MSGFMT]) - - dnl Test whether it is GNU msgfmt >= 0.15. -changequote(,)dnl - case `$MSGFMT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) MSGFMT_015=: ;; - *) MSGFMT_015=$MSGFMT ;; - esac -changequote([,])dnl - AC_SUBST([MSGFMT_015]) -changequote(,)dnl - case `$GMSGFMT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) GMSGFMT_015=: ;; - *) GMSGFMT_015=$GMSGFMT ;; - esac -changequote([,])dnl - AC_SUBST([GMSGFMT_015]) - - dnl Search for GNU xgettext 0.12 or newer in the PATH. - dnl The first test excludes Solaris xgettext and early GNU xgettext versions. - dnl The second test excludes FreeBSD xgettext. - AM_PATH_PROG_WITH_TEST(XGETTEXT, xgettext, - [$ac_dir/$ac_word --omit-header --copyright-holder= --msgid-bugs-address= /dev/null >&]AS_MESSAGE_LOG_FD[ 2>&1 && - (if $ac_dir/$ac_word --omit-header --copyright-holder= --msgid-bugs-address= /dev/null 2>&1 >/dev/null | grep usage >/dev/null; then exit 1; else exit 0; fi)], - :) - dnl Remove leftover from FreeBSD xgettext call. - rm -f messages.po - - dnl Test whether it is GNU xgettext >= 0.15. -changequote(,)dnl - case `$XGETTEXT --version | sed 1q | sed -e 's,^[^0-9]*,,'` in - '' | 0.[0-9] | 0.[0-9].* | 0.1[0-4] | 0.1[0-4].*) XGETTEXT_015=: ;; - *) XGETTEXT_015=$XGETTEXT ;; - esac -changequote([,])dnl - AC_SUBST([XGETTEXT_015]) - - dnl Search for GNU msgmerge 0.11 or newer in the PATH. - AM_PATH_PROG_WITH_TEST(MSGMERGE, msgmerge, - [$ac_dir/$ac_word --update -q /dev/null /dev/null >&]AS_MESSAGE_LOG_FD[ 2>&1], :) - - dnl Installation directories. - dnl Autoconf >= 2.60 defines localedir. For older versions of autoconf, we - dnl have to define it here, so that it can be used in po/Makefile. - test -n "$localedir" || localedir='${datadir}/locale' - AC_SUBST([localedir]) - - dnl Support for AM_XGETTEXT_OPTION. - test -n "${XGETTEXT_EXTRA_OPTIONS+set}" || XGETTEXT_EXTRA_OPTIONS= - AC_SUBST([XGETTEXT_EXTRA_OPTIONS]) - - AC_CONFIG_COMMANDS([po-directories], [[ - for ac_file in $CONFIG_FILES; do - # Support "outfile[:infile[:infile...]]" - case "$ac_file" in - *:*) ac_file=`echo "$ac_file"|sed 's%:.*%%'` ;; - esac - # PO directories have a Makefile.in generated from Makefile.in.in. - case "$ac_file" in */Makefile.in) - # Adjust a relative srcdir. - ac_dir=`echo "$ac_file"|sed 's%/[^/][^/]*$%%'` - ac_dir_suffix="/`echo "$ac_dir"|sed 's%^\./%%'`" - ac_dots=`echo "$ac_dir_suffix"|sed 's%/[^/]*%../%g'` - # In autoconf-2.13 it is called $ac_given_srcdir. - # In autoconf-2.50 it is called $srcdir. - test -n "$ac_given_srcdir" || ac_given_srcdir="$srcdir" - case "$ac_given_srcdir" in - .) top_srcdir=`echo $ac_dots|sed 's%/$%%'` ;; - /*) top_srcdir="$ac_given_srcdir" ;; - *) top_srcdir="$ac_dots$ac_given_srcdir" ;; - esac - # Treat a directory as a PO directory if and only if it has a - # POTFILES.in file. This allows packages to have multiple PO - # directories under different names or in different locations. - if test -f "$ac_given_srcdir/$ac_dir/POTFILES.in"; then - rm -f "$ac_dir/POTFILES" - test -n "$as_me" && echo "$as_me: creating $ac_dir/POTFILES" || echo "creating $ac_dir/POTFILES" - cat "$ac_given_srcdir/$ac_dir/POTFILES.in" | sed -e "/^#/d" -e "/^[ ]*\$/d" -e "s,.*, $top_srcdir/& \\\\," | sed -e "\$s/\(.*\) \\\\/\1/" > "$ac_dir/POTFILES" - POMAKEFILEDEPS="POTFILES.in" - # ALL_LINGUAS, POFILES, UPDATEPOFILES, DUMMYPOFILES, GMOFILES depend - # on $ac_dir but don't depend on user-specified configuration - # parameters. - if test -f "$ac_given_srcdir/$ac_dir/LINGUAS"; then - # The LINGUAS file contains the set of available languages. - if test -n "$OBSOLETE_ALL_LINGUAS"; then - test -n "$as_me" && echo "$as_me: setting ALL_LINGUAS in configure.in is obsolete" || echo "setting ALL_LINGUAS in configure.in is obsolete" - fi - ALL_LINGUAS_=`sed -e "/^#/d" -e "s/#.*//" "$ac_given_srcdir/$ac_dir/LINGUAS"` - # Hide the ALL_LINGUAS assigment from automake < 1.5. - eval 'ALL_LINGUAS''=$ALL_LINGUAS_' - POMAKEFILEDEPS="$POMAKEFILEDEPS LINGUAS" - else - # The set of available languages was given in configure.in. - # Hide the ALL_LINGUAS assigment from automake < 1.5. - eval 'ALL_LINGUAS''=$OBSOLETE_ALL_LINGUAS' - fi - # Compute POFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).po) - # Compute UPDATEPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).po-update) - # Compute DUMMYPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).nop) - # Compute GMOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).gmo) - case "$ac_given_srcdir" in - .) srcdirpre= ;; - *) srcdirpre='$(srcdir)/' ;; - esac - POFILES= - UPDATEPOFILES= - DUMMYPOFILES= - GMOFILES= - for lang in $ALL_LINGUAS; do - POFILES="$POFILES $srcdirpre$lang.po" - UPDATEPOFILES="$UPDATEPOFILES $lang.po-update" - DUMMYPOFILES="$DUMMYPOFILES $lang.nop" - GMOFILES="$GMOFILES $srcdirpre$lang.gmo" - done - # CATALOGS depends on both $ac_dir and the user's LINGUAS - # environment variable. - INST_LINGUAS= - if test -n "$ALL_LINGUAS"; then - for presentlang in $ALL_LINGUAS; do - useit=no - if test "%UNSET%" != "$LINGUAS"; then - desiredlanguages="$LINGUAS" - else - desiredlanguages="$ALL_LINGUAS" - fi - for desiredlang in $desiredlanguages; do - # Use the presentlang catalog if desiredlang is - # a. equal to presentlang, or - # b. a variant of presentlang (because in this case, - # presentlang can be used as a fallback for messages - # which are not translated in the desiredlang catalog). - case "$desiredlang" in - "$presentlang"*) useit=yes;; - esac - done - if test $useit = yes; then - INST_LINGUAS="$INST_LINGUAS $presentlang" - fi - done - fi - CATALOGS= - if test -n "$INST_LINGUAS"; then - for lang in $INST_LINGUAS; do - CATALOGS="$CATALOGS $lang.gmo" - done - fi - test -n "$as_me" && echo "$as_me: creating $ac_dir/Makefile" || echo "creating $ac_dir/Makefile" - sed -e "/^POTFILES =/r $ac_dir/POTFILES" -e "/^# Makevars/r $ac_given_srcdir/$ac_dir/Makevars" -e "s|@POFILES@|$POFILES|g" -e "s|@UPDATEPOFILES@|$UPDATEPOFILES|g" -e "s|@DUMMYPOFILES@|$DUMMYPOFILES|g" -e "s|@GMOFILES@|$GMOFILES|g" -e "s|@CATALOGS@|$CATALOGS|g" -e "s|@POMAKEFILEDEPS@|$POMAKEFILEDEPS|g" "$ac_dir/Makefile.in" > "$ac_dir/Makefile" - for f in "$ac_given_srcdir/$ac_dir"/Rules-*; do - if test -f "$f"; then - case "$f" in - *.orig | *.bak | *~) ;; - *) cat "$f" >> "$ac_dir/Makefile" ;; - esac - fi - done - fi - ;; - esac - done]], - [# Capture the value of obsolete ALL_LINGUAS because we need it to compute - # POFILES, UPDATEPOFILES, DUMMYPOFILES, GMOFILES, CATALOGS. But hide it - # from automake < 1.5. - eval 'OBSOLETE_ALL_LINGUAS''="$ALL_LINGUAS"' - # Capture the value of LINGUAS because we need it to compute CATALOGS. - LINGUAS="${LINGUAS-%UNSET%}" - ]) -]) - -dnl Postprocesses a Makefile in a directory containing PO files. -AC_DEFUN([AM_POSTPROCESS_PO_MAKEFILE], -[ - # When this code is run, in config.status, two variables have already been - # set: - # - OBSOLETE_ALL_LINGUAS is the value of LINGUAS set in configure.in, - # - LINGUAS is the value of the environment variable LINGUAS at configure - # time. - -changequote(,)dnl - # Adjust a relative srcdir. - ac_dir=`echo "$ac_file"|sed 's%/[^/][^/]*$%%'` - ac_dir_suffix="/`echo "$ac_dir"|sed 's%^\./%%'`" - ac_dots=`echo "$ac_dir_suffix"|sed 's%/[^/]*%../%g'` - # In autoconf-2.13 it is called $ac_given_srcdir. - # In autoconf-2.50 it is called $srcdir. - test -n "$ac_given_srcdir" || ac_given_srcdir="$srcdir" - case "$ac_given_srcdir" in - .) top_srcdir=`echo $ac_dots|sed 's%/$%%'` ;; - /*) top_srcdir="$ac_given_srcdir" ;; - *) top_srcdir="$ac_dots$ac_given_srcdir" ;; - esac - - # Find a way to echo strings without interpreting backslash. - if test "X`(echo '\t') 2>/dev/null`" = 'X\t'; then - gt_echo='echo' - else - if test "X`(printf '%s\n' '\t') 2>/dev/null`" = 'X\t'; then - gt_echo='printf %s\n' - else - echo_func () { - cat <<EOT -$* -EOT - } - gt_echo='echo_func' - fi - fi - - # A sed script that extracts the value of VARIABLE from a Makefile. - sed_x_variable=' -# Test if the hold space is empty. -x -s/P/P/ -x -ta -# Yes it was empty. Look if we have the expected variable definition. -/^[ ]*VARIABLE[ ]*=/{ - # Seen the first line of the variable definition. - s/^[ ]*VARIABLE[ ]*=// - ba -} -bd -:a -# Here we are processing a line from the variable definition. -# Remove comment, more precisely replace it with a space. -s/#.*$/ / -# See if the line ends in a backslash. -tb -:b -s/\\$// -# Print the line, without the trailing backslash. -p -tc -# There was no trailing backslash. The end of the variable definition is -# reached. Clear the hold space. -s/^.*$// -x -bd -:c -# A trailing backslash means that the variable definition continues in the -# next line. Put a nonempty string into the hold space to indicate this. -s/^.*$/P/ -x -:d -' -changequote([,])dnl - - # Set POTFILES to the value of the Makefile variable POTFILES. - sed_x_POTFILES=`$gt_echo "$sed_x_variable" | sed -e '/^ *#/d' -e 's/VARIABLE/POTFILES/g'` - POTFILES=`sed -n -e "$sed_x_POTFILES" < "$ac_file"` - # Compute POTFILES_DEPS as - # $(foreach file, $(POTFILES), $(top_srcdir)/$(file)) - POTFILES_DEPS= - for file in $POTFILES; do - POTFILES_DEPS="$POTFILES_DEPS "'$(top_srcdir)/'"$file" - done - POMAKEFILEDEPS="" - - if test -n "$OBSOLETE_ALL_LINGUAS"; then - test -n "$as_me" && echo "$as_me: setting ALL_LINGUAS in configure.in is obsolete" || echo "setting ALL_LINGUAS in configure.in is obsolete" - fi - if test -f "$ac_given_srcdir/$ac_dir/LINGUAS"; then - # The LINGUAS file contains the set of available languages. - ALL_LINGUAS_=`sed -e "/^#/d" -e "s/#.*//" "$ac_given_srcdir/$ac_dir/LINGUAS"` - POMAKEFILEDEPS="$POMAKEFILEDEPS LINGUAS" - else - # Set ALL_LINGUAS to the value of the Makefile variable LINGUAS. - sed_x_LINGUAS=`$gt_echo "$sed_x_variable" | sed -e '/^ *#/d' -e 's/VARIABLE/LINGUAS/g'` - ALL_LINGUAS_=`sed -n -e "$sed_x_LINGUAS" < "$ac_file"` - fi - # Hide the ALL_LINGUAS assigment from automake < 1.5. - eval 'ALL_LINGUAS''=$ALL_LINGUAS_' - # Compute POFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).po) - # Compute UPDATEPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).po-update) - # Compute DUMMYPOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(lang).nop) - # Compute GMOFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).gmo) - # Compute PROPERTIESFILES - # as $(foreach lang, $(ALL_LINGUAS), $(top_srcdir)/$(DOMAIN)_$(lang).properties) - # Compute CLASSFILES - # as $(foreach lang, $(ALL_LINGUAS), $(top_srcdir)/$(DOMAIN)_$(lang).class) - # Compute QMFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(lang).qm) - # Compute MSGFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(frob $(lang)).msg) - # Compute RESOURCESDLLFILES - # as $(foreach lang, $(ALL_LINGUAS), $(srcdir)/$(frob $(lang))/$(DOMAIN).resources.dll) - case "$ac_given_srcdir" in - .) srcdirpre= ;; - *) srcdirpre='$(srcdir)/' ;; - esac - POFILES= - UPDATEPOFILES= - DUMMYPOFILES= - GMOFILES= - PROPERTIESFILES= - CLASSFILES= - QMFILES= - MSGFILES= - RESOURCESDLLFILES= - for lang in $ALL_LINGUAS; do - POFILES="$POFILES $srcdirpre$lang.po" - UPDATEPOFILES="$UPDATEPOFILES $lang.po-update" - DUMMYPOFILES="$DUMMYPOFILES $lang.nop" - GMOFILES="$GMOFILES $srcdirpre$lang.gmo" - PROPERTIESFILES="$PROPERTIESFILES \$(top_srcdir)/\$(DOMAIN)_$lang.properties" - CLASSFILES="$CLASSFILES \$(top_srcdir)/\$(DOMAIN)_$lang.class" - QMFILES="$QMFILES $srcdirpre$lang.qm" - frobbedlang=`echo $lang | sed -e 's/\..*$//' -e 'y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/'` - MSGFILES="$MSGFILES $srcdirpre$frobbedlang.msg" - frobbedlang=`echo $lang | sed -e 's/_/-/g' -e 's/^sr-CS/sr-SP/' -e 's/@latin$/-Latn/' -e 's/@cyrillic$/-Cyrl/' -e 's/^sr-SP$/sr-SP-Latn/' -e 's/^uz-UZ$/uz-UZ-Latn/'` - RESOURCESDLLFILES="$RESOURCESDLLFILES $srcdirpre$frobbedlang/\$(DOMAIN).resources.dll" - done - # CATALOGS depends on both $ac_dir and the user's LINGUAS - # environment variable. - INST_LINGUAS= - if test -n "$ALL_LINGUAS"; then - for presentlang in $ALL_LINGUAS; do - useit=no - if test "%UNSET%" != "$LINGUAS"; then - desiredlanguages="$LINGUAS" - else - desiredlanguages="$ALL_LINGUAS" - fi - for desiredlang in $desiredlanguages; do - # Use the presentlang catalog if desiredlang is - # a. equal to presentlang, or - # b. a variant of presentlang (because in this case, - # presentlang can be used as a fallback for messages - # which are not translated in the desiredlang catalog). - case "$desiredlang" in - "$presentlang"*) useit=yes;; - esac - done - if test $useit = yes; then - INST_LINGUAS="$INST_LINGUAS $presentlang" - fi - done - fi - CATALOGS= - JAVACATALOGS= - QTCATALOGS= - TCLCATALOGS= - CSHARPCATALOGS= - if test -n "$INST_LINGUAS"; then - for lang in $INST_LINGUAS; do - CATALOGS="$CATALOGS $lang.gmo" - JAVACATALOGS="$JAVACATALOGS \$(DOMAIN)_$lang.properties" - QTCATALOGS="$QTCATALOGS $lang.qm" - frobbedlang=`echo $lang | sed -e 's/\..*$//' -e 'y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/'` - TCLCATALOGS="$TCLCATALOGS $frobbedlang.msg" - frobbedlang=`echo $lang | sed -e 's/_/-/g' -e 's/^sr-CS/sr-SP/' -e 's/@latin$/-Latn/' -e 's/@cyrillic$/-Cyrl/' -e 's/^sr-SP$/sr-SP-Latn/' -e 's/^uz-UZ$/uz-UZ-Latn/'` - CSHARPCATALOGS="$CSHARPCATALOGS $frobbedlang/\$(DOMAIN).resources.dll" - done - fi - - sed -e "s|@POTFILES_DEPS@|$POTFILES_DEPS|g" -e "s|@POFILES@|$POFILES|g" -e "s|@UPDATEPOFILES@|$UPDATEPOFILES|g" -e "s|@DUMMYPOFILES@|$DUMMYPOFILES|g" -e "s|@GMOFILES@|$GMOFILES|g" -e "s|@PROPERTIESFILES@|$PROPERTIESFILES|g" -e "s|@CLASSFILES@|$CLASSFILES|g" -e "s|@QMFILES@|$QMFILES|g" -e "s|@MSGFILES@|$MSGFILES|g" -e "s|@RESOURCESDLLFILES@|$RESOURCESDLLFILES|g" -e "s|@CATALOGS@|$CATALOGS|g" -e "s|@JAVACATALOGS@|$JAVACATALOGS|g" -e "s|@QTCATALOGS@|$QTCATALOGS|g" -e "s|@TCLCATALOGS@|$TCLCATALOGS|g" -e "s|@CSHARPCATALOGS@|$CSHARPCATALOGS|g" -e 's,^#distdir:,distdir:,' < "$ac_file" > "$ac_file.tmp" - if grep -l '@TCLCATALOGS@' "$ac_file" > /dev/null; then - # Add dependencies that cannot be formulated as a simple suffix rule. - for lang in $ALL_LINGUAS; do - frobbedlang=`echo $lang | sed -e 's/\..