'\" '\" Copyright (c) 1994 The Regents of the University of California. '\" Copyright (c) 1994-1996 Sun Microsystems, Inc. '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" '\" SCCS: @(#) RegExp.3 1.9 96/08/26 12:59:48 '\" '\" The definitions below are for supplemental macros used in Tcl/Tk '\" manual entries. '\" '\" .AP type name in/out ?indent? '\" Start paragraph describing an argument to a library procedure. '\" type is type of argument (int, etc.), in/out is either "in", "out", '\" or "in/out" to describe whether procedure reads or modifies arg, '\" and indent is equivalent to second arg of .IP (shouldn't ever be '\" needed; use .AS below instead) '\" '\" .AS ?type? ?name? '\" Give maximum sizes of arguments for setting tab stops. Type and '\" name are examples of largest possible arguments that will be passed '\" to .AP later. If args are omitted, default tab stops are used. '\" '\" .BS '\" Start box enclosure. From here until next .BE, everything will be '\" enclosed in one large box. '\" '\" .BE '\" End of box enclosure. '\" '\" .CS '\" Begin code excerpt. '\" '\" .CE '\" End code excerpt. '\" '\" .VS ?version? ?br? '\" Begin vertical sidebar, for use in marking newly-changed parts '\" of man pages. The first argument is ignored and used for recording '\" the version when the .VS was added, so that the sidebars can be '\" found and removed when they reach a certain age. If another argument '\" is present, then a line break is forced before starting the sidebar. '\" '\" .VE '\" End of vertical sidebar. '\" '\" .DS '\" Begin an indented unfilled display. '\" '\" .DE '\" End of indented unfilled display. '\" '\" .SO '\" Start of list of standard options for a Tk widget. The '\" options follow on successive lines, in four columns separated '\" by tabs. '\" '\" .SE '\" End of list of standard options for a Tk widget. '\" '\" .OP cmdName dbName dbClass '\" Start of description of a specific option. cmdName gives the '\" option's name as specified in the class command, dbName gives '\" the option's name in the option database, and dbClass gives '\" the option's class in the option database. '\" '\" .UL arg1 arg2 '\" Print arg1 underlined, then print arg2 normally. '\" '\" SCCS: @(#) man.macros 1.9 97/08/22 18:50:59 '\" '\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. .if t .wh -1.3i ^B .nr ^l \n(.l .ad b '\" # Start an argument description .de AP .ie !"\\$4"" .TP \\$4 .el \{\ . ie !"\\$2"" .TP \\n()Cu . el .TP 15 .\} .ie !"\\$3"" \{\ .ta \\n()Au \\n()Bu \&\\$1 \\fI\\$2\\fP (\\$3) .\".b .\} .el \{\ .br .ie !"\\$2"" \{\ \&\\$1 \\fI\\$2\\fP .\} .el \{\ \&\\fI\\$1\\fP .\} .\} .. '\" # define tabbing values for .AP .de AS .nr )A 10n .if !"\\$1"" .nr )A \\w'\\$1'u+3n .nr )B \\n()Au+15n .\" .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n .nr )C \\n()Bu+\\w'(in/out)'u+2n .. .AS Tcl_Interp Tcl_CreateInterp in/out '\" # BS - start boxed text '\" # ^y = starting y location '\" # ^b = 1 .de BS .br .mk ^y .nr ^b 1u .if n .nf .if n .ti 0 .if n \l'\\n(.lu\(ul' .if n .fi .. '\" # BE - end boxed text (draw box now) .de BE .nf .ti 0 .mk ^t .ie n \l'\\n(^lu\(ul' .el \{\ .\" Draw four-sided box normally, but don't draw top of .\" box if the box started on an earlier page. .ie !\\n(^b-1 \{\ \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .el \}\ \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .\} .fi .br .nr ^b 0 .. '\" # VS - start vertical sidebar '\" # ^Y = starting y location '\" # ^v = 1 (for troff; for nroff this doesn't matter) .de VS .if !"\\$2"" .br .mk ^Y .ie n 'mc \s12\(br\s0 .el .nr ^v 1u .. '\" # VE - end of vertical sidebar .de VE .ie n 'mc .el \{\ .ev 2 .nf .ti 0 .mk ^t \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n' .sp -1 .fi .ev .\} .nr ^v 0 .. '\" # Special macro to handle page bottom: finish off current '\" # box/sidebar if in box/sidebar mode, then invoked standard '\" # page bottom macro. .de ^B .ev 2 'ti 0 'nf .mk ^t .if \\n(^b \{\ .\" Draw three-sided box if this is the box's first page, .\" draw two sides but no top otherwise. .ie !\\n(^b-1 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .\} .if \\n(^v \{\ .nr ^x \\n(^tu+1v-\\n(^Yu \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c .\} .bp 'fi .ev .if \\n(^b \{\ .mk ^y .nr ^b 2 .\} .if \\n(^v \{\ .mk ^Y .