| 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 "Text::Balanced 3" |
| 132 | .TH Text::Balanced 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Text::Balanced \- Extract delimited text sequences from strings. |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 8 |
| 138 | \& use Text::Balanced qw ( |
| 139 | \& extract_delimited |
| 140 | \& extract_bracketed |
| 141 | \& extract_quotelike |
| 142 | \& extract_codeblock |
| 143 | \& extract_variable |
| 144 | \& extract_tagged |
| 145 | \& extract_multiple |
| 146 | .Ve |
| 147 | .PP |
| 148 | .Vb 3 |
| 149 | \& gen_delimited_pat |
| 150 | \& gen_extract_tagged |
| 151 | \& ); |
| 152 | .Ve |
| 153 | .PP |
| 154 | .Vb 2 |
| 155 | \& # Extract the initial substring of $text that is delimited by |
| 156 | \& # two (unescaped) instances of the first character in $delim. |
| 157 | .Ve |
| 158 | .PP |
| 159 | .Vb 1 |
| 160 | \& ($extracted, $remainder) = extract_delimited($text,$delim); |
| 161 | .Ve |
| 162 | .PP |
| 163 | .Vb 3 |
| 164 | \& # Extract the initial substring of $text that is bracketed |
| 165 | \& # with a delimiter(s) specified by $delim (where the string |
| 166 | \& # in $delim contains one or more of '(){}[]<>'). |
| 167 | .Ve |
| 168 | .PP |
| 169 | .Vb 1 |
| 170 | \& ($extracted, $remainder) = extract_bracketed($text,$delim); |
| 171 | .Ve |
| 172 | .PP |
| 173 | .Vb 2 |
| 174 | \& # Extract the initial substring of $text that is bounded by |
| 175 | \& # an XML tag. |
| 176 | .Ve |
| 177 | .PP |
| 178 | .Vb 1 |
| 179 | \& ($extracted, $remainder) = extract_tagged($text); |
| 180 | .Ve |
| 181 | .PP |
| 182 | .Vb 2 |
| 183 | \& # Extract the initial substring of $text that is bounded by |
| 184 | \& # a C<BEGIN>...C<END> pair. Don't allow nested C<BEGIN> tags |
| 185 | .Ve |
| 186 | .PP |
| 187 | .Vb 2 |
| 188 | \& ($extracted, $remainder) = |
| 189 | \& extract_tagged($text,"BEGIN","END",undef,{bad=>["BEGIN"]}); |
| 190 | .Ve |
| 191 | .PP |
| 192 | .Vb 2 |
| 193 | \& # Extract the initial substring of $text that represents a |
| 194 | \& # Perl "quote or quote-like operation" |
| 195 | .Ve |
| 196 | .PP |
| 197 | .Vb 1 |
| 198 | \& ($extracted, $remainder) = extract_quotelike($text); |
| 199 | .Ve |
| 200 | .PP |
| 201 | .Vb 3 |
| 202 | \& # Extract the initial substring of $text that represents a block |
| 203 | \& # of Perl code, bracketed by any of character(s) specified by $delim |
| 204 | \& # (where the string $delim contains one or more of '(){}[]<>'). |
| 205 | .Ve |
| 206 | .PP |
| 207 | .Vb 1 |
| 208 | \& ($extracted, $remainder) = extract_codeblock($text,$delim); |
| 209 | .Ve |
| 210 | .PP |
| 211 | .Vb 3 |
| 212 | \& # Extract the initial substrings of $text that would be extracted by |
| 213 | \& # one or more sequential applications of the specified functions |
| 214 | \& # or regular expressions |
| 215 | .Ve |
| 216 | .PP |
| 217 | .Vb 7 |
| 218 | \& @extracted = extract_multiple($text, |
| 219 | \& [ \e&extract_bracketed, |
| 220 | \& \e&extract_quotelike, |
| 221 | \& \e&some_other_extractor_sub, |
| 222 | \& qr/[xyz]*/, |
| 223 | \& 'literal', |
| 224 | \& ]); |
| 225 | .Ve |
| 226 | .PP |
| 227 | # Create a string representing an optimized pattern (a la Friedl) |
| 228 | # that matches a substring delimited by any of the specified characters |
| 229 | # (in this case: any type of quote or a slash) |
| 230 | .PP |
| 231 | .Vb 1 |
| 232 | \& $patstring = gen_delimited_pat(q{'"`/}); |
| 233 | .Ve |
| 234 | .PP |
| 235 | # Generate a reference to an anonymous sub that is just like extract_tagged |
| 236 | # but pre-compiled and optimized for a specific pair of tags, and consequently |
| 237 | # much faster (i.e. 3 times faster). It uses qr// for better performance on |
| 238 | # repeated calls, so it only works under Perl 5.005 or later. |
| 239 | .PP |
| 240 | .Vb 1 |
| 241 | \& $extract_head = gen_extract_tagged('<HEAD>','</HEAD>'); |
| 242 | .Ve |
| 243 | .PP |
| 244 | .Vb 1 |
| 245 | \& ($extracted, $remainder) = $extract_head->($text); |
| 246 | .Ve |
| 247 | .SH "DESCRIPTION" |
| 248 | .IX Header "DESCRIPTION" |
| 249 | The various \f(CW\*(C`extract_...\*(C'\fR subroutines may be used to |
| 250 | extract a delimited substring, possibly after skipping a |
| 251 | specified prefix string. By default, that prefix is |
| 252 | optional whitespace (\f(CW\*(C`/\es*/\*(C'\fR), but you can change it to whatever |
| 253 | you wish (see below). |
| 254 | .PP |
| 255 | The substring to be extracted must appear at the |
| 256 | current \f(CW\*(C`pos\*(C'\fR location of the string's variable |
| 257 | (or at index zero, if no \f(CW\*(C`pos\*(C'\fR position is defined). |
| 258 | In other words, the \f(CW\*(C`extract_...\*(C'\fR subroutines \fIdon't\fR |
| 259 | extract the first occurance of a substring anywhere |
| 260 | in a string (like an unanchored regex would). Rather, |
| 261 | they extract an occurance of the substring appearing |
| 262 | immediately at the current matching position in the |
| 263 | string (like a \f(CW\*(C`\eG\*(C'\fR\-anchored regex would). |
| 264 | .Sh "General behaviour in list contexts" |
| 265 | .IX Subsection "General behaviour in list contexts" |
| 266 | In a list context, all the subroutines return a list, the first three |
| 267 | elements of which are always: |
| 268 | .IP "[0]" 4 |
| 269 | .IX Item "[0]" |
| 270 | The extracted string, including the specified delimiters. |
| 271 | If the extraction fails an empty string is returned. |
| 272 | .IP "[1]" 4 |
| 273 | .IX Item "[1]" |
| 274 | The remainder of the input string (i.e. the characters after the |
| 275 | extracted string). On failure, the entire string is returned. |
| 276 | .IP "[2]" 4 |
| 277 | .IX Item "[2]" |
| 278 | The skipped prefix (i.e. the characters before the extracted string). |
| 279 | On failure, the empty string is returned. |
| 280 | .PP |
| 281 | Note that in a list context, the contents of the original input text (the first |
| 282 | argument) are not modified in any way. |
| 283 | .PP |
| 284 | However, if the input text was passed in a variable, that variable's |
| 285 | \&\f(CW\*(C`pos\*(C'\fR value is updated to point at the first character after the |
| 286 | extracted text. That means that in a list context the various |
| 287 | subroutines can be used much like regular expressions. For example: |
| 288 | .PP |
| 289 | .Vb 4 |
| 290 | \& while ( $next = (extract_quotelike($text))[0] ) |
| 291 | \& { |
| 292 | \& # process next quote-like (in $next) |
| 293 | \& } |
| 294 | .Ve |
| 295 | .Sh "General behaviour in scalar and void contexts" |
| 296 | .IX Subsection "General behaviour in scalar and void contexts" |
| 297 | In a scalar context, the extracted string is returned, having first been |
| 298 | removed from the input text. Thus, the following code also processes |
| 299 | each quote-like operation, but actually removes them from \f(CW$text:\fR |
| 300 | .PP |
| 301 | .Vb 4 |
| 302 | \& while ( $next = extract_quotelike($text) ) |
| 303 | \& { |
| 304 | \& # process next quote-like (in $next) |
| 305 | \& } |
| 306 | .Ve |
| 307 | .PP |
| 308 | Note that if the input text is a read-only string (i.e. a literal), |
| 309 | no attempt is made to remove the extracted text. |
| 310 | .PP |
| 311 | In a void context the behaviour of the extraction subroutines is |
| 312 | exactly the same as in a scalar context, except (of course) that the |
| 313 | extracted substring is not returned. |
| 314 | .Sh "A note about prefixes" |
| 315 | .IX Subsection "A note about prefixes" |
| 316 | Prefix patterns are matched without any trailing modifiers (\f(CW\*(C`/gimsox\*(C'\fR etc.) |
| 317 | This can bite you if you're expecting a prefix specification like |
