diff options
Diffstat (limited to 'doc/RegExp.3')
-rw-r--r-- | doc/RegExp.3 | 116 |
1 files changed, 116 insertions, 0 deletions
diff --git a/doc/RegExp.3 b/doc/RegExp.3 new file mode 100644 index 0000000..fef9245 --- /dev/null +++ b/doc/RegExp.3 @@ -0,0 +1,116 @@ +'\" +'\" 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 +'\" +.so man.macros +.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 <tcl.h>\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 |