diff options
| -rw-r--r-- | ChangeLog | 10 | ||||
| -rw-r--r-- | doc/gawk.info | 1523 | ||||
| -rw-r--r-- | doc/gawk.texi | 681 | ||||
| -rw-r--r-- | missing_d/ChangeLog | 4 | ||||
| -rw-r--r-- | missing_d/strftime.c | 2 | ||||
| -rw-r--r-- | pc/ChangeLog | 6 | ||||
| -rw-r--r-- | pc/config.h | 7 | ||||
| -rw-r--r-- | re.c | 10 | ||||
| -rw-r--r-- | replace.c | 7 | ||||
| -rw-r--r-- | test/ChangeLog | 5 | ||||
| -rw-r--r-- | test/funstack.awk | 12 | ||||
| -rw-r--r-- | test/gsubtst5.ok | 1 | ||||
| -rw-r--r-- | test/igncfs.awk | 2 | ||||
| -rw-r--r-- | test/longwrds.awk | 2 | ||||
| -rw-r--r-- | test/ofmtbig.awk | 3 | ||||
| -rw-r--r-- | test/subamp.awk | 2 |
16 files changed, 1192 insertions, 1085 deletions
@@ -1,3 +1,13 @@ +Mon Nov 29 21:59:21 2010 Arnold D. Robbins <arnold@skeeve.com> + + * re.c (check_bracket_exp): Add check and warning for ranges. + I may live to regret this. + +Mon Nov 29 20:09:18 2010 Eli Zaretskii <eliz@gnu.org> + + * replace.c [!HAVE_STRFTIME]: For __MINGW32__, define + HAVE_STRFTIME while compiling missing_d/strftime.c. + Thu Nov 25 20:12:28 2010 John Haque <j.eh@mchsi.com> * awkgram.y (grammar): Bug fix in delete for loop efficiency hack. diff --git a/doc/gawk.info b/doc/gawk.info index 70c63046..67e5f0f1 100644 --- a/doc/gawk.info +++ b/doc/gawk.info @@ -184,7 +184,6 @@ texts being (a) (see below), and with the Back-Cover Texts being (b) * Getline Notes:: Important things to know about `getline'. * Getline Summary:: Summary of `getline' Variants. -* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Command line directories:: What happens if you put a directory on the command line. * Print:: The `print' statement. @@ -256,6 +255,7 @@ texts being (a) (see below), and with the Back-Cover Texts being (b) * I/O And BEGIN/END:: I/O issues in BEGIN/END rules. * Empty:: The empty pattern, which matches every record. +* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Using Shell Variables:: How to use shell variables with `awk'. * Action Overview:: What goes into an action. @@ -2927,7 +2927,6 @@ have to be named on the `awk' command line (*note Getline::). * Multiple Line:: Reading multi-line records. * Getline:: Reading files under explicit program control using the `getline' function. -* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Command line directories:: What happens if you put a directory on the command line. @@ -4091,7 +4090,7 @@ feature of `RS' does not apply. It does apply to the default field separator of a single space: `FS = " "'. -File: gawk.info, Node: Getline, Next: BEGINFILE/ENDFILE, Prev: Multiple Line, Up: Reading Files +File: gawk.info, Node: Getline, Next: Command line directories, Prev: Multiple Line, Up: Reading Files 3.9 Explicit Input with `getline' ================================= @@ -4515,70 +4514,9 @@ VAR Table 3.1: getline Variants and What They Set -File: gawk.info, Node: BEGINFILE/ENDFILE, Next: Command line directories, Prev: Getline, Up: Reading Files - -3.10 The `BEGINFILE' and `ENDFILE' Special Patterns -=================================================== - - NOTE: This minor node describes a `gawk'-specific feature. - - Two special kinds of rule, `BEGINFILE' and `ENDFILE', give you -"hooks" into `gawk''s command-line file processing loop. As with the -`BEGIN' and `END' rules (*note BEGIN/END::), all `BEGINFILE' rules in a -program are merged, in the order they are read by `gawk', and all -`ENDFILE' rules are merged as well. +File: gawk.info, Node: Command line directories, Prev: Getline, Up: Reading Files - The body of the `BEGINFILE' rules is executed just before `gawk' -reads the first record from a file. `FILENAME' is set to the name of -the current file, and `FNR' is set to zero. - - The `BEGINFILE' rule provides you the opportunity for two tasks that -would otherwise be difficult or impossible to perform: - - 1. You can test if the file is readable. Normally, it is a fatal - error if a file named on the command line cannot be opened for - reading. However, you can bypass the fatal error and move on to - the next file on the command line. - - You do this by checking if the `ERRNO' variable is not the empty - string; if so, then `gawk' was not able to open the file. In this - case, your program can execute the `nextfile' statement (*note - Nextfile Statement::). This casuses `gawk' to skip the file - entirely. Otherwise, `gawk' exits with the usual fatal error. - - 2. If you have written extensions that modify the record handling (by - inserting an "open hook"), you can invoke them at this point, - before `gawk' has started processing the file. (This is a _very_ - advanced feature, currently used only by the XMLgawk project - (http://xgawk.sourceforge.net).) - - The `ENDFILE' rule is called when `gawk' has finished processing the -last record in an input file. For the last input file, it will be -called before any `END' rules. - - Normally, when an error occurs when reading input in the normal input -processing loop, the error is fatal. However, if an `ENDFILE' rule is -present, the error becomes non-fatal, and instead `ERRNO' is set. This -makes it possible to catch and process I/O errors at the level of the -`awk' program. - - The `next' statement (*note Next Statement::) is not allowed inside -either a `BEGINFILE' or and `ENDFILE' rule. The `nextfile' statement -(*note Nextfile Statement::) is allowed only inside a `BEGINFILE' rule, -but not inside an `ENDFILE' rule. - - The `getline' statement (*note Getline::) is restricted inside both -`BEGINFILE' and `ENDFILE'. Only the `getline VARIABLE < FILE' form is -allowed. - - `BEGINFILE' and `ENDFILE' are `gawk' extensions. In most other -`awk' implementations, or if `gawk' is in compatibility mode (*note -Options::), they are not special. - - -File: gawk.info, Node: Command line directories, Prev: BEGINFILE/ENDFILE, Up: Reading Files - -3.11 Directories On The Command Line +3.10 Directories On The Command Line ==================================== According to the POSIX standard, files named on the `awk' command line @@ -7270,6 +7208,7 @@ File: gawk.info, Node: Pattern Overview, Next: Using Shell Variables, Up: Pat * Ranges:: Pairs of patterns specify record ranges. * BEGIN/END:: Specifying initialization and cleanup rules. * Empty:: The empty pattern, which matches every record. +* BEGINFILE/ENDFILE:: Two special patterns for advanced control. Patterns in `awk' control the execution of rules--a rule is executed when its pattern matches the current input record. The following is a @@ -7296,6 +7235,11 @@ summary of the types of `awk' patterns: `EMPTY' The empty pattern matches every input record. (*Note Empty::.) +`BEGINFILE' +`ENDFILE' + Special patterns for you to supply startup or cleanup actions to + done on a per file basis. (*Note BEGINFILE/ENDFILE::.) + File: gawk.info, Node: Regexp Patterns, Next: Expression Patterns, Up: Pattern Overview @@ -7386,9 +7330,9 @@ contain the string `foo': The subexpressions of a Boolean operator in a pattern can be constant regular expressions, comparisons, or any other `awk' expressions. Range patterns are not expressions, so they cannot appear -inside Boolean patterns. Likewise, the special patterns `BEGIN' and -`END', which never match any input record, are not expressions and -cannot appear inside Boolean patterns. +inside Boolean patterns. Likewise, the special patterns `BEGIN', `END', +`BEGINFILE' and `ENDFILE', which never match any input record, are not +expressions and cannot appear inside Boolean patterns. File: gawk.info, Node: Ranges, Next: BEGIN/END, Prev: Expression Patterns, Up: Pattern Overview @@ -7453,9 +7397,7 @@ worked around; range patterns do not combine with other patterns: $ echo Yes | gawk '(/1/,/2/) || /Yes/' error--> gawk: cmd. line:1: (/1/,/2/) || /Yes/ - error--> gawk: cmd. line:1: ^ parse error - error--> gawk: cmd. line:2: (/1/,/2/) || /Yes/ - error--> gawk: cmd. line:2: ^ unexpected newline + error--> gawk: cmd. line:1: ^ syntax error File: gawk.info, Node: BEGIN/END, Next: Empty, Prev: Ranges, Up: Pattern Overview @@ -7563,7 +7505,7 @@ however, that Unix `awk', and possibly other implementations, do not. The third point follows from the first two. The meaning of `print' inside a `BEGIN' or `END' rule is the same as always: `print $0'. If -`$0' is the null string, then this prints an empty line. Many long +`$0' is the null string, then this prints an empty record. Many long time `awk' programmers use an unadorned `print' in `BEGIN' and `END' rules, to mean `print ""', relying on `$0' being null. Although one might generally get away with this in `BEGIN' rules, it is a very bad @@ -7579,7 +7521,7 @@ the input has been read. (*Note Next Statement::, and see *note Nextfile Statement::.) -File: gawk.info, Node: Empty, Prev: BEGIN/END, Up: Pattern Overview +File: gawk.info, Node: Empty, Next: BEGINFILE/ENDFILE, Prev: BEGIN/END, Up: Pattern Overview 6.1.5 The Empty Pattern ----------------------- @@ -7592,6 +7534,67 @@ input record. For example, the program: prints the first field of every record. +File: gawk.info, Node: BEGINFILE/ENDFILE, Prev: Empty, Up: Pattern Overview + +6.1.6 The `BEGINFILE' and `ENDFILE' Special Patterns +---------------------------------------------------- + + NOTE: This minor node describes a `gawk'-specific feature. + + Two special kinds of rule, `BEGINFILE' and `ENDFILE', give you +"hooks" into `gawk''s command-line file processing loop. As with the +`BEGIN' and `END' rules (*note BEGIN/END::), all `BEGINFILE' rules in a +program are merged, in the order they are read by `gawk', and all +`ENDFILE' rules are merged as well. + + The body of the `BEGINFILE' rules is executed just before `gawk' +reads the first record from a file. `FILENAME' is set to the name of +the current file, and `FNR' is set to zero. + + The `BEGINFILE' rule provides you the opportunity for two tasks that +would otherwise be difficult or impossible to perform: + + 1. You can test if the file is readable. Normally, it is a fatal + error if a file named on the command line cannot be opened for + reading. However, you can bypass the fatal error and move on to + the next file on the command line. + + You do this by checking if the `ERRNO' variable is not the empty + string; if so, then `gawk' was not able to open the file. In this + case, your program can execute the `nextfile' statement (*note + Nextfile Statement::). This casuses `gawk' to skip the file + entirely. Otherwise, `gawk' exits with the usual fatal error. + + 2. If you have written extensions that modify the record handling (by + inserting an "open hook"), you can invoke them at this point, + before `gawk' has started processing the file. (This is a _very_ + advanced feature, currently used only by the XMLgawk project + (http://xgawk.sourceforge.net).) + + The `ENDFILE' rule is called when `gawk' has finished processing the +last record in an input file. For the last input file, it will be +called before any `END' rules. + + Normally, when an error occurs when reading input in the normal input +processing loop, the error is fatal. However, if an `ENDFILE' rule is +present, the error becomes non-fatal, and instead `ERRNO' is set. This +makes it possible to catch and process I/O errors at the level of the +`awk' program. + + The `next' statement (*note Next Statement::) is not allowed inside +either a `BEGINFILE' or and `ENDFILE' rule. The `nextfile' statement +(*note Nextfile Statement::) is allowed only inside a `BEGINFILE' rule, +but not inside an `ENDFILE' rule. + + The `getline' statement (*note Getline::) is restricted inside both +`BEGINFILE' and `ENDFILE'. Only the `getline VARIABLE < FILE' form is +allowed. + + `BEGINFILE' and `ENDFILE' are `gawk' extensions. In most other +`awk' implementations, or if `gawk' is in compatibility mode (*note +Options::), they are not special. + + File: gawk.info, Node: Using Shell Variables, Next: Action Overview, Prev: Pattern Overview, Up: Patterns and Actions 6.2 Using Shell Variables in Programs @@ -7607,7 +7610,7 @@ program. variable's value into the program inside the script. For example, in the following program: - echo -n "Enter search pattern: " + printf "Enter search pattern: " read pattern awk "/$pattern/ "'{ nmatches++ } END { print nmatches, "found" }' /path/to/data @@ -7628,7 +7631,7 @@ variable's value. Then use dynamic regexps to match the pattern (*note Computed Regexps::). The following shows how to redo the previous example using this technique: - echo -n "Enter search pattern: " + printf "Enter search pattern: " read pattern awk -v pat="$pattern" '$0 ~ pat { nmatches++ } END { print nmatches, "found" }' /path/to/data @@ -7655,8 +7658,8 @@ which (but not both) may be omitted. The purpose of the "action" is to tell `awk' what to do once a match for the pattern is found. Thus, in outline, an `awk' program generally looks like this: - [PATTERN] [{ ACTION }] - [PATTERN] [{ ACTION }] + [PATTERN] { ACTION } + PATTERN [{ ACTION }] ... function NAME(ARGS) { ... } ... @@ -7709,7 +7712,7 @@ File: gawk.info, Node: Statements, Next: Built-in Variables, Prev: Action Ove "Control statements", such as `if', `while', and so on, control the flow of execution in `awk' programs. Most of the control statements in -`awk' are patterned on similar statements in C. +`awk' are patterned after similar statements in C. All the control statements start with special keywords, such as `if' and `while', to distinguish them from simple expressions. Many control @@ -7802,7 +7805,8 @@ is never executed and `awk' continues with the statement following the loop. This example prints the first three fields of each record, one per line: - awk '{ i = 1 + awk '{ + i = 1 while (i <= 3) { print $i i++ @@ -7847,7 +7851,8 @@ Contrast this with the corresponding `while' statement: This statement does not execute BODY even once if the CONDITION is false to begin with. The following is an example of a `do' statement: - { i = 1 + { + i = 1 do { print $0 i++ @@ -7880,7 +7885,8 @@ INCREMENT. Typically, INITIALIZATION sets a variable to either zero or one, INCREMENT adds one to it, and CONDITION compares it against the desired number of iterations. For example: - awk '{ for (i = 1; i <= 3; i++) + awk '{ + for (i = 1; i <= 3; i++) print $i }' inventory-shipped @@ -7969,7 +7975,7 @@ statement looks like this: } Control flow in the `switch' statement works as it does in C. Once a -match to a given case is made, case statement bodies are executed until +match to a given case is made, the case statement bodies execute until a `break', `continue', `next', `nextfile' or `exit' is encountered, or the end of the `switch' statement itself. For example: @@ -7997,8 +8003,8 @@ is executed and then falls through into the `default' section, executing its `print' statement. In turn, the -1 case will also be executed since the `default' does not halt execution. - This feature is a `gawk' extension, and is not available in POSIX -`awk'. + This `switch' statement is a `gawk' extension. If `gawk' is in +compatibility mode (*note Options::), it is not available. File: gawk.info, Node: Break Statement, Next: Continue Statement, Prev: Switch Statement, Up: Statements @@ -8013,9 +8019,10 @@ divisor of any integer, and also identifies prime numbers: # find smallest divisor of num { num = $1 - for (div = 2; div*div <= num; div++) + for (div = 2; div * div <= num; div++) { if (num % div == 0) break + } if (num % div == 0) printf "Smallest divisor of %d is %d\n", num, div else @@ -8040,19 +8047,22 @@ Statement::.) printf "Smallest divisor of %d is %d\n", num, div break } - if (div*div > num) { + if (div * div > num) { printf "%d is prime\n", num break } } } + The `break' statement is also used to break out of the `switch' +statement. This is discussed in *note Switch Statement::. + The `break' statement has no meaning when used outside the body of a -loop. However, although it was never documented, historical -implementations of `awk' treated the `break' statement outside of a -loop as if it were a `next' statement (*note Next Statement::). Recent -versions of Unix `awk' no longer allow this usage, nor does `gawk'. -(d.c.) +loop or `switch'. However, although it was never documented, +historical implementations of `awk' treated the `break' statement +outside of a loop as if it were a `next' statement (*note Next +Statement::). Recent versions of Unix `awk' no longer allow this usage, +nor does `gawk'. (d.c.) File: gawk.info, Node: Continue Statement, Next: Next Statement, Prev: Break Statement, Up: Statements @@ -8060,7 +8070,7 @@ File: gawk.info, Node: Continue Statement, Next: Next Statement, Prev: Break 6.4.7 The `continue' Statement ------------------------------ -As with `break', the `continue' statement is used only inside `for', +Similar to `break', the `continue' statement is used only inside `for', `while', and `do' loops. It skips over the rest of the loop body, causing the next cycle around the loop to begin immediately. Contrast this with `break', which jumps out of the loop altogether. @@ -8143,15 +8153,19 @@ see the bad record. The error message is redirected to the standard error output stream, as error messages should be. For more detail see *note Special Files::. + If the `next' statement causes the end of the input to be reached, +then the code in any `END' rules is executed. *Note BEGIN/END::. + + The `next' statement is not inside `BEGINFILE' and `ENDFILE' rules. +*Note BEGINFILE/ENDFILE::. + According to the POSIX standard, the behavior is undefined if the `next' statement is used in a `BEGIN' or `END' rule. `gawk' treats it as a syntax error. Although POSIX permits it, some other `awk' implementations don't allow the `next' statement inside function bodies (*note User-defined::). Just as with any other `next' statement, a `next' statement inside a function body reads the next record and -starts processing it with the first rule in the program. If the `next' -statement causes the end of the input to be reached, then the code in -any `END' rules is executed. *Note BEGIN/END::. +starts processing it with the first rule in the program. File: gawk.info, Node: Nextfile Statement, Next: Exit Statement, Prev: Next Statement, Up: Statements @@ -8182,6 +8196,10 @@ Normally, in order to move on to the next data file, a program has to continue scanning the unwanted records. The `nextfile' statement accomplishes this much more efficiently. + In addition, `nextfile' is useful inside a `BEGINFILE' rule to skip +over a file that would otherwise cause `gawk' to exit with a fatal +error. *Note BEGINFILE/ENDFILE::. + While one might think that `close(FILENAME)' would accomplish the same as `nextfile', this isn't true. `close()' is reserved for closing files, pipes, and coprocesses that are opened with redirections. It is @@ -8199,13 +8217,6 @@ Versions::) also supports `nextfile'. However, it doesn't allow the and starts processing it with the first rule in the program, just as any other `nextfile' statement. - *Caution:* Versions of `gawk' prior to 3.0 used two words (`next -file') for the `nextfile' statement. In version 3.0, this was changed -to one word, because the treatment of `file' was inconsistent. When it -appeared after `next', `file' was a keyword; otherwise, it was a -regular identifier. The old usage is no longer accepted; `next file' -generates a syntax error. - The `nextfile' statement has a special purpose when used inside a `BEGINFILE' rule; see *note BEGINFILE/ENDFILE::. @@ -8225,8 +8236,8 @@ ignored. The `exit' statement is written as follows: program stops processing everything immediately. No input records are read. However, if an `END' rule is present, as part of executing the `exit' statement, the `END' rule is executed (*note BEGIN/END::). If -`exit' is used as part of an `END' rule, it causes the program to stop -immediately. +`exit' is used in the body of an `END' rule, it causes the program to +stop immediately. An `exit' statement that is not part of a `BEGIN' or `END' rule stops the execution of any further automatic rules for the current @@ -8352,8 +8363,8 @@ specific to `gawk' are marked with a pound sign (`#'). record. If the value is the null string (`""'), then each character in the record becomes a separate field. (This