diff options
Diffstat (limited to 'doc')
| -rw-r--r-- | doc/ChangeLog | 41 | ||||
| -rw-r--r-- | doc/Makefile.in | 130 | ||||
| -rw-r--r-- | doc/awkcard.in | 28 | ||||
| -rw-r--r-- | doc/gawk.1 | 43 | ||||
| -rw-r--r-- | doc/gawk.info | 2109 | ||||
| -rw-r--r-- | doc/gawk.texi | 944 | ||||
| -rw-r--r-- | doc/texinfo.tex | 1302 |
7 files changed, 3566 insertions, 1031 deletions
diff --git a/doc/ChangeLog b/doc/ChangeLog index 568d7c78..a04db485 100644 --- a/doc/ChangeLog +++ b/doc/ChangeLog @@ -17,6 +17,38 @@ * gawk.texi, gawk.1: Add AWKLIBPATH. +2012-04-27 Arnold D. Robbins <arnold@skeeve.com> + + * gawk.texi: Add that -b affects output. + +2012-04-27 Arnold D. Robbins <arnold@skeeve.com> + + * texinfo.tex: Update to latest from automake 1.12. + +2012-04-09 Arnold D. Robbins <arnold@skeeve.com> + + * texinfo.tex: Update to latest from automake 1.11.4. + +2012-04-11 John Haque <j.eh@mchsi.com> + + * gawk.texi: Change RNDMODE to ROUNDMODE. + * gawk.1, awkcard.in: Ditto. + +2012-04-11 Arnold D. Robbins <arnold@skeeve.com> + + * gawk.texi: Change --arbitrary-precision to --bignum. + * gawk.1: Ditto. + * awkcard.in: Add --bignum, RNDMODE, PREC. + +2012-04-08 Arnold D. Robbins <arnold@skeeve.com> + + * gawk.texi: Editing on new chapter on arbitrary precision numbers. + +2012-03-31 John Haque <j.eh@mchsi.com> + + * gawk.texi, gawk.1: Add text on support for arbitrary precision + numbers. + 2012-02-06 Arnold D. Robbins <arnold@skeeve.com> * gawk.texi, gawk.1: And some minor edits thereunto. @@ -37,6 +69,15 @@ * gawk.1: Same. * awkcard.in: Same. +2012-03-28 Arnold D. Robbins <arnold@skeeve.com> + + * 4.0.1: Release tar ball made. + +2012-02-10 Arnold D. Robbins <arnold@skeeve.com> + + * gawk.texi, awkcard.in: Bump patch level. + * texinfo.tex: Updated from Texinfo CVS. + 2011-12-06 Arnold D. Robbins <arnold@skeeve.com> * gawk.texi: Various typo fixes from mailing list. diff --git a/doc/Makefile.in b/doc/Makefile.in index 6c04681b..81aace35 100644 --- a/doc/Makefile.in +++ b/doc/Makefile.in @@ -1,9 +1,9 @@ -# Makefile.in generated by automake 1.11.1 from Makefile.am. +# Makefile.in generated by automake 1.12 from Makefile.am. # @configure_input@ # Copyright (C) 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, -# 2003, 2004, 2005, 2006, 2007, 2008, 2009 Free Software Foundation, -# Inc. +# 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software +# Foundation, Inc. # This Makefile.in is free software; the Free Software Foundation # gives unlimited permission to copy and/or distribute it, # with or without modifications, as long as this notice is preserved. @@ -39,6 +39,23 @@ # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA # VPATH = @srcdir@ +am__make_dryrun = \ + { \ + am__dry=no; \ + case $$MAKEFLAGS in \ + *\\[\ \ ]*) \ + echo 'am--echo: ; @echo "AM" OK' | $(MAKE) -f - 2>/dev/null \ + | grep '^AM OK$$' >/dev/null || am__dry=yes;; \ + *) \ + for am__flg in $$MAKEFLAGS; do \ + case $$am__flg in \ + *=*|--*) ;; \ + *n*) am__dry=yes; break;; \ + esac; \ + done;; \ + esac; \ + test $$am__dry = yes; \ + } pkgdatadir = $(datadir)/@PACKAGE@ pkgincludedir = $(includedir)/@PACKAGE@ pkglibdir = $(libdir)/@PACKAGE@ @@ -58,20 +75,20 @@ POST_UNINSTALL = : build_triplet = @build@ host_triplet = @host@ subdir = doc -DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in ChangeLog \ - texinfo.tex +DIST_COMMON = $(srcdir)/Makefile.am $(srcdir)/Makefile.in \ + $(top_srcdir)/mkinstalldirs ChangeLog texinfo.tex ACLOCAL_M4 = $(top_srcdir)/aclocal.m4 am__aclocal_m4_deps = $(top_srcdir)/m4/arch.m4 \ $(top_srcdir)/m4/codeset.m4 $(top_srcdir)/m4/gettext.m4 \ $(top_srcdir)/m4/iconv.m4 $(top_srcdir)/m4/intlmacosx.m4 \ - $(top_srcdir)/m4/intmax_t.m4 $(top_srcdir)/m4/inttypes_h.m4 \ $(top_srcdir)/m4/isc-posix.m4 $(top_srcdir)/m4/lcmessage.m4 \ $(top_srcdir)/m4/lib-ld.m4 $(top_srcdir)/m4/lib-link.m4 \ $(top_srcdir)/m4/lib-prefix.m4 $(top_srcdir)/m4/libsigsegv.m4 \ $(top_srcdir)/m4/libtool.m4 $(top_srcdir)/m4/longlong.m4 \ $(top_srcdir)/m4/ltoptions.m4 $(top_srcdir)/m4/ltsugar.m4 \ $(top_srcdir)/m4/ltversion.m4 $(top_srcdir)/m4/lt~obsolete.m4 \ - $(top_srcdir)/m4/nls.m4 $(top_srcdir)/m4/po.m4 \ + $(top_srcdir)/m4/mpfr.m4 $(top_srcdir)/m4/nls.m4 \ + $(top_srcdir)/m4/noreturn.m4 $(top_srcdir)/m4/po.m4 \ $(top_srcdir)/m4/progtest.m4 $(top_srcdir)/m4/readline.m4 \ $(top_srcdir)/m4/socket.m4 $(top_srcdir)/m4/stdint_h.m4 \ $(top_srcdir)/m4/uintmax_t.m4 $(top_srcdir)/m4/ulonglong.m4 \ @@ -96,6 +113,11 @@ TEXI2PDF = $(TEXI2DVI) --pdf --batch MAKEINFOHTML = $(MAKEINFO) --html AM_MAKEINFOHTMLFLAGS = $(AM_MAKEINFOFLAGS) DVIPS = dvips +am__can_run_installinfo = \ + case $$AM_UPDATE_INFO_DIR in \ + n|no|NO) false;; \ + *) (install-info --version) >/dev/null 2>&1;; \ + esac am__installdirs = "$(DESTDIR)$(infodir)" "$(DESTDIR)$(man1dir)" am__vpath_adj_setup = srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; am__vpath_adj = case $$p in \ @@ -118,6 +140,12 @@ am__nobase_list = $(am__nobase_strip_setup); \ am__base_list = \ sed '$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;$$!N;s/\n/ /g' | \ sed '$$!N;$$!N;$$!N;$$!N;s/\n/ /g' +am__uninstall_files_from_dir = { \ + test -z "$$files" \ + || { test ! -d "$$dir" && test ! -f "$$dir" && test ! -r "$$dir"; } \ + || { echo " ( cd '$$dir' && rm -f" $$files ")"; \ + $(am__cd) "$$dir" && rm -f $$files; }; \ + } man1dir = $(mandir)/man1 NROFF = nroff MANS = $(man_MANS) @@ -162,6 +190,7 @@ LD = @LD@ LDFLAGS = @LDFLAGS@ LIBICONV = @LIBICONV@ LIBINTL = @LIBINTL@ +LIBMPFR = @LIBMPFR@ LIBOBJS = @LIBOBJS@ LIBREADLINE = @LIBREADLINE@ LIBS = @LIBS@ @@ -366,12 +395,12 @@ clean-libtool: .texi.dvi: TEXINPUTS="$(am__TEXINFO_TEX_DIR)$(PATH_SEPARATOR)$$TEXINPUTS" \ MAKEINFO='$(MAKEINFO) $(AM_MAKEINFOFLAGS) $(MAKEINFOFLAGS) -I $(srcdir)' \ - $(TEXI2DVI) $< + $(TEXI2DVI) --clean $< .texi.pdf: TEXINPUTS="$(am__TEXINFO_TEX_DIR)$(PATH_SEPARATOR)$$TEXINPUTS" \ MAKEINFO='$(MAKEINFO) $(AM_MAKEINFOFLAGS) $(MAKEINFOFLAGS) -I $(srcdir)' \ - $(TEXI2PDF) $< + $(TEXI2PDF) --clean $< .texi.html: rm -rf $(@:.html=.htp) @@ -396,7 +425,7 @@ gawkinet.pdf: gawkinet.texi gawkinet.html: gawkinet.texi .dvi.ps: TEXINPUTS="$(am__TEXINFO_TEX_DIR)$(PATH_SEPARATOR)$$TEXINPUTS" \ - $(DVIPS) -o $@ $< + $(DVIPS) -o $@ $< uninstall-dvi-am: @$(NORMAL_UNINSTALL) @@ -418,9 +447,7 @@ uninstall-html-am: uninstall-info-am: @$(PRE_UNINSTALL) - @if test -d '$(DESTDIR)$(infodir)' && \ - (install-info --version && \ - install-info --version 2>&1 | sed 1q | grep -i -v debian) >/dev/null 2>&1; then \ + @if test -d '$(DESTDIR)$(infodir)' && $(am__can_run_installinfo); then \ list='$(INFO_DEPS)'; \ for file in $$list; do \ relfile=`echo "$$file" | sed 's|^.*/||'`; \ @@ -498,11 +525,18 @@ maintainer-clean-aminfo: done install-man1: $(man_MANS) @$(NORMAL_INSTALL) - test -z "$(man1dir)" || $(MKDIR_P) "$(DESTDIR)$(man1dir)" - @list=''; test -n "$(man1dir)" || exit 0; \ - { for i in $$list; do echo "$$i"; done; \ - l2='$(man_MANS)'; for i in $$l2; do echo "$$i"; done | \ - sed -n '/\.1[a-z]*$$/p'; \ + @list1=''; \ + list2='$(man_MANS)'; \ + test -n "$(man1dir)" \ + && test -n "`echo $$list1$$list2`" \ + || exit 0; \ + echo " $(MKDIR_P) '$(DESTDIR)$(man1dir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(man1dir)" || exit 1; \ + { for i in $$list1; do echo "$$i"; done; \ + if test -n "$$list2"; then \ + for i in $$list2; do echo "$$i"; done \ + | sed -n '/\.1[a-z]*$$/p'; \ + fi; \ } | while read p; do \ if test -f $$p; then d=; else d="$(srcdir)/"; fi; \ echo "$$d$$p"; echo "$$p"; \ @@ -531,15 +565,15 @@ uninstall-man1: sed -n '/\.1[a-z]*$$/p'; \ } | sed -e 's,.*/,,;h;s,.*\.,,;s,^[^1][0-9a-z]*$$,1,;x' \ -e 's,\.[0-9a-z]*$$,,;$(transform);G;s,\n,.,'`; \ - test -z "$$files" || { \ - echo " ( cd '$(DESTDIR)$(man1dir)' && rm -f" $$files ")"; \ - cd "$(DESTDIR)$(man1dir)" && rm -f $$files; } + dir='$(DESTDIR)$(man1dir)'; $(am__uninstall_files_from_dir) tags: TAGS TAGS: ctags: CTAGS CTAGS: +cscope cscopelist: + distdir: $(DISTFILES) @list='$(MANS)'; if test -n "$$list"; then \ @@ -548,10 +582,10 @@ distdir: $(DISTFILES) if test -f "$$d$$p"; then echo "$$d$$p"; else :; fi; done`; \ if test -n "$$list" && \ grep 'ab help2man is required to generate this page' $$list >/dev/null; then \ - echo "error: found man pages containing the \`missing help2man' replacement text:" >&2; \ + echo "error: found man pages containing the 'missing help2man' replacement text:" >&2; \ grep -l 'ab help2man is required to generate this page' $$list | sed 's/^/ /' >&2; \ echo " to fix them, install help2man, remove and regenerate the man pages;" >&2; \ - echo " typically \`make maintainer-clean' will remove them" >&2; \ + echo " typically 'make maintainer-clean' will remove them" >&2; \ exit 1; \ else :; fi; \ else :; fi @@ -604,10 +638,15 @@ install-am: all-am installcheck: installcheck-am install-strip: - $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ - install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ - `test -z '$(STRIP)' || \ - echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install + if test -z '$(STRIP)'; then \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + install; \ + else \ + $(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \ + install_sh_PROGRAM="$(INSTALL_STRIP_PROGRAM)" INSTALL_STRIP_FLAG=-s \ + "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'" install; \ + fi mostlyclean-generic: clean-generic: @@ -647,8 +686,11 @@ install-dvi: install-dvi-am install-dvi-am: $(DVIS) @$(NORMAL_INSTALL) - test -z "$(dvidir)" || $(MKDIR_P) "$(DESTDIR)$(dvidir)" @list='$(DVIS)'; test -n "$(dvidir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(dvidir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(dvidir)" || exit 1; \ + fi; \ for p in $$list; do \ if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ echo "$$d$$p"; \ @@ -663,18 +705,22 @@ install-html: install-html-am install-html-am: $(HTMLS) @$(NORMAL_INSTALL) - test -z "$(htmldir)" || $(MKDIR_P) "$(DESTDIR)$(htmldir)" @list='$(HTMLS)'; list2=; test -n "$(htmldir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(htmldir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(htmldir)" || exit 1; \ + fi; \ for p in $$list; do \ if test -f "$$p" || test -d "$$p"; then d=; else d="$(srcdir)/"; fi; \ $(am__strip_dir) \ - if test -d "$$d$$p"; then \ + d2=$$d$$p; \ + if test -d "$$d2"; then \ echo " $(MKDIR_P) '$(DESTDIR)$(htmldir)/$$f'"; \ $(MKDIR_P) "$(DESTDIR)$(htmldir)/$$f" || exit 1; \ - echo " $(INSTALL_DATA) '$$d$$p'/* '$(DESTDIR)$(htmldir)/$$f'"; \ - $(INSTALL_DATA) "$$d$$p"/* "$(DESTDIR)$(htmldir)/$$f" || exit $$?; \ + echo " $(INSTALL_DATA) '$$d2'/* '$(DESTDIR)$(htmldir)/$$f'"; \ + $(INSTALL_DATA) "$$d2"/* "$(DESTDIR)$(htmldir)/$$f" || exit $$?; \ else \ - list2="$$list2 $$d$$p"; \ + list2="$$list2 $$d2"; \ fi; \ done; \ test -z "$$list2" || { echo "$$list2" | $(am__base_list) | \ @@ -686,9 +732,12 @@ install-info: install-info-am install-info-am: $(INFO_DEPS) @$(NORMAL_INSTALL) - test -z "$(infodir)" || $(MKDIR_P) "$(DESTDIR)$(infodir)" @srcdirstrip=`echo "$(srcdir)" | sed 's|.|.|g'`; \ list='$(INFO_DEPS)'; test -n "$(infodir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(infodir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(infodir)" || exit 1; \ + fi; \ for file in $$list; do \ case $$file in \ $(srcdir)/*) file=`echo "$$file" | sed "s|^$$srcdirstrip/||"`;; \ @@ -706,8 +755,7 @@ install-info-am: $(INFO_DEPS) echo " $(INSTALL_DATA) $$files '$(DESTDIR)$(infodir)'"; \ $(INSTALL_DATA) $$files "$(DESTDIR)$(infodir)" || exit $$?; done @$(POST_INSTALL) - @if (install-info --version && \ - install-info --version 2>&1 | sed 1q | grep -i -v debian) >/dev/null 2>&1; then \ + @if $(am__can_run_installinfo); then \ list='$(INFO_DEPS)'; test -n "$(infodir)" || list=; \ for file in $$list; do \ relfile=`echo "$$file" | sed 's|^.*/||'`; \ @@ -721,8 +769,11 @@ install-pdf: install-pdf-am install-pdf-am: $(PDFS) @$(NORMAL_INSTALL) - test -z "$(pdfdir)" || $(MKDIR_P) "$(DESTDIR)$(pdfdir)" @list='$(PDFS)'; test -n "$(pdfdir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(pdfdir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(pdfdir)" || exit 1; \ + fi; \ for p in $$list; do \ if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ echo "$$d$$p"; \ @@ -734,8 +785,11 @@ install-ps: install-ps-am install-ps-am: $(PSS) @$(NORMAL_INSTALL) - test -z "$(psdir)" || $(MKDIR_P) "$(DESTDIR)$(psdir)" @list='$(PSS)'; test -n "$(psdir)" || list=; \ + if test -n "$$list"; then \ + echo " $(MKDIR_P) '$(DESTDIR)$(psdir)'"; \ + $(MKDIR_P) "$(DESTDIR)$(psdir)" || exit 1; \ + fi; \ for p in $$list; do \ if test -f "$$p"; then d=; else d="$(srcdir)/"; fi; \ echo "$$d$$p"; \ diff --git a/doc/awkcard.in b/doc/awkcard.in index c8d41833..b7d87691 100644 --- a/doc/awkcard.in +++ b/doc/awkcard.in @@ -1,7 +1,8 @@ .\" AWK Reference Card --- Arnold Robbins, arnold@skeeve.com .\" .\" Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, -.\" 2003, 2004, 2005, 2007, 2009, 2010, 2011 Free Software Foundation, Inc. +.\" 2003, 2004, 2005, 2007, 2009, 2010, 2011, 2012 +.\" Free Software Foundation, Inc. .\" .\" Permission is granted to make and distribute verbatim copies of .\" this reference card provided the copyright notice and this permission @@ -100,7 +101,7 @@ Brian Kernighan and Michael Brennan who reviewed it. .SL .nf \*(FRCopyright \(co 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, -2005, 2007, 2009, 2010, 2011 Free Software Foundation, Inc. +2005, 2007, 2009, 2010, 2011, 2012 Free Software Foundation, Inc. .nf .BT @@ -281,6 +282,8 @@ If \*(FIvalue\*(FR is \*(FCinvalid\*(FR, only issue warnings about things that are actually invalid (not fully implemented yet). +.TI "\*(FC\-M\*(FR, \*(FC\-\^\-bignum\*(FR +Enable arbitrary-precision arithmetic. .TI "\*(FC\-n\*(FR, \*(FC\-\^\-non\-decimal\-data\*(FR Recognize octal and hexadecimal values in input data. \*(FIUse this option with great caution!\*(FR @@ -299,10 +302,11 @@ of each statement in the program. .TI "\*(FC\-P\*(FR, \*(FC\-\^\-posix\*(FR Disable common and GNU extensions. .TI "\*(FC\-r\*(FR, \*(FC\-\^\-re\-interval\*(FR -Enable \*(FIinterval expressions\*(FR in regular -expression matching (see \fHRegular -Expressions\fP below). Useful if -\*(FC\-\^\-traditional\*(FR is specified.\*(CB +Enable \*(FIinterval expressions\*(FR.\*(CB +... in regular +... expression matching (see \fHRegular +... Expressions\fP below). Useful if +... \*(FC\-\^\-traditional\*(FR is specified .in -4n .EB "\s+2\f(HBCOMMAND LINE ARGUMENTS (\*(GK\f(HB)\*(FR\s0" @@ -609,7 +613,11 @@ T} \*(FCORS\fP T{ Output record separator, a newline by default. T} -\*(CB\*(FCPROCINFO\fP T{ +\*(CB\*(FCPREC\fP T{ +The working precision of arbitrary precision floating-point +numbers, 53 by default. +T} +\*(FCPROCINFO\fP T{ Elements of this array provide access to information about the running AWK program. See \*(AM for details.\*(CD @@ -618,6 +626,10 @@ T} Length of the string matched by \*(FCmatch()\*(FR; \-1 if no match. T} +\*(CB\*(FCROUNDMODE\fP T{ +The rounding mode to use for arbitrary precision arithmetic, +by default \*(FC"N"\fP.\*(CD +T} \*(FCRS\fP T{ Input record separator, a newline by default (see \fHRecords\fP above). @@ -1914,7 +1926,7 @@ to use the current domain.\*(CB .ES .nf \*(CDHost: \*(FCftp.gnu.org\*(FR -File: \*(FC/gnu/gawk/gawk-4.0.0.tar.gz\fP +File: \*(FC/gnu/gawk/gawk-4.0.1.tar.gz\fP .in +.2i .fi GNU \*(AK (\*(GK). There may be a later version. @@ -354,6 +354,16 @@ only warnings about things that are actually invalid are issued. (This is not fully implemented yet.) .TP .PD 0 +.B \-M +.TP +.PD +.B \-\^\-bignum +Force arbitrary precision arithmetic on numbers. This option has +no effect if +.I gawk +is not compiled to use the GNU MPFR and MP libraries. +.TP +.PD 0 .B \-n .TP .PD @@ -1040,6 +1050,10 @@ The output field separator, a space by default. .B ORS The output record separator, by default a newline. .TP +.B PREC +The working precision of arbitrary precision floating-point +numbers, 53 by default. +.TP .B PROCINFO The elements of this array provide access to information about the running \*(AK program. @@ -1146,11 +1160,40 @@ where is a redirection string or a filename. A value of zero or less than zero means no timeout. .TP +\fBPROCINFO["mpfr_version"]\fP +the version of the GNU MPFR library used for arbitrary precision +number support in +.IR gawk . +.TP +\fBPROCINFO["gmp_version"]\fP +the version of the GNU MP library used for arbitrary precision +number support in +.IR gawk . +.TP +\fBPROCINFO["prec_max"]\fP +the maximum precision supported by the GNU MPFR library for +arbitrary precision floating-point numbers. +.TP +\fBPROCINFO["prec_min"]\fP +the minimum precision allowed by the GNU MPFR library for +arbitrary precision floating-point numbers. +.TP \fBPROCINFO["version"]\fP the version of .IR gawk . .RE .TP +.B ROUNDMODE +The rounding mode to use for arbitrary precision arithmetic on +numbers, by default \fB"N"\fR (IEEE-754 roundTiesToEven mode). +The accepted values are +\fB"N"\fR or \fB"n"\fR for roundTiesToEven, +\fB"U"\fR or \fB"u"\fR for roundTowardPositive, +\fB"D"\fR or \fB"d"\fR for roundTowardNegative, +\fB"Z"\fR or \fB"z"\fR for roundTowardZero, +and if your version of GNU MPFR library supports it, +\fB"A"\fR or \fB"a"\fR for roundTiesToAway. +.TP .B RS The input record separator, by default a newline. .TP diff --git a/doc/gawk.info b/doc/gawk.info index 75e1f481..68460636 100644 --- a/doc/gawk.info +++ b/doc/gawk.info @@ -10,8 +10,8 @@ START-INFO-DIR-ENTRY END-INFO-DIR-ENTRY Copyright (C) 1989, 1991, 1992, 1993, 1996, 1997, 1998, 1999, 2000, -2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011 Free Software -Foundation, Inc. +2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011, 2012 Free +Software Foundation, Inc. This is Edition 4 of `GAWK: Effective AWK Programming: A User's @@ -42,8 +42,8 @@ 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, 1997, 1998, 1999, 2000, -2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011 Free Software -Foundation, Inc. +2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011, 2012 Free +Software Foundation, Inc. This is Edition 4 of `GAWK: Effective AWK Programming: A User's @@ -89,6 +89,8 @@ texts being (a) (see below), and with the Back-Cover Texts being (b) * Functions:: Built-in and user-defined functions. * Internationalization:: Getting `gawk' to speak your language. +* Arbitrary Precision Arithmetic:: Arbitrary precision arithmetic with + `gawk'. * Advanced Features:: Stuff for advanced users, specific to `gawk'. * Library Functions:: A Library of `awk' Functions. @@ -357,6 +359,21 @@ texts being (a) (see below), and with the Back-Cover Texts being (b) * I18N Portability:: `awk'-level portability issues. * I18N Example:: A simple i18n example. * Gawk I18N:: `gawk' is also internationalized. +* Floating-point Programming:: Effective floating-point programming. +* Floating-point Representation:: Binary floating-point representation. +* Floating-point Context:: Floating-point context. +* Rounding Mode:: Floating-point rounding mode. +* Arbitrary Precision Floats:: Arbitrary precision floating-point + arithmetic with `gawk'. +* Setting Precision:: Setting the working precision. +* Setting Rounding Mode:: Setting the rounding mode. +* Floating-point Constants:: Representing floating-point constants. +* Changing Precision:: Changing the precision of a number. +* Exact Arithmetic:: Exact arithmetic with floating-point numbers. +* Integer Programming:: Effective integer programming. +* Arbitrary Precision Integers:: Arbitrary precision integer + arithmetic with `gawk'. +* MPFR and GMP Libraries:: Information about the MPFR and GMP libraries. * Nondecimal Data:: Allowing nondecimal input data. * Array Sorting:: Facilities for controlling array traversal and sorting arrays. @@ -1105,10 +1122,12 @@ it is today. It has been and continues to be a pleasure working with this team of fine people. John Haque contributed the modifications to convert `gawk' into a -byte-code interpreter, including the debugger. Stephen Davies -contributed to the effort to bring the byte-code changes into the -mainstream code base. Efraim Yawitz contributed the initial text of -*note Debugger::. +byte-code interpreter, including the debugger, and the additional +modifications for support of arbitrary precision arithmetic. Stephen +Davies contributed to the effort to bring the byte-code changes into +the mainstream code base. Efraim Yawitz contributed the initial text +of *note Debugger::. John Haque contributed the initial text of *note +Arbitrary Precision Arithmetic::. I would like to thank Brian Kernighan for invaluable assistance during the testing and debugging of `gawk', and for ongoing help and @@ -1398,7 +1417,8 @@ pass to that interpreter. The operating system then runs the interpreter with the given argument and the full argument list of the executed program. The first argument in the list is the full file name of the `awk' program. The rest of the argument list contains either -options to `awk', or data files, or both. +options to `awk', or data files, or both. Note that on many systems +`awk' may be found in `/usr/bin' instead of in `/bin'. Caveat Emptor. File: gawk.info, Node: Comments, Next: Quoting, Prev: Executable Scripts, Up: Running gawk @@ -2187,6 +2207,9 @@ 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 + treated as single-byte characters. + Normally, `gawk' follows the POSIX standard and attempts to process its input data according to the current locale. This can often involve converting multibyte characters into wide characters @@ -2300,6 +2323,12 @@ The following list describes options mandated by the POSIX standard: inappropriate construct. As `awk' programs are usually short, doing so is not burdensome. +`-M' +`--bignum' + Force arbitrary precision arithmetic on numbers. This option has + no effect if `gawk' is not compiled to use the GNU MPFR and MP + libraries (*note Arbitrary Precision Arithmetic::). + `-n' `--non-decimal-data' Enable automatic interpretation of octal and hexadecimal values in @@ -3249,6 +3278,10 @@ sequences and that are not listed in the table stand for themselves: constants are valid and work the way you want them to, using any version of `awk'.(2) + Finally, when `{' and `}' appear in regexp constants in a way that + cannot be interpreted as an interval expression (such as + `/q{a}/'), then they stand for themselves. + In regular expressions, the `*', `+', and `?' operators, as well as the braces `{' and `}', have the highest precedence, followed by concatenation, and finally by `|'. As in arithmetic, parentheses can @@ -3332,7 +3365,7 @@ Class Meaning `[:upper:]' Uppercase alphabetic characters. `[:xdigit:]'Characters that are hexadecimal digits. -Table 3.1: POSIX Character Classes +Table 3.1: POSIX Character Classes For example, before the POSIX standard, you had to write `/[A-Za-z0-9]/' to match alphanumeric characters. If your character @@ -5295,7 +5328,7 @@ COMMAND `|& getline' Sets `$0' and `NF' Extension COMMAND `|& getline' Sets VAR Extension VAR -Table 4.1: getline Variants and What They Set +Table 4.1: getline Variants and What They Set File: gawk.info, Node: Read Timeout, Next: Command line directories, Prev: Getline, Up: Reading Files @@ -6963,7 +6996,7 @@ Feature Default `--posix' or `--use-lc-numeric' Input Use period Use locale `strtonum()'Use period Use locale -Table 6.1: Locale Decimal Point versus A Period +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 @@ -7305,7 +7338,7 @@ LVALUE `%=' MODULUS Sets LVALUE to its remainder by MODULUS. LVALUE `^=' POWER LVALUE `**=' POWER Raises LVALUE to the power POWER. (c.e.) -Table 6.2: Arithmetic Assignment Operators +Table 6.2: Arithmetic Assignment Operators NOTE: Only the `^=' operator is specified by POSIX. For maximum portability, do not use the `**=' operator. @@ -7610,7 +7643,7 @@ X `!~' Y True if the string X does not match the regexp SUBSCRIPT `in' True if the array ARRAY has an element with the ARRAY subscript SUBSCRIPT. -Table 6.3: Relational Operators +Table 6.3: Relational Operators Comparison expressions have the value one if true and zero if false. When comparing operands of mixed types, numeric operands are converted @@ -9351,6 +9384,15 @@ specific to `gawk' are marked with a pound sign (`#'). every `print' statement. Its default value is `"\n"', the newline character. (*Note Output Separators::.) +`PREC #' + The working precision of arbitrary precision floating-point + numbers, 53 by default (*note Setting Precision::). + +`ROUNDMODE #' + The rounding mode to use for arbitrary precision arithmetic on + numbers, by default `"N"' (`roundTiesToEven' in the IEEE-754 + standard) (*note Setting Rounding Mode::). + `RS' This is `awk''s input record separator. Its default value is a string containing a single newline character, which means that an @@ -9557,6 +9599,23 @@ with a pound sign (`#'). `PROCINFO["version"]' The version of `gawk'. + The following additional elements in the array are available to + provide information about the MPFR and GMP libraries if your + version of `gawk' supports arbitrary precision numbers (*note + Arbitrary Precision Arithmetic::): + + `PROCINFO["mpfr_version"]' + The version of the GNU MPFR library. + + `PROCINFO["gmp_version"]' + The version of the GNU MP library. + + `PROCINFO["prec_max"]' + The maximum precision supported by MPFR. + + `PROCINFO["prec_min"]' + The minimum precision required by MPFR. + On some systems, there may be elements in the array, `"group1"' through `"groupN"' for some N. N is the number of supplementary groups that the process has. Use the `in' operator to test for @@ -10726,7 +10785,8 @@ with numbers. Optional parameters are enclosed in square brackets ([ ]): `atan2(Y, X)' - Return the arctangent of `Y / X' in radians. + Return the arctangent of `Y / X' in radians. You can use `pi = + atan2(0, -1)' to retrieve the value of pi. `cos(X)' Return the cosine of X, with X in radians. @@ -11421,7 +11481,7 @@ is illustrated in *note table-sub-escapes::. `\\\\\\&' `\\\&' a literal `\\&' `\\q' `\q' a literal `\q' -Table 9.1: Historical Escape Sequence Processing for `sub()' and +Table 9.1: Historical Escape Sequence Processing for `sub()' and `gsub()' This table shows both the lexical-level processing, where an odd number @@ -11446,8 +11506,7 @@ literally. The interpretation of `\' and `&' then becomes as shown in `\\\\&' `\\&' a literal `\', then the matched text `\\\\\\&' `\\\&' a literal `\&' -Table 9.2: 1992 POSIX Rules for sub and gsub Escape Sequence -Processing +Table 9.2: 1992 POSIX Rules for sub and gsub Escape Sequence Processing This appears to solve the problem. Unfortunately, the phrasing of the standard is unusual. It says, in effect, that `\' turns off the special @@ -11476,7 +11535,7 @@ table-sub-proposed::. `\\q' `\q' a literal `\q' `\\\\' `\\' `\\' -Table 9.3: Proposed rules for sub and backslash +Table 9.3: Proposed rules for sub and backslash In a nutshell, at the runtime level, there are now three special sequences of characters (`\\\&', `\\&' and `\&') whereas historically @@ -11503,7 +11562,7 @@ rules are presented in *note table-posix-sub::. `\\q' `\q' a literal `\q' `\\\\' `\\' `\' -Table 9.4: POSIX rules for `sub()' and `gsub()' +Table 9.4: POSIX rules for `sub()' and `gsub()' The only case where the difference is noticeable is the last one: `\\\\' is seen as `\\' and produces `\' instead of `\\'. @@ -11535,7 +11594,7 @@ the `\' does not, as shown in *note table-gensub-escapes::. `\\\\\\&' `\\\&' a literal `\&' `\\q' `\q' a literal `q' -Table 9.5: Escape Sequence Processing for `gensub()' +Table 9.5: 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 @@ -12084,7 +12143,7 @@ table-bitwise-ops::. 