2 '\" Copyright (c) 1998 Sun Microsystems, Inc.
4 '\" See the file "license.terms" for information on usage and redistribution
5 '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
7 .TH regexp n 8.3 Tcl "Tcl Built-In Commands"
8 .\" The -*- nroff -*- definitions below are for supplemental macros used
9 .\" in Tcl/Tk manual entries.
11 .\" .AP type name in/out ?indent?
12 .\" Start paragraph describing an argument to a library procedure.
13 .\" type is type of argument (int, etc.), in/out is either "in", "out",
14 .\" or "in/out" to describe whether procedure reads or modifies arg,
15 .\" and indent is equivalent to second arg of .IP (shouldn't ever be
16 .\" needed; use .AS below instead)
19 .\" Give maximum sizes of arguments for setting tab stops. Type and
20 .\" name are examples of largest possible arguments that will be passed
21 .\" to .AP later. If args are omitted, default tab stops are used.
24 .\" Start box enclosure. From here until next .BE, everything will be
25 .\" enclosed in one large box.
28 .\" End of box enclosure.
31 .\" Begin code excerpt.
36 .\" .VS ?version? ?br?
37 .\" Begin vertical sidebar, for use in marking newly-changed parts
38 .\" of man pages. The first argument is ignored and used for recording
39 .\" the version when the .VS was added, so that the sidebars can be
40 .\" found and removed when they reach a certain age. If another argument
41 .\" is present, then a line break is forced before starting the sidebar.
44 .\" End of vertical sidebar.
47 .\" Begin an indented unfilled display.
50 .\" End of indented unfilled display.
53 .\" Start of list of standard options for a Tk widget. The manpage
54 .\" argument defines where to look up the standard options; if
55 .\" omitted, defaults to "options". The options follow on successive
56 .\" lines, in three columns separated by tabs.
59 .\" End of list of standard options for a Tk widget.
61 .\" .OP cmdName dbName dbClass
62 .\" Start of description of a specific option. cmdName gives the
63 .\" option's name as specified in the class command, dbName gives
64 .\" the option's name in the option database, and dbClass gives
65 .\" the option's class in the option database.
68 .\" Print arg1 underlined, then print arg2 normally.
71 .\" Print arg1 in quotes, then arg2 normally (for trailing punctuation).
74 .\" Print an open parenthesis, arg1 in quotes, then arg2 normally
75 .\" (for trailing punctuation) and then a closing parenthesis.
77 .\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages.
81 .\" # Start an argument description
85 . ie !"\\$2"" .TP \\n()Cu
90 \&\\$1 \\fI\\$2\\fP (\\$3)
103 .\" # define tabbing values for .AP
106 .if !"\\$1"" .nr )A \\w'\\$1'u+3n
109 .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n
110 .nr )C \\n()Bu+\\w'(in/out)'u+2n
112 .AS Tcl_Interp Tcl_CreateInterp in/out
113 .\" # BS - start boxed text
114 .\" # ^y = starting y location
122 .if n \l'\\n(.lu\(ul'
125 .\" # BE - end boxed text (draw box now)
130 .ie n \l'\\n(^lu\(ul'
132 .\" Draw four-sided box normally, but don't draw top of
133 .\" box if the box started on an earlier page.
135 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul'
138 \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul'
145 .\" # VS - start vertical sidebar
146 .\" # ^Y = starting y location
147 .\" # ^v = 1 (for troff; for nroff this doesn't matter)
151 .ie n 'mc \s12\(br\s0
154 .\" # VE - end of vertical sidebar
162 \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n'
169 .\" # Special macro to handle page bottom: finish off current
170 .\" # box/sidebar if in box/sidebar mode, then invoked standard
171 .\" # page bottom macro.
178 .\" Draw three-sided box if this is the box's first page,
179 .\" draw two sides but no top otherwise.
180 .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
181 .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c
184 .nr ^x \\n(^tu+1v-\\n(^Yu
185 \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c
198 .\" # DS - begin display
204 .\" # DE - end display
210 .\" # SO - start of list of standard options
212 'ie '\\$1'' .ds So \\fBoptions\\fR
213 'el .ds So \\fB\\$1\\fR
214 .SH "STANDARD OPTIONS"
220 .\" # SE - end of list of standard options
225 See the \\*(So manual entry for details on the standard options.
227 .\" # OP - start of full description for a single option
232 Command-Line Name: \\fB\\$1\\fR
233 Database Name: \\fB\\$2\\fR
234 Database Class: \\fB\\$3\\fR
238 .\" # CS - begin code excerpt
244 .\" # CE - end code excerpt
249 .\" # UL - underline word
253 .\" # QW - apply quotation marks to word
255 .ie '\\*(lq'"' ``\\$1''\\$2
256 .\"" fix emacs highlighting
257 .el \\*(lq\\$1\\*(rq\\$2
259 .\" # PQ - apply parens and quotation marks to word
261 .ie '\\*(lq'"' (``\\$1''\\$2)\\$3
262 .\"" fix emacs highlighting
263 .el (\\*(lq\\$1\\*(rq\\$2)\\$3
265 .\" # QR - quoted range
267 .ie '\\*(lq'"' ``\\$1''\\-``\\$2''\\$3
268 .\"" fix emacs highlighting
269 .el \\*(lq\\$1\\*(rq\\-\\*(lq\\$2\\*(rq\\$3
271 .\" # MT - "empty" string
276 '\" Note: do not modify the .SH NAME line immediately below!
278 regexp \- Match a regular expression against a string
280 \fBregexp \fR?\fIswitches\fR? \fIexp string \fR?\fImatchVar\fR? ?\fIsubMatchVar subMatchVar ...\fR?