| 318 | \&'.*?(?=<H1>)' to skip everything up to the first <H1> tag. Such a prefix |
| 319 | pattern will only succeed if the <H1> tag is on the current line, since |
| 320 | \&. normally doesn't match newlines. |
| 321 | .PP |
| 322 | To overcome this limitation, you need to turn on /s matching within |
| 323 | the prefix pattern, using the \f(CW\*(C`(?s)\*(C'\fR directive: '(?s).*?(?=<H1>)' |
| 324 | .ie n .Sh """extract_delimited""" |
| 325 | .el .Sh "\f(CWextract_delimited\fP" |
| 326 | .IX Subsection "extract_delimited" |
| 327 | The \f(CW\*(C`extract_delimited\*(C'\fR function formalizes the common idiom |
| 328 | of extracting a single-character-delimited substring from the start of |
| 329 | a string. For example, to extract a single-quote delimited string, the |
| 330 | following code is typically used: |
| 331 | .PP |
| 332 | .Vb 2 |
| 333 | \& ($remainder = $text) =~ s/\eA('(\e\e.|[^'])*')//s; |
| 334 | \& $extracted = $1; |
| 335 | .Ve |
| 336 | .PP |
| 337 | but with \f(CW\*(C`extract_delimited\*(C'\fR it can be simplified to: |
| 338 | .PP |
| 339 | .Vb 1 |
| 340 | \& ($extracted,$remainder) = extract_delimited($text, "'"); |
| 341 | .Ve |
| 342 | .PP |
| 343 | \&\f(CW\*(C`extract_delimited\*(C'\fR takes up to four scalars (the input text, the |
| 344 | delimiters, a prefix pattern to be skipped, and any escape characters) |
| 345 | and extracts the initial substring of the text that |
| 346 | is appropriately delimited. If the delimiter string has multiple |
| 347 | characters, the first one encountered in the text is taken to delimit |
| 348 | the substring. |
| 349 | The third argument specifies a prefix pattern that is to be skipped |
| 350 | (but must be present!) before the substring is extracted. |
| 351 | The final argument specifies the escape character to be used for each |
| 352 | delimiter. |
| 353 | .PP |
| 354 | All arguments are optional. If the escape characters are not specified, |
| 355 | every delimiter is escaped with a backslash (\f(CW\*(C`\e\*(C'\fR). |
| 356 | If the prefix is not specified, the |
| 357 | pattern \f(CW'\es*'\fR \- optional whitespace \- is used. If the delimiter set |
| 358 | is also not specified, the set \f(CW\*(C`/["'`]/\*(C'\fR is used. If the text to be processed |
| 359 | is not specified either, \f(CW$_\fR is used. |
| 360 | .PP |
| 361 | In list context, \f(CW\*(C`extract_delimited\*(C'\fR returns a array of three |
| 362 | elements, the extracted substring (\fIincluding the surrounding |
| 363 | delimiters\fR), the remainder of the text, and the skipped prefix (if |
| 364 | any). If a suitable delimited substring is not found, the first |
| 365 | element of the array is the empty string, the second is the complete |
| 366 | original text, and the prefix returned in the third element is an |
| 367 | empty string. |
| 368 | .PP |
| 369 | In a scalar context, just the extracted substring is returned. In |
| 370 | a void context, the extracted substring (and any prefix) are simply |
| 371 | removed from the beginning of the first argument. |
| 372 | .PP |
| 373 | Examples: |
| 374 | .PP |
| 375 | .Vb 1 |
| 376 | \& # Remove a single-quoted substring from the very beginning of $text: |
| 377 | .Ve |
| 378 | .PP |
| 379 | .Vb 1 |
| 380 | \& $substring = extract_delimited($text, "'", ''); |
| 381 | .Ve |
| 382 | .PP |
| 383 | .Vb 3 |
| 384 | \& # Remove a single-quoted Pascalish substring (i.e. one in which |
| 385 | \& # doubling the quote character escapes it) from the very |
| 386 | \& # beginning of $text: |
| 387 | .Ve |
| 388 | .PP |
| 389 | .Vb 1 |
| 390 | \& $substring = extract_delimited($text, "'", '', "'"); |
| 391 | .Ve |
| 392 | .PP |
| 393 | .Vb 3 |
| 394 | \& # Extract a single- or double- quoted substring from the |
| 395 | \& # beginning of $text, optionally after some whitespace |
| 396 | \& # (note the list context to protect $text from modification): |
| 397 | .Ve |
| 398 | .PP |
| 399 | .Vb 1 |
| 400 | \& ($substring) = extract_delimited $text, q{"'}; |
| 401 | .Ve |
| 402 | .PP |
| 403 | .Vb 1 |
| 404 | \& # Delete the substring delimited by the first '/' in $text: |
| 405 | .Ve |
| 406 | .PP |
| 407 | .Vb 1 |
| 408 | \& $text = join '', (extract_delimited($text,'/','[^/]*')[2,1]; |
| 409 | .Ve |
| 410 | .PP |
| 411 | Note that this last example is \fInot\fR the same as deleting the first |
| 412 | quote-like pattern. For instance, if \f(CW$text\fR contained the string: |
| 413 | .PP |
| 414 | .Vb 1 |
| 415 | \& "if ('./cmd' =~ m/$UNIXCMD/s) { $cmd = $1; }" |
| 416 | .Ve |
| 417 | .PP |
| 418 | then after the deletion it would contain: |
| 419 | .PP |
| 420 | .Vb 1 |
| 421 | \& "if ('.$UNIXCMD/s) { $cmd = $1; }" |
| 422 | .Ve |
| 423 | .PP |
| 424 | not: |
| 425 | .PP |
| 426 | .Vb 1 |
| 427 | \& "if ('./cmd' =~ ms) { $cmd = $1; }" |
| 428 | .Ve |
| 429 | .PP |
| 430 | See \*(L"extract_quotelike\*(R" for a (partial) solution to this problem. |
| 431 | .ie n .Sh """extract_bracketed""" |
| 432 | .el .Sh "\f(CWextract_bracketed\fP" |
| 433 | .IX Subsection "extract_bracketed" |
| 434 | Like \f(CW"extract_delimited"\fR, the \f(CW\*(C`extract_bracketed\*(C'\fR function takes |
| 435 | up to three optional scalar arguments: a string to extract from, a delimiter |
| 436 | specifier, and a prefix pattern. As before, a missing prefix defaults to |
| 437 | optional whitespace and a missing text defaults to \f(CW$_\fR. However, a missing |
| 438 | delimiter specifier defaults to \f(CW'{}()[]<>'\fR (see below). |
| 439 | .PP |
| 440 | \&\f(CW\*(C`extract_bracketed\*(C'\fR extracts a balanced-bracket-delimited |
| 441 | substring (using any one (or more) of the user-specified delimiter |
| 442 | brackets: '(..)', '{..}', '[..]', or '<..>'). Optionally it will also |
| 443 | respect quoted unbalanced brackets (see below). |
| 444 | .PP |
| 445 | A \*(L"delimiter bracket\*(R" is a bracket in list of delimiters passed as |
| 446 | \&\f(CW\*(C`extract_bracketed\*(C'\fR's second argument. Delimiter brackets are |
| 447 | specified by giving either the left or right (or both!) versions |
| 448 | of the required bracket(s). Note that the order in which |
| 449 | two or more delimiter brackets are specified is not significant. |
| 450 | .PP |
| 451 | A \*(L"balanced\-bracket\-delimited substring\*(R" is a substring bounded by |
| 452 | matched brackets, such that any other (left or right) delimiter |
| 453 | bracket \fIwithin\fR the substring is also matched by an opposite |
| 454 | (right or left) delimiter bracket \fIat the same level of nesting\fR. Any |
| 455 | type of bracket not in the delimiter list is treated as an ordinary |
| 456 | character. |
| 457 | .PP |
| 458 | In other words, each type of bracket specified as a delimiter must be |
| 459 | balanced and correctly nested within the substring, and any other kind of |
| 460 | (\*(L"non\-delimiter\*(R") bracket in the substring is ignored. |
| 461 | .PP |
| 462 | For example, given the string: |
| 463 | .PP |
| 464 | .Vb 1 |
| 465 | \& $text = "{ an '[irregularly :-(] {} parenthesized >:-)' string }"; |
| 466 | .Ve |
| 467 | .PP |
| 468 | then a call to \f(CW\*(C`extract_bracketed\*(C'\fR in a list context: |
| 469 | .PP |
| 470 | .Vb 1 |
| 471 | \& @result = extract_bracketed( $text, '{}' ); |
| 472 | .Ve |
| 473 | .PP |
| 474 | would return: |
| 475 | .PP |
| 476 | .Vb 1 |
| 477 | \& ( "{ an '[irregularly :-(] {} parenthesized >:-)' string }" , "" , "" ) |
| 478 | .Ve |
| 479 | .PP |
| 480 | since both sets of \f(CW'{..}'\fR brackets are properly nested and evenly balanced. |
| 481 | (In a scalar context just the first element of the array would be returned. In |