*$//' -e 'y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/'` - cat >> "$ac_file.tmp" <<EOF -$frobbedlang.msg: $lang.po - @echo "\$(MSGFMT) -c --tcl -d \$(srcdir) -l $lang $srcdirpre$lang.po"; \ - \$(MSGFMT) -c --tcl -d "\$(srcdir)" -l $lang $srcdirpre$lang.po || { rm -f "\$(srcdir)/$frobbedlang.msg"; exit 1; } -EOF - done - fi - if grep -l '@CSHARPCATALOGS@' "$ac_file" > /dev/null; then - # Add dependencies that cannot be formulated as a simple suffix rule. - for lang in $ALL_LINGUAS; do - frobbedlang=`echo $lang | sed -e 's/_/-/g' -e 's/^sr-CS/sr-SP/' -e 's/@latin$/-Latn/' -e 's/@cyrillic$/-Cyrl/' -e 's/^sr-SP$/sr-SP-Latn/' -e 's/^uz-UZ$/uz-UZ-Latn/'` - cat >> "$ac_file.tmp" <<EOF -$frobbedlang/\$(DOMAIN).resources.dll: $lang.po - @echo "\$(MSGFMT) -c --csharp -d \$(srcdir) -l $lang $srcdirpre$lang.po -r \$(DOMAIN)"; \ - \$(MSGFMT) -c --csharp -d "\$(srcdir)" -l $lang $srcdirpre$lang.po -r "\$(DOMAIN)" || { rm -f "\$(srcdir)/$frobbedlang.msg"; exit 1; } -EOF - done - fi - if test -n "$POMAKEFILEDEPS"; then - cat >> "$ac_file.tmp" <<EOF -Makefile: $POMAKEFILEDEPS -EOF - fi - mv "$ac_file.tmp" "$ac_file" -]) - -dnl Initializes the accumulator used by AM_XGETTEXT_OPTION. -AC_DEFUN([AM_XGETTEXT_OPTION_INIT], -[ - XGETTEXT_EXTRA_OPTIONS= -]) - -dnl Registers an option to be passed to xgettext in the po subdirectory. -AC_DEFUN([AM_XGETTEXT_OPTION], -[ - AC_REQUIRE([AM_XGETTEXT_OPTION_INIT]) - XGETTEXT_EXTRA_OPTIONS="$XGETTEXT_EXTRA_OPTIONS $1" -]) diff --git a/extension/testext.c b/extension/testext.c index 7462265b..4a1e7032 100644 --- a/extension/testext.c +++ b/extension/testext.c @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 2012, 2013, 2014 + * Copyright (C) 2012, 2013, 2014, 2015 * the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the @@ -302,11 +302,11 @@ var_test(int nargs, awk_value_t *result) goto out; } - /* look up PROCINFO - should fail */ + /* look up PROCINFO - should succeed fail */ if (sym_lookup("PROCINFO", AWK_ARRAY, & value)) - printf("var_test: sym_lookup of PROCINFO failed - got a value!\n"); + printf("var_test: sym_lookup of PROCINFO passed - got a value!\n"); else - printf("var_test: sym_lookup of PROCINFO passed - did not get a value\n"); + printf("var_test: sym_lookup of PROCINFO failed - did not get a value\n"); /* look up a reserved variable - should pass */ if (sym_lookup("ARGC", AWK_NUMBER, & value)) diff --git a/extras/Makefile.in b/extras/Makefile.in index f6416f56..f6741221 100644 --- a/extras/Makefile.in +++ b/extras/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -38,7 +38,17 @@ # VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -102,8 +112,6 @@ POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ subdir = extras -DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Makefile.am \ - $(top_srcdir)/mkinstalldirs ChangeLog ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/codeset.m4 $(top_srcdir)/m4/gettext.m4 \ @@ -118,6 +126,7 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/ulonglong.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs CONFIG_HEADER = $(top_builddir)/config.h CONFIG_CLEAN_FILES = @@ -171,6 +180,8 @@ am__uninstall_files_from_dir = { \ am__installdirs = "$(DESTDIR)$(profiledir)" DATA = $(profile_DATA) am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +am__DIST_COMMON = $(srcdir)/Makefile.in $(top_srcdir)/mkinstalldirs \ + ChangeLog DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) ACLOCAL = @ACLOCAL@ AMTAR = @AMTAR@ @@ -317,7 +328,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(am__configure_deps) echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu extras/Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu extras/Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -510,6 +520,8 @@ uninstall-am: uninstall-profileDATA pdf-am ps ps-am tags-am uninstall uninstall-am \ uninstall-profileDATA +.PRECIOUS: Makefile + # Tell versions [3.59,3.63) of GNU make to not export all variables. # Otherwise a system limit (for SysV at least) may be exceeded. @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 2012-2014 the Free Software Foundation, Inc. + * Copyright (C) 2012-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -790,7 +790,6 @@ api_set_array_element(awk_ext_id_t id, awk_array_t a_cookie, elem->parent_array = array; elem->vname = estrdup(index->str_value.str, index->str_value.len); - make_aname(elem); } return awk_true; @@ -2,7 +2,7 @@ NOTE: getopt is part of the C library, so if you don't know what "Keep this file name-space clean" means, talk to drepper@gnu.org before changing it! - Copyright (C) 1987-2014 Free Software Foundation, Inc. + Copyright (C) 1987-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -613,7 +613,7 @@ _getopt_internal_r (int argc, char *const *argv, const char *optstring, fputc_unlocked ('\n', fp); - if (__builtin_expect (fclose (fp) != EOF, 1)) + if (__glibc_likely (fclose (fp) != EOF)) { _IO_flockfile (stderr); @@ -1,5 +1,5 @@ /* Declarations for getopt. - Copyright (C) 1989-2014 Free Software Foundation, Inc. + Copyright (C) 1989-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -1,5 +1,5 @@ /* getopt_long and getopt_long_only entry points for GNU getopt. - Copyright (C) 1987-2014 Free Software Foundation, Inc. + Copyright (C) 1987-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or diff --git a/getopt_int.h b/getopt_int.h index d255c8ee..03d62277 100644 --- a/getopt_int.h +++ b/getopt_int.h @@ -1,5 +1,5 @@ /* Internal declarations for getopt. - Copyright (C) 1989-2014 Free Software Foundation, Inc. + Copyright (C) 1989-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or @@ -1,7 +1,7 @@ #!/bin/sh # install - install a program, script, or datafile -scriptversion=2013-10-30.23; # UTC +scriptversion=2013-12-25.23; # UTC # This originates from X11R5 (mit/util/scripts/install.sh), which was # later released in X11R6 (xc/config/util/install.sh) with the @@ -82,7 +82,7 @@ dir_arg= dst_arg= copy_on_change=false -no_target_directory= +is_target_a_directory=possibly usage="\ Usage: $0 [OPTION]... [-T] SRCFILE DSTFILE @@ -139,14 +139,16 @@ while test $# -ne 0; do -s) stripcmd=$stripprog;; - -t) dst_arg=$2 + -t) + is_target_a_directory=always + dst_arg=$2 # Protect names problematic for 'test' and other utilities. case $dst_arg in -* | [=\(\)!]) dst_arg=./$dst_arg;; esac shift;; - -T) no_target_directory=true;; + -T) is_target_a_directory=never;; --version) echo "$0 $scriptversion"; exit $?;; @@ -161,6 +163,16 @@ while test $# -ne 0; do shift done +# We allow the use of options -d and -T together, by making -d +# take the precedence; this is for compatibility with GNU install. + +if test -n "$dir_arg"; then + if test -n "$dst_arg"; then + echo "$0: target directory not allowed when installing a directory." >&2 + exit 1 + fi +fi + if test $# -ne 0 && test -z "$dir_arg$dst_arg"; then # When -d is used, all remaining arguments are directories to create. # When -t is used, the destination is already specified. @@ -192,6 +204,15 @@ if test $# -eq 0; then fi if test -z "$dir_arg"; then + if test $# -gt 1 || test "$is_target_a_directory" = always; then + if test ! -d "$dst_arg"; then + echo "$0: $dst_arg: Is not a directory." >&2 + exit 1 + fi + fi +fi + +if test -z "$dir_arg"; then do_exit='(exit $ret); exit $ret' trap "ret=129; $do_exit" 1 trap "ret=130; $do_exit" 2 @@ -253,7 +274,7 @@ do # If destination is a directory, append