284 Determines whether the regular expression \fIexp\fR matches part or
285 all of \fIstring\fR and returns 1 if it does, 0 if it does not, unless
286 \fB\-inline\fR is specified (see below).
287 (Regular expression matching is described in the \fBre_syntax\fR
290 If additional arguments are specified after \fIstring\fR then they
291 are treated as the names of variables in which to return
292 information about which part(s) of \fIstring\fR matched \fIexp\fR.
293 \fIMatchVar\fR will be set to the range of \fIstring\fR that
294 matched all of \fIexp\fR. The first \fIsubMatchVar\fR will contain
295 the characters in \fIstring\fR that matched the leftmost parenthesized
296 subexpression within \fIexp\fR, the next \fIsubMatchVar\fR will
297 contain the characters that matched the next parenthesized
298 subexpression to the right in \fIexp\fR, and so on.
300 If the initial arguments to \fBregexp\fR start with \fB\-\fR then
301 they are treated as switches. The following switches are
306 Instead of attempting to match the regular expression, returns a list
307 containing information about the regular expression. The first
308 element of the list is a subexpression count. The second element is a
309 list of property names that describe various attributes of the regular
310 expression. This switch is primarily intended for debugging purposes.
314 Enables use of the expanded regular expression syntax where
315 whitespace and comments are ignored. This is the same as specifying
316 the \fB(?x)\fR embedded option (see the \fBre_syntax\fR manual page).
320 Changes what is stored in the \fIsubMatchVar\fRs.
321 Instead of storing the matching characters from \fIstring\fR,
323 will contain a list of two decimal strings giving the indices
324 in \fIstring\fR of the first and last characters in the matching
329 Enables newline-sensitive matching. By default, newline is a
330 completely ordinary character with no special meaning. With this
333 bracket expressions and
337 matches an empty string after any newline in addition to its normal
340 matches an empty string before any newline in
341 addition to its normal function. This flag is equivalent to
342 specifying both \fB\-linestop\fR and \fB\-lineanchor\fR, or the
343 \fB(?n)\fR embedded option (see the \fBre_syntax\fR manual page).
347 Changes the behavior of
349 bracket expressions and
352 stop at newlines. This is the same as specifying the \fB(?p)\fR
353 embedded option (see the \fBre_syntax\fR manual page).
357 Changes the behavior of
364 beginning and end of a line respectively. This is the same as
365 specifying the \fB(?w)\fR embedded option (see the \fBre_syntax\fR
370 Causes upper-case characters in \fIstring\fR to be treated as
371 lower case during the matching process.
375 Causes the regular expression to be matched as many times as possible
376 in the string, returning the total number of matches found. If this
377 is specified with match variables, they will contain information for
382 Causes the command to return, as a list, the data that would otherwise
383 be placed in match variables. When using \fB\-inline\fR,
384 match variables may not be specified. If used with \fB\-all\fR, the
385 list will be concatenated at each iteration, such that a flat list is
386 always returned. For each match iteration, the command will append the
387 overall match data, plus one element for each subexpression in the
388 regular expression. Examples are:
392 \fBregexp\fR -inline -- {\ew(\ew)} " inlined "
394 \fBregexp\fR -all -inline -- {\ew(\ew)} " inlined "
395 \fI\(-> in n li i ne e\fR
399 \fB\-start\fR \fIindex\fR
401 Specifies a character index offset into the string to start
402 matching the regular expression at.
403 The \fIindex\fR value is interpreted in the same manner
404 as the \fIindex\fR argument to \fBstring index\fR.
405 When using this switch,
407 will not match the beginning of the line, and \eA will still
408 match the start of the string at \fIindex\fR. If \fB\-indices\fR
409 is specified, the indices will be indexed starting from the
410 absolute beginning of the input string.
411 \fIindex\fR will be constrained to the bounds of the input string.
415 Marks the end of switches. The argument following this one will
416 be treated as \fIexp\fR even if it starts with a \fB\-\fR.
418 If there are more \fIsubMatchVar\fRs than parenthesized
419 subexpressions within \fIexp\fR, or if a particular subexpression
420 in \fIexp\fR does not match the string (e.g. because it was in a
421 portion of the expression that was not matched), then the corresponding
422 \fIsubMatchVar\fR will be set to
424 if \fB\-indices\fR has been specified or to an empty string otherwise.
427 Find the first occurrence of a word starting with \fBfoo\fR in a
428 string that is not actually an instance of \fBfoobar\fR, and get the
429 letters following it up to the end of the word into a variable:
432 \fBregexp\fR {\emfoo(?!bar\eM)(\ew*)} $string \-> restOfWord
435 Note that the whole matched substring has been placed in the variable
437 which is a name chosen to look nice given that we are not
438 actually interested in its contents.
440 Find the index of the word \fBbadger\fR (in any case) within a string
441 and store that in the variable \fBlocation\fR:
444 \fBregexp\fR \-indices {(?i)\embadger\eM} $string location
447 This could also be written as a \fIbasic\fR regular expression (as opposed
448 to using the default syntax of \fIadvanced\fR regular expressions) match by
449 prefixing the expression with a suitable flag:
452 \fBregexp\fR \-indices {(?ib)\e<badger\e>} $string location
455 This counts the number of octal digits in a string:
458 \fBregexp\fR \-all {[0\-7]} $string
461 This lists all words (consisting of all sequences of non-whitespace
462 characters) in a string, and is useful as a more powerful version of the
466 \fBregexp\fR \-all \-inline {\eS+} $string
469 re_syntax(n), regsub(n), string(n)
471 match, parsing, pattern, regular expression, splitting, string