| 482 | a void context, \f(CW$text\fR would be replaced by an empty string.) |
| 483 | .PP |
| 484 | Likewise the call in: |
| 485 | .PP |
| 486 | .Vb 1 |
| 487 | \& @result = extract_bracketed( $text, '{[' ); |
| 488 | .Ve |
| 489 | .PP |
| 490 | would return the same result, since all sets of both types of specified |
| 491 | delimiter brackets are correctly nested and balanced. |
| 492 | .PP |
| 493 | However, the call in: |
| 494 | .PP |
| 495 | .Vb 1 |
| 496 | \& @result = extract_bracketed( $text, '{([<' ); |
| 497 | .Ve |
| 498 | .PP |
| 499 | would fail, returning: |
| 500 | .PP |
| 501 | .Vb 1 |
| 502 | \& ( undef , "{ an '[irregularly :-(] {} parenthesized >:-)' string }" ); |
| 503 | .Ve |
| 504 | .PP |
| 505 | because the embedded pairs of \f(CW'(..)'\fRs and \f(CW'[..]'\fRs are \*(L"cross\-nested\*(R" and |
| 506 | the embedded \f(CW'>'\fR is unbalanced. (In a scalar context, this call would |
| 507 | return an empty string. In a void context, \f(CW$text\fR would be unchanged.) |
| 508 | .PP |
| 509 | Note that the embedded single-quotes in the string don't help in this |
| 510 | case, since they have not been specified as acceptable delimiters and are |
| 511 | therefore treated as non-delimiter characters (and ignored). |
| 512 | .PP |
| 513 | However, if a particular species of quote character is included in the |
| 514 | delimiter specification, then that type of quote will be correctly handled. |
| 515 | for example, if \f(CW$text\fR is: |
| 516 | .PP |
| 517 | .Vb 1 |
| 518 | \& $text = '<A HREF=">>>>">link</A>'; |
| 519 | .Ve |
| 520 | .PP |
| 521 | then |
| 522 | .PP |
| 523 | .Vb 1 |
| 524 | \& @result = extract_bracketed( $text, '<">' ); |
| 525 | .Ve |
| 526 | .PP |
| 527 | returns: |
| 528 | .PP |
| 529 | .Vb 1 |
| 530 | \& ( '<A HREF=">>>>">', 'link</A>', "" ) |
| 531 | .Ve |
| 532 | .PP |
| 533 | as expected. Without the specification of \f(CW\*(C`"\*(C'\fR as an embedded quoter: |
| 534 | .PP |
| 535 | .Vb 1 |
| 536 | \& @result = extract_bracketed( $text, '<>' ); |
| 537 | .Ve |
| 538 | .PP |
| 539 | the result would be: |
| 540 | .PP |
| 541 | .Vb 1 |
| 542 | \& ( '<A HREF=">', '>>>">link</A>', "" ) |
| 543 | .Ve |
| 544 | .PP |
| 545 | In addition to the quote delimiters \f(CW\*(C`'\*(C'\fR, \f(CW\*(C`"\*(C'\fR, and \f(CW\*(C``\*(C'\fR, full Perl quote-like |
| 546 | quoting (i.e. q{string}, qq{string}, etc) can be specified by including the |
| 547 | letter 'q' as a delimiter. Hence: |
| 548 | .PP |
| 549 | .Vb 1 |
| 550 | \& @result = extract_bracketed( $text, '<q>' ); |
| 551 | .Ve |
| 552 | .PP |
| 553 | would correctly match something like this: |
| 554 | .PP |
| 555 | .Vb 1 |
| 556 | \& $text = '<leftop: conj /and/ conj>'; |
| 557 | .Ve |
| 558 | .PP |
| 559 | See also: \f(CW"extract_quotelike"\fR and \f(CW"extract_codeblock"\fR. |
| 560 | .ie n .Sh """extract_variable""" |
| 561 | .el .Sh "\f(CWextract_variable\fP" |
| 562 | .IX Subsection "extract_variable" |
| 563 | \&\f(CW\*(C`extract_variable\*(C'\fR extracts any valid Perl variable or |
| 564 | variable-involved expression, including scalars, arrays, hashes, array |
| 565 | accesses, hash look\-ups, method calls through objects, subroutine calles |
| 566 | through subroutine references, etc. |
| 567 | .PP |
| 568 | The subroutine takes up to two optional arguments: |
| 569 | .IP "1." 4 |
| 570 | A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 571 | .IP "2." 4 |
| 572 | A string specifying a pattern to be matched as a prefix (which is to be |
| 573 | skipped). If omitted, optional whitespace is skipped. |
| 574 | .PP |
| 575 | On success in a list context, an array of 3 elements is returned. The |
| 576 | elements are: |
| 577 | .IP "[0]" 4 |
| 578 | .IX Item "[0]" |
| 579 | the extracted variable, or variablish expression |
| 580 | .IP "[1]" 4 |
| 581 | .IX Item "[1]" |
| 582 | the remainder of the input text, |
| 583 | .IP "[2]" 4 |
| 584 | .IX Item "[2]" |
| 585 | the prefix substring (if any), |
| 586 | .PP |
| 587 | On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 588 | .PP |
| 589 | In a scalar context, \f(CW\*(C`extract_variable\*(C'\fR returns just the complete |
| 590 | substring that matched a variablish expression. \f(CW\*(C`undef\*(C'\fR is returned on |
| 591 | failure. In addition, the original input text has the returned substring |
| 592 | (and any prefix) removed from it. |
| 593 | .PP |
| 594 | In a void context, the input text just has the matched substring (and |
| 595 | any specified prefix) removed. |
| 596 | .ie n .Sh """extract_tagged""" |
| 597 | .el .Sh "\f(CWextract_tagged\fP" |
| 598 | .IX Subsection "extract_tagged" |
| 599 | \&\f(CW\*(C`extract_tagged\*(C'\fR extracts and segments text between (balanced) |
| 600 | specified tags. |
| 601 | .PP |
| 602 | The subroutine takes up to five optional arguments: |
| 603 | .IP "1." 4 |
| 604 | A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 605 | .IP "2." 4 |
| 606 | A string specifying a pattern to be matched as the opening tag. |
| 607 | If the pattern string is omitted (or \f(CW\*(C`undef\*(C'\fR) then a pattern |
| 608 | that matches any standard \s-1XML\s0 tag is used. |
| 609 | .IP "3." 4 |
| 610 | A string specifying a pattern to be matched at the closing tag. |
| 611 | If the pattern string is omitted (or \f(CW\*(C`undef\*(C'\fR) then the closing |
| 612 | tag is constructed by inserting a \f(CW\*(C`/\*(C'\fR after any leading bracket |
| 613 | characters in the actual opening tag that was matched (\fInot\fR the pattern |
| 614 | that matched the tag). For example, if the opening tag pattern |
| 615 | is specified as \f(CW'{{\ew+}}'\fR and actually matched the opening tag |
| 616 | \&\f(CW"{{DATA}}"\fR, then the constructed closing tag would be \f(CW"{{/DATA}}"\fR. |
| 617 | .IP "4." 4 |
| 618 | A string specifying a pattern to be matched as a prefix (which is to be |
| 619 | skipped). If omitted, optional whitespace is skipped. |
| 620 | .IP "5." 4 |
| 621 | A hash reference containing various parsing options (see below) |
| 622 | .PP |
| 623 | The various options that can be specified are: |
| 624 | .ie n .IP """reject => $listref""" 4 |
| 625 | .el .IP "\f(CWreject => $listref\fR" 4 |
| 626 | .IX Item "reject => $listref" |
| 627 | The list reference contains one or more strings specifying patterns |
| 628 | that must \fInot\fR appear within the tagged text. |
| 629 | .Sp |
| 630 | For example, to extract |
| 631 | an \s-1HTML\s0 link (which should not contain nested links) use: |
| 632 | .Sp |
| 633 | .Vb 1 |
| 634 | \& extract_tagged($text, '<A>', '</A>', undef, {reject => ['<A>']} ); |
| 635 | .Ve |
| 636 | .ie n .IP """ignore => $listref""" 4 |
| 637 | .el .IP "\f(CWignore => $listref\fR" 4 |
| 638 | .IX Item "ignore => $listref" |
| 639 | The list reference contains one or more strings specifying patterns |
| 640 | that are \fInot\fR be be treated as nested tags within the tagged text |
| 641 | (even if they would match the start tag pattern). |
| 642 | .Sp |
| 643 | For example, to extract an arbitrary \s-1XML\s0 tag, but ignore \*(L"empty\*(R" elements: |
| 644 | .Sp |
| 645 | .Vb 1 |
| 646 | \& extract_tagged($text, undef, undef, undef, {ignore => ['<[^>]*/>']} ); |
| 647 | .Ve |
| 648 | .Sp |
| 649 | (also see \*(L"gen_delimited_pat\*(R" below). |
| 650 | .ie n .IP """fail => $str""" 4 |
| 651 | .el .IP "\f(CWfail => $str\fR" 4 |
| 652 | .IX Item "fail => $str" |
| 653 | The \f(CW\*(C`fail\*(C'\fR option indicates the action to be taken if a matching end |
| 654 | tag is not encountered (i.e. before the end of the string or some |
| 655 | \&\f(CW\*(C`reject\*(C'\fR pattern matches). By default, a failure to match a closing |