the input filename; won't work # if double slashes aren't ignored. if test -d "$dst"; then - if test -n "$no_target_directory"; then + if test "$is_target_a_directory" = never; then echo "$0: $dst_arg: Is a directory" >&2 exit 1 fi diff --git a/m4/ChangeLog b/m4/ChangeLog index 9ef76c4f..41febbdd 100644 --- a/m4/ChangeLog +++ b/m4/ChangeLog @@ -1,3 +1,8 @@ +2015-01-24 gettextize <bug-gnu-gettext@gnu.org> + + * iconv.m4: Upgrade to gettext-0.19.4. + * po.m4: Upgrade to gettext-0.19.4. + 2014-11-19 gettextize <bug-gnu-gettext@gnu.org> * gettext.m4: Upgrade to gettext-0.19.3. diff --git a/m4/iconv.m4 b/m4/iconv.m4 index 4b29c5f2..4e373631 100644 --- a/m4/iconv.m4 +++ b/m4/iconv.m4 @@ -1,4 +1,4 @@ -# iconv.m4 serial 18 (gettext-0.18.2) +# iconv.m4 serial 19 (gettext-0.18.2) dnl Copyright (C) 2000-2002, 2007-2014 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -72,27 +72,33 @@ AC_DEFUN([AM_ICONV_LINK], if test $am_cv_lib_iconv = yes; then LIBS="$LIBS $LIBICONV" fi - AC_RUN_IFELSE( - [AC_LANG_SOURCE([[ + am_cv_func_iconv_works=no + for ac_iconv_const in '' 'const'; do + AC_RUN_IFELSE( + [AC_LANG_PROGRAM( + [[ #include <iconv.h> #include <string.h> -int main () -{ - int result = 0; + +#ifndef ICONV_CONST +# define ICONV_CONST $ac_iconv_const +#endif + ]], + [[int result = 0; /* Test against AIX 5.1 bug: Failures are not distinguishable from successful returns. */ { iconv_t cd_utf8_to_88591 = iconv_open ("ISO8859-1", "UTF-8"); if (cd_utf8_to_88591 != (iconv_t)(-1)) { - static const char input[] = "\342\202\254"; /* EURO SIGN */ + static ICONV_CONST char input[] = "\342\202\254"; /* EURO SIGN */ char buf[10]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_utf8_to_88591, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res == 0) result |= 1; @@ -105,14 +111,14 @@ int main () iconv_t cd_ascii_to_88591 = iconv_open ("ISO8859-1", "646"); if (cd_ascii_to_88591 != (iconv_t)(-1)) { - static const char input[] = "\263"; + static ICONV_CONST char input[] = "\263"; char buf[10]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_ascii_to_88591, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res == 0) result |= 2; @@ -124,14 +130,14 @@ int main () iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1"); if (cd_88591_to_utf8 != (iconv_t)(-1)) { - static const char input[] = "\304"; + static ICONV_CONST char input[] = "\304"; static char buf[2] = { (char)0xDE, (char)0xAD }; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = 1; char *outptr = buf; size_t outbytesleft = 1; size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if (res != (size_t)(-1) || outptr - buf > 1 || buf[1] != (char)0xAD) result |= 4; @@ -144,14 +150,14 @@ int main () iconv_t cd_88591_to_utf8 = iconv_open ("utf8", "iso88591"); if (cd_88591_to_utf8 != (iconv_t)(-1)) { - static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; + static ICONV_CONST char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; char buf[50]; - const char *inptr = input; + ICONV_CONST char *inptr = input; size_t inbytesleft = strlen (input); char *outptr = buf; size_t outbytesleft = sizeof (buf); size_t res = iconv (cd_88591_to_utf8, - (char **) &inptr, &inbytesleft, + &inptr, &inbytesleft, &outptr, &outbytesleft); if ((int)res > 0) result |= 8; @@ -171,17 +177,14 @@ int main () && iconv_open ("utf8", "eucJP") == (iconv_t)(-1)) result |= 16; return result; -}]])], - [am_cv_func_iconv_works=yes], - [am_cv_func_iconv_works=no], - [ -changequote(,)dnl - case "$host_os" in - aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; - *) am_cv_func_iconv_works="guessing yes" ;; - esac -changequote([,])dnl - ]) +]])], + [am_cv_func_iconv_works=yes], , + [case "$host_os" in + aix* | hpux*) am_cv_func_iconv_works="guessing no" ;; + *) am_cv_func_iconv_works="guessing yes" ;; + esac]) + test "$am_cv_func_iconv_works" = no || break + done LIBS="$am_save_LIBS" ]) case "$am_cv_func_iconv_works" in @@ -1,4 +1,4 @@ -# po.m4 serial 22 (gettext-0.19) +# po.m4 serial 24 (gettext-0.19) dnl Copyright (C) 1995-2014 Free Software Foundation, Inc. dnl This file is free software; the Free Software Foundation dnl gives unlimited permission to copy and/or distribute it, @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 1986, 1988, 1989, 1991-2014 the Free Software Foundation, Inc. + * Copyright (C) 1986, 1988, 1989, 1991-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -24,7 +24,7 @@ */ /* FIX THIS BEFORE EVERY RELEASE: */ -#define UPDATE_YEAR 2014 +#define UPDATE_YEAR 2015 #include "awk.h" #include "getopt.h" @@ -794,10 +794,10 @@ init_vars() (*(vp->assign))(); } - /* Set up deferred variables (loaded only when accessed). */ + /* Load PROCINFO and ENVIRON */ if (! do_traditional) - register_deferred_variable("PROCINFO", load_procinfo); - register_deferred_variable("ENVIRON", load_environ); + load_procinfo(); + load_environ(); } /* path_environ --- put path variable into environment if not already there */ @@ -1,9 +1,9 @@ #! /bin/sh # Common wrapper for a few potentially missing GNU programs. -scriptversion=2012-06-26.16; # UTC +scriptversion=2013-10-28.13; # UTC -# Copyright (C) 1996-2013 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # Originally written by Fran,cois Pinard <pinard@iro.umontreal.ca>, 1996. # This program is free software; you can redistribute it and/or modify @@ -160,7 +160,7 @@ give_advice () ;; autom4te*) echo "You might have modified some maintainer files that require" - echo "the 'automa4te' program to be rebuilt." + echo "the 'autom4te' program to be rebuilt." program_details 'autom4te' ;; bison*|yacc*) diff --git a/po/ChangeLog b/po/ChangeLog index 022e5326..3ef4175b 100644 --- a/po/ChangeLog +++ b/po/ChangeLog @@ -1,3 +1,7 @@ +2015-01-24 Arnold D. Robbins <arnold@skeeve.com> + + * POTFILES.in: Brought up to date. + 2014-11-19 gettextize <bug-gnu-gettext@gnu.org> * Makefile.in.in: Upgrade to gettext-0.19.3. diff --git a/po/POTFILES.in b/po/POTFILES.in index 63461e76..0781efc1 100644 --- a/po/POTFILES.in +++ b/po/POTFILES.in @@ -13,11 +13,17 @@ ext.c extension/filefuncs.c extension/fnmatch.c extension/fork.c +extension/gawkfts.c extension/inplace.c extension/ordchr.c extension/readdir.c extension/readfile.c +extension/revoutput.c +extension/revtwoway.c extension/rwarray.c +extension/rwarray0.c +extension/stack.c +extension/testext.c extension/time.c field.c floatcomp.c @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2013 Free Software Foundation, Inc. + Copyright (C) 2002-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -17,6 +17,14 @@ License along with the GNU C Library; if not, see <http://www.gnu.org/licenses/>. */ +#ifdef HAVE_STDINT_H +#include <stdint.h> +#endif + +#ifdef _LIBC +# include <locale/weight.h> +#endif + static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern, size_t length, reg_syntax_t syntax); static void re_compile_fastmap_iter (regex_t *bufp, @@ -3163,6 +3171,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token, re_token_t token2; start_elem.opr.name = start_name_buf; + start_elem.type = COLL_SYM; ret = parse_bracket_element (&start_elem, regexp, token, token_len, dfa, syntax, first_round); if (BE (ret != REG_NOERROR, 0)) @@ -3206,6 +3215,7 @@ parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token, if (is_range_exp == 1) { end_elem.opr.name = end_name_buf; + end_elem.type = COLL_SYM; ret = parse_bracket_element (&end_elem, regexp, &token2, token_len2, dfa, syntax, 1); if (BE (ret != REG_NOERROR, 0)) @@ -3479,8 +3489,6 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name) int32_t idx1, idx2; unsigned int ch; size_t len; - /* This #include defines a local function! */ -# include <locale/weight.h> /* Calculate the index for equivalence class. */ cp = name; table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); @@ -3490,7 +3498,7 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name) _NL_COLLATE_EXTRAMB); indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); - idx1 = findidx (&cp, -1); + idx1 = findidx (table, indirect, extra, &cp, -1); if (BE (idx1 == 0 || *cp != '\0', 0)) /* This isn't a valid character. */ return REG_ECOLLATE; @@ -3502,7 +3510,7 @@ build_equiv_class (bitset_t sbcset, const unsigned char *name) { char_buf[0] = ch; cp = char_buf; - idx2 = findidx (&cp, 1); + idx2 = findidx (table, indirect, extra, &cp, 1); /* idx2 = table[ch]; */ @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2014 Free Software Foundation, Inc. + Copyright (C) 2002-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -1,6 +1,6 @@ /* Definitions for data structures and routines for the regular expression library. - Copyright (C) 1985, 1989-2014 Free Software Foundation, Inc. + Copyright (C) 1985, 1989-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or diff --git a/regex_internal.c b/regex_internal.c index 9e427081..5a5b9363 100644 --- a/regex_internal.c +++ b/regex_internal.c @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2014 Free Software Foundation, Inc. + Copyright (C) 2002-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. diff --git a/regex_internal.h b/regex_internal.h index 3fc2fc58..9aab5e52 100644 --- a/regex_internal.h +++ b/regex_internal.h @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2014 Free Software Foundation, Inc. + Copyright (C) 2002-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -79,7 +79,6 @@ is_blank (int c) # ifndef _RE_DEFINE_LOCALE_FUNCTIONS # define _RE_DEFINE_LOCALE_FUNCTIONS 1 # include <locale/localeinfo.h> -# include <locale/elem-hash.h> # include <locale/coll-lookup.h> # endif #endif @@ -792,7 +791,7 @@ re_string_elem_size_at (const re_string_t *pstr, int idx) indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); p = pstr->mbs + idx; - findidx (&p, pstr->len - idx); + findidx (table, indirect, extra, &p, pstr->len - idx); return p - pstr->mbs - idx; } else @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2013 Free Software Foundation, Inc. + Copyright (C) 2002-2015 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -3762,6 +3762,10 @@ group_nodes_into_DFAstates (const re_dfa_t *dfa, const re_dfastate_t *state, one collating element like '.', '[a-z]', opposite to the other nodes can only accept one byte. */ +# ifdef _LIBC +# include <locale/weight.h> +# endif + static int internal_function check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, @@ -3883,8 +3887,6 @@ check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, const int32_t *table, *indirect; const unsigned char *weights, *extra; const char *collseqwc; - /* This #include defines a local function! */ -# include <locale/weight.h> /* match with collating_symbol? */ if (cset->ncoll_syms) @@ -3940,7 +3942,7 @@ check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB); indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); - int32_t idx = findidx (&cp, elem_len); + int32_t idx = findidx (table, indirect, extra, &cp, elem_len); if (idx > 0) for (i = 0; i < cset->nequiv_classes; ++i) { @@ -3,7 +3,7 @@ */ /* - * Copyright (C) 1986, 1988, 1989, 1991-2013 the Free Software Foundation, Inc. + * Copyright (C) 1986, 1988, 1989, 1991-2015 the Free Software Foundation, Inc. * * This file is part of GAWK, the GNU implementation of the * AWK Programming Language. @@ -565,7 +565,6 @@ load_symbols() sym_array->parent_array = PROCINFO_node; sym_array->vname = estrdup("identifiers", 11); - make_aname(sym_array); user = make_string("user", 4); extension = make_string("extension", 9); @@ -626,6 +625,67 @@ load_symbols() unref(array); } +/* check_param_names --- make sure no parameter is the name of a function */ + +bool +check_param_names(void) +{ + int i, j; + NODE **list; + NODE *f; + long max; + bool result = true; + NODE n; + + if (func_table->table_size == 0) + return result; + + max = func_table->table_size * 2; + + memset(& n, sizeof n, 0); + n.type = Node_val; + n.flags = STRING|STRCUR; + n.stfmt = -1; + + /* + * assoc_list() returns an array with two elements per awk array + * element. Elements i and i+1 in the C array represent the key + * and value of element j in the awk array. Thus the loops use += 2 + * to go through the awk array. + * + * In this case, the name is in list[i], and the function is + * in list[i+1]. Just what we need. + */ + + list = assoc_list(func_table, "@unsorted", ASORTI); + + for (i = 0; i < max; i += 2) { + f = list[i+1]; + if (f->type == Node_builtin_func || f->param_cnt == 0) + continue; + + /* loop over each param in function i */ + for (j = 0; j < f->param_cnt; j++) { + /* compare to function names */ + + /* use a fake node to avoid malloc/free of make_string */ + n.stptr = f->fparms[j].param; + n.stlen = strlen(f->fparms[j].param); + + if (in_array(func_table, & n)) { + error( + _("function `%s': can't use function `%s' as a parameter name"), + list[i]->stptr, + f->fparms[j].param); + result = false; + } + } + } + + efree(list); + return result; +} + #define pool_size d.dl #define freei x.xi static INSTRUCTION *pool_list; diff --git a/test/ChangeLog b/test/ChangeLog index bff1d808..b0979d8a 100644 --- a/test/ChangeLog +++ b/test/ChangeLog @@ -4,6 +4,49 @@ * nonfatal1.awk, nonfatal1.ok: New files. * nonfatal2.awk, nonfatal2.ok: New files. +2015-02-01 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (paramasfunc1, paramasfunc2): Now need --posix. + * indirectcall.awk: Restore after code change. + +2015-01-30 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (callparam, paramasfunc1, paramasfunc2): New tests. + * callparam.awk, callparam.ok: New files. + * paramasfunc1.awk, paramasfunc1.ok: New files. + * paramasfunc2.awk, paramasfunc2.ok: New files. + * exit.sh, indirectcall.awk: Update after code change. + +2015-01-19 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (profile8): Actually add the test and the files. + Thanks to Hermann Peifer for the report. + +2015-01-16 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (profile8): New test. + * profile8.awk, profile8.ok: New files. + +2015-01-14 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (dumpvars): Grep out ENVIRON and PROCINFO since + those can be different depending on who runs the test. + * dumpvars.ok, id.ok: Updated after code changes. + +2015-01-07 Arnold D. Robbins <arnold@skeeve.com> + + * Makefile.am (regexpbrack): New