Commit | Line | Data |
---|---|---|
86530b38 AT |
1 | '\" |
2 | '\" Copyright (c) 1998 Sun Microsystems, Inc. | |
3 | '\" | |
4 | '\" See the file "license.terms" for information on usage and redistribution | |
5 | '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. | |
6 | '\" | |
7 | '\" RCS: @(#) $Id: regexp.n,v 1.12.2.1 2004/10/27 14:23:57 dkf Exp $ | |
8 | '\" | |
9 | '\" The definitions below are for supplemental macros used in Tcl/Tk | |
10 | '\" manual entries. | |
11 | '\" | |
12 | '\" .AP type name in/out ?indent? | |
13 | '\" Start paragraph describing an argument to a library procedure. | |
14 | '\" type is type of argument (int, etc.), in/out is either "in", "out", | |
15 | '\" or "in/out" to describe whether procedure reads or modifies arg, | |
16 | '\" and indent is equivalent to second arg of .IP (shouldn't ever be | |
17 | '\" needed; use .AS below instead) | |
18 | '\" | |
19 | '\" .AS ?type? ?name? | |
20 | '\" Give maximum sizes of arguments for setting tab stops. Type and | |
21 | '\" name are examples of largest possible arguments that will be passed | |
22 | '\" to .AP later. If args are omitted, default tab stops are used. | |
23 | '\" | |
24 | '\" .BS | |
25 | '\" Start box enclosure. From here until next .BE, everything will be | |
26 | '\" enclosed in one large box. | |
27 | '\" | |
28 | '\" .BE | |
29 | '\" End of box enclosure. | |
30 | '\" | |
31 | '\" .CS | |
32 | '\" Begin code excerpt. | |
33 | '\" | |
34 | '\" .CE | |
35 | '\" End code excerpt. | |
36 | '\" | |
37 | '\" .VS ?version? ?br? | |
38 | '\" Begin vertical sidebar, for use in marking newly-changed parts | |
39 | '\" of man pages. The first argument is ignored and used for recording | |
40 | '\" the version when the .VS was added, so that the sidebars can be | |
41 | '\" found and removed when they reach a certain age. If another argument | |
42 | '\" is present, then a line break is forced before starting the sidebar. | |
43 | '\" | |
44 | '\" .VE | |
45 | '\" End of vertical sidebar. | |
46 | '\" | |
47 | '\" .DS | |
48 | '\" Begin an indented unfilled display. | |
49 | '\" | |
50 | '\" .DE | |
51 | '\" End of indented unfilled display. | |
52 | '\" | |
53 | '\" .SO | |
54 | '\" Start of list of standard options for a Tk widget. The | |
55 | '\" options follow on successive lines, in four columns separated | |
56 | '\" by tabs. | |
57 | '\" | |
58 | '\" .SE | |
59 | '\" End of list of standard options for a Tk widget. | |
60 | '\" | |
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. | |
66 | '\" | |
67 | '\" .UL arg1 arg2 | |
68 | '\" Print arg1 underlined, then print arg2 normally. | |
69 | '\" | |
70 | '\" RCS: @(#) $Id: man.macros,v 1.4 2000/08/25 06:18:32 ericm Exp $ | |
71 | '\" | |
72 | '\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. | |
73 | .if t .wh -1.3i ^B | |
74 | .nr ^l \n(.l | |
75 | .ad b | |
76 | '\" # Start an argument description | |
77 | .de AP | |
78 | .ie !"\\$4"" .TP \\$4 | |
79 | .el \{\ | |
80 | . ie !"\\$2"" .TP \\n()Cu | |
81 | . el .TP 15 | |
82 | .\} | |
83 | .ta \\n()Au \\n()Bu | |
84 | .ie !"\\$3"" \{\ | |
85 | \&\\$1 \\fI\\$2\\fP (\\$3) | |
86 | .\".b | |
87 | .\} | |
88 | .el \{\ | |
89 | .br | |
90 | .ie !"\\$2"" \{\ | |
91 | \&\\$1 \\fI\\$2\\fP | |
92 | .\} | |
93 | .el \{\ | |
94 | \&\\fI\\$1\\fP | |
95 | .\} | |
96 | .\} | |
97 | .. | |
98 | '\" # define tabbing values for .AP | |
99 | .de AS | |
100 | .nr )A 10n | |
101 | .if !"\\$1"" .nr )A \\w'\\$1'u+3n | |
102 | .nr )B \\n()Au+15n | |
103 | .\" | |
104 | .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n | |
105 | .nr )C \\n()Bu+\\w'(in/out)'u+2n | |
106 | .. | |
107 | .AS Tcl_Interp Tcl_CreateInterp in/out | |