| 656 | tag causes \f(CW\*(C`extract_tagged\*(C'\fR to immediately fail. |
| 657 | .Sp |
| 658 | However, if the string value associated with <reject> is \*(L"\s-1MAX\s0\*(R", then |
| 659 | \&\f(CW\*(C`extract_tagged\*(C'\fR returns the complete text up to the point of failure. |
| 660 | If the string is \*(L"\s-1PARA\s0\*(R", \f(CW\*(C`extract_tagged\*(C'\fR returns only the first paragraph |
| 661 | after the tag (up to the first line that is either empty or contains |
| 662 | only whitespace characters). |
| 663 | If the string is "", the the default behaviour (i.e. failure) is reinstated. |
| 664 | .Sp |
| 665 | For example, suppose the start tag \*(L"/para\*(R" introduces a paragraph, which then |
| 666 | continues until the next \*(L"/endpara\*(R" tag or until another \*(L"/para\*(R" tag is |
| 667 | encountered: |
| 668 | .Sp |
| 669 | .Vb 1 |
| 670 | \& $text = "/para line 1\en\enline 3\en/para line 4"; |
| 671 | .Ve |
| 672 | .Sp |
| 673 | .Vb 2 |
| 674 | \& extract_tagged($text, '/para', '/endpara', undef, |
| 675 | \& {reject => '/para', fail => MAX ); |
| 676 | .Ve |
| 677 | .Sp |
| 678 | .Vb 1 |
| 679 | \& # EXTRACTED: "/para line 1\en\enline 3\en" |
| 680 | .Ve |
| 681 | .Sp |
| 682 | Suppose instead, that if no matching \*(L"/endpara\*(R" tag is found, the \*(L"/para\*(R" |
| 683 | tag refers only to the immediately following paragraph: |
| 684 | .Sp |
| 685 | .Vb 1 |
| 686 | \& $text = "/para line 1\en\enline 3\en/para line 4"; |
| 687 | .Ve |
| 688 | .Sp |
| 689 | .Vb 2 |
| 690 | \& extract_tagged($text, '/para', '/endpara', undef, |
| 691 | \& {reject => '/para', fail => MAX ); |
| 692 | .Ve |
| 693 | .Sp |
| 694 | .Vb 1 |
| 695 | \& # EXTRACTED: "/para line 1\en" |
| 696 | .Ve |
| 697 | .Sp |
| 698 | Note that the specified \f(CW\*(C`fail\*(C'\fR behaviour applies to nested tags as well. |
| 699 | .PP |
| 700 | On success in a list context, an array of 6 elements is returned. The elements are: |
| 701 | .IP "[0]" 4 |
| 702 | .IX Item "[0]" |
| 703 | the extracted tagged substring (including the outermost tags), |
| 704 | .IP "[1]" 4 |
| 705 | .IX Item "[1]" |
| 706 | the remainder of the input text, |
| 707 | .IP "[2]" 4 |
| 708 | .IX Item "[2]" |
| 709 | the prefix substring (if any), |
| 710 | .IP "[3]" 4 |
| 711 | .IX Item "[3]" |
| 712 | the opening tag |
| 713 | .IP "[4]" 4 |
| 714 | .IX Item "[4]" |
| 715 | the text between the opening and closing tags |
| 716 | .IP "[5]" 4 |
| 717 | .IX Item "[5]" |
| 718 | the closing tag (or "" if no closing tag was found) |
| 719 | .PP |
| 720 | On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 721 | .PP |
| 722 | In a scalar context, \f(CW\*(C`extract_tagged\*(C'\fR returns just the complete |
| 723 | substring that matched a tagged text (including the start and end |
| 724 | tags). \f(CW\*(C`undef\*(C'\fR is returned on failure. In addition, the original input |
| 725 | text has the returned substring (and any prefix) removed from it. |
| 726 | .PP |
| 727 | In a void context, the input text just has the matched substring (and |
| 728 | any specified prefix) removed. |
| 729 | .ie n .Sh """gen_extract_tagged""" |
| 730 | .el .Sh "\f(CWgen_extract_tagged\fP" |
| 731 | .IX Subsection "gen_extract_tagged" |
| 732 | (Note: This subroutine is only available under Perl5.005) |
| 733 | .PP |
| 734 | \&\f(CW\*(C`gen_extract_tagged\*(C'\fR generates a new anonymous subroutine which |
| 735 | extracts text between (balanced) specified tags. In other words, |
| 736 | it generates a function identical in function to \f(CW\*(C`extract_tagged\*(C'\fR. |
| 737 | .PP |
| 738 | The difference between \f(CW\*(C`extract_tagged\*(C'\fR and the anonymous |
| 739 | subroutines generated by |
| 740 | \&\f(CW\*(C`gen_extract_tagged\*(C'\fR, is that those generated subroutines: |
| 741 | .IP "\(bu" 4 |
| 742 | do not have to reparse tag specification or parsing options every time |
| 743 | they are called (whereas \f(CW\*(C`extract_tagged\*(C'\fR has to effectively rebuild |
| 744 | its tag parser on every call); |
| 745 | .IP "\(bu" 4 |
| 746 | make use of the new qr// construct to pre-compile the regexes they use |
| 747 | (whereas \f(CW\*(C`extract_tagged\*(C'\fR uses standard string variable interpolation |
| 748 | to create tag-matching patterns). |
| 749 | .PP |
| 750 | The subroutine takes up to four optional arguments (the same set as |
| 751 | \&\f(CW\*(C`extract_tagged\*(C'\fR except for the string to be processed). It returns |
| 752 | a reference to a subroutine which in turn takes a single argument (the text to |
| 753 | be extracted from). |
| 754 | .PP |
| 755 | In other words, the implementation of \f(CW\*(C`extract_tagged\*(C'\fR is exactly |
| 756 | equivalent to: |
| 757 | .PP |
| 758 | .Vb 6 |
| 759 | \& sub extract_tagged |
| 760 | \& { |
| 761 | \& my $text = shift; |
| 762 | \& $extractor = gen_extract_tagged(@_); |
| 763 | \& return $extractor->($text); |
| 764 | \& } |
| 765 | .Ve |
| 766 | .PP |
| 767 | (although \f(CW\*(C`extract_tagged\*(C'\fR is not currently implemented that way, in order |
| 768 | to preserve pre\-5.005 compatibility). |
| 769 | .PP |
| 770 | Using \f(CW\*(C`gen_extract_tagged\*(C'\fR to create extraction functions for specific tags |
| 771 | is a good idea if those functions are going to be called more than once, since |
| 772 | their performance is typically twice as good as the more general-purpose |
| 773 | \&\f(CW\*(C`extract_tagged\*(C'\fR. |
| 774 | .ie n .Sh """extract_quotelike""" |
| 775 | .el .Sh "\f(CWextract_quotelike\fP" |
| 776 | .IX Subsection "extract_quotelike" |
| 777 | \&\f(CW\*(C`extract_quotelike\*(C'\fR attempts to recognize, extract, and segment any |
| 778 | one of the various Perl quotes and quotelike operators (see |
| 779 | \&\fIperlop\fR\|(3)) Nested backslashed delimiters, embedded balanced bracket |
| 780 | delimiters (for the quotelike operators), and trailing modifiers are |
| 781 | all caught. For example, in: |
| 782 | .PP |
| 783 | .Vb 1 |
| 784 | \& extract_quotelike 'q # an octothorpe: \e# (not the end of the q!) #' |
| 785 | .Ve |
| 786 | .PP |
| 787 | .Vb 1 |
| 788 | \& extract_quotelike ' "You said, \e"Use sed\e"." ' |
| 789 | .Ve |
| 790 | .PP |
| 791 | .Vb 1 |
| 792 | \& extract_quotelike ' s{([A-Z]{1,8}\e.[A-Z]{3})} /\eL$1\eE/; ' |
| 793 | .Ve |
| 794 | .PP |
| 795 | .Vb 1 |
| 796 | \& extract_quotelike ' tr/\e\e\e/\e\e\e\e/\e\e\e//ds; ' |
| 797 | .Ve |
| 798 | .PP |
| 799 | the full Perl quotelike operations are all extracted correctly. |
| 800 | .PP |
| 801 | Note too that, when using the /x modifier on a regex, any comment |
| 802 | containing the current pattern delimiter will cause the regex to be |
| 803 | immediately terminated. In other words: |
| 804 | .PP |
| 805 | .Vb 5 |
| 806 | \& 'm / |
| 807 | \& (?i) # CASE INSENSITIVE |
| 808 | \& [a-z_] # LEADING ALPHABETIC/UNDERSCORE |
| 809 | \& [a-z0-9]* # FOLLOWED BY ANY NUMBER OF ALPHANUMERICS |
| 810 | \& /x' |
| 811 | .Ve |
| 812 | .PP |
| 813 | will be extracted as if it were: |
| 814 | .PP |
| 815 | .Vb 3 |
| 816 | \& 'm / |
| 817 | \& (?i) # CASE INSENSITIVE |
| 818 | \& [a-z_] # LEADING ALPHABETIC/' |
| 819 | .Ve |
| 820 | .PP |
| 821 | This behaviour is identical to that of the actual compiler. |
| 822 | .PP |
| 823 | \&\f(CW\*(C`extract_quotelike\*(C'\fR takes two arguments: the text to be processed and |
| 824 | a prefix to be matched at the very beginning of the text. If no prefix |
| 825 | is specified, optional whitespace is the default. If no text is given, |
| 826 | \&\f(CW$_\fR is used. |
| 827 | .PP |
| 828 | In a list context, an array of 11 elements is returned. The elements are: |
| 829 | .IP "[0]" 4 |
| 830 | .IX Item "[0]" |