test. + * regexpbrack.awk, regexpbrack.in, regexpbrack.ok: New files. + + Unrelated: + + * Makefile.am (printfbad4): New test. + * printfbad4.awk, printfbad4.ok: New files. + + Unrelated: + + * testext.ok: Adjust for code changes. + 2014-12-24 Arnold D. Robbins <arnold@skeeve.com> * Makefile.am (badbuild): New test. diff --git a/test/Makefile.am b/test/Makefile.am index 802a3551..053f89fd 100644 --- a/test/Makefile.am +++ b/test/Makefile.am @@ -1,7 +1,7 @@ # # test/Makefile.am --- automake input file for gawk # -# Copyright (C) 1988-2014 the Free Software Foundation, Inc. +# Copyright (C) 1988-2015 the Free Software Foundation, Inc. # # This file is part of GAWK, the GNU implementation of the # AWK Programming Language. @@ -132,6 +132,8 @@ EXTRA_DIST = \ beginfile2.ok \ beginfile2.sh \ binmode1.ok \ + callparam.awk \ + callparam.ok \ charasbytes.awk \ charasbytes.in \ charasbytes.ok \ @@ -646,6 +648,10 @@ EXTRA_DIST = \ out1.ok \ out2.ok \ out3.ok \ + paramasfunc1.awk \ + paramasfunc1.ok \ + paramasfunc2.awk \ + paramasfunc2.ok \ paramdup.awk \ paramdup.ok \ paramres.awk \ @@ -696,6 +702,8 @@ EXTRA_DIST = \ printfbad2.ok \ printfbad3.awk \ printfbad3.ok \ + printfbad4.awk \ + printfbad4.ok \ printfloat.awk \ printhuge.awk \ printhuge.ok \ @@ -717,6 +725,8 @@ EXTRA_DIST = \ profile6.ok \ profile7.awk \ profile7.ok \ + profile8.awk \ + profile8.ok \ prt1eval.awk \ prt1eval.ok \ prtoeval.awk \ @@ -748,6 +758,9 @@ EXTRA_DIST = \ regeq.awk \ regeq.in \ regeq.ok \ + regexpbrack.awk \ + regexpbrack.in \ + regexpbrack.ok \ regexprange.awk \ regexprange.ok \ reginttrad.awk \ @@ -984,7 +997,7 @@ BASIC_TESTS = \ arynocls aryprm1 aryprm2 aryprm3 aryprm4 aryprm5 aryprm6 aryprm7 \ aryprm8 arysubnm asgext awkpath \ back89 backgsub badassign1 badbuild \ - childin clobber closebad clsflnam compare compare2 concat1 concat2 \ + callparam childin clobber closebad clsflnam compare compare2 concat1 concat2 \ concat3 concat4 convfmt \ datanonl defref delargv delarpm2 delarprm delfunc dfamb1 dfastress dynlj \ eofsplit exit2 exitval1 exitval2 \ @@ -1002,10 +1015,11 @@ BASIC_TESTS = \ nlinstr nlstrina noeffect nofile nofmtch noloop1 noloop2 nonl \ noparms nors nulrsend numindex numsubstr \ octsub ofmt ofmta ofmtbig ofmtfidl ofmts ofs1 onlynl opasnidx opasnslf \ + paramasfunc1 paramasfunc2 \ paramdup paramres paramtyp paramuninitglobal parse1 parsefld parseme \ pcntplus posix2008sub prdupval prec printf0 printf1 prmarscl prmreuse \ prt1eval prtoeval \ - rand randtest range1 rebt8b1 redfilnm regeq regexprange regrange reindops \ + rand randtest range1 rebt8b1 redfilnm regeq regexpbrack regexprange regrange reindops \ reparse resplit rri1 rs rsnul1nl rsnulbig rsnulbig2 rstest1 rstest2 \ rstest3 rstest4 rstest5 rswhite \ scalar sclforin sclifin sortempty sortglos splitargv splitarr splitdef \ @@ -1033,8 +1047,9 @@ GAWK_EXT_TESTS = \ manyfiles match1 match2 match3 mbstr1 \ nastyparm next nondec nondec2 \ nonfatal1 nonfatal2 \ - patsplit posix printfbad1 printfbad2 printfbad3 printhuge procinfs \ - profile1 profile2 profile3 profile4 profile5 profile6 profile7 pty1 \ + patsplit posix printfbad1 printfbad2 printfbad3 printfbad4 printhuge procinfs \ + profile1 profile2 profile3 profile4 profile5 profile6 profile7 \ + profile8 pty1 \ rebuf regnul1 regnul2 regx8bit reginttrad reint reint2 rsgetline rsglstdin rsstart1 \ rsstart2 rsstart3 rstest6 shadow sortfor sortu split_after_fpat \ splitarg4 strftime \ @@ -1681,7 +1696,7 @@ beginfile2: dumpvars:: @echo $@ @AWKPATH="$(srcdir)" $(AWK) --dump-variables 1 < "$(srcdir)"/$@.in >/dev/null 2>&1 || echo EXIT CODE: $$? >>_$@ - @mv awkvars.out _$@ + @grep -v ENVIRON < awkvars.out | grep -v PROCINFO > _$@; rm awkvars.out @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ profile1: @@ -1727,6 +1742,11 @@ profile7: @sed 1,2d < ap-$@.out > _$@; rm ap-$@.out @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +profile8: + @echo $@ + @$(AWK) --pretty-print=_$@ -f "$(srcdir)"/$@.awk > /dev/null + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + posix2008sub: @echo $@ @$(AWK) --posix -f "$(srcdir)"/$@.awk > _$@ 2>&1 @@ -2011,6 +2031,15 @@ genpot: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --gen-pot >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +paramasfunc1:: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --posix >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + +paramasfunc2:: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --posix >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ # Targets generated for other tests: include Maketests diff --git a/test/Makefile.in b/test/Makefile.in index 70dd1f4e..25ea167b 100644 --- a/test/Makefile.in +++ b/test/Makefile.in @@ -1,7 +1,7 @@ -# Makefile.in generated by automake 1.14.1 from Makefile.am. +# Makefile.in generated by automake 1.15 from Makefile.am. # @configure_input@ -# Copyright (C) 1994-2013 Free Software Foundation, Inc. +# Copyright (C) 1994-2014 Free Software Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, @@ -17,7 +17,7 @@ # # test/Makefile.am --- automake input file for gawk # -# Copyright (C) 1988-2014 the Free Software Foundation, Inc. +# Copyright (C) 1988-2015 the Free Software Foundation, Inc. # # This file is part of GAWK, the GNU implementation of the # AWK Programming Language. @@ -37,7 +37,17 @@ # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA # VPATH = @srcdir@ -am__is_gnu_make = test -n '$(MAKEFILE_LIST)' && test -n '$(MAKELEVEL)' +am__is_gnu_make = { \ + if test -z '$(MAKELEVEL)'; then \ + false; \ + elif test -n '$(MAKE_HOST)'; then \ + true; \ + elif test -n '$(MAKE_VERSION)' && test -n '$(CURDIR)'; then \ + true; \ + else \ + false; \ + fi; \ +} am__make_running_with_option = \ case $${target_option-} in \ ?) ;; \ @@ -100,9 +110,6 @@ PRE_UNINSTALL = : POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ -DIST_COMMON = $(srcdir)/Maketests $(srcdir)/Makefile.in \ - $(srcdir)/Makefile.am $(top_srcdir)/mkinstalldirs ChangeLog \ - README subdir = test ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ @@ -118,6 +125,7 @@ am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/ulonglong.m4 $(top_srcdir)/configure.ac am__configure_deps = $(am__aclocal_m4_deps) $(CONFIGURE_DEPENDENCIES) \ $(ACLOCAL_M4) +DIST_COMMON = $(srcdir)/Makefile.am $(am__DIST_COMMON) mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs CONFIG_HEADER = $(top_builddir)/config.h CONFIG_CLEAN_FILES = @@ -142,6 +150,8 @@ am__can_run_installinfo = \ *) (install-info --version) >/dev/null 2>&1;; \ esac am__tagged_files = $(HEADERS) $(SOURCES) $(TAGS_FILES) $(LISP) +am__DIST_COMMON = $(srcdir)/Makefile.in $(srcdir)/Maketests \ + $(top_srcdir)/mkinstalldirs ChangeLog README DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST) ACLOCAL = @ACLOCAL@ AMTAR = @AMTAR@ @@ -379,6 +389,8 @@ EXTRA_DIST = \ beginfile2.ok \ beginfile2.sh \ binmode1.ok \ + callparam.awk \ + callparam.ok \ charasbytes.awk \ charasbytes.in \ charasbytes.ok \ @@ -893,6 +905,10 @@ EXTRA_DIST = \ out1.ok \ out2.ok \ out3.ok \ + paramasfunc1.awk \ + paramasfunc1.ok \ + paramasfunc2.awk \ + paramasfunc2.ok \ paramdup.awk \ paramdup.ok \ paramres.awk \ @@ -943,6 +959,8 @@ EXTRA_DIST = \ printfbad2.ok \ printfbad3.awk \ printfbad3.ok \ + printfbad4.awk \ + printfbad4.ok \ printfloat.awk \ printhuge.awk \ printhuge.ok \ @@ -964,6 +982,8 @@ EXTRA_DIST = \ profile6.ok \ profile7.awk \ profile7.ok \ + profile8.awk \ + profile8.ok \ prt1eval.awk \ prt1eval.ok \ prtoeval.awk \ @@ -995,6 +1015,9 @@ EXTRA_DIST = \ regeq.awk \ regeq.in \ regeq.ok \ + regexpbrack.awk \ + regexpbrack.in \ + regexpbrack.ok \ regexprange.awk \ regexprange.ok \ reginttrad.awk \ @@ -1230,7 +1253,7 @@ BASIC_TESTS = \ arynocls aryprm1 aryprm2 aryprm3 aryprm4 aryprm5 aryprm6 aryprm7 \ aryprm8 arysubnm asgext awkpath \ back89 backgsub badassign1 badbuild \ - childin clobber closebad clsflnam compare compare2 concat1 concat2 \ + callparam childin clobber closebad clsflnam compare compare2 concat1 concat2 \ concat3 concat4 convfmt \ datanonl defref delargv delarpm2 delarprm delfunc dfamb1 dfastress dynlj \ eofsplit exit2 exitval1 exitval2 \ @@ -1248,10 +1271,11 @@ BASIC_TESTS = \ nlinstr nlstrina noeffect nofile nofmtch noloop1 noloop2 nonl \ noparms nors nulrsend numindex numsubstr \ octsub ofmt ofmta ofmtbig ofmtfidl ofmts ofs1 onlynl opasnidx opasnslf \ + paramasfunc1 paramasfunc2 \ paramdup paramres paramtyp paramuninitglobal parse1 parsefld parseme \ pcntplus posix2008sub prdupval prec printf0 printf1 prmarscl prmreuse \ prt1eval prtoeval \ - rand randtest range1 rebt8b1 redfilnm regeq regexprange regrange reindops \ + rand randtest range1 rebt8b1 redfilnm regeq regexpbrack regexprange regrange reindops \ reparse resplit rri1 rs rsnul1nl rsnulbig rsnulbig2 rstest1 rstest2 \ rstest3 rstest4 rstest5 rswhite \ scalar sclforin sclifin sortempty sortglos splitargv splitarr splitdef \ @@ -1279,8 +1303,9 @@ GAWK_EXT_TESTS = \ manyfiles match1 match2 match3 mbstr1 \ nastyparm next nondec nondec2 \ nonfatal1 nonfatal2 \ - patsplit posix printfbad1 printfbad2 printfbad3 printhuge procinfs \ - profile1 profile2 profile3 profile4 profile5 profile6 profile7 pty1 \ + patsplit posix printfbad1 printfbad2 printfbad3 printfbad4 printhuge procinfs \ + profile1 profile2 profile3 profile4 profile5 profile6 profile7 \ + profile8 pty1 \ rebuf regnul1 regnul2 regx8bit reginttrad reint reint2 rsgetline rsglstdin rsstart1 \ rsstart2 rsstart3 rstest6 shadow sortfor sortu split_after_fpat \ splitarg4 strftime \ @@ -1358,7 +1383,6 @@ $(srcdir)/Makefile.in: $(srcdir)/Makefile.am $(srcdir)/Maketests $(am__configur echo ' cd $(top_srcdir) && $(AUTOMAKE) --gnu test/Makefile'; \ $(am__cd) $(top_srcdir) && \ $(AUTOMAKE) --gnu test/Makefile -.PRECIOUS: Makefile Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status @case '$?' in \ *config.status*) \ @@ -1367,6 +1391,7 @@ Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status echo ' cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe)'; \ cd $(top_builddir) && $(SHELL) ./config.status $(subdir)/$@ $(am__depfiles_maybe);; \ esac; +$(srcdir)/Maketests $(am__empty): $(top_builddir)/config.status: $(top_srcdir)/configure $(CONFIG_STATUS_DEPENDENCIES) cd $(top_builddir) && $(MAKE) $(AM_MAKEFLAGS) am--refresh @@ -1525,6 +1550,8 @@ uninstall-am: maintainer-clean-generic mostlyclean mostlyclean-generic pdf \ pdf-am ps ps-am tags-am uninstall uninstall-am +.PRECIOUS: Makefile + # Message stuff is to make it a little easier to follow. # Make the pass-fail last and dependent on others to avoid @@ -2107,7 +2134,7 @@ beginfile2: dumpvars:: @echo $@ @AWKPATH="$(srcdir)" $(AWK) --dump-variables 1 < "$(srcdir)"/$@.in >/dev/null 2>&1 || echo EXIT CODE: $$? >>_$@ - @mv awkvars.out _$@ + @grep -v ENVIRON < awkvars.out | grep -v PROCINFO > _$@; rm awkvars.out @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ profile1: @@ -2152,6 +2179,11 @@ profile7: @sed 1,2d < ap-$@.out > _$@; rm ap-$@.out @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +profile8: + @echo $@ + @$(AWK) --pretty-print=_$@ -f "$(srcdir)"/$@.awk > /dev/null + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + posix2008sub: @echo $@ @$(AWK) --posix -f "$(srcdir)"/$@.awk > _$@ 2>&1 @@ -2434,6 +2466,16 @@ genpot: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --gen-pot >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + +paramasfunc1:: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --posix >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + +paramasfunc2:: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk --posix >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ Gt-dummy: # file Maketests, generated from Makefile.am by the Gentests program addcomma: @@ -2566,6 +2608,11 @@ badbuild: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +callparam: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + childin: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @@ -3133,6 +3180,11 @@ regeq: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +regexpbrack: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + regexprange: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @@ -3603,6 +3655,11 @@ printfbad3: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +printfbad4: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + procinfs: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ diff --git a/test/Maketests b/test/Maketests index 08085a0f..9e19a2d5 100644 --- a/test/Maketests +++ b/test/Maketests @@ -130,6 +130,11 @@ badbuild: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +callparam: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + childin: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @@ -697,6 +702,11 @@ regeq: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +regexpbrack: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk < "$(srcdir)"/$@.in >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + regexprange: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @@ -1167,6 +1177,11 @@ printfbad3: @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ +printfbad4: + @echo $@ + @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ + @-$(CMP) "$(srcdir)"/$@.ok _$@ && rm -f _$@ + procinfs: @echo $@ @AWKPATH="$(srcdir)" $(AWK) -f $@.awk >_$@ 2>&1 || echo EXIT CODE: $$? >>_$@ diff --git a/test/callparam.awk b/test/callparam.awk new file mode 100644 index 00000000..b925db01 --- /dev/null +++ b/test/callparam.awk @@ -0,0 +1,6 @@ +BEGIN { f() } + +function f( a, b) +{ + a = b() +} diff --git a/test/callparam.ok b/test/callparam.ok new file mode 100644 index 00000000..00a027e8 --- /dev/null +++ b/test/callparam.ok @@ -0,0 +1,2 @@ +gawk: callparam.awk:5: error: attempt to use non-function `b' in function call +EXIT CODE: 1 diff --git a/test/exit.sh b/test/exit.sh index 9510dcdc..3922f83c 100755 --- a/test/exit.sh +++ b/test/exit.sh @@ -30,7 +30,7 @@ x='function f(){ exit}; BEGINFILE {f()}; NR>1{ f()}; END{print NR}' $AWK 'BEGIN { print "a\nb" }' | $AWK "$x" echo "-- 5" -y='function strip(f) { sub(/.*\//, "", f); return f };' +y='function strip(val) { sub(/.