0 | 0 0 | 0 1 | 0 1 1 | 0 1 | 1 1 | 1 0 -Table 9.6: Bitwise Operations +Table 9.6: Bitwise Operations As you can see, the result of an AND operation is 1 only when _both_ bits are 1. The result of an OR operation is 1 if _either_ bit is 1. @@ -13070,7 +13129,7 @@ example, in the following case: `gawk' will look up the actual function to call only once. -File: gawk.info, Node: Internationalization, Next: Advanced Features, Prev: Functions, Up: Top +File: gawk.info, Node: Internationalization, Next: Arbitrary Precision Arithmetic, Prev: Functions, Up: Top 10 Internationalization with `gawk' *********************************** @@ -13650,9 +13709,745 @@ writing, the latest version of GNU `gettext' is version 0.18.1 usage messages, warnings, and fatal errors in the local language. -File: gawk.info, Node: Advanced Features, Next: Library Functions, Prev: Internationalization, Up: Top +File: gawk.info, Node: Arbitrary Precision Arithmetic, Next: Advanced Features, Prev: Internationalization, Up: Top + +11 Arbitrary Precision Arithmetic with `gawk' +********************************************* + + There's a credibility gap: We don't know how much of the + computer's answers to believe. Novice computer users solve this + problem by implicitly trusting in the computer as an infallible + authority; they tend to believe that all digits of a printed + answer are significant. Disillusioned computer users have just the + opposite approach; they are constantly afraid that their answers + are almost meaningless. + + Donald Knuth(1) + + This minor node decsribes how to use the arbitrary precision (also +known as "multiple precision" or "infinite precision") numeric +capabilites in `gawk' to produce maximally accurate results when you +need it. But first you should check if your version of `gawk' supports +arbitrary precision arithmetic. The easiest way to find out is to look +at the output of the following command: + + $ gawk --version + -| GNU Awk 4.1.0 (GNU MPFR 3.1.0, GNU MP 5.0.3) + -| Copyright (C) 1989, 1991-2012 Free Software Foundation. + ... + + `gawk' uses the GNU MPFR (http://www.mpfr.org) and GNU MP +(http://gmplib.org) (GMP) libraries for arbitrary precision arithmetic +on numbers. So if you do not see the names of these libraries in the +output, then your version of `gawk' does not support arbitrary +precision arithmetic. + + Even if you aren't interested in arbitrary precision arithmetic, you +may still benifit from knowing about how `gawk' handles numbers in +general, and the limitations of doing arithmetic with ordinary `gawk' +numbers. + +* Menu: + +* Floating-point Programming:: Effective Floating-point Programming. +* Floating-point Representation:: Binary Floating-point Representation. +* Floating-point Context:: Floating-point Context. +* Rounding Mode:: Floating-point Rounding Mode. +* Arbitrary Precision Floats:: Arbitrary Precision Floating-point + Arithmetic with `gawk'. +* Setting Precision:: Setting the Working Precision. +* Setting Rounding Mode:: Setting the Rounding Mode. +* Floating-point Constants:: Representing Floating-point Constants. +* Changing Precision:: Changing the Precision of a Number. +* Exact Arithmetic:: Exact Arithmetic with Floating-point Numbers. +* Integer Programming:: Effective Integer Programming. +* Arbitrary Precision Integers:: Arbitrary Precision Integer + Arithmetic with `gawk'. +* MPFR and GMP Libraries:: Information About the MPFR and GMP Libraries. + + ---------- Footnotes ---------- + + (1) Donald E. Knuth. `The Art of Computer Programming'. Volume 2, +`Seminumerical Algorithms', third edition, 1998, ISBN 0-201-89683-4, p. +229. + + +File: gawk.info, Node: Floating-point Programming, Next: Floating-point Representation, Up: Arbitrary Precision Arithmetic + +11.1 Effective Floating-point Programming +========================================= + +Numerical programming is an extensive area; if you need to develop +sophisticated numerical algorithms then `gawk' may not be the ideal +tool, and this documentation may not be sufficient. It might require a +book or two to communicate how to compute with ideal accuracy and +precision and the result often depends on the particular application. + + NOTE: A floating-point calculation's "accuracy" is how close it + comes to the real value. This is as opposed to the "precision", + which usually refers to the number of bits used to represent the + number (see the Wikipedia article + (http://en.wikipedia.org/wiki/Accuracy_and_precision) for more + information). + + Binary floating-point representations and arithmetic are inexact. +Simple values like 0.1 cannot be precisely represented using binary +floating-point numbers, and the limited precision of floating-point +numbers means that slight changes in the order of operations or the +precision of intermediate storage can change the result. To make +matters worse with arbitrary precision floating-point, you can set the +precision before starting a computation, but then you cannot be sure of +the number of significant decimal places in the final result. + + Sometimes you need to think more about what you really want and +what's really happening. Consider the two numbers in the following +example: + + x = 0.875 # 1/2 + 1/4 + 1/8 + y = 0.425 + + Unlike the number in `y', the number stored in `x' is exactly +representable in binary since it can be written as a finite sum of one +or more fractions whose denominators are all powers of two. When +`gawk' reads a floating-point number from program source, it +automatically rounds that number to whatever precision your machine +supports. If you try to print the numeric content of a variable using +an output format string of `"%.17g"', it may not produce the same +number as you assigned to it: + + $ gawk 'BEGIN { x = 0.875; y = 0.425 + > printf("%0.17g, %0.17g\n", x, y) }' + -| 0.875, 0.42499999999999999 + + Often the error is so small you do not even notice it, and if you do, +you can always specify how much precision you would like in your output. +Usually this is a format string like `"%.15g"', which when used in the +previous example, produces an output identical to the input. + + Because the underlying representation can be little bit off from the +exact value, comparing floats to see if they are equal is generally not +a good idea. Here is an example where it does not work like you expect: + + $ gawk 'BEGIN { print (0.1 + 12.2 == 12.3) }' + -| 0 + + The loss of accuracy during a single computation with floating-point +numbers usually isn't enough to worry about. However, if you compute a +value which is the result of a sequence of floating point operations, +the error can accumulate and greatly affect the computation itself. +Here is an attempt to compute the value of the constant pi using one of +its many series representations: + + BEGIN { + x = 1.0 / sqrt(3.0) + n = 6 + for (i = 1; i < 30; i++) { + n = n * 2.0 + x = (sqrt(x * x + 1) - 1) / x + printf("%.15f\n", n * x) + } + } + + When run, the early errors propagating through later computations +cause the loop to terminate prematurely after an attempt to divide by +zero. + + $ gawk -f pi.awk + -| 3.215390309173475 + -| 3.159659942097510 + -| 3.146086215131467 + -| 3.142714599645573 + ... + -| 3.224515243534819 + -| 2.791117213058638 + -| 0.000000000000000 + error--> gawk: pi.awk:6: fatal: division by zero attempted + + Here is one more example where the inaccuracies in internal +representations yield an unexpected result: + + $ gawk 'BEGIN { + > for (d = 1.1; d <= 1.5; d += 0.1) + > i++ + > print i + > }' + -| 4 + + Can computation using aribitrary precision help with the previous +examples? If you are impatient to know, see *note Exact Arithmetic::. + + Instead of aribitrary precision floating-point arithmetic, often all +you need is an adjustment of your logic or a different order for the +operations in your calculation. The stability and the accuracy of the +computation of the constant pi in the previous example can be enhanced +by using the following simple algebraic transformation: + + (sqrt(x * x + 1) - 1) / x = x / (sqrt(x * x + 1) + x) + + There is no need to be unduly suspicious about the results from +floating-point arithmetic. The lesson to remember is that +floating-point math is always more complex than the math using pencil +and paper. In order to take advantage of the power of computer +floating-point, you need to know its limitations and work within them. +For most casual use of floating-point arithmetic, you will often get +the expected result in the end if you simply round the display of your +final results to the correct number of significant decimal digits. +Avoid presenting numerical data in a manner that implies better +precision than is actually the case. + + +File: gawk.info, Node: Floating-point Representation, Next: Floating-point Context, Prev: Floating-point Programming, Up: Arbitrary Precision Arithmetic + +11.2 Binary Floating-point Representation +========================================= + +Although floating-point representations vary from machine to machine, +the most commonly encountered representation is that defined by the +IEEE 754 Standard. An IEEE-754 format value has three components: + + * a sign bit telling whether the number is positive or negative, -11 Advanced Features of `gawk' + * an "exponent" giving its order of magnitude, E, + + * and a "significand", S, specifying the actual digits of the number. + + The value of the number is then S * 2^E. The first bit of a +non-zero binary significand is always one, so the significand in an +IEEE-754 format only includes the fractional part, leaving the leading +one implicit. + + Three of the standard IEEE-754 types are 32-bit single precision, +64-bit double precision and 128-bit quadruple precision. The standard +also specifies extended precision formats to allow greater precisions +and larger exponent ranges. + + +File: gawk.info, Node: Floating-point Context, Next: Rounding Mode, Prev: Floating-point Representation, Up: Arbitrary Precision Arithmetic + +11.3 Floating-point Context +=========================== + +A floating-point context defines the environment for arithmetic +operations. It governs precision, sets rules for rounding and limits +range for exponents. The context has the following primary components: + +`precision' + Precision of the floating-point format in bits. + +`emax' + Maximum exponent allowed for this format. + +`emin' + Minimum exponent allowed for this format. + +`underflow behavior' + The format may or may not support gradual underflow. + +`rounding' + The rounding mode of this context. + + *note table-ieee-formats:: lists the precision and exponent field +values for the basic IEEE-754 binary formats: + +Name Total bits Precision emin emax +--------------------------------------------------------------------------- +Single 32 24 -126 +127 +Double 64 53 -1022 +1023 +Quadruple 128 113 -16382 +16383 + +Table 11.1: Basic IEEE Formats + + NOTE: The precision numbers include the implied leading one that + gives them one extra bit of significand. + + A floating-point context can also determine which signals are treated +as exceptions, and can set rules for arithmetic with special values. +Please consult the IEEE-754 standard or other resources for details. + + `gawk' ordinarily uses the hardware double precision representation +for numbers. On most systems, this is IEEE-754 floating-point format, +corresponding to 64-bit binary with 53 bits of precision. + + NOTE: In case an underflow occurs, the standard allows, but does + not require, the result from an arithmetic operation to be a + number smaller than the smallest nonzero normalized number. Such + numbers do not have as many significant digits as normal numbers, + and are called "denormals" or "subnormals". The alternative, + simply returning a zero, is called "flush to zero". The basic + IEEE-754 binary formats support subnormal numbers. + + +File: gawk.info, Node: Rounding Mode, Next: Arbitrary Precision Floats, Prev: Floating-point Context, Up: Arbitrary Precision Arithmetic + +11.4 Floating-point Rounding Mode +================================= + +The "rounding mode" specifies the behavior for the results of numerical +operations when discarding extra precision. Each rounding mode indicates +how the least significant returned digit of a rounded result is to be +calculated. The `ROUNDMODE' variable (*note Setting Rounding Mode::) +provides program level control over the rounding mode. *note +table-rounding-modes:: lists the IEEE-754 defined rounding modes: + +Rounding Mode IEEE Name `ROUNDMODE' +--------------------------------------------------------------------------- +Round to nearest, ties to even `roundTiesToEven' `"N"' or `"n"' +Round toward plus Infinity `roundTowardPositive' `"U"' or `"u"' +Round toward negative Infinity `roundTowardNegative' `"D"' or `"d"' +Round toward zero `roundTowardZero' `"Z"' or `"z"' +Round to nearest, ties away `roundTiesToAway' `"A"' or `"a"' +from zero + +Table 11.2: Rounding Modes + + The default mode `roundTiesToEven' is the most preferred, but the +least intuitive. This method does the obvious thing for most values, by +rounding them up or down to the nearest digit. For example, rounding +1.132 to two digits yields 1.13, and rounding 1.157 yields 1.16. + + However, when it comes to rounding a value that is exactly halfway +between, things do not work the way you probably learned in school. In +this case, the number is rounded to the nearest even digit. So +rounding 0.125 to two digits rounds down to 0.12, but rounding 0.6875 +to three digits rounds up to 0.688. You probably have already +encountered this rounding mode when using the `printf' routine to +format floating-point numbers. For example: + + BEGIN { + x = -4.5 + for (i = 1; i < 10; i++) { + x += 1.0 + printf("%4.1f => %2.0f\n", x, x) + } + } + +produces the following output when run(1): + + -3.5 => -4 + -2.5 => -2 + -1.5 => -2 + -0.5 => 0 + 0.5 => 0 + 1.5 => 2 + 2.5 => 2 + 3.5 => 4 + 4.5 => 4 + + The theory behind the rounding mode `roundTiesToEven' is that it +more or less evenly distributes upward and downward rounds of exact +halves, which might cause the round-off error to cancel itself out. +This is the default rounding mode used in IEEE-754 computing functions +and operators. + + The other rounding modes are rarely used. Round toward positive +infinity (`roundTowardPositive') and round toward negative infinity +(`roundTowardNegative') are often used to implement interval arithmetic, +where you adjust the rounding mode to calculate upper and lower bounds +for the range of output. The `roundTowardZero' mode can be used for +converting floating-point numbers to integers. The rounding mode +`roundTiesToAway' rounds the result to the nearest number and selects +the number with the larger magnitude if a tie occurs. + + Some numerical analysts will tell you that your choice of rounding +style has tremendous impact on the final outcome, and advise you to +wait until final output for any rounding. Instead, you can often +achieve this goal by setting the precision initially to some value +sufficiently larger than the final desired precision, so that the +accumulation of round-off error does not influence the outcome. If you +suspect that results from your computation are sensitive to +accumulation of round-off error, one way to be sure is to look for a +significant difference in output when you change the rounding mode. + + ---------- Footnotes ---------- + + (1) It is possible for the output to be completely different if the +C library in your system does not use the IEEE-754 even-rounding rule +to round halfway cases for `printf()'. + + +File: gawk.info, Node: Arbitrary Precision Floats, Next: Setting Precision, Prev: Rounding Mode, Up: Arbitrary Precision Arithmetic + +11.5 Arbitrary Precision Floating-point Arithmetic with `gawk' +============================================================== + +`gawk' uses the GNU MPFR library for arbitrary precision floating-point +arithmetic. The MPFR library provides precise control over precisions +and rounding modes, and gives correctly rounded reproducible +platform-independent results. With the command-line option `--bignum' +or `-M', all floating-point arithmetic operators and numeric functions +can yield results to any desired precision level supported by MPFR. +Two built-in variables `PREC' (*note Setting Precision::) and +`ROUNDMODE' (*note Setting Rounding Mode::) provide control over the +working precision and the rounding mode. The precision and the +rounding mode are set globally for every operation to follow. + + The default working precision for arbitrary precision floats is 53, +and the default value for `ROUNDMODE' is `"N"', which selects the +IEEE-754 `roundTiesToEven' (*note Rounding Mode::) rounding mode.(1) +`gawk' uses the default exponent range in MPFR (EMAX = 2^30 - 1, EMIN = +-EMAX) for all floating-point contexts. There is no explicit mechanism +to adjust the exponent range. MPFR does not implement subnormal +numbers by default, and this behavior cannot be changed in `gawk'. + + NOTE: When emulating an IEEE-754 format (*note Setting + Precision::), `gawk' internally adjusts the exponent range to the + value defined for the format and also performs computations needed + for gradual underflow (subnormal numbers). + + NOTE: MPFR numbers are variable-size entities, consuming only as + much space as needed to store the significant digits. Since the + performance using MPFR numbers pales in comparison to doing math + using the underlying machine types, you should consider using only + as much precision as needed by your program. + + ---------- Footnotes ---------- + + (1) The default precision is 53, since according to the MPFR +documentation, the library should be able to exactly reproduce all +computations with double-precision machine floating-point numbers +(`double' type in C), except the default exponent range is much wider +and subnormal numbers are not implemented. + + +File: gawk.info, Node: Setting Precision, Next: Setting Rounding Mode, Prev: Arbitrary Precision Floats, Up: Arbitrary Precision Arithmetic + +11.6 Setting the Working Precision +================================== + +`gawk' uses a global working precision; it does not keep track of the +precision or accuracy of individual numbers. Performing an arithmetic +operation or calling a built-in function rounds the result to the +current working precision. The default working precision is 53 which +can be modified using the built-in variable `PREC'. You can also set the +value to one of the following pre-defined case-insensitive strings to +emulate an IEEE-754 binary format: + +`PREC' IEEE-754 Binary Format +--------------------------------------------------- +`"half"' 16-bit half-precision. +`"single"' Basic 32-bit single precision. +`"double"' Basic 64-bit double precision. +`"quad"' Basic 128-bit quadruple precision. +`"oct"' 256-bit octuple precision. + + The following example illustrates the effects of changing precision +on arithmetic operations: + + $ gawk -M -vPREC=100 'BEGIN { x = 1.0e-400; print x + 0; \ + > PREC = "double"; print x + 0 }' + -| 1e-400 + -| 0 + + Binary and decimal precisions are related approximately according to +the formula: + + PREC = 3.322 * DPS + +Here, PREC denotes the binary precision (measured in bits) and DPS +(short for decimal places) is the decimal digits. We can easily +calculate how many decimal digits the 53-bit significand of an IEEE +double is equivalent to: 53 / 3.332 which is equal to about 15.95. But +what does 15.95 digits actually mean? It depends whether you are +concerned about how many digits you can rely on, or how many digits you +need. + + It is important to know how many bits it takes to uniquely identify +a double-precision value (the C type `double'). If you want to convert +from `double' to decimal and back to `double' (e.g., saving a `double' +representing an intermediate result to a file, and later reading it +back to restart the computation), then a few more decimal digits are +required. 17 digits is generally enough for a `double'. + + It can also be important to know what decimal numbers can be uniquely +represented with a `double'. If you want to convert from decimal to +`double' and back again, 15 digits is the most that you can get. Stated +differently, you should not present the numbers from your +floating-point computations with more than 15 significant digits in +them. + + Conversely, it takes a precision of 332 bits to hold an approximation +of constant pi that is accurate to 100 decimal places. You should +always add some extra bits in order to avoid the confusing round-off +issues that occur because numbers are stored internally in binary. + + +File: gawk.info, Node: Setting Rounding Mode, Next: Floating-point Constants, Prev: Setting Precision, Up: Arbitrary Precision Arithmetic + +11.7 Setting the Rounding Mode +============================== + +The built-in variable `ROUNDMODE' has the default value `"N"', which +selects the IEEE-754 rounding mode `roundTiesToEven'. The other +possible values for `ROUNDMODE' are `"U"' for rounding mode +`roundTowardPositive', `"D"' for `roundTowardNegative', and `"Z"' for +`roundTowardZero'. `gawk' also accepts `"A"' to select the IEEE-754 +mode `roundTiesToAway' if your version of the MPFR library supports it; +otherwise setting `ROUNDMODE' to this value has no effect. *Note +Rounding Mode::, for the meanings of the various rounding modes. + + Here is an example of how to change the default rounding behavior of +`printf''s output: + + $ gawk -M -vROUNDMODE="Z" 'BEGIN { printf("%.2f\n", 1.378) }' + -| 1.37 + + +File: gawk.info, Node: Floating-point Constants, Next: Changing Precision, Prev: Setting Rounding Mode, Up: Arbitrary Precision Arithmetic + +11.8 Representing Floating-point Constants +========================================== + +Be wary of floating-point constants! When reading a floating-point +constant from program source code, `gawk' uses the default precision, +unless overridden by an assignment to the special variable `PREC' on +the command line, to store it internally as a MPFR number. Changing +the precision using `PREC' in the program text does not change the +precision of a constant. If you need to represent a floating-point +constant at a higher precision than the default and cannot use a +command line assignment to `PREC', you should either specify the +constant as a string, or a rational number whenever possible. The +following example illustrates the differences among various ways to +print a floating-point constant: + + $ gawk -M 'BEGIN { PREC = 113; printf("%0.25f\n", 0.1) }' + -| 0.1000000000000000055511151 + $ gawk -M -vPREC = 113 'BEGIN { printf("%0.25f\n", 0.1) }' + -| 0.1000000000000000000000000 + $ gawk -M 'BEGIN { PREC = 113; printf("%0.25f\n", "0.1") }' + -| 0.1000000000000000000000000 + $ gawk -M 'BEGIN { PREC = 113; printf("%0.25f\n", 1/10) }' + -| 0.1000000000000000000000000 + + In the first case, the number is stored with the default precision +of 53. + + +File: gawk.info, Node: Changing Precision, Next: Exact Arithmetic, Prev: Floating-point Constants, Up: Arbitrary Precision Arithmetic + +11.9 Changing the Precision of a Number +======================================= + + The point is that in any variable-precision package, a decision is + made on how to treat numbers given as data, or arising in + intermediate results, which are represented in floating-point + format to a precision lower than working precision. Do we promote + them to full membership of the high-precision club, or do we treat + them and all their associates as second-class citizens? Sometimes + the first course is proper, sometimes the second, and it takes + careful analysis to tell which. + + Dirk Laurie(1) + + `gawk' does not implicitly modify the precision of any previously +computed results when the working precision is changed with an +assignment to `PREC'. The precision of a number is always the one that +was used at the time of its creation, and there is no way for the user +to explicitly change it afterwards. However, since the result of a +floating-point arithmetic operation is always an arbitrary precision +floating-point value--with a precision set by the value of `PREC'--one +of the following workarounds effectively accomplishes the desired +behavior: + + x = x + 0.0 + +or: + + x += 0.0 + + ---------- Footnotes ---------- + + (1) Dirk Laurie. `Variable-precision Arithmetic Considered Perilous +- A Detective Story'. Electronic Transactions on Numerical Analysis. +Volume 28, pp. 168-173, 2008. + + +File: gawk.info, Node: Exact Arithmetic, Next: Integer Programming, Prev: Changing Precision, Up: Arbitrary Precision Arithmetic + +11.10 Exact Arithmetic with Floating-point Numbers +================================================== + + CAUTION: Never depend on the exactness of floating-point + arithmetic, even for apparently simple expressions! + + Can arbitrary precision arithmetic give exact results? There are no +easy answers. The standard rules of algebra often do not apply when +using floating-point arithmetic. Among other things, the distributive +and associative laws do not hold completely, and order of operation may +be important for your computation. Rounding error, cumulative precision +loss and underflow are often troublesome. + + When `gawk' tests the expressions `0.1 + 12.2' and `12.3' for +equality using the machine double precision arithmetic, it decides that +they are not equal! (*Note Floating-point Programming::.) You can get +the result you want by increasing the precision; 56 in this case will +get the job done: + + $ gawk -M -vPREC=56 'BEGIN { print (0.1 + 12.2 == 12.3) }' + -| 1 + + If adding more bits is good, perhaps adding even more bits of +precision is better? Here is what happens if we use an even larger +value of `PREC': + + $ gawk -M -vPREC=201 'BEGIN { print (0.1 + 12.2 == 12.3) }' + -| 0 + + This is not a bug in `gawk' or in the MPFR library. It is easy to +forget that the finite number of bits used to store the value is often +just an approximation after proper rounding. The test for equality +succeeds if and only if _all_ bits in the two operands are exactly the +same. Since this is not necessarily true after floating-point +computations with a particular precision and effective rounding rule, a +straight test for equality may not work. + + So, don't assume that floating-point values can be compared for +equality. You should also exercise caution when using other forms of +comparisons. The standard way to compare between floating-point +numbers is to determine how much error (or "tolerance") you will allow +in a comparison and check to see if one value is within this error +range of the other. + + In applications where 15 or fewer decimal places suffice, hardware +double precision arithmetic can be adequate, and is usually much faster. +But you do need to keep in mind that every floating-point operation can +suffer a new rounding error with catastrophic consequences as +illustrated by our attempt to compute the value of the constant pi, +(*note Floating-point Programming::). Extra precision can greatly +enhance the stability and the accuracy of your computation in such +cases. + + Repeated addition is not necessarily equivalent to multiplication in +floating-point arithmetic. In the last example (*note Floating-point +Programming::), you may or may not succeed in getting the correct +result by choosing an arbitrarily large value for `PREC'. Reformulation +of the problem at hand is often the correct approach in such situations. + + +File: gawk.info, Node: Integer Programming, Next: Arbitrary Precision Integers, Prev: Exact Arithmetic, Up: Arbitrary Precision Arithmetic + +11.11 Effective Integer Programming +=================================== + +As has been mentioned already, `gawk' ordinarily uses hardware double +precision with 64-bit IEEE binary floating-point representation for +numbers on most systems. A large integer like 9007199254740997 has a +binary representation that, although finite, is more than 53 bits long; +it must also be rounded to 53 bits. The biggest integer that can be +stored in a C `double' is usually the same as the largest possible +value of a `double'. If your system `double' is an IEEE 64-bit +`double', this largest possible value is an integer and can be +represented precisely. What more should one know about integers? + + If you want to know what is the largest integer, such that it and +all smaller integers can be stored in 64-bit doubles without losing +precision, then the answer is 2^53. The next representable number is +the even number 2^53 + 2, meaning it is unlikely that you will be able +to make `gawk' print 2^53 + 1 in integer format. The range of integers +exactly representable by a 64-bit double is [-2^53, 2^53]. If you ever +see an integer outside this range in `gawk' using 64-bit doubles, you +have reason to be very suspicious about the accuracy of the output. +Here is a simple program with erroneous output: + + $ gawk 'BEGIN { i = 2^53 - 1; for (j = 0; j < 4; j++) print i + j }' + -| 9007199254740991 + -| 9007199254740992 + -| 9007199254740992 + -| 9007199254740994 + + The lesson is to not assume that any large integer printed by `gawk' +represents an exact result from your computation, especially if it wraps +around on your screen. + + +File: gawk.info, Node: Arbitrary Precision Integers, Next: MPFR and GMP Libraries, Prev: Integer Programming, Up: Arbitrary Precision Arithmetic + +11.12 Arbitrary Precision Integer Arithmetic with `gawk' +======================================================== + +If the option `--bignum' or `-M' is specified, `gawk' performs all +integer arithmetic using GMP arbitrary precision integers. Any number +that looks like an integer in a program source or data file is stored +as an arbitrary precision integer. The size of the integer is limited +only by your computer's memory. The current floating-point context has +no effect on operations involving integers. For example, the following +computes 5^4^3^2, the result of which is beyond the limits of ordinary +`gawk' numbers: + + $ gawk -M 'BEGIN { + > x = 5^4^3^2 + > print "# of digits =", length(x) + > print substr(x, 1, 20), "...", substr(x, length(x) - 19, 20) + > }' + -| # of digits = 183231 + -| 62060698786608744707 ... 92256259918212890625 + + If you were to compute the same value using arbitrary precision +floating-point values instead, the precision needed for correct output +(using the formula `prec = 3.322 * dps'), would be 3.322 x 183231, or +608693. + + The result from an arithmetic operation with an integer and a +floating-point value is a floating-point value with a precision equal +to the working precision. The following program calculates the eighth +term in Sylvester's sequence(1) using a recurrence: + + $ gawk -M 'BEGIN { + > s = 2.0 + > for (i = 1; i <= 7; i++) + > s = s * (s - 1) + 1 + > print s + > }' + -| 113423713055421845118910464 + + The output differs from the acutal number, +113423713055421844361000443, because the default precision of 53 is not +enough to represent the floating-point results exactly. You can either +increase the precision (100 is enough in this case), or replace the +floating-point constant `2.0' with an integer, to perform all +computations using integer arithmetic to get the correct output. + + It will sometimes be necessary for `gawk' to implicitly convert an +arbitrary precision integer into an arbitrary precision floating-point +value. This is primarily because the MPFR library does not always +provide the relevant interface to process arbitrary precision integers +or mixed-mode numbers as needed by an operation or function. In such a +case, the precision is set to the minimum value necessary for exact +conversion, and the working precision is not used for this purpose. If +this is not what you need or want, you can employ a subterfuge like +this: + + gawk -M 'BEGIN { n = 13; print (n + 0.0) % 2.0 }' + + You can avoid this issue altogether by specifying the number as a +float to begin with: + + gawk -M 'BEGIN { n = 13.0; print n % 2.0 }' + + Note that for the particular example above, there is unlikely to be a +reason for simply not using the following: + + gawk -M 'BEGIN { n = 13; print n % 2 }' + + ---------- Footnotes ---------- + + (1) Weisstein, Eric W. `Sylvester's Sequence'. From MathWorld-A +Wolfram Web Resource. +`http://mathworld.wolfram.com/SylvestersSequence.html' + + +File: gawk.info, Node: MPFR and GMP Libraries, Prev: Arbitrary Precision Integers, Up: Arbitrary Precision Arithmetic + +11.13 Information About the MPFR and GMP Libraries +================================================== + +There are a few elements available in the `PROCINFO' array to provide +information about the MPFR and GMP libraries. *Note Auto-set::, for +more information. + + +File: gawk.info, Node: Advanced Features, Next: Library Functions, Prev: Arbitrary Precision Arithmetic, Up: Top + +12 Advanced Features of `gawk' ****************************** Write documentation as if whoever reads it is a violent psychopath @@ -13685,7 +14480,7 @@ and likely to change, its description is relegated to an appendix. File: gawk.info, Node: Nondecimal Data, Next: Array Sorting, Up: Advanced Features -11.1 Allowing Nondecimal Input Data +12.1 Allowing Nondecimal Input Data =================================== If you run `gawk' with the `--non-decimal-data' option, you can have @@ -13727,7 +14522,7 @@ request it. File: gawk.info, Node: Array Sorting, Next: Two-way I/O, Prev: Nondecimal Data, Up: Advanced Features -11.2 Controlling Array Traversal and Array Sorting +12.2 Controlling Array Traversal and Array Sorting ================================================== `gawk' lets you control the order in which a `for (i in array)' loop @@ -13746,7 +14541,7 @@ to order the elements during sorting. File: gawk.info, Node: Controlling Array Traversal, Next: Array Sorting Functions, Up: Array Sorting -11.2.1 Controlling Array Traversal +12.2.1 Controlling Array Traversal ---------------------------------- By default, the order in which a `for (i in array)' loop scans an array @@ -13977,7 +14772,7 @@ the default. File: gawk.info, Node: Array Sorting Functions, Prev: Controlling Array Traversal, Up: Array Sorting -11.2.2 Sorting Array Values and Indices with `gawk' +12.2.2 Sorting Array Values and Indices with `gawk' --------------------------------------------------- In most `awk' implementations, sorting an array requires writing a @@ -14072,7 +14867,7 @@ extensions, they are not available in that case. File: gawk.info, Node: Two-way I/O, Next: TCP/IP Networking, Prev: Array Sorting, Up: Advanced Features -11.3 Two-Way Communications with Another Process +12.3 Two-Way Communications with Another Process ================================================ From: brennan@whidbey.com (Mike Brennan) @@ -14207,7 +15002,7 @@ regular pipes. File: gawk.info, Node: TCP/IP Networking, Next: Profiling, Prev: Two-way I/O, Up: Advanced Features -11.4 Using `gawk' for Network Programming +12.4 Using `gawk' for Network Programming ========================================= `EMISTERED': @@ -14284,7 +15079,7 @@ examples. File: gawk.info, Node: Profiling, Prev: TCP/IP Networking, Up: Advanced Features -11.5 Profiling Your `awk' Programs +12.5 Profiling Your `awk' Programs ================================== You may produce execution traces of your `awk' programs. This is done @@ -14502,7 +15297,7 @@ without any execution counts. File: gawk.info, Node: Library Functions, Next: Sample Programs, Prev: Advanced Features, Up: Top -12 A Library of `awk' Functions +13 A Library of `awk' Functions ******************************* *note User-defined::, describes how to write your own `awk' functions. @@ -14574,7 +15369,7 @@ contents of the input record. File: gawk.info, Node: Library Names, Next: General Functions, Up: Library Functions -12.1 Naming Library Function Global Variables +13.1 Naming Library Function Global Variables ============================================= Due to the way the `awk' language evolved, variables are either @@ -14654,7 +15449,7 @@ verifying this. File: gawk.info, Node: General Functions, Next: Data File Management, Prev: Library Names, Up: Library Functions -12.2 General Programming +13.2 General Programming ======================== This minor node presents a number of functions that are of general @@ -14677,7 +15472,7 @@ programming use. File: gawk.info, Node: Strtonum Function, Next: Assert Function, Up: General Functions -12.2.1 Converting Strings To Numbers +13.2.1 Converting Strings To Numbers ------------------------------------ The `strtonum()' function (*note String Functions::) is a `gawk' @@ -14761,7 +15556,7 @@ be tested with `gawk' and the results compared to the built-in File: gawk.info, Node: Assert Function, Next: Round Function, Prev: Strtonum Function, Up: General Functions -12.2.2 Assertions +13.2.2 Assertions ----------------- When writing large programs, it is often useful to know that a @@ -14847,7 +15642,7 @@ rule always ends with an `exit' statement. File: gawk.info, Node: Round Function, Next: Cliff Random Function, Prev: Assert Function, Up: General Functions -12.2.3 Rounding Numbers +13.2.3 Rounding Numbers ----------------------- The