| 831 | the extracted quotelike substring (including trailing modifiers), |
| 832 | .IP "[1]" 4 |
| 833 | .IX Item "[1]" |
| 834 | the remainder of the input text, |
| 835 | .IP "[2]" 4 |
| 836 | .IX Item "[2]" |
| 837 | the prefix substring (if any), |
| 838 | .IP "[3]" 4 |
| 839 | .IX Item "[3]" |
| 840 | the name of the quotelike operator (if any), |
| 841 | .IP "[4]" 4 |
| 842 | .IX Item "[4]" |
| 843 | the left delimiter of the first block of the operation, |
| 844 | .IP "[5]" 4 |
| 845 | .IX Item "[5]" |
| 846 | the text of the first block of the operation |
| 847 | (that is, the contents of |
| 848 | a quote, the regex of a match or substitution or the target list of a |
| 849 | translation), |
| 850 | .IP "[6]" 4 |
| 851 | .IX Item "[6]" |
| 852 | the right delimiter of the first block of the operation, |
| 853 | .IP "[7]" 4 |
| 854 | .IX Item "[7]" |
| 855 | the left delimiter of the second block of the operation |
| 856 | (that is, if it is a \f(CW\*(C`s\*(C'\fR, \f(CW\*(C`tr\*(C'\fR, or \f(CW\*(C`y\*(C'\fR), |
| 857 | .IP "[8]" 4 |
| 858 | .IX Item "[8]" |
| 859 | the text of the second block of the operation |
| 860 | (that is, the replacement of a substitution or the translation list |
| 861 | of a translation), |
| 862 | .IP "[9]" 4 |
| 863 | .IX Item "[9]" |
| 864 | the right delimiter of the second block of the operation (if any), |
| 865 | .IP "[10]" 4 |
| 866 | .IX Item "[10]" |
| 867 | the trailing modifiers on the operation (if any). |
| 868 | .PP |
| 869 | For each of the fields marked \*(L"(if any)\*(R" the default value on success is |
| 870 | an empty string. |
| 871 | On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 872 | .PP |
| 873 | In a scalar context, \f(CW\*(C`extract_quotelike\*(C'\fR returns just the complete substring |
| 874 | that matched a quotelike operation (or \f(CW\*(C`undef\*(C'\fR on failure). In a scalar or |
| 875 | void context, the input text has the same substring (and any specified |
| 876 | prefix) removed. |
| 877 | .PP |
| 878 | Examples: |
| 879 | .PP |
| 880 | .Vb 1 |
| 881 | \& # Remove the first quotelike literal that appears in text |
| 882 | .Ve |
| 883 | .PP |
| 884 | .Vb 1 |
| 885 | \& $quotelike = extract_quotelike($text,'.*?'); |
| 886 | .Ve |
| 887 | .PP |
| 888 | .Vb 2 |
| 889 | \& # Replace one or more leading whitespace-separated quotelike |
| 890 | \& # literals in $_ with "<QLL>" |
| 891 | .Ve |
| 892 | .PP |
| 893 | .Vb 1 |
| 894 | \& do { $_ = join '<QLL>', (extract_quotelike)[2,1] } until $@; |
| 895 | .Ve |
| 896 | .PP |
| 897 | .Vb 1 |
| 898 | \& # Isolate the search pattern in a quotelike operation from $text |
| 899 | .Ve |
| 900 | .PP |
| 901 | .Vb 9 |
| 902 | \& ($op,$pat) = (extract_quotelike $text)[3,5]; |
| 903 | \& if ($op =~ /[ms]/) |
| 904 | \& { |
| 905 | \& print "search pattern: $pat\en"; |
| 906 | \& } |
| 907 | \& else |
| 908 | \& { |
| 909 | \& print "$op is not a pattern matching operation\en"; |
| 910 | \& } |
| 911 | .Ve |
| 912 | .ie n .Sh """extract_quotelike"" and ""here documents""" |
| 913 | .el .Sh "\f(CWextract_quotelike\fP and ``here documents''" |
| 914 | .IX Subsection "extract_quotelike and here documents" |
| 915 | \&\f(CW\*(C`extract_quotelike\*(C'\fR can successfully extract \*(L"here documents\*(R" from an input |
| 916 | string, but with an important caveat in list contexts. |
| 917 | .PP |
| 918 | Unlike other types of quote-like literals, a here document is rarely |
| 919 | a contiguous substring. For example, a typical piece of code using |
| 920 | here document might look like this: |
| 921 | .PP |
| 922 | .Vb 4 |
| 923 | \& <<'EOMSG' || die; |
| 924 | \& This is the message. |
| 925 | \& EOMSG |
| 926 | \& exit; |
| 927 | .Ve |
| 928 | .PP |
| 929 | Given this as an input string in a scalar context, \f(CW\*(C`extract_quotelike\*(C'\fR |
| 930 | would correctly return the string \*(L"<<'\s-1EOMSG\s0'\enThis is the message.\enEOMSG\*(R", |
| 931 | leaving the string \*(L" || die;\enexit;\*(R" in the original variable. In other words, |
| 932 | the two separate pieces of the here document are successfully extracted and |
| 933 | concatenated. |
| 934 | .PP |
| 935 | In a list context, \f(CW\*(C`extract_quotelike\*(C'\fR would return the list |
| 936 | .IP "[0]" 4 |
| 937 | .IX Item "[0]" |
| 938 | \&\*(L"<<'\s-1EOMSG\s0'\enThis is the message.\enEOMSG\en\*(R" (i.e. the full extracted here document, |
| 939 | including fore and aft delimiters), |
| 940 | .IP "[1]" 4 |
| 941 | .IX Item "[1]" |
| 942 | \&\*(L" || die;\enexit;\*(R" (i.e. the remainder of the input text, concatenated), |
| 943 | .IP "[2]" 4 |
| 944 | .IX Item "[2]" |
| 945 | "" (i.e. the prefix substring \*(-- trivial in this case), |
| 946 | .IP "[3]" 4 |
| 947 | .IX Item "[3]" |
| 948 | \&\*(L"<<\*(R" (i.e. the \*(L"name\*(R" of the quotelike operator) |
| 949 | .IP "[4]" 4 |
| 950 | .IX Item "[4]" |
| 951 | \&\*(L"'\s-1EOMSG\s0'\*(R" (i.e. the left delimiter of the here document, including any quotes), |
| 952 | .IP "[5]" 4 |
| 953 | .IX Item "[5]" |
| 954 | \&\*(L"This is the message.\en\*(R" (i.e. the text of the here document), |
| 955 | .IP "[6]" 4 |
| 956 | .IX Item "[6]" |
| 957 | \&\*(L"\s-1EOMSG\s0\*(R" (i.e. the right delimiter of the here document), |
| 958 | .IP "[7..10]" 4 |
| 959 | .IX Item "[7..10]" |
| 960 | "" (a here document has no second left delimiter, second text, second right |
| 961 | delimiter, or trailing modifiers). |
| 962 | .PP |
| 963 | However, the matching position of the input variable would be set to |
| 964 | \&\*(L"exit;\*(R" (i.e. \fIafter\fR the closing delimiter of the here document), |
| 965 | which would cause the earlier \*(L" || die;\enexit;\*(R" to be skipped in any |
| 966 | sequence of code fragment extractions. |
| 967 | .PP |
| 968 | To avoid this problem, when it encounters a here document whilst |
| 969 | extracting from a modifiable string, \f(CW\*(C`extract_quotelike\*(C'\fR silently |
| 970 | rearranges the string to an equivalent piece of Perl: |
| 971 | .PP |
| 972 | .Vb 5 |
| 973 | \& <<'EOMSG' |
| 974 | \& This is the message. |
| 975 | \& EOMSG |
| 976 | \& || die; |
| 977 | \& exit; |
| 978 | .Ve |
| 979 | .PP |
| 980 | in which the here document \fIis\fR contiguous. It still leaves the |
| 981 | matching position after the here document, but now the rest of the line |
| 982 | on which the here document starts is not skipped. |
| 983 | .PP |
| 984 | To prevent <extract_quotelike> from mucking about with the input in this way |
| 985 | (this is the only case where a list-context \f(CW\*(C`extract_quotelike\*(C'\fR does so), |
| 986 | you can pass the input variable as an interpolated literal: |
| 987 | .PP |
| 988 | .Vb 1 |
| 989 | \& $quotelike = extract_quotelike("$var"); |
| 990 | .Ve |
| 991 | .ie n .Sh """extract_codeblock""" |
| 992 | .el .Sh "\f(CWextract_codeblock\fP" |
| 993 | .IX Subsection "extract_codeblock" |
| 994 | \&\f(CW\*(C`extract_codeblock\*(C'\fR attempts to recognize and extract a balanced |
| 995 | bracket delimited substring that may contain unbalanced brackets |
| 996 | inside Perl quotes or quotelike operations. That is, \f(CW\*(C`extract_codeblock\*(C'\fR |
| 997 | is like a combination of \f(CW"extract_bracketed"\fR and |
| 998 | \&\f(CW"extract_quotelike"\fR. |
| 999 | .PP |
| 1000 | \&\f(CW\*(C`extract_codeblock\*(C'\fR takes the same initial three parameters as \f(CW\*(C`extract_bracketed\*(C'\fR: |
| 1001 | a text to process, a set of delimiter brackets to look for, and a prefix to |
| 1002 | match first. It also takes an optional fourth parameter, which allows the |
| 1003 | outermost delimiter brackets to be specified separately (see below). |
| 1004 | .PP |
