| 1 | .\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32 |
| 2 | .\" |
| 3 | .\" Standard preamble: |
| 4 | .\" ======================================================================== |
| 5 | .de Sh \" Subsection heading |
| 6 | .br |
| 7 | .if t .Sp |
| 8 | .ne 5 |
| 9 | .PP |
| 10 | \fB\\$1\fR |
| 11 | .PP |
| 12 | .. |
| 13 | .de Sp \" Vertical space (when we can't use .PP) |
| 14 | .if t .sp .5v |
| 15 | .if n .sp |
| 16 | .. |
| 17 | .de Vb \" Begin verbatim text |
| 18 | .ft CW |
| 19 | .nf |
| 20 | .ne \\$1 |
| 21 | .. |
| 22 | .de Ve \" End verbatim text |
| 23 | .ft R |
| 24 | .fi |
| 25 | .. |
| 26 | .\" Set up some character translations and predefined strings. \*(-- will |
| 27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left |
| 28 | .\" double quote, and \*(R" will give a right double quote. | will give a |
| 29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to |
| 30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' |
| 31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. |
| 32 | .tr \(*W-|\(bv\*(Tr |
| 33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' |
| 34 | .ie n \{\ |
| 35 | . ds -- \(*W- |
| 36 | . ds PI pi |
| 37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch |
| 38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch |
| 39 | . ds L" "" |
| 40 | . ds R" "" |
| 41 | . ds C` "" |
| 42 | . ds C' "" |
| 43 | 'br\} |
| 44 | .el\{\ |
| 45 | . ds -- \|\(em\| |
| 46 | . ds PI \(*p |
| 47 | . ds L" `` |
| 48 | . ds R" '' |
| 49 | 'br\} |
| 50 | .\" |
| 51 | .\" If the F register is turned on, we'll generate index entries on stderr for |
| 52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index |
| 53 | .\" entries marked with X<> in POD. Of course, you'll have to process the |
| 54 | .\" output yourself in some meaningful fashion. |
| 55 | .if \nF \{\ |
| 56 | . de IX |
| 57 | . tm Index:\\$1\t\\n%\t"\\$2" |
| 58 | .. |
| 59 | . nr % 0 |
| 60 | . rr F |
| 61 | .\} |
| 62 | .\" |
| 63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 64 | .\" way too many mistakes in technical documents. |
| 65 | .hy 0 |
| 66 | .if n .na |
| 67 | .\" |
| 68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). |
| 69 | .\" Fear. Run. Save yourself. No user-serviceable parts. |
| 70 | . \" fudge factors for nroff and troff |
| 71 | .if n \{\ |
| 72 | . ds #H 0 |
| 73 | . ds #V .8m |
| 74 | . ds #F .3m |
| 75 | . ds #[ \f1 |
| 76 | . ds #] \fP |
| 77 | .\} |
| 78 | .if t \{\ |
| 79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) |
| 80 | . ds #V .6m |
| 81 | . ds #F 0 |
| 82 | . ds #[ \& |
| 83 | . ds #] \& |
| 84 | .\} |
| 85 | . \" simple accents for nroff and troff |
| 86 | .if n \{\ |
| 87 | . ds ' \& |
| 88 | . ds ` \& |
| 89 | . ds ^ \& |
| 90 | . ds , \& |
| 91 | . ds ~ ~ |
| 92 | . ds / |
| 93 | .\} |
| 94 | .if t \{\ |
| 95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" |
| 96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' |
| 97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' |
| 98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' |
| 99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' |
| 100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' |
| 101 | .\} |
| 102 | . \" troff and (daisy-wheel) nroff accents |
| 103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' |
| 104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' |
| 105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] |
| 106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' |
| 107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' |