way `printf' and `sprintf()' (*note Printf::) perform rounding @@ -14893,7 +15688,7 @@ might be useful if your `awk''s `printf' does unbiased rounding: File: gawk.info, Node: Cliff Random Function, Next: Ordinal Functions, Prev: Round Function, Up: General Functions -12.2.4 The Cliff Random Number Generator +13.2.4 The Cliff Random Number Generator ---------------------------------------- The Cliff random number generator @@ -14922,7 +15717,7 @@ might try using this function instead. File: gawk.info, Node: Ordinal Functions, Next: Join Function, Prev: Cliff Random Function, Up: General Functions -12.2.5 Translating Between Characters and Numbers +13.2.5 Translating Between Characters and Numbers ------------------------------------------------- One commercial implementation of `awk' supplies a built-in function, @@ -15020,7 +15815,7 @@ extensions, you can simplify `_ord_init' to loop from 0 to 255. File: gawk.info, Node: Join Function, Next: Gettimeofday Function, Prev: Ordinal Functions, Up: General Functions -12.2.6 Merging an Array into a String +13.2.6 Merging an Array into a String ------------------------------------- When doing string processing, it is often useful to be able to join all @@ -15067,7 +15862,7 @@ makes string operations more difficult than they really need to be. File: gawk.info, Node: Gettimeofday Function, Prev: Join Function, Up: General Functions -12.2.7 Managing the Time of Day +13.2.7 Managing the Time of Day ------------------------------- The `systime()' and `strftime()' functions described in *note Time @@ -15149,7 +15944,7 @@ optional timestamp value to use instead of the current time. File: gawk.info, Node: Data File Management, Next: Getopt Function, Prev: General Functions, Up: Library Functions -12.3 Data File Management +13.3 Data File Management ========================= This minor node presents functions that are useful for managing @@ -15166,7 +15961,7 @@ command-line data files. File: gawk.info, Node: Filetrans Function, Next: Rewind Function, Up: Data File Management -12.3.1 Noting Data File Boundaries +13.3.1 Noting Data File Boundaries ---------------------------------- The `BEGIN' and `END' rules are each executed exactly once at the @@ -15264,7 +16059,7 @@ it provides an easy way to do per-file cleanup processing. File: gawk.info, Node: Rewind Function, Next: File Checking, Prev: Filetrans Function, Up: Data File Management -12.3.2 Rereading the Current File +13.3.2 Rereading the Current File --------------------------------- Another request for a new built-in function was for a `rewind()' @@ -15306,7 +16101,7 @@ Nextfile Statement::). File: gawk.info, Node: File Checking, Next: Empty Files, Prev: Rewind Function, Up: Data File Management -12.3.3 Checking for Readable Data Files +13.3.3 Checking for Readable Data Files --------------------------------------- Normally, if you give `awk' a data file that isn't readable, it stops @@ -15335,7 +16130,7 @@ in the list). See also *note ARGC and ARGV::. File: gawk.info, Node: Empty Files, Next: Ignoring Assigns, Prev: File Checking, Up: Data File Management -12.3.4 Checking For Zero-length Files +13.3.4 Checking For Zero-length Files ------------------------------------- All known `awk' implementations silently skip over zero-length files. @@ -15392,7 +16187,7 @@ intervening value in `ARGV' is a variable assignment. File: gawk.info, Node: Ignoring Assigns, Prev: Empty Files, Up: Data File Management -12.3.5 Treating Assignments as File Names +13.3.5 Treating Assignments as File Names ----------------------------------------- Occasionally, you might not want `awk' to process command-line variable @@ -15435,7 +16230,7 @@ arguments are left alone. File: gawk.info, Node: Getopt Function, Next: Passwd Functions, Prev: Data File Management, Up: Library Functions -12.4 Processing Command-Line Options +13.4 Processing Command-Line Options ==================================== Most utilities on POSIX compatible systems take options on the command @@ -15728,7 +16523,7 @@ have left it alone, since using `substr()' is more portable. File: gawk.info, Node: Passwd Functions, Next: Group Functions, Prev: Getopt Function, Up: Library Functions -12.5 Reading the User Database +13.5 Reading the User Database ============================== The `PROCINFO' array (*note Built-in Variables::) provides access to @@ -15971,7 +16766,7 @@ network database. File: gawk.info, Node: Group Functions, Next: Walking Arrays, Prev: Passwd Functions, Up: Library Functions -12.6 Reading the Group Database +13.6 Reading the Group Database =============================== Much of the discussion presented in *note Passwd Functions::, applies @@ -16205,7 +17000,7 @@ very simple, relying on `awk''s associative arrays to do work. File: gawk.info, Node: Walking Arrays, Prev: Group Functions, Up: Library Functions -12.7 Traversing Arrays of Arrays +13.7 Traversing Arrays of Arrays ================================ *note Arrays of Arrays::, described how `gawk' provides arrays of @@ -16256,7 +17051,7 @@ value. Here is a main program to demonstrate: File: gawk.info, Node: Sample Programs, Next: Debugger, Prev: Library Functions, Up: Top -13 Practical `awk' Programs +14 Practical `awk' Programs *************************** *note Library Functions::, presents the idea that reading programs in a @@ -16276,7 +17071,7 @@ Library Functions::. File: gawk.info, Node: Running Examples, Next: Clones, Up: Sample Programs -13.1 Running the Example Programs +14.1 Running the Example Programs ================================= To run a given program, you would typically do something like this: @@ -16299,7 +17094,7 @@ OPTIONS are any command-line options for the program that start with a File: gawk.info, Node: Clones, Next: Miscellaneous Programs, Prev: Running Examples, Up: Sample Programs -13.2 Reinventing Wheels for Fun and Profit +14.2 Reinventing Wheels for Fun and Profit ========================================== This minor node presents a number of POSIX utilities implemented in @@ -16329,7 +17124,7 @@ programming for "real world" tasks. File: gawk.info, Node: Cut Program, Next: Egrep Program, Up: Clones -13.2.1 Cutting out Fields and Columns +14.2.1 Cutting out Fields and Columns ------------------------------------- The `cut' utility selects, or "cuts," characters or fields from its @@ -16588,7 +17383,7 @@ solution to the problem of picking the input line apart by characters. File: gawk.info, Node: Egrep Program, Next: Id Program, Prev: Cut Program, Up: Clones -13.2.2 Searching for Regular Expressions in Files +14.2.2 Searching for Regular Expressions in Files ------------------------------------------------- The `egrep' utility searches files for patterns. It uses regular @@ -16820,7 +17615,7 @@ the translated line, not the original. File: gawk.info, Node: Id Program, Next: Split Program, Prev: Egrep Program, Up: Clones -13.2.3 Printing out User Information +14.2.3 Printing out User Information ------------------------------------ The `id' utility lists a user's real and effective user ID numbers, @@ -16927,7 +17722,7 @@ body never executes. File: gawk.info, Node: Split Program, Next: Tee Program, Prev: Id Program, Up: Clones -13.2.4 Splitting a Large File into Pieces +14.2.4 Splitting a Large File into Pieces ----------------------------------------- The `split' program splits large text files into smaller pieces. Usage @@ -17035,7 +17830,7 @@ not relevant for what the program aims to demonstrate. File: gawk.info, Node: Tee Program, Next: Uniq Program, Prev: Split Program, Up: Clones -13.2.5 Duplicating Output into Multiple Files +14.2.5 Duplicating Output into Multiple Files --------------------------------------------- The `tee' program is known as a "pipe fitting." `tee' copies its @@ -17123,7 +17918,7 @@ N input records and M output files, the first method only executes N File: gawk.info, Node: Uniq Program, Next: Wc Program, Prev: Tee Program, Up: Clones -13.2.6 Printing Nonduplicated Lines of Text +14.2.6 Printing Nonduplicated Lines of Text ------------------------------------------- The `uniq' utility reads sorted lines of data on its standard input, @@ -17342,7 +18137,7 @@ line of input data: File: gawk.info, Node: Wc Program, Prev: Uniq Program, Up: Clones -13.2.7 Counting Things +14.2.7 Counting Things ---------------------- The `wc' (word count) utility counts lines, words, and characters in @@ -17487,7 +18282,7 @@ characters, not bytes. File: gawk.info, Node: Miscellaneous Programs, Prev: Clones, Up: Sample Programs -13.3 A Grab Bag of `awk' Programs +14.3 A Grab Bag of `awk' Programs ================================= This minor node is a large "grab bag" of miscellaneous programs. We @@ -17514,7 +18309,7 @@ hope you find them both interesting and enjoyable. File: gawk.info, Node: Dupword Program, Next: Alarm Program, Up: Miscellaneous Programs -13.3.1 Finding Duplicated Words in a Document +14.3.1 Finding Duplicated Words in a Document --------------------------------------------- A common error when writing large amounts of prose is to accidentally @@ -17562,7 +18357,7 @@ word, comparing it to the previous one: File: gawk.info, Node: Alarm Program, Next: Translate Program, Prev: Dupword Program, Up: Miscellaneous Programs -13.3.2 An Alarm Clock Program +14.3.2 An Alarm Clock Program ----------------------------- Nothing cures insomnia like a ringing alarm clock. @@ -17695,7 +18490,7 @@ necessary: File: gawk.info, Node: Translate Program, Next: Labels Program, Prev: Alarm Program, Up: Miscellaneous Programs -13.3.3 Transliterating Characters +14.3.3 Transliterating Characters --------------------------------- The system `tr' utility transliterates characters. For example, it is @@ -17821,7 +18616,7 @@ split each character in a string into separate array elements. File: gawk.info, Node: Labels Program, Next: Word Sorting, Prev: Translate Program, Up: Miscellaneous Programs -13.3.4 Printing Mailing Labels +14.3.4 Printing Mailing Labels ------------------------------ Here is a "real world"(1) program. This script reads lists of names and @@ -17928,7 +18723,7 @@ something done." File: gawk.info, Node: Word Sorting, Next: History Sorting, Prev: Labels Program, Up: Miscellaneous Programs -13.3.5 Generating Word-Usage Counts +14.3.5 Generating Word-Usage Counts ----------------------------------- When working with large amounts of text, it can be interesting to know @@ -18032,7 +18827,7 @@ operating system documentation for more information on how to use the File: gawk.info, Node: History Sorting, Next: Extract Program, Prev: Word Sorting, Up: Miscellaneous Programs -13.3.6 Removing Duplicates from Unsorted Text +14.3.6 Removing Duplicates from Unsorted Text --------------------------------------------- The `uniq' program (*note Uniq Program::), removes duplicate lines from @@ -18079,7 +18874,7 @@ seen. File: gawk.info, Node: Extract Program, Next: Simple Sed, Prev: History Sorting, Up: Miscellaneous Programs -13.3.7 Extracting Programs from Texinfo Source Files +14.3.7 Extracting Programs from Texinfo Source Files ---------------------------------------------------- The nodes *note Library Functions::, and *note Sample Programs::, are @@ -18279,7 +19074,7 @@ function. Consider how you might use it to simplify the code. File: gawk.info, Node: Simple Sed, Next: Igawk Program, Prev: Extract Program, Up: Miscellaneous Programs -13.3.8 A Simple Stream Editor +14.3.8 A Simple Stream Editor ----------------------------- The `sed' utility is a stream editor, a program that reads a stream of @@ -18360,7 +19155,7 @@ the single rule handles the printing scheme outlined above, using File: gawk.info, Node: Igawk Program, Next: Anagram Program, Prev: Simple Sed, Up: Miscellaneous Programs -13.3.9 An Easy Way to Use Library Functions +14.3.9 An Easy Way to Use Library Functions ------------------------------------------- In *note Include Files::, we saw how `gawk' provides a built-in @@ -18757,7 +19552,7 @@ can loop forever if the file exists but is empty. Caveat emptor. File: gawk.info, Node: Anagram Program, Next: Signature Program, Prev: Igawk Program, Up: Miscellaneous Programs -13.3.10 Finding Anagrams From A Dictionary +14.3.10 Finding Anagrams From A Dictionary ------------------------------------------ An interesting programming challenge is to search for "anagrams" in a @@ -18847,7 +19642,7 @@ otherwise the anagrams would appear in arbitrary order: File: gawk.info, Node: Signature Program, Prev: Anagram Program, Up: Miscellaneous Programs -13.3.11 And Now For Something Completely Different +14.3.11 And Now For Something Completely Different -------------------------------------------------- The following program was written by Davide Brini and is published on @@ -18874,7 +19669,7 @@ supplies the following copyright terms: File: gawk.info, Node: Debugger, Next: Language History, Prev: Sample Programs, Up: Top -14 Debugging `awk' Programs +15 Debugging `awk' Programs *************************** It would be nice if computer programs worked perfectly the first time @@ -18898,7 +19693,7 @@ program is easy. File: gawk.info, Node: Debugging, Next: Sample Debugging Session, Up: Debugger -14.1 Introduction to `gawk' Debugger +15.1 Introduction to `gawk' Debugger ==================================== This minor node introduces debugging in general and begins the @@ -18913,7 +19708,7 @@ discussion of debugging in `gawk'. File: gawk.info, Node: Debugging Concepts, Next: Debugging Terms, Up: Debugging -14.1.1 Debugging in General +15.1.1 Debugging in General --------------------------- (If you have used debuggers in other languages, you may want to skip @@ -18953,7 +19748,7 @@ functional program that you or someone else wrote). File: gawk.info, Node: Debugging Terms, Next: Awk Debugging, Prev: Debugging Concepts, Up: Debugging -14.1.2 Additional Debugging Concepts +15.1.2 Additional Debugging Concepts ------------------------------------ Before diving in to the details, we need to introduce several important @@ -19005,7 +19800,7 @@ 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 +15.1.3 Awk Debugging -------------------- Debugging an `awk' program has some specific aspects that are not @@ -19027,7 +19822,7 @@ commands. File: gawk.info, Node: Sample Debugging Session, Next: List of Debugger Commands, Prev: Debugging, Up: Debugger -14.2 Sample Debugging Session +15.2 Sample Debugging Session ============================= In order to illustrate the use of `gawk' as a debugger, let's look at a @@ -19043,7 +19838,7 @@ example. File: gawk.info, Node: Debugger Invocation, Next: Finding The Bug, Up: Sample Debugging Session -14.2.1 How to Start the Debugger +15.2.1 How to Start the Debugger -------------------------------- Starting the debugger is almost exactly like running `awk', except you @@ -19075,7 +19870,7 @@ code has been executed. File: gawk.info, Node: Finding The Bug, Prev: Debugger Invocation, Up: Sample Debugging Session -14.2.2 Finding the Bug +15.2.2 Finding the Bug ---------------------- Let's say that we are having a problem using (a faulty version of) @@ -19272,7 +20067,7 @@ and problem solved! File: gawk.info, Node: List of Debugger Commands, Next: Readline Support, Prev: Sample Debugging Session, Up: Debugger -14.3 Main Debugger Commands +15.3 Main Debugger Commands =========================== The `gawk' debugger command set can be divided into the following @@ -19311,7 +20106,7 @@ when just hitting <Enter>. This works for the commands `list', `next', File: gawk.info, Node: Breakpoint Control, Next: Debugger Execution Control, Up: List of Debugger Commands -14.3.1 Control of Breakpoints +15.3.1 Control of Breakpoints ----------------------------- As we saw above, the first thing you probably want to do in a debugging @@ -19406,7 +20201,7 @@ controlling breakpoints are: File: gawk.info, Node: Debugger Execution Control, Next: Viewing And Changing Data, Prev: Breakpoint Control, Up: List of Debugger Commands -14.3.2 Control of Execution +15.3.2 Control of Execution --------------------------- Now that your breakpoints are ready, you can start running the program @@ -19496,7 +20291,7 @@ execution of the program than we saw in our earlier example: File: gawk.info, Node: Viewing And Changing Data, Next: Execution Stack, Prev: Debugger Execution Control, Up: List of Debugger Commands -14.3.3 Viewing and Changing Data +15.3.3 Viewing and Changing Data -------------------------------- The commands for viewing and changing variables inside of `gawk' are: @@ -19585,7 +20380,7 @@ AWK STATEMENTS File: gawk.info, Node: Execution Stack, Next: Debugger Info, Prev: Viewing And Changing Data, Up: List of Debugger Commands -14.3.4 Dealing with the Stack +15.3.4 Dealing with the Stack ----------------------------- Whenever you run a program which contains any function calls, `gawk' @@ -19622,7 +20417,7 @@ are: File: gawk.info, Node: Debugger Info, Next: Miscellaneous Debugger Commands, Prev: Execution Stack, Up: List of Debugger Commands -14.3.5 Obtaining Information about the Program and the Debugger State +15.3.5 Obtaining Information about the Program and the Debugger State --------------------------------------------------------------------- Besides looking at the values of variables, there is often a need to get @@ -19731,7 +20526,7 @@ from a file. The commands are: File: gawk.info, Node: Miscellaneous Debugger Commands, Prev: Debugger Info, Up: List of Debugger Commands -14.3.6 Miscellaneous Commands +15.3.6 Miscellaneous Commands ----------------------------- There are a few more commands which do not fit into the previous @@ -19851,7 +20646,7 @@ categories, as follows: File: gawk.info, Node: Readline Support, Next: Limitations, Prev: List of Debugger Commands, Up: Debugger -14.4 Readline Support +15.4 Readline Support ===================== If `gawk' is compiled with the `readline' library, you can take @@ -19878,7 +20673,7 @@ Variable name completion File: gawk.info, Node: Limitations, Prev: Readline Support, Up: Debugger -14.5 Limitations and Future Plans +15.5 Limitations and Future Plans ================================= We hope you find the `gawk' debugger useful and enjoyable to work with, @@ -24918,7 +25713,7 @@ Index * * (asterisk), * operator, as regexp operator: Regexp Operators. (line 87) * * (asterisk), * operator, null strings, matching: Gory Details. - (line 165) + (line 164) * * (asterisk), ** operator <1>: Precedence. (line 49) * * (asterisk), ** operator: Arithmetic Ops. (line 81) * * (asterisk), **= operator <1>: Precedence. (line 95) @@ -24942,76 +25737,78 @@ Index * - (hyphen), filenames beginning with: Options. (line 59) * - (hyphen), in bracket expressions: Bracket Expressions. (line 17) * --assign option: Options. (line 32) -* --c option: Options. (line 78) +* --bignum option: Options. (line 187) +* --c option: Options. (line 81) * --characters-as-bytes option: Options. (line 68) -* --copyright option: Options. (line 85) -* --debug option: Options. (line 105) +* --copyright option: Options. (line 88) +* --debug option: Options. (line 108) * --disable-lint configuration option: Additional Configuration Options. (line 9) * --disable-nls configuration option: Additional Configuration Options. (line 24) * --dump-variables option <1>: Library Names. (line 45) -* --dump-variables option: Options. (line 90) -* --exec option: Options. (line 122) +* --dump-variables option: Options. (line 93) +* --exec option: Options. (line 125) * --field-separator option: Options. (line 21) * --file option: Options. (line 25) * --gen-pot option <1>: String Extraction. (line 6) -* --gen-pot option: Options. (line 144) -* --help option: Options. (line 151) -* --L option: Options. (line 265) -* --lint option <1>: Options. (line 165) +* --gen-pot option: Options. (line 147) +* --help option: Options. (line 154) +* --L option: Options. (line 274) +* --lint option <1>: Options. (line 168) * --lint option: Command Line. (line 20) -* --lint-old option: Options. (line 265) -* --load option: Options. (line 156) +* --lint-old option: Options. (line 274) +* --load option: Options. (line 159) * --non-decimal-data option <1>: Nondecimal Data. (line 6) -* --non-decimal-data option: Options. (line 184) +* --non-decimal-data option: Options. (line 193) * --non-decimal-data option, strtonum() function and: Nondecimal Data. (line 36) -* --optimize option: Options. (line 205) -* --posix option: Options. (line 224) -* --posix option, --traditional option and: Options. (line 243) -* --pretty-print option: Options. (line 197) +* --optimize option: Options. (line 214) +* --posix option: Options. (line 233) +* --posix option, --traditional option and: Options. (line 252) +* --pretty-print option: Options. (line 206) * --profile option <1>: Profiling. (line 12) -* --profile option: Options. (line 212) -* --re-interval option: Options. (line 249) -* --sandbox option: Options. (line 256) +* --profile option: Options. (line 221) +* --re-interval option: Options. (line 258) +* --sandbox option: Options. (line 265) * --sandbox option, disabling system() function: I/O Functions. (line 85) * --sandbox option, input redirection with getline: Getline. (line 19) * --sandbox option, output redirection with print, printf: Redirection. (line 6) -* --source option: Options. (line 114) -* --traditional option: Options. (line 78) -* --traditional option, --posix option and: Options. (line 243) -* --use-lc-numeric option: Options. (line 192) -* --version option: Options. (line 270) +* --source option: Options. (line 117) +* --traditional option: Options. (line 81) +* --traditional option, --posix option and: Options. (line 252) +* --use-lc-numeric option: Options. (line 201) +* --version option: Options. (line 279) * --with-whiny-user-strftime configuration option: Additional Configuration Options. (line 29) * -b option: Options. (line 68) -* -C option: Options. (line 85) -* -D option: Options. (line 105) -* -d option: Options. (line 90) -* -E option: Options. (line 122) -* -e option: Options. (line 114) +* -C option: Options. (line 88) +* -D option: Options. (line 108) +* -d option: Options. (line 93) +* -E option: Options. (line 125) +* -e option: Options. (line 117) * -F option: Command Line Field Separator. (line 6) * -f option: Options. (line 25) * -F option: Options. (line 21) * -f option: Long. (line 12) -* -F option, -Ft sets FS to TAB: Options. (line 278) -* -f option, on command line: Options. (line 283) -* -g option: Options. (line 144) -* -h option: Options. (line 151) -* -l option: Options. (line 156) -* -N option: Options. (line 192) -* -n option: Options. (line 184) -* -O option: Options. (line 205) -* -o option: Options. (line 197) -* -P option: Options. (line 224) -* -p option: Options. (line 212) -* -r option: Options. (line 249) -* -S option: Options. (line 256) -* -V option: Options. (line 270) +* -F option, -Ft sets FS to TAB: Options. (line 287) +* -f option, on command line: Options. (line 292) +* -g option: Options. (line 147) +* -h option: Options. (line 154) +* -l option: Options. (line 159) +* -M option: Options. (line 187) +* -N option: Options. (line 201) +* -n option: Options. (line 193) +* -O option: Options. (line 214) +* -o option: Options. (line 206) +* -P option: Options. (line 233) +* -p option: Options. (line 221) +* -r option: Options. (line 258) +* -S option: Options. (line 265) +* -V option: Options. (line 279) * -v option: Options. (line 32) * -v option, variables, assigning: Assignment Options. (line 12) * -W option: Options. (line 46) @@ -25151,7 +25948,7 @@ Index (line 67) * advanced features, data files as single record: Records. (line 175) * advanced features, fixed-width data: Constant Size. (line 9) -* advanced features, FNR/NR variables: Auto-set. (line 208) +* advanced features, FNR/NR variables: Auto-set. (line 225) * advanced features, gawk: Advanced Features. (line 6) * advanced features, gawk, network programming: TCP/IP Networking. (line 6) @@ -25161,7 +25958,7 @@ Index (line 23) * advanced features, network connections, See Also networks, connections: Advanced Features. (line 6) -* advanced features, null strings, matching: Gory Details. (line 165) +* advanced features, null strings, matching: Gory Details. (line 164) * advanced features, operators, precedence: Increment Ops. (line 61) * advanced features, piping into sh: Redirection. (line 143) * advanced features, regexp constants: Assignment Ops. (line 148) @@ -25186,6 +25983,8 @@ Index * and Boolean-logic operator: Boolean Ops. (line 6) * and() function (gawk): Bitwise Functions. (line 39) * ANSI: Glossary. (line 35) +* arbitrary precision: Arbitrary Precision Arithmetic. + (line 6) * archeologists: Bugs. (line 6) * ARGC/ARGV variables <1>: ARGC and ARGV. (line 6) * ARGC/ARGV variables: Auto-set. (line 11) @@ -25258,7 +26057,7 @@ Index * asterisk (*), * operator, as regexp operator: Regexp Operators. (line 87) * asterisk (*), * operator, null strings, matching: Gory Details. - (line 165) + (line 164) * asterisk (*), ** operator <1>: Precedence. (line 49) * asterisk (*), ** operator: Arithmetic Ops. (line 81) * asterisk (*), **= operator <1>: Precedence. (line 95) @@ -25267,10 +26066,10 @@ Index * asterisk (*), *= operator: Assignment Ops. (line 129) * atan2() function: Numeric Functions. (line 11) * awf (amazingly workable formatter) program: Glossary. (line 25) -* awk debugging, enabling: Options. (line 105) -* awk enabling: Options. (line 197) +* awk debugging, enabling: Options. (line 108) +* awk enabling: Options. (line 206) * awk language, POSIX version: Assignment Ops. (line 136) -* awk profiling, enabling: Options. (line 212) +* awk profiling, enabling: Options. (line 221) * awk programs <1>: Two Rules. (line 6) * awk programs <2>: Executable Scripts. (line 6) * awk programs: Getting Started. (line 12) @@ -25328,7 +26127,7 @@ Index * AWKPATH environment variable: AWKPATH Variable. (line 6) * awkprof.out file: Profiling. (line 6) * awksed.awk program: Simple Sed. (line 25) -* awkvars.out file: Options. (line 90) +* awkvars.out file: Options. (line 93) * b debugger command (alias for break): Breakpoint Control. (line 11) * backslash (\) <1>: Regexp Operators. (line 18) * backslash (\) <2>: Quoting. (line 31) @@ -25495,7 +26294,7 @@ Index * case sensitivity, regexps and <1>: User-modified. (line 82) * case sensitivity, regexps and: Case-sensitivity. (line 6) * case sensitivity, string comparisons and: User-modified. (line 82) -* CGI, awk scripts for: Options. (line 122) +* CGI, awk scripts for: Options. (line 125) * character lists, See bracket expressions: Regexp Operators. (line 55) * character sets (machine character encodings) <1>: Glossary. (line 141) * character sets (machine character encodings): Ordinal Functions. @@ -25581,7 +26380,7 @@ Index (line 60) * compatibility mode (gawk), octal numbers: Nondecimal-numbers. (line 60) -* compatibility mode (gawk), specifying: Options. (line 78) +* compatibility mode (gawk), specifying: Options. (line 81) * compiled programs <1>: Glossary. (line 161) * compiled programs: Basic High Level. (line 14) * compiling gawk for Cygwin: Cygwin. (line 6) @@ -25602,8 +26401,12 @@ Index (line 29) * configuration options, gawk: Additional Configuration Options. (line 6) +* constants, floating-point: Floating-point Constants. + (line 6) * constants, nondecimal: Nondecimal Data. (line 6) * constants, types of: Constants. (line 6) +* context, floating-point: Floating-point Context. + (line 6) * continue statement: Continue Statement. (line 6) * control statements: Statements. (line 6) * converting, case: String Functions. (line 522) @@ -25623,10 +26426,10 @@ Index * coprocesses, closing: Close Files And Pipes. (line 6) * coprocesses, getline from: Getline/Coprocess. (line 6) -* cos() function: Numeric Functions. (line 14) +* cos() function: Numeric Functions. (line 15) * counting: Wc Program. (line 6) * csh utility: Statements/Lines. (line 44) -* csh utility, POSIXLY_CORRECT environment variable: Options. (line 325) +* csh utility, POSIXLY_CORRECT environment variable: Options. (line 334) * csh utility, |& operator, comparison with: Two-way I/O. (line 44) * ctime() user-defined function: Function Example. (line 72) * currency symbols, localization: Explaining gettext. (line 103) @@ -25658,7 +26461,7 @@ Index (line 47) * dark corner, FILENAME variable <1>: Auto-set. (line 93) * dark corner, FILENAME variable: Getline Notes. (line 19) -* dark corner, FNR/NR variables: Auto-set. (line 208) +* dark corner, FNR/NR variables: Auto-set. (line 225) * dark corner, format-control characters: Control Letters. (line 18) * dark corner, FS as null string: Single Character Fields. (line 20) @@ -25795,7 +26598,7 @@ Index (line 67) * debugging awk programs: Debugger. (line 6) * debugging gawk, bug reports: Bugs. (line 9) -* decimal point character, locale specific: Options. (line 240) +* decimal point character, locale specific: Options. (line 249) * decrement operators: Increment Ops. (line 35) * default keyword: Switch Statement. (line 6) * Deifik, Scott <1>: Bugs. (line 70) @@ -25859,7 +26662,7 @@ Index * differences in awk and gawk, regular expressions: Case-sensitivity. (line 26) * differences in awk and gawk, RS/RT variables: Records. (line 167) -* differences in awk and gawk, RT variable: Auto-set. (line 197) +* differences in awk and gawk, RT variable: Auto-set. (line 214) * differences in awk and gawk, single-character fields: Single Character Fields. (line 6) * differences in awk and gawk, split() function: String Functions. @@ -25869,7 +26672,7 @@ Index * differences in awk and gawk, strtonum() function (gawk): String Functions. (line 404) * differences in awk and gawk, TEXTDOMAIN variable: User-modified. - (line 153) + (line 162) * differences in awk and gawk, trunc-mod operation: Arithmetic Ops. (line 66) * directories, changing: Sample Library. (line 6) @@ -25987,7 +26790,7 @@ Index * exclamation point (!), !