| 1005 | Omitting the first argument (input text) means process \f(CW$_\fR instead. |
| 1006 | Omitting the second argument (delimiter brackets) indicates that only \f(CW'{'\fR is to be used. |
| 1007 | Omitting the third argument (prefix argument) implies optional whitespace at the start. |
| 1008 | Omitting the fourth argument (outermost delimiter brackets) indicates that the |
| 1009 | value of the second argument is to be used for the outermost delimiters. |
| 1010 | .PP |
| 1011 | Once the prefix an dthe outermost opening delimiter bracket have been |
| 1012 | recognized, code blocks are extracted by stepping through the input text and |
| 1013 | trying the following alternatives in sequence: |
| 1014 | .IP "1." 4 |
| 1015 | Try and match a closing delimiter bracket. If the bracket was the same |
| 1016 | species as the last opening bracket, return the substring to that |
| 1017 | point. If the bracket was mismatched, return an error. |
| 1018 | .IP "2." 4 |
| 1019 | Try to match a quote or quotelike operator. If found, call |
| 1020 | \&\f(CW\*(C`extract_quotelike\*(C'\fR to eat it. If \f(CW\*(C`extract_quotelike\*(C'\fR fails, return |
| 1021 | the error it returned. Otherwise go back to step 1. |
| 1022 | .IP "3." 4 |
| 1023 | Try to match an opening delimiter bracket. If found, call |
| 1024 | \&\f(CW\*(C`extract_codeblock\*(C'\fR recursively to eat the embedded block. If the |
| 1025 | recursive call fails, return an error. Otherwise, go back to step 1. |
| 1026 | .IP "4." 4 |
| 1027 | Unconditionally match a bareword or any other single character, and |
| 1028 | then go back to step 1. |
| 1029 | .PP |
| 1030 | Examples: |
| 1031 | .PP |
| 1032 | .Vb 1 |
| 1033 | \& # Find a while loop in the text |
| 1034 | .Ve |
| 1035 | .PP |
| 1036 | .Vb 4 |
| 1037 | \& if ($text =~ s/.*?while\es*\e{/{/) |
| 1038 | \& { |
| 1039 | \& $loop = "while " . extract_codeblock($text); |
| 1040 | \& } |
| 1041 | .Ve |
| 1042 | .PP |
| 1043 | .Vb 2 |
| 1044 | \& # Remove the first round-bracketed list (which may include |
| 1045 | \& # round- or curly-bracketed code blocks or quotelike operators) |
| 1046 | .Ve |
| 1047 | .PP |
| 1048 | .Vb 1 |
| 1049 | \& extract_codeblock $text, "(){}", '[^(]*'; |
| 1050 | .Ve |
| 1051 | .PP |
| 1052 | The ability to specify a different outermost delimiter bracket is useful |
| 1053 | in some circumstances. For example, in the Parse::RecDescent module, |
| 1054 | parser actions which are to be performed only on a successful parse |
| 1055 | are specified using a \f(CW\*(C`<defer:...>\*(C'\fR directive. For example: |
| 1056 | .PP |
| 1057 | .Vb 2 |
| 1058 | \& sentence: subject verb object |
| 1059 | \& <defer: {$::theVerb = $item{verb}} > |
| 1060 | .Ve |
| 1061 | .PP |
| 1062 | Parse::RecDescent uses \f(CW\*(C`extract_codeblock($text, '{}<>')\*(C'\fR to extract the code |
| 1063 | within the \f(CW\*(C`<defer:...>\*(C'\fR directive, but there's a problem. |
| 1064 | .PP |
| 1065 | A deferred action like this: |
| 1066 | .PP |
| 1067 | .Vb 1 |
| 1068 | \& <defer: {if ($count>10) {$count--}} > |
| 1069 | .Ve |
| 1070 | .PP |
| 1071 | will be incorrectly parsed as: |
| 1072 | .PP |
| 1073 | .Vb 1 |
| 1074 | \& <defer: {if ($count> |
| 1075 | .Ve |
| 1076 | .PP |
| 1077 | because the \*(L"less than\*(R" operator is interpreted as a closing delimiter. |
| 1078 | .PP |
| 1079 | But, by extracting the directive using |
| 1080 | \&\f(CW\*(C`extract_codeblock($text,\ '{}',\ undef,\ '<>')\*(C'\fR |
| 1081 | the '>' character is only treated as a delimited at the outermost |
| 1082 | level of the code block, so the directive is parsed correctly. |
| 1083 | .ie n .Sh """extract_multiple""" |
| 1084 | .el .Sh "\f(CWextract_multiple\fP" |
| 1085 | .IX Subsection "extract_multiple" |
| 1086 | The \f(CW\*(C`extract_multiple\*(C'\fR subroutine takes a string to be processed and a |
| 1087 | list of extractors (subroutines or regular expressions) to apply to that string. |
| 1088 | .PP |
| 1089 | In an array context \f(CW\*(C`extract_multiple\*(C'\fR returns an array of substrings |
| 1090 | of the original string, as extracted by the specified extractors. |
| 1091 | In a scalar context, \f(CW\*(C`extract_multiple\*(C'\fR returns the first |
| 1092 | substring successfully extracted from the original string. In both |
| 1093 | scalar and void contexts the original string has the first successfully |
| 1094 | extracted substring removed from it. In all contexts |
| 1095 | \&\f(CW\*(C`extract_multiple\*(C'\fR starts at the current \f(CW\*(C`pos\*(C'\fR of the string, and |
| 1096 | sets that \f(CW\*(C`pos\*(C'\fR appropriately after it matches. |
| 1097 | .PP |
| 1098 | Hence, the aim of of a call to \f(CW\*(C`extract_multiple\*(C'\fR in a list context |
| 1099 | is to split the processed string into as many non-overlapping fields as |
| 1100 | possible, by repeatedly applying each of the specified extractors |
| 1101 | to the remainder of the string. Thus \f(CW\*(C`extract_multiple\*(C'\fR is |
| 1102 | a generalized form of Perl's \f(CW\*(C`split\*(C'\fR subroutine. |
| 1103 | .PP |
| 1104 | The subroutine takes up to four optional arguments: |
| 1105 | .IP "1." 4 |
| 1106 | A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 1107 | .IP "2." 4 |
| 1108 | A reference to a list of subroutine references and/or qr// objects and/or |
| 1109 | literal strings and/or hash references, specifying the extractors |
| 1110 | to be used to split the string. If this argument is omitted (or |
| 1111 | \&\f(CW\*(C`undef\*(C'\fR) the list: |
| 1112 | .Sp |
| 1113 | .Vb 5 |
| 1114 | \& [ |
| 1115 | \& sub { extract_variable($_[0], '') }, |
| 1116 | \& sub { extract_quotelike($_[0],'') }, |
| 1117 | \& sub { extract_codeblock($_[0],'{}','') }, |
| 1118 | \& ] |
| 1119 | .Ve |
| 1120 | .Sp |
| 1121 | is used. |
| 1122 | .IP "3." 4 |
| 1123 | An number specifying the maximum number of fields to return. If this |
| 1124 | argument is omitted (or \f(CW\*(C`undef\*(C'\fR), split continues as long as possible. |
| 1125 | .Sp |
| 1126 | If the third argument is \fIN\fR, then extraction continues until \fIN\fR fields |
| 1127 | have been successfully extracted, or until the string has been completely |
| 1128 | processed. |
| 1129 | .Sp |
| 1130 | Note that in scalar and void contexts the value of this argument is |
| 1131 | automatically reset to 1 (under \f(CW\*(C`\-w\*(C'\fR, a warning is issued if the argument |
| 1132 | has to be reset). |
| 1133 | .IP "4." 4 |
| 1134 | A value indicating whether unmatched substrings (see below) within the |
| 1135 | text should be skipped or returned as fields. If the value is true, |
| 1136 | such substrings are skipped. Otherwise, they are returned. |
| 1137 | .PP |
| 1138 | The extraction process works by applying each extractor in |
| 1139 | sequence to the text string. |
| 1140 | .PP |
| 1141 | If the extractor is a subroutine it is called in a list context and is |
| 1142 | expected to return a list of a single element, namely the extracted |
| 1143 | text. It may optionally also return two further arguments: a string |
| 1144 | representing the text left after extraction (like $' for a pattern |
| 1145 | match), and a string representing any prefix skipped before the |
| 1146 | extraction (like $` in a pattern match). Note that this is designed |
| 1147 | to facilitate the use of other Text::Balanced subroutines with |
| 1148 | \&\f(CW\*(C`extract_multiple\*(C'\fR. Note too that the value returned by an extractor |
| 1149 | subroutine need not bear any relationship to the corresponding substring |
| 1150 | of the original text (see examples below). |
| 1151 | .PP |