behavior is a `gawk' extension. POSIX `awk' does not specify the behavior - when `FS' is the null string.) *FIXME: NEXT ED:* Mark as common - extension. + when `FS' is the null string. Nonetheless, some other versions of + `awk' also treat `""' specially.) The default value is `" "', a string consisting of a single space. As a special exception, this value means that any sequence of @@ -8366,10 +8377,10 @@ specific to `gawk' are marked with a pound sign (`#'). awk -F, 'PROGRAM' INPUT-FILES - If `gawk' is using `FIELDWIDTHS' for field splitting, assigning a - value to `FS' causes `gawk' to return to the normal, `FS'-based - field splitting. An easy way to do this is to simply say `FS = - FS', perhaps with an explanatory comment. + If `gawk' is using `FIELDWIDTHS' or `FPAT' for field splitting, + assigning a value to `FS' causes `gawk' to return to the normal, + `FS'-based field splitting. An easy way to do this is to simply + say `FS = FS', perhaps with an explanatory comment. `IGNORECASE #' If `IGNORECASE' is nonzero or non-null, then all string comparisons @@ -8496,7 +8507,7 @@ with a pound sign (`#'). The value of `ARGV[0]' can vary from system to system. Also, you should note that the program text is _not_ included in `ARGV', nor are any of `awk''s command-line options. *Note ARGC and ARGV::, - for information about how `awk' uses these variables. + for information about how `awk' uses these variables. (d.c.) `ARGIND #' The index in `ARGV' of the current file being processed. Every @@ -8519,7 +8530,7 @@ with a pound sign (`#'). Options::), it is not special. `ENVIRON' - An associative array that contains the values of the environment. + An associative array containing the values of the environment. The array indices are the environment variable names; the elements are the values of the particular environment variables. For example, `ENVIRON["HOME"]' might be `/home/arnold'. Changing this @@ -8562,7 +8573,7 @@ with a pound sign (`#'). `FNR' The current record number in the current file. `FNR' is - incremented each time a new record is read (*note Getline::). It + incremented each time a new record is read (*note Records::). It is reinitialized to zero each time a new input file is started. `NF' @@ -8587,10 +8598,10 @@ with a pound sign (`#'). alphabetically) are guaranteed to be available: `PROCINFO["egid"]' - The value of the `getegid' system call. + The value of the `getegid()' system call. `PROCINFO["euid"]' - The value of the `geteuid' system call. + The value of the `geteuid()' system call. `PROCINFO["FS"]' This is `"FS"' if field splitting with `FS' is in effect, @@ -8599,7 +8610,7 @@ with a pound sign (`#'). effect. `PROCINFO["gid"]' - The value of the `getgid' system call. + The value of the `getgid()' system call. `PROCINFO["pgrpid"]' The process group ID of the current process. @@ -8611,17 +8622,20 @@ with a pound sign (`#'). The parent process ID of the current process. `PROCINFO["uid"]' - The value of the `getuid' system call. + The value of the `getuid()' system call. `PROCINFO["version"]' - The version of `gawk'. This is available from version 3.1.4 - and later. + The version of `gawk'. 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 these elements (*note Reference to Elements::). + The `PROCINFO' array is also used to cause coprocesses to + communicate over pseudo-ttys instead of through two-way pipes; + this is discussed further in *note Two-way I/O::. + This array is a `gawk' extension. In other `awk' implementations, or if `gawk' is in compatibility mode (*note Options::), it is not special. @@ -8653,8 +8667,8 @@ Advanced Notes: Changing `NR' and `FNR' `awk' increments `NR' and `FNR' each time it reads a record, instead of setting them to the absolute value of the number of records read. This means that a program can change these variables and their new values -are incremented for each record. (d.c.) This is demonstrated in the -following example: +are incremented for each record. (d.c.) The following example shows +this: $ echo '1 > 2 @@ -8695,19 +8709,22 @@ information contained in `ARGC' and `ARGV': In this example, `ARGV[0]' contains `awk', `ARGV[1]' contains `inventory-shipped', and `ARGV[2]' contains `BBS-list'. Notice that -the `awk' program is not entered in `ARGV'. The other special -command-line options, with their arguments, are also not entered. This -includes variable assignments done with the `-v' option (*note -Options::). Normal variable assignments on the command line _are_ -treated as arguments and do show up in the `ARGV' array: - - $ cat showargs.awk - -| BEGIN { - -| printf "A=%d, B=%d\n", A, B - -| for (i = 0; i < ARGC; i++) - -| printf "\tARGV[%d] = %s\n", i, ARGV[i] - -| } - -| END { printf "A=%d, B=%d\n", A, B } +the `awk' program is not entered in `ARGV'. The other command-line +options, with their arguments, are also not entered. This includes +variable assignments done with the `-v' option (*note Options::). +Normal variable assignments on the command line _are_ treated as +arguments and do show up in the `ARGV' array. Given the following +program in a file named `showargs.awk': + + BEGIN { + printf "A=%d, B=%d\n", A, B + for (i = 0; i < ARGC; i++) + printf "\tARGV[%d] = %s\n", i, ARGV[i] + } + END { printf "A=%d, B=%d\n", A, B } + +Running it produces the following: + $ awk -v A=1 -f showargs.awk B=2 /dev/null -| A=1, B=0 -| ARGV[0] = awk @@ -8737,8 +8754,7 @@ elements from `ARGV' (*note Delete::). actual processing of the input begins. *Note Split Program::, and see *note Tee Program::, for examples of each way of removing elements from `ARGV'. The following fragment processes `ARGV' in order to examine, -and then remove, command-line options: *FIXME: NEXT ED:* Add xref to -rewind() function. +and then remove, command-line options: BEGIN { for (i = 1; i < ARGC; i++) { @@ -8780,15 +8796,16 @@ File: gawk.info, Node: Arrays, Next: Functions, Prev: Patterns and Actions, ***************** An "array" is a table of values called "elements". The elements of an -array are distinguished by their indices. "Indices" may be either +array are distinguished by their "indices". Indices may be either numbers or strings. This major node describes how arrays work in `awk', how to use array elements, how to scan through every element in an array, and how to remove array elements. It also describes how `awk' simulates multidimensional arrays, as well as some of the less obvious points -about array usage. The major node finishes with a discussion of -`gawk''s facility for sorting an array based on its indices. +about array usage. The major node moves on to discuss `gawk''s facility +for sorting arrays, and ends with a brief description of `gawk''s +ability to support true multidimensional arrays. `awk' maintains a single set of names that may be used for naming variables, arrays, and functions (*note User-defined::). Thus, you @@ -8833,7 +8850,7 @@ File: gawk.info, Node: Array Intro, Next: Reference to Elements, Up: Array Ba 7.1.1 Introduction to Arrays ---------------------------- - Doing linear scans over an associative array is like tryinng to + Doing linear scans over an associative array is like trying to club someone to death with a loaded Uzi. Larry Wall @@ -8868,7 +8885,6 @@ declared.) example, conceptually, if the element values are 8, `"foo"', `""', and 30: - *FIXME: NEXT ED:* Use real images here +---------+---------+--------+---------+ | 8 | "foo" | "" | 30 | Value +---------+---------+--------+---------+ @@ -8882,10 +8898,10 @@ position with zero elements before it. that each array is a collection of pairs: an index and its corresponding array element value: - Element 3 Value 30 - Element 1 Value "foo" - Element 0 Value 8 - Element 2 Value "" + Index 3 Value 30 + Index 1 Value "foo" + Index 0 Value 8 + Index 2 Value "" The pairs are shown in jumbled order because their order is irrelevant. @@ -8893,11 +8909,11 @@ The pairs are shown in jumbled order because their order is irrelevant. at any time. For example, suppose a tenth element is added to the array whose value is `"number ten"'. The result is: - Element 10 Value "number ten" - Element 3 Value 30 - Element 1 Value "foo" - Element 0 Value 8 - Element 2 Value "" + Index 10 Value "number ten" + Index 3 Value 30 + Index 1 Value "foo" + Index 0 Value 8 + Index 2 Value "" Now the array is "sparse", which just means some indices are missing. It has elements 0-3 and 10, but doesn't have elements 4, 5, 6, 7, 8, or @@ -8908,10 +8924,10 @@ have to be positive integers. Any number, or even a string, can be an index. For example, the following is an array that translates words from English to French: - Element "dog" Value "chien" - Element "cat" Value "chat" - Element "one" Value "un" - Element 1 Value "un" + Index "dog" Value "chien" + Index "cat" Value "chat" + Index "one" Value "un" + Index 1 Value "un" Here we decided to translate the number one in both spelled-out and numeric form--thus illustrating that a single array can have both @@ -8950,9 +8966,21 @@ array `foo' at index `4.3'. A reference to an array element that has no recorded value yields a value of `""', the null string. This includes elements that have not been assigned any value as well as elements that have been deleted -(*note Delete::). Such a reference automatically creates that array -element, with the null string as its value. (In some cases, this is -unfortunate, because it might waste memory inside `awk'.) +(*note Delete::). + + NOTE: A reference to an element that does not exist + _automatically_ creates that array element, with the null string + as its value. (In some cases, this is unfortunate, because it + might waste memory inside `awk'.) + + Novice `awk' programmers often make the mistake of checking if an + element exists by checking if the value is empty: + + # Check if "foo" exists in a: Incorrect! + if (a["foo"] != "") ... + + This is incorrect, since this will _create_ `a["foo"]' if it + didn't exist before! To determine whether an element exists in an array at a certain index, use the following expression: @@ -9167,7 +9195,9 @@ array and then returns. delete an array and then use the array's name as a scalar (i.e., a regular variable). For example, the following does not work: - a[1] = 3; delete a; a = 3 + a[1] = 3 + delete a + a = 3 ---------- Footnotes ---------- @@ -9179,7 +9209,7 @@ File: gawk.info, Node: Numeric Array Subscripts, Next: Uninitialized Subscript 7.3 Using Numbers to Subscript Arrays ===================================== -An important aspect about arrays to remember is that _array subscripts +An important aspect to remember about arrays is that _array subscripts are always strings_. When a numeric value is used as a subscript, it is converted to a string value before being used for subscripting (*note Conversion::). This means that the value of the built-in @@ -9201,8 +9231,8 @@ string value `"12.153"' (using the default conversion value of assigned the value one. The program then changes the value of `CONVFMT'. The test `(xyz in data)' generates a new string value from `xyz'--this time `"12.15"'--because the value of `CONVFMT' only allows -two significant digits. This test fails, since `"12.15"' is a -different string from `"12.153"'. +two significant digits. This test fails, since `"12.15"' is different +from `"12.153"'. According to the rules for conversions (*note Conversion::), integer values are always converted to strings as integers, no matter what the @@ -9221,8 +9251,8 @@ the same element! As with many things in `awk', the majority of the time things work as one would expect them to. But it is useful to have a precise -knowledge of the actual rules which sometimes can have a subtle effect -on your programs. +knowledge of the actual rules since they can sometimes have a subtle +effect on your programs. File: gawk.info, Node: Uninitialized Subscripts, Next: Multi-dimensional, Prev: Numeric Array Subscripts, Up: Arrays @@ -9247,9 +9277,10 @@ might look like this: Unfortunately, the very first line of input data did not come out in the output! - At first glance, this program should have worked. The variable -`lines' is uninitialized, and uninitialized variables have the numeric -value zero. So, `awk' should have printed the value of `l[0]'. + Upon first glance, we would think that this program should have +worked. The variable `lines' is uninitialized, and uninitialized +variables have the numeric value zero. So, `awk' should have printed +the value of `l[0]'. The issue here is that subscripts for `awk' arrays are _always_ strings. Uninitialized variables, when used as strings, have the value @@ -9436,41 +9467,24 @@ and then sorts `dest', destroying its indices. However, the `source' array is not affected. Often, what's needed is to sort on the values of the _indices_ -instead of the values of the elements. To do that, starting with -`gawk' 3.1.2, use the `asorti()' function. The interface is identical -to that of `asort()', except that the index values are used for -sorting, and become the values of the result array: +instead of the values of the elements. To do that, use the `asorti()' +function. The interface is identical to that of `asort()', except that +the index values are used for sorting, and become the values of the +result array: { source[$0] = some_func($0) } END { n = asorti(source, dest) for (i = 1; i <= n; i++) { - DO SOMETHING WITH dest[i] Work with sorted indices directly + Work with sorted indices directly: + DO SOMETHING WITH dest[i] ... - DO SOMETHING WITH source[dest[i]] Access original array via sorted indices + Access original array via sorted indices: + DO SOMETHING WITH source[dest[i]] } } - If your version of `gawk' is 3.1.0 or 3.1.1, you don't have -`asorti()'. Instead, use a helper array to hold the sorted index -values, and then access the original array's elements. It works in the -following way: - - POPULATE THE ARRAY data - # copy indices - j = 1 - for (i in data) { - ind[j] = i # index value becomes element value - j++ - } - n = asort(ind) # index values are now sorted - for (i = 1; i <= n; i++) { - DO SOMETHING WITH ind[i] Work with sorted indices directly - ... - DO SOMETHING WITH data[ind[i]] Access original array via sorted indices - } - Sorting the array by replacing the indices provides maximal flexibility. To traverse the elements in decreasing order, use a loop that goes from N down to 1, either over the elements or over the @@ -9487,9 +9501,15 @@ to `ind', there is only one copy of the actual index strings. comparison rules." Because `IGNORECASE' affects string comparisons, the value of `IGNORECASE' also affects sorting for both `asort()' and `asorti()'. Note also that the locale's sorting order does _not_ come -into play; comparisons are based on character values only. Caveat +into play; comparisons are based on character values only.(1) Caveat Emptor. + ---------- Footnotes ---------- + + (1) This is true because locale-based comparison occurs only when in +POSIX compatibility mode, and since `asort()' and `asorti()' are `gawk' +extensions, they are not available in that case. + File: gawk.info, Node: Arrays of Arrays, Prev: Array Sorting, Up: Arrays @@ -9605,7 +9625,7 @@ File: gawk.info, Node: Functions, Next: Internationalization, Prev: Arrays, This major node describes `awk''s built-in functions, which fall into three categories: numeric, string, and I/O. `gawk' provides additional groups of functions to work with values that represent time, do bit -manipulation, and internationalize and localize programs. +manipulation, sort arrays, and internationalize and localize programs. Besides the built-in functions, `awk' has provisions for writing new functions that the rest of a program can use. The second half of this @@ -9695,39 +9715,32 @@ The following list describes all of the built-in functions that work with numbers. Optional parameters are enclosed in square brackets ([ ]): -`int(X)' - This returns the nearest integer to X, located between X and zero - and truncated toward zero. - - For example, `int(3)' is 3, `int(3.9)' is 3, `int(-3.9)' is -3, - and `int(-3)' is -3 as well. +`atan2(Y, X)' + Return the arctangent of `Y / X' in radians. -`sqrt(X)' - This returns the positive square root of X. `gawk' reports an - error if X is negative. Thus, `sqrt(4)' is 2. +`cos(X)' + Return the cosine of X, with X in radians. `exp(X)' - This returns the exponential of X (`e ^ X') or reports an error if - X is out of range. The range of values X can have depends on your + Return the exponential of X (`e ^ X') or report an error if X is + out of range. The range of values X can have depends on your machine's floating-point representation. -`log(X)' - This returns the natural logarithm of X, if X is positive; - otherwise, it reports an error. - -`sin(X)' - This returns the sine of X, with X in radians. +`int(X)' + Return the nearest integer to X, located between X and zero and + truncated toward zero. -`cos(X)' - This returns the cosine of X, with X in radians. + For example, `int(3)' is 3, `int(3.9)' is 3, `int(-3.9)' is -3, + and `int(-3)' is -3 as well. -`atan2(Y, X)' - This returns the arctangent of `Y / X' in radians. +`log(X)' + Return the natural logarithm of X, if X is positive; otherwise, + report an error. `rand()' - This returns a random number. The values of `rand()' are - uniformly distributed between zero and one. The value could be - zero but is never one.(1) + Return a random number. The values of `rand()' are uniformly + distributed between zero and one. The value could be zero but is + never one.(1) Often random integers are needed instead. Following is a user-defined function that can be used to obtain a random @@ -9757,25 +9770,32 @@ brackets ([ ]): *Caution:* In most `awk' implementations, including `gawk', `rand()' starts generating numbers from the same starting number, - or "seed", each time you run `awk'. Thus, a program generates the - same results each time you run it. The numbers are random within - one `awk' run but predictable from run to run. This is convenient - for debugging, but if you want a program to do different things - each time it is used, you must change the seed to a value that is - different in each run. To do this, use `srand()'. + or "seed", each time you run `awk'.(2) Thus, a program generates + the same results each time you run it. The numbers are random + within one `awk' run but predictable from run to run. This is + convenient for debugging, but if you want a program to do + different things each time it is used, you must change the seed to + a value that is different in each run. To do this, use `srand()'. + +`sin(X)' + Return the sine of X, with X in radians. + +`sqrt(X)' + Return the positive square root of X. `gawk' reports an error if + X is negative. Thus, `sqrt(4)' is 2. `srand([X])' - The function `srand()' sets the starting point, or seed, for - generating random numbers to the value X. + Set the starting point, or seed, for generating random numbers to + the value X. Each seed value leads to a particular sequence of random - numbers.(2) Thus, if the seed is set to the same value a second + numbers.