\} .. '\" # DS - begin display .de DS .RS .nf .sp .. '\" # DE - end display .de DE .fi .RE .sp .. '\" # SO - start of list of standard options .de SO .SH "STANDARD OPTIONS" .LP .nf .ta 4c 8c 12c .ft B .. '\" # SE - end of list of standard options .de SE .fi .ft R .LP See the \\fBoptions\\fR manual entry for details on the standard options. .. '\" # OP - start of full description for a single option .de OP .LP .nf .ta 4c Command-Line Name: \\fB\\$1\\fR Database Name: \\fB\\$2\\fR Database Class: \\fB\\$3\\fR .fi .IP .. '\" # CS - begin code excerpt .de CS .RS .nf .ta .25i .5i .75i 1i .. '\" # CE - end code excerpt .de CE .fi .RE .. .de UL \\$1\l'|0\(ul'\\$2 .. .TH Tcl_RegExpMatch 3 7.4 Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_RegExpMatch, Tcl_RegExpCompile, Tcl_RegExpExec, Tcl_RegExpRange \- Pattern matching with regular expressions .SH SYNOPSIS .nf \fB#include \fR .sp int \fBTcl_RegExpMatch\fR(\fIinterp\fR, \fIstring\fR, \fIpattern\fR) .sp Tcl_RegExp \fBTcl_RegExpCompile\fR(\fIinterp\fR, \fIpattern\fR) .sp int \fBTcl_RegExpExec\fR(\fIinterp\fR, \fIregexp\fR, \fIstring\fR, \fIstart\fR) .sp \fBTcl_RegExpRange\fR(\fIregexp\fR, \fIindex\fR, \fIstartPtr\fR, \fIendPtr\fR) .SH ARGUMENTS .AS Tcl_Interp *interp .AP Tcl_Interp *interp in Tcl interpreter to use for error reporting. .AP char *string in String to check for a match with a regular expression. .AP char *pattern in String in the form of a regular expression pattern. .AP Tcl_RegExp regexp in Compiled regular expression. Must have been returned previously by \fBTcl_RegExpCompile\fR. .AP char *start in If \fIstring\fR is just a portion of some other string, this argument identifies the beginning of the larger string. If it isn't the same as \fIstring\fR, then no \fB^\fR matches will be allowed. .AP int index in Specifies which range is desired: 0 means the range of the entire match, 1 or greater means the range that matched a parenthesized sub-expression. .AP char **startPtr out The address of the first character in the range is stored here, or NULL if there is no such range. .AP char **endPtr out The address of the character just after the last one in the range is stored here, or NULL if there is no such range. .BE .SH DESCRIPTION .PP \fBTcl_RegExpMatch\fR determines whether its \fIpattern\fR argument matches \fIregexp\fR, where \fIregexp\fR is interpreted as a regular expression using the same rules as for the \fBregexp\fR Tcl command. If there is a match then \fBTcl_RegExpMatch\fR returns 1. If there is no match then \fBTcl_RegExpMatch\fR returns 0. If an error occurs in the matching process (e.g. \fIpattern\fR is not a valid regular expression) then \fBTcl_RegExpMatch\fR returns \-1 and leaves an error message in \fIinterp->result\fR. .PP \fBTcl_RegExpCompile\fR, \fBTcl_RegExpExec\fR, and \fBTcl_RegExpRange\fR provide lower-level access to the regular expression pattern matcher. \fBTcl_RegExpCompile\fR compiles a regular expression string into the internal form used for efficient pattern matching. The return value is a token for this compiled form, which can be used in subsequent calls to \fBTcl_RegExpExec\fR or \fBTcl_RegExpRange\fR. If an error occurs while compiling the regular expression then \fBTcl_RegExpCompile\fR returns NULL and leaves an error message in \fIinterp->result\fR. Note: the return value from \fBTcl_RegExpCompile\fR is only valid up to the next call to \fBTcl_RegExpCompile\fR; it is not safe to retain these values for long periods of time. .PP \fBTcl_RegExpExec\fR executes the regular expression pattern matcher. It returns 1 if \fIstring\fR contains a range of characters that match \fIregexp\fR, 0 if no match is found, and \-1 if an error occurs. In the case of an error, \fBTcl_RegExpExec\fR leaves an error message in \fIinterp->result\fR. When searching a string for multiple matches of a pattern, it is important to distinguish between the start of the original string and the start of the current search. For example, when searching for the second occurrence of a match, the \fIstring\fR argument might point to the character just after the first match; however, it is important for the pattern matcher to know that this is not the start of the entire string, so that it doesn't allow \fB^\fR atoms in the pattern to match. The \fIstart\fR argument provides this information by pointing to the start of the overall string containing \fIstring\fR. \fIStart\fR will be less than or equal to \fIstring\fR; if it is less than \fIstring\fR then no \fB^\fR matches will be allowed. .PP \fBTcl_RegExpRange\fR may be invoked after \fBTcl_RegExpExec\fR returns; it provides detailed information about what ranges of the string matched what parts of the pattern. \fBTcl_RegExpRange\fR returns a pair of pointers in \fI*startPtr\fR and \fI*endPtr\fR that identify a range of characters in the source string for the most recent call to \fBTcl_RegExpExec\fR. \fIIndex\fR indicates which of several ranges is desired: if \fIindex\fR is 0, information is returned about the overall range of characters that matched the entire pattern; otherwise, information is returned about the range of characters that matched the \fIindex\fR'th parenthesized subexpression within the pattern. If there is no range corresponding to \fIindex\fR then NULL is stored in \fI*firstPtr\fR and \fI*lastPtr\fR. .SH KEYWORDS match, pattern, regular expression, string, subexpression