| 1152 | If the extractor is a precompiled regular expression or a string, |
| 1153 | it is matched against the text in a scalar context with a leading |
| 1154 | \&'\eG' and the gc modifiers enabled. The extracted value is either |
| 1155 | \&\f(CW$1\fR if that variable is defined after the match, or else the |
| 1156 | complete match (i.e. $&). |
| 1157 | .PP |
| 1158 | If the extractor is a hash reference, it must contain exactly one element. |
| 1159 | The value of that element is one of the |
| 1160 | above extractor types (subroutine reference, regular expression, or string). |
| 1161 | The key of that element is the name of a class into which the successful |
| 1162 | return value of the extractor will be blessed. |
| 1163 | .PP |
| 1164 | If an extractor returns a defined value, that value is immediately |
| 1165 | treated as the next extracted field and pushed onto the list of fields. |
| 1166 | If the extractor was specified in a hash reference, the field is also |
| 1167 | blessed into the appropriate class, |
| 1168 | .PP |
| 1169 | If the extractor fails to match (in the case of a regex extractor), or returns an empty list or an undefined value (in the case of a subroutine extractor), it is |
| 1170 | assumed to have failed to extract. |
| 1171 | If none of the extractor subroutines succeeds, then one |
| 1172 | character is extracted from the start of the text and the extraction |
| 1173 | subroutines reapplied. Characters which are thus removed are accumulated and |
| 1174 | eventually become the next field (unless the fourth argument is true, in which |
| 1175 | case they are disgarded). |
| 1176 | .PP |
| 1177 | For example, the following extracts substrings that are valid Perl variables: |
| 1178 | .PP |
| 1179 | .Vb 3 |
| 1180 | \& @fields = extract_multiple($text, |
| 1181 | \& [ sub { extract_variable($_[0]) } ], |
| 1182 | \& undef, 1); |
| 1183 | .Ve |
| 1184 | .PP |
| 1185 | This example separates a text into fields which are quote delimited, |
| 1186 | curly bracketed, and anything else. The delimited and bracketed |
| 1187 | parts are also blessed to identify them (the \*(L"anything else\*(R" is unblessed): |
| 1188 | .PP |
| 1189 | .Vb 5 |
| 1190 | \& @fields = extract_multiple($text, |
| 1191 | \& [ |
| 1192 | \& { Delim => sub { extract_delimited($_[0],q{'"}) } }, |
| 1193 | \& { Brack => sub { extract_bracketed($_[0],'{}') } }, |
| 1194 | \& ]); |
| 1195 | .Ve |
| 1196 | .PP |
| 1197 | This call extracts the next single substring that is a valid Perl quotelike |
| 1198 | operator (and removes it from \f(CW$text\fR): |
| 1199 | .PP |
| 1200 | .Vb 4 |
| 1201 | \& $quotelike = extract_multiple($text, |
| 1202 | \& [ |
| 1203 | \& sub { extract_quotelike($_[0]) }, |
| 1204 | \& ], undef, 1); |
| 1205 | .Ve |
| 1206 | .PP |
| 1207 | Finally, here is yet another way to do comma-separated value parsing: |
| 1208 | .PP |
| 1209 | .Vb 6 |
| 1210 | \& @fields = extract_multiple($csv_text, |
| 1211 | \& [ |
| 1212 | \& sub { extract_delimited($_[0],q{'"}) }, |
| 1213 | \& qr/([^,]+)(.*)/, |
| 1214 | \& ], |
| 1215 | \& undef,1); |
| 1216 | .Ve |
| 1217 | .PP |
| 1218 | The list in the second argument means: |
| 1219 | \&\fI\*(L"Try and extract a ' or \*(R" delimited string, otherwise extract anything up to a comma..."\fR. |
| 1220 | The undef third argument means: |
| 1221 | \&\fI\*(L"...as many times as possible...\*(R"\fR, |
| 1222 | and the true value in the fourth argument means |
| 1223 | \&\fI\*(L"...discarding anything else that appears (i.e. the commas)\*(R"\fR. |
| 1224 | .PP |
| 1225 | If you wanted the commas preserved as separate fields (i.e. like split |
| 1226 | does if your split pattern has capturing parentheses), you would |
| 1227 | just make the last parameter undefined (or remove it). |
| 1228 | .ie n .Sh """gen_delimited_pat""" |
| 1229 | .el .Sh "\f(CWgen_delimited_pat\fP" |
| 1230 | .IX Subsection "gen_delimited_pat" |
| 1231 | The \f(CW\*(C`gen_delimited_pat\*(C'\fR subroutine takes a single (string) argument and |
| 1232 | > builds a Friedl-style optimized regex that matches a string delimited |
| 1233 | by any one of the characters in the single argument. For example: |
| 1234 | .PP |
| 1235 | .Vb 1 |
| 1236 | \& gen_delimited_pat(q{'"}) |
| 1237 | .Ve |
| 1238 | .PP |
| 1239 | returns the regex: |
| 1240 | .PP |
| 1241 | .Vb 1 |
| 1242 | \& (?:\e"(?:\e\e\e"|(?!\e").)*\e"|\e'(?:\e\e\e'|(?!\e').)*\e') |
| 1243 | .Ve |
| 1244 | .PP |
| 1245 | Note that the specified delimiters are automatically quotemeta'd. |
| 1246 | .PP |
| 1247 | A typical use of \f(CW\*(C`gen_delimited_pat\*(C'\fR would be to build special purpose tags |
| 1248 | for \f(CW\*(C`extract_tagged\*(C'\fR. For example, to properly ignore \*(L"empty\*(R" \s-1XML\s0 elements |
| 1249 | (which might contain quoted strings): |
| 1250 | .PP |
| 1251 | .Vb 1 |
| 1252 | \& my $empty_tag = '<(' . gen_delimited_pat(q{'"}) . '|.)+/>'; |
| 1253 | .Ve |
| 1254 | .PP |
| 1255 | .Vb 1 |
| 1256 | \& extract_tagged($text, undef, undef, undef, {ignore => [$empty_tag]} ); |
| 1257 | .Ve |
| 1258 | .PP |
| 1259 | \&\f(CW\*(C`gen_delimited_pat\*(C'\fR may also be called with an optional second argument, |
| 1260 | which specifies the \*(L"escape\*(R" character(s) to be used for each delimiter. |
| 1261 | For example to match a Pascal-style string (where ' is the delimiter |
| 1262 | and '' is a literal ' within the string): |
| 1263 | .PP |
| 1264 | .Vb 1 |
| 1265 | \& gen_delimited_pat(q{'},q{'}); |
| 1266 | .Ve |
| 1267 | .PP |
| 1268 | Different escape characters can be specified for different delimiters. |
| 1269 | For example, to specify that '/' is the escape for single quotes |
| 1270 | and '%' is the escape for double quotes: |
| 1271 | .PP |
| 1272 | .Vb 1 |
| 1273 | \& gen_delimited_pat(q{'"},q{/%}); |
| 1274 | .Ve |
| 1275 | .PP |
| 1276 | If more delimiters than escape chars are specified, the last escape char |
| 1277 | is used for the remaining delimiters. |
| 1278 | If no escape char is specified for a given specified delimiter, '\e' is used. |
| 1279 | .PP |
| 1280 | Note that |
| 1281 | \&\f(CW\*(C`gen_delimited_pat\*(C'\fR was previously called |
| 1282 | \&\f(CW\*(C`delimited_pat\*(C'\fR. That name may still be used, but is now deprecated. |
| 1283 | .SH "DIAGNOSTICS" |
| 1284 | .IX Header "DIAGNOSTICS" |
| 1285 | In a list context, all the functions return \f(CW\*(C`(undef,$original_text)\*(C'\fR |
| 1286 | on failure. In a scalar context, failure is indicated by returning \f(CW\*(C`undef\*(C'\fR |
| 1287 | (in this case the input text is not modified in any way). |
| 1288 | .PP |
| 1289 | In addition, on failure in \fIany\fR context, the \f(CW$@\fR variable is set. |
| 1290 | Accessing \f(CW\*(C`$@\->{error}\*(C'\fR returns one of the error diagnostics listed |
| 1291 | below. |
| 1292 | Accessing \f(CW\*(C`$@\->{pos}\*(C'\fR returns the offset into the original string at |
| 1293 | which the error was detected (although not necessarily where it occurred!) |
| 1294 | Printing \f(CW$@\fR directly produces the error message, with the offset appended. |
| 1295 | On success, the \f(CW$@\fR variable is guaranteed to be \f(CW\*(C`undef\*(C'\fR. |
| 1296 | .PP |
| 1297 | The available diagnostics are: |
| 1298 | .ie n .IP """Did not find a suitable bracket: ""%s""""" 4 |
| 1299 | .el .IP "\f(CWDid not find a suitable bracket: ``%s''\fR" 4 |
| 1300 | .IX Item "Did not find a suitable bracket: ""%s""" |
| 1301 | The delimiter provided to \f(CW\*(C`extract_bracketed\*(C'\fR was not one of |
| 1302 | \&\f(CW'()[]<>{}'\fR. |
| 1303 | .ie n .IP """Did not find prefix: /%s/""" 4 |
| 1304 | .el .IP "\f(CWDid not find prefix: /%s/\fR" 4 |
| 1305 | .IX Item "Did not find prefix: /%s/" |