~ operator: Regexp Usage. (line 19) * exit statement: Exit Statement. (line 6) * exit status, of gawk: Exit Status. (line 6) -* exp() function: Numeric Functions. (line 17) +* exp() function: Numeric Functions. (line 18) * expand utility: Very Simple. (line 69) * expressions: Expressions. (line 6) * expressions, as patterns: Expression Patterns. (line 6) @@ -26093,7 +26896,7 @@ Index * files, as single records: Records. (line 196) * files, awk programs in: Long. (line 6) * files, awkprof.out: Profiling. (line 6) -* files, awkvars.out: Options. (line 90) +* files, awkvars.out: Options. (line 93) * files, closing: I/O Functions. (line 10) * files, descriptors, See file descriptors: Special FD. (line 6) * files, group: Group Functions. (line 6) @@ -26121,7 +26924,7 @@ Index * files, portable object template: Explaining gettext. (line 30) * files, portable object, converting to message object files: I18N Example. (line 62) -* files, portable object, generating: Options. (line 144) +* files, portable object, generating: Options. (line 147) * files, processing, ARGIND variable and: Auto-set. (line 47) * files, reading: Rewind Function. (line 6) * files, reading, multiline records: Multiple Line. (line 6) @@ -26136,12 +26939,14 @@ Index * fixed-width data: Constant Size. (line 9) * flag variables <1>: Tee Program. (line 20) * flag variables: Boolean Ops. (line 67) +* floating-point numbers, arbitrary precision: Arbitrary Precision Arithmetic. + (line 6) * floating-point, numbers <1>: Unexpected Results. (line 6) * floating-point, numbers: Basic Data Typing. (line 21) * floating-point, numbers, AWKNUM internal type: Internals. (line 19) * FNR variable <1>: Auto-set. (line 103) * FNR variable: Records. (line 6) -* FNR variable, changing: Auto-set. (line 208) +* FNR variable, changing: Auto-set. (line 225) * for statement: For Statement. (line 6) * for statement, in arrays: Scanning an Array. (line 20) * force_number() internal function: Internals. (line 27) @@ -26177,7 +26982,7 @@ Index * FS variable, --field-separator option and: Options. (line 21) * FS variable, as null string: Single Character Fields. (line 20) -* FS variable, as TAB character: Options. (line 236) +* FS variable, as TAB character: Options. (line 245) * FS variable, changing value of: Field Separators. (line 34) * FS variable, running awk programs and: Cut Program. (line 68) * FS variable, setting from command line: Command Line Field Separator. @@ -26234,7 +27039,7 @@ Index (line 44) * functions, user-defined, next/nextfile statements and: Next Statement. (line 45) -* G-d: Acknowledgments. (line 81) +* G-d: Acknowledgments. (line 83) * Garfinkle, Scott: Contributors. (line 35) * gawk program, dynamic profiling: Profiling. (line 171) * gawk, ARGIND variable in: Other Arguments. (line 12) @@ -26263,7 +27068,7 @@ Index (line 139) * gawk, ERRNO variable in: Getline. (line 19) * gawk, escape sequences: Escape Sequences. (line 125) -* gawk, extensions, disabling: Options. (line 224) +* gawk, extensions, disabling: Options. (line 233) * gawk, features, adding: Adding Code. (line 6) * gawk, features, advanced: Advanced Features. (line 6) * gawk, fflush() function in: I/O Functions. (line 44) @@ -26315,8 +27120,8 @@ Index (line 26) * gawk, regular expressions, operators: GNU Regexp Operators. (line 6) -* gawk, regular expressions, precedence: Regexp Operators. (line 157) -* gawk, RT variable in <1>: Auto-set. (line 197) +* gawk, regular expressions, precedence: Regexp Operators. (line 161) +* gawk, RT variable in <1>: Auto-set. (line 214) * gawk, RT variable in <2>: Getline/Variable/File. (line 10) * gawk, RT variable in <3>: Multiple Line. (line 129) @@ -26325,10 +27130,10 @@ Index * gawk, source code, obtaining: Getting. (line 6) * gawk, splitting fields and: Constant Size. (line 87) * gawk, string-translation functions: I18N Functions. (line 6) -* gawk, TEXTDOMAIN variable in: User-modified. (line 153) +* gawk, TEXTDOMAIN variable in: User-modified. (line 162) * gawk, timestamps: Time Functions. (line 6) * gawk, uses for: Preface. (line 36) -* gawk, versions of, information about, printing: Options. (line 270) +* gawk, versions of, information about, printing: Options. (line 279) * gawk, VMS version of: VMS Installation. (line 6) * gawk, word-boundary operator: GNU Regexp Operators. (line 63) @@ -26380,6 +27185,8 @@ Index * gettext() function (C library): Explaining gettext. (line 62) * gettimeofday() user-defined function: Gettimeofday Function. (line 16) +* GMP: Arbitrary Precision Arithmetic. + (line 6) * GNITS mailing list: Acknowledgments. (line 52) * GNU awk, See gawk: Preface. (line 49) * GNU Free Documentation License: GNU Free Documentation License. @@ -26388,7 +27195,7 @@ Index * GNU Lesser General Public License: Glossary. (line 397) * GNU long options <1>: Options. (line 6) * GNU long options: Command Line. (line 13) -* GNU long options, printing list of: Options. (line 151) +* GNU long options, printing list of: Options. (line 154) * GNU Project <1>: Glossary. (line 319) * GNU Project: Manual History. (line 11) * GNU/Linux <1>: Glossary. (line 611) @@ -26396,7 +27203,7 @@ Index * GNU/Linux: Manual History. (line 28) * GPL (General Public License) <1>: Glossary. (line 310) * GPL (General Public License): Manual History. (line 11) -* GPL (General Public License), printing: Options. (line 85) +* GPL (General Public License), printing: Options. (line 88) * grcat program: Group Functions. (line 16) * Grigera, Juan: Contributors. (line 58) * group database, reading: Group Functions. (line 6) @@ -26419,7 +27226,7 @@ Index * help debugger command: Miscellaneous Debugger Commands. (line 68) * hexadecimal numbers: Nondecimal-numbers. (line 6) -* hexadecimal values, enabling interpretation of: Options. (line 184) +* hexadecimal values, enabling interpretation of: Options. (line 193) * histsort.awk program: History Sorting. (line 25) * Hughes, Phil: Acknowledgments. (line 43) * HUP signal: Profiling. (line 203) @@ -26433,6 +27240,8 @@ Index * i debugger command (alias for info): Debugger Info. (line 13) * id utility: Id Program. (line 6) * id.awk program: Id Program. (line 30) +* IEEE-754 format: Floating-point Representation. + (line 6) * if statement <1>: If Statement. (line 6) * if statement: Regexp Usage. (line 19) * if statement, actions, changing: Ranges. (line 25) @@ -26465,6 +27274,8 @@ Index * index() function: String Functions. (line 155) * indexing arrays: Array Intro. (line 50) * indirect function calls: Indirect Calls. (line 6) +* infinite precision: Arbitrary Precision Arithmetic. + (line 6) * info debugger command: Debugger Info. (line 13) * initialization, automatic: More Complex. (line 38) * input files: Reading Files. (line 6) @@ -26491,7 +27302,9 @@ Index * installation, VMS: VMS Installation. (line 6) * installing gawk: Installation. (line 6) * INT signal (MS-Windows): Profiling. (line 206) -* int() function: Numeric Functions. (line 22) +* int() function: Numeric Functions. (line 23) +* integer, arbitrary precision: Arbitrary Precision Integers. + (line 6) * integers: Basic Data Typing. (line 21) * integers, unsigned: Basic Data Typing. (line 30) * interacting with other programs: I/O Functions. (line 63) @@ -26530,7 +27343,7 @@ Index * internationalization: I18N Functions. (line 6) * internationalization, localization <1>: Internationalization. (line 13) -* internationalization, localization: User-modified. (line 153) +* internationalization, localization: User-modified. (line 162) * internationalization, localization, character classes: Bracket Expressions. (line 90) * internationalization, localization, gawk and: Internationalization. @@ -26570,16 +27383,19 @@ Index * Kernighan, Brian <3>: Contributors. (line 12) * Kernighan, Brian <4>: BTL. (line 6) * Kernighan, Brian <5>: Concatenation. (line 6) -* Kernighan, Brian <6>: Acknowledgments. (line 75) +* Kernighan, Brian <6>: Acknowledgments. (line 77) * Kernighan, Brian <7>: Conventions. (line 34) * Kernighan, Brian: History. (line 17) * kill command, dynamic profiling: Profiling. (line 180) * Knights, jedi: Undocumented. (line 6) +* Knuth, Donald: Arbitrary Precision Arithmetic. + (line 6) * Kwok, Conrad: Contributors. (line 35) * l debugger command (alias for list): Miscellaneous Debugger Commands. (line 74) * labels.awk program: Labels Program. (line 51) * languages, data-driven: Basic High Level. (line 83) +* Laurie, Dirk: Changing Precision. (line 6) * LC_ALL locale category: Explaining gettext. (line 120) * LC_COLLATE locale category: Explaining gettext. (line 93) * LC_CTYPE locale category: Explaining gettext. (line 97) @@ -26640,9 +27456,9 @@ Index * lint checking, array subscripts: Uninitialized Subscripts. (line 43) * lint checking, empty programs: Command Line. (line 16) -* lint checking, issuing warnings: Options. (line 165) +* lint checking, issuing warnings: Options. (line 168) * lint checking, POSIXLY_CORRECT environment variable: Options. - (line 309) + (line 318) * lint checking, undefined functions: Pass By Value/Reference. (line 88) * LINT variable: User-modified. (line 98) @@ -26652,16 +27468,16 @@ Index * list debugger command: Miscellaneous Debugger Commands. (line 74) * loading extension: Loading Extensions. (line 6) -* loading, library: Options. (line 156) +* loading, library: Options. (line 159) * local variables: Variable Scope. (line 6) * locale categories: Explaining gettext. (line 80) -* locale decimal point character: Options. (line 240) +* locale decimal point character: Options. (line 249) * locale, definition of: Locales. (line 6) * localization: I18N and L10N. (line 6) * localization, See internationalization, localization: I18N and L10N. (line 6) * log files, timestamps in: Time Functions. (line 6) -* log() function: Numeric Functions. (line 29) +* log() function: Numeric Functions. (line 30) * logical false/true: Truth Values. (line 6) * logical operators, See Boolean expressions: Boolean Ops. (line 6) * login information: Passwd Functions. (line 16) @@ -26691,7 +27507,7 @@ Index * matching, expressions, See comparison expressions: Typing and Comparison. (line 9) * matching, leftmost longest: Multiple Line. (line 26) -* matching, null strings: Gory Details. (line 165) +* matching, null strings: Gory Details. (line 164) * mawk program: Other Versions. (line 35) * McPhee, Patrick: Contributors. (line 100) * memory, releasing: Internals. (line 92) @@ -26706,7 +27522,11 @@ Index * mktime() function (gawk): Time Functions. (line 24) * modifiers, in format specifiers: Format Modifiers. (line 6) * monetary information, localization: Explaining gettext. (line 103) +* MPFR: Arbitrary Precision Arithmetic. + (line 6) * msgfmt utility: I18N Example. (line 62) +* multiple precision: Arbitrary Precision Arithmetic. + (line 6) * n debugger command (alias for next): Debugger Execution Control. (line 43) * names, arrays/variables <1>: Library Names. (line 6) @@ -26723,7 +27543,7 @@ Index * networks, programming: TCP/IP Networking. (line 6) * networks, support for: Special Network. (line 6) * newlines <1>: Boolean Ops. (line 67) -* newlines <2>: Options. (line 230) +* newlines <2>: Options. (line 239) * newlines: Statements/Lines. (line 6) * newlines, as field separators: Default Field Splitting. (line 6) @@ -26762,7 +27582,7 @@ Index * not Boolean-logic operator: Boolean Ops. (line 6) * NR variable <1>: Auto-set. (line 119) * NR variable: Records. (line 6) -* NR variable, changing: Auto-set. (line 208) +* NR variable, changing: Auto-set. (line 225) * null strings <1>: Basic Data Typing. (line 50) * null strings <2>: Truth Values. (line 6) * null strings <3>: Regexp Field Splitting. @@ -26772,7 +27592,7 @@ Index * null strings, as array subscripts: Uninitialized Subscripts. (line 43) * null strings, converting numbers to strings: Conversion. (line 21) -* null strings, matching: Gory Details. (line 165) +* null strings, matching: Gory Details. (line 164) * null strings, quoting and: Quoting. (line 62) * number sign (#), #! (executable scripts): Executable Scripts. (line 6) @@ -26793,7 +27613,7 @@ Index * numbers, hexadecimal: Nondecimal-numbers. (line 6) * numbers, NODE internal type: Internals. (line 23) * numbers, octal: Nondecimal-numbers. (line 6) -* numbers, random: Numeric Functions. (line 63) +* numbers, random: Numeric Functions. (line 64) * numbers, rounding: Round Function. (line 6) * numeric, constants: Scalar Constants. (line 6) * numeric, output format: OFMT. (line 6) @@ -26803,7 +27623,7 @@ Index * oawk utility: Names. (line 17) * obsolete features: Obsolete. (line 6) * octal numbers: Nondecimal-numbers. (line 6) -* octal values, enabling interpretation of: Options. (line 184) +* octal values, enabling interpretation of: Options. (line 193) * OFMT variable <1>: User-modified. (line 115) * OFMT variable <2>: Conversion. (line 55) * OFMT variable: OFMT. (line 15) @@ -26856,7 +27676,7 @@ Index * options, deprecated: Obsolete. (line 6) * options, long <1>: Options. (line 6) * options, long: Command Line. (line 13) -* options, printing list of: Options. (line 151) +* options, printing list of: Options. (line 154) * OR bitwise operation: Bitwise Functions. (line 6) * or Boolean-logic operator: Boolean Ops. (line 6) * or() function (gawk): Bitwise Functions. (line 48) @@ -26948,13 +27768,13 @@ Index * portability, NF variable, decrementing: Changing Fields. (line 115) * portability, operators: Increment Ops. (line 61) * portability, operators, not in POSIX awk: Precedence. (line 98) -* portability, POSIXLY_CORRECT environment variable: Options. (line 330) +* portability, POSIXLY_CORRECT environment variable: Options. (line 339) * portability, substr() function: String Functions. (line 512) * portable object files <1>: Translator i18n. (line 6) * portable object files: Explaining gettext. (line 36) * portable object files, converting to message object files: I18N Example. (line 62) -* portable object files, generating: Options. (line 144) +* portable object files, generating: Options. (line 147) * portable object template files: Explaining gettext. (line 30) * porting gawk: New Ports. (line 6) * positional specifiers, printf statement <1>: Printf Ordering. @@ -26995,17 +27815,19 @@ Index * POSIX awk, OFMT variable and: OFMT. (line 27) * POSIX awk, period (.), using: Regexp Operators. (line 50) * POSIX awk, printf format strings and: Format Modifiers. (line 159) -* POSIX awk, regular expressions and: Regexp Operators. (line 157) +* POSIX awk, regular expressions and: Regexp Operators. (line 161) * POSIX awk, timestamps and: Time Functions. (line 6) * POSIX awk, | I/O operator and: Getline/Pipe. (line 52) -* POSIX mode: Options. (line 224) +* POSIX mode: Options. (line 233) * POSIX, awk and: Preface. (line 23) * POSIX, gawk extensions not included in: POSIX/GNU. (line 6) * POSIX, programs, implementing in awk: Clones. (line 6) -* POSIXLY_CORRECT environment variable: Options. (line 309) +* POSIXLY_CORRECT environment variable: Options. (line 318) +* PREC variable <1>: Setting Precision. (line 6) +* PREC variable: User-modified. (line 134) * precedence <1>: Precedence. (line 6) * precedence: Increment Ops. (line 61) -* precedence, regexp operators: Regexp Operators. (line 152) +* precedence, regexp operators: Regexp Operators. (line 156) * print debugger command: Viewing And Changing Data. (line 36) * print statement: Printing. (line 16) @@ -27036,7 +27858,7 @@ Index * printf statement, sprintf() function and: Round Function. (line 6) * printf statement, syntax of: Basic Printf. (line 6) * printing: Printing. (line 6) -* printing, list of options: Options. (line 151) +* printing, list of options: Options. (line 154) * printing, mailing labels: Labels Program. (line 6) * printing, unduplicated lines of text: Uniq Program. (line 6) * printing, user information: Id Program. (line 6) @@ -27096,12 +27918,12 @@ Index * r debugger command (alias for run): Debugger Execution Control. (line 62) * Rakitzis, Byron: History Sorting. (line 25) -* rand() function: Numeric Functions. (line 33) +* rand() function: Numeric Functions. (line 34) * random numbers, Cliff: Cliff Random Function. (line 6) * random numbers, rand()/srand() functions: Numeric Functions. - (line 33) -* random numbers, seed of: Numeric Functions. (line 63) + (line 34) +* random numbers, seed of: Numeric Functions. (line 64) * range expressions (regexps): Bracket Expressions. (line 6) * range patterns: Ranges. (line 6) * Rankin, Pat <1>: Bugs. (line 72) @@ -27111,7 +27933,7 @@ Index * readable data files, checking: File Checking. (line 6) * readable.awk program: File Checking. (line 11) * recipe for a programming language: History. (line 6) -* record separators <1>: User-modified. (line 134) +* record separators <1>: User-modified. (line 143) * record separators: Records. (line 14) * record separators, changing: Records. (line 81) * record separators, regular expressions as: Records. (line 112) @@ -27159,7 +27981,7 @@ Index (line 59) * regular expressions, gawk, command-line options: GNU Regexp Operators. (line 70) -* regular expressions, interval expressions and: Options. (line 249) +* regular expressions, interval expressions and: Options. (line 258) * regular expressions, leftmost longest match: Leftmost Longest. (line 6) * regular expressions, operators <1>: Regexp Operators. (line 6) @@ -27171,7 +27993,7 @@ Index * regular expressions, operators, gawk: GNU Regexp Operators. (line 6) * regular expressions, operators, precedence of: Regexp Operators. - (line 152) + (line 156) * regular expressions, searching for: Egrep Program. (line 6) * relational operators, See comparison operators: Typing and Comparison. (line 9) @@ -27193,7 +28015,7 @@ Index * right angle bracket (>), >> operator (I/O): Redirection. (line 50) * right shift, bitwise: Bitwise Functions. (line 32) * Ritchie, Dennis: Basic Data Typing. (line 74) -* RLENGTH variable: Auto-set. (line 184) +* RLENGTH variable: Auto-set. (line 201) * RLENGTH variable, match() function and: String Functions. (line 223) * Robbins, Arnold <1>: Future Extensions. (line 6) * Robbins, Arnold <2>: Bugs. (line 32) @@ -27204,23 +28026,27 @@ Index * Robbins, Arnold: Command Line Field Separator. (line 80) * Robbins, Bill: Getline/Pipe. (line 36) -* Robbins, Harry: Acknowledgments. (line 81) -* Robbins, Jean: Acknowledgments. (line 81) +* Robbins, Harry: Acknowledgments. (line 83) +* Robbins, Jean: Acknowledgments. (line 83) * Robbins, Miriam <1>: Passwd Functions. (line 90) * Robbins, Miriam <2>: Getline/Pipe. (line 36) -* Robbins, Miriam: Acknowledgments. (line 81) +* Robbins, Miriam: Acknowledgments. (line 83) * Robinson, Will: Dynamic Extensions. (line 6) * robot, the: Dynamic Extensions. (line 6) * Rommel, Kai Uwe: Contributors. (line 43) * round() user-defined function: Round Function. (line 16) +* rounding mode, floating-point: Rounding Mode. (line 6) * rounding numbers: Round Function. (line 6) -* RS variable <1>: User-modified. (line 134) +* ROUNDMODE variable <1>: Setting Rounding Mode. + (line 6) +* ROUNDMODE variable: User-modified. (line 138) +* RS variable <1>: User-modified. (line 143) * RS variable: Records. (line 20) * RS variable, multiline records and: Multiple Line. (line 17) * rshift() function (gawk): Bitwise Functions. (line 51) -* RSTART variable: Auto-set. (line 190) +* RSTART variable: Auto-set. (line 207) * RSTART variable, match() function and: String Functions. (line 223) -* RT variable <1>: Auto-set. (line 197) +* RT variable <1>: Auto-set. (line 214) * RT variable <2>: Getline/Variable/File. (line 10) * RT variable <3>: Multiple Line. (line 129) @@ -27233,7 +28059,7 @@ Index * rvalues/lvalues: Assignment Ops. (line 32) * s debugger command (alias for step): Debugger Execution Control. (line 68) -* sandbox mode: Options. (line 256) +* sandbox mode: Options. (line 265) * scalar values: Basic Data Typing. (line 13) * Schorr, Andrew: Acknowledgments. (line 60) * Schreiber, Bert: Acknowledgments. (line 38) @@ -27265,11 +28091,11 @@ Index * separators, field, FIELDWIDTHS variable and: User-modified. (line 35) * separators, field, FPAT variable and: User-modified. (line 45) * separators, field, POSIX and: Fields. (line 6) -* separators, for records <1>: User-modified. (line 134) +* separators, for records <1>: User-modified. (line 143) * separators, for records: Records. (line 14) * separators, for records, regular expressions as: Records. (line 112) * separators, for statements in actions: Action Overview. (line 19) -* separators, subscript: User-modified. (line 147) +* separators, subscript: User-modified. (line 156) * set debugger command: Viewing And Changing Data. (line 59) * shells, piping commands into: Redirection. (line 143) @@ -27306,7 +28132,7 @@ Index * SIGUSR1 signal: Profiling. (line 180) * silent debugger command: Debugger Execution Control. (line 10) -* sin() function: Numeric Functions. (line 74) +* sin() function: Numeric Functions. (line 75) * single precision floating-point: Basic Data Typing. (line 36) * single quote (') <1>: Quoting. (line 31) * single quote (') <2>: Long. (line 33) @@ -27331,7 +28157,7 @@ Index * source code, jawk: Other Versions. (line 97) * source code, libmawk: Other Versions. (line 105) * source code, mawk: Other Versions. (line 35) -* source code, mixing: Options. (line 114) +* source code, mixing: Options. (line 117) * source code, pawk: Other Versions. (line 69) * source code, QSE Awk: Other Versions. (line 109) * source code, QuikTrim Awk: Other Versions. (line 113) @@ -27349,9 +28175,9 @@ Index * sprintf() function, OFMT variable and: User-modified. (line 124) * sprintf() function, print/printf statements and: Round Function. (line 6) -* sqrt() function: Numeric Functions. (line 77) +* sqrt() function: Numeric Functions. (line 78) * square brackets ([]): Regexp Operators. (line 55) -* srand() function: Numeric Functions. (line 81) +* srand() function: Numeric Functions. (line 82) * Stallman, Richard <1>: Glossary. (line 301) * Stallman, Richard <2>: Contributors. (line 24) * Stallman, Richard <3>: Acknowledgments. (line 18) @@ -27402,7 +28228,7 @@ Index (line 43) * sub() function, arguments of: String Functions. (line 462) * sub() function, escape processing: Gory Details. (line 6) -* subscript separators: User-modified. (line 147) +* subscript separators: User-modified. (line 156) * subscripts in arrays, multidimensional: Multi-dimensional. (line 10) * subscripts in arrays, multidimensional, scanning: Multi-scanning. (line 11) @@ -27410,7 +28236,7 @@ Index (line 6) * subscripts in arrays, uninitialized variables as: Uninitialized Subscripts. (line 6) -* SUBSEP variable: User-modified. (line 147) +* SUBSEP variable: User-modified. (line 156) * SUBSEP variable, multidimensional arrays: Multi-dimensional. (line 16) * substr() function: String Functions. (line 481) @@ -27443,7 +28269,7 @@ Index * 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 153) +* TEXTDOMAIN variable: User-modified. (line 162) * TEXTDOMAIN variable, BEGIN pattern and: Programmer i18n. (line 60) * TEXTDOMAIN variable, portability and: I18N Portability. (line 20) * textdomain() function (C library): Explaining gettext. (line 27) @@ -27471,7 +28297,7 @@ Index * trace debugger command: Miscellaneous Debugger Commands. (line 110) * translate.awk program: Translate Program. (line 55) -* troubleshooting, --non-decimal-data option: Options. (line 184) +* troubleshooting, --non-decimal-data option: Options. (line 193) * troubleshooting, == operator: Comparison Operators. (line 37) * troubleshooting, awk uses FS not IFS: Field Separators. (line 29) @@ -27503,7 +28329,7 @@ Index * troubleshooting, substr() function: String Functions. (line 499) * troubleshooting, system() function: I/O Functions. (line 85) * troubleshooting, typographical errors, global variables: Options. - (line 95) + (line 98) * true, logical: Truth Values. (line 6) * Trueman, David <1>: Contributors. (line 31) * Trueman, David <2>: Acknowledgments. (line 47) @@ -27575,7 +28401,7 @@ Index (line 6) * variables, getline command into, using: Getline/Variable. (line 6) * variables, global, for library functions: Library Names. (line 11) -* variables, global, printing list of: Options. (line 90) +* variables, global, printing list of: Options. (line 93) * variables, initializing: Using Variables. (line 20) * variables, local: Variable Scope. (line 6) * variables, names of: Arrays. (line 18) @@ -27605,7 +28431,7 @@ Index * Wall, Larry <1>: Future Extensions. (line 6) * Wall, Larry: Array Intro. (line 6) * Wallin, Anders: Acknowledgments. (line 60) -* warnings, issuing: Options. (line 165) +* warnings, issuing: Options. (line 168) * watch debugger command: Viewing And Changing Data. (line 67) * wc utility: Wc Program. (line 6) @@ -27617,7 +28443,7 @@ Index * whitespace, as field separators: Default Field Splitting. (line 6) * whitespace, functions, calling: Calling Built-in. (line 10) -* whitespace, newlines as: Options. (line 230) +* whitespace, newlines as: Options. (line 239) * Williams, Kent: Contributors. (line 35) * Woehlke, Matthew: Contributors. (line 79) * Woods, John: Contributors. (line 28) @@ -27672,422 +28498,443 @@ Index Tag Table: -Node: Top1346 -Node: Foreword30610 -Node: Preface34955 -Ref: Preface-Footnote-138008 -Ref: Preface-Footnote-238114 -Node: History38346 -Node: Names40737 -Ref: Names-Footnote-142214 -Node: This Manual42286 -Ref: This Manual-Footnote-147224 -Node: Conventions47324 -Node: Manual History49458 -Ref: Manual History-Footnote-152728 -Ref: Manual History-Footnote-252769 -Node: How To Contribute52843 -Node: Acknowledgments53987 -Node: Getting Started58318 -Node: Running gawk60697 -Node: One-shot61883 -Node: Read Terminal63108 -Ref: Read Terminal-Footnote-164758 -Ref: Read Terminal-Footnote-265034 -Node: Long65205 -Node: Executable Scripts66581 -Ref: Executable Scripts-Footnote-168450 -Ref: Executable Scripts-Footnote-268552 -Node: Comments69003 -Node: Quoting71470 -Node: DOS Quoting76093 -Node: Sample Data Files76768 -Node: Very Simple79800 -Node: Two Rules84399 -Node: More Complex86546 -Ref: More Complex-Footnote-189476 -Node: Statements/Lines89561 -Ref: Statements/Lines-Footnote-194023 -Node: Other Features94288 -Node: When95216 -Node: Invoking Gawk97363 -Node: Command Line98824 -Node: Options99607 -Ref: Options-Footnote-1113930 -Node: Other Arguments113955 -Node: Naming Standard Input116613 -Node: Environment Variables117707 -Node: AWKPATH Variable118265 -Ref: AWKPATH Variable-Footnote-1120854 -Node: AWKLIBPATH Variable121114 -Node: Other Environment Variables121711 -Node: Exit Status124206 -Node: Include Files124881 -Node: Loading Shared Libraries128382 -Node: Obsolete129607 -Node: Undocumented130304 -Node: Regexp130547 -Node: Regexp Usage131936 -Node: Escape Sequences133962 -Node: Regexp Operators139725 -Ref: Regexp Operators-Footnote-1146922 -Ref: Regexp Operators-Footnote-2147069 -Node: Bracket Expressions147167 -Ref: table-char-classes149057 -Node: GNU Regexp Operators151583 -Node: Case-sensitivity155306 -Ref: Case-sensitivity-Footnote-1158274 -Ref: Case-sensitivity-Footnote-2158509 -Node: Leftmost Longest158617 -Node: Computed Regexps159818 -Node: Reading Files163228 -Node: Records165232 -Ref: Records-Footnote-1173906 -Node: Fields173943 -Ref: Fields-Footnote-1176976 -Node: Nonconstant Fields177062 -Node: Changing Fields179264 -Node: Field Separators185245 -Node: Default Field Splitting187874 -Node: Regexp Field Splitting188991 -Node: Single Character Fields192333 -Node: Command Line Field Separator193392 -Node: Field Splitting Summary196833 -Ref: Field Splitting Summary-Footnote-1200025 -Node: Constant Size200126 -Node: Splitting By Content204710 -Ref: Splitting By Content-Footnote-1208436 -Node: Multiple Line208476 -Ref: Multiple Line-Footnote-1214323 -Node: Getline214502 -Node: Plain Getline216718 -Node: Getline/Variable218807 -Node: Getline/File219948 -Node: Getline/Variable/File221270 -Ref: Getline/Variable/File-Footnote-1222869 -Node: Getline/Pipe222956 -Node: Getline/Variable/Pipe225516 -Node: Getline/Coprocess226623 -Node: Getline/Variable/Coprocess227866 -Node: Getline Notes228580 -Node: Getline Summary230522 -Ref: table-getline-variants230865 -Node: Read Timeout231724 -Ref: Read Timeout-Footnote-1235469 -Node: Command line directories235526 -Node: Printing236156 -Node: Print237787 -Node: Print Examples239124 -Node: Output Separators241908 -Node: OFMT243668 -Node: Printf245026 -Node: Basic Printf245932 -Node: Control Letters247471 -Node: Format Modifiers251283 -Node: Printf Examples257292 -Node: Redirection260007 -Node: Special Files266991 -Node: Special FD267524 -Ref: Special FD-Footnote-1271149 -Node: Special Network271223 -Node: Special Caveats272073 -Node: Close Files And Pipes272869 -Ref: Close Files And Pipes-Footnote-1279892 -Ref: Close Files And Pipes-Footnote-2280040 -Node: Expressions280190 -Node: Values281322 -Node: Constants281998 -Node: Scalar Constants282678 -Ref: Scalar Constants-Footnote-1283537 -Node: Nondecimal-numbers283719 -Node: Regexp Constants286778 -Node: Using Constant Regexps287253 -Node: Variables290308 -Node: Using Variables290963 -Node: Assignment Options292687 -Node: Conversion294559 -Ref: table-locale-affects299935 -Ref: Conversion-Footnote-1300562 -Node: All Operators300671 -Node: Arithmetic Ops301301 -Node: Concatenation303806 -Ref: Concatenation-Footnote-1306599 -Node: Assignment Ops306719 -Ref: table-assign-ops311707 -Node: Increment Ops313118 -Node: Truth Values and Conditions316588 -Node: Truth Values317671 -Node: Typing and Comparison318720 -Node: Variable Typing319509 -Ref: Variable Typing-Footnote-1323406 -Node: Comparison Operators323528 -Ref: table-relational-ops323938 -Node: POSIX String Comparison327490 -Ref: POSIX String Comparison-Footnote-1328446 -Node: Boolean Ops328584 -Ref: Boolean Ops-Footnote-1332662 -Node: Conditional Exp332753 -Node: Function Calls334485 -Node: Precedence338079 -Node: Locales341748 -Node: Patterns and Actions342837 -Node: Pattern Overview343891 -Node: Regexp Patterns345560 -Node: Expression Patterns346103 -Node: Ranges349788 -Node: BEGIN/END352754 -Node: Using BEGIN/END353516 -Ref: Using BEGIN/END-Footnote-1356247 -Node: I/O And BEGIN/END356353 -Node: BEGINFILE/ENDFILE358635 -Node: Empty361528 -Node: Using Shell Variables361844 -Node: Action Overview364129 -Node: Statements366486 -Node: If Statement368340 -Node: While Statement369839 -Node: Do Statement371883 -Node: For Statement373039 -Node: Switch Statement376191 -Node: Break Statement378288 -Node: Continue Statement380278 -Node: Next Statement382071 -Node: Nextfile Statement384461 -Node: Exit Statement387006 -Node: Built-in Variables389422 -Node: User-modified390517 -Ref: User-modified-Footnote-1398543 -Node: Auto-set398605 -Ref: Auto-set-Footnote-1407958 -Node: ARGC and ARGV408163 -Node: Arrays412014 -Node: Array Basics413519 -Node: Array Intro414345 -Node: Reference to Elements418663 -Node: Assigning Elements420933 -Node: Array Example421424 -Node: Scanning an Array423156 -Node: Controlling Scanning425470 -Ref: Controlling Scanning-Footnote-1430403 -Node: Delete430719 -Ref: Delete-Footnote-1433154 -Node: Numeric Array Subscripts433211 -Node: Uninitialized Subscripts435394 -Node: Multi-dimensional437022 -Node: Multi-scanning440116 -Node: Arrays of Arrays441707 -Node: Functions446352 -Node: Built-in447174 -Node: Calling Built-in448252 -Node: Numeric Functions450240 -Ref: Numeric Functions-Footnote-1454005 -Ref: Numeric Functions-Footnote-2454362 -Ref: Numeric Functions-Footnote-3454410 -Node: String Functions454679 -Ref: String Functions-Footnote-1478176 -Ref: String Functions-Footnote-2478305 -Ref: String Functions-Footnote-3478553 -Node: Gory Details478640 -Ref: table-sub-escapes480319 -Ref: table-sub-posix-92481676 -Ref: table-sub-proposed483022 -Ref: table-posix-sub484375 -Ref: table-gensub-escapes485924 -Ref: Gory Details-Footnote-1487134 -Ref: Gory Details-Footnote-2487185 -Node: I/O Functions487336 -Ref: I/O Functions-Footnote-1493991 -Node: Time Functions494138 -Ref: Time Functions-Footnote-1505030 -Ref: Time Functions-Footnote-2505098 -Ref: Time Functions-Footnote-3505256 -Ref: Time Functions-Footnote-4505367 -Ref: Time Functions-Footnote-5505479 -Ref: Time Functions-Footnote-6505706 -Node: Bitwise Functions505972 -Ref: table-bitwise-ops506530 -Ref: Bitwise Functions-Footnote-1510693 -Node: Type Functions510877 -Node: I18N Functions511347 -Node: User-defined512974 -Node: Definition Syntax513778 -Ref: Definition Syntax-Footnote-1518688 -Node: Function Example518757 -Node: Function Caveats521351 -Node: Calling A Function521772 -Node: Variable Scope522887 -Node: Pass By Value/Reference524862 -Node: Return Statement528302 -Node: Dynamic Typing531283 -Node: Indirect Calls532018 -Node: Internationalization541703 -Node: I18N and L10N543129 -Node: Explaining gettext543815 -Ref: Explaining gettext-Footnote-1548881 -Ref: Explaining gettext-Footnote-2549065 -Node: Programmer i18n549230 -Node: Translator i18n553430 -Node: String Extraction554223 -Ref: String Extraction-Footnote-1555184 -Node: Printf Ordering555270 -Ref: Printf Ordering-Footnote-1558054 -Node: I18N Portability558118 -Ref: I18N Portability-Footnote-1560567 -Node: I18N Example560630 -Ref: I18N Example-Footnote-1563265 -Node: Gawk I18N563337 -Node: Advanced Features563954 -Node: Nondecimal Data565467 -Node: Array Sorting567050 -Node: Controlling Array Traversal567747 -Node: Array Sorting Functions575984 -Ref: Array Sorting Functions-Footnote-1579658 -Ref: Array Sorting Functions-Footnote-2579751 -Node: Two-way I/O579945 -Ref: Two-way I/O-Footnote-1585377 -Node: TCP/IP Networking585447 -Node: Profiling588291 -Node: Library Functions595745 -Ref: Library Functions-Footnote-1598752 -Node: Library Names598923 -Ref: Library Names-Footnote-1602394 -Ref: Library Names-Footnote-2602614 -Node: General Functions602700 -Node: Strtonum Function603653 -Node: Assert Function606583 -Node: Round Function609909 -Node: Cliff Random Function611452 -Node: Ordinal Functions612468 -Ref: Ordinal Functions-Footnote-1615538 -Ref: Ordinal Functions-Footnote-2615790 -Node: Join Function615999 -Ref: Join Function-Footnote-1617770 -Node: Gettimeofday Function617970 -Node: Data File Management621685 -Node: Filetrans Function622317 -Node: Rewind Function626456 -Node: File Checking627843 -Node: Empty Files628937 -Node: Ignoring Assigns631167 -Node: Getopt Function632720 -Ref: Getopt Function-Footnote-1644024 -Node: Passwd Functions644227 -Ref: Passwd Functions-Footnote-1653202 -Node: Group Functions653290 -Node: Walking Arrays661374 -Node: Sample Programs662943 -Node: Running Examples663608 -Node: Clones664336 -Node: Cut Program665560 -Node: Egrep Program675405 -Ref: Egrep Program-Footnote-1683178 -Node: Id Program683288 -Node: Split Program686904 -Ref: Split Program-Footnote-1690423 -Node: Tee Program690551 -Node: Uniq Program693354 -Node: Wc Program700783 -Ref: Wc Program-Footnote-1705049 -Ref: Wc Program-Footnote-2705249 -Node: Miscellaneous Programs705341 -Node: Dupword Program706529 -Node: Alarm Program708560 -Node: Translate Program713309 -Ref: Translate Program-Footnote-1717696 -Ref: Translate Program-Footnote-2717924 -Node: Labels Program718058 -Ref: Labels Program-Footnote-1721429 -Node: Word Sorting721513 -Node: History Sorting725397 -Node: Extract Program727236 -Ref: Extract