| 108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] |
| 109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] |
| 110 | .ds ae a\h'-(\w'a'u*4/10)'e |
| 111 | .ds Ae A\h'-(\w'A'u*4/10)'E |
| 112 | . \" corrections for vroff |
| 113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' |
| 114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' |
| 115 | . \" for low resolution devices (crt and lpr) |
| 116 | .if \n(.H>23 .if \n(.V>19 \ |
| 117 | \{\ |
| 118 | . ds : e |
| 119 | . ds 8 ss |
| 120 | . ds o a |
| 121 | . ds d- d\h'-1'\(ga |
| 122 | . ds D- D\h'-1'\(hy |
| 123 | . ds th \o'bp' |
| 124 | . ds Th \o'LP' |
| 125 | . ds ae ae |
| 126 | . ds Ae AE |
| 127 | .\} |
| 128 | .rm #[ #] #H #V #F C |
| 129 | .\" ======================================================================== |
| 130 | .\" |
| 131 | .IX Title "PERLREREF 1" |
| 132 | .TH PERLREREF 1 "2006-01-07" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | perlreref \- Perl Regular Expressions Reference |
| 135 | .SH "DESCRIPTION" |
| 136 | .IX Header "DESCRIPTION" |
| 137 | This is a quick reference to Perl's regular expressions. |
| 138 | For full information see perlre and perlop, as well |
| 139 | as the \*(L"\s-1SEE\s0 \s-1ALSO\s0\*(R" section in this document. |
| 140 | .Sh "\s-1OPERATORS\s0" |
| 141 | .IX Subsection "OPERATORS" |
| 142 | .Vb 2 |
| 143 | \& =~ determines to which variable the regex is applied. |
| 144 | \& In its absence, $_ is used. |
| 145 | .Ve |
| 146 | .PP |
| 147 | .Vb 1 |
| 148 | \& $var =~ /foo/; |
| 149 | .Ve |
| 150 | .PP |
| 151 | .Vb 3 |
| 152 | \& !~ determines to which variable the regex is applied, |
| 153 | \& and negates the result of the match; it returns |
| 154 | \& false if the match succeeds, and true if it fails. |
| 155 | .Ve |
| 156 | .PP |
| 157 | .Vb 1 |
| 158 | \& $var !~ /foo/; |
| 159 | .Ve |
| 160 | .PP |
| 161 | .Vb 2 |
| 162 | \& m/pattern/igmsoxc searches a string for a pattern match, |
| 163 | \& applying the given options. |
| 164 | .Ve |
| 165 | .PP |
| 166 | .Vb 7 |
| 167 | \& i case-Insensitive |
| 168 | \& g Global - all occurrences |
| 169 | \& m Multiline mode - ^ and $ match internal lines |
| 170 | \& s match as a Single line - . matches \en |
| 171 | \& o compile pattern Once |
| 172 | \& x eXtended legibility - free whitespace and comments |
| 173 | \& c don't reset pos on failed matches when using /g |
| 174 | .Ve |
| 175 | .PP |
| 176 | .Vb 3 |
| 177 | \& If 'pattern' is an empty string, the last I<successfully> matched |
| 178 | \& regex is used. Delimiters other than '/' may be used for both this |
| 179 | \& operator and the following ones. |
| 180 | .Ve |
| 181 | .PP |
| 182 | .Vb 3 |
| 183 | \& qr/pattern/imsox lets you store a regex in a variable, |
| 184 | \& or pass one around. Modifiers as for m// and are stored |
| 185 | \& within the regex. |
| 186 | .Ve |
| 187 | .PP |
| 188 | .Vb 3 |
| 189 | \& s/pattern/replacement/igmsoxe substitutes matches of |
| 190 | \& 'pattern' with 'replacement'. Modifiers as for m// |
| 191 | \& with one addition: |
| 192 | .Ve |
| 193 | .PP |
| 194 | .Vb 1 |
| 195 | \& e Evaluate replacement as an expression |
| 196 | .Ve |
| 197 | .PP |
| 198 | .Vb 2 |
| 199 | \& 'e' may be specified multiple times. 'replacement' is interpreted |
| 200 | \& as a double quoted string unless a single-quote (') is the delimiter. |
| 201 | .Ve |
| 202 | .PP |
| 203 | .Vb 2 |
| 204 | \& ?pattern? is like m/pattern/ but matches only once. No alternate |