(3) Thus, if the seed is set to the same value a second time, the same sequence of random numbers is produced again. - Different `awk' implementations use different random-number - generators internally. Don't expect the same `awk' program to - produce the same series of random numbers when executed by - different versions of `awk'. + CAUTION: Different `awk' implementations use different + random-number generators internally. Don't expect the same + `awk' program to produce the same series of random numbers + when executed by different versions of `awk'. If the argument X is omitted, as in `srand()', then the current date and time of day are used for a seed. This is the way to get @@ -9790,10 +9810,12 @@ brackets ([ ]): (1) The C version of `rand()' is known to produce fairly poor sequences of random numbers. However, nothing requires that an `awk' implementation use the C `rand()' to implement the `awk' version of -`rand()'. In fact, `gawk' uses the BSD `random' function, which is +`rand()'. In fact, `gawk' uses the BSD `random()' function, which is considerably better than `rand()', to produce random numbers. - (2) Computer-generated random numbers really are not truly random. + (2) `mawk' uses a different seed each time. + + (3) Computer-generated random numbers really are not truly random. They are technically known as "pseudorandom." This means that while the numbers in a sequence appear to be random, you can in fact generate the same sequence of random numbers over and over again. @@ -9816,15 +9838,14 @@ with a pound sign (`#'): `gensub()'. `asort(SOURCE [, DEST]) #' - `asort()' is a `gawk'-specific extension, returning the number of - elements in the array SOURCE. The contents of SOURCE are sorted - using `gawk''s normal rules for comparing values (in particular, - `IGNORECASE' affects the sorting) and the indices of the sorted - values of SOURCE are replaced with sequential integers starting - with one. If the optional array DEST is specified, then SOURCE is - duplicated into DEST. DEST is then sorted, leaving the indices of - SOURCE unchanged. For example, if the contents of `a' are as - follows: + Return the number of elements in the array SOURCE. `gawk' sorts + the contents of SOURCE using the normal rules for comparing values + (in particular, `IGNORECASE' affects the sorting) and replaces the + indices of the sorted values of SOURCE with sequential integers + starting with one. If the optional array DEST is specified, then + SOURCE is duplicated into DEST. DEST is then sorted, leaving the + indices of SOURCE unchanged. For example, if the contents of `a' + are as follows: a["last"] = "de" a["first"] = "sac" @@ -9845,22 +9866,20 @@ with a pound sign (`#'): in compatibility mode (*note Options::). `asorti(SOURCE [, DEST]) #' - `asorti()' is a `gawk'-specific extension, returning the number of - elements in the array SOURCE. It works similarly to `asort()', - however, the _indices_ are sorted, instead of the values. As - array indices are always strings, the comparison performed is - always a string comparison. (Here too, `IGNORECASE' affects the - sorting.) + Return the number of elements in the array SOURCE. It works + similarly to `asort()', however, the _indices_ are sorted, instead + of the values. As array indices are always strings, the + comparison performed is always a string comparison. (Here too, + `IGNORECASE' affects the sorting.) The `asorti()' function is described in more detail in *note Array - Sorting::. It was added in `gawk' 3.1.2. `asorti()' is a `gawk' - extension; it is not available in compatibility mode (*note - Options::). + Sorting::. `asorti()' is a `gawk' extension; it is not available + in compatibility mode (*note Options::). `index(IN, FIND)' - This searches the string IN for the first occurrence of the string - FIND, and returns the position in characters where that occurrence - begins in the string IN. Consider the following example: + Search the string IN for the first occurrence of the string FIND, + and return the position in characters where that occurrence begins + in the string IN. Consider the following example: $ awk 'BEGIN { print index("peanut", "an") }' -| 3 @@ -9869,8 +9888,8 @@ with a pound sign (`#'): string indices in `awk' start at one.) `length([STRING])' - This returns the number of characters in STRING. If STRING is a - number, the length of the digit string representing that number is + Return the number of characters in STRING. If STRING is a number, + the length of the digit string representing that number is returned. For example, `length("abcde")' is 5. By contrast, `length(15 * 35)' works out to 3. In this example, 15 * 35 = 525, and 525 is then converted to the string `"525"', which has three @@ -9899,25 +9918,24 @@ with a pound sign (`#'): If `--lint' has been specified on the command line, `gawk' issues a warning about this. - Beginning with `gawk' version 3.1.5, when supplied an array - argument, the `length()' function returns the number of elements - in the array. This is less useful than it might seem at first, as - the array is not guaranteed to be indexed from one to the number - of elements in it. If `--lint' is provided on the command line - (*note Options::), `gawk' warns that passing an array argument is - not portable. If `--posix' is supplied, using an array argument - is a fatal error (*note Arrays::). + With `gawk' and several other `awk' implementations, when supplied + an array argument, the `length()' function returns the number of + elements in the array. This is less useful than it might seem at + first, as the array is not guaranteed to be indexed from one to + the number of elements in it. If `--lint' is provided on the + command line (*note Options::), `gawk' warns that passing an array + argument is not portable. If `--posix' is supplied, using an + array argument is a fatal error (*note Arrays::). `match(STRING, REGEXP [, ARRAY])' - The `match()' function searches STRING for the longest, leftmost - substring matched by the regular expression, REGEXP. It returns - the character position, or "index", at which that substring begins - (one, if it starts at the beginning of STRING). If no match is - found, it returns zero. + Search STRING for the longest, leftmost substring matched by the + regular expression, REGEXP and return the character position, or + "index", at which that substring begins (one, if it starts at the + beginning of STRING). If no match is found, return zero. The REGEXP argument may be either a regexp constant (`/.../') or a string constant (`"..."'). In the latter case, the string is - treated as a regexp to be matched. *note Computed Regexps::, for a + treated as a regexp to be matched. *Note Computed Regexps::, for a discussion of the difference between the two forms, and the implications for writing your program correctly. @@ -9971,12 +9989,11 @@ with a pound sign (`#'): $ echo foooobazbarrrrr | > gawk '{ match($0, /(fo+).+(bar*)/, arr) - > print arr[1], arr[2] }' + > print arr[1], arr[2] }' -| foooo barrrrr - In addition, beginning with `gawk' 3.1.2, multidimensional - subscripts are available providing the start index and length of - each matched subexpression: + In addition, multidimensional subscripts are available providing + the start index and length of each matched subexpression: $ echo foooobazbarrrrr | > gawk '{ match($0, /(fo+).+(bar*)/, arr) @@ -9997,14 +10014,14 @@ with a pound sign (`#'): compatibility mode (*note Options::), using a third argument is a fatal error. -`patsplit(STRING, ARRAY [, FIELDPAT [, SEPS ] ])' - This function divides STRING into pieces defined by FIELDPAT and - stores the pieces in ARRAY and the separator strings in the SEPS - array. The first piece is stored in `ARRAY[1]', the second piece - in `ARRAY[2]', and so forth. The string value of the third - argument, FIELDPAT, is a regexp describing the fields in STRING - (just as `FPAT' is a regexp describing the fields in input - records). If FIELDPAT is omitted, the value of `FPAT' is used. +`patsplit(STRING, ARRAY [, FIELDPAT [, SEPS ] ]) #' + Divide STRING into pieces defined by FIELDPAT and store the pieces + in ARRAY and the separator strings in the SEPS array. The first + piece is stored in `ARRAY[1]', the second piece in `ARRAY[2]', and + so forth. The third argument, FIELDPAT, is a regexp describing + the fields in STRING (just as `FPAT' is a regexp describing the + fields in input records). It may be either a regexp constant or a + string. If FIELDPAT is omitted, the value of `FPAT' is used. `patsplit()' returns the number of elements created. `SEPS[I]' is the separator string between `ARRAY[I]' and `ARRAY[I+1]'. Any leading separator will be in `SEPS[0]'. @@ -10012,6 +10029,12 @@ with a pound sign (`#'): The `patsplit()' function splits strings into pieces in a manner similar to the way input lines are split into fields using `FPAT'. + Before splitting the string, `patsplit()' deletes any previously + existing elements in the arrays ARRAY and SEPS. + + The `patsplit()' function is a `gawk' extension. In compatibility + mode (*note Options::), it is not available. + `split(STRING, ARRAY [, FIELDSEP [, SEPS ] ])' This function divides STRING into pieces separated by FIELDSEP and stores the pieces in ARRAY and the separator strings in the SEPS @@ -11678,17 +11701,17 @@ to force it to be a string value.) Here is the result of running the program: $ gawk -f indirectcall.awk class_data1 - => Biology 101: - => sum: <352.8> - => average: <88.2> - => - => Chemistry 305: - => sum: <356.4> - => average: <89.1> - => - => English 401: - => sum: <376.1> - => average: <94.025> + -| Biology 101: + -| sum: <352.8> + -| average: <88.2> + -| + -| Chemistry 305: + -| sum: <356.4> + -| average: <89.1> + -| + -| English 401: + -| sum: <376.1> + -| average: <94.025> The ability to use indirect function calls is more powerful than you may think at first. The C and C++ languages provide "function @@ -11808,23 +11831,23 @@ names of the two comparison functions: Finally, here are the results when the enhanced program is run: $ gawk -f quicksort.awk -f indirectcall.awk class_data2 - => Biology 101: - => sum: <352.8> - => average: <88.2> - => sort: <78.5 87.0 92.4 94.9> - => rsort: <94.9 92.4 87.0 78.5> - => - => Chemistry 305: - => sum: <356.4> - => average: <89.1> - => sort: <75.2 88.2 94.7 98.3> - => rsort: <98.3 94.7 88.2 75.2> - => - => English 401: - => sum: <376.1> - => average: <94.025> - => sort: <87.1 93.4 95.6 100.0> - => rsort: <100.0 95.6 93.4 87.1> + -| Biology 101: + -| sum: <352.8> + -| average: <88.2> + -| sort: <78.5 87.0 92.4 94.9> + -| rsort: <94.9 92.4 87.0 78.5> + -| + -| Chemistry 305: + -| sum: <356.4> + -| average: <89.1> + -| sort: <75.2 88.2 94.7 98.3> + -| rsort: <98.3 94.7 88.2 75.2> + -| + -| English 401: + -| sum: <376.1> + -| average: <94.025> + -| sort: <87.1 93.4 95.6 100.0> + -| rsort: <100.0 95.6 93.4 87.1> Remember that you must supply a leading `@' in front of an indirect function call. @@ -24493,7 +24516,7 @@ Index (line 67) * advanced features, data files as single record: Records. (line 172) * advanced features, fixed-width data: Constant Size. (line 9) -* advanced features, FNR/NR variables: Auto-set. (line 192) +* advanced features, FNR/NR variables: Auto-set. (line 195) * advanced features, gawk: Advanced Features. (line 6) * advanced features, gawk, network programming: TCP/IP Networking. (line 6) @@ -24545,7 +24568,7 @@ Index * arithmetic operators: Arithmetic Ops. (line 6) * arrays: Arrays. (line 6) * arrays, as parameters to functions: Function Caveats. (line 55) -* arrays, associative: Array Intro. (line 51) +* arrays, associative: Array Intro. (line 50) * arrays, associative, clearing: Internals. (line 66) * arrays, associative, library functions and: Library Names. (line 57) * arrays, deleting entire contents: Delete. (line 39) @@ -24557,16 +24580,16 @@ Index (line 6) * arrays, elements, retrieving number of: String Functions. (line 18) * arrays, for statement and: Scanning an Array. (line 20) -* arrays, IGNORECASE variable and: Array Intro. (line 93) -* arrays, indexing: Array Intro. (line 51) +* arrays, IGNORECASE variable and: Array Intro. (line 92) +* arrays, indexing: Array Intro. (line 50) * arrays, merging into strings: Join Function. (line 6) * arrays, multidimensional: Multi-dimensional. (line 10) * arrays, multidimensional, scanning: Multi-scanning. (line 11) -* arrays, names of: Arrays. (line 17) +* arrays, names of: Arrays. (line 18) * arrays, scanning: Scanning an Array. (line 6) * arrays, sorting: Array Sorting. (line 6) -* arrays, sorting, IGNORECASE variable and: Array Sorting. (line 86) -* arrays, sparse: Array Intro. (line 72) +* arrays, sorting, IGNORECASE variable and: Array Sorting. (line 69) +* arrays, sparse: Array Intro. (line 71) * arrays, subscripts: Numeric Array Subscripts. (line 6) * arrays, subscripts, uninitialized variables as: Uninitialized Subscripts. @@ -24577,7 +24600,7 @@ Index * asort() function (gawk) <1>: String Functions. (line 18) * asort() function (gawk): Array Sorting. (line 6) * asort() function (gawk), arrays, sorting: Array Sorting. (line 6) -* asorti() function (gawk): String Functions. (line 47) +* asorti() function (gawk): String Functions. (line 46) * assert function (C library): Assert Function. (line 6) * assert user-defined function: Assert Function. (line 28) * assertions: Assert Function. (line 6) @@ -24587,7 +24610,7 @@ Index * assignments as filenames: Ignoring Assigns. (line 6) * assoc_clear internal function: Internals. (line 66) * assoc_lookup internal function: Internals. (line 70) -* associative arrays: Array Intro. (line 51) +* associative arrays: Array Intro. (line 50) * asterisk (*), * operator, as multiplication operator: Precedence. (line 55) * asterisk (*), * operator, as regexp operator: Regexp Operators. @@ -24602,7 +24625,7 @@ Index * asterisk (*), **= operator: Assignment Ops. (line 129) * asterisk (*), *= operator <1>: Precedence. (line 95) * asterisk (*), *= operator: Assignment Ops. (line 129) -* atan2() function: Numeric Functions. (line 37) +* atan2() function: Numeric Functions. (line 11) * atari: Atari Installation. (line 9) * awf (amazingly workable formatter) program: Glossary. (line 20) * awk language, POSIX version: Assignment Ops. (line 136) @@ -24727,7 +24750,7 @@ Index * BEGIN pattern, getline and: Getline Notes. (line 19) * BEGIN pattern, headings, adding: Print Examples. (line 43) * BEGIN pattern, next/nextfile statements and <1>: Next Statement. - (line 39) + (line 45) * BEGIN pattern, next/nextfile statements and: I/O And BEGIN/END. (line 36) * BEGIN pattern, OFS/ORS variables, assigning values to: Output Separators. @@ -24738,6 +24761,8 @@ Index * BEGIN pattern, pwcat program: Passwd Functions. (line 128) * BEGIN pattern, running awk programs and: Cut Program. (line 66) * BEGIN pattern, TEXTDOMAIN variable and: Programmer i18n. (line 58) +* BEGINFILE pattern, Boolean patterns and: Expression Patterns. + (line 73) * BEGINFILE special pattern: BEGINFILE/ENDFILE. (line 6) * beginfile user-defined function: Filetrans Function. (line 60) * Bell Laboratories awk extensions: BTL. (line 6) @@ -24805,8 +24830,8 @@ Index * caret (^), ^= operator: Assignment Ops. (line 129) * caret (^), in character lists: Character Lists. (line 16) * case keyword: Switch Statement. (line 6) -* case sensitivity, array indices and: Array Intro. (line 93) -* case sensitivity, converting case: String Functions. (line 492) +* case sensitivity, array indices and: Array Intro. (line 92) +* case sensitivity, converting case: String Functions. (line 493) * case sensitivity, example programs: Library Functions. (line 43) * case sensitivity, gawk: Case-sensitivity. (line 26) * case sensitivity, regexps and <1>: User-modified. (line 82) @@ -24911,7 +24936,7 @@ Index * constants, types of: Constants. (line 6) * continue statement: Continue Statement. (line 6) * control statements: Statements. (line 6) -* converting, case: String Functions. (line 492) +* converting, case: String Functions. (line 493) * converting, dates to timestamps: Time Functions. (line 72) * converting, during subscripting: Numeric Array Subscripts. (line 31) @@ -24927,7 +24952,7 @@ Index * coprocesses, closing: Close Files And Pipes. (line 6) * coprocesses, getline from: Getline/Coprocess. (line 6) -* cos() function: Numeric Functions. (line 34) +* cos() function: Numeric Functions. (line 14) * counting: Wc Program. (line 6) * csh utility: Statements/Lines. (line 44) * csh utility, POSIXLY_CORRECT environment variable: Options. (line 300) @@ -24947,8 +24972,8 @@ Index * dark corner, ^, in FS: Regexp Field Splitting. (line 59) * dark corner, array subscripts: Uninitialized Subscripts. - (line 42) -* dark corner, break statement: Break Statement. (line 47) + (line 43) +* dark corner, break statement: Break Statement. (line 51) * dark corner, close() function: Close Files And Pipes. (line 131) * dark corner, command-line arguments: Assignment Options. (line 43) @@ -24962,13 +24987,13 @@ Index (line 47) * dark corner, FILENAME variable <1>: Auto-set. (line 92) * dark corner, FILENAME variable: Getline Notes. (line 19) -* dark corner, FNR/NR variables: Auto-set. (line 192) +* dark corner, FNR/NR variables: Auto-set. (line 195) * dark corner, format-control characters: Control Letters. (line 18) * dark corner, FS as null string: Single Character Fields. (line 20) * dark corner, input files: Records. (line 98) * dark corner, invoking awk: Command Line. (line 16) -* dark corner, length() function: String Functions. (line 87) +* dark corner, length() function: String Functions. (line 84) * dark corner, multiline records: Multiple Line. (line 35) * dark corner, NF variable, decrementing: Changing Fields. (line 107) * dark corner, OFMT variable: OFMT. (line 27) @@ -24978,8 +25003,9 @@ Index (line 148) * dark corner, regexp constants, as arguments to user-defined functions: Using Constant Regexps. (line 43) -* dark corner, split() function: String Functions. (line 259) +* dark corner, split() function: String Functions. (line 260) * dark corner, strings, storing: Records. (line 188) +* dark corner, value of ARGV[0]: Auto-set. (line 35) * data, fixed-width: Constant Size. (line 9) * data-driven languages: Basic High Level. (line 85) * database, group, reading: Group Functions. (line 6) @@ -25109,9 +25135,9 @@ Index * deleting elements in arrays: Delete. (line 6) * deleting entire arrays: Delete. (line 39) * dgawk: Debugger. (line 6) -* differences between gawk and awk: String Functions. (line 101) +* differences between gawk and awk: String Functions. (line 98) * differences in awk and gawk, ARGC/ARGV variables: ARGC and ARGV. - (line 86) + (line 88) * differences in awk and gawk, ARGIND variable: Auto-set. (line 40) * differences in awk and gawk, array elements, deleting: Delete. (line 39) @@ -25149,7 +25175,7 @@ Index (line 34) * differences in awk and gawk, LINT variable: User-modified. (line 98) * differences in awk and gawk, match() function: String Functions. - (line 165) + (line 161) * differences in awk and gawk, next/nextfile statements: Nextfile Statement. (line 6) * differences in awk and gawk, print/printf statements: Format Modifiers. @@ -25161,15 +25187,15 @@ Index * differences in awk and gawk, regular expressions: Case-sensitivity. (line 26) * differences in awk and gawk, RS/RT variables: Records. (line 164) -* differences in awk and gawk, RT variable: Auto-set. (line 181) +* differences in awk and gawk, RT variable: Auto-set. (line 184) * differences in awk and gawk, single-character fields: Single Character Fields. (line 6) * differences in awk and gawk, split() function: String Functions. - (line 248) + (line 249) * differences in awk and gawk, strings: Scalar Constants. (line 20) * differences in awk and gawk, strings, storing: Records. (line 184) * differences in awk and gawk, strtonum() function (gawk): String Functions. - (line 286) + (line 287) * differences in awk and gawk, TEXTDOMAIN variable: User-modified. (line 153) * differences in awk and gawk, trunc-mod operation: Arithmetic Ops. @@ -25230,12 +25256,13 @@ Index * END pattern, Boolean patterns and: Expression Patterns. (line 73) * END pattern, exit statement and: Exit Statement. (line 12) * END pattern, next/nextfile statements and <1>: Next Statement. - (line 39) + (line 45) * END pattern, next/nextfile statements and: I/O And BEGIN/END. (line 36) * END pattern, operators and: Using BEGIN/END. (line 17) * END pattern, pgawk program: Profiling. (line 69) * END pattern, print statement and: I/O And BEGIN/END. (line 16) +* ENDFILE pattern, Boolean patterns and: Expression Patterns. (line 73) * ENDFILE special pattern: BEGINFILE/ENDFILE. (line 6) * endfile user-defined function: Filetrans Function. (line 60) * endgrent function (C library): Group Functions. (line 215) @@ -25284,7 +25311,7 @@ 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 22) +* exp() function: Numeric Functions. (line 17) * expand utility: Very Simple. (line 69) * expressions: Expressions. (line 6) * expressions, as patterns: Expression Patterns. (line 6) @@ -25421,7 +25448,7 @@ Index * floating-point, numbers, AWKNUM internal type: Internals. (line 19) * FNR variable <1>: Auto-set. (line 102) * FNR variable: Records. (line 6) -* FNR variable, changing: Auto-set. (line 192) +* FNR