108 | '\" # BS - start boxed text | |
109 | '\" # ^y = starting y location | |
110 | '\" # ^b = 1 | |
111 | .de BS | |
112 | .br | |
113 | .mk ^y | |
114 | .nr ^b 1u | |
115 | .if n .nf | |
116 | .if n .ti 0 | |
117 | .if n \l'\\n(.lu\(ul' | |
118 | .if n .fi | |
119 | .. | |
120 | '\" # BE - end boxed text (draw box now) | |
121 | .de BE | |
122 | .nf | |
123 | .ti 0 | |
124 | .mk ^t | |
125 | .ie n \l'\\n(^lu\(ul' | |
126 | .el \{\ | |
127 | .\" Draw four-sided box normally, but don't draw top of | |
128 | .\" box if the box started on an earlier page. | |
129 | .ie !\\n(^b-1 \{\ | |
130 | \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' | |
131 | .\} | |
132 | .el \}\ | |
133 | \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' | |
134 | .\} | |
135 | .\} | |
136 | .fi | |
137 | .br | |
138 | .nr ^b 0 | |
139 | .. | |
140 | '\" # VS - start vertical sidebar | |
141 | '\" # ^Y = starting y location | |
142 | '\" # ^v = 1 (for troff; for nroff this doesn't matter) | |
143 | .de VS | |
144 | .if !"\\$2"" .br | |
145 | .mk ^Y | |
146 | .ie n 'mc \s12\(br\s0 | |
147 | .el .nr ^v 1u | |
148 | .. | |
149 | '\" # VE - end of vertical sidebar | |
150 | .de VE | |
151 | .ie n 'mc | |
152 | .el \{\ | |
153 | .ev 2 | |
154 | .nf | |
155 | .ti 0 | |
156 | .mk ^t | |
157 | \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n' | |
158 | .sp -1 | |
159 | .fi | |
160 | .ev | |
161 | .\} | |
162 | .nr ^v 0 | |
163 | .. | |
164 | '\" # Special macro to handle page bottom: finish off current | |
165 | '\" # box/sidebar if in box/sidebar mode, then invoked standard | |
166 | '\" # page bottom macro. | |
167 | .de ^B | |
168 | .ev 2 | |
169 | 'ti 0 | |
170 | 'nf | |
171 | .mk ^t | |
172 | .if \\n(^b \{\ | |
173 | .\" Draw three-sided box if this is the box's first page, | |
174 | .\" draw two sides but no top otherwise. | |
175 | .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 | |
176 | .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c | |
177 | .\} | |
178 | .if \\n(^v \{\ | |
179 | .nr ^x \\n(^tu+1v-\\n(^Yu | |
180 | \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c | |
181 | .\} | |
182 | .bp | |
183 | 'fi | |
184 | .ev | |
185 | .if \\n(^b \{\ | |
186 | .mk ^y | |
187 | .nr ^b 2 | |
188 | .\} | |
189 | .if \\n(^v \{\ | |
190 | .mk ^Y | |
191 | .\} | |
192 | .. | |
193 | '\" # DS - begin display | |
194 | .de DS | |
195 | .RS | |
196 | .nf | |
197 | .sp | |
198 | .. | |
199 | '\" # DE - end display | |
200 | .de DE | |
201 | .fi | |
202 | .RE | |
203 | .sp | |
204 | .. | |
205 | '\" # SO - start of list of standard options | |
206 | .de SO | |
207 | .SH "STANDARD OPTIONS" | |
208 | .LP | |
209 | .nf | |
210 | .ta 5.5c 11c | |
211 | .ft B | |
212 | .. | |
213 | '\" # SE - end of list of standard options | |
214 | .de SE | |
215 | .fi | |
216 | .ft R | |
217 | .LP | |
218 | See the \\fBoptions\\fR manual entry for details on the standard options. | |
219 | .. | |
220 | '\" # OP - start of full description for a single option | |
221 | .de OP | |
222 | .LP | |
223 | .nf | |
224 | .ta 4c | |
225 | Command-Line Name: \\fB\\$1\\fR | |
226 | Database Name: \\fB\\$2\\fR | |
227 | Database Class: \\fB\\$3\\fR | |
228 | .fi | |
229 | .IP | |
230 | .. | |
231 | '\" # CS - begin code excerpt | |
232 | .de CS | |
233 | .RS | |
234 | .nf | |
235 | .ta .25i .5i .75i 1i | |
236 | .. | |
237 | '\" # CE - end code excerpt | |
238 | .de CE | |
239 | .fi | |
240 | .RE | |
241 | .. | |
242 | .de UL | |
243 | \\$1\l'|0\(ul'\\$2 | |
244 | .. | |
245 | .TH regexp n 8.3 Tcl "Tcl Built-In Commands" | |
246 | .BS | |
247 | '\" Note: do not modify the .SH NAME line immediately below! | |
248 | .SH NAME | |
249 | regexp \- Match a regular expression against a string | |