| 205 | \& delimiters can be used. Must be reset with L<reset|perlfunc/reset>. |
| 206 | .Ve |
| 207 | .Sh "\s-1SYNTAX\s0" |
| 208 | .IX Subsection "SYNTAX" |
| 209 | .Vb 13 |
| 210 | \& \e Escapes the character immediately following it |
| 211 | \& . Matches any single character except a newline (unless /s is used) |
| 212 | \& ^ Matches at the beginning of the string (or line, if /m is used) |
| 213 | \& $ Matches at the end of the string (or line, if /m is used) |
| 214 | \& * Matches the preceding element 0 or more times |
| 215 | \& + Matches the preceding element 1 or more times |
| 216 | \& ? Matches the preceding element 0 or 1 times |
| 217 | \& {...} Specifies a range of occurrences for the element preceding it |
| 218 | \& [...] Matches any one of the characters contained within the brackets |
| 219 | \& (...) Groups subexpressions for capturing to $1, $2... |
| 220 | \& (?:...) Groups subexpressions without capturing (cluster) |
| 221 | \& | Matches either the subexpression preceding or following it |
| 222 | \& \e1, \e2 ... The text from the Nth group |
| 223 | .Ve |
| 224 | .Sh "\s-1ESCAPE\s0 \s-1SEQUENCES\s0" |
| 225 | .IX Subsection "ESCAPE SEQUENCES" |
| 226 | These work as in normal strings. |
| 227 | .PP |
| 228 | .Vb 11 |
| 229 | \& \ea Alarm (beep) |
| 230 | \& \ee Escape |
| 231 | \& \ef Formfeed |
| 232 | \& \en Newline |
| 233 | \& \er Carriage return |
| 234 | \& \et Tab |
| 235 | \& \e037 Any octal ASCII value |
| 236 | \& \ex7f Any hexadecimal ASCII value |
| 237 | \& \ex{263a} A wide hexadecimal value |
| 238 | \& \ecx Control-x |
| 239 | \& \eN{name} A named character |
| 240 | .Ve |
| 241 | .PP |
| 242 | .Vb 6 |
| 243 | \& \el Lowercase next character |
| 244 | \& \eu Titlecase next character |
| 245 | \& \eL Lowercase until \eE |
| 246 | \& \eU Uppercase until \eE |
| 247 | \& \eQ Disable pattern metacharacters until \eE |
| 248 | \& \eE End case modification |
| 249 | .Ve |
| 250 | .PP |
| 251 | For Titlecase, see \*(L"Titlecase\*(R". |
| 252 | .PP |
| 253 | This one works differently from normal strings: |
| 254 | .PP |
| 255 | .Vb 1 |
| 256 | \& \eb An assertion, not backspace, except in a character class |
| 257 | .Ve |
| 258 | .Sh "\s-1CHARACTER\s0 \s-1CLASSES\s0" |
| 259 | .IX Subsection "CHARACTER CLASSES" |
| 260 | .Vb 4 |
| 261 | \& [amy] Match 'a', 'm' or 'y' |
| 262 | \& [f-j] Dash specifies "range" |
| 263 | \& [f-j-] Dash escaped or at start or end means 'dash' |
| 264 | \& [^f-j] Caret indicates "match any character _except_ these" |
| 265 | .Ve |
| 266 | .PP |
| 267 | The following sequences work within or without a character class. |
| 268 | The first six are locale aware, all are Unicode aware. The default |
| 269 | character class equivalent are given. See perllocale and |
| 270 | perlunicode for details. |
| 271 | .PP |
| 272 | .Vb 6 |
| 273 | \& \ed A digit [0-9] |
| 274 | \& \eD A nondigit [^0-9] |
| 275 | \& \ew A word character [a-zA-Z0-9_] |
| 276 | \& \eW A non-word character [^a-zA-Z0-9_] |
| 277 | \& \es A whitespace character [ \et\en\er\ef] |
| 278 | \& \eS A non-whitespace character [^ \et\en\er\ef] |
| 279 | .Ve |
| 280 | .PP |
| 281 | .Vb 6 |
| 282 | \& \eC Match a byte (with Unicode, '.' matches a character) |
| 283 | \& \epP Match P-named (Unicode) property |
| 284 | \& \ep{...} Match Unicode property with long name |
| 285 | \& \ePP Match non-P |
| 286 | \& \eP{...} Match lack of Unicode property with long name |
| 287 | \& \eX Match extended unicode sequence |
| 288 | .Ve |
| 289 | .PP |
| 290 | \&\s-1POSIX\s0 character classes and their Unicode and Perl equivalents: |