*\//, "", val); return val };' x='BEGINFILE{if(++i==1) exit;}; END{print i, strip(FILENAME)}' $AWK "$y$x" /dev/null $0 @@ -71,3 +71,4 @@ lshift -> builtin SYMTAB -> array strtonum -> builtin toupper -> builtin +ENVIRON -> array diff --git a/test/paramasfunc1.awk b/test/paramasfunc1.awk new file mode 100644 index 00000000..b0d06849 --- /dev/null +++ b/test/paramasfunc1.awk @@ -0,0 +1,9 @@ +BEGIN{ X() } + +function X( abc) +{ + abc = "stamp out " + print abc abc() +} + +function abc() { return "dark corners" } diff --git a/test/paramasfunc1.ok b/test/paramasfunc1.ok new file mode 100644 index 00000000..9ee95116 --- /dev/null +++ b/test/paramasfunc1.ok @@ -0,0 +1,3 @@ +gawk: paramasfunc1.awk:6: error: attempt to use non-function `abc' in function call +gawk: error: function `X': can't use function `abc' as a parameter name +EXIT CODE: 1 diff --git a/test/paramasfunc2.awk b/test/paramasfunc2.awk new file mode 100644 index 00000000..849b3d1b --- /dev/null +++ b/test/paramasfunc2.awk @@ -0,0 +1,10 @@ +BEGIN{ X() } + +function abc() { return "dark corners" } + +function X( abc) +{ + abc = "stamp out " + print abc abc() +} + diff --git a/test/paramasfunc2.ok b/test/paramasfunc2.ok new file mode 100644 index 00000000..2cdf4f66 --- /dev/null +++ b/test/paramasfunc2.ok @@ -0,0 +1,3 @@ +gawk: paramasfunc2.awk:8: error: attempt to use non-function `abc' in function call +gawk: error: function `X': can't use function `abc' as a parameter name +EXIT CODE: 1 diff --git a/test/printfbad4.awk b/test/printfbad4.awk new file mode 100644 index 00000000..dd9220ae --- /dev/null +++ b/test/printfbad4.awk @@ -0,0 +1,5 @@ +BEGIN { + for (i = 1; i <= 10; i++) { + printf "%03$*d %2$d \n", 4, 5, i + } +} diff --git a/test/printfbad4.ok b/test/printfbad4.ok new file mode 100644 index 00000000..71eed3d6 --- /dev/null +++ b/test/printfbad4.ok @@ -0,0 +1,2 @@ +gawk: printfbad4.awk:3: fatal: fatal: must use `count$' on all formats or none +EXIT CODE: 2 diff --git a/test/profile8.awk b/test/profile8.awk new file mode 100644 index 00000000..16252cea --- /dev/null +++ b/test/profile8.awk @@ -0,0 +1,9 @@ +# Some +# header +# comments + +# Add up +{ sum += $1 } + +# Print sum +END { print sum } diff --git a/test/profile8.ok b/test/profile8.ok new file mode 100644 index 00000000..34f7a96b --- /dev/null +++ b/test/profile8.ok @@ -0,0 +1,14 @@ +# Some +# header +# comments + +# Add up +{ + sum += $1 +} + +# Print sum +END { + print sum +} + diff --git a/test/regexpbrack.awk b/test/regexpbrack.awk new file mode 100644 index 00000000..136cd194 --- /dev/null +++ b/test/regexpbrack.awk @@ -0,0 +1,2 @@ +/[]+()0-9.,$%/'"-]*$/ +/^[]+()0-9.,$%/'"-]*$/ diff --git a/test/regexpbrack.in b/test/regexpbrack.in new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/test/regexpbrack.in diff --git a/test/regexpbrack.ok b/test/regexpbrack.ok new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/test/regexpbrack.ok diff --git a/test/testext.ok b/test/testext.ok index 9b36bf72..a828ecb2 100644 --- a/test/testext.ok +++ b/test/testext.ok @@ -15,7 +15,7 @@ try_modify_environ: set_array_element of ENVIRON failed try_modify_environ: marking element "testext" for deletion try_del_environ() could not delete element - pass try_del_environ() could not add an element - pass -var_test: sym_lookup of PROCINFO passed - did not get a value +var_test: sym_lookup of PROCINFO passed - got a value! var_test: sym_lookup of ARGC passed - got a value! var_test: sym_update of ARGC failed - correctly var_test: sym_update("testvar") succeeded @@ -1,9 +1,9 @@ #! /bin/sh # ylwrap - wrapper for lex/yacc invocations. -scriptversion=2012-07-14.08; # UTC +scriptversion=2013-01-12.17; # UTC -# Copyright (C) 1996-2012 Free Software Foundation, Inc. +# Copyright (C) 1996-2014 Free Software Foundation, Inc. # # Written by Tom Tromey <tromey@cygnus.com>. # @@ -40,12 +40,13 @@ get_dirname () # guard FILE # ---------- # The CPP macro used to guard inclusion of FILE. -guard() +guard () { - printf '%s\n' "$from" \ - | sed \ - -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/'\ - -e 's/[^ABCDEFGHIJKLMNOPQRSTUVWXYZ]/_/g' + printf '%s\n' "$1" \ + | sed \ + -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ + -e 's/[^ABCDEFGHIJKLMNOPQRSTUVWXYZ]/_/g' \ + -e 's/__*/_/g' } # quote_for_sed [STRING] @@ -95,17 +96,17 @@ esac # The input. -input="$1" +input=$1 shift # We'll later need for a correct munging of "#line" directives. input_sub_rx=`get_dirname "$input" | quote_for_sed` -case "$input" in +case $input in [\\/]* | ?:[\\/]*) # Absolute path; do nothing. ;; *) # Relative path. Make it absolute. - input="`pwd`/$input" + input=`pwd`/$input ;; esac input_rx=`get_dirname "$input" | quote_for_sed` @@ -121,12 +122,18 @@ fi # The parser itself, the first file, is the destination of the .y.c # rule in the Makefile. parser=$1 + # A sed program to s/FROM/TO/g for all the FROM/TO so that, for # instance, we rename #include "y.tab.h" into #include "parse.h" # during the conversion from y.tab.c to parse.c. -rename_sed= -while test "$#" -ne 0; do - if test "$1" = "--"; then +sed_fix_filenames= + +# Also rename header guards, as Bison 2.7 for instance uses its header +# guard in its implementation file. +sed_fix_header_guards= + +while test $# -ne 0; do + if test x"$1" = x"--"; then shift break fi @@ -141,20 +148,19 @@ while test "$#" -ne 0; do shift to=$1 shift - rename_sed="${rename_sed}s|"`quote_for_sed "$from"`"|$to|g;" + sed_fix_filenames="${sed_fix_filenames}s|"`quote_for_sed "$from"`"|$to|g;" + sed_fix_header_guards="${sed_fix_header_guards}s|"`guard "$from"`"|"`guard "$to"`"|g;" done # The program to run. -prog="$1" +prog=$1 shift # Make any relative path in $prog absolute. -case "$prog" in +case $prog in [\\/]* | ?:[\\/]*) ;; - *[\\/]*) prog="`pwd`/$prog" ;; + *[\\/]*) prog=`pwd`/$prog ;; esac -# FIXME: add hostname here for parallel makes that run commands on -# other machines. But that might take us over the 14-char limit. dirname=ylwrap$$ do_exit="cd '`pwd`' && rm -rf $dirname > /dev/null 2>&1;"' (exit $ret); exit $ret' trap "ret=129; $do_exit" 1 @@ -174,13 +180,13 @@ ret=$? if test $ret -eq 0; then for from in * do - to=`printf '%s\n' "$from" | sed "$rename_sed"` + to=`printf '%s\n' "$from" | sed "$sed_fix_filenames"` if test -f "$from"; then # If $2 is an absolute path name, then just use that, # otherwise prepend '../'. case $to in [\\/]* | ?:[\\/]*) target=$to;; - *) target="../$to";; + *) target=../$to;; esac # Do not overwrite unchanged header files to avoid useless @@ -189,7 +195,7 @@ if test $ret -eq 0; then # output of all other files to a temporary file so we can # compare them to existing versions. if test $from != $parser; then - realtarget="$target" + realtarget=$target target=tmp-`printf '%s\n' "$target" | sed 's|.*[\\/]||g'` fi @@ -197,10 +203,11 @@ if test $ret -eq 0; then # debug information point at an absolute srcdir. Use the real # output file name, not yy.lex.c for instance. Adjust the # include guards too. - FROM=`guard "$from"` - TARGET=`guard "$to"` - sed -e "/^#/!b" -e "s|$input_rx|$input_sub_rx|" -e "$rename_sed" \ - -e "s|$FROM|$TARGET|" "$from" >"$target" || ret=$? + sed -e "/^#/!b" \ + -e "s|$input_rx|$input_sub_rx|" \ + -e "$sed_fix_filenames" \ + -e "$sed_fix_header_guards" \ + "$from" >"$target" || ret=$? # Check whether files must be updated. if test "$from" != "$parser"; then |