250 | ||
251 | .SH SYNOPSIS | |
252 | \fBregexp \fR?\fIswitches\fR? \fIexp string \fR?\fImatchVar\fR? ?\fIsubMatchVar subMatchVar ...\fR? | |
253 | .BE | |
254 | ||
255 | .SH DESCRIPTION | |
256 | .PP | |
257 | Determines whether the regular expression \fIexp\fR matches part or | |
258 | all of \fIstring\fR and returns 1 if it does, 0 if it doesn't, unless | |
259 | \fB-inline\fR is specified (see below). | |
260 | (Regular expression matching is described in the \fBre_syntax\fR | |
261 | reference page.) | |
262 | .LP | |
263 | If additional arguments are specified after \fIstring\fR then they | |
264 | are treated as the names of variables in which to return | |
265 | information about which part(s) of \fIstring\fR matched \fIexp\fR. | |
266 | \fIMatchVar\fR will be set to the range of \fIstring\fR that | |
267 | matched all of \fIexp\fR. The first \fIsubMatchVar\fR will contain | |
268 | the characters in \fIstring\fR that matched the leftmost parenthesized | |
269 | subexpression within \fIexp\fR, the next \fIsubMatchVar\fR will | |
270 | contain the characters that matched the next parenthesized | |
271 | subexpression to the right in \fIexp\fR, and so on. | |
272 | .PP | |
273 | If the initial arguments to \fBregexp\fR start with \fB\-\fR then | |
274 | they are treated as switches. The following switches are | |
275 | currently supported: | |
276 | .TP 15 | |
277 | \fB\-about\fR | |
278 | Instead of attempting to match the regular expression, returns a list | |
279 | containing information about the regular expression. The first | |
280 | element of the list is a subexpression count. The second element is a | |
281 | list of property names that describe various attributes of the regular | |
282 | expression. This switch is primarily intended for debugging purposes. | |
283 | .TP 15 | |
284 | \fB\-expanded\fR | |
285 | Enables use of the expanded regular expression syntax where | |
286 | whitespace and comments are ignored. This is the same as specifying | |
287 | the \fB(?x)\fR embedded option (see the \fBre_syntax\fR manual page). | |
288 | .TP 15 | |
289 | \fB\-indices\fR | |
290 | Changes what is stored in the \fIsubMatchVar\fRs. | |
291 | Instead of storing the matching characters from \fIstring\fR, | |
292 | each variable | |
293 | will contain a list of two decimal strings giving the indices | |
294 | in \fIstring\fR of the first and last characters in the matching | |
295 | range of characters. | |
296 | .TP 15 | |
297 | \fB\-line\fR | |
298 | Enables newline-sensitive matching. By default, newline is a | |
299 | completely ordinary character with no special meaning. With this | |
300 | flag, `[^' bracket expressions and `.' never match newline, `^' | |
301 | matches an empty string after any newline in addition to its normal | |
302 | function, and `$' matches an empty string before any newline in | |
303 | addition to its normal function. This flag is equivalent to | |
304 | specifying both \fB\-linestop\fR and \fB\-lineanchor\fR, or the | |
305 | \fB(?n)\fR embedded option (see the \fBre_syntax\fR manual page). | |
306 | .TP 15 | |
307 | \fB\-linestop\fR | |
308 | Changes the behavior of `[^' bracket expressions and `.' so that they | |
309 | stop at newlines. This is the same as specifying the \fB(?p)\fR | |
310 | embedded option (see the \fBre_syntax\fR manual page). | |
311 | .TP 15 | |
312 | \fB\-lineanchor\fR | |
313 | Changes the behavior of `^' and `$' (the ``anchors'') so they match the | |
314 | beginning and end of a line respectively. This is the same as | |
315 | specifying the \fB(?w)\fR embedded option (see the \fBre_syntax\fR | |
316 | manual page). | |
317 | .TP 15 | |