variable, changing: Auto-set. (line 195) * for statement: For Statement. (line 6) * for statement, in arrays: Scanning an Array. (line 20) * force_number internal function: Internals. (line 27) @@ -25498,7 +25525,7 @@ Index * functions, library, user database, reading: Passwd Functions. (line 6) * functions, names of <1>: Definition Syntax. (line 21) -* functions, names of: Arrays. (line 17) +* functions, names of: Arrays. (line 18) * functions, recursive: Definition Syntax. (line 73) * functions, return values, setting: Internals. (line 136) * functions, string-translation: I18N Functions. (line 6) @@ -25508,15 +25535,15 @@ Index * functions, user-defined, counts: Profiling. (line 135) * functions, user-defined, library of: Library Functions. (line 6) * functions, user-defined, next/nextfile statements and <1>: Nextfile Statement. - (line 39) + (line 43) * functions, user-defined, next/nextfile statements and: Next Statement. - (line 39) + (line 45) * G-d: Acknowledgments. (line 79) * Garfinkle, Scott: Contributors. (line 37) * gawk, awk and <1>: This Manual. (line 14) * gawk, awk and: Preface. (line 22) * gawk, bitwise operations in: Bitwise Functions. (line 39) -* gawk, break statement in: Break Statement. (line 47) +* gawk, break statement in: Break Statement. (line 51) * gawk, built-in variables and: Built-in Variables. (line 14) * gawk, character classes and: Character Lists. (line 91) * gawk, coding style in: Adding Code. (line 32) @@ -25565,9 +25592,7 @@ Index * gawk, list of contributors to: Contributors. (line 6) * gawk, MS-DOS version of: PC Using. (line 11) * gawk, newlines in: Statements/Lines. (line 12) -* gawk, next file statement in: Nextfile Statement. (line 46) -* gawk, nextfile statement in <1>: Nextfile Function. (line 6) -* gawk, nextfile statement in: Nextfile Statement. (line 46) +* gawk, nextfile statement in: Nextfile Function. (line 6) * gawk, octal numbers and: Nondecimal-numbers. (line 42) * gawk, OS/2 version of: PC Using. (line 11) * gawk, regexp constants and: Using Constant Regexps. @@ -25588,7 +25613,7 @@ Index (line 63) * General Public License (GPL): Glossary. (line 295) * General Public License, See GPL: Manual History. (line 11) -* gensub() function (gawk) <1>: String Functions. (line 400) +* gensub() function (gawk) <1>: String Functions. (line 401) * gensub() function (gawk): Using Constant Regexps. (line 43) * gensub() function (gawk), escape processing: Gory Details. (line 6) @@ -25656,10 +25681,10 @@ Index * group database, reading: Group Functions. (line 6) * group file: Group Functions. (line 6) * groups, information about: Group Functions. (line 6) -* gsub() function <1>: String Functions. (line 384) +* gsub() function <1>: String Functions. (line 385) * gsub() function: Using Constant Regexps. (line 43) -* gsub() function, arguments of: String Functions. (line 364) +* gsub() function, arguments of: String Functions. (line 365) * gsub() function, escape processing: Gory Details. (line 6) * h debugger command (alias for help): Miscellaneous Dgawk Commands. (line 71) @@ -25693,8 +25718,8 @@ Index * ignore debugger command: Breakpoint Control. (line 80) * IGNORECASE variable <1>: User-modified. (line 82) * IGNORECASE variable: Case-sensitivity. (line 26) -* IGNORECASE variable, array sorting and: Array Sorting. (line 86) -* IGNORECASE variable, array subscripts and: Array Intro. (line 93) +* IGNORECASE variable, array sorting and: Array Sorting. (line 69) +* IGNORECASE variable, array subscripts and: Array Intro. (line 92) * IGNORECASE variable, in example programs: Library Functions. (line 43) * implementation issues, gawk: Notes. (line 6) @@ -25702,16 +25727,16 @@ Index * implementation issues, gawk, limits <1>: Redirection. (line 135) * implementation issues, gawk, limits: Getline Notes. (line 14) * in operator <1>: Id Program. (line 93) -* in operator <2>: For Statement. (line 74) +* in operator <2>: For Statement. (line 75) * in operator <3>: Precedence. (line 83) * in operator: Comparison Operators. (line 11) * in operator, arrays and <1>: Scanning an Array. (line 17) * in operator, arrays and: Reference to Elements. - (line 25) + (line 37) * increment operators: Increment Ops. (line 6) -* index() function: String Functions. (line 60) -* indexing arrays: Array Intro. (line 51) +* index() function: String Functions. (line 57) +* indexing arrays: Array Intro. (line 50) * indirect function calls: Indirect Calls. (line 6) * info debugger command: Dgawk Info. (line 12) * initialization, automatic: More Complex. (line 38) @@ -25743,7 +25768,7 @@ Index * installation, vms: VMS Installation. (line 6) * installing gawk: Installation. (line 6) * INT signal (MS-DOS): Profiling. (line 210) -* int() function: Numeric Functions. (line 11) +* int() function: Numeric Functions. (line 22) * integers: Basic Data Typing. (line 21) * integers, unsigned: Basic Data Typing. (line 28) * interacting with other programs: I/O Functions. (line 64) @@ -25817,7 +25842,7 @@ Index (line 11) * left shift, bitwise: Bitwise Functions. (line 32) * leftmost longest match: Multiple Line. (line 26) -* length() function: String Functions. (line 71) +* length() function: String Functions. (line 68) * Lesser General Public License (LGPL): Glossary. (line 373) * LGPL (Lesser General Public License): Glossary. (line 373) * libraries of awk functions: Library Functions. (line 6) @@ -25857,7 +25882,7 @@ Index * lint checking: User-modified. (line 98) * lint checking, array elements: Delete. (line 34) * lint checking, array subscripts: Uninitialized Subscripts. - (line 42) + (line 43) * lint checking, empty programs: Command Line. (line 16) * lint checking, issuing warnings: Options. (line 141) * lint checking, POSIXLY_CORRECT environment variable: Options. @@ -25877,13 +25902,13 @@ Index * localization, See internationalization, localization: I18N and L10N. (line 6) * log files, timestamps in: Time Functions. (line 6) -* log() function: Numeric Functions. (line 27) +* log() function: Numeric Functions. (line 29) * logical false/true: Truth Values. (line 6) * logical operators, See Boolean expressions: Boolean Ops. (line 6) * login information: Passwd Functions. (line 16) * long options: Command Line. (line 13) * loops: While Statement. (line 6) -* loops, continue statements and: For Statement. (line 63) +* loops, continue statements and: For Statement. (line 64) * loops, count for header: Profiling. (line 129) * loops, exiting: Break Statement. (line 6) * loops, See Also while statement: While Statement. (line 6) @@ -25901,9 +25926,9 @@ Index (line 6) * marked strings, extracting: String Extraction. (line 6) * Marx, Groucho: Increment Ops. (line 61) -* match() function: String Functions. (line 111) +* match() function: String Functions. (line 108) * match() function, RSTART/RLENGTH variables: String Functions. - (line 129) + (line 125) * matching, expressions, See comparison expressions: Typing and Comparison. (line 9) * matching, leftmost longest: Multiple Line. (line 26) @@ -25926,11 +25951,11 @@ Index * n debugger command (alias for next): Dgawk Execution Control. (line 43) * names, arrays/variables <1>: Library Names. (line 6) -* names, arrays/variables: Arrays. (line 17) +* names, arrays/variables: Arrays. (line 18) * names, functions <1>: Library Names. (line 6) * names, functions: Definition Syntax. (line 21) * namespace issues <1>: Library Names. (line 6) -* namespace issues: Arrays. (line 17) +* namespace issues: Arrays. (line 18) * namespace issues, functions: Definition Syntax. (line 21) * nargs internal variable: Internals. (line 46) * nawk utility: Names. (line 17) @@ -25953,18 +25978,16 @@ Index * next debugger command: Dgawk Execution Control. (line 43) * next file statement: POSIX/GNU. (line 155) -* next file statement, in gawk: Nextfile Statement. (line 46) * next statement <1>: Next Statement. (line 6) * next statement: Boolean Ops. (line 85) * next statement, BEGIN/END patterns and: I/O And BEGIN/END. (line 36) -* next statement, user-defined functions and: Next Statement. (line 39) +* next statement, user-defined functions and: Next Statement. (line 45) * nextfile statement: Nextfile Statement. (line 6) * nextfile statement, BEGIN/END patterns and: I/O And BEGIN/END. (line 36) * nextfile statement, implementing: Nextfile Function. (line 6) -* nextfile statement, in gawk: Nextfile Statement. (line 46) * nextfile statement, user-defined functions and: Nextfile Statement. - (line 39) + (line 43) * nextfile user-defined function: Nextfile Function. (line 38) * nexti debugger command: Dgawk Execution Control. (line 49) @@ -25979,7 +26002,7 @@ Index * not Boolean-logic operator: Boolean Ops. (line 6) * NR variable <1>: Auto-set. (line 118) * NR variable: Records. (line 6) -* NR variable, changing: Auto-set. (line 192) +* NR variable, changing: Auto-set. (line 195) * null strings <1>: Basic Data Typing. (line 47) * null strings <2>: Truth Values. (line 6) * null strings <3>: Regexp Field Splitting. @@ -25987,7 +26010,7 @@ Index * null strings: Records. (line 102) * null strings, array elements and: Delete. (line 27) * null strings, as array subscripts: Uninitialized Subscripts. - (line 42) + (line 43) * null strings, converting numbers to strings: Conversion. (line 21) * null strings, matching: Gory Details. (line 159) * null strings, quoting and: Quoting. (line 62) @@ -26010,7 +26033,7 @@ 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 70) +* numbers, random: Numeric Functions. (line 63) * numbers, rounding: Round Function. (line 6) * numeric, constants: Scalar Constants. (line 6) * numeric, output format: OFMT. (line 6) @@ -26102,7 +26125,7 @@ Index * parentheses (): Regexp Operators. (line 78) * parentheses (), pgawk program: Profiling. (line 144) * password file: Passwd Functions. (line 16) -* patsplit() function: String Functions. (line 200) +* patsplit() function: String Functions. (line 195) * patterns: Patterns and Actions. (line 6) * patterns, comparison expressions as: Expression Patterns. (line 14) @@ -26112,7 +26135,7 @@ Index * patterns, expressions as: Regexp Patterns. (line 6) * patterns, ranges in: Ranges. (line 6) * patterns, regexp constants as: Expression Patterns. (line 36) -* patterns, types of: Pattern Overview. (line 14) +* patterns, types of: Pattern Overview. (line 15) * pawk profiling Bell Labs awk: Other Versions. (line 93) * PC operating systems, gawk on: PC Using. (line 6) * PC operating systems, gawk on, installing: PC Installation. (line 6) @@ -26159,7 +26182,7 @@ Index * portability, gawk: New Ports. (line 6) * portability, gettext library and: Explaining gettext. (line 10) * portability, internationalization and: I18N Portability. (line 6) -* portability, length() function: String Functions. (line 80) +* portability, length() function: String Functions. (line 77) * portability, new awk vs. old awk: Conversion. (line 54) * portability, next statement in user-defined functions: Function Caveats. (line 99) @@ -26167,7 +26190,7 @@ Index * portability, operators: Increment Ops. (line 61) * portability, operators, not in POSIX awk: Precedence. (line 98) * portability, POSIXLY_CORRECT environment variable: Options. (line 305) -* portability, substr() function: String Functions. (line 482) +* portability, substr() function: String Functions. (line 483) * 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. @@ -26188,7 +26211,7 @@ Index * POSIX awk, backslashes in string constants: Escape Sequences. (line 113) * POSIX awk, BEGIN/END patterns: I/O And BEGIN/END. (line 16) -* POSIX awk, break statement and: Break Statement. (line 47) +* POSIX awk, break statement and: Break Statement. (line 51) * POSIX awk, changes in awk versions: POSIX. (line 6) * POSIX awk, character lists and: Character Lists. (line 23) * POSIX awk, character lists and, character classes: Character Lists. @@ -26202,10 +26225,10 @@ Index * POSIX awk, FS variable and: User-modified. (line 66) * POSIX awk, function keyword in: Definition Syntax. (line 78) * POSIX awk, functions and, gsub()/sub(): Gory Details. (line 53) -* POSIX awk, functions and, length(): String Functions. (line 80) +* POSIX awk, functions and, length(): String Functions. (line 77) * POSIX awk, GNU long options and: Options. (line 15) * POSIX awk, interval expressions in: Regexp Operators. (line 134) -* POSIX awk, next/nextfile statements and: Next Statement. (line 39) +* POSIX awk, next/nextfile statements and: Next Statement. (line 45) * POSIX awk, numeric strings and: Variable Typing. (line 6) * POSIX awk, OFMT variable and <1>: Conversion. (line 54) * POSIX awk, OFMT variable and: OFMT. (line 27) @@ -26308,12 +26331,12 @@ Index * r debugger command (alias for run): Dgawk Execution Control. (line 62) * Rakitzis, Byron: History Sorting. (line 25) -* rand() function: Numeric Functions. (line 40) +* rand() function: Numeric Functions. (line 33) * random numbers, Cliff: Cliff Random Function. (line 6) * random numbers, rand()/srand() functions: Numeric Functions. - (line 40) -* random numbers, seed of: Numeric Functions. (line 70) + (line 33) +* random numbers, seed of: Numeric Functions. (line 63) * range expressions: Character Lists. (line 6) * range patterns: Ranges. (line 6) * Rankin, Pat <1>: Bugs. (line 71) @@ -26339,7 +26362,7 @@ Index * recursive functions: Definition Syntax. (line 73) * redirection of input: Getline/File. (line 6) * redirection of output: Redirection. (line 6) -* reference counting, sorting arrays: Array Sorting. (line 79) +* reference counting, sorting arrays: Array Sorting. (line 62) * regexp constants <1>: Comparison Operators. (line 103) * regexp constants <2>: Regexp Constants. (line 6) @@ -26405,8 +26428,8 @@ Index * right angle bracket (>), >> operator (I/O): Redirection. (line 50) * right shift, bitwise: Bitwise Functions. (line 32) * Ritchie, Dennis: Basic Data Typing. (line 71) -* RLENGTH variable: Auto-set. (line 168) -* RLENGTH variable, match() function and: String Functions. (line 129) +* RLENGTH variable: Auto-set. (line 171) +* RLENGTH variable, match() function and: String Functions. (line 125) * Robbins, Arnold <1>: Future Extensions. (line 6) * Robbins, Arnold <2>: Bugs. (line 29) * Robbins, Arnold <3>: Contributors. (line 95) @@ -26431,9 +26454,9 @@ Index * RS variable: Records. (line 20) * RS variable, multiline records and: Multiple Line. (line 17) * rshift() function (gawk): Bitwise Functions. (line 46) -* RSTART variable: Auto-set. (line 174) -* RSTART variable, match() function and: String Functions. (line 129) -* RT variable <1>: Auto-set. (line 181) +* RSTART variable: Auto-set. (line 177) +* RSTART variable, match() function and: String Functions. (line 125) +* RT variable <1>: Auto-set. (line 184) * RT variable <2>: Multiple Line. (line 129) * RT variable: Records. (line 112) * Rubin, Paul <1>: Contributors. (line 16) @@ -26454,7 +26477,7 @@ Index * search paths, for source files <1>: VMS Running. (line 28) * search paths, for source files <2>: Igawk Program. (line 358) * search paths, for source files: AWKPATH Variable. (line 6) -* searching: String Functions. (line 60) +* searching: String Functions. (line 57) * searching, files for regular expressions: Egrep Program. (line 6) * searching, for words: Dupword Program. (line 6) * sed utility <1>: Glossary. (line 12) @@ -26492,7 +26515,7 @@ Index * side effects <1>: Increment Ops. (line 11) * side effects: Concatenation. (line 42) * side effects, array indexing: Reference to Elements. - (line 30) + (line 42) * side effects, asort() function: Array Sorting. (line 25) * side effects, assignment expressions: Assignment Ops. (line 23) * side effects, Boolean operators: Boolean Ops. (line 30) @@ -26507,7 +26530,7 @@ Index * signals, USR1/SIGUSR1: Profiling. (line 185) * silent debugger command: Dgawk Execution Control. (line 10) -* sin() function: Numeric Functions. (line 31) +* sin() function: Numeric Functions. (line 73) * single quote (') <1>: Quoting. (line 31) * single quote (') <2>: Long. (line 33) * single quote ('): One-shot. (line 15) @@ -26531,18 +26554,18 @@ Index * source code, mawk: Other Versions. (line 34) * source code, mixing: Options. (line 102) * source files, search path for: Igawk Program. (line 358) -* sparse arrays: Array Intro. (line 72) +* sparse arrays: Array Intro. (line 71) * Spencer, Henry: Glossary. (line 12) * split utility: Split Program. (line 6) -* split() function: String Functions. (line 215) +* split() function: String Functions. (line 216) * split() function, array elements, deleting: Delete. (line 56) * split.awk program: Split Program. (line 30) -* sprintf() function <1>: String Functions. (line 278) +* sprintf() function <1>: String Functions. (line 279) * sprintf() function: OFMT. (line 15) * sprintf() function, OFMT variable and: User-modified. (line 124) * sprintf() function, print/printf statements and: Round Function. (line 6) -* sqrt() function: Numeric Functions. (line 18) +* sqrt() function: Numeric Functions. (line 76) * square brackets ([]): Regexp Operators. (line 55) * srand() function: Numeric Functions. (line 80) * Stallman, Richard <1>: Glossary. (line 286) @@ -26585,14 +26608,14 @@ Index * strings, null: Regexp Field Splitting. (line 43) * strings, numeric: Variable Typing. (line 6) -* strings, splitting: String Functions. (line 234) -* strtonum() function (gawk): String Functions. (line 286) +* strings, splitting: String Functions. (line 235) +* strtonum() function (gawk): String Functions. (line 287) * strtonum() function (gawk), --non-decimal-data option and: Nondecimal Data. (line 36) -* sub() function <1>: String Functions. (line 307) +* sub() function <1>: String Functions. (line 308) * sub() function: Using Constant Regexps. (line 43) -* sub() function, arguments of: String Functions. (line 364) +* sub() function, arguments of: String Functions. (line 365) * sub() function, escape processing: Gory Details. (line 6) * subscript separators: User-modified. (line 147) * subscripts in arrays, multidimensional: Multi-dimensional. (line 10) @@ -26605,7 +26628,7 @@ Index * SUBSEP variable: User-modified. (line 147) * SUBSEP variable, multidimensional arrays: Multi-dimensional. (line 16) -* substr() function: String Functions. (line 451) +* substr() function: String Functions. (line 452) * Sumner, Andrew: Other Versions. (line 81) * switch statement: Switch Statement. (line 6) * syntactic ambiguity: /= operator vs. /=.../ regexp constant: Assignment Ops. @@ -26657,8 +26680,8 @@ Index * timestamps, converting dates to: Time Functions. (line 72) * timestamps, formatted: Gettimeofday Function. (line 6) -* tolower() function: String Functions. (line 493) -* toupper() function: String Functions. (line 499) +* tolower() function: String Functions. (line 494) +* toupper() function: String Functions. (line 500) * tr utility: Translate Program. (line 6) * trace debugger command: Miscellaneous Dgawk Commands. (line 113) @@ -26683,8 +26706,8 @@ Index * troubleshooting, gawk, fatal errors, function arguments: Calling Built-in. (line 16) * troubleshooting, getline function: File Checking. (line 24) -* troubleshooting, gsub()/sub() functions: String Functions. (line 374) -* troubleshooting, match() function: String Functions. (line 195) +* troubleshooting, gsub()/sub() functions: String Functions. (line 375) +* troubleshooting, match() function: String Functions. (line 190) * troubleshooting, print statement, omitting commas: Print Examples. (line 31) * troubleshooting, printing: Redirection. (line 118) @@ -26693,7 +26716,7 @@ Index * troubleshooting, regexp constants vs. string constants: Computed Regexps. (line 38) * troubleshooting, string concatenation: Concatenation. (line 27) -* troubleshooting, substr() function: String Functions. (line 469) +* troubleshooting, substr() function: String Functions. (line 470) * troubleshooting, system() function: I/O Functions. (line 88) * troubleshooting, typographical errors, global variables: Options. (line 92) @@ -26766,7 +26789,7 @@ Index * variables, global, for library functions: Library Names. (line 11) * variables, global, printing list of: Options. (line 88) * variables, initializing: Using Variables. (line 20) -* variables, names of: Arrays. (line 17) +* variables, names of: Arrays. (line 18) * variables, private: Library Names. (line 11) * variables, setting: Options. (line 30) * variables, shadowing: Definition Syntax. (line 61) @@ -26908,349 +26931,351 @@ Node: Leftmost Longest123883 Node: Computed Regexps125084 Node: Locales128501 Node: Reading Files131591 -Node: Records133607 -Ref: Records-Footnote-1142173 -Node: Fields142210 -Ref: Fields-Footnote-1145242 -Node: Nonconstant Fields145328 -Node: Changing Fields147530 -Node: Field Separators152815 -Node: Default Field Splitting155444 -Node: Regexp Field Splitting156561 -Node: Single Character Fields159911 -Node: Command Line Field Separator160962 -Node: Field Splitting Summary164401 -Ref: Field Splitting Summary-Footnote-1167587 -Node: Constant Size167688 -Node: Splitting By Content172159 -Ref: Splitting By Content-Footnote-1175761 -Node: Multiple Line175801 -Ref: Multiple Line-Footnote-1181541 -Node: Getline181720 -Node: Plain Getline183941 -Node: Getline/Variable186030 -Node: Getline/File187171 -Node: Getline/Variable/File188493 -Ref: Getline/Variable/File-Footnote-1190092 -Node: Getline/Pipe190179 -Node: Getline/Variable/Pipe192727 -Node: Getline/Coprocess193834 -Node: Getline/Variable/Coprocess195077 -Node: Getline Notes195791 -Node: Getline Summary197733 -Ref: table-getline-variants198017 -Node: BEGINFILE/ENDFILE198922 -Node: Command line directories201777 -Node: Printing202412 -Node: Print204043 -Node: Print Examples205380 -Node: Output Separators208164 -Node: OFMT209923 -Node: Printf211281 -Node: Basic Printf212187 -Node: Control Letters213724 -Node: Format Modifiers217536 -Node: Printf Examples223547 -Node: Redirection226262 -Node: Special Files233240 -Node: Special FD233773 -Ref: Special FD-Footnote-1237348 -Node: Special Network237422 -Node: Special Caveats238277 -Node: Close Files And Pipes239071 -Ref: Close Files And Pipes-Footnote-1246015 -Ref: Close Files And Pipes-Footnote-2246163 -Node: Expressions246313 -Node: Values247382 -Node: Constants248058 -Node: Scalar Constants248738 -Ref: Scalar Constants-Footnote-1249597 -Node: Nondecimal-numbers249779 -Node: Regexp Constants252838 -Node: Using Constant Regexps253313 -Node: Variables256318 -Node: Using Variables256973 -Node: Assignment Options258700 -Node: Conversion260581 -Ref: table-locale-affects265955 -Ref: Conversion-Footnote-1266579 -Node: All Operators266688 -Node: Arithmetic Ops267318 -Node: Concatenation269817 -Ref: Concatenation-Footnote-1272610 -Node: Assignment Ops272729 -Ref: table-assign-ops277717 -Node: Increment Ops279118 -Node: Truth Values and Conditions282596 -Node: Truth Values283679 -Node: Typing and Comparison284727 -Node: Variable Typing285516 -Ref: Variable Typing-Footnote-1289413 -Node: Comparison Operators289535 -Ref: table-relational-ops289945 -Node: POSIX String Comparison293494 -Ref: POSIX String Comparison-Footnote-1294451 -Node: Boolean Ops294589 -Ref: Boolean Ops-Footnote-1298667 -Node: Conditional Exp298758 -Node: Function Calls300490 -Node: Precedence304049 -Node: Patterns and Actions307702 -Node: Pattern Overview308756 -Node: Regexp Patterns310193 -Node: Expression Patterns310736 -Node: Ranges314286 -Node: BEGIN/END317375 -Node: Using BEGIN/END318125 -Ref: Using BEGIN/END-Footnote-1320856 -Node: I/O And BEGIN/END320970 -Node: Empty323237 -Node: Using Shell Variables323545 -Node: Action Overview325826 -Node: Statements328184 -Node: If Statement330040 -Node: While Statement331539 -Node: Do Statement333571 -Node: For Statement334720 -Node: Switch Statement337860 -Node: Break Statement339908 -Node: Continue Statement341728 -Node: Next Statement343426 -Node: Nextfile Statement345706 -Node: Exit Statement348424 -Node: Built-in Variables350695 -Node: User-modified351790 -Ref: User-modified-Footnote-1359756 -Node: Auto-set359818 -Ref: Auto-set-Footnote-1368480 -Node: ARGC and ARGV368685 -Node: Arrays372446 -Node: Array Basics373955 -Node: Array Intro374666 -Node: Reference to Elements379053 -Node: Assigning Elements380952 -Node: Array Example381443 -Node: Scanning an Array383175 -Node: Delete385452 -Ref: Delete-Footnote-1387842 -Node: Numeric Array Subscripts387899 -Node: Uninitialized Subscripts390086 -Node: Multi-dimensional391692 -Node: Multi-scanning394783 -Node: Array Sorting396367 -Node: Arrays of Arrays400197 -Node: Functions404305 -Node: Built-in405114 -Node: Calling Built-in406128 -Node: Numeric Functions408104 -Ref: Numeric Functions-Footnote-1411858 -Ref: Numeric Functions-Footnote-2412192 -Node: String Functions412461 -Ref: String Functions-Footnote-1434295 -Ref: String Functions-Footnote-2434424 -Ref: String Functions-Footnote-3434672 -Node: Gory Details434759 -Ref: table-sub-escapes436416 -Ref: table-sub-posix-92437762 -Ref: table-sub-proposed439105 -Ref: table-posix-2001-sub440465 -Ref: table-gensub-escapes441740 -Ref: Gory Details-Footnote-1442943 -Node: I/O Functions442994 -Ref: I/O Functions-Footnote-1449782 -Node: Time Functions449873 -Ref: Time Functions-Footnote-1460685 -Ref: Time Functions-Footnote-2460753 -Ref: Time Functions-Footnote-3460911 -Ref: Time Functions-Footnote-4461022 -Ref: Time Functions-Footnote-5461149 -Ref: Time Functions-Footnote-6461376 -Node: Bitwise Functions461642 -Ref: table-bitwise-ops462220 -Ref: Bitwise Functions-Footnote-1466460 -Node: I18N Functions466644 -Node: User-defined468367 -Node: Definition Syntax469171 -Node: Function Example473869 -Node: Function Caveats476451 -Node: Return Statement480376 -Node: Dynamic Typing483033 -Node: Indirect Calls483770 -Node: Internationalization493405 -Node: I18N and L10N494824 -Node: Explaining gettext495508 -Ref: Explaining gettext-Footnote-1500419 -Ref: Explaining gettext-Footnote-2500658 -Node: Programmer i18n500827 -Node: Translator i18n505062 -Node: String Extraction505853 -Ref: String Extraction-Footnote-1506810 -Node: Printf Ordering506936 -Ref: Printf Ordering-Footnote-1509716 -Node: I18N Portability509780 -Ref: I18N Portability-Footnote-1512225 -Node: I18N Example512288 -Ref: I18N Example-Footnote-1514908 -Node: Gawk I18N514980 -Node: Advanced Features515558 -Node: Nondecimal Data516873 -Node: Two-way I/O518434 -Ref: Two-way I/O-Footnote-1523917 -Node: TCP/IP Networking523994 -Node: Profiling526784 -Node: Invoking Gawk534245 -Node: Command Line535552 -Node: Options536337 -Ref: Options-Footnote-1549425 -Node: Other Arguments549450 -Node: AWKPATH Variable552131 -Ref: AWKPATH Variable-Footnote-1554906 -Node: Exit Status555166 -Node: Include Files555838 -Node: Obsolete559439 -Node: Undocumented560240 -Node: Known Bugs560502 -Node: Library Functions561104 -Ref: Library Functions-Footnote-1564085 -Node: Library Names564256 -Ref: Library Names-Footnote-1567729 -Ref: Library Names-Footnote-2567948 -Node: General Functions568034 -Node: Nextfile Function569097 -Node: Strtonum Function573461 -Node: Assert Function576402 -Node: Round Function579706 -Node: Cliff Random Function581246 -Node: Ordinal Functions582261 -Ref: Ordinal Functions-Footnote-1585321 -Node: Join Function585537 -Ref: Join Function-Footnote-1587299 -Node: Gettimeofday Function587499 -Node: Data File Management591210 -Node: Filetrans Function591842 -Node: Rewind Function595268 -Node: File Checking596714 -Node: Empty Files597744 -Node: Ignoring Assigns599969 -Node: Getopt Function601517 -Ref: Getopt Function-Footnote-1612799 -Node: Passwd Functions613002 -Ref: Passwd Functions-Footnote-1621980 -Node: Group Functions622068 -Node: Sample Programs630165 -Node: Running Examples630834 -Node: Clones631562 -Node: Cut Program632694 -Node: Egrep Program642453 -Ref: Egrep Program-Footnote-1650203 -Node: Id Program650313 -Node: Split Program653920 -Node: Tee Program657388 -Node: Uniq Program660131 -Node: Wc Program667498 -Ref: Wc Program-Footnote-1671742 -Node: Miscellaneous Programs671938 -Node: Dupword Program673058 -Node: Alarm Program675089 -Node: Translate Program679631 -Ref: Translate Program-Footnote-1684010 -Ref: Translate Program-Footnote-2684247 -Node: Labels Program684381 -Ref: Labels Program-Footnote-1687672 -Node: Word Sorting687756 -Node: History Sorting692103 -Node: Extract Program693941 -Node: Simple Sed701299 -Node: Igawk Program704356 -Ref: Igawk Program-Footnote-1719087 -Ref: Igawk Program-Footnote-2719288 -Node: Signature Program719426 -Node: Debugger720506 -Node: Debugging721382 -Node: Debugging Concepts721696 -Node: Debugging Terms723549 -Node: Awk Debugging726097 -Node: Sample dgawk session726989 -Node: dgawk invocation727481 -Node: Finding The Bug728665 -Node: List of Debugger Commands735180 -Node: Breakpoint Control736495 -Node: Dgawk Execution Control739705 -Node: Viewing And Changing Data743054 -Node: Dgawk Stack746350 -Node: Dgawk Info747811 -Node: Miscellaneous Dgawk Commands751749 -Node: Readline Support757465 -Node: Dgawk Limitations758281 -Node: Language History760453 -Node: V7/SVR3.1761830 -Node: SVR4764125 -Node: POSIX765570 -Node: BTL767282 -Node: POSIX/GNU768972 -Node: Contributors778636 -Node: Installation782241 -Node: Gawk Distribution783212 -Node: Getting783696 -Node: Extracting784522 -Node: Distribution contents785910 -Node: Unix Installation790983 -Node: Quick Installation791574 -Node: Additional Configuration Options793276 -Node: Configuration Philosophy795039 -Node: Non-Unix Installation797403 -Node: PC Installation797868 -Node: PC Binary Installation799174 -Node: PC Compiling801017 -Node: PC Dynamic805522 -Node: PC Using807885 -Node: Cygwin812433 -Node: MSYS813417 -Node: VMS Installation813923 -Node: VMS Compilation814527 -Node: VMS Installation Details816104 -Node: VMS Running817734 -Node: VMS POSIX819331 -Node: VMS Old Gawk820629 -Node: Unsupported821098 -Node: Atari Installation821560 -Node: Atari Compiling822847 -Node: Atari Using824736 -Node: BeOS Installation827583 -Node: Tandem Installation828728 -Node: Bugs830407 -Node: Other Versions834239 -Node: Notes839461 -Node: Compatibility Mode840153 -Node: Additions840936 -Node: Adding Code841686 -Node: New Ports847738 -Node: Dynamic Extensions851870 -Node: Internals853251 -Node: Plugin License863656 -Node: Sample Library864290 -Node: Internal File Description864954 -Node: Internal File Ops868649 -Ref: Internal File Ops-Footnote-1873525 -Node: Using Internal File Ops873673 -Node: Future Extensions875698 -Node: Basic Concepts879735 -Node: Basic High Level880492 -Ref: Basic High Level-Footnote-1884608 -Node: Basic Data Typing884802 -Node: Floating Point Issues889239 -Node: String Conversion Precision890322 -Ref: String Conversion Precision-Footnote-1892016 -Node: Unexpected Results892125 -Node: POSIX Floating Point Problems893951 -Ref: POSIX Floating Point Problems-Footnote-1897650 -Node: Glossary897688 -Node: Copying921456 -Node: GNU Free Documentation License959013 -Node: next-edition984157 -Node: unresolved984509 -Node: revision985009 -Node: consistency985432 -Node: Index988785 +Node: Records133532 +Ref: Records-Footnote-1142098 +Node: Fields142135 +Ref: Fields-Footnote-1145167 +Node: Nonconstant Fields145253 +Node: Changing Fields147455 +Node: Field Separators152740 +Node: Default Field Splitting155369 +Node: Regexp Field Splitting156486 +Node: Single Character Fields159836 +Node: Command Line Field Separator160887 +Node: Field Splitting Summary164326 +Ref: Field Splitting Summary-Footnote-1167512 +Node: Constant Size167613 +Node: Splitting By Content172084 +Ref: Splitting By Content-Footnote-1175686 +Node: Multiple Line175726 +Ref: Multiple Line-Footnote-1181466 +Node: Getline181645 +Node: Plain Getline183873 +Node: Getline/Variable185962 +Node: Getline/File187103 +Node: Getline/Variable/File188425 +Ref: Getline/Variable/File-Footnote-1190024 +Node: Getline/Pipe190111 +Node: Getline/Variable/Pipe192659 +Node: Getline/Coprocess193766 +Node: Getline/Variable/Coprocess195009 +Node: Getline Notes195723 +Node: Getline Summary197665 +Ref: table-getline-variants197949 +Node: Command line directories198854 +Node: Printing199479 +Node: Print201110 +Node: Print Examples202447 +Node: Output Separators205231 +Node: OFMT206990 +Node: Printf208348 +Node: Basic Printf209254 +Node: Control Letters210791 +Node: Format Modifiers214603 +Node: Printf Examples220614 +Node: Redirection223329 +Node: Special Files230307 +Node: Special FD230840 +Ref: Special FD-Footnote-1234415 +Node: Special Network234489 +Node: Special Caveats235344 +Node: Close Files And Pipes236138 +Ref: Close Files And Pipes-Footnote-1243082 +Ref: Close Files And Pipes-Footnote-2243230 +Node: Expressions243380 +Node: Values244449 +Node: Constants245125 +Node: Scalar Constants245805 +Ref: Scalar Constants-Footnote-1246664 +Node: Nondecimal-numbers246846 +Node: Regexp Constants249905 +Node: Using Constant Regexps250380 +Node: Variables253385 +Node: Using Variables254040 +Node: Assignment Options255767 +Node: Conversion257648 +Ref: table-locale-affects263022 +Ref: Conversion-Footnote-1263646 +Node: All Operators263755 +Node: Arithmetic Ops264385 +Node: Concatenation266884 +Ref: Concatenation-Footnote-1269677 +Node: Assignment Ops269796 +Ref: table-assign-ops274784 +Node: Increment Ops276185 +Node: Truth Values and Conditions279663 +Node: Truth Values280746 +Node: Typing and Comparison281794 +Node: Variable Typing282583 +Ref: Variable Typing-Footnote-1286480 +Node: Comparison Operators286602 +Ref: table-relational-ops287012 +Node: POSIX String Comparison290561 +Ref: POSIX String Comparison-Footnote-1291518 +Node: Boolean Ops291656 +Ref: Boolean Ops-Footnote-1295734 +Node: Conditional Exp295825 +Node: Function Calls297557 +Node: Precedence301116 +Node: Patterns and Actions304769 +Node: Pattern Overview305823 +Node: Regexp Patterns307489 +Node: Expression Patterns308032 +Node: Ranges311606 +Node: BEGIN/END314572 +Node: Using BEGIN/END315322 +Ref: Using BEGIN/END-Footnote-1318053 +Node: I/O And BEGIN/END318167 +Node: Empty320436 +Node: BEGINFILE/ENDFILE320770 +Node: Using Shell Variables323595 +Node: Action Overview325874 +Node: Statements328231 +Node: If Statement330090 +Node: While Statement331589 +Node: Do Statement333633 +Node: For Statement334789 +Node: Switch Statement337941 +Node: Break Statement340038 +Node: Continue Statement342014 +Node: Next Statement343715 +Node: Nextfile Statement346097 +Node: Exit Statement348615 +Node: Built-in Variables350890 +Node: User-modified351985 +Ref: User-modified-Footnote-1359986 +Node: Auto-set360048 +Ref: Auto-set-Footnote-1368839 +Node: ARGC and ARGV369044 +Node: Arrays372803 +Node: Array Basics374374 +Node: Array Intro375085 +Node: Reference to Elements379403 +Node: Assigning Elements381673 +Node: Array Example382164 +Node: Scanning an Array383896 +Node: Delete386173 +Ref: Delete-Footnote-1388571 +Node: Numeric Array Subscripts388628 +Node: Uninitialized Subscripts390811 +Node: Multi-dimensional392439 +Node: Multi-scanning395530 +Node: Array Sorting397114 +Ref: Array Sorting-Footnote-1400312 +Node: Arrays of Arrays400506 +Node: Functions404614 +Node: Built-in405436 +Node: Calling Built-in406450 +Node: Numeric Functions408426 +Ref: Numeric Functions-Footnote-1412135 +Ref: Numeric Functions-Footnote-2412471 +Ref: Numeric Functions-Footnote-3412519 +Node: String Functions412788 +Ref: String Functions-Footnote-1434670 +Ref: String Functions-Footnote-2434799 +Ref: String Functions-Footnote-3435047 +Node: Gory Details435134 +Ref: table-sub-escapes436791 +Ref: table-sub-posix-92438137 +Ref: table-sub-proposed439480 +Ref: table-posix-2001-sub440840 +Ref: table-gensub-escapes442115 +Ref: Gory Details-Footnote-1443318 +Node: I/O Functions443369 +Ref: I/O Functions-Footnote-1450157 +Node: Time Functions450248 +Ref: Time Functions-Footnote-1461060 +Ref: Time Functions-Footnote-2461128 +Ref: Time Functions-Footnote-3461286 +Ref: Time Functions-Footnote-4461397 +Ref: Time Functions-Footnote-5461524 +Ref: Time Functions-Footnote-6461751 +Node: Bitwise Functions462017 +Ref: table-bitwise-ops462595 +Ref: Bitwise Functions-Footnote-1466835 +Node: I18N Functions467019 +Node: User-defined468742 +Node: Definition Syntax469546 +Node: Function Example474244 +Node: Function Caveats476826 +Node: Return Statement480751 +Node: Dynamic Typing483408 +Node: Indirect Calls484145 +Node: Internationalization493780 +Node: I18N and L10N495199 +Node: Explaining gettext495883 +Ref: Explaining gettext-Footnote-1500794 +Ref: Explaining gettext-Footnote-2501033 +Node: Programmer i18n501202 +Node: Translator i18n505437 +Node: String Extraction506228 +Ref: String Extraction-Footnote-1507185 +Node: Printf Ordering507311 +Ref: Printf Ordering-Footnote-1510091 +Node: I18N Portability510155 +Ref: I18N Portability-Footnote-1512600 +Node: I18N Example512663 +Ref: I18N Example-Footnote-1515283 +Node: Gawk I18N515355 +Node: Advanced Features515933 +Node: Nondecimal Data517248 +Node: Two-way I/O518809 +Ref: Two-way I/O-Footnote-1524292 +Node: TCP/IP Networking524369 +Node: Profiling527159 +Node: Invoking Gawk534620 +Node: Command Line535927 +Node: Options536712 +Ref: Options-Footnote-1549800 +Node: Other Arguments549825 +Node: AWKPATH Variable552506 +Ref: AWKPATH Variable-Footnote-1555281 +Node: Exit Status555541 +Node: Include Files556213 +Node: Obsolete559814 +Node: Undocumented560615 +Node: Known Bugs560877 +Node: Library Functions561479 +Ref: Library Functions-Footnote-1564460 +Node: Library Names564631 +Ref: Library Names-Footnote-1568104 +Ref: Library Names-Footnote-2568323 +Node: General Functions568409 +Node: Nextfile Function569472 +Node: Strtonum Function573836 +Node: Assert Function576777 +Node: Round Function580081 +Node: Cliff Random Function581621 +Node: Ordinal Functions582636 +Ref: Ordinal Functions-Footnote-1585696 +Node: Join Function585912 +Ref: Join Function-Footnote-1587674 +Node: Gettimeofday Function587874 +Node: Data File Management591585 +Node: Filetrans Function592217 +Node: Rewind Function595643 +Node: File Checking597089 +Node: Empty Files598119 +Node: Ignoring Assigns600344 +Node: Getopt Function601892 +Ref: Getopt Function-Footnote-1613174 +Node: Passwd Functions613377 +Ref: Passwd Functions-Footnote-1622355 +Node: Group Functions622443 +Node: Sample Programs630540 +Node: Running Examples631209 +Node: Clones631937 +Node: Cut Program633069 +Node: Egrep Program642828 +Ref: Egrep Program-Footnote-1650578 +Node: Id Program650688 +Node: Split Program654295 +Node: Tee Program657763 +Node: Uniq Program660506 +Node: Wc Program667873 +Ref: Wc Program-Footnote-1672117 +Node: Miscellaneous Programs672313 +Node: Dupword Program673433 +Node: Alarm Program675464 +Node: Translate Program680006 +Ref: Translate Program-Footnote-1684385 +Ref: Translate Program-Footnote-2684622 +Node: Labels Program684756 +Ref: Labels Program-Footnote-1688047 +Node: Word Sorting688131 +Node: History Sorting692478 +Node: Extract Program694316 +Node: Simple Sed701674 +Node: Igawk Program704731 +Ref: Igawk Program-Footnote-1719462 +Ref: Igawk Program-Footnote-2719663 +Node: Signature Program719801 +Node: Debugger720881 +Node: Debugging721757 +Node: Debugging Concepts722071 +Node: Debugging Terms723924 +Node: Awk Debugging726472 +Node: Sample dgawk session727364 +Node: dgawk invocation727856 +Node: Finding The Bug729040 +Node: List of Debugger Commands735555 +Node: Breakpoint Control736870 +Node: Dgawk Execution Control740080 +Node: Viewing And Changing Data743429 +Node: Dgawk Stack746725 +Node: Dgawk Info748186 +Node: Miscellaneous Dgawk Commands752124 +Node: Readline Support757840 +Node: Dgawk Limitations758656 +Node: Language History760828 +Node: V7/SVR3.1762205 +Node: SVR4764500 +Node: POSIX765945 +Node: BTL767657 +Node: POSIX/GNU769347 +Node: Contributors779011 +Node: Installation782616 +Node: Gawk Distribution783587 +Node: Getting784071 +Node: Extracting784897 +Node: Distribution contents786285 +Node: Unix Installation791358 +Node: Quick Installation791949 +Node: Additional Configuration Options793651 +Node: Configuration Philosophy795414 +Node: Non-Unix Installation797778 +Node: PC Installation798243 +Node: PC Binary Installation799549 +Node: PC Compiling801392 +Node: PC Dynamic805897 +Node: PC Using808260 +Node: Cygwin812808 +Node: MSYS813792 +Node: VMS Installation814298 +Node: VMS Compilation814902 +Node: VMS Installation Details816479 +Node: VMS Running818109 +Node: VMS POSIX819706 +Node: VMS Old Gawk821004 +Node: Unsupported821473 +Node: Atari Installation821935 +Node: Atari Compiling823222 +Node: Atari Using825111 +Node: BeOS Installation827958 +Node: Tandem Installation829103 +Node: Bugs830782 +Node: Other Versions834614 +Node: Notes839836 +Node: Compatibility Mode840528 +Node: Additions841311 +Node: Adding Code842061 +Node: New Ports848113 +Node: Dynamic Extensions852245 +Node: Internals853626 +Node: Plugin License864031 +Node: Sample Library864665 +Node: Internal File Description865329 +Node: Internal File Ops869024 +Ref: Internal File Ops-Footnote-1873900 +Node: Using Internal File Ops874048 +Node: Future Extensions876073 +Node: Basic Concepts880110 +Node: Basic High Level880867 +Ref: Basic High Level-Footnote-1884983 +Node: Basic Data Typing885177 +Node: Floating Point Issues889614 +Node: String Conversion Precision890697 +Ref: String Conversion Precision-Footnote-1892391 +Node: Unexpected Results892500 +Node: POSIX Floating Point Problems894326 +Ref: POSIX Floating Point Problems-Footnote-1898025 +Node: Glossary898063 +Node: Copying921831 +Node: GNU Free Documentation License959388 +Node: next-edition984532 +Node: unresolved984884 +Node: revision985384 +Node: consistency985807 +Node: Index989160 End Tag Table diff --git a/doc/gawk.texi b/doc/gawk.texi index 59770d5f..0ebfd1b4 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -364,7 +364,6 @@ particular records in a file and perform operations upon them. * Getline Notes:: Important things to know about @code{getline}. * Getline Summary:: Summary of @code{getline} Variants. -* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Command line directories:: What happens if you put a directory on the command line. * Print:: The @code{print} statement. @@ -436,6 +435,7 @@ particular records in a file and perform operations upon them. * I/O And BEGIN/END:: I/O issues in BEGIN/END rules. * Empty:: The empty pattern, which matches every record. +* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Using Shell Variables:: How to use shell variables with @command{awk}. * Action Overview:: What goes into an action. @@ -4090,7 +4090,6 @@ used with it do not have to be named on the @command{awk} command line * Multiple Line:: Reading multi-line records. * Getline:: Reading files under explicit program control using the @code{getline} function. -* BEGINFILE/ENDFILE:: Two special patterns for advanced control. * Command line directories:: What happens if you put a directory on the command line. @end menu @@ -6127,72 +6126,6 @@ listing which built-in variables are set by each one. @c ENDOFRANGE inex @c ENDOFRANGE infir -@node BEGINFILE/ENDFILE -@section The @code{BEGINFILE} and @code{ENDFILE} Special Patterns -@cindex @code{BEGINFILE} special pattern -@cindex @code{ENDFILE} special pattern - -@quotation NOTE -This @value{SECTION} describes a @command{gawk}-specific feature. -@end quotation - -Two special kinds of rule, @code{BEGINFILE} and @code{ENDFILE}, give -you ``hooks'' into @command{gawk}'s command-line file processing loop. -As with the @code{BEGIN} and @code{END} rules (@pxref{BEGIN/END}), all -@code{BEGINFILE} rules in a program are merged, in the order they are -read by @command{gawk}, and all @code{ENDFILE} rules are merged as well. - -The body of the @code{BEGINFILE} rules is executed just before -@command{gawk} reads the first record from a file. @code{FILENAME} -is set to the name of the current file, and @code{FNR} is set to zero. - -The @code{BEGINFILE} rule provides you the opportunity for two tasks -that would otherwise be difficult or impossible to perform: - -@enumerate 1 -@item -You can test if the file is readable. Normally, it is a fatal error if a -file named on the command line cannot be opened for reading. However, -you can bypass the fatal error and move on to the next file on the -command line. - -You do this by checking if the @code{ERRNO} variable is not the empty -string; if so, then @command{gawk} was not able to open the file. In -this case, your program can execute the @code{nextfile} statement -(@pxref{Nextfile Statement}). This casuses @command{gawk} to skip -the file entirely. Otherwise, @command{gawk} exits with the usual -fatal error. - -@item -If you have written extensions that modify the record handling (by inserting -an ``open hook''), you can invoke them at this point, before @command{gawk} -has started processing the file. (This is a @emph{very} advanced feature, -currently used only by the @uref{http://xgawk.sourceforge.net, XMLgawk project}.) -@end enumerate - -The @code{ENDFILE} rule is called when @command{gawk} has finished processing -the last record in an input file. For the last input file, -it will be called before any @code{END} rules. - -Normally, when an error occurs when reading input in the normal input -processing loop, the error is fatal. However, if an @code{ENDFILE} -rule is present, the error becomes non-fatal, and instead @code{ERRNO} -is set. This makes it possible to catch and process I/O errors at the -level of the @command{awk} program. - -The @code{next} statement (@pxref{Next Statement}) is not allowed inside -either a @code{BEGINFILE} or and @code{ENDFILE} rule. The @code{nextfile} -statement (@pxref{Nextfile Statement}) is allowed only inside a -@code{BEGINFILE} rule, but not inside an @code{ENDFILE} rule. - -The @code{getline} statement (@pxref{Getline}) is restricted inside -both @code{BEGINFILE} and @code{ENDFILE}. Only the @samp{getline -@var{variable} < @var{file}} form is allowed. - -@code{BEGINFILE} and @code{ENDFILE} are @command{gawk} extensions. -In most other @command{awk} implementations, or if @command{gawk} is in -compatibility mode (@pxref{Options}), they are not special. - @node Command line directories @section Directories On The Command Line @cindex directories, command line @@ -9830,6 +9763,7 @@ building something useful. * Ranges:: Pairs of patterns specify record ranges. * BEGIN/END:: Specifying initialization and cleanup rules. * Empty:: The empty pattern, which matches every record. +* BEGINFILE/ENDFILE:: Two special patterns for advanced control. @end menu @cindex patterns, types of @@ -9863,6 +9797,12 @@ Special patterns for you to supply startup or cleanup actions for your @item @var{empty} The empty pattern matches every input record. (@xref{Empty}.) + +@item BEGINFILE +@itemx ENDFILE +Special patterns for you to supply startup or cleanup actions to +done on a per file basis. +(@xref{BEGINFILE/ENDFILE}.) @end table @node Regexp Patterns @@ -9916,7 +9856,7 @@ whose first field is precisely @samp{foo}: @cindex @code{!} (exclamation point), @code{!~} operator @cindex exclamation point (@code{!}), @code{!~} operator @example -$ awk '$1 == "foo" @{ print $2 @}' BBS-list +$ @kbd{awk '$1 == "foo" @{ print $2 @}' BBS-list} @end example @noindent @@ -9925,7 +9865,7 @@ Contrast this with the following regular expression match, which accepts any record with a first field that contains @samp{foo}: @example -$ awk '$1 ~ /foo/ @{ print $2 @}' BBS-list +$ @kbd{awk '$1 ~ /foo/ @{ print $2 @}' BBS-list} @print{} 555-1234 @print{} 555-6699 @print{} 555-6480 @@ -9947,7 +9887,7 @@ For example, the following command prints all the records in @file{BBS-list} that contain both @samp{2400} and @samp{foo}: @example -$ awk '/2400/ && /foo/' BBS-list +$ @kbd{awk '/2400/ && /foo/' BBS-list} @print{} fooey 555-1234 2400/1200/300 B @end example @@ -9956,7 +9896,7 @@ The following command prints all records in (or both, of course): @example -$ awk '/2400/ || /foo/' BBS-list +$ @kbd{awk '/2400/ || /foo/' BBS-list} @print{} alpo-net 555-3412 2400/1200/300 A @print{} bites 555-1675 2400/1200/300 A @print{} fooey 555-1234 2400/1200/300 B @@ -9970,7 +9910,7 @@ The following command prints all records in @file{BBS-list} that do @emph{not} contain the string @samp{foo}: @example -$ awk '! /foo/' BBS-list +$ @kbd{awk '! /foo/' BBS-list} @print{} aardvark 555-5553 1200/300 B @print{} alpo-net 555-3412 2400/1200/300 A @print{} barfly 555-7685 1200/300 A @@ -9982,10 +9922,13 @@ $ awk '! /foo/' BBS-list @cindex @code{BEGIN} pattern, Boolean patterns and @cindex @code{END} pattern, Boolean patterns and +@cindex @code{BEGINFILE} pattern, Boolean patterns and +@cindex @code{ENDFILE} pattern, Boolean patterns and The subexpressions of a Boolean operator in a pattern can be constant regular expressions, comparisons, or any other @command{awk} expressions. Range patterns are not expressions, so they cannot appear inside Boolean -patterns. Likewise, the special patterns @code{BEGIN} and @code{END}, +patterns. Likewise, the special patterns @code{BEGIN}, @code{END}, +@code{BEGINFILE} and @code{ENDFILE}, which never match any input record, are not expressions and cannot appear inside Boolean patterns. @@ -10070,11 +10013,9 @@ This cannot be changed or worked around; range patterns do not combine with other patterns: @example -$ echo Yes | gawk '(/1/,/2/) || /Yes/' +$ @kbd{echo Yes | gawk '(/1/,/2/) || /Yes/'} @error{} gawk: cmd. line:1: (/1/,/2/) || /Yes/ -@error{} gawk: cmd. line:1: ^ parse error -@error{} gawk: cmd. line:2: (/1/,/2/) || /Yes/ -@error{} gawk: cmd. line:2: ^ unexpected newline +@error{} gawk: cmd. line:1: ^ syntax error @end example @node BEGIN/END @@ -10106,10 +10047,10 @@ is read. Likewise, an @code{END} rule is executed once only, after all the input is read. For example: @example -$ awk ' -> BEGIN @{ print "Analysis of \"foo\"" @} -> /foo/ @{ ++n @} -> END @{ print "\"foo\" appears", n, "times." @}' BBS-list +$ @kbd{awk '} +> @kbd{BEGIN @{ print "Analysis of \"foo\"" @}} +> @kbd{/foo/ @{ ++n @}} +> @kbd{END @{ print "\"foo\" appears", n, "times." @}' BBS-list} @print{} Analysis of "foo" @print{} "foo" appears 4 times. @end example @@ -10194,7 +10135,7 @@ other implementations, do not. The third point follows from the first two. The meaning of @samp{print} inside a @code{BEGIN} or @code{END} rule is the same as always: @samp{print $0}. If @code{$0} is the null string, then this prints an -empty line. Many long time @command{awk} programmers use an unadorned +empty record. Many long time @command{awk} programmers use an unadorned @samp{print} in @code{BEGIN} and @code{END} rules, to mean @samp{@w{print ""}}, relying on @code{$0} being null. Although one might generally get away with this in @code{BEGIN} rules, it is a very bad idea in @code{END} rules, @@ -10228,6 +10169,72 @@ awk '@{ print $1 @}' BBS-list @noindent prints the first field of every record. + +@node BEGINFILE/ENDFILE +@subsection The @code{BEGINFILE} and @code{ENDFILE} Special Patterns +@cindex @code{BEGINFILE} special pattern +@cindex @code{ENDFILE} special pattern + +@quotation NOTE +This @value{SECTION} describes a @command{gawk}-specific feature. +@end quotation + +Two special kinds of rule, @code{BEGINFILE} and @code{ENDFILE}, give +you ``hooks'' into @command{gawk}'s command-line file processing loop. +As with the @code{BEGIN} and @code{END} rules (@pxref{BEGIN/END}), all +@code{BEGINFILE} rules in a program are merged, in the order they are +read by @command{gawk}, and all @code{ENDFILE} rules are merged as well. + +The body of the @code{BEGINFILE} rules is executed just before +@command{gawk} reads the first record from a file. @code{FILENAME} +is set to the name of the current file, and @code{FNR} is set to zero. + +The @code{BEGINFILE} rule provides you the opportunity for two tasks +that would otherwise be difficult or impossible to perform: + +@enumerate 1 +@item +You can test if the file is readable. Normally, it is a fatal error if a +file named on the command line cannot be opened for reading. However, +you can bypass the fatal error and move on to the next file on the +command line. + +You do this by checking if the @code{ERRNO} variable is not the empty +string; if so, then @command{gawk} was not able to open the file. In +this case, your program can execute the @code{nextfile} statement +(@pxref{Nextfile Statement}). This casuses @command{gawk} to skip +the file entirely. Otherwise, @command{gawk} exits with the usual +fatal error. + +@item +If you have written extensions that modify the record handling (by inserting +an ``open hook''), you can invoke them at this point, before @command{gawk} +has started processing the file. (This is a @emph{very} advanced feature, +currently used only by the @uref{http://xgawk.sourceforge.net, XMLgawk project}.) +@end enumerate + +The @code{ENDFILE} rule is called when @command{gawk} has finished processing +the last record in an input file. For the last input file, +it will be called before any @code{END} rules. + +Normally, when an error occurs when reading input in the normal input +processing loop, the error is fatal. However, if an @code{ENDFILE} +rule is present, the error becomes non-fatal, and instead @code{ERRNO} +is set. This makes it possible to catch and process I/O errors at the +level of the @command{awk} program. + +The @code{next} statement (@pxref{Next Statement}) is not allowed inside +either a @code{BEGINFILE} or and @code{ENDFILE} rule. The @code{nextfile} +statement (@pxref{Nextfile Statement}) is allowed only inside a +@code{BEGINFILE} rule, but not inside an @code{ENDFILE} rule. + +The @code{getline} statement (@pxref{Getline}) is restricted inside +both @code{BEGINFILE} and @code{ENDFILE}. Only the @samp{getline +@var{variable} < @var{file}} form is allowed. + +@code{BEGINFILE} and @code{ENDFILE} are @command{gawk} extensions. +In most other @command{awk} implementations, or if @command{gawk} is in +compatibility mode (@pxref{Options}), they are not special. @c ENDOFRANGE pat @node Using Shell Variables @@ -10249,7 +10256,7 @@ the variable's value into the program inside the script. For example, in the following program: @example -echo -n "Enter search pattern: " +printf "Enter search pattern: " read pattern awk "/$pattern/ "'@{ nmatches++ @} END @{ print nmatches, "found" @}' /path/to/data @@ -10277,7 +10284,7 @@ The following shows how to redo the previous example using this technique: @example -echo -n "Enter search pattern: " +printf "Enter search pattern: " read pattern awk -v pat="$pattern" '$0 ~ pat @{ nmatches++ @} END @{ print nmatches, "found" @}' /path/to/data @@ -10310,8 +10317,8 @@ both) may be omitted. The purpose of the @dfn{action} is to tell in outline, an @command{awk} program generally looks like this: @example -@r{[}@var{pattern}@r{]} @r{[}@{ @var{action} @}@r{]} -@r{[}@var{pattern}@r{]} @r{[}@{ @var{action} @}@r{]} +@r{[}@var{pattern}@r{]} @{ @var{action} @} + @var{pattern} @r{[}@{ @var{action} @}@r{]} @dots{} function @var{name}(@var{args}) @{ @dots{} @} @dots{} @@ -10387,7 +10394,7 @@ For deleting array elements. @dfn{Control statements}, such as @code{if}, @code{while}, and so on, control the flow of execution in @command{awk} programs. Most of the -control statements in @command{awk} are patterned on similar statements in C. +control statements in @command{awk} are patterned after similar statements in C. @cindex compound statements@comma{} control statements and @cindex statements, compound@comma{} control statements and @@ -10509,7 +10516,8 @@ the loop. This example prints the first three fields of each record, one per line: @example -awk '@{ i = 1 +awk '@{ + i = 1 while (i <= 3) @{ print $i i++ @@ -10562,7 +10570,8 @@ is false to begin with. The following is an example of a @code{do} statement: @example -@{ i = 1 +@{ + i = 1 do @{ print $0 i++ @@ -10602,7 +10611,8 @@ compares it against the desired number of iterations. For example: @example -awk '@{ for (i = 1; i <= 3; i++) +awk '@{ + for (i = 1; i <= 3; i++) print $i @}' inventory-shipped @end example @@ -10665,7 +10675,6 @@ type and more natural to think of. Counting the number of iterations is very common in loops. It can be easier to think of this counting as part of looping rather than as something to do inside the loop. -@ifinfo @cindex @code{in} operator There is an alternate version of the @code{for} loop, for iterating over all the indices of an array: @@ -10678,7 +10687,6 @@ for (i in array) @noindent @xref{Scanning an Array}, for more information on this version of the @code{for} loop. -@end ifinfo @node Switch Statement @subsection The @code{switch} Statement @@ -10710,7 +10718,7 @@ default: Control flow in the @code{switch} statement works as it does in C. Once a match to a given -case is made, case statement bodies are executed until a @code{break}, +case is made, the case statement bodies execute until a @code{break}, @code{continue}, @code{next}, @code{nextfile} or @code{exit} is encountered, or the end of the @code{switch} statement itself. For example: @@ -10741,8 +10749,10 @@ the @code{print} statement is executed and then falls through into the the @minus{}1 case will also be executed since the @code{default} does not halt execution. -This feature is a @command{gawk} extension, and is not available in -POSIX @command{awk}. +This @code{switch} statement is a @command{gawk} extension. +If @command{gawk} is in compatibility mode +(@pxref{Options}), +it is not available. @node Break Statement @subsection The @code{break} Statement @@ -10758,9 +10768,10 @@ numbers: # find smallest divisor of num @{ num = $1 - for (div = 2; div*div <= num; div++) + for (div = 2; div * div <= num; div++) @{ if (num % div == 0) break + @} if (num % div == 0) printf "Smallest divisor of %d is %d\n", num, div else @@ -10788,7 +10799,7 @@ an @code{if}: printf "Smallest divisor of %d is %d\n", num, div break @} - if (div*div > num) @{ + if (div * div > num) @{ printf "%d is prime\n", num break @} @@ -10796,6 +10807,10 @@ an @code{if}: @} @end example +The @code{break} statement is also used to break out of the +@code{switch} statement. +This is discussed in @ref{Switch Statement}. + @c @cindex @code{break}, outside of loops @c @cindex historical features @c @cindex @command{awk} language, POSIX version @@ -10803,7 +10818,8 @@ an @code{if}: @cindex dark corner, @code{break} statement @cindex @command{gawk}, @code{break} statement in The @code{break} statement has no meaning when -used outside the body of a loop. However, although it was never documented, +used outside the body of a loop or @code{switch}. +However, although it was never documented, historical implementations of @command{awk} treated the @code{break} statement outside of a loop as if it were a @code{next} statement (@pxref{Next Statement}). @@ -10815,7 +10831,7 @@ nor does @command{gawk}. @subsection The @code{continue} Statement @cindex @code{continue} statement -As with @code{break}, the @code{continue} statement is used only inside +Similar to @code{break}, the @code{continue} statement is used only inside @code{for}, @code{while}, and @code{do} loops. It skips over the rest of the loop body, causing the next cycle around the loop to begin immediately. Contrast this with @code{break}, which jumps out @@ -10919,6 +10935,13 @@ messages should be. For more detail see @ref{Special Files}. +If the @code{next} statement causes the end of the input to be reached, +then the code in any @code{END} rules is executed. +@xref{BEGIN/END}. + +The @code{next} statement is not inside @code{BEGINFILE} and +@code{ENDFILE} rules. @xref{BEGINFILE/ENDFILE}. + @c @cindex @command{awk} language, POSIX version @c @cindex @code{next}, inside a user-defined function @cindex @code{BEGIN} pattern, @code{next}/@code{nextfile} statements and @@ -10936,9 +10959,6 @@ statement inside function bodies Just as with any other @code{next} statement, a @code{next} statement inside a function body reads the next record and starts processing it with the first rule in the program. -If the @code{next} statement causes the end of the input to be reached, -then the code in any @code{END} rules is executed. -@xref{BEGIN/END}. @node Nextfile Statement @subsection Using @command{gawk}'s @code{nextfile} Statement @@ -10972,6 +10992,10 @@ Normally, in order to move on to the next @value{DF}, a program has to continue scanning the unwanted records. The @code{nextfile} statement accomplishes this much more efficiently. +In addition, @code{nextfile} is useful inside a @code{BEGINFILE} +rule to skip over a file that would otherwise cause @command{gawk} +to exit with a fatal error. @xref{BEGINFILE/ENDFILE}. + While one might think that @samp{close(FILENAME)} would accomplish the same as @code{nextfile}, this isn't true. @code{close()} is reserved for closing files, pipes, and coprocesses that are @@ -10986,26 +11010,12 @@ statement. @cindex functions, user-defined, @code{next}/@code{nextfile} statements and @cindex @code{nextfile} statement, user-defined functions and -The current version of the Bell Laboratories @command{awk} -(@pxref{Other Versions}) -also supports @code{nextfile}. However, it doesn't allow the @code{nextfile} -statement inside function bodies -(@pxref{User-defined}). -@command{gawk} does; a @code{nextfile} inside a -function body reads the next record and starts processing it with the -first rule in the program, just as any other @code{nextfile} statement. - -@cindex @code{next file} statement, in @command{gawk} -@cindex @command{gawk}, @code{next file} statement in -@cindex @code{nextfile} statement, in @command{gawk} -@cindex @command{gawk}, @code{nextfile} statement in -@strong{Caution:} Versions of @command{gawk} prior to 3.0 used two -words (@samp{next file}) for the @code{nextfile} statement. -In @value{PVERSION} 3.0, this was changed -to one word, because the treatment of @samp{file} was -inconsistent. When it appeared after @code{next}, @samp{file} was a keyword; -otherwise, it was a regular identifier. The old usage is no longer -accepted; @samp{next file} generates a syntax error. +The current version of the Bell Laboratories @command{awk} (@pxref{Other +Versions}) also supports @code{nextfile}. However, it doesn't allow the +@code{nextfile} statement inside function bodies (@pxref{User-defined}). +@command{gawk} does; a @code{nextfile} inside a function body reads the +next record and starts processing it with the first rule in the program, +just as any other @code{nextfile} statement. The @code{nextfile} statement has a special purpose when used inside a @code{BEGINFILE} rule; see @ref{BEGINFILE/ENDFILE}. @@ -11030,7 +11040,7 @@ read. However, if an @code{END} rule is present, as part of executing the @code{exit} statement, the @code{END} rule is executed (@pxref{BEGIN/END}). -If @code{exit} is used as part of an @code{END} rule, it causes +If @code{exit} is used in the body of an @code{END} rule, it causes the program to stop immediately. An @code{exit} statement that is not part of a @code{BEGIN} or @code{END} @@ -11207,8 +11217,9 @@ expression that matches the separations between fields in an input record. If the value is the null string (@code{""}), then each character in the record becomes a separate field. (This behavior is a @command{gawk} extension. POSIX @command{awk} does not -specify the behavior when @code{FS} is the null string.) -@strong{FIXME: NEXT ED:} Mark as common extension. +specify the behavior when @code{FS} is the null string. +Nonetheless, some other versions of @command{awk} also treat +@code{""} specially.) @cindex POSIX @command{awk}, @code{FS} variable and The default value is @w{@code{" "}}, a string consisting of a single @@ -11225,7 +11236,8 @@ awk -F, '@var{program}' @var{input-files} @end example @cindex @command{gawk}, field separators and -If @command{gawk} is using @code{FIELDWIDTHS} for field splitting, +If @command{gawk} is using @code{FIELDWIDTHS} or @code{FPAT} +for field splitting, assigning a value to @code{FS} causes @command{gawk} to return to the normal, @code{FS}-based field splitting. An easy way to do this is to simply say @samp{FS = FS}, perhaps with an explanatory comment. @@ -11383,10 +11395,10 @@ Unlike most @command{awk} arrays, In the following example: @example -$ awk 'BEGIN @{ -> for (i = 0; i < ARGC; i++) -> print ARGV[i] -> @}' inventory-shipped BBS-list +$ @kbd{awk 'BEGIN @{} +> @kbd{for (i = 0; i < ARGC; i++)} +> @kbd{print ARGV[i]} +> @kbd{@}' inventory-shipped BBS-list} @print{} awk @print{} inventory-shipped @print{} BBS-list @@ -11404,11 +11416,13 @@ The names @code{ARGC} and @code{ARGV}, as well as the convention of indexing the array from 0 to @code{ARGC} @minus{} 1, are derived from the C language's method of accessing command-line arguments. +@cindex dark corner, value of @code{ARGV[0]} The value of @code{ARGV[0]} can vary from system to system. Also, you should note that the program text is @emph{not} included in @code{ARGV}, nor are any of @command{awk}'s command-line options. @xref{ARGC and ARGV}, for information about how @command{awk} uses these variables. +@value{DARKCORNER} @cindex @code{ARGIND} variable @cindex differences in @command{awk} and @command{gawk}, @code{ARGIND} variable @@ -11438,7 +11452,7 @@ it is not special. @cindex @code{ENVIRON} variable @cindex environment variables @item ENVIRON -An associative array that contains the values of the environment. The array +An associative array containing the values of the environment. The array indices are the environment variable names; the elements are the values of the particular environment variables. For example, @code{ENVIRON["HOME"]} might be @file{/home/arnold}. Changing this array @@ -11503,7 +11517,7 @@ inside a @code{BEGIN} rule can give @item FNR The current record number in the current file. @code{FNR} is incremented each time a new record is read -(@pxref{Getline}). It is reinitialized +(@pxref{Records}). It is reinitialized to zero each time a new input file is started. @cindex @code{NF} variable @@ -11541,10 +11555,10 @@ are guaranteed to be available: @table @code @item PROCINFO["egid"] -The value of the @code{getegid} system call. +The value of the @code{getegid()} system call. @item PROCINFO["euid"] -The value of the @code{geteuid} system call. +The value of the @code{geteuid()} system call. @item PROCINFO["FS"] This is @@ -11553,7 +11567,7 @@ This is or it is @code{"FPAT"} if field matching with @code{FPAT} is in effect. @item PROCINFO["gid"] -The value of the @code{getgid} system call. +The value of the @code{getgid()} system call. @item PROCINFO["pgrpid"] The process group ID of the current process. @@ -11565,11 +11579,10 @@ The process ID of the current process. The parent process ID of the current process. @item PROCINFO["uid"] -The value of the @code{getuid} system call. +The value of the @code{getuid()} system call. @item PROCINFO["version"] -The version of @command{gawk}. This is available from -@value{PVERSION} 3.1.4 and later. +The version of @command{gawk}. @end table On some systems, there may be elements in the array, @code{"group1"} @@ -11578,6 +11591,10 @@ supplementary groups that the process has. Use the @code{in} operator to test for these elements (@pxref{Reference to Elements}). +The @code{PROCINFO} array is also used to cause coprocesses +to communicate over pseudo-ttys instead of through two-way pipes; +this is discussed further in @ref{Two-way I/O}. + This array is a @command{gawk} extension. In other @command{awk} implementations, or if @command{gawk} is in compatibility mode @@ -11628,14 +11645,14 @@ value of the number of records read. This means that a program can change these variables and their new values are incremented for each record. @value{DARKCORNER} -This is demonstrated in the following example: +The following example shows this: @example -$ echo '1 -> 2 -> 3 -> 4' | awk 'NR == 2 @{ NR = 17 @} -> @{ print NR @}' +$ @kbd{echo '1} +> @kbd{2} +> @kbd{3} +> @kbd{4' | awk 'NR == 2 @{ NR = 17 @}} +> @kbd{@{ print NR @}'} @print{} 1 @print{} 17 @print{} 18 @@ -11660,10 +11677,10 @@ presented the following program describing the information contained in @code{AR and @code{ARGV}: @example -$ awk 'BEGIN @{ -> for (i = 0; i < ARGC; i++) -> print ARGV[i] -> @}' inventory-shipped BBS-list +$ @kbd{awk 'BEGIN @{} +> @kbd{for (i = 0; i < ARGC; i++)} +> @kbd{print ARGV[i]} +> @kbd{@}' inventory-shipped BBS-list} @print{} awk @print{} inventory-shipped @print{} BBS-list @@ -11674,21 +11691,27 @@ In this example, @code{ARGV[0]} contains @samp{awk}, @code{ARGV[1]} contains @samp{inventory-shipped}, and @code{ARGV[2]} contains @samp{BBS-list}. Notice that the @command{awk} program is not entered in @code{ARGV}. The -other special command-line options, with their arguments, are also not +other command-line options, with their arguments, are also not entered. This includes variable assignments done with the @option{-v} option (@pxref{Options}). Normal variable assignments on the command line @emph{are} -treated as arguments and do show up in the @code{ARGV} array: +treated as arguments and do show up in the @code{ARGV} array. +Given the following program in a file named @file{showargs.awk}: + +@example +BEGIN @{ + printf "A=%d, B=%d\n", A, B + for (i = 0; i < ARGC; i++) + printf "\tARGV[%d] = %s\n", i, ARGV[i] +@} +END @{ printf "A=%d, B=%d\n", A, B @} +@end example + +@noindent +Running it produces the following: @example -$ cat showargs.awk -@print{} BEGIN @{ -@print{} printf "A=%d, B=%d\n", A, B -@print{} for (i = 0; i < ARGC; i++) -@print{} printf "\tARGV[%d] = %s\n", i, ARGV[i] -@print{} @} -@print{} END @{ printf "A=%d, B=%d\n", A, B @} -$ awk -v A=1 -f showargs.awk B=2 /dev/null +$ @kbd{awk -v A=1 -f showargs.awk B=2 /dev/null} @print{} A=1, B=0 @print{} ARGV[0] = awk @print{} ARGV[1] = B=2 @@ -11724,7 +11747,6 @@ before actual processing of the input begins. of each way of removing elements from @code{ARGV}. The following fragment processes @code{ARGV} in order to examine, and then remove, command-line options: -@strong{FIXME: NEXT ED:} Add xref to rewind() function. @example BEGIN @{ @@ -11775,7 +11797,7 @@ are passed on to the @command{awk} program. @cindex arrays An @dfn{array} is a table of values called @dfn{elements}. The -elements of an array are distinguished by their indices. @dfn{Indices} +elements of an array are distinguished by their @dfn{indices}. Indices may be either numbers or strings. This @value{CHAPTER} describes how arrays work in @command{awk}, @@ -11783,8 +11805,9 @@ how to use array elements, how to scan through every element in an array, and how to remove array elements. It also describes how @command{awk} simulates multidimensional arrays, as well as some of the less obvious points about array usage. -The @value{CHAPTER} finishes with a discussion of @command{gawk}'s facility -for sorting an array based on its indices. +The @value{CHAPTER} moves on to discuss @command{gawk}'s facility +for sorting arrays, and ends with a brief description of @command{gawk}'s +ability to support true multidimensional arrays. @cindex variables, names of @cindex functions, names of @@ -11832,7 +11855,7 @@ an array. @cindex Wall, Larry @quotation -@i{Doing linear scans over an associative array is like tryinng to club someone +@i{Doing linear scans over an associative array is like trying to club someone to death with a loaded Uzi.}@* Larry Wall @end quotation @@ -11869,7 +11892,7 @@ A contiguous array of four elements might look like the following example, conceptually, if the element values are 8, @code{"foo"}, @code{""}, and 30: -@strong{FIXME: NEXT ED:} Use real images here +@c @strong{FIXME: NEXT ED:} Use real images here @iftex @c from Karl Berry, much thanks for the help. @tex @@ -11888,22 +11911,14 @@ conceptually, if the element values are 8, @code{"foo"}, }} @end tex @end iftex -@ifinfo -@example -+---------+---------+--------+---------+ -| 8 | "foo" | "" | 30 | @r{Value} -+---------+---------+--------+---------+ - 0 1 2 3 @r{Index} -@end example -@end ifinfo -@ifxml +@ifnottex @example +---------+---------+--------+---------+ | 8 | "foo" | "" | 30 | @r{Value} +---------+---------+--------+---------+ 0 1 2 3 @r{Index} @end example -@end ifxml +@end ifnottex @noindent Only the values are stored; the indices are implicit from the order of @@ -11921,10 +11936,10 @@ that each array is a collection of pairs: an index and its corresponding array element value: @example -@r{Element} 3 @r{Value} 30 -@r{Element} 1 @r{Value} "foo" -@r{Element} 0 @r{Value} 8 -@r{Element} 2 @r{Value} "" +@r{Index} 3 @r{Value} 30 +@r{Index} 1 @r{Value} "foo" +@r{Index} 0 @r{Value} 8 +@r{Index} 2 @r{Value} "" @end example @noindent @@ -11935,11 +11950,11 @@ at any time. For example, suppose a tenth element is added to the array whose value is @w{@code{"number ten"}}. The result is: @example -@r{Element} 10 @r{Value} "number ten" -@r{Element} 3 @r{Value} 30 -@r{Element} 1 @r{Value} "foo" -@r{Element} 0 @r{Value} 8 -@r{Element} 2 @r{Value} "" +@r{Index} 10 @r{Value} "number ten" +@r{Index} 3 @r{Value} 30 +@r{Index} 1 @r{Value} "foo" +@r{Index} 0 @r{Value} 8 +@r{Index} 2 @r{Value} "" @end example @noindent @@ -11954,10 +11969,10 @@ an index. For example, the following is an array that translates words from English to French: @example -@r{Element} "dog" @r{Value} "chien" -@r{Element} "cat" @r{Value} "chat" -@r{Element} "one" @r{Value} "un" -@r{Element} 1 @r{Value} "un" +@r{Index} "dog" @r{Value} "chien" +@r{Index} "cat" @r{Value} "chat" +@r{Index} "one" @r{Value} "un" +@r{Index} 1 @r{Value} "un" @end example @noindent @@ -12009,10 +12024,25 @@ of array @code{foo} at index @samp{4.3}. A reference to an array element that has no recorded value yields a value of @code{""}, the null string. This includes elements that have not been assigned any value as well as elements that have been -deleted (@pxref{Delete}). Such a reference -automatically creates that array element, with the null string as its value. -(In some cases, this is unfortunate, because it might waste memory inside -@command{awk}.) +deleted (@pxref{Delete}). + +@quotation NOTE +A reference to an element that does not exist @emph{automatically} creates +that array element, with the null string as its value. (In some cases, +this is unfortunate, because it might waste memory inside @command{awk}.) + +Novice @command{awk} programmers often make the mistake of checking if +an element exists by checking if the value is empty: + +@example +# Check if "foo" exists in a: @ii{Incorrect!} +if (a["foo"] != "") @dots{} +@end example + +@noindent +This is incorrect, since this will @emph{create} @code{a["foo"]} +if it didn't exist before! +@end quotation @c @cindex arrays, @code{in} operator and @cindex @code{in} operator, arrays and @@ -12296,7 +12326,9 @@ delete an array and then use the array's name as a scalar (i.e., a regular variable). For example, the following does not work: @example -a[1] = 3; delete a; a = 3 +a[1] = 3 +delete a +a = 3 @end example @node Numeric Array Subscripts @@ -12306,7 +12338,7 @@ a[1] = 3; delete a; a = 3 @cindex arrays, subscripts @cindex subscripts in arrays, numbers as @cindex @code{CONVFMT} variable, array subscripts and -An important aspect about arrays to remember is that @emph{array subscripts +An important aspect to remember about arrays is that @emph{array subscripts are always strings}. When a numeric value is used as a subscript, it is converted to a string value before being used for subscripting (@pxref{Conversion}). @@ -12333,7 +12365,7 @@ The program then changes the value of @code{CONVFMT}. The test @samp{(xyz in data)} generates a new string value from @code{xyz}---this time @code{"12.15"}---because the value of @code{CONVFMT} only allows two significant digits. This test fails, -since @code{"12.15"} is a different string from @code{"12.153"}. +since @code{"12.15"} is different from @code{"12.153"}. @cindex converting, during subscripting According to the rules for conversions @@ -12362,7 +12394,7 @@ all refer to the same element! As with many things in @command{awk}, the majority of the time things work as one would expect them to. But it is useful to have a precise -knowledge of the actual rules which sometimes can have a subtle +knowledge of the actual rules since they can sometimes have a subtle effect on your programs. @node Uninitialized Subscripts @@ -12378,13 +12410,13 @@ A reasonable attempt to do so (with some test data) might look like this: @example -$ echo 'line 1 -> line 2 -> line 3' | awk '@{ l[lines] = $0; ++lines @} -> END @{ -> for (i = lines-1; i >= 0; --i) -> print l[i] -> @}' +$ @kbd{echo 'line 1} +> @kbd{line 2} +> @kbd{line 3' | awk '@{ l[lines] = $0; ++lines @}} +> @kbd{END @{} +> @kbd{for (i = lines-1; i >= 0; --i)} +> @kbd{print l[i]} +> @kbd{@}'} @print{} line 3 @print{} line 2 @end example @@ -12392,7 +12424,8 @@ $ echo 'line 1 Unfortunately, the very first line of input data did not come out in the output! -At first glance, this program should have worked. The variable @code{lines} +Upon first glance, we would think that this program should have worked. +The variable @code{lines} is uninitialized, and uninitialized variables have the numeric value zero. So, @command{awk} should have printed the value of @code{l[0]}. @@ -12473,7 +12506,7 @@ combined strings that are ambiguous. Suppose that @code{SUBSEP} is stored as @samp{foo["a@@b@@c"]}. To test whether a particular index sequence exists in a -multidimensional array, use the same operator (@samp{in}) that is +multidimensional array, use the same operator (@code{in}) that is used for single dimensional arrays. Write the whole sequence of indices in parentheses, separated by commas, as the left operand: @@ -12626,7 +12659,7 @@ However, the @code{source} array is not affected. Often, what's needed is to sort on the values of the @emph{indices} instead of the values of the elements. -To do that, starting with @command{gawk} 3.1.2, use the +To do that, use the @code{asorti()} function. The interface is identical to that of @code{asort()}, except that the index values are used for sorting, and become the values of the result array: @@ -12637,34 +12670,15 @@ become the values of the result array: END @{ n = asorti(source, dest) for (i = 1; i <= n; i++) @{ - @var{do something with} dest[i] @i{Work with sorted indices directly} + @ii{Work with sorted indices directly:} + @var{do something with} dest[i] @dots{} - @var{do something with} source[dest[i]] @i{Access original array via sorted indices} + @ii{Access original array via sorted indices:} + @var{do something with} source[dest[i]] @} @} @end example -If your version of @command{gawk} is 3.1.0 or 3.1.1, you don't -have @code{asorti()}. Instead, use a helper array -to hold the sorted index values, and then access the original array's -elements. It works in the following way: - -@example -@var{populate the array} data -# copy indices -j = 1 -for (i in data) @{ - ind[j] = i # index value becomes element value - j++ -@} -n = asort(ind) # index values are now sorted -for (i = 1; i <= n; i++) @{ - @var{do something with} ind[i] @i{Work with sorted indices directly} - @dots{} - @var{do something with} data[ind[i]] @i{Access original array via sorted indices} -@} -@end example - Sorting the array by replacing the indices provides maximal flexibility. To traverse the elements in decreasing order, use a loop that goes from @var{n} down to 1, either over the elements or over the indices. @@ -12686,7 +12700,10 @@ We said previously that comparisons are done using @command{gawk}'s string comparisons, the value of @code{IGNORECASE} also affects sorting for both @code{asort()} and @code{asorti()}. Note also that the locale's sorting order does @emph{not} -come into play; comparisons are based on character values only. +come into play; comparisons are based on character values only.@footnote{This +is true because locale-based comparison occurs only when in POSIX +compatibility mode, and since @code{asort()} and @code{asorti()} are +@command{gawk} extensions, they are not available in that case.