Program-Footnote-1734719 -Node: Simple Sed734847 -Node: Igawk Program737909 -Ref: Igawk Program-Footnote-1753066 -Ref: Igawk Program-Footnote-2753267 -Node: Anagram Program753405 -Node: Signature Program756473 -Node: Debugger757573 -Node: Debugging758525 -Node: Debugging Concepts758958 -Node: Debugging Terms760814 -Node: Awk Debugging763411 -Node: Sample Debugging Session764303 -Node: Debugger Invocation764823 -Node: Finding The Bug766152 -Node: List of Debugger Commands772640 -Node: Breakpoint Control773974 -Node: Debugger Execution Control777638 -Node: Viewing And Changing Data780998 -Node: Execution Stack784354 -Node: Debugger Info785821 -Node: Miscellaneous Debugger Commands789802 -Node: Readline Support795247 -Node: Limitations796078 -Node: Language History798330 -Node: V7/SVR3.1799842 -Node: SVR4802163 -Node: POSIX803605 -Node: BTL804613 -Node: POSIX/GNU805347 -Node: Common Extensions810638 -Node: Ranges and Locales811745 -Ref: Ranges and Locales-Footnote-1816349 -Node: Contributors816570 -Node: Installation820831 -Node: Gawk Distribution821725 -Node: Getting822209 -Node: Extracting823035 -Node: Distribution contents824727 -Node: Unix Installation829949 -Node: Quick Installation830566 -Node: Additional Configuration Options832528 -Node: Configuration Philosophy834005 -Node: Non-Unix Installation836347 -Node: PC Installation836805 -Node: PC Binary Installation838104 -Node: PC Compiling839952 -Node: PC Testing842896 -Node: PC Using844072 -Node: Cygwin848257 -Node: MSYS849257 -Node: VMS Installation849771 -Node: VMS Compilation850374 -Ref: VMS Compilation-Footnote-1851381 -Node: VMS Installation Details851439 -Node: VMS Running853074 -Node: VMS Old Gawk854681 -Node: Bugs855155 -Node: Other Versions859007 -Node: Notes864322 -Node: Compatibility Mode865014 -Node: Additions865797 -Node: Accessing The Source866609 -Node: Adding Code868034 -Node: New Ports874001 -Node: Dynamic Extensions878114 -Node: Internals879554 -Node: Plugin License888376 -Node: Loading Extensions889014 -Node: Sample Library890853 -Node: Internal File Description891543 -Node: Internal File Ops895258 -Ref: Internal File Ops-Footnote-1900000 -Node: Using Internal File Ops900140 -Node: Future Extensions902517 -Node: Basic Concepts905021 -Node: Basic High Level905778 -Ref: Basic High Level-Footnote-1909813 -Node: Basic Data Typing909998 -Node: Floating Point Issues914523 -Node: String Conversion Precision915606 -Ref: String Conversion Precision-Footnote-1917306 -Node: Unexpected Results917415 -Node: POSIX Floating Point Problems919241 -Ref: POSIX Floating Point Problems-Footnote-1922946 -Node: Glossary922984 -Node: Copying947960 -Node: GNU Free Documentation License985517 -Node: Index1010654 +Node: Top1352 +Node: Foreword31758 +Node: Preface36103 +Ref: Preface-Footnote-139156 +Ref: Preface-Footnote-239262 +Node: History39494 +Node: Names41885 +Ref: Names-Footnote-143362 +Node: This Manual43434 +Ref: This Manual-Footnote-148372 +Node: Conventions48472 +Node: Manual History50606 +Ref: Manual History-Footnote-153876 +Ref: Manual History-Footnote-253917 +Node: How To Contribute53991 +Node: Acknowledgments55135 +Node: Getting Started59631 +Node: Running gawk62010 +Node: One-shot63196 +Node: Read Terminal64421 +Ref: Read Terminal-Footnote-166071 +Ref: Read Terminal-Footnote-266347 +Node: Long66518 +Node: Executable Scripts67894 +Ref: Executable Scripts-Footnote-169763 +Ref: Executable Scripts-Footnote-269865 +Node: Comments70412 +Node: Quoting72879 +Node: DOS Quoting77502 +Node: Sample Data Files78177 +Node: Very Simple81209 +Node: Two Rules85808 +Node: More Complex87955 +Ref: More Complex-Footnote-190885 +Node: Statements/Lines90970 +Ref: Statements/Lines-Footnote-195432 +Node: Other Features95697 +Node: When96625 +Node: Invoking Gawk98772 +Node: Command Line100233 +Node: Options101016 +Ref: Options-Footnote-1115658 +Node: Other Arguments115683 +Node: Naming Standard Input118341 +Node: Environment Variables119435 +Node: AWKPATH Variable119993 +Ref: AWKPATH Variable-Footnote-1122582 +Node: AWKLIBPATH Variable122842 +Node: Other Environment Variables123439 +Node: Exit Status125934 +Node: Include Files126609 +Node: Loading Shared Libraries130110 +Node: Obsolete131335 +Node: Undocumented132032 +Node: Regexp132275 +Node: Regexp Usage133664 +Node: Escape Sequences135690 +Node: Regexp Operators141453 +Ref: Regexp Operators-Footnote-1148833 +Ref: Regexp Operators-Footnote-2148980 +Node: Bracket Expressions149078 +Ref: table-char-classes150968 +Node: GNU Regexp Operators153491 +Node: Case-sensitivity157214 +Ref: Case-sensitivity-Footnote-1160182 +Ref: Case-sensitivity-Footnote-2160417 +Node: Leftmost Longest160525 +Node: Computed Regexps161726 +Node: Reading Files165136 +Node: Records167140 +Ref: Records-Footnote-1175814 +Node: Fields175851 +Ref: Fields-Footnote-1178884 +Node: Nonconstant Fields178970 +Node: Changing Fields181172 +Node: Field Separators187153 +Node: Default Field Splitting189782 +Node: Regexp Field Splitting190899 +Node: Single Character Fields194241 +Node: Command Line Field Separator195300 +Node: Field Splitting Summary198741 +Ref: Field Splitting Summary-Footnote-1201933 +Node: Constant Size202034 +Node: Splitting By Content206618 +Ref: Splitting By Content-Footnote-1210344 +Node: Multiple Line210384 +Ref: Multiple Line-Footnote-1216231 +Node: Getline216410 +Node: Plain Getline218626 +Node: Getline/Variable220715 +Node: Getline/File221856 +Node: Getline/Variable/File223178 +Ref: Getline/Variable/File-Footnote-1224777 +Node: Getline/Pipe224864 +Node: Getline/Variable/Pipe227424 +Node: Getline/Coprocess228531 +Node: Getline/Variable/Coprocess229774 +Node: Getline Notes230488 +Node: Getline Summary232430 +Ref: table-getline-variants232773 +Node: Read Timeout233629 +Ref: Read Timeout-Footnote-1237374 +Node: Command line directories237431 +Node: Printing238061 +Node: Print239692 +Node: Print Examples241029 +Node: Output Separators243813 +Node: OFMT245573 +Node: Printf246931 +Node: Basic Printf247837 +Node: Control Letters249376 +Node: Format Modifiers253188 +Node: Printf Examples259197 +Node: Redirection261912 +Node: Special Files268896 +Node: Special FD269429 +Ref: Special FD-Footnote-1273054 +Node: Special Network273128 +Node: Special Caveats273978 +Node: Close Files And Pipes274774 +Ref: Close Files And Pipes-Footnote-1281797 +Ref: Close Files And Pipes-Footnote-2281945 +Node: Expressions282095 +Node: Values283227 +Node: Constants283903 +Node: Scalar Constants284583 +Ref: Scalar Constants-Footnote-1285442 +Node: Nondecimal-numbers285624 +Node: Regexp Constants288683 +Node: Using Constant Regexps289158 +Node: Variables292213 +Node: Using Variables292868 +Node: Assignment Options294592 +Node: Conversion296464 +Ref: table-locale-affects301840 +Ref: Conversion-Footnote-1302464 +Node: All Operators302573 +Node: Arithmetic Ops303203 +Node: Concatenation305708 +Ref: Concatenation-Footnote-1308501 +Node: Assignment Ops308621 +Ref: table-assign-ops313609 +Node: Increment Ops315017 +Node: Truth Values and Conditions318487 +Node: Truth Values319570 +Node: Typing and Comparison320619 +Node: Variable Typing321408 +Ref: Variable Typing-Footnote-1325305 +Node: Comparison Operators325427 +Ref: table-relational-ops325837 +Node: POSIX String Comparison329386 +Ref: POSIX String Comparison-Footnote-1330342 +Node: Boolean Ops330480 +Ref: Boolean Ops-Footnote-1334558 +Node: Conditional Exp334649 +Node: Function Calls336381 +Node: Precedence339975 +Node: Locales343644 +Node: Patterns and Actions344733 +Node: Pattern Overview345787 +Node: Regexp Patterns347456 +Node: Expression Patterns347999 +Node: Ranges351684 +Node: BEGIN/END354650 +Node: Using BEGIN/END355412 +Ref: Using BEGIN/END-Footnote-1358143 +Node: I/O And BEGIN/END358249 +Node: BEGINFILE/ENDFILE360531 +Node: Empty363424 +Node: Using Shell Variables363740 +Node: Action Overview366025 +Node: Statements368382 +Node: If Statement370236 +Node: While Statement371735 +Node: Do Statement373779 +Node: For Statement374935 +Node: Switch Statement378087 +Node: Break Statement380184 +Node: Continue Statement382174 +Node: Next Statement383967 +Node: Nextfile Statement386357 +Node: Exit Statement388902 +Node: Built-in Variables391318 +Node: User-modified392413 +Ref: User-modified-Footnote-1400768 +Node: Auto-set400830 +Ref: Auto-set-Footnote-1410738 +Node: ARGC and ARGV410943 +Node: Arrays414794 +Node: Array Basics416299 +Node: Array Intro417125 +Node: Reference to Elements421443 +Node: Assigning Elements423713 +Node: Array Example424204 +Node: Scanning an Array425936 +Node: Controlling Scanning428250 +Ref: Controlling Scanning-Footnote-1433183 +Node: Delete433499 +Ref: Delete-Footnote-1435934 +Node: Numeric Array Subscripts435991 +Node: Uninitialized Subscripts438174 +Node: Multi-dimensional439802 +Node: Multi-scanning442896 +Node: Arrays of Arrays444487 +Node: Functions449132 +Node: Built-in449954 +Node: Calling Built-in451032 +Node: Numeric Functions453020 +Ref: Numeric Functions-Footnote-1456852 +Ref: Numeric Functions-Footnote-2457209 +Ref: Numeric Functions-Footnote-3457257 +Node: String Functions457526 +Ref: String Functions-Footnote-1481023 +Ref: String Functions-Footnote-2481152 +Ref: String Functions-Footnote-3481400 +Node: Gory Details481487 +Ref: table-sub-escapes483166 +Ref: table-sub-posix-92484520 +Ref: table-sub-proposed485863 +Ref: table-posix-sub487213 +Ref: table-gensub-escapes488759 +Ref: Gory Details-Footnote-1489966 +Ref: Gory Details-Footnote-2490017 +Node: I/O Functions490168 +Ref: I/O Functions-Footnote-1496823 +Node: Time Functions496970 +Ref: Time Functions-Footnote-1507862 +Ref: Time Functions-Footnote-2507930 +Ref: Time Functions-Footnote-3508088 +Ref: Time Functions-Footnote-4508199 +Ref: Time Functions-Footnote-5508311 +Ref: Time Functions-Footnote-6508538 +Node: Bitwise Functions508804 +Ref: table-bitwise-ops509362 +Ref: Bitwise Functions-Footnote-1513522 +Node: Type Functions513706 +Node: I18N Functions514176 +Node: User-defined515803 +Node: Definition Syntax516607 +Ref: Definition Syntax-Footnote-1521517 +Node: Function Example521586 +Node: Function Caveats524180 +Node: Calling A Function524601 +Node: Variable Scope525716 +Node: Pass By Value/Reference527691 +Node: Return Statement531131 +Node: Dynamic Typing534112 +Node: Indirect Calls534847 +Node: Internationalization544532 +Node: I18N and L10N545971 +Node: Explaining gettext546657 +Ref: Explaining gettext-Footnote-1551723 +Ref: Explaining gettext-Footnote-2551907 +Node: Programmer i18n552072 +Node: Translator i18n556272 +Node: String Extraction557065 +Ref: String Extraction-Footnote-1558026 +Node: Printf Ordering558112 +Ref: Printf Ordering-Footnote-1560896 +Node: I18N Portability560960 +Ref: I18N Portability-Footnote-1563409 +Node: I18N Example563472 +Ref: I18N Example-Footnote-1566107 +Node: Gawk I18N566179 +Node: Arbitrary Precision Arithmetic566796 +Ref: Arbitrary Precision Arithmetic-Footnote-1569671 +Node: Floating-point Programming569819 +Node: Floating-point Representation575089 +Node: Floating-point Context576193 +Ref: table-ieee-formats577028 +Node: Rounding Mode578398 +Ref: table-rounding-modes579025 +Ref: Rounding Mode-Footnote-1582148 +Node: Arbitrary Precision Floats582329 +Ref: Arbitrary Precision Floats-Footnote-1584370 +Node: Setting Precision584681 +Node: Setting Rounding Mode587439 +Node: Floating-point Constants588356 +Node: Changing Precision589775 +Ref: Changing Precision-Footnote-1591175 +Node: Exact Arithmetic591348 +Node: Integer Programming594361 +Node: Arbitrary Precision Integers596141 +Ref: Arbitrary Precision Integers-Footnote-1599165 +Node: MPFR and GMP Libraries599311 +Node: Advanced Features599696 +Node: Nondecimal Data601219 +Node: Array Sorting602802 +Node: Controlling Array Traversal603499 +Node: Array Sorting Functions611736 +Ref: Array Sorting Functions-Footnote-1615410 +Ref: Array Sorting Functions-Footnote-2615503 +Node: Two-way I/O615697 +Ref: Two-way I/O-Footnote-1621129 +Node: TCP/IP Networking621199 +Node: Profiling624043 +Node: Library Functions631497 +Ref: Library Functions-Footnote-1634504 +Node: Library Names634675 +Ref: Library Names-Footnote-1638146 +Ref: Library Names-Footnote-2638366 +Node: General Functions638452 +Node: Strtonum Function639405 +Node: Assert Function642335 +Node: Round Function645661 +Node: Cliff Random Function647204 +Node: Ordinal Functions648220 +Ref: Ordinal Functions-Footnote-1651290 +Ref: Ordinal Functions-Footnote-2651542 +Node: Join Function651751 +Ref: Join Function-Footnote-1653522 +Node: Gettimeofday Function653722 +Node: Data File Management657437 +Node: Filetrans Function658069 +Node: Rewind Function662208 +Node: File Checking663595 +Node: Empty Files664689 +Node: Ignoring Assigns666919 +Node: Getopt Function668472 +Ref: Getopt Function-Footnote-1679776 +Node: Passwd Functions679979 +Ref: Passwd Functions-Footnote-1688954 +Node: Group Functions689042 +Node: Walking Arrays697126 +Node: Sample Programs698695 +Node: Running Examples699360 +Node: Clones700088 +Node: Cut Program701312 +Node: Egrep Program711157 +Ref: Egrep Program-Footnote-1718930 +Node: Id Program719040 +Node: Split Program722656 +Ref: Split Program-Footnote-1726175 +Node: Tee Program726303 +Node: Uniq Program729106 +Node: Wc Program736535 +Ref: Wc Program-Footnote-1740801 +Ref: Wc Program-Footnote-2741001 +Node: Miscellaneous Programs741093 +Node: Dupword Program742281 +Node: Alarm Program744312 +Node: Translate Program749061 +Ref: Translate Program-Footnote-1753448 +Ref: Translate Program-Footnote-2753676 +Node: Labels Program753810 +Ref: Labels Program-Footnote-1757181 +Node: Word Sorting757265 +Node: History Sorting761149 +Node: Extract Program762988 +Ref: Extract Program-Footnote-1770471 +Node: Simple Sed770599 +Node: Igawk Program773661 +Ref: Igawk Program-Footnote-1788818 +Ref: Igawk Program-Footnote-2789019 +Node: Anagram Program789157 +Node: Signature Program792225 +Node: Debugger793325 +Node: Debugging794277 +Node: Debugging Concepts794710 +Node: Debugging Terms796566 +Node: Awk Debugging799163 +Node: Sample Debugging Session800055 +Node: Debugger Invocation800575 +Node: Finding The Bug801904 +Node: List of Debugger Commands808392 +Node: Breakpoint Control809726 +Node: Debugger Execution Control813390 +Node: Viewing And Changing Data816750 +Node: Execution Stack820106 +Node: Debugger Info821573 +Node: Miscellaneous Debugger Commands825554 +Node: Readline Support830999 +Node: Limitations831830 +Node: Language History834082 +Node: V7/SVR3.1835594 +Node: SVR4837915 +Node: POSIX839357 +Node: BTL840365 +Node: POSIX/GNU841099 +Node: Common Extensions846390 +Node: Ranges and Locales847497 +Ref: Ranges and Locales-Footnote-1852101 +Node: Contributors852322 +Node: Installation856583 +Node: Gawk Distribution857477 +Node: Getting857961 +Node: Extracting858787 +Node: Distribution contents860479 +Node: Unix Installation865701 +Node: Quick Installation866318 +Node: Additional Configuration Options868280 +Node: Configuration Philosophy869757 +Node: Non-Unix Installation872099 +Node: PC Installation872557 +Node: PC Binary Installation873856 +Node: PC Compiling875704 +Node: PC Testing878648 +Node: PC Using879824 +Node: Cygwin884009 +Node: MSYS885009 +Node: VMS Installation885523 +Node: VMS Compilation886126 +Ref: VMS Compilation-Footnote-1887133 +Node: VMS Installation Details887191 +Node: VMS Running888826 +Node: VMS Old Gawk890433 +Node: Bugs890907 +Node: Other Versions894759 +Node: Notes900074 +Node: Compatibility Mode900766 +Node: Additions901549 +Node: Accessing The Source902361 +Node: Adding Code903786 +Node: New Ports909753 +Node: Dynamic Extensions913866 +Node: Internals915306 +Node: Plugin License924128 +Node: Loading Extensions924766 +Node: Sample Library926605 +Node: Internal File Description927295 +Node: Internal File Ops931010 +Ref: Internal File Ops-Footnote-1935752 +Node: Using Internal File Ops935892 +Node: Future Extensions938269 +Node: Basic Concepts940773 +Node: Basic High Level941530 +Ref: Basic High Level-Footnote-1945565 +Node: Basic Data Typing945750 +Node: Floating Point Issues950275 +Node: String Conversion Precision951358 +Ref: String Conversion Precision-Footnote-1953058 +Node: Unexpected Results953167 +Node: POSIX Floating Point Problems954993 +Ref: POSIX Floating Point Problems-Footnote-1958698 +Node: Glossary958736 +Node: Copying983712 +Node: GNU Free Documentation License1021269 +Node: Index1046406 End Tag Table diff --git a/doc/gawk.texi b/doc/gawk.texi index 7b46026b..d3f5c672 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -20,7 +20,7 @@ @c applies to and all the info about who's publishing this edition @c These apply across the board. -@set UPDATE-MONTH November, 2011 +@set UPDATE-MONTH February, 2012 @set VERSION 4.0 @set PATCHLEVEL 1 @@ -79,9 +79,11 @@ @c some special symbols @iftex @set LEQ @math{@leq} +@set PI @math{@pi} @end iftex @ifnottex @set LEQ <= +@set PI @i{pi} @end ifnottex @ifnottex @@ -143,7 +145,7 @@ Some comments on the layout for TeX. @copying Copyright @copyright{} 1989, 1991, 1992, 1993, 1996, 1997, 1998, 1999, -2000, 2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011 +2000, 2001, 2002, 2003, 2004, 2005, 2007, 2009, 2010, 2011, 2012 Free Software Foundation, Inc. @sp 2 @@ -285,6 +287,8 @@ particular records in a file and perform operations upon them. * Functions:: Built-in and user-defined functions. * Internationalization:: Getting @command{gawk} to speak your language. +* Arbitrary Precision Arithmetic:: Arbitrary precision arithmetic with + @command{gawk}. * Advanced Features:: Stuff for advanced users, specific to @command{gawk}. * Library Functions:: A Library of @command{awk} Functions. @@ -554,6 +558,21 @@ particular records in a file and perform operations upon them. * I18N Portability:: @command{awk}-level portability issues. * I18N Example:: A simple i18n example. * Gawk I18N:: @command{gawk} is also internationalized. +* Floating-point Programming:: Effective floating-point programming. +* Floating-point Representation:: Binary floating-point representation. +* Floating-point Context:: Floating-point context. +* Rounding Mode:: Floating-point rounding mode. +* Arbitrary Precision Floats:: Arbitrary precision floating-point + arithmetic with @command{gawk}. +* Setting Precision:: Setting the working precision. +* Setting Rounding Mode:: Setting the rounding mode. +* Floating-point Constants:: Representing floating-point constants. +* Changing Precision:: Changing the precision of a number. +* Exact Arithmetic:: Exact arithmetic with floating-point numbers. +* Integer Programming:: Effective integer programming. +* Arbitrary Precision Integers:: Arbitrary precision integer + arithmetic with @command{gawk}. +* MPFR and GMP Libraries:: Information about the MPFR and GMP libraries. * Nondecimal Data:: Allowing nondecimal input data. * Array Sorting:: Facilities for controlling array traversal and sorting arrays. @@ -1598,10 +1617,13 @@ has been and continues to be a pleasure working with this team of fine people. John Haque contributed the modifications to convert @command{gawk} -into a byte-code interpreter, including the debugger. Stephen Davies +into a byte-code interpreter, including the debugger, and the +additional modifications for support of arbitrary precision arithmetic. +Stephen Davies contributed to the effort to bring the byte-code changes into the mainstream code base. Efraim Yawitz contributed the initial text of @ref{Debugger}. +John Haque contributed the initial text of @ref{Arbitrary Precision Arithmetic}. @cindex Kernighan, Brian I would like to thank Brian Kernighan for invaluable assistance during the @@ -1973,9 +1995,11 @@ line beginning with @samp{#!} lists the full @value{FN} of an interpreter to run and an optional initial command-line argument to pass to that interpreter. The operating system then runs the interpreter with the given argument and the full argument list of the executed program. The first argument -in the list is the full @value{FN} of the @command{awk} program. The rest of the +in the list is the full @value{FN} of the @command{awk} program. +The rest of the argument list contains either options to @command{awk}, or @value{DF}s, -or both.} as if you had +or both. Note that on many systems @command{awk} may be found in +@file{/usr/bin} instead of in @file{/bin}. Caveat Emptor.} as if you had typed @samp{awk -f advice}: @example @@ -3058,6 +3082,9 @@ The following list describes @command{gawk}-specific options: @cindex @code{-b} option @cindex @code{--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. + Normally, @command{gawk} follows the POSIX standard and attempts to process its input data according to the current locale. This can often involve converting multibyte characters into wide characters (internally), and @@ -3219,6 +3246,14 @@ when eliminating problems pointed out by @option{--lint}, you should take care to search for all occurrences of each inappropriate construct. As @command{awk} programs are usually short, doing so is not burdensome. +@item -M +@itemx --bignum +@cindex @code{-M} option +@cindex @code{--bignum} option +Force arbitrary precision arithmetic on numbers. This option has no effect +if @command{gawk} is not compiled to use the GNU MPFR and MP libraries +(@pxref{Arbitrary Precision Arithmetic}). + @item -n @itemx --non-decimal-data @cindex @code{-n} option @@ -4573,6 +4608,10 @@ it is good practice to always escape them with a backslash. Then the regexp constants are valid and work the way you want them to, using any version of @command{awk}.@footnote{Use two backslashes if you're using a string constant with a regexp operator or function.} + +Finally, when @samp{@{} and @samp{@}} appear in regexp constants +in a way that cannot be interpreted as an interval expression +(such as @code{/q@{a@}/}), then they stand for themselves. @end table @cindex precedence, regexp operators @@ -12659,6 +12698,18 @@ This is the output record separator. It is output at the end of every @code{print} statement. Its default value is @code{"\n"}, the newline character. (@xref{Output Separators}.) +@cindex @code{PREC} variable +@item PREC # +The working precision of arbitrary precision floating-point numbers, +53 by default (@pxref{Setting Precision}). + +@cindex @code{ROUNDMODE} variable +@item ROUNDMODE # +The rounding mode to use for arbitrary precision arithmetic on +numbers, by default @code{"N"} (@samp{roundTiesToEven} in +the IEEE-754 standard) +(@pxref{Setting Rounding Mode}). + @cindex @code{RS} variable @cindex separators, for records @cindex record separators @@ -12944,6 +12995,25 @@ The value of the @code{getuid()} system call. The version of @command{gawk}. @end table +The following additional elements in the array +are available to provide information about the MPFR and GMP libraries +if your version of @command{gawk} supports arbitrary precision numbers +(@pxref{Arbitrary Precision Arithmetic}): + +@table @code +@item PROCINFO["mpfr_version"] +The version of the GNU MPFR library. + +@item PROCINFO["gmp_version"] +The version of the GNU MP library. + +@item PROCINFO["prec_max"] +The maximum precision supported by MPFR. + +@item PROCINFO["prec_min"] +The minimum precision required by MPFR. +@end table + On some systems, there may be elements in the array, @code{"group1"} through @code{"group@var{N}"} for some @var{N}. @var{N} is the number of supplementary groups that the process has. Use the @code{in} operator @@ -14400,6 +14470,13 @@ Optional parameters are enclosed in square brackets@w{ ([ ]):} @item atan2(@var{y}, @var{x}) @cindex @code{atan2()} function Return the arctangent of @code{@var{y} / @var{x}} in radians. +You can use @samp{pi = atan2(0, -1)} to retrieve the value of +@tex +$\pi$. +@end tex +@ifnottex +pi. +@end ifnottex @item cos(@var{x}) @cindex @code{cos()} function @@ -18355,6 +18432,863 @@ then @command{gawk} produces usage messages, warnings, and fatal errors in the local language. @c ENDOFRANGE inloc +@node Arbitrary Precision Arithmetic +@chapter Arbitrary Precision Arithmetic with @command{gawk} +@cindex arbitrary precision +@cindex multiple precision +@cindex infinite precision +@cindex floating-point numbers, arbitrary precision +@cindex MPFR +@cindex GMP + +@cindex Knuth, Donald +@quotation +@i{There's a credibility gap: We don't know how much of the computer's answers +to believe. Novice computer users solve this problem by implicitly trusting +in the computer as an infallible authority; they tend to believe that all +digits of a printed answer are significant. Disillusioned computer users have +just the opposite approach; they are constantly afraid that their answers +are almost meaningless.} + +Donald Knuth@footnote{Donald E.@: Knuth. +@cite{The Art of Computer Programming}. Volume 2, +@cite{Seminumerical Algorithms}, third edition, +1998, ISBN 0-201-89683-4, p.@: 229.} +@end quotation + +This @value{SECTION} decsribes how to use the arbitrary precision +(also known as @dfn{multiple precision} or @dfn{infinite precision}) numeric +capabilites in @command{gawk} to produce maximally accurate results +when you need it. But first you should check if your version of +@command{gawk} supports arbitrary precision arithmetic. +The easiest way to find out is to look at the output of +the following command: + +@example +$ @kbd{gawk --version} +@print{} GNU Awk 4.1.0 (GNU MPFR 3.1.0, GNU MP 5.0.3) +@print{} Copyright (C) 1989, 1991-2012 Free Software Foundation. +@dots{} +@end example + +@command{gawk} uses the +@uref{http://www.mpfr.org, GNU MPFR} +and +@uref{http://gmplib.org, GNU MP} (GMP) +libraries for arbitrary precision +arithmetic on numbers. So if you do not see the names of these libraries +in the output, then your version of @command{gawk} does not support +arbitrary precision arithmetic. + +Even if you aren't interested in arbitrary precision arithmetic, you +may still benifit from knowing about how @command{gawk} handles numbers +in general, and the limitations of doing arithmetic with ordinary +@command{gawk} numbers. + +@menu +* Floating-point Programming:: Effective Floating-point Programming. +* Floating-point Representation:: Binary Floating-point Representation. +* Floating-point Context:: Floating-point Context. +* Rounding Mode:: Floating-point Rounding Mode. +* Arbitrary Precision Floats:: Arbitrary Precision Floating-point + Arithmetic with @command{gawk}. +* Setting Precision:: Setting the Working Precision. +* Setting Rounding Mode:: Setting the Rounding Mode. +* Floating-point Constants:: Representing Floating-point Constants. +* Changing Precision:: Changing the Precision of a Number. +* Exact Arithmetic:: Exact Arithmetic with Floating-point Numbers. +* Integer Programming:: Effective Integer Programming. +* Arbitrary Precision Integers:: Arbitrary Precision Integer + Arithmetic with @command{gawk}. +* MPFR and GMP Libraries:: Information About the MPFR and GMP Libraries. +@end menu + +@node Floating-point Programming +@section Effective Floating-point Programming + +Numerical programming is an extensive area; if you need to develop +sophisticated numerical algorithms then @command{gawk} may not be +the ideal tool, and this documentation may not be sufficient. +@c FIXME: JOHN: Do you want to cite some actual books? +It might require a book or two to communicate how to compute +with ideal accuracy and precision +and the result often depends on the particular application. + +@quotation NOTE +A floating-point calculation's @dfn{accuracy} is how close it comes +to the real value. This is as opposed to the @dfn{precision}, which +usually refers to the number of bits used to represent the number +(see @uref{http://en.wikipedia.org/wiki/Accuracy_and_precision, +the Wikipedia article} for more information). +@end quotation + +Binary floating-point representations and arithmetic are inexact. +Simple values like 0.1 cannot be precisely represented using +binary floating-point numbers, and the limited precision of +floating-point numbers means that slight changes in +the order of operations or the precision of intermediate storage +can change the result. To make matters worse with arbitrary precision +floating-point, you can set the precision before starting a computation, +but then you cannot be sure of the number of significant decimal places +in the final result. + +Sometimes you need to think more about what you really want +and what's really happening. Consider the two numbers +in the following example: + +@example +x = 0.875 # 1/2 + 1/4 + 1/8 +y = 0.425 +@end example + +Unlike the number in @code{y}, the number stored in @code{x} +is exactly representable +in binary since it can be written as a finite sum of one or +more fractions whose denominators are all powers of two. +When @command{gawk} reads a floating-point number from +program source, it automatically rounds that number to whatever +precision your machine supports. If you try to print the numeric +content of a variable using an output format string of @code{"%.17g"}, +it may not produce the same number as you assigned to it: + +@example +$ @kbd{gawk 'BEGIN @{ x = 0.875; y = 0.425} +> @kbd{ printf("%0.17g, %0.17g\n", x, y) @}'} +@print{} 0.875, 0.42499999999999999 +@end example + +Often the error is so small you do not even notice it, and if you do, +you can always specify how much precision you would like in your output. +Usually this is a format string like @code{"%.15g"}, which when +used in the previous example, produces an output identical to the input. + +Because the underlying representation can be little bit off from the exact value, +comparing floats to see if they are equal is generally not a good idea. +Here is an example where it does not work like you expect: + +@example +$ @kbd{gawk 'BEGIN @{ print (0.1 + 12.2 == 12.3) @}'} +@print{} 0 +@end example + +The loss of accuracy during a single computation with floating-point numbers +usually isn't enough to worry about. However, if you compute a value +which is the result of a sequence of floating point operations, +the error can accumulate and greatly affect the computation itself. +Here is an attempt to compute the value of the constant +@value{PI} using one of its many series representations: + +@example +BEGIN @{ + x = 1.0 / sqrt(3.0) + n = 6 + for (i = 1; i < 30; i++) @{ + n = n * 2.0 + x = (sqrt(x * x + 1) - 1) / x + printf("%.15f\n", n * x) + @} +@} +@end example + +When run, the early errors propagating through later computations +cause the loop to terminate prematurely after an attempt to divide by zero. + +@example +$ @kbd{gawk -f pi.awk} +@print{} 3.215390309173475 +@print{} 3.159659942097510 +@print{} 3.146086215131467 +@print{} 3.142714599645573 +@dots{} +@print{} 3.224515243534819 +@print{} 2.791117213058638 +@print{} 0.000000000000000 +@error{} gawk: pi.awk:6: fatal: division by zero attempted +@end example + +Here is one more example where the inaccuracies in internal representations +yield an unexpected result: + +@example +$ @kbd{gawk 'BEGIN @{} +> @kbd{for (d = 1.1; d <= 1.5; d += 0.1)} +> @kbd{i++} +> @kbd{print i} +> @kbd{@}'} +@print{} 4 +@end example + +Can computation using aribitrary precision help with the previous examples? +If you are impatient to know, see +@ref{Exact Arithmetic}. + +Instead of aribitrary precision floating-point arithmetic, +often all you need is an adjustment of your logic +or a different order for the operations in your calculation. +The stability and the accuracy of the computation of the constant @value{PI} +in the previous example can be enhanced by using the following +simple algebraic transformation: + +@example +(sqrt(x * x + 1) - 1) / x = x / (sqrt(x * x + 1) + x) +@end example + +There is no need to be unduly suspicious about the results from +floating-point arithmetic. The lesson to remember is that +floating-point math is always more complex than the math using +pencil and paper. In order to take advantage of the power +of computer floating-point, you need to know its limitations +and work within them. For most casual use of floating-point arithmetic, +you will often get the expected result in the end if you simply round +the display of your final results to the correct number of significant +decimal digits. Avoid presenting numerical data in a manner that +implies better precision than is actually the case. + +@node Floating-point Representation +@section Binary Floating-point Representation +@cindex IEEE-754 format + +Although floating-point representations vary from machine to machine, +the most commonly encountered representation is that defined by the +IEEE 754 Standard. An IEEE-754 format value has three components: + +@itemize @bullet +@item +a sign bit telling whether the number is positive or negative, + +@item +an @dfn{exponent} giving its order of magnitude, @var{e}, + +@item +and a @dfn{significand}, @var{s}, +specifying the actual digits of the number. +@end itemize + +The value of the +number is then +@iftex +@math{s @cdot 2^e}. +@end iftex +@ifnottex +@var{s * 2^e}. +@end ifnottex +The first bit of a non-zero binary significand +is always one, so the significand in an IEEE-754 format only includes the +fractional part, leaving the leading one implicit. + +Three of the standard IEEE-754 types are 32-bit single precision, +64-bit double precision and 128-bit quadruple precision. +The standard also specifies extended precision formats +to allow greater precisions and larger exponent ranges. + +@node Floating-point Context +@section Floating-point Context +@cindex context, floating-point + +A floating-point context defines the environment for arithmetic operations. +It governs precision, sets rules for rounding and limits range for exponents. +The context has the following primary components: + +@table @code +@item precision +Precision of the floating-point format in bits. +@item emax +Maximum exponent allowed for this format. +@item emin +Minimum exponent allowed for this format. +@item underflow behavior +The format may or may not support gradual underflow. +@item rounding +The rounding mode of this context. +@end table + +@ref{table-ieee-formats} lists the precision and exponent +field values for the basic IEEE-754 binary formats: + +@float Table,table-ieee-formats +@caption{Basic IEEE Formats} +@multitable @columnfractions .20 .20 .20 .20 .20 +@headitem Name @tab Total bits @tab Precision @tab emin @tab emax +@item Single @tab 32 @tab 24 @tab @minus{}126 @tab +127 +@item Double @tab 64 @tab 53 @tab @minus{}1022 @tab +1023 +@item Quadruple @tab 128 @tab 113 @tab @minus{}16382 @tab +16383 +@end multitable +@end float + +@quotation NOTE +The precision numbers include the implied leading one that gives them +one extra bit of significand. +@end quotation + +A floating-point context can also determine which signals are treated +as exceptions, and can set rules for arithmetic with special values. +Please consult the IEEE-754 standard or other resources for details. + +@command{gawk} ordinarily uses the hardware double precision +representation for numbers. On most systems, this is IEEE-754 +floating-point format, corresponding to 64-bit binary with 53 bits +of precision. + +@quotation NOTE +In case an underflow occurs, the standard allows, but does not require, +the result from an arithmetic operation to be a number smaller than +the smallest nonzero normalized number. Such numbers do +not have as many significant digits as normal numbers, and are called +@dfn{denormals} or @dfn{subnormals}. The alternative, simply returning a zero, +is called @dfn{flush to zero}. The basic IEEE-754 binary formats +support subnormal numbers. +@end quotation + +@node Rounding Mode +@section Floating-point Rounding Mode +@cindex rounding mode, floating-point + +The @dfn{rounding mode} specifies the behavior for the results of numerical +operations when discarding extra precision. Each rounding mode indicates +how the least significant returned digit of a rounded result is to +be calculated. +The @code{ROUNDMODE} variable (@pxref{Setting Rounding Mode}) provides +program level control over the rounding mode. +@ref{table-rounding-modes} lists the IEEE-754 defined +rounding modes: + +@float Table,table-rounding-modes +@caption{Rounding Modes} +@multitable @columnfractions .45 .30 .25 +@headitem Rounding Mode @tab IEEE Name @tab @code{ROUNDMODE} +@item Round to nearest, ties to even @tab @code{roundTiesToEven} @tab @code{"N"} or @code{"n"} +@item Round toward plus Infinity @tab @code{roundTowardPositive} @tab @code{"U"} or @code{"u"} +@item Round toward negative Infinity @tab @code{roundTowardNegative} @tab @code{"D"} or @code{"d"} +@item Round toward zero @tab @code{roundTowardZero} @tab @code{"Z"} or @code{"z"} +@item Round to nearest, ties away from zero @tab @code{roundTiesToAway} @tab @code{"A"} or @code{"a"} +@end multitable +@end float + +The default mode @samp{roundTiesToEven} is the most preferred, +but the least intuitive. This method does the obvious thing for most values, +by rounding them up or down to the nearest digit. +For example, rounding 1.132 to two digits yields 1.13, +and rounding 1.157 yields 1.16. + +However, when it comes to rounding a value that is exactly halfway between, +things do not work the way you probably learned in school. +In this case, the number is rounded to the nearest even digit. +So rounding 0.125 to two digits rounds down to 0.12, +but rounding 0.6875 to three digits rounds up to 0.688. +You probably have already encountered this rounding mode when +using the @code{printf} routine to format floating-point numbers. +For example: + +@example +BEGIN @{ + x = -4.5 + for (i = 1; i < 10; i++) @{ + x += 1.0 + printf("%4.1f => %2.0f\n", x, x) + @} +@} +@end example + +@noindent +produces the following output when run@footnote{It +is possible for the output to be completely different if the +C library in your system does not use the IEEE-754 even-rounding +rule to round halfway cases for @code{printf()}.}: + +@example +-3.5 => -4 +-2.5 => -2 +-1.5 => -2 +-0.5 => 0 + 0.5 => 0 + 1.5 => 2 + 2.5 => 2 + 3.5 => 4 + 4.5 => 4 +@end example + +The theory behind the rounding mode @samp{roundTiesToEven} is that +it more or less evenly distributes upward and downward rounds +of exact halves, which might cause the round-off error +to cancel itself out. This is the default rounding mode used +in IEEE-754 computing functions and operators. + +The other rounding modes are rarely used. +Round toward positive infinity (@samp{roundTowardPositive}) +and round toward negative infinity (@samp{roundTowardNegative}) +are often used to implement interval arithmetic, +where you adjust the rounding mode to calculate upper and lower bounds +for the range of output. The @samp{roundTowardZero} +mode can be used for converting floating-point numbers to integers. +The rounding mode @samp{roundTiesToAway} rounds the result to the +nearest number and selects the number with the larger magnitude +if a tie occurs. + +Some numerical analysts will tell you that your choice of rounding style +has tremendous impact on the final outcome, and advise you to wait until +final output for any rounding. Instead, you can often achieve this goal by +setting the precision initially to some value sufficiently larger than +the final desired precision, so that the accumulation of round-off error +does not influence the outcome. +If you suspect that results from your computation are +sensitive to accumulation of round-off error, +one way to be sure is to look for a significant difference in output +when you change the rounding mode. + +@node Arbitrary Precision Floats +@section Arbitrary Precision Floating-point Arithmetic with @command{gawk} + +@command{gawk} uses the GNU MPFR library +for arbitrary precision floating-point arithmetic. The MPFR library +provides precise control over precisions and rounding modes, and gives +correctly rounded reproducible platform-independent results. With the +command-line option @option{--bignum} or @option{-M}, +all floating-point arithmetic operators and numeric functions can yield +results to any desired precision level supported by MPFR. +Two built-in +variables @code{PREC} +(@pxref{Setting Precision}) +and @code{ROUNDMODE} +(@pxref{Setting Rounding Mode}) +provide control over the working precision and the rounding mode. +The precision and the rounding mode are set globally for every operation +to follow. + +The default working precision for arbitrary precision floats is 53, +and the default value for @code{ROUNDMODE} is @code{"N"}, +which selects the IEEE-754 +@samp{roundTiesToEven} (@pxref{Rounding Mode}) rounding mode.@footnote{The +default precision is 53, since according to the MPFR documentation, +the library should be able to exactly reproduce all computations with +double-precision machine floating-point numbers (@code{double} type +in C), except the default exponent range is much wider and subnormal +numbers are not implemented.} +@command{gawk} uses the default exponent range in MPFR +@iftex +(@math{emax = 2^{30} - 1, emin = -emax}) +@end iftex +@ifnottex +(@var{emax} = 2^30 @minus{} 1, @var{emin} = @minus{}@var{emax}) +@end ifnottex +for all floating-point contexts. +There is no explicit mechanism to adjust the exponent range. +MPFR does not implement subnormal numbers by default, +and this behavior cannot be changed in @command{gawk}. + +@quotation NOTE +When emulating an IEEE-754 format (@pxref{Setting Precision}), +@command{gawk} internally adjusts the exponent range +to the value defined for the format and also performs computations needed for +gradual underflow (subnormal numbers). +@end quotation + +@quotation NOTE +MPFR numbers are variable-size entities, consuming only as much space as +needed to store the significant digits. Since the performance using MPFR +numbers pales in comparison to doing math using the underlying machine +types, you should consider using only as much precision as needed by +your program. +@end quotation + +@node Setting Precision +@section Setting the Working Precision +@cindex @code{PREC} variable + +@command{gawk} uses a global working precision; it does not keep track of +the precision or accuracy of individual numbers. Performing an arithmetic +operation or calling a built-in function rounds the result to the current +working precision. The default working precision is 53 which can be +modified using the built-in variable @code{PREC}. You can also set the +value to one of the following pre-defined case-insensitive strings +to emulate an IEEE-754 binary format: + +@multitable {@code{"double"}} {12345678901234567890123456789012345} +@headitem @code{PREC} @tab IEEE-754 Binary Format +@item @code{"half"} @tab 16-bit half-precision. +@item @code{"single"} @tab Basic 32-bit single precision. +@item @code{"double"} @tab Basic 64-bit double precision. +@item @code{"quad"} @tab Basic 128-bit quadruple precision. +@item @code{"oct"} @tab 256-bit octuple precision. +@end multitable + +The following example illustrates the effects of changing precision +on arithmetic operations: + +@example +$ @kbd{gawk -M -vPREC=100 'BEGIN @{ x = 1.0e-400; print x + 0; \} +> @kbd{PREC = "double"; print x + 0 @}'} +@print{} 1e-400 +@print{} 0 +@end example + +Binary and decimal precisions are related approximately according to the +formula: + +@iftex +@math{prec = 3.322 @cdot dps} +@end iftex +@ifnottex +@var{prec} = 3.322 * @var{dps} +@end ifnottex + +@noindent +Here, @var{prec} denotes the binary precision +(measured in bits) and @var{dps} (short for decimal places) +is the decimal digits. We can easily calculate how many decimal +digits the 53-bit significand of an IEEE double is equivalent to: +53 / 3.332 which is equal to about 15.95. +But what does 15.95 digits actually mean? It depends whether you are +concerned about how many digits you can rely on, or how many digits +you need. + +It is important to know how many bits it takes to uniquely identify +a double-precision value (the C type @code{double}). If you want to +convert from @code{double} to decimal and back to @code{double} (e.g., +saving a @code{double} representing an intermediate result to a file, and +later reading it back to restart the computation), then a few more decimal +digits are required. 17 digits is generally enough for a @code{double}. + +It can also be important to know what decimal numbers can be uniquely +represented with a @code{double}. If you want to convert +from decimal to @code{double} and back again, 15 digits is the most that +you can get. Stated differently, you should not present +the numbers from your floating-point computations with more than 15 +significant digits in them. + +Conversely, it takes a precision of 332 bits to hold an approximation +of constant @value{PI} that is accurate to 100 decimal places. +You should always add some extra bits in order to avoid the confusing round-off +issues that occur because numbers are stored internally in binary. + +@node Setting Rounding Mode +@section Setting the Rounding Mode +@cindex @code{ROUNDMODE} variable + +The built-in variable @code{ROUNDMODE} has the default value @code{"N"}, +which selects the IEEE-754 rounding mode @samp{roundTiesToEven}. +The other possible values for @code{ROUNDMODE} are @code{"U"} for rounding mode +@samp{roundTowardPositive}, @code{"D"} for @samp{roundTowardNegative}, +and @code{"Z"} for @samp{roundTowardZero}. +@command{gawk} also accepts @code{"A"} to select the IEEE-754 mode +@samp{roundTiesToAway} +if your version of the MPFR library supports it; otherwise setting +@code{ROUNDMODE} to this value has no effect. @xref{Rounding Mode}, +for the meanings of the various rounding modes. + +Here is an example of how to change the default rounding behavior of +@code{printf}'s output: + +@example +$ @kbd{gawk -M -vROUNDMODE="Z" 'BEGIN @{ printf("%.2f\n", 1.378) @}'} +@print{} 1.37 +@end example + +@node Floating-point Constants +@section Representing Floating-point Constants +@cindex constants, floating-point + +Be wary of floating-point constants! When reading a floating-point constant +from program source code, @command{gawk} uses the default precision, +unless overridden +by an assignment to the special variable @code{PREC} on the command +line, to store it internally as a MPFR number. +Changing the precision using @code{PREC} in the program text does +not change the precision of a constant. If you need to +represent a floating-point constant at a higher precision than the +default and cannot use a command line assignment to @code{PREC}, +you should either specify the constant as a string, or +a rational number whenever possible. The following example +illustrates the differences among various ways to +print a floating-point constant: + +@example +$ @kbd{gawk -M 'BEGIN @{ PREC = 113; printf("%0.25f\n", 0.1) @}'} +@print{} 0.1000000000000000055511151 +$ @kbd{gawk -M -vPREC = 113 'BEGIN @{ printf("%0.25f\n", 0.1) @}'} +@print{} 0.1000000000000000000000000 +$ @kbd{gawk -M 'BEGIN @{ PREC = 113; printf("%0.25f\n", "0.1") @}'} +@print{} 0.1000000000000000000000000 +$ @kbd{gawk -M 'BEGIN @{ PREC = 113; printf("%0.25f\n", 1/10) @}'} +@print{} 0.1000000000000000000000000 +@end example + +In the first case, the number is stored with the default precision of 53. + +@node Changing Precision +@section Changing the Precision of a Number + +@cindex Laurie, Dirk +@quotation +@i{The point is that in any variable-precision package, +a decision is made on how to treat numbers given as data, +or arising in intermediate results, which are represented in +floating-point format to a precision lower than working precision. +Do we promote them to full membership of the high-precision club, +or do we treat them and all their associates as second-class citizens? +Sometimes the first course is proper, sometimes the second, and it takes +careful analysis to tell which.} + +Dirk Laurie@footnote{Dirk Laurie. +@cite{Variable-precision Arithmetic Considered Perilous -- A Detective Story}. +Electronic Transactions on Numerical Analysis. Volume 28, pp. 168-173, 2008.} +@end quotation + +@command{gawk} does not implicitly modify the precision of any previously +computed results when the working precision is changed with an assignment +to @code{PREC}. The precision of a number is always the one that was +used at the time of its creation, and there is no way for the user +to explicitly change it afterwards. However, since the result of a +floating-point arithmetic operation is always an arbitrary precision +floating-point value---with a precision set by the value of @code{PREC}---one of the +following workarounds effectively accomplishes the desired behavior: + +@example +x = x + 0.0 +@end example + +@noindent +or: + +@example +x += 0.0 +@end example + +@node Exact Arithmetic +@section Exact Arithmetic with Floating-point Numbers + +@quotation CAUTION +Never depend on the exactness of floating-point arithmetic, +even for apparently simple expressions! +@end quotation + +Can arbitrary precision arithmetic give exact results? There are +no easy answers. The standard rules of algebra often do not apply +when using floating-point arithmetic. +Among other things, the distributive and associative laws +do not hold completely, and order of operation may be important +for your computation. Rounding error, cumulative precision loss +and underflow are often troublesome. + +When @command{gawk} tests the expressions @samp{0.1 + 12.2} and @samp{12.3} +for equality +using the machine double precision arithmetic, it decides that they +are not equal! +(@xref{Floating-point Programming}.) +You can get the result you want by increasing the precision; +56 in this case will get the job done: + +@example +$ @kbd{gawk -M -vPREC=56 'BEGIN @{ print (0.1 + 12.2 == 12.3) @}'} +@print{} 1 +@end example + +If adding more bits is good, perhaps adding even more bits of +precision is better? +Here is what happens if we use an even larger value of @code{PREC}: + +@example +$ @kbd{gawk -M -vPREC=201 'BEGIN @{ print (0.1 + 12.2 == 12.3) @}'} +@print{} 0 +@end example + +This is not a bug in @command{gawk} or in the MPFR library. +It is easy to forget that the finite number of bits used to store the value +is often just an approximation after proper rounding. +The test for equality succeeds if and only if @emph{all} bits in the two operands +are exactly the same. Since this is not necessarily true after floating-point +computations with a particular precision and effective rounding rule, +a straight test for equality may not work. + +So, don't assume that floating-point values can be compared for equality. +You should also exercise caution when using other forms of comparisons. +The standard way to compare between floating-point numbers is to determine +how much error (or @dfn{tolerance}) you will allow in a comparison and +check to see if one value is within this error range of the other. + +In applications where 15 or fewer decimal places suffice, +hardware double precision arithmetic can be adequate, and is usually much faster. +But you do need to keep in mind that every floating-point operation +can suffer a new rounding error with catastrophic consequences as illustrated +by our attempt to compute the value of the constant @value{PI}, +(@pxref{Floating-point Programming}). +Extra precision can greatly enhance the stability and the accuracy +of your computation in such cases. + +Repeated addition is not necessarily equivalent to multiplication +in floating-point arithmetic. In the last example +(@pxref{Floating-point Programming}), +you may or may not succeed in getting the correct result by choosing +an arbitrarily large value for @code{PREC}. Reformulation of +the problem at hand is often the correct approach in such situations. + + +@node Integer Programming +@section Effective Integer Programming + +As has been mentioned already, @command{gawk} ordinarily uses hardware double +precision with 64-bit IEEE binary floating-point representation +for numbers on most systems. A large integer like 9007199254740997 +has a binary representation that, although finite, is more than 53 bits long; +it must also be rounded to 53 bits. +The biggest integer that can be stored in a C @code{double} is usually the same +as the largest possible value of a @code{double}. If your system @code{double} +is an IEEE 64-bit @code{double}, this largest possible value is an integer and +can be represented precisely. What more should one know about integers? + +If you want to know what is the largest integer, such that it and +all smaller integers can be stored in 64-bit doubles without losing precision, +then the answer is +@iftex +@math{2^{53}}. +@end iftex +@ifnottex +2^53. +@end ifnottex +The next representable number is the even number +@iftex +@math{2^{53} + 2}, +@end iftex +@ifnottex +2^53 + 2, +@end ifnottex +meaning it is unlikely that you will be able to make +@command{gawk} print +@iftex +@math{2^{53} + 1} +@end iftex +@ifnottex +2^53 + 1 +@end ifnottex +in integer format. +The range of integers exactly representable by a 64-bit double +is +@iftex +@math{[-2^{53}, 2^{53}]}. +@end iftex +@ifnottex +[@minus{}2^53, 2^53]. +@end ifnottex +If you ever see an integer outside this range in @command{gawk} +using 64-bit doubles, you have reason to be very suspicious about +the accuracy of the output. Here is a simple program with erroneous output: + +@example +$ @kbd{gawk 'BEGIN @{ i = 2^53 - 1; for (j = 0; j < 4; j++) print i + j @}'} +@print{} 9007199254740991 +@print{} 9007199254740992 +@print{} 9007199254740992 +@print{} 9007199254740994 +@end example + +The lesson is to not assume that any large integer printed by @command{gawk} +represents an exact result from your computation, especially if it wraps +around on your screen. + +@node Arbitrary Precision Integers +@section Arbitrary Precision Integer Arithmetic with @command{gawk} +@cindex integer, arbitrary precision + +If the option @option{--bignum} or @option{-M} is specified, +@command{gawk} performs all +integer arithmetic using GMP arbitrary precision integers. +Any number that looks like an integer in a program source or data file +is stored as an arbitrary precision integer. +The size of the integer is limited only by your computer's memory. +The current floating-point context has no effect on operations involving integers. +For example, the following computes +@iftex +@math{5^{4^{3^{2}}}}, +@end iftex +@ifnottex +5^4^3^2, +@end ifnottex +the result of which is beyond the +limits of ordinary @command{gawk} numbers: + +@example +$ @kbd{gawk -M 'BEGIN @{} +> @kbd{x = 5^4^3^2} +> @kbd{print "# of digits =", length(x)} +> @kbd{print substr(x, 1, 20), "...", substr(x, length(x) - 19, 20)} +> @kbd{@}'} +@print{} # of digits = 183231 +@print{} 62060698786608744707 ... 92256259918212890625 +@end example + +If you were to compute the same value using arbitrary precision +floating-point values instead, the precision needed for correct output +(using the formula +@iftex +@math{prec = 3.322 @cdot dps}), +would be @math{3.322 @cdot 183231}, +@end iftex +@ifnottex +@samp{prec = 3.322 * dps}), +would be 3.322 x 183231, +@end ifnottex +or 608693. + +The result from an arithmetic operation with an integer and a floating-point value +is a floating-point value with a precision equal to the working precision. +The following program calculates the eighth term in +Sylvester's sequence@footnote{Weisstein, Eric W. +@cite{Sylvester's Sequence}. From MathWorld--A Wolfram Web Resource. +@url{http://mathworld.wolfram.com/SylvestersSequence.html}} +using a recurrence: + +@example +$ @kbd{gawk -M 'BEGIN @{} +> @kbd{s = 2.0} +> @kbd{for (i = 1; i <= 7; i++)} +> @kbd{s = s * (s - 1) + 1} +> @kbd{print s} +> @kbd{@}'} +@print{} 113423713055421845118910464 +@end example + +The output differs from the acutal number, 113423713055421844361000443, +because the default precision of 53 is not enough to represent the +floating-point results exactly. You can either increase the precision +(100 is enough in this case), or replace the floating-point constant +@code{2.0} with an integer, to perform all computations using integer +arithmetic to get the correct output. + +It will sometimes be necessary for @command{gawk} to implicitly convert an +arbitrary precision integer into an arbitrary precision floating-point value. +This is primarily because the MPFR library does not always provide the +relevant interface to process arbitrary precision integers or mixed-mode +numbers as needed by an operation or function. +In such a case, the precision is set to the minimum value necessary +for exact conversion, and the working precision is not used for this purpose. +If this is not what you need or want, you can employ a subterfuge +like this: + +@example +gawk -M 'BEGIN @{ n = 13; print (n + 0.0) % 2.0 @}' +@end example + +You can avoid this issue altogether by specifying the number as a float +to begin with: + +@example +gawk -M 'BEGIN @{ n = 13.0; print n % 2.0 @}' +@end example + +Note that for the particular example above, there is unlikely to be a +reason for simply not using the following: + +@example +gawk -M 'BEGIN @{ n = 13; print n % 2 @}' +@end example + + +@node MPFR and GMP Libraries +@section Information About the MPFR and GMP Libraries + +There are a few elements available in the @code{PROCINFO} array +to provide information about the MPFR and GMP libraries. +@xref{Auto-set}, for more information. + @node Advanced Features @chapter Advanced Features of @command{gawk} @cindex advanced features, network connections, See Also networks, connections diff --git a/doc/texinfo.tex b/doc/texinfo.tex index 1130b8fc..e4dca02c 100644 --- a/doc/texinfo.tex +++ b/doc/texinfo.tex @@ -3,11 +3,11 @@ % Load plain if necessary, i.e., if running under initex. \expandafter\ifx\csname fmtname\endcsname\relax\input plain\fi % -\def\texinfoversion{2010-12-23.17} +\def\texinfoversion{2012-04-06.11} % % Copyright 1985, 1986, 1988, 1990, 1991, 1992, 1993, 1994, 1995, % 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, -% 2007, 2008, 2009, 2010 Free Software Foundation, Inc. +% 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation, Inc. % % This texinfo.tex file is free software: you can redistribute it and/or % modify it under the terms of the GNU General Public License as @@ -116,10 +116,11 @@ % Set up fixed words for English if not already set. \ifx\putwordAppendix\undefined \gdef\putwordAppendix{Appendix}\fi \ifx\putwordChapter\undefined \gdef\putwordChapter{Chapter}\fi +\ifx\putworderror\undefined \gdef\putworderror{error}\fi \ifx\putwordfile\undefined \gdef\putwordfile{file}\fi \ifx\putwordin\undefined \gdef\putwordin{in}\fi -\ifx\putwordIndexIsEmpty\undefined \gdef\putwordIndexIsEmpty{(Index is empty)}\fi -\ifx\putwordIndexNonexistent\undefined \gdef\putwordIndexNonexistent{(Index is nonexistent)}\fi +\ifx\putwordIndexIsEmpty\undefined \gdef\putwordIndexIsEmpty{(Index is empty)}\fi +\ifx\putwordIndexNonexistent\undefined \gdef\putwordIndexNonexistent{(Index is nonexistent)}\fi \ifx\putwordInfo\undefined \gdef\putwordInfo{Info}\fi \ifx\putwordInstanceVariableof\undefined \gdef\putwordInstanceVariableof{Instance Variable of}\fi \ifx\putwordMethodon\undefined \gdef\putwordMethodon{Method on}\fi @@ -158,15 +159,18 @@ \def\spaceisspace{\catcode`\ =\spacecat} % sometimes characters are active, so we need control sequences. +\chardef\ampChar = `\& \chardef\colonChar = `\: \chardef\commaChar = `\, \chardef\dashChar = `\- \chardef\dotChar = `\. \chardef\exclamChar= `\! +\chardef\hashChar = `\# \chardef\lquoteChar= `\` \chardef\questChar = `\? \chardef\rquoteChar= `\' \chardef\semiChar = `\; +\chardef\slashChar = `\/ \chardef\underChar = `\_ % Ignore a token. @@ -215,7 +219,7 @@ \tracingmacros2 \tracingrestores1 \showboxbreadth\maxdimen \showboxdepth\maxdimen - \ifx\eTeXversion\undefined\else % etex gives us more logging + \ifx\eTeXversion\thisisundefined\else % etex gives us more logging \tracingscantokens1 \tracingifs1 \tracinggroups1 @@ -226,6 +230,13 @@ \errorcontextlines16 }% +% @errormsg{MSG}. Do the index-like expansions on MSG, but if things +% aren't perfect, it's not the end of the world, being an error message, +% after all. +% +\def\errormsg{\begingroup \indexnofonts \doerrormsg} +\def\doerrormsg#1{\errmessage{#1}} + % add check for \lastpenalty to plain's definitions. If the last thing % we did was a \nobreak, we don't want to insert more space. % @@ -545,7 +556,7 @@ } \def\inenvironment#1{% \ifx#1\empty - out of any environment% + outside of any environment% \else in environment \expandafter\string#1% \fi @@ -557,7 +568,7 @@ \parseargdef\end{% \if 1\csname iscond.#1\endcsname \else - % The general wording of \badenverr may not be ideal, but... --kasal, 06nov03 + % The general wording of \badenverr may not be ideal. \expandafter\checkenv\csname#1\endcsname \csname E#1\endcsname \endgroup @@ -608,7 +619,7 @@ \else\ifx\temp\offword \plainnonfrenchspacing \else \errhelp = \EMsimple - \errmessage{Unknown @frenchspacing option `\temp', must be on/off}% + \errmessage{Unknown @frenchspacing option `\temp', must be on|off}% \fi\fi } @@ -690,15 +701,6 @@ where each line of input produces a line of output.} \newdimen\mil \mil=0.001in -% Old definition--didn't work. -%\parseargdef\need{\par % -%% This method tries to make TeX break the page naturally -%% if the depth of the box does not fit. -%{\baselineskip=0pt% -%\vtop to #1\mil{\vfil}\kern -#1\mil\nobreak -%\prevdepth=-1000pt -%}} - \parseargdef\need{% % Ensure vertical mode, so we don't make a big box in the middle of a % paragraph. @@ -849,6 +851,7 @@ where each line of input produces a line of output.} \makevalueexpandable % we want to expand any @value in FILE. \turnoffactive % and allow special characters in the expansion \indexnofonts % Allow `@@' and other weird things in file names. + \wlog{texinfo.tex: doing @include of #1^^J}% \edef\temp{\noexpand\input #1 }% % % This trickery is to read FILE outside of a group, in case it makes @@ -884,7 +887,7 @@ where each line of input produces a line of output.} \def\popthisfilestack{\errthisfilestackempty} \def\errthisfilestackempty{\errmessage{Internal error: the stack of filenames is empty.}} - +% \def\thisfile{} % @center line @@ -892,36 +895,46 @@ where each line of input produces a line of output.} % \parseargdef\center{% \ifhmode - \let\next\centerH + \let\centersub\centerH \else - \let\next\centerV + \let\centersub\centerV \fi - \next{\hfil \ignorespaces#1\unskip \hfil}% + \centersub{\hfil \ignorespaces#1\unskip \hfil}% + \let\centersub\relax % don't let the definition persist, just in case } -\def\centerH#1{% - {% - \hfil\break - \advance\hsize by -\leftskip - \advance\hsize by -\rightskip - \line{#1}% - \break - }% +\def\centerH#1{{% + \hfil\break + \advance\hsize by -\leftskip + \advance\hsize by -\rightskip + \line{#1}% + \break +}} +% +\newcount\centerpenalty +\def\centerV#1{% + % The idea here is the same as in \startdefun, \cartouche, etc.: if + % @center is the first thing after a section heading, we need to wipe + % out the negative parskip inserted by \sectionheading, but still + % prevent a page break here. + \centerpenalty = \lastpenalty + \ifnum\centerpenalty>10000 \vskip\parskip \fi + \ifnum\centerpenalty>9999 \penalty\centerpenalty \fi + \line{\kern\leftskip #1\kern\rightskip}% } -\def\centerV#1{\line{\kern\leftskip #1\kern\rightskip}} % @sp n outputs n lines of vertical space - +% \parseargdef\sp{\vskip #1\baselineskip} % @comment ...line which is ignored... % @c is the same as @comment % @ignore ... @end ignore is another way to write a comment - +% \def\comment{\begingroup \catcode`\^^M=\other% \catcode`\@=\other \catcode`\{=\other \catcode`\}=\other% \commentxxx} {\catcode`\^^M=\other \gdef\commentxxx#1^^M{\endgroup}} - +% \let\c=\comment % @paragraphindent NCHARS @@ -1078,9 +1091,8 @@ where each line of input produces a line of output.} \newif\ifpdfmakepagedest % when pdftex is run in dvi mode, \pdfoutput is defined (so \pdfoutput=1 -% can be set). So we test for \relax and 0 as well as \undefined, -% borrowed from ifpdf.sty. -\ifx\pdfoutput\undefined +% can be set). So we test for \relax and 0 as well as being undefined. +\ifx\pdfoutput\thisisundefined \else \ifx\pdfoutput\relax \else @@ -1095,50 +1107,24 @@ where each line of input produces a line of output.