| 291 | .PP |
| 292 | .Vb 15 |
| 293 | \& alnum IsAlnum Alphanumeric |
| 294 | \& alpha IsAlpha Alphabetic |
| 295 | \& ascii IsASCII Any ASCII char |
| 296 | \& blank IsSpace [ \et] Horizontal whitespace (GNU extension) |
| 297 | \& cntrl IsCntrl Control characters |
| 298 | \& digit IsDigit \ed Digits |
| 299 | \& graph IsGraph Alphanumeric and punctuation |
| 300 | \& lower IsLower Lowercase chars (locale and Unicode aware) |
| 301 | \& print IsPrint Alphanumeric, punct, and space |
| 302 | \& punct IsPunct Punctuation |
| 303 | \& space IsSpace [\es\eck] Whitespace |
| 304 | \& IsSpacePerl \es Perl's whitespace definition |
| 305 | \& upper IsUpper Uppercase chars (locale and Unicode aware) |
| 306 | \& word IsWord \ew Alphanumeric plus _ (Perl extension) |
| 307 | \& xdigit IsXDigit [0-9A-Fa-f] Hexadecimal digit |
| 308 | .Ve |
| 309 | .PP |
| 310 | Within a character class: |
| 311 | .PP |
| 312 | .Vb 3 |
| 313 | \& POSIX traditional Unicode |
| 314 | \& [:digit:] \ed \ep{IsDigit} |
| 315 | \& [:^digit:] \eD \eP{IsDigit} |
| 316 | .Ve |
| 317 | .Sh "\s-1ANCHORS\s0" |
| 318 | .IX Subsection "ANCHORS" |
| 319 | All are zero-width assertions. |
| 320 | .PP |
| 321 | .Vb 8 |
| 322 | \& ^ Match string start (or line, if /m is used) |
| 323 | \& $ Match string end (or line, if /m is used) or before newline |
| 324 | \& \eb Match word boundary (between \ew and \eW) |
| 325 | \& \eB Match except at word boundary (between \ew and \ew or \eW and \eW) |
| 326 | \& \eA Match string start (regardless of /m) |
| 327 | \& \eZ Match string end (before optional newline) |
| 328 | \& \ez Match absolute string end |
| 329 | \& \eG Match where previous m//g left off |
| 330 | .Ve |
| 331 | .Sh "\s-1QUANTIFIERS\s0" |
| 332 | .IX Subsection "QUANTIFIERS" |
| 333 | Quantifiers are greedy by default \*(-- match the \fBlongest\fR leftmost. |
| 334 | .PP |
| 335 | .Vb 8 |
| 336 | \& Maximal Minimal Allowed range |
| 337 | \& ------- ------- ------------- |
| 338 | \& {n,m} {n,m}? Must occur at least n times but no more than m times |
| 339 | \& {n,} {n,}? Must occur at least n times |
| 340 | \& {n} {n}? Must occur exactly n times |
| 341 | \& * *? 0 or more times (same as {0,}) |
| 342 | \& + +? 1 or more times (same as {1,}) |
| 343 | \& ? ?? 0 or 1 time (same as {0,1}) |
| 344 | .Ve |
| 345 | .PP |
| 346 | There is no quantifier {,n} \*(-- that gets understood as a literal string. |
| 347 | .Sh "\s-1EXTENDED\s0 \s-1CONSTRUCTS\s0" |
| 348 | .IX Subsection "EXTENDED CONSTRUCTS" |
| 349 | .Vb 11 |
| 350 | \& (?#text) A comment |
| 351 | \& (?imxs-imsx:...) Enable/disable option (as per m// modifiers) |
| 352 | \& (?=...) Zero-width positive lookahead assertion |
| 353 | \& (?!...) Zero-width negative lookahead assertion |
| 354 | \& (?<=...) Zero-width positive lookbehind assertion |
| 355 | \& (?<!...) Zero-width negative lookbehind assertion |
| 356 | \& (?>...) Grab what we can, prohibit backtracking |
| 357 | \& (?{ code }) Embedded code, return value becomes $^R |
| 358 | \& (??{ code }) Dynamic regex, return value used as regex |
| 359 | \& (?(cond)yes|no) cond being integer corresponding to capturing parens |
| 360 | \& (?(cond)yes) or a lookaround/eval zero-width assertion |
| 361 | .Ve |
| 362 | .Sh "\s-1VARIABLES\s0" |
| 363 | .IX Subsection "VARIABLES" |
| 364 | .Vb 2 |
| 365 | \& $_ Default variable for operators to use |
| 366 | \& $* Enable multiline matching (deprecated; not in 5.9.0 or later) |
| 367 | .Ve |
| 368 | .PP |
| 369 | .Vb 3 |
| 370 | \& $& Entire matched string |