} Caveat Emptor. @node Arrays of Arrays @@ -12835,7 +12852,7 @@ This @value{CHAPTER} describes @command{awk}'s built-in functions, which fall into three categories: numeric, string, and I/O. @command{gawk} provides additional groups of functions to work with values that represent time, do -bit manipulation, and internationalize and localize programs. +bit manipulation, sort arrays, and internationalize and localize programs. Besides the built-in functions, @command{awk} has provisions for writing new functions that the rest of a program can use. @@ -12936,53 +12953,43 @@ the built-in functions that work with numbers. Optional parameters are enclosed in square brackets@w{ ([ ]):} @table @code -@item int(@var{x}) -@cindex @code{int()} function -This returns the nearest integer to @var{x}, located between @var{x} and zero and -truncated toward zero. - -For example, @code{int(3)} is 3, @code{int(3.9)} is 3, @code{int(-3.9)} -is @minus{}3, and @code{int(-3)} is @minus{}3 as well. +@item atan2(@var{y}, @var{x}) +@cindex @code{atan2()} function +Return the arctangent of @code{@var{y} / @var{x}} in radians. -@item sqrt(@var{x}) -@cindex @code{sqrt()} function -This returns the positive square root of @var{x}. -@command{gawk} reports an error -if @var{x} is negative. Thus, @code{sqrt(4)} is 2. +@item cos(@var{x}) +@cindex @code{cos()} function +Return the cosine of @var{x}, with @var{x} in radians. @item exp(@var{x}) @cindex @code{exp()} function -This returns the exponential of @var{x} (@code{e ^ @var{x}}) or reports +Return the exponential of @var{x} (@code{e ^ @var{x}}) or report an error if @var{x} is out of range. The range of values @var{x} can have depends on your machine's floating-point representation. -@item log(@var{x}) -@cindex @code{log()} function -This returns the natural logarithm of @var{x}, if @var{x} is positive; -otherwise, it reports an error. - -@item sin(@var{x}) -@cindex @code{sin()} function -This returns the sine of @var{x}, with @var{x} in radians. +@item int(@var{x}) +@cindex @code{int()} function +Return the nearest integer to @var{x}, located between @var{x} and zero and +truncated toward zero. -@item cos(@var{x}) -@cindex @code{cos()} function -This returns the cosine of @var{x}, with @var{x} in radians. +For example, @code{int(3)} is 3, @code{int(3.9)} is 3, @code{int(-3.9)} +is @minus{}3, and @code{int(-3)} is @minus{}3 as well. -@item atan2(@var{y}, @var{x}) -@cindex @code{atan2()} function -This returns the arctangent of @code{@var{y} / @var{x}} in radians. +@item log(@var{x}) +@cindex @code{log()} function +Return the natural logarithm of @var{x}, if @var{x} is positive; +otherwise, report an error. @item rand() @cindex @code{rand()} function @cindex random numbers, @code{rand()}/@code{srand()} functions -This returns a random number. The values of @code{rand()} are +Return a random number. The values of @code{rand()} are uniformly distributed between zero and one. The value could be zero but is never one.@footnote{The C version of @code{rand()} is known to produce fairly poor sequences of random numbers. However, nothing requires that an @command{awk} implementation use the C @code{rand()} to implement the @command{awk} version of @code{rand()}. -In fact, @command{gawk} uses the BSD @code{random} function, which is +In fact, @command{gawk} uses the BSD @code{random()} function, which is considerably better than @code{rand()}, to produce random numbers.} Often random integers are needed instead. Following is a user-defined function @@ -13017,10 +13024,10 @@ function roll(n) @{ return 1 + int(rand() * n) @} @cindex numbers, random @cindex random numbers, seed of -@c MAWK uses a different seed each time. @strong{Caution:} In most @command{awk} implementations, including @command{gawk}, @code{rand()} starts generating numbers from the same -starting number, or @dfn{seed}, each time you run @command{awk}. Thus, +starting number, or @dfn{seed}, each time you run @command{awk}.@footnote{@command{mawk} +uses a different seed each time.} Thus, a program generates the same results each time you run it. The numbers are random within one @command{awk} run but predictable from run to run. This is convenient for debugging, but if you want @@ -13028,9 +13035,19 @@ a program to do different things each time it is used, you must change the seed to a value that is different in each run. To do this, use @code{srand()}. +@item sin(@var{x}) +@cindex @code{sin()} function +Return the sine of @var{x}, with @var{x} in radians. + +@item sqrt(@var{x}) +@cindex @code{sqrt()} function +Return the positive square root of @var{x}. +@command{gawk} reports an error +if @var{x} is negative. Thus, @code{sqrt(4)} is 2. + @item srand(@r{[}@var{x}@r{]}) @cindex @code{srand()} function -The function @code{srand()} sets the starting point, or seed, +Set the starting point, or seed, for generating random numbers to the value @var{x}. Each seed value leads to a particular sequence of random @@ -13041,10 +13058,12 @@ fact generate the same sequence of random numbers over and over again.} Thus, if the seed is set to the same value a second time, the same sequence of random numbers is produced again. +@quotation CAUTION Different @command{awk} implementations use different random-number generators internally. Don't expect the same @command{awk} program to produce the same series of random numbers when executed by different versions of @command{awk}. +@end quotation If the argument @var{x} is omitted, as in @samp{srand()}, then the current date and time of day are used for a seed. This is the way to get random @@ -13074,12 +13093,13 @@ specific to @command{gawk} are marked with a pound sign@w{ (@samp{#}):} @item asort(@var{source} @r{[}, @var{dest}@r{]}) # @cindex arrays, elements, retrieving number of @cindex @code{asort()} function (@command{gawk}) -@code{asort()} is a @command{gawk}-specific extension, returning the number of -elements in the array @var{source}. The contents of @var{source} are -sorted using @command{gawk}'s normal rules for comparing values +Return the number of elements in the array @var{source}. +@command{gawk} sorts the contents of @var{source} +using the normal rules for comparing values (in particular, @code{IGNORECASE} affects the sorting) -and the indices -of the sorted values of @var{source} are replaced with sequential +and replaces +the indices +of the sorted values of @var{source} with sequential integers starting with one. If the optional array @var{dest} is specified, then @var{source} is duplicated into @var{dest}. @var{dest} is then sorted, leaving the indices of @var{source} unchanged. @@ -13114,8 +13134,7 @@ in compatibility mode (@pxref{Options}). @item asorti(@var{source} @r{[}, @var{dest}@r{]}) # @cindex @code{asorti()} function (@command{gawk}) -@code{asorti()} is a @command{gawk}-specific extension, returning the number of -elements in the array @var{source}. +Return the number of elements in the array @var{source}. It works similarly to @code{asort()}, however, the @emph{indices} are sorted, instead of the values. As array indices are always strings, the comparison performed is always a string comparison. (Here too, @@ -13123,19 +13142,18 @@ the comparison performed is always a string comparison. (Here too, The @code{asorti()} function is described in more detail in @ref{Array Sorting}. -It was added in @command{gawk} 3.1.2. @code{asorti()} is a @command{gawk} extension; it is not available in compatibility mode (@pxref{Options}). @item index(@var{in}, @var{find}) @cindex @code{index()} function @cindex searching -This searches the string @var{in} for the first occurrence of the string -@var{find}, and returns the position in characters where that occurrence +Search the string @var{in} for the first occurrence of the string +@var{find}, and return the position in characters where that occurrence begins in the string @var{in}. Consider the following example: @example -$ awk 'BEGIN @{ print index("peanut", "an") @}' +$ @kbd{awk 'BEGIN @{ print index("peanut", "an") @}'} @print{} 3 @end example @@ -13145,7 +13163,7 @@ If @var{find} is not found, @code{index()} returns zero. @item length(@r{[}@var{string}@r{]}) @cindex @code{length()} function -This returns the number of characters in @var{string}. If +Return the number of characters in @var{string}. If @var{string} is a number, the length of the digit string representing that number is returned. For example, @code{length("abcde")} is 5. By contrast, @code{length(15 * 35)} works out to 3. In this example, 15 * 35 = @@ -13174,11 +13192,11 @@ implementations of @command{awk} leave the variable without a type. Consider: @example -$ gawk 'BEGIN @{ print length(x) ; x[1] = 1 @}' +$ @kbd{gawk 'BEGIN @{ print length(x) ; x[1] = 1 @}'} @print{} 0 @error{} gawk: fatal: attempt to use scalar `x' as array -$ nawk 'BEGIN @{ print length(x) ; x[1] = 1 @}' +$ @kbd{nawk 'BEGIN @{ print length(x) ; x[1] = 1 @}'} @print{} 0 @end example @@ -13189,7 +13207,7 @@ warning about this. @cindex differences between @command{gawk} and @command{awk} -Beginning with @command{gawk} @value{PVERSION} 3.1.5, when supplied an +With @command{gawk} and several other @command{awk} implementations, when supplied an array argument, the @code{length()} function returns the number of elements in the array. This is less useful than it might seem at first, as the array is not guaranteed to be indexed from one to the number of elements @@ -13202,16 +13220,16 @@ If @option{--posix} is supplied, using an array argument is a fatal error @item match(@var{string}, @var{regexp} @r{[}, @var{array}@r{]}) @cindex @code{match()} function -The @code{match()} function searches @var{string} for the +Search @var{string} for the longest, leftmost substring matched by the regular expression, -@var{regexp}. It returns the character position, or @dfn{index}, +@var{regexp} and return the character position, or @dfn{index}, at which that substring begins (one, if it starts at the beginning of -@var{string}). If no match is found, it returns zero. +@var{string}). If no match is found, return zero. The @var{regexp} argument may be either a regexp constant (@code{/@dots{}/}) or a string constant (@code{"@dots{}"}). In the latter case, the string is treated as a regexp to be matched. -@ref{Computed Regexps}, for a +@xref{Computed Regexps}, for a discussion of the difference between the two forms, and the implications for writing your program correctly. @@ -13282,24 +13300,23 @@ subexpression. For example: @example -$ echo foooobazbarrrrr | -> gawk '@{ match($0, /(fo+).+(bar*)/, arr) -> print arr[1], arr[2] @}' +$ @kbd{echo foooobazbarrrrr |} +> @kbd{gawk '@{ match($0, /(fo+).+(bar*)/, arr)} +> @kbd{print arr[1], arr[2] @}'} @print{} foooo barrrrr @end example In addition, -beginning with @command{gawk} 3.1.2, multidimensional subscripts are available providing the start index and length of each matched subexpression: @example -$ echo foooobazbarrrrr | -> gawk '@{ match($0, /(fo+).+(bar*)/, arr) -> print arr[1], arr[2] -> print arr[1, "start"], arr[1, "length"] -> print arr[2, "start"], arr[2, "length"] -> @}' +$ @kbd{echo foooobazbarrrrr |} +> @kbd{gawk '@{ match($0, /(fo+).+(bar*)/, arr)} +> @kbd{print arr[1], arr[2]} +> @kbd{print arr[1, "start"], arr[1, "length"]} +> @kbd{print arr[2, "start"], arr[2, "length"]} +> @kbd{@}'} @print{} foooo barrrrr @print{} 1 5 @print{} 9 7 @@ -13316,16 +13333,18 @@ The @var{array} argument to @code{match()} is a (@pxref{Options}), using a third argument is a fatal error. -@item patsplit(@var{string}, @var{array} @r{[}, @var{fieldpat} @r{[}, @var{seps} @r{]} @r{]}) +@item patsplit(@var{string}, @var{array} @r{[}, @var{fieldpat} @r{[}, @var{seps} @r{]} @r{]}) # @cindex @code{patsplit()} function -This function divides @var{string} into pieces defined by @var{fieldpat} -and stores the pieces in @var{array} and the separator strings in the +Divide +@var{string} into pieces defined by @var{fieldpat} +and store the pieces in @var{array} and the separator strings in the @var{seps} array. The first piece is stored in @code{@var{array}[1]}, the second piece in @code{@var{array}[2]}, and so -forth. The string value of the third argument, @var{fieldpat}, is +forth. The third argument, @var{fieldpat}, is a regexp describing the fields in @var{string} (just as @code{FPAT} is -a regexp describing the fields in input records). If -@var{fieldpat} is omitted, the value of @code{FPAT} is used. +a regexp describing the fields in input records). +It may be either a regexp constant or a string. +If @var{fieldpat} is omitted, the value of @code{FPAT} is used. @code{patsplit()} returns the number of elements created. @code{@var{seps}[@var{i}]} is the separator string @@ -13335,6 +13354,14 @@ Any leading separator will be in @code{@var{seps}[0]}. The @code{patsplit()} function splits strings into pieces in a manner similar to the way input lines are split into fields using @code{FPAT}. +Before splitting the string, @code{patsplit()} deletes any previously existing +elements in the arrays @var{array} and @var{seps}. + +The @code{patsplit()} function is a +@command{gawk} extension. In compatibility mode +(@pxref{Options}), +it is not available. + @item split(@var{string}, @var{array} @r{[}, @var{fieldsep} @r{[}, @var{seps} @r{]} @r{]}) @cindex @code{split()} function This function divides @var{string} into pieces separated by @var{fieldsep} @@ -14335,7 +14362,7 @@ it is the number of seconds since 1970-01-01 00:00:00 UTC, not counting leap seconds.@footnote{@xref{Glossary}, especially the entries ``Epoch'' and ``UTC.''} All known POSIX-compliant systems support timestamps from 0 through -@math{2^31 - 1}, which is sufficient to represent times through +@math{2^{31} - 1}, which is sufficient to represent times through 2038-01-19 03:14:07 UTC. Many systems support a wider range of timestamps, including negative timestamps that represent times before the epoch. @@ -15686,17 +15713,17 @@ Here is the result of running the program: @example $ @kbd{gawk -f indirectcall.awk class_data1} -@result{} Biology 101: -@result{} sum: <352.8> -@result{} average: <88.2> -@result{} -@result{} Chemistry 305: -@result{} sum: <356.4> -@result{} average: <89.1> -@result{} -@result{} English 401: -@result{} sum: <376.1> -@result{} average: <94.025> +@print{} Biology 101: +@print{} sum: <352.8> +@print{} average: <88.2> +@print{} +@print{} Chemistry 305: +@print{} sum: <356.4> +@print{} average: <89.1> +@print{} +@print{} English 401: +@print{} sum: <376.1> +@print{} average: <94.025> @end example The ability to use indirect function calls is more powerful than you may @@ -15853,23 +15880,23 @@ Finally, here are the results when the enhanced program is run: @example $ @kbd{gawk -f quicksort.awk -f indirectcall.awk class_data2} -@result{} Biology 101: -@result{} sum: <352.8> -@result{} average: <88.2> -@result{} sort: <78.5 87.0 92.4 94.9> -@result{} rsort: <94.9 92.4 87.0 78.5> -@result{} -@result{} Chemistry 305: -@result{} sum: <356.4> -@result{} average: <89.1> -@result{} sort: <75.2 88.2 94.7 98.3> -@result{} rsort: <98.3 94.7 88.2 75.2> -@result{} -@result{} English 401: -@result{} sum: <376.1> -@result{} average: <94.025> -@result{} sort: <87.1 93.4 95.6 100.0> -@result{} rsort: <100.0 95.6 93.4 87.1> +@print{} Biology 101: +@print{} sum: <352.8> +@print{} average: <88.2> +@print{} sort: <78.5 87.0 92.4 94.9> +@print{} rsort: <94.9 92.4 87.0 78.5> +@print{} +@print{} Chemistry 305: +@print{} sum: <356.4> +@print{} average: <89.1> +@print{} sort: <75.2 88.2 94.7 98.3> +@print{} rsort: <98.3 94.7 88.2 75.2> +@print{} +@print{} English 401: +@print{} sum: <376.1> +@print{} average: <94.025> +@print{} sort: <87.1 93.4 95.6 100.0> +@print{} rsort: <100.0 95.6 93.4 87.1> @end example Remember that you must supply a leading @samp{@@} in front of an indirect function call. diff --git a/missing_d/ChangeLog b/missing_d/ChangeLog index 40e4ede0..4eaa802f 100644 --- a/missing_d/ChangeLog +++ b/missing_d/ChangeLog @@ -1,3 +1,7 @@ +Mon Nov 29 20:09:40 2010 Eli Zaretskii <eliz@gnu.org> + + * strftime.c <tzname>: Don't declare for __MINGW32__. + Thu Nov 25 21:16:58 2010 Arnold D. Robbins <arnold@skeeve.com> * strcoll.c: New file. diff --git a/missing_d/strftime.c b/missing_d/strftime.c index 69a0c517..d4b9ecf4 100644 --- a/missing_d/strftime.c +++ b/missing_d/strftime.c @@ -55,8 +55,10 @@ # endif #endif #if HAVE_TZNAME +#ifndef __MINGW32__ extern char *tzname[]; #endif +#endif /* Do multibyte processing if multibytes are supported, unless multibyte sequences are safe in formats. Multibyte sequences are diff --git a/pc/ChangeLog b/pc/ChangeLog index 7a9f9553..9da36a16 100644 --- a/pc/ChangeLog +++ b/pc/ChangeLog @@ -1,3 +1,9 @@ +Mon Nov 29 20:10:00 2010 Eli Zaretskii <eliz@gnu.org> + + * config.h (HAVE_STRFTIME): Don't define for __MINGW32__. Define + strftime to rpl_strftime, to avoid infinite recursion in + missing_d/strftime.c. + Fri Nov 12 12:36:18 2010 Scott Deifik <scottd.mail@sbcglobal.net> * Makefile.tst: Sync with mainline version. diff --git a/pc/config.h b/pc/config.h index c0295f16..76250eac 100644 --- a/pc/config.h +++ b/pc/config.h @@ -312,8 +312,13 @@ /* Define if you have the strerror function. */ #define HAVE_STRERROR 1 -/* Define if you have the strftime function. */ +#ifdef __MINGW32__ +/* Define if you have the strftime function. __MINGW32__ uses the + replacement from missing_d, to support the %e specifier. */ +#define strftime rpl_strftime +#else #define HAVE_STRFTIME 1 +#endif /* Define if you have the strncasecmp function. */ #define HAVE_STRNCASECMP 1 @@ -533,10 +533,20 @@ again: goto done; for (count++, sp++; *sp != '\0'; sp++) { + static short range_warned = FALSE; + if (*sp == '[') count++; else if (*sp == ']') count--; + if (*sp == '-' && ! range_warned && count == 1 + && sp[-1] != '[' && sp[1] != ']' + && ! isdigit(sp[-1]) && ! isdigit(sp[1])) { + /* found a range, we think */ + range_warned = TRUE; + warning(_("range of the form `[%c-%c]' is locale dependant"), + sp[-1], sp[1]); + } if (count == 0) break; } @@ -60,7 +60,14 @@ #endif /* HAVE_STRERROR */ #ifndef HAVE_STRFTIME +# ifdef __MINGW32__ +/* Need to use underlying_strftime in replacement strftime. */ +# define HAVE_STRFTIME 1 +# endif #include "missing_d/strftime.c" +# ifdef __MINGW32__ +# undef HAVE_STRFTIME +# endif #endif /* HAVE_STRFTIME */ #ifndef HAVE_STRCHR diff --git a/test/ChangeLog b/test/ChangeLog index 2ad540dc..667fc755 100644 --- a/test/ChangeLog +++ b/test/ChangeLog @@ -1,3 +1,8 @@ +Mon Nov 29 21:52:49 2010 Arnold D. Robbins <arnold@skeeve.com> + + * funstack.awk, gsubtst5.ok, igncfs.awk, longwrds.awk, + ofmtbig.awk, subamp.awk: Fix regexes to remove ranges. + Fri Nov 12 11:58:40 2010 Arnold D. Robbins <arnold@skeeve.com> * Makefile.am (dumpvars): New test. diff --git a/test/funstack.awk b/test/funstack.awk index 9a630213..95456903 100644 --- a/test/funstack.awk +++ b/test/funstack.awk @@ -663,7 +663,8 @@ function html_header() function html_label( label) { label = Volume "(" Number "):" Month ":" Year - gsub(/[^A-Za-z0-9():,;.\/\-]/,"",label) + # gsub(/[^A-Za-z0-9():,;.\/\-]/,"",label) + gsub(/[^[:alnum:]():,;.\/\-]/,"",label) return (label) } @@ -673,7 +674,8 @@ function html_length(s) if (HTML) { gsub(/<\/?[^>]*>/,"",s) # remove SGML tags - gsub(/&[A-Za-z0-9]+;/,"",s) # remove SGML entities + # gsub(/&[A-Za-z0-9]+;/,"",s) # remove SGML entities + gsub(/&[[:alnum:]]+;/,"",s) # remove SGML entities } return (length(s)) } @@ -949,8 +951,10 @@ function TeX_to_HTML_nonmath(s) { gsub(/\\\&/, "\\&", s) # reduce TeX ampersands to conventional ones - gsub(/\\[a-z][a-z] +/,"",s) # remove TeX font changes - gsub(/\\[^A-Za-z]/,"",s) # remove remaining TeX control symbols + #gsub(/\\[a-z][a-z] +/,"",s) # remove TeX font changes + gsub(/\\[[:lower:]][[:lower:]] +/,"",s) # remove TeX font changes + #gsub(/\\[^A-Za-z]/,"",s) # remove remaining TeX control symbols + gsub(/\\[^[:alpha:]]/,"",s) # remove remaining TeX control symbols } } return (s) diff --git a/test/gsubtst5.ok b/test/gsubtst5.ok index b038c8af..2119b6c6 100644 --- a/test/gsubtst5.ok +++ b/test/gsubtst5.ok @@ -1 +1,2 @@ +gawk: gsubtst5.awk:95: warning: range of the form `["-\]' is locale dependant ThisIsaTitleMyTitle diff --git a/test/igncfs.awk b/test/igncfs.awk index ebb58b24..5e3c6b66 100644 --- a/test/igncfs.awk +++ b/test/igncfs.awk @@ -1,6 +1,6 @@ BEGIN { IGNORECASE=1 - FS="[^a-z]+" + FS="[^[:lower:]]+" } { for (i=1; i<NF; i++) printf "%s, ", $i diff --git a/test/longwrds.awk b/test/longwrds.awk index d4b4d92d..77654bb0 100644 --- a/test/longwrds.awk +++ b/test/longwrds.awk @@ -9,7 +9,7 @@ BEGIN { { for (i = 1; i <= NF; i++) { tmp = tolower($i) - if (0 != (pos = match(tmp, /([a-z]|-)+/))) + if (0 != (pos = match(tmp, /([[:lower:]]|-)+/))) used[substr(tmp, pos, RLENGTH)] = 1 } } diff --git a/test/ofmtbig.awk b/test/ofmtbig.awk index f1b23849..df4f9bb0 100644 --- a/test/ofmtbig.awk +++ b/test/ofmtbig.awk @@ -88,7 +88,8 @@ $0 ~ /^[0-9]+$/ { next } -$0 ~ /^[a-z]+/ { +# $0 ~ /^[a-z]+/ { +$0 ~ /^[[:lower:]]+/ { print dir, highest, lowest dir = $0 lowest = big diff --git a/test/subamp.awk b/test/subamp.awk index 2638e6ea..731726cf 100644 --- a/test/subamp.awk +++ b/test/subamp.awk @@ -1 +1 @@ -{ sub(/[a-z]/, "&") ; print } +{ sub(/[[:lower:]]/, "&") ; print } |