} % for display in the outlines, and in other places. Thus, we have to % double any backslashes. Otherwise, a name like "\node" will be % interpreted as a newline (\n), followed by o, d, e. Not good. -% http://www.ntg.nl/pipermail/ntg-pdftex/2004-July/000654.html -% (and related messages, the final outcome is that it is up to the TeX -% user to double the backslashes and otherwise make the string valid, so -% that's what we do). - -% double active backslashes. -% -{\catcode`\@=0 \catcode`\\=\active - @gdef@activebackslashdouble{% - @catcode`@\=@active - @let\=@doublebackslash} -} - -% To handle parens, we must adopt a different approach, since parens are -% not active characters. hyperref.dtx (which has the same problem as -% us) handles it with this amazing macro to replace tokens, with minor -% changes for Texinfo. It is included here under the GPL by permission -% from the author, Heiko Oberdiek. -% -% #1 is the tokens to replace. -% #2 is the replacement. -% #3 is the control sequence with the string. -% -\def\HyPsdSubst#1#2#3{% - \def\HyPsdReplace##1#1##2\END{% - ##1% - \ifx\\##2\\% - \else - #2% - \HyReturnAfterFi{% - \HyPsdReplace##2\END - }% - \fi - }% - \xdef#3{\expandafter\HyPsdReplace#3#1\END}% -} -\long\def\HyReturnAfterFi#1\fi{\fi#1} - -% #1 is a control sequence in which to do the replacements. -\def\backslashparens#1{% - \xdef#1{#1}% redefine it as its expansion; the definition is simply - % \lastnode when called from \setref -> \pdfmkdest. - \HyPsdSubst{(}{\realbackslash(}{#1}% - \HyPsdSubst{)}{\realbackslash)}{#1}% +% +% See http://www.ntg.nl/pipermail/ntg-pdftex/2004-July/000654.html and +% related messages. The final outcome is that it is up to the TeX user +% to double the backslashes and otherwise make the string valid, so +% that's what we do. pdftex 1.30.0 (ca.2005) introduced a primitive to +% do this reliably, so we use it. + +% #1 is a control sequence in which to do the replacements, +% which we \xdef. +\def\txiescapepdf#1{% + \ifx\pdfescapestring\relax + % No primitive available; should we give a warning or log? + % Many times it won't matter. + \else + % The expandable \pdfescapestring primitive escapes parentheses, + % backslashes, and other special chars. + \xdef#1{\pdfescapestring{#1}}% + \fi } \newhelp\nopdfimagehelp{Texinfo supports .png, .jpg, .jpeg, and .pdf images @@ -1197,32 +1183,34 @@ output) for that.)} % % #1 is image name, #2 width (might be empty/whitespace), #3 height (ditto). \def\dopdfimage#1#2#3{% - \def\imagewidth{#2}\setbox0 = \hbox{\ignorespaces #2}% - \def\imageheight{#3}\setbox2 = \hbox{\ignorespaces #3}% + \def\pdfimagewidth{#2}\setbox0 = \hbox{\ignorespaces #2}% + \def\pdfimageheight{#3}\setbox2 = \hbox{\ignorespaces #3}% % - % pdftex (and the PDF format) support .png, .jpg, .pdf (among - % others). Let's try in that order. + % pdftex (and the PDF format) support .pdf, .png, .jpg (among + % others). Let's try in that order, PDF first since if + % someone has a scalable image, presumably better to use that than a + % bitmap. \let\pdfimgext=\empty \begingroup - \openin 1 #1.png \ifeof 1 - \openin 1 #1.jpg \ifeof 1 - \openin 1 #1.jpeg \ifeof 1 - \openin 1 #1.JPG \ifeof 1 - \openin 1 #1.pdf \ifeof 1 - \openin 1 #1.PDF \ifeof 1 + \openin 1 #1.pdf \ifeof 1 + \openin 1 #1.PDF \ifeof 1 + \openin 1 #1.png \ifeof 1 + \openin 1 #1.jpg \ifeof 1 + \openin 1 #1.jpeg \ifeof 1 + \openin 1 #1.JPG \ifeof 1 \errhelp = \nopdfimagehelp \errmessage{Could not find image file #1 for pdf}% - \else \gdef\pdfimgext{PDF}% + \else \gdef\pdfimgext{JPG}% \fi - \else \gdef\pdfimgext{pdf}% + \else \gdef\pdfimgext{jpeg}% \fi - \else \gdef\pdfimgext{JPG}% + \else \gdef\pdfimgext{jpg}% \fi - \else \gdef\pdfimgext{jpeg}% + \else \gdef\pdfimgext{png}% \fi - \else \gdef\pdfimgext{jpg}% + \else \gdef\pdfimgext{PDF}% \fi - \else \gdef\pdfimgext{png}% + \else \gdef\pdfimgext{pdf}% \fi \closein 1 \endgroup @@ -1234,8 +1222,8 @@ output) for that.)} \else \immediate\pdfximage \fi - \ifdim \wd0 >0pt width \imagewidth \fi - \ifdim \wd2 >0pt height \imageheight \fi + \ifdim \wd0 >0pt width \pdfimagewidth \fi + \ifdim \wd2 >0pt height \pdfimageheight \fi \ifnum\pdftexversion<13 #1.\pdfimgext \else @@ -1250,10 +1238,9 @@ output) for that.)} % such as \, aren't expanded when present in a section title. \indexnofonts \turnoffactive - \activebackslashdouble \makevalueexpandable \def\pdfdestname{#1}% - \backslashparens\pdfdestname + \txiescapepdf\pdfdestname \safewhatsit{\pdfdest name{\pdfdestname} xyz}% }} % @@ -1285,28 +1272,22 @@ output) for that.)} % page number. We could generate a destination for the section % text in the case where a section has no node, but it doesn't % seem worth the trouble, since most documents are normally structured. - \def\pdfoutlinedest{#3}% + \edef\pdfoutlinedest{#3}% \ifx\pdfoutlinedest\empty \def\pdfoutlinedest{#4}% \else - % Doubled backslashes in the name. - {\activebackslashdouble \xdef\pdfoutlinedest{#3}% - \backslashparens\pdfoutlinedest}% + \txiescapepdf\pdfoutlinedest \fi % - % Also double the backslashes in the display string. - {\activebackslashdouble \xdef\pdfoutlinetext{#1}% - \backslashparens\pdfoutlinetext}% + % Also escape PDF chars in the display string. + \edef\pdfoutlinetext{#1}% + \txiescapepdf\pdfoutlinetext % \pdfoutline goto name{\pdfmkpgn{\pdfoutlinedest}}#2{\pdfoutlinetext}% } % \def\pdfmakeoutlines{% \begingroup - % Thanh's hack / proper braces in bookmarks - \edef\mylbrace{\iftrue \string{\else}\fi}\let\{=\mylbrace - \edef\myrbrace{\iffalse{\else\string}\fi}\let\}=\myrbrace - % % Read toc silently, to get counts of subentries for \pdfoutline. \def\partentry##1##2##3##4{}% ignore parts in the outlines \def\numchapentry##1##2##3##4{% @@ -1362,15 +1343,26 @@ output) for that.)} % Latin 2 (0xea) gets translated to a | character. Info from % Staszek Wawrykiewicz, 19 Jan 2004 04:09:24 +0100. % - % xx to do this right, we have to translate 8-bit characters to - % their "best" equivalent, based on the @documentencoding. Right - % now, I guess we'll just let the pdf reader have its way. + % TODO this right, we have to translate 8-bit characters to + % their "best" equivalent, based on the @documentencoding. Too + % much work for too little return. Just use the ASCII equivalents + % we use for the index sort strings. + % \indexnofonts \setupdatafile + % We can have normal brace characters in the PDF outlines, unlike + % Texinfo index files. So set that up. + \def\{{\lbracecharliteral}% + \def\}{\rbracecharliteral}% \catcode`\\=\active \otherbackslash \input \tocreadfilename \endgroup } + {\catcode`[=1 \catcode`]=2 + \catcode`{=\other \catcode`}=\other + \gdef\lbracecharliteral[{]% + \gdef\rbracecharliteral[}]% + ] % \def\skipspaces#1{\def\PP{#1}\def\D{|}% \ifx\PP\D\let\nextsp\relax @@ -1380,7 +1372,13 @@ output) for that.)} \fi \fi \nextsp} - \def\getfilename#1{\filenamelength=0\expandafter\skipspaces#1|\relax} + \def\getfilename#1{% + \filenamelength=0 + % If we don't expand the argument now, \skipspaces will get + % snagged on things like "@value{foo}". + \edef\temp{#1}% + \expandafter\skipspaces\temp|\relax + } \ifnum\pdftexversion < 14 \let \startlink \pdfannotlink \else @@ -1512,7 +1510,7 @@ output) for that.)} % if we are producing pdf, and we have \pdffontattr, then define cmaps. % (\pdffontattr was introduced many years ago, but people still run % older pdftex's; it's easy to conditionalize, so we do.) -\ifpdf \ifx\pdffontattr\undefined \else +\ifpdf \ifx\pdffontattr\thisisundefined \else \begingroup \catcode`\^^M=\active \def^^M{^^J}% Output line endings as the ^^J char. \catcode`\%=12 \immediate\pdfobj stream {%!PS-Adobe-3.0 Resource-CMap @@ -1779,7 +1777,7 @@ end % Use cm as the default font prefix. % To specify the font prefix, you must define \fontprefix % before you read in texinfo.tex. -\ifx\fontprefix\undefined +\ifx\fontprefix\thisisundefined \def\fontprefix{cm} \fi % Support font families that don't use the same naming scheme as CM. @@ -2070,7 +2068,7 @@ end % \parseargdef\fonttextsize{% \def\textsizearg{#1}% - \wlog{doing @fonttextsize \textsizearg}% + %\wlog{doing @fonttextsize \textsizearg}% % % Set \globaldefs so that documents can use this inside @tex, since % makeinfo 4.8 does not support it, but we need it nonetheless. @@ -2252,12 +2250,14 @@ end % Markup style setup for left and right quotes. \defmarkupstylesetup\markupsetuplq{% - \expandafter\let\expandafter \temp \csname markupsetuplq\currentmarkupstyle\endcsname + \expandafter\let\expandafter \temp + \csname markupsetuplq\currentmarkupstyle\endcsname \ifx\temp\relax \markupsetuplqdefault \else \temp \fi } \defmarkupstylesetup\markupsetuprq{% - \expandafter\let\expandafter \temp \csname markupsetuprq\currentmarkupstyle\endcsname + \expandafter\let\expandafter \temp + \csname markupsetuprq\currentmarkupstyle\endcsname \ifx\temp\relax \markupsetuprqdefault \else \temp \fi } @@ -2291,12 +2291,11 @@ end \let\markupsetuplqkbd \markupsetnoligaturesquoteleft -% Allow an option to not replace quotes with a regular directed right -% quote/apostrophe (char 0x27), but instead use the undirected quote -% from cmtt (char 0x0d). The undirected quote is ugly, so don't make it -% the default, but it works for pasting with more pdf viewers (at least -% evince), the lilypond developers report. xpdf does work with the -% regular 0x27. +% Allow an option to not use regular directed right quote/apostrophe +% (char 0x27), but instead the undirected quote from cmtt (char 0x0d). +% The undirected quote is ugly, so don't make it the default, but it +% works for pasting with more pdf viewers (at least evince), the +% lilypond developers report. xpdf does work with the regular 0x27. % \def\codequoteright{% \expandafter\ifx\csname SETtxicodequoteundirected\endcsname\relax @@ -2320,6 +2319,36 @@ end \else \char'22 \fi } +% Commands to set the quote options. +% +\parseargdef\codequoteundirected{% + \def\temp{#1}% + \ifx\temp\onword + \expandafter\let\csname SETtxicodequoteundirected\endcsname + = t% + \else\ifx\temp\offword + \expandafter\let\csname SETtxicodequoteundirected\endcsname + = \relax + \else + \errhelp = \EMsimple + \errmessage{Unknown @codequoteundirected value `\temp', must be on|off}% + \fi\fi +} +% +\parseargdef\codequotebacktick{% + \def\temp{#1}% + \ifx\temp\onword + \expandafter\let\csname SETtxicodequotebacktick\endcsname + = t% + \else\ifx\temp\offword + \expandafter\let\csname SETtxicodequotebacktick\endcsname + = \relax + \else + \errhelp = \EMsimple + \errmessage{Unknown @codequotebacktick value `\temp', must be on|off}% + \fi\fi +} + % [Knuth] pp. 380,381,391, disable Spanish ligatures ?` and !` of \tt font. \def\noligaturesquoteleft{\relax\lq} @@ -2347,7 +2376,9 @@ end \else\ifx\next-% \else\ifx\next.% \else\ptexslash - \fi\fi\fi} + \fi\fi\fi + \aftersmartic +} % like \smartslanted except unconditionally uses \ttsl, and no ic. % @var is set to this for defun arguments. @@ -2357,9 +2388,15 @@ end % ttsl for book titles, do we? \def\cite#1{{\sl #1}\futurelet\next\smartitaliccorrection} +\def\aftersmartic{} +\def\var#1{% + \let\saveaftersmartic = \aftersmartic + \def\aftersmartic{\null\let\aftersmartic=\saveaftersmartic}% + \smartslanted{#1}% +} + \let\i=\smartitalic \let\slanted=\smartslanted -\def\var#1{\smartslanted{#1}} \let\dfn=\smartslanted \let\emph=\smartitalic @@ -2455,7 +2492,7 @@ end \plainfrenchspacing #1% }% - \null + \null % reset spacefactor to 1000 } % We *must* turn on hyphenation at `-' and `_' in @code. @@ -2487,6 +2524,8 @@ end } } +\def\codex #1{\tclose{#1}\endgroup} + \def\realdash{-} \def\codedash{-\discretionary{}{}{}} \def\codeunder{% @@ -2500,7 +2539,6 @@ end \discretionary{}{}{}}% {\_}% } -\def\codex #1{\tclose{#1}\endgroup} % An additional complication: the above will allow breaks after, e.g., % each of the four underscores in __typeof__. This is undesirable in @@ -2520,63 +2558,18 @@ end \allowcodebreaksfalse \else \errhelp = \EMsimple - \errmessage{Unknown @allowcodebreaks option `\txiarg'}% + \errmessage{Unknown @allowcodebreaks option `\txiarg', must be true|false}% \fi\fi } -% @kbd is like @code, except that if the argument is just one @key command, -% then @kbd has no effect. -\def\kbd#1{{\setupmarkupstyle{kbd}\def\look{#1}\expandafter\kbdfoo\look??\par}} - -% @kbdinputstyle -- arg is `distinct' (@kbd uses slanted tty font always), -% `example' (@kbd uses ttsl only inside of @example and friends), -% or `code' (@kbd uses normal tty font always). -\parseargdef\kbdinputstyle{% - \def\txiarg{#1}% - \ifx\txiarg\worddistinct - \gdef\kbdexamplefont{\ttsl}\gdef\kbdfont{\ttsl}% - \else\ifx\txiarg\wordexample - \gdef\kbdexamplefont{\ttsl}\gdef\kbdfont{\tt}% - \else\ifx\txiarg\wordcode - \gdef\kbdexamplefont{\tt}\gdef\kbdfont{\tt}% - \else - \errhelp = \EMsimple - \errmessage{Unknown @kbdinputstyle option `\txiarg'}% - \fi\fi\fi -} -\def\worddistinct{distinct} -\def\wordexample{example} -\def\wordcode{code} - -% Default is `distinct'. -\kbdinputstyle distinct - -\def\xkey{\key} -\def\kbdfoo#1#2#3\par{\def\one{#1}\def\three{#3}\def\threex{??}% -\ifx\one\xkey\ifx\threex\three \key{#2}% -\else{\tclose{\kbdfont\setupmarkupstyle{kbd}\look}}\fi -\else{\tclose{\kbdfont\setupmarkupstyle{kbd}\look}}\fi} - -% For @indicateurl, @env, @command quotes seem unnecessary, so use \code. -\let\indicateurl=\code -\let\env=\code -\let\command=\code - -% @clicksequence{File @click{} Open ...} -\def\clicksequence#1{\begingroup #1\endgroup} - -% @clickstyle @arrow (by default) -\parseargdef\clickstyle{\def\click{#1}} -\def\click{\arrow} - % @uref (abbreviation for `urlref') takes an optional (comma-separated) % second argument specifying the text to display and an optional third % arg as text to display instead of (rather than in addition to) the url -% itself. First (mandatory) arg is the url. Perhaps eventually put in -% a hypertex \special here. -% -\def\uref#1{\douref #1,,,\finish} -\def\douref#1,#2,#3,#4\finish{\begingroup +% itself. First (mandatory) arg is the url. +% (This \urefnobreak definition isn't used now, leaving it for a while +% for comparison.) +\def\urefnobreak#1{\dourefnobreak #1,,,\finish} +\def\dourefnobreak#1,#2,#3,#4\finish{\begingroup \unsepspaces \pdfurl{#1}% \setbox0 = \hbox{\ignorespaces #3}% @@ -2597,6 +2590,103 @@ end \endlink \endgroup} +% This \urefbreak definition is the active one. +\def\urefbreak{\begingroup \urefcatcodes \dourefbreak} +\let\uref=\urefbreak +\def\dourefbreak#1{\urefbreakfinish #1,,,\finish} +\def\urefbreakfinish#1,#2,#3,#4\finish{% doesn't work in @example + \unsepspaces + \pdfurl{#1}% + \setbox0 = \hbox{\ignorespaces #3}% + \ifdim\wd0 > 0pt + \unhbox0 % third arg given, show only that + \else + \setbox0 = \hbox{\ignorespaces #2}% + \ifdim\wd0 > 0pt + \ifpdf + \unhbox0 % PDF: 2nd arg given, show only it + \else + \unhbox0\ (\urefcode{#1})% DVI: 2nd arg given, show both it and url + \fi + \else + \urefcode{#1}% only url given, so show it + \fi + \fi + \endlink +\endgroup} + +% Allow line breaks around only a few characters (only). +\def\urefcatcodes{% + \catcode\ampChar=\active \catcode\dotChar=\active + \catcode\hashChar=\active \catcode\questChar=\active + \catcode\slashChar=\active +} +{ + \urefcatcodes + % + \global\def\urefcode{\begingroup + \setupmarkupstyle{code}% + \urefcatcodes + \let&\urefcodeamp + \let.\urefcodedot + \let#\urefcodehash + \let?\urefcodequest + \let/\urefcodeslash + \codex + } + % + % By default, they are just regular characters. + \global\def&{\normalamp} + \global\def.{\normaldot} + \global\def#{\normalhash} + \global\def?{\normalquest} + \global\def/{\normalslash} +} + +% we put a little stretch before and after the breakable chars, to help +% line breaking of long url's. The unequal skips make look better in +% cmtt at least, especially for dots. +\def\urefprestretch{\urefprebreak \hskip0pt plus.13em } +\def\urefpoststretch{\urefpostbreak \hskip0pt plus.1em } +% +\def\urefcodeamp{\urefprestretch \&\urefpoststretch} +\def\urefcodedot{\urefprestretch .\urefpoststretch} +\def\urefcodehash{\urefprestretch \#\urefpoststretch} +\def\urefcodequest{\urefprestretch ?\urefpoststretch} +\def\urefcodeslash{\futurelet\next\urefcodeslashfinish} +{ + \catcode`\/=\active + \global\def\urefcodeslashfinish{% + \urefprestretch \slashChar + % Allow line break only after the final / in a sequence of + % slashes, to avoid line break between the slashes in http://. + \ifx\next/\else \urefpoststretch \fi + } +} + +% One more complication: by default we'll break after the special +% characters, but some people like to break before the special chars, so +% allow that. Also allow no breaking at all, for manual control. +% +\parseargdef\urefbreakstyle{% + \def\txiarg{#1}% + \ifx\txiarg\wordnone + \def\urefprebreak{\nobreak}\def\urefpostbreak{\nobreak} + \else\ifx\txiarg\wordbefore + \def\urefprebreak{\allowbreak}\def\urefpostbreak{\nobreak} + \else\ifx\txiarg\wordafter + \def\urefprebreak{\nobreak}\def\urefpostbreak{\allowbreak} + \else + \errhelp = \EMsimple + \errmessage{Unknown @urefbreakstyle setting `\txiarg'}% + \fi\fi\fi +} +\def\wordafter{after} +\def\wordbefore{before} +\def\wordnone{none} + +\urefbreakstyle after + % @url synonym for @uref, since that's how everyone uses it. % \let\url=\uref @@ -2618,6 +2708,51 @@ end \let\email=\uref \fi +% @kbd is like @code, except that if the argument is just one @key command, +% then @kbd has no effect. +\def\kbd#1{{\setupmarkupstyle{kbd}\def\look{#1}\expandafter\kbdfoo\look??\par}} + +% @kbdinputstyle -- arg is `distinct' (@kbd uses slanted tty font always), +% `example' (@kbd uses ttsl only inside of @example and friends), +% or `code' (@kbd uses normal tty font always). +\parseargdef\kbdinputstyle{% + \def\txiarg{#1}% + \ifx\txiarg\worddistinct + \gdef\kbdexamplefont{\ttsl}\gdef\kbdfont{\ttsl}% + \else\ifx\txiarg\wordexample + \gdef\kbdexamplefont{\ttsl}\gdef\kbdfont{\tt}% + \else\ifx\txiarg\wordcode + \gdef\kbdexamplefont{\tt}\gdef\kbdfont{\tt}% + \else + \errhelp = \EMsimple + \errmessage{Unknown @kbdinputstyle setting `\txiarg'}% + \fi\fi\fi +} +\def\worddistinct{distinct} +\def\wordexample{example} +\def\wordcode{code} + +% Default is `distinct'. +\kbdinputstyle distinct + +\def\xkey{\key} +\def\kbdfoo#1#2#3\par{\def\one{#1}\def\three{#3}\def\threex{??}% +\ifx\one\xkey\ifx\threex\three \key{#2}% +\else{\tclose{\kbdfont\setupmarkupstyle{kbd}\look}}\fi +\else{\tclose{\kbdfont\setupmarkupstyle{kbd}\look}}\fi} + +% For @indicateurl, @env, @command quotes seem unnecessary, so use \code. +\let\indicateurl=\code +\let\env=\code +\let\command=\code + +% @clicksequence{File @click{} Open ...} +\def\clicksequence#1{\begingroup #1\endgroup} + +% @clickstyle @arrow (by default) +\parseargdef\clickstyle{\def\click{#1}} +\def\click{\arrow} + % Typeset a dimension, e.g., `in' or `pt'. The only reason for the % argument is to make the input look right: @dmn{pt} instead of @dmn{}pt. % @@ -2639,6 +2774,7 @@ end \ifx\temp\empty \else \space ({\unsepspaces \ignorespaces \temp \unskip})% \fi + \null % reset \spacefactor=1000 } % @abbr for "Comput. J." and the like. @@ -2651,6 +2787,7 @@ end \ifx\temp\empty \else \space ({\unsepspaces \ignorespaces \temp \unskip})% \fi + \null % reset \spacefactor=1000 } % @asis just yields its argument. Used with @table, for example. @@ -2715,20 +2852,48 @@ end } } +% @inlinefmt{FMTNAME,PROCESSED-TEXT} and @inlineraw{FMTNAME,RAW-TEXT}. +% Ignore unless FMTNAME == tex; then it is like @iftex and @tex, +% except specified as a normal braced arg, so no newlines to worry about. +% +\def\outfmtnametex{tex} +% +\long\def\inlinefmt#1{\doinlinefmt #1,\finish} +\long\def\doinlinefmt#1,#2,\finish{% + \def\inlinefmtname{#1}% + \ifx\inlinefmtname\outfmtnametex \ignorespaces #2\fi +} +% For raw, must switch into @tex before parsing the argument, to avoid +% setting catcodes prematurely. Doing it this way means that, for +% example, @inlineraw{html, foo{bar} gets a parse error instead of being +% ignored. But this isn't important because if people want a literal +% *right* brace they would have to use a command anyway, so they may as +% well use a command to get a left brace too. We could re-use the +% delimiter character idea from \verb, but it seems like overkill. +% +\long\def\inlineraw{\tex \doinlineraw} +\long\def\doinlineraw#1{\doinlinerawtwo #1,\finish} +\def\doinlinerawtwo#1,#2,\finish{% + \def\inlinerawname{#1}% + \ifx\inlinerawname\outfmtnametex \ignorespaces #2\fi + \endgroup % close group opened by \tex. +} + \message{glyphs,} % and logos. -% @@ prints an @. +% @@ prints an @, as does @atchar{}. \def\@{\char64 } +\let\atchar=\@ -% Used to generate quoted braces. Unless we're in typewriter, use -% \ecfont because the CM text fonts do not have braces, and we don't -% want to switch into math. +% @{ @} @lbracechar{} @rbracechar{} all generate brace characters. +% Unless we're in typewriter, use \ecfont because the CM text fonts do +% not have braces, and we don't want to switch into math. \def\mylbrace{{\ifmonospace\else\ecfont\fi \char123}} \def\myrbrace{{\ifmonospace\else\ecfont\fi \char125}} -\let\{=\mylbrace -\let\}=\myrbrace +\let\{=\mylbrace \let\lbracechar=\{ +\let\}=\myrbrace \let\rbracechar=\} \begingroup % Definitions to produce \{ and \} commands for indices, % and @{ and @} for the aux/toc files. @@ -2856,7 +3021,7 @@ end {\tentt \global\dimen0 = 3em}% Width of the box. \dimen2 = .55pt % Thickness of rules % The text. (`r' is open on the right, `e' somewhat less so on the left.) -\setbox0 = \hbox{\kern-.75pt \reducedsf error\kern-1.5pt} +\setbox0 = \hbox{\kern-.75pt \reducedsf \putworderror\kern-1.5pt} % \setbox\errorbox=\hbox to \dimen0{\hfil \hsize = \dimen0 \advance\hsize by -5.8pt % Space to left+right. @@ -3005,7 +3170,7 @@ end % Textures 1.7.7 (preloaded format=plain 93.10.14) (68K) 16 APR 2004 02:38 % so we'll define it if necessary. % -\ifx\Orb\undefined +\ifx\Orb\thisisundefined \def\Orb{\mathhexbox20D} \fi @@ -3033,8 +3198,9 @@ end \newif\ifsetshortcontentsaftertitlepage \let\setshortcontentsaftertitlepage = \setshortcontentsaftertitlepagetrue -\parseargdef\shorttitlepage{\begingroup\hbox{}\vskip 1.5in \chaprm \centerline{#1}% - \endgroup\page\hbox{}\page} +\parseargdef\shorttitlepage{% + \begingroup \hbox{}\vskip 1.5in \chaprm \centerline{#1}% + \endgroup\page\hbox{}\page} \envdef\titlepage{% % Open one extra group, as we want to close it in the middle of \Etitlepage. @@ -3094,7 +3260,7 @@ end \finishedtitlepagetrue } -%%% Macros to be used within @titlepage: +% Macros to be used within @titlepage: \let\subtitlerm=\tenrm \def\subtitlefont{\subtitlerm \normalbaselineskip = 13pt \normalbaselines} @@ -3127,7 +3293,7 @@ end } -%%% Set up page headings and footings. +% Set up page headings and footings. \let\thispage=\folio @@ -3279,7 +3445,7 @@ end % This produces Day Month Year style of output. % Only define if not already defined, in case a txi-??.tex file has set % up a different format (e.g., txi-cs.tex does this). -\ifx\today\undefined +\ifx\today\thisisundefined \def\today{% \number\day\space \ifcase\month @@ -3826,18 +3992,18 @@ end \setbox0=\vbox{X}\global\multitablelinespace=\the\baselineskip \global\advance\multitablelinespace by-\ht0 \fi -%% Test to see if parskip is larger than space between lines of -%% table. If not, do nothing. -%% If so, set to same dimension as multitablelinespace. +% Test to see if parskip is larger than space between lines of +% table. If not, do nothing. +% If so, set to same dimension as multitablelinespace. \ifdim\multitableparskip>\multitablelinespace \global\multitableparskip=\multitablelinespace -\global\advance\multitableparskip-7pt %% to keep parskip somewhat smaller - %% than skip between lines in the table. +\global\advance\multitableparskip-7pt % to keep parskip somewhat smaller + % than skip between lines in the table. \fi% \ifdim\multitableparskip=0pt \global\multitableparskip=\multitablelinespace -\global\advance\multitableparskip-7pt %% to keep parskip somewhat smaller - %% than skip between lines in the table. +\global\advance\multitableparskip-7pt % to keep parskip somewhat smaller + % than skip between lines in the table. \fi} @@ -4285,6 +4451,7 @@ end \definedummyword\guillemetright \definedummyword\guilsinglleft \definedummyword\guilsinglright + \definedummyword\lbracechar \definedummyword\leq \definedummyword\minus \definedummyword\ogonek @@ -4297,6 +4464,7 @@ end \definedummyword\quoteleft \definedummyword\quoteright \definedummyword\quotesinglbase + \definedummyword\rbracechar \definedummyword\result \definedummyword\textdegree % @@ -4348,7 +4516,9 @@ end \definedummyword\t % % Commands that take arguments. + \definedummyword\abbr \definedummyword\acronym + \definedummyword\anchor \definedummyword\cite \definedummyword\code \definedummyword\command @@ -4358,7 +4528,9 @@ end \definedummyword\emph \definedummyword\env \definedummyword\file + \definedummyword\image \definedummyword\indicateurl + \definedummyword\inforef \definedummyword\kbd \definedummyword\key \definedummyword\math @@ -4405,7 +4577,10 @@ end % content at all. So for index sorting, we map @{ and @} to strings % starting with |, since that ASCII character is between ASCII { and }. \def\{{|a}% + \def\lbracechar{|a}% + % \def\}{|b}% + \def\rbracechar{|b}% % % Non-English letters. \def\AA{AA}% @@ -4581,10 +4756,9 @@ end % % ..., ready, GO: % -\def\safewhatsit#1{% -\ifhmode +\def\safewhatsit#1{\ifhmode #1% -\else + \else % \lastskip and \lastpenalty cannot both be nonzero simultaneously. \whatsitskip = \lastskip \edef\lastskipmacro{\the\lastskip}% @@ -4608,7 +4782,6 @@ end % to re-insert the same penalty (values >10000 are used for various % signals); since we just inserted a non-discardable item, any % following glue (such as a \parskip) would be a breakpoint. For example: - % % @deffn deffn-whatever % @vindex index-whatever % Description. @@ -4621,8 +4794,7 @@ end % (the whatsit from the \write), so we must insert a \nobreak. \nobreak\vskip\whatsitskip \fi -\fi -} +\fi} % The index entry written in the file actually looks like % \entry {sortstring}{page}{topic} @@ -5242,7 +5414,8 @@ end \global\let\subsubsection = \appendixsubsubsec } -\outer\parseargdef\unnumbered{\unnmhead0{#1}} % normally unnmhead0 calls unnumberedzzz +% normally unnmhead0 calls unnumberedzzz: +\outer\parseargdef\unnumbered{\unnmhead0{#1}} \def\unnumberedzzz#1{% \global\secno=0 \global\subsecno=0 \global\subsubsecno=0 \global\advance\unnumberedno by 1 @@ -5286,40 +5459,47 @@ end \let\top\unnumbered % Sections. +% \outer\parseargdef\numberedsec{\numhead1{#1}} % normally calls seczzz \def\seczzz#1{% \global\subsecno=0 \global\subsubsecno=0 \global\advance\secno by 1 \sectionheading{#1}{sec}{Ynumbered}{\the\chapno.\the\secno}% } -\outer\parseargdef\appendixsection{\apphead1{#1}} % normally calls appendixsectionzzz +% normally calls appendixsectionzzz: +\outer\parseargdef\appendixsection{\apphead1{#1}} \def\appendixsectionzzz#1{% \global\subsecno=0 \global\subsubsecno=0 \global\advance\secno by 1 \sectionheading{#1}{sec}{Yappendix}{\appendixletter.\the\secno}% } \let\appendixsec\appendixsection -\outer\parseargdef\unnumberedsec{\unnmhead1{#1}} % normally calls unnumberedseczzz +% normally calls unnumberedseczzz: +\outer\parseargdef\unnumberedsec{\unnmhead1{#1}} \def\unnumberedseczzz#1{% \global\subsecno=0 \global\subsubsecno=0 \global\advance\secno by 1 \sectionheading{#1}{sec}{Ynothing}{\the\unnumberedno.\the\secno}% } % Subsections. -\outer\parseargdef\numberedsubsec{\numhead2{#1}} % normally calls numberedsubseczzz +% +% normally calls numberedsubseczzz: +\outer\parseargdef\numberedsubsec{\numhead2{#1}} \def\numberedsubseczzz#1{% \global\subsubsecno=0 \global\advance\subsecno by 1 \sectionheading{#1}{subsec}{Ynumbered}{\the\chapno.\the\secno.\the\subsecno}% } -\outer\parseargdef\appendixsubsec{\apphead2{#1}} % normally calls appendixsubseczzz +% normally calls appendixsubseczzz: +\outer\parseargdef\appendixsubsec{\apphead2{#1}} \def\appendixsubseczzz#1{% \global\subsubsecno=0 \global\advance\subsecno by 1 \sectionheading{#1}{subsec}{Yappendix}% {\appendixletter.\the\secno.\the\subsecno}% } -\outer\parseargdef\unnumberedsubsec{\unnmhead2{#1}} %normally calls unnumberedsubseczzz +% normally calls unnumberedsubseczzz: +\outer\parseargdef\unnumberedsubsec{\unnmhead2{#1}} \def\unnumberedsubseczzz#1{% \global\subsubsecno=0 \global\advance\subsecno by 1 \sectionheading{#1}{subsec}{Ynothing}% @@ -5327,21 +5507,25 @@ end } % Subsubsections. -\outer\parseargdef\numberedsubsubsec{\numhead3{#1}} % normally numberedsubsubseczzz +% +% normally numberedsubsubseczzz: +\outer\parseargdef\numberedsubsubsec{\numhead3{#1}} \def\numberedsubsubseczzz#1{% \global\advance\subsubsecno by 1 \sectionheading{#1}{subsubsec}{Ynumbered}% {\the\chapno.\the\secno.\the\subsecno.\the\subsubsecno}% } -\outer\parseargdef\appendixsubsubsec{\apphead3{#1}} % normally appendixsubsubseczzz +% normally appendixsubsubseczzz: +\outer\parseargdef\appendixsubsubsec{\apphead3{#1}} \def\appendixsubsubseczzz#1{% \global\advance\subsubsecno by 1 \sectionheading{#1}{subsubsec}{Yappendix}% {\appendixletter.\the\secno.\the\subsecno.\the\subsubsecno}% } -\outer\parseargdef\unnumberedsubsubsec{\unnmhead3{#1}} %normally unnumberedsubsubseczzz +% normally unnumberedsubsubseczzz: +\outer\parseargdef\unnumberedsubsubsec{\unnmhead3{#1}} \def\unnumberedsubsubseczzz#1{% \global\advance\subsubsecno by 1 \sectionheading{#1}{subsubsec}{Ynothing}% @@ -5391,14 +5575,13 @@ end % (including whitespace, linebreaking, etc. around it), % given all the information in convenient, parsed form. -%%% Args are the skip and penalty (usually negative) +% Args are the skip and penalty (usually negative) \def\dobreak#1#2{\par\ifdim\lastskip<#1\removelastskip\penalty#2\vskip#1\fi} -%%% Define plain chapter starts, and page on/off switching for it % Parameter controlling skip before chapter headings (if needed) - \newskip\chapheadingskip +% Define plain chapter starts, and page on/off switching for it. \def\chapbreak{\dobreak \chapheadingskip {-4000}} \def\chappager{\par\vfill\supereject} % Because \domark is called before \chapoddpage, the filler page will @@ -5601,6 +5784,8 @@ end % \def\sectionheading#1#2#3#4{% {% + \checkenv{}% should not be in an environment. + % % Switch to the right set of fonts. \csname #2fonts\endcsname \rmisbold % @@ -5712,15 +5897,15 @@ end % % We'll almost certainly start a paragraph next, so don't let that % glue accumulate. (Not a breakpoint because it's preceded by a - % discardable item.) + % discardable item.) However, when a paragraph is not started next + % (\startdefun, \cartouche, \center, etc.), this needs to be wiped out + % or the negative glue will cause weirdly wrong output, typically + % obscuring the section heading with something else. \vskip-\parskip % - % This is purely so the last item on the list is a known \penalty > - % 10000. This is so \startdefun can avoid allowing breakpoints after - % section headings. Otherwise, it would insert a valid breakpoint between: - % - % @section sec-whatever - % @deffn def-whatever + % This is so the last item on the main vertical list is a known + % \penalty > 10000, so \startdefun, etc., can recognize the situation + % and do the needful. \penalty 10001 } @@ -6136,6 +6321,12 @@ end \normbskip=\baselineskip \normpskip=\parskip \normlskip=\lineskip % Flag to tell @lisp, etc., not to narrow margin. \let\nonarrowing = t% + % + % If this cartouche directly follows a sectioning command, we need the + % \parskip glue (backspaced over by default) or the cartouche can + % collide with the section heading. + \ifnum\lastpenalty>10000 \vskip\parskip \penalty\lastpenalty \fi + % \vbox\bgroup \baselineskip=0pt\parskip=0pt\lineskip=0pt \carttop @@ -6149,7 +6340,7 @@ end \lineskip=\normlskip \parskip=\normpskip \vskip -\parskip - \comment % For explanation, see the end of \def\group. + \comment % For explanation, see the end of def\group. } \def\Ecartouche{% \ifhmode\par\fi @@ -6346,7 +6537,7 @@ end % \def\Equotation{% \par - \ifx\quotationauthor\undefined\else + \ifx\quotationauthor\thisisundefined\else % indent a bit. \leftline{\kern 2\leftskip \sl ---\quotationauthor}% \fi @@ -6505,6 +6696,7 @@ end \makevalueexpandable \setupverbatim \indexnofonts % Allow `@@' and other weird things in file names. + \wlog{texinfo.tex: doing @verbatiminclude of #1^^J}% \input #1 \afterenvbreak }% @@ -6554,7 +6746,7 @@ end % commands also insert a nobreak penalty, and we don't want to allow % a break between a section heading and a defun. % - % As a minor refinement, we avoid "club" headers by signalling + % As a further refinement, we avoid "club" headers by signalling % with penalty of 10003 after the very first @deffn in the % sequence (see above), and penalty of 10002 after any following % @def command. @@ -6621,13 +6813,36 @@ end \def\domakedefun#1#2#3{% \envdef#1{% \startdefun + \doingtypefnfalse % distinguish typed functions from all else \parseargusing\activeparens{\printdefunline#3}% }% \def#2{\dodefunx#1}% \def#3% } -%%% Untyped functions: +\newif\ifdoingtypefn % doing typed function? +\newif\ifrettypeownline % typeset return type on its own line? + +% @deftypefnnewline on|off says whether the return type of typed functions +% are printed on their own line. This affects @deftypefn, @deftypefun, +% @deftypeop, and @deftypemethod. +% +\parseargdef\deftypefnnewline{% + \def\temp{#1}% + \ifx\temp\onword + \expandafter\let\csname SETtxideftypefnnl\endcsname + = \empty + \else\ifx\temp\offword + \expandafter\let\csname SETtxideftypefnnl\endcsname + = \relax + \else + \errhelp = \EMsimple + \errmessage{Unknown @txideftypefnnl value `\temp', + must be on|off}% + \fi\fi +} + +% Untyped functions: % @deffn category name args \makedefun{deffn}{\deffngeneral{}} @@ -6646,7 +6861,7 @@ end \defname{#2}{}{#3}\magicamp\defunargs{#4\unskip}% } -%%% Typed functions: +% Typed functions: % @deftypefn category type name args \makedefun{deftypefn}{\deftypefngeneral{}} @@ -6661,10 +6876,11 @@ end % \def\deftypefngeneral#1#2 #3 #4 #5\endheader{% \dosubind{fn}{\code{#4}}{#1}% + \doingtypefntrue \defname{#2}{#3}{#4}\defunargs{#5\unskip}% } -%%% Typed variables: +% Typed variables: % @deftypevr category type var args \makedefun{deftypevr}{\deftypecvgeneral{}} @@ -6682,7 +6898,7 @@ end \defname{#2}{#3}{#4}\defunargs{#5\unskip}% } -%%% Untyped variables: +% Untyped variables: % @defvr category var args \makedefun{defvr}#1 {\deftypevrheader{#1} {} } @@ -6693,7 +6909,8 @@ end % \defcvof {category of}class var args \def\defcvof#1#2 {\deftypecvof{#1}#2 {} } -%%% Type: +% Types: + % @deftp category name args \makedefun{deftp}#1 #2 #3\endheader{% \doind{tp}{\code{#2}}% @@ -6721,25 +6938,49 @@ end % We are followed by (but not passed) the arguments, if any. % \def\defname#1#2#3{% + \par % Get the values of \leftskip and \rightskip as they were outside the @def... \advance\leftskip by -\defbodyindent % - % How we'll format the type name. Putting it in brackets helps + % Determine if we are typesetting the return type of a typed function + % on a line by itself. + \rettypeownlinefalse + \ifdoingtypefn % doing a typed function specifically? + % then check user option for putting return type on its own line: + \expandafter\ifx\csname SETtxideftypefnnl\endcsname\relax \else + \rettypeownlinetrue + \fi + \fi + % + % How we'll format the category name. Putting it in brackets helps % distinguish it from the body text that may end up on the next line % just below it. \def\temp{#1}% \setbox0=\hbox{\kern\deflastargmargin \ifx\temp\empty\else [\rm\temp]\fi} % - % Figure out line sizes for the paragraph shape. + % Figure out line sizes for the paragraph shape. We'll always have at + % least two. + \tempnum = 2 + % % The first line needs space for \box0; but if \rightskip is nonzero, % we need only space for the part of \box0 which exceeds it: \dimen0=\hsize \advance\dimen0 by -\wd0 \advance\dimen0 by \rightskip + % + % If doing a return type on its own line, we'll have another line. + \ifrettypeownline + \advance\tempnum by 1 + \def\maybeshapeline{0in \hsize}% + \else + \def\maybeshapeline{}% + \fi + % % The continuations: \dimen2=\hsize \advance\dimen2 by -\defargsindent - % (plain.tex says that \dimen1 should be used only as global.) - \parshape 2 0in \dimen0 \defargsindent \dimen2 % - % Put the type name to the right margin. + % The final paragraph shape: + \parshape \tempnum 0in \dimen0 \maybeshapeline \defargsindent \dimen2 + % + % Put the category name at the right margin. \noindent \hbox to 0pt{% \hfil\box0 \kern-\hsize @@ -6761,8 +7002,16 @@ end % . this still does not fix the ?