318 | \fB\-nocase\fR | |
319 | Causes upper-case characters in \fIstring\fR to be treated as | |
320 | lower case during the matching process. | |
321 | .VS 8.3 | |
322 | .TP 15 | |
323 | \fB\-all\fR | |
324 | Causes the regular expression to be matched as many times as possible | |
325 | in the string, returning the total number of matches found. If this | |
326 | is specified with match variables, they will contain information for | |
327 | the last match only. | |
328 | .TP 15 | |
329 | \fB\-inline\fR | |
330 | Causes the command to return, as a list, the data that would otherwise | |
331 | be placed in match variables. When using \fB-inline\fR, | |
332 | match variables may not be specified. If used with \fB-all\fR, the | |
333 | list will be concatenated at each iteration, such that a flat list is | |
334 | always returned. For each match iteration, the command will append the | |
335 | overall match data, plus one element for each subexpression in the | |
336 | regular expression. Examples are: | |
337 | .CS | |
338 | regexp -inline -- {\\w(\\w)} " inlined " | |
339 | => {in n} | |
340 | regexp -all -inline -- {\\w(\\w)} " inlined " | |
341 | => {in n li i ne e} | |
342 | .CE | |
343 | .TP 15 | |
344 | \fB\-start\fR \fIindex\fR | |
345 | Specifies a character index offset into the string to start | |
346 | matching the regular expression at. When using this switch, `^' | |
347 | will not match the beginning of the line, and \\A will still | |
348 | match the start of the string at \fIindex\fR. If \fB\-indices\fR | |
349 | is specified, the indices will be indexed starting from the | |
350 | absolute beginning of the input string. | |
351 | \fIindex\fR will be constrained to the bounds of the input string. | |
352 | .VE 8.3 | |
353 | .TP 15 | |
354 | \fB\-\|\-\fR | |
355 | Marks the end of switches. The argument following this one will | |
356 | be treated as \fIexp\fR even if it starts with a \fB\-\fR. | |
357 | .PP | |
358 | If there are more \fIsubMatchVar\fR's than parenthesized | |
359 | subexpressions within \fIexp\fR, or if a particular subexpression | |
360 | in \fIexp\fR doesn't match the string (e.g. because it was in a | |
361 | portion of the expression that wasn't matched), then the corresponding | |
362 | \fIsubMatchVar\fR will be set to ``\fB\-1 \-1\fR'' if \fB\-indices\fR | |
363 | has been specified or to an empty string otherwise. | |
364 | .SH EXAMPLES | |
365 | Find the first occurrence of a word starting with \fBfoo\fR in a | |
366 | string that is not actually an instance of \fBfoobar\fR, and get the | |
367 | letters following it up to the end of the word into a variable: | |
368 | .CS | |
369 | \fBregexp\fR {\\<foo(?!bar\\>)(\\w*)} $string \-> restOfWord | |
370 | .CE | |
371 | Note that the whole matched substring has been placed in the variable | |
372 | \fB\->\fR which is a name chosen to look nice given that we are not | |
373 | actually interested in its contents. | |
374 | .PP | |
375 | Find the index of the word \fBbadger\fR (in any case) within a string | |
376 | and store that in the variable \fBlocation\fR: | |
377 | .CS | |
378 | \fBregexp\fR \-indices {(?i)\\<badger\\>} $string location | |
379 | .CE | |
380 | .PP | |
381 | Count the number of octal digits in a string: | |
382 | .CS | |
383 | \fBregexp\fR \-all {[0\-7]} $string | |
384 | .CE | |
385 | .PP | |
386 | List all words (consisting of all sequences of non-whitespace | |
387 | characters) in a string: | |
388 | .CS | |
389 | \fBregexp\fR \-all \-inline {\\S+} $string | |
390 | .CE | |
391 | ||
392 | .SH "SEE ALSO" | |
393 | re_syntax(n), regsub(n) | |
394 | ||
395 | .SH KEYWORDS | |
396 | match, regular expression, string |