| 371 | \& $` Everything prior to matched string |
| 372 | \& $' Everything after to matched string |
| 373 | .Ve |
| 374 | .PP |
| 375 | The use of those last three will slow down \fBall\fR regex use |
| 376 | within your program. Consult perlvar for \f(CW@LAST_MATCH_START\fR |
| 377 | to see equivalent expressions that won't cause slow down. |
| 378 | See also Devel::SawAmpersand. |
| 379 | .PP |
| 380 | .Vb 6 |
| 381 | \& $1, $2 ... hold the Xth captured expr |
| 382 | \& $+ Last parenthesized pattern match |
| 383 | \& $^N Holds the most recently closed capture |
| 384 | \& $^R Holds the result of the last (?{...}) expr |
| 385 | \& @- Offsets of starts of groups. $-[0] holds start of whole match |
| 386 | \& @+ Offsets of ends of groups. $+[0] holds end of whole match |
| 387 | .Ve |
| 388 | .PP |
| 389 | Captured groups are numbered according to their \fIopening\fR paren. |
| 390 | .Sh "\s-1FUNCTIONS\s0" |
| 391 | .IX Subsection "FUNCTIONS" |
| 392 | .Vb 4 |
| 393 | \& lc Lowercase a string |
| 394 | \& lcfirst Lowercase first char of a string |
| 395 | \& uc Uppercase a string |
| 396 | \& ucfirst Titlecase first char of a string |
| 397 | .Ve |
| 398 | .PP |
| 399 | .Vb 4 |
| 400 | \& pos Return or set current match position |
| 401 | \& quotemeta Quote metacharacters |
| 402 | \& reset Reset ?pattern? status |
| 403 | \& study Analyze string for optimizing matching |
| 404 | .Ve |
| 405 | .PP |
| 406 | .Vb 1 |
| 407 | \& split Use regex to split a string into parts |
| 408 | .Ve |
| 409 | .PP |
| 410 | The first four of these are like the escape sequences \f(CW\*(C`\eL\*(C'\fR, \f(CW\*(C`\el\*(C'\fR, |
| 411 | \&\f(CW\*(C`\eU\*(C'\fR, and \f(CW\*(C`\eu\*(C'\fR. For Titlecase, see \*(L"Titlecase\*(R". |
| 412 | .Sh "\s-1TERMINOLOGY\s0" |
| 413 | .IX Subsection "TERMINOLOGY" |
| 414 | \fITitlecase\fR |
| 415 | .IX Subsection "Titlecase" |
| 416 | .PP |
| 417 | Unicode concept which most often is equal to uppercase, but for |
| 418 | certain characters like the German \*(L"sharp s\*(R" there is a difference. |
| 419 | .SH "AUTHOR" |
| 420 | .IX Header "AUTHOR" |
| 421 | Iain Truskett. |
| 422 | .PP |
| 423 | This document may be distributed under the same terms as Perl itself. |
| 424 | .SH "SEE ALSO" |
| 425 | .IX Header "SEE ALSO" |
| 426 | .IP "\(bu" 4 |
| 427 | perlretut for a tutorial on regular expressions. |
| 428 | .IP "\(bu" 4 |
| 429 | perlrequick for a rapid tutorial. |
| 430 | .IP "\(bu" 4 |
| 431 | perlre for more details. |
| 432 | .IP "\(bu" 4 |
| 433 | perlvar for details on the variables. |
| 434 | .IP "\(bu" 4 |
| 435 | perlop for details on the operators. |
| 436 | .IP "\(bu" 4 |
| 437 | perlfunc for details on the functions. |
| 438 | .IP "\(bu" 4 |
| 439 | perlfaq6 for FAQs on regular expressions. |
| 440 | .IP "\(bu" 4 |
| 441 | The re module to alter behaviour and aid |
| 442 | debugging. |
| 443 | .IP "\(bu" 4 |
| 444 | \&\*(L"Debugging regular expressions\*(R" in perldebug |
| 445 | .IP "\(bu" 4 |
| 446 | perluniintro, perlunicode, charnames and locale |
| 447 | for details on regexes and internationalisation. |
| 448 | .IP "\(bu" 4 |
| 449 | \&\fIMastering Regular Expressions\fR by Jeffrey Friedl |
| 450 | (\fIhttp://regex.info/\fR) for a thorough grounding and |
| 451 | reference on the topic. |
| 452 | .SH "THANKS" |
| 453 | .IX Header "THANKS" |
| 454 | David P.C. Wollmann, |
| 455 | Richard Soderberg, |
| 456 | Sean M. Burke, |
| 457 | Tom Christiansen, |
| 458 | Jim Cromie, |
| 459 | and |
| 460 | Jeffrey Goff |
| 461 | for useful advice. |