` and !` ligatures, but so far no % one has made identifiers using them :). \df \tt - \def\temp{#2}% return value type - \ifx\temp\empty\else \tclose{\temp} \fi + \def\temp{#2}% text of the return type + \ifx\temp\empty\else + \tclose{\temp}% typeset the return type + \ifrettypeownline + % put return type on its own line; prohibit line break following: + \hfil\vadjust{\nobreak}\break + \else + \space % type on same line, so just followed by a space + \fi + \fi % no return type #3% output function name }% {\rm\enskip}% hskip 0.5 em of \tenrm @@ -6880,7 +7129,7 @@ end % To do this right we need a feature of e-TeX, \scantokens, % which we arrange to emulate with a temporary file in ordinary TeX. -\ifx\eTeXversion\undefined +\ifx\eTeXversion\thisisundefined \newwrite\macscribble \def\scantokens#1{% \toks0={#1}% @@ -6905,12 +7154,14 @@ end % ... and for \example: \spaceisspace % - % The \empty here causes a following catcode 5 newline to be eaten - % as part of reading whitespace after a control sequence. It does - % not eat a catcode 13 newline. There's no good way to handle the - % two cases. See the Macro Details node in the manual for the - % workaround we currently have to recommend for macros and + % The \empty here causes a following catcode 5 newline to be eaten as + % part of reading whitespace after a control sequence. It does not + % eat a catcode 13 newline. There's no good way to handle the two + % cases (untried: maybe e-TeX's \everyeof could help, though plain TeX + % would then have different behavior). See the Macro Details node in + % the manual for the workaround we recommend for macros and % line-oriented commands. + % \scantokens{#1\empty}% \endgroup} @@ -7045,9 +7296,15 @@ end \def\macroxxx#1{% \getargs{#1}% now \macname is the macname and \argl the arglist \ifx\argl\empty % no arguments - \paramno=0 + \paramno=0\relax \else \expandafter\parsemargdef \argl;% + \if\paramno>256\relax + \ifx\eTeXversion\thisisundefined + \errhelp = \EMsimple + \errmessage{You need eTeX to compile a file with macros with more than 256 arguments} + \fi + \fi \fi \if1\csname ismacro.\the\macname\endcsname \message{Warning: redefining \the\macname}% @@ -7097,9 +7354,17 @@ end \def\getmacname#1 #2\relax{\macname={#1}} \def\getmacargs#1{\def\argl{#1}} +% For macro processing make @ a letter so that we can make Texinfo private macro names. +\edef\texiatcatcode{\the\catcode`\@} +\catcode `@=11\relax + % Parse the optional {params} list. Set up \paramno and \paramlist -% so \defmacro knows what to do. Define \macarg.blah for each blah -% in the params list to be ##N where N is the position in that list. +% so \defmacro knows what to do. Define \macarg.BLAH for each BLAH +% in the params list to some hook where the argument si to be expanded. If +% there are less than 10 arguments that hook is to be replaced by ##N where N +% is the position in that list, that is to say the macro arguments are to be +% defined `a la TeX in the macro body. +% % That gets used by \mbodybackslash (above). % % We need to get `macro parameter char #' into several definitions. @@ -7109,12 +7374,33 @@ end % % The same technique is used to protect \eatspaces till just before % the macro is used. - +% +% If there are 10 or more arguments, a different technique is used, where the +% hook remains in the body, and when macro is to be expanded the body is +% processed again to replace the arguments. +% +% In that case, the hook is \the\toks N-1, and we simply set \toks N-1 to the +% argument N value and then \edef the body (nothing else will expand because of +% the catcode regime underwhich the body was input). +% +% If you compile with TeX (not eTeX), and you have macros with 10 or more +% arguments, you need that no macro has more than 256 arguments, otherwise an +% error is produced. \def\parsemargdef#1;{% \paramno=0\def\paramlist{}% \let\hash\relax \let\xeatspaces\relax \parsemargdefxxx#1,;,% + % In case that there are 10 or more arguments we parse again the arguments + % list to set new definitions for the \macarg.BLAH macros corresponding to + % each BLAH argument. It was anyhow needed to parse already once this list + % in order to count the arguments, and as macros with at most 9 arguments + % are by far more frequent than macro with 10 or more arguments, defining + % twice the \macarg.BLAH macros does not cost too much processing power. + \ifnum\paramno<10\relax\else + \paramno0\relax + \parsemmanyargdef@@#1,;,% 10 or more arguments + \fi } \def\parsemargdefxxx#1,{% \if#1;\let\next=\relax @@ -7125,16 +7411,205 @@ end \edef\paramlist{\paramlist\hash\the\paramno,}% \fi\next} +\def\parsemmanyargdef@@#1,{% + \if#1;\let\next=\relax + \else + \let\next=\parsemmanyargdef@@ + \edef\tempb{\eatspaces{#1}}% + \expandafter\def\expandafter\tempa + \expandafter{\csname macarg.\tempb\endcsname}% + % Note that we need some extra \noexpand\noexpand, this is because we + % don't want \the to be expanded in the \parsermacbody as it uses an + % \xdef . + \expandafter\edef\tempa + {\noexpand\noexpand\noexpand\the\toks\the\paramno}% + \advance\paramno by 1\relax + \fi\next} + % These two commands read recursive and nonrecursive macro bodies. % (They're different since rec and nonrec macros end differently.) % + +\catcode `\@\texiatcatcode \long\def\parsemacbody#1@end macro% {\xdef\temp{\eatcr{#1}}\endgroup\defmacro}% \long\def\parsermacbody#1@end rmacro% {\xdef\temp{\eatcr{#1}}\endgroup\defmacro}% +\catcode `\@=11\relax + +\let\endargs@\relax +\let\nil@\relax +\def\nilm@{\nil@}% +\long\def\nillm@{\nil@}% + +% This macro is expanded during the Texinfo macro expansion, not during its +% definition. It gets all the arguments values and assigns them to macros +% macarg.ARGNAME +% +% #1 is the macro name +% #2 is the list of argument names +% #3 is the list of argument values +\def\getargvals@#1#2#3{% + \def\macargdeflist@{}% + \def\saveparamlist@{#2}% Need to keep a copy for parameter expansion. + \def\paramlist{#2,\nil@}% + \def\macroname{#1}% + \begingroup + \macroargctxt + \def\argvaluelist{#3,\nil@}% + \def\@tempa{#3}% + \ifx\@tempa\empty + \setemptyargvalues@ + \else + \getargvals@@ + \fi +} -% This defines the macro itself. There are six cases: recursive and -% nonrecursive macros of zero, one, and many arguments. +% +\def\getargvals@@{% + \ifx\paramlist\nilm@ + % Some sanity check needed here that \argvaluelist is also empty. + \ifx\argvaluelist\nillm@ + \else + \errhelp = \EMsimple + \errmessage{Too many arguments in macro `\macroname'!}% + \fi + \let\next\macargexpandinbody@ + \else + \ifx\argvaluelist\nillm@ + % No more arguments values passed to macro. Set remaining named-arg + % macros to empty. + \let\next\setemptyargvalues@ + \else + % pop current arg name into \@tempb + \def\@tempa##1{\pop@{\@tempb}{\paramlist}##1\endargs@}% + \expandafter\@tempa\expandafter{\paramlist}% + % pop current argument value into \@tempc + \def\@tempa##1{\longpop@{\@tempc}{\argvaluelist}##1\endargs@}% + \expandafter\@tempa\expandafter{\argvaluelist}% + % Here \@tempb is the current arg name and \@tempc is the current arg value. + % First place the new argument macro definition into \@tempd + \expandafter\macname\expandafter{\@tempc}% + \expandafter\let\csname macarg.\@tempb\endcsname\relax + \expandafter\def\expandafter\@tempe\expandafter{% + \csname macarg.\@tempb\endcsname}% + \edef\@tempd{\long\def\@tempe{\the\macname}}% + \push@\@tempd\macargdeflist@ + \let\next\getargvals@@ + \fi + \fi + \next +} + +\def\push@#1#2{% + \expandafter\expandafter\expandafter\def + \expandafter\expandafter\expandafter#2% + \expandafter\expandafter\expandafter{% + \expandafter#1#2}% +} + +% Replace arguments by their values in the macro body, and place the result +% in macro \@tempa +\def\macvalstoargs@{% + % To do this we use the property that token registers that are \the'ed + % within an \edef expand only once. So we are going to place all argument + % values into respective token registers. + % + % First we save the token context, and initialize argument numbering. + \begingroup + \paramno0\relax + % Then, for each argument number #N, we place the corresponding argument + % value into a new token list register \toks#N + \expandafter\putargsintokens@\saveparamlist@,;,% + % Then, we expand the body so that argument are replaced by their + % values. The trick for values not to be expanded themselves is that they + % are within tokens and that tokens expand only once in an \edef . + \edef\@tempc{\csname mac.\macroname .body\endcsname}% + % Now we restore the token stack pointer to free the token list registers + % which we have used, but we make sure that expanded body is saved after + % group. + \expandafter + \endgroup + \expandafter\def\expandafter\@tempa\expandafter{\@tempc}% + } + +\def\macargexpandinbody@{% + %% Define the named-macro outside of this group and then close this group. + \expandafter + \endgroup + \macargdeflist@ + % First the replace in body the macro arguments by their values, the result + % is in \@tempa . + \macvalstoargs@ + % Then we point at the \norecurse or \gobble (for recursive) macro value + % with \@tempb . + \expandafter\let\expandafter\@tempb\csname mac.\macroname .recurse\endcsname + % Depending on whether it is recursive or not, we need some tailing + % \egroup . + \ifx\@tempb\gobble + \let\@tempc\relax + \else + \let\@tempc\egroup + \fi + % And now we do the real job: + \edef\@tempd{\noexpand\@tempb{\macroname}\noexpand\scanmacro{\@tempa}\@tempc}% + \@tempd +} + +\def\putargsintokens@#1,{% + \if#1;\let\next\relax + \else + \let\next\putargsintokens@ + % First we allocate the new token list register, and give it a temporary + % alias \@tempb . + \toksdef\@tempb\the\paramno + % Then we place the argument value into that token list register. + \expandafter\let\expandafter\@tempa\csname macarg.#1\endcsname + \expandafter\@tempb\expandafter{\@tempa}% + \advance\paramno by 1\relax + \fi + \next +} + +% Save the token stack pointer into macro #1 +\def\texisavetoksstackpoint#1{\edef#1{\the\@cclvi}} +% Restore the token stack pointer from number in macro #1 +\def\texirestoretoksstackpoint#1{\expandafter\mathchardef\expandafter\@cclvi#1\relax} +% newtoks that can be used non \outer . +\def\texinonouternewtoks{\alloc@ 5\toks \toksdef \@cclvi} + +% Tailing missing arguments are set to empty +\def\setemptyargvalues@{% + \ifx\paramlist\nilm@ + \let\next\macargexpandinbody@ + \else + \expandafter\setemptyargvaluesparser@\paramlist\endargs@ + \let\next\setemptyargvalues@ + \fi + \next +} + +\def\setemptyargvaluesparser@#1,#2\endargs@{% + \expandafter\def\expandafter\@tempa\expandafter{% + \expandafter\def\csname macarg.#1\endcsname{}}% + \push@\@tempa\macargdeflist@ + \def\paramlist{#2}% +} + +% #1 is the element target macro +% #2 is the list macro +% #3,#4\endargs@ is the list value +\def\pop@#1#2#3,#4\endargs@{% + \def#1{#3}% + \def#2{#4}% +} +\long\def\longpop@#1#2#3,#4\endargs@{% + \long\def#1{#3}% + \long\def#2{#4}% +} + +% This defines a Texinfo @macro. There are eight cases: recursive and +% nonrecursive macros of zero, one, up to nine, and many arguments. % Much magic with \expandafter here. % \xdef is used so that macro definitions will survive the file % they're defined in; @include reads the file inside a group. @@ -7153,17 +7628,25 @@ end \expandafter\noexpand\csname\the\macname xxx\endcsname}% \expandafter\xdef\csname\the\macname xxx\endcsname##1{% \egroup\noexpand\scanmacro{\temp}}% - \else % many - \expandafter\xdef\csname\the\macname\endcsname{% - \bgroup\noexpand\macroargctxt - \noexpand\csname\the\macname xx\endcsname}% - \expandafter\xdef\csname\the\macname xx\endcsname##1{% - \expandafter\noexpand\csname\the\macname xxx\endcsname ##1,}% - \expandafter\expandafter - \expandafter\xdef - \expandafter\expandafter - \csname\the\macname xxx\endcsname - \paramlist{\egroup\noexpand\scanmacro{\temp}}% + \else + \ifnum\paramno<10\relax % at most 9 + \expandafter\xdef\csname\the\macname\endcsname{% + \bgroup\noexpand\macroargctxt + \noexpand\csname\the\macname xx\endcsname}% + \expandafter\xdef\csname\the\macname xx\endcsname##1{% + \expandafter\noexpand\csname\the\macname xxx\endcsname ##1,}% + \expandafter\expandafter + \expandafter\xdef + \expandafter\expandafter + \csname\the\macname xxx\endcsname + \paramlist{\egroup\noexpand\scanmacro{\temp}}% + \else % 10 or more + \expandafter\xdef\csname\the\macname\endcsname{% + \noexpand\getargvals@{\the\macname}{\argl}% + }% + \global\expandafter\let\csname mac.\the\macname .body\endcsname\temp + \global\expandafter\let\csname mac.\the\macname .recurse\endcsname\gobble + \fi \fi \else \ifcase\paramno @@ -7180,23 +7663,33 @@ end \egroup \noexpand\norecurse{\the\macname}% \noexpand\scanmacro{\temp}\egroup}% - \else % many - \expandafter\xdef\csname\the\macname\endcsname{% - \bgroup\noexpand\macroargctxt - \expandafter\noexpand\csname\the\macname xx\endcsname}% - \expandafter\xdef\csname\the\macname xx\endcsname##1{% - \expandafter\noexpand\csname\the\macname xxx\endcsname ##1,}% - \expandafter\expandafter - \expandafter\xdef - \expandafter\expandafter - \csname\the\macname xxx\endcsname - \paramlist{% - \egroup - \noexpand\norecurse{\the\macname}% - \noexpand\scanmacro{\temp}\egroup}% + \else % at most 9 + \ifnum\paramno<10\relax + \expandafter\xdef\csname\the\macname\endcsname{% + \bgroup\noexpand\macroargctxt + \expandafter\noexpand\csname\the\macname xx\endcsname}% + \expandafter\xdef\csname\the\macname xx\endcsname##1{% + \expandafter\noexpand\csname\the\macname xxx\endcsname ##1,}% + \expandafter\expandafter + \expandafter\xdef + \expandafter\expandafter + \csname\the\macname xxx\endcsname + \paramlist{% + \egroup + \noexpand\norecurse{\the\macname}% + \noexpand\scanmacro{\temp}\egroup}% + \else % 10 or more: + \expandafter\xdef\csname\the\macname\endcsname{% + \noexpand\getargvals@{\the\macname}{\argl}% + }% + \global\expandafter\let\csname mac.\the\macname .body\endcsname\temp + \global\expandafter\let\csname mac.\the\macname .recurse\endcsname\norecurse + \fi \fi \fi} +\catcode `\@\texiatcatcode\relax + \def\norecurse#1{\bgroup\cslet{#1}{macsave.#1}} % \braceorline decides whether the next nonwhitespace character is a @@ -7235,7 +7728,8 @@ end % @inforef is relatively simple. \def\inforef #1{\inforefzzz #1,,,,**} -\def\inforefzzz #1,#2,#3,#4**{\putwordSee{} \putwordInfo{} \putwordfile{} \file{\ignorespaces #3{}}, +\def\inforefzzz #1,#2,#3,#4**{% + \putwordSee{} \putwordInfo{} \putwordfile{} \file{\ignorespaces #3{}}, node \samp{\ignorespaces#1{}}} % @node's only job in TeX is to define \lastnode, which is used in @@ -7296,11 +7790,32 @@ end \toks0 = \expandafter{\lastsection}% \immediate \writexrdef{title}{\the\toks0 }% \immediate \writexrdef{snt}{\csname #2\endcsname}% \Ynumbered etc. - \safewhatsit{\writexrdef{pg}{\folio}}% will be written later, during \shipout + \safewhatsit{\writexrdef{pg}{\folio}}% will be written later, at \shipout }% \fi } +% @xrefautosectiontitle on|off says whether @section(ing) names are used +% automatically in xrefs, if the third arg is not explicitly specified. +% This was provided as a "secret" @set xref-automatic-section-title +% variable, now it's official. +% +\parseargdef\xrefautomaticsectiontitle{% + \def\temp{#1}% + \ifx\temp\onword + \expandafter\let\csname SETxref-automatic-section-title\endcsname + = \empty + \else\ifx\temp\offword + \expandafter\let\csname SETxref-automatic-section-title\endcsname + = \relax + \else + \errhelp = \EMsimple + \errmessage{Unknown @xrefautomaticsectiontitle value `\temp', + must be on|off}% + \fi\fi +} + +% % @xref, @pxref, and @ref generate cross-references. For \xrefX, #1 is % the node name, #2 the name of the Info cross-reference, #3 the printed % node name, #4 the name of the Info file, #5 the name of the printed @@ -7309,26 +7824,41 @@ end \def\pxref#1{\putwordsee{} \xrefX[#1,,,,,,,]} \def\xref#1{\putwordSee{} \xrefX[#1,,,,,,,]} \def\ref#1{\xrefX[#1,,,,,,,]} +% +\newbox\toprefbox +\newbox\printedrefnamebox +\newbox\infofilenamebox +\newbox\printedmanualbox +% \def\xrefX[#1,#2,#3,#4,#5,#6]{\begingroup \unsepspaces - \def\printedmanual{\ignorespaces #5}% + % + % Get args without leading/trailing spaces. \def\printedrefname{\ignorespaces #3}% - \setbox1=\hbox{\printedmanual\unskip}% - \setbox0=\hbox{\printedrefname\unskip}% - \ifdim \wd0 = 0pt + \setbox\printedrefnamebox = \hbox{\printedrefname\unskip}% + % + \def\infofilename{\ignorespaces #4}% + \setbox\infofilenamebox = \hbox{\infofilename\unskip}% + % + \def\printedmanual{\ignorespaces #5}% + \setbox\printedmanualbox = \hbox{\printedmanual\unskip}% + % + % If the printed reference name (arg #3) was not explicitly given in + % the @xref, figure out what we want to use. + \ifdim \wd\printedrefnamebox = 0pt % No printed node name was explicitly given. - \expandafter\ifx\csname SETxref-automatic-section-title\endcsname\relax - % Use the node name inside the square brackets. + \expandafter\ifx\csname SETxref-automatic-section-title\endcsname \relax + % Not auto section-title: use node name inside the square brackets. \def\printedrefname{\ignorespaces #1}% \else - % Use the actual chapter/section title appear inside - % the square brackets. Use the real section title if we have it. - \ifdim \wd1 > 0pt - % It is in another manual, so we don't have it. + % Auto section-title: use chapter/section title inside + % the square brackets if we have it. + \ifdim \wd\printedmanualbox > 0pt + % It is in another manual, so we don't have it; use node name. \def\printedrefname{\ignorespaces #1}% \else \ifhavexrefs - % We know the real title if we have the xref values. + % We (should) know the real title if we have the xref values. \def\printedrefname{\refx{#1-title}{}}% \else % Otherwise just copy the Info node name. @@ -7342,13 +7872,20 @@ end \ifpdf {\indexnofonts \turnoffactive + \makevalueexpandable % This expands tokens, so do it after making catcode changes, so _ - % etc. don't get their TeX definitions. + % etc. don't get their TeX definitions. This ignores all spaces in + % #4, including (wrongly) those in the middle of the filename. \getfilename{#4}% % - % See comments at \activebackslashdouble. - {\activebackslashdouble \xdef\pdfxrefdest{#1}% - \backslashparens\pdfxrefdest}% + % This (wrongly) does not take account of leading or trailing + % spaces in #1, which should be ignored. + \edef\pdfxrefdest{#1}% + \ifx\pdfxrefdest\empty + \def\pdfxrefdest{Top}% no empty targets + \else + \txiescapepdf\pdfxrefdest % escape PDF special chars + \fi % \leavevmode \startlink attr{/Border [0 0 0]}% @@ -7375,29 +7912,42 @@ end \iffloat\Xthisreftitle % If the user specified the print name (third arg) to the ref, % print it instead of our usual "Figure 1.2". - \ifdim\wd0 = 0pt + \ifdim\wd\printedrefnamebox = 0pt \refx{#1-snt}{}% \else \printedrefname \fi % - % if the user also gave the printed manual name (fifth arg), append + % If the user also gave the printed manual name (fifth arg), append % "in MANUALNAME". - \ifdim \wd1 > 0pt + \ifdim \wd\printedmanualbox > 0pt \space \putwordin{} \cite{\printedmanual}% \fi \else % node/anchor (non-float) references. + % + % If we use \unhbox to print the node names, TeX does not insert + % empty discretionaries after hyphens, which means that it will not + % find a line break at a hyphen in a node names. Since some manuals + % are best written with fairly long node names, containing hyphens, + % this is a loss. Therefore, we give the text of the node name + % again, so it is as if TeX is seeing it for the first time. + % + \ifdim \wd\printedmanualbox > 0pt + % Cross-manual reference with a printed manual name. + % + \crossmanualxref{\cite{\printedmanual\unskip}}% + % + \else\ifdim \wd\infofilenamebox > 0pt + % Cross-manual reference with only an info filename (arg 4), no + % printed manual name (arg 5). This is essentially the same as + % the case above; we output the filename, since we have nothing else. + % + \crossmanualxref{\code{\infofilename\unskip}}% % - % If we use \unhbox0 and \unhbox1 to print the node names, TeX does not - % insert empty discretionaries after hyphens, which means that it will - % not find a line break at a hyphen in a node names. Since some manuals - % are best written with fairly long node names, containing hyphens, this - % is a loss. Therefore, we give the text of the node name again, so it - % is as if TeX is seeing it for the first time. - \ifdim \wd1 > 0pt - \putwordSection{} ``\printedrefname'' \putwordin{} \cite{\printedmanual}% \else + % Reference within this manual. + % % _ (for example) has to be the character _ for the purposes of the % control sequence corresponding to the node, but it has to expand % into the usual \leavevmode...\vrule stuff for purposes of @@ -7409,7 +7959,7 @@ end \setbox2 = \hbox{\ignorespaces \refx{#1-snt}{}}% \ifdim \wd2 > 0pt \refx{#1-snt}\space\fi }% - % output the `[mynode]' via a macro so it can be overridden. + % output the `[mynode]' via the macro below so it can be overridden. \xrefprintnodename\printedrefname % % But we always want a comma and a space: @@ -7417,11 +7967,37 @@ end % % output the `page 3'. \turnoffactive \putwordpage\tie\refx{#1-pg}{}% - \fi + \fi\fi \fi \endlink \endgroup} +% Output a cross-manual xref to #1. Used just above (twice). +% +% Only include the text "Section ``foo'' in" if the foo is neither +% missing or Top. Thus, @xref{,,,foo,The Foo Manual} outputs simply +% "see The Foo Manual", the idea being to refer to the whole manual. +% +% But, this being TeX, we can't easily compare our node name against the +% string "Top" while ignoring the possible spaces before and after in +% the input. By adding the arbitrary 7sp below, we make it much less +% likely that a real node name would have the same width as "Top" (e.g., +% in a monospaced font). Hopefully it will never happen in practice. +% +% For the same basic reason, we retypeset the "Top" at every +% reference, since the current font is indeterminate. +% +\def\crossmanualxref#1{% + \setbox\toprefbox = \hbox{Top\kern7sp}% + \setbox2 = \hbox{\ignorespaces \printedrefname \unskip \kern7sp}% + \ifdim \wd2 > 7sp % nonempty? + \ifdim \wd2 = \wd\toprefbox \else % same as Top? + \putwordSection{} ``\printedrefname'' \putwordin{}\space + \fi + \fi + #1% +} + % This macro is called from \xrefX for the `[nodename]' part of xref % output. It's a separate macro only so it can be changed more easily, % since square brackets don't work well in some documents. Particularly @@ -7637,7 +8213,7 @@ end % space to prevent strange expansion errors.) \def\supereject{\par\penalty -20000\footnoteno =0 } -% @footnotestyle is meaningful for info output only. +% @footnotestyle is meaningful for Info output only. \let\footnotestyle=\comment {\catcode `\@=11 @@ -7700,6 +8276,8 @@ end % expands into a box, it must come within the paragraph, lest it % provide a place where TeX can split the footnote. \footstrut + % + % Invoke rest of plain TeX footnote routine. \futurelet\next\fo@t } }%end \catcode `\@=11 @@ -7787,7 +8365,7 @@ end it from ftp://tug.org/tex/epsf.tex.} % \def\image#1{% - \ifx\epsfbox\undefined + \ifx\epsfbox\thisisundefined \ifwarnednoepsf \else \errhelp = \noepsfhelp \errmessage{epsf.tex not found, images will be ignored}% @@ -7811,6 +8389,13 @@ end % If the image is by itself, center it. \ifvmode \imagevmodetrue + \else \ifx\centersub\centerV + % for @center @image, we need a vbox so we can have our vertical space + \imagevmodetrue + \vbox\bgroup % vbox has better behavior than vtop herev + \fi\fi + % + \ifimagevmode \nobreak\medskip % Usually we'll have text after the image which will insert % \parskip glue, so insert it here too to equalize the space @@ -7820,9 +8405,13 @@ end \fi % % Leave vertical mode so that indentation from an enclosing - % environment such as @quotation is respected. On the other hand, if - % it's at the top level, we don't want the normal paragraph indentation. - \noindent + % environment such as @quotation is respected. + % However, if we're at the top level, we don't want the + % normal paragraph indentation. + % On the other hand, if we are in the case of @center @image, we don't + % want to start a paragraph, which will create a hsize-width box and + % eradicate the centering. + \ifx\centersub\centerV\else \noindent \fi % % Output the image. \ifpdf @@ -7834,7 +8423,10 @@ end \epsfbox{#1.eps}% \fi % - \ifimagevmode \medskip \fi % space after the standalone image + \ifimagevmode + \medskip % space after a standalone image + \fi + \ifx\centersub\centerV \egroup \fi \endgroup} @@ -8252,7 +8844,7 @@ directory should work if nowhere else does.} % % Latin1 (ISO-8859-1) character definitions. \def\latonechardefs{% - \gdef^^a0{~} + \gdef^^a0{\tie} \gdef^^a1{\exclamdown} \gdef^^a2{\missingcharmsg{CENT SIGN}} \gdef^^a3{{\pounds}} @@ -8282,7 +8874,7 @@ directory should work if nowhere else does.} \gdef^^b9{$^1$} \gdef^^ba{\ordm} % - \gdef^^bb{\guilletright} + \gdef^^bb{\guillemetright} \gdef^^bc{$1\over4$} \gdef^^bd{$1\over2$} \gdef^^be{$3\over4$} @@ -8374,7 +8966,7 @@ directory should work if nowhere else does.} % Latin2 (ISO-8859-2) character definitions. \def\lattwochardefs{% - \gdef^^a0{~} + \gdef^^a0{\tie} \gdef^^a1{\ogonek{A}} \gdef^^a2{\u{}} \gdef^^a3{\L} @@ -8547,7 +9139,7 @@ directory should work if nowhere else does.} \gdef\DeclareUnicodeCharacter#1#2{% \countUTFz = "#1\relax - \wlog{\space\space defining Unicode char U+#1 (decimal \the\countUTFz)}% + %\wlog{\space\space defining Unicode char U+#1 (decimal \the\countUTFz)}% \begingroup \parseXMLCharref \def\UTFviiiTwoOctets##1##2{% @@ -9223,28 +9815,21 @@ directory should work if nowhere else does.} \message{and turning on texinfo input format.} +\def^^L{\par} % remove \outer, so ^L can appear in an @comment + % DEL is a comment character, in case @c does not suffice. \catcode`\^^? = 14 % Define macros to output various characters with catcode for normal text. -\catcode`\"=\other -\catcode`\~=\other -\catcode`\^=\other -\catcode`\_=\other -\catcode`\|=\other -\catcode`\<=\other -\catcode`\>=\other -\catcode`\+=\other -\catcode`\$=\other -\def\normaldoublequote{"} -\def\normaltilde{~} -\def\normalcaret{^} -\def\normalunderscore{_} -\def\normalverticalbar{|} -\def\normalless{<} -\def\normalgreater{>} -\def\normalplus{+} -\def\normaldollar{$}%$ font-lock fix +\catcode`\"=\other \def\normaldoublequote{"} +\catcode`\$=\other \def\normaldollar{$}%$ font-lock fix +\catcode`\+=\other \def\normalplus{+} +\catcode`\<=\other \def\normalless{<} +\catcode`\>=\other \def\normalgreater{>} +\catcode`\^=\other \def\normalcaret{^} +\catcode`\_=\other \def\normalunderscore{_} +\catcode`\|=\other \def\normalverticalbar{|} +\catcode`\~=\other \def\normaltilde{~} % This macro is used to make a character print one way in \tt % (where it can probably be output as-is), and another way in other fonts, @@ -9322,14 +9907,24 @@ directory should work if nowhere else does.} % In texinfo, backslash is an active character; it prints the backslash % in fixed width font. -\catcode`\\=\active -@def@normalbackslash{{@tt@backslashcurfont}} +\catcode`\\=\active % @ for escape char from now on. + +% The story here is that in math mode, the \char of \backslashcurfont +% ends up printing the roman \ from the math symbol font (because \char +% in math mode uses the \mathcode, and plain.tex sets +% \mathcode`\\="026E). It seems better for @backslashchar{} to always +% print a typewriter backslash, hence we use an explicit \mathchar, +% which is the decimal equivalent of "715c (class 7, e.g., use \fam; +% ignored family value; char position "5C). We can't use " for the +% usual hex value because it has already been made active. +@def@normalbackslash{{@tt @ifmmode @mathchar29020 @else @backslashcurfont @fi}} +@let@backslashchar = @normalbackslash % @backslashchar{} is for user documents. + % On startup, @fixbackslash assigns: % @let \ = @normalbackslash - % \rawbackslash defines an active \ to do \backslashcurfont. % \otherbackslash defines an active \ to be a literal `\' character with -% catcode other. +% catcode other. We switch back and forth between these. @gdef@rawbackslash{@let\=@backslashcurfont} @gdef@otherbackslash{@let\=@realbackslash} @@ -9337,16 +9932,16 @@ directory should work if nowhere else does.} % the literal character `\'. % @def@normalturnoffactive{% - @let\=@normalbackslash @let"=@normaldoublequote - @let~=@normaltilde + @let$=@normaldollar %$ font-lock fix + @let+=@normalplus + @let<=@normalless + @let>=@normalgreater + @let\=@normalbackslash @let^=@normalcaret @let_=@normalunderscore @let|=@normalverticalbar - @let<=@normalless - @let>=@normalgreater - @let+=@normalplus - @let$=@normaldollar %$ font-lock fix + @let~=@normaltilde @markupsetuplqdefault @markupsetuprqdefault @unsepspaces @@ -9378,10 +9973,19 @@ directory should work if nowhere else does.} % Say @foo, not \foo, in error messages. @escapechar = `@@ +% These (along with & and #) are made active for url-breaking, so need +% active definitions as the normal characters. +@def@normaldot{.} +@def@normalquest{?} +@def@normalslash{/} + % These look ok in all fonts, so just make them not special. -@catcode`@& = @other -@catcode`@# = @other -@catcode`@% = @other +% @hashchar{} gets its own user-level command, because of #line. +@catcode`@& = @other @def@normalamp{&} +@catcode`@# = @other @def@normalhash{#} +@catcode`@% = @other @def@normalpercent{%} + +@let @hashchar = @normalhash @c Finally, make ` and ' active, so that txicodequoteundirected and @c txicodequotebacktick work right in, e.g., @w{@code{`foo'}}. If we |