| 1306 | A non-optional prefix was specified but wasn't found at the start of the text. |
| 1307 | .ie n .IP """Did not find opening bracket after prefix: ""%s""""" 4 |
| 1308 | .el .IP "\f(CWDid not find opening bracket after prefix: ``%s''\fR" 4 |
| 1309 | .IX Item "Did not find opening bracket after prefix: ""%s""" |
| 1310 | \&\f(CW\*(C`extract_bracketed\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR was expecting a |
| 1311 | particular kind of bracket at the start of the text, and didn't find it. |
| 1312 | .ie n .IP """No quotelike operator found after prefix: ""%s""""" 4 |
| 1313 | .el .IP "\f(CWNo quotelike operator found after prefix: ``%s''\fR" 4 |
| 1314 | .IX Item "No quotelike operator found after prefix: ""%s""" |
| 1315 | \&\f(CW\*(C`extract_quotelike\*(C'\fR didn't find one of the quotelike operators \f(CW\*(C`q\*(C'\fR, |
| 1316 | \&\f(CW\*(C`qq\*(C'\fR, \f(CW\*(C`qw\*(C'\fR, \f(CW\*(C`qx\*(C'\fR, \f(CW\*(C`s\*(C'\fR, \f(CW\*(C`tr\*(C'\fR or \f(CW\*(C`y\*(C'\fR at the start of the substring |
| 1317 | it was extracting. |
| 1318 | .ie n .IP """Unmatched closing bracket: ""%c""""" 4 |
| 1319 | .el .IP "\f(CWUnmatched closing bracket: ``%c''\fR" 4 |
| 1320 | .IX Item "Unmatched closing bracket: ""%c""" |
| 1321 | \&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR encountered |
| 1322 | a closing bracket where none was expected. |
| 1323 | .ie n .IP """Unmatched opening bracket(s): ""%s""""" 4 |
| 1324 | .el .IP "\f(CWUnmatched opening bracket(s): ``%s''\fR" 4 |
| 1325 | .IX Item "Unmatched opening bracket(s): ""%s""" |
| 1326 | \&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR ran |
| 1327 | out of characters in the text before closing one or more levels of nested |
| 1328 | brackets. |
| 1329 | .ie n .IP """Unmatched embedded quote (%s)""" 4 |
| 1330 | .el .IP "\f(CWUnmatched embedded quote (%s)\fR" 4 |
| 1331 | .IX Item "Unmatched embedded quote (%s)" |
| 1332 | \&\f(CW\*(C`extract_bracketed\*(C'\fR attempted to match an embedded quoted substring, but |
| 1333 | failed to find a closing quote to match it. |
| 1334 | .ie n .IP """Did not find closing delimiter to match '%s'""" 4 |
| 1335 | .el .IP "\f(CWDid not find closing delimiter to match '%s'\fR" 4 |
| 1336 | .IX Item "Did not find closing delimiter to match '%s'" |
| 1337 | \&\f(CW\*(C`extract_quotelike\*(C'\fR was unable to find a closing delimiter to match the |
| 1338 | one that opened the quote-like operation. |
| 1339 | .ie n .IP """Mismatched closing bracket: expected ""%c"" but found ""%s""""" 4 |
| 1340 | .el .IP "\f(CWMismatched closing bracket: expected ``%c'' but found ``%s''\fR" 4 |
| 1341 | .IX Item "Mismatched closing bracket: expected ""%c"" but found ""%s""" |
| 1342 | \&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR found |
| 1343 | a valid bracket delimiter, but it was the wrong species. This usually |
| 1344 | indicates a nesting error, but may indicate incorrect quoting or escaping. |
| 1345 | .ie n .IP """No block delimiter found after quotelike ""%s""""" 4 |
| 1346 | .el .IP "\f(CWNo block delimiter found after quotelike ``%s''\fR" 4 |
| 1347 | .IX Item "No block delimiter found after quotelike ""%s""" |
| 1348 | \&\f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR found one of the |
| 1349 | quotelike operators \f(CW\*(C`q\*(C'\fR, \f(CW\*(C`qq\*(C'\fR, \f(CW\*(C`qw\*(C'\fR, \f(CW\*(C`qx\*(C'\fR, \f(CW\*(C`s\*(C'\fR, \f(CW\*(C`tr\*(C'\fR or \f(CW\*(C`y\*(C'\fR |
| 1350 | without a suitable block after it. |
| 1351 | .ie n .IP """Did not find leading dereferencer""" 4 |
| 1352 | .el .IP "\f(CWDid not find leading dereferencer\fR" 4 |
| 1353 | .IX Item "Did not find leading dereferencer" |
| 1354 | \&\f(CW\*(C`extract_variable\*(C'\fR was expecting one of '$', '@', or '%' at the start of |
| 1355 | a variable, but didn't find any of them. |
| 1356 | .ie n .IP """Bad identifier after dereferencer""" 4 |
| 1357 | .el .IP "\f(CWBad identifier after dereferencer\fR" 4 |
| 1358 | .IX Item "Bad identifier after dereferencer" |
| 1359 | \&\f(CW\*(C`extract_variable\*(C'\fR found a '$', '@', or '%' indicating a variable, but that |
| 1360 | character was not followed by a legal Perl identifier. |
| 1361 | .ie n .IP """Did not find expected opening bracket at %s""" 4 |
| 1362 | .el .IP "\f(CWDid not find expected opening bracket at %s\fR" 4 |
| 1363 | .IX Item "Did not find expected opening bracket at %s" |
| 1364 | \&\f(CW\*(C`extract_codeblock\*(C'\fR failed to find any of the outermost opening brackets |
| 1365 | that were specified. |
| 1366 | .ie n .IP """Improperly nested codeblock at %s""" 4 |
| 1367 | .el .IP "\f(CWImproperly nested codeblock at %s\fR" 4 |
| 1368 | .IX Item "Improperly nested codeblock at %s" |
| 1369 | A nested code block was found that started with a delimiter that was specified |
| 1370 | as being only to be used as an outermost bracket. |
| 1371 | .ie n .IP """Missing second block for quotelike ""%s""""" 4 |
| 1372 | .el .IP "\f(CWMissing second block for quotelike ``%s''\fR" 4 |
| 1373 | .IX Item "Missing second block for quotelike ""%s""" |
| 1374 | \&\f(CW\*(C`extract_codeblock\*(C'\fR or \f(CW\*(C`extract_quotelike\*(C'\fR found one of the |
| 1375 | quotelike operators \f(CW\*(C`s\*(C'\fR, \f(CW\*(C`tr\*(C'\fR or \f(CW\*(C`y\*(C'\fR followed by only one block. |
| 1376 | .ie n .IP """No match found for opening bracket""" 4 |
| 1377 | .el .IP "\f(CWNo match found for opening bracket\fR" 4 |
| 1378 | .IX Item "No match found for opening bracket" |
| 1379 | \&\f(CW\*(C`extract_codeblock\*(C'\fR failed to find a closing bracket to match the outermost |
| 1380 | opening bracket. |
| 1381 | .ie n .IP """Did not find opening tag: /%s/""" 4 |
| 1382 | .el .IP "\f(CWDid not find opening tag: /%s/\fR" 4 |
| 1383 | .IX Item "Did not find opening tag: /%s/" |
| 1384 | \&\f(CW\*(C`extract_tagged\*(C'\fR did not find a suitable opening tag (after any specified |
| 1385 | prefix was removed). |
| 1386 | .ie n .IP """Unable to construct closing tag to match: /%s/""" 4 |
| 1387 | .el .IP "\f(CWUnable to construct closing tag to match: /%s/\fR" 4 |
| 1388 | .IX Item "Unable to construct closing tag to match: /%s/" |
| 1389 | \&\f(CW\*(C`extract_tagged\*(C'\fR matched the specified opening tag and tried to |
| 1390 | modify the matched text to produce a matching closing tag (because |
| 1391 | none was specified). It failed to generate the closing tag, almost |
| 1392 | certainly because the opening tag did not start with a |
| 1393 | bracket of some kind. |
| 1394 | .ie n .IP """Found invalid nested tag: %s""" 4 |
| 1395 | .el .IP "\f(CWFound invalid nested tag: %s\fR" 4 |
| 1396 | .IX Item "Found invalid nested tag: %s" |
| 1397 | \&\f(CW\*(C`extract_tagged\*(C'\fR found a nested tag that appeared in the \*(L"reject\*(R" list |
| 1398 | (and the failure mode was not \*(L"\s-1MAX\s0\*(R" or \*(L"\s-1PARA\s0\*(R"). |
| 1399 | .ie n .IP """Found unbalanced nested tag: %s""" 4 |
| 1400 | .el .IP "\f(CWFound unbalanced nested tag: %s\fR" 4 |
| 1401 | .IX Item "Found unbalanced nested tag: %s" |
| 1402 | \&\f(CW\*(C`extract_tagged\*(C'\fR found a nested opening tag that was not matched by a |
| 1403 | corresponding nested closing tag (and the failure mode was not \*(L"\s-1MAX\s0\*(R" or \*(L"\s-1PARA\s0\*(R"). |
| 1404 | .ie n .IP """Did not find closing tag""" 4 |
| 1405 | .el .IP "\f(CWDid not find closing tag\fR" 4 |
| 1406 | .IX Item "Did not find closing tag" |
| 1407 | \&\f(CW\*(C`extract_tagged\*(C'\fR reached the end of the text without finding a closing tag |
| 1408 | to match the original opening tag (and the failure mode was not |
| 1409 | \&\*(L"\s-1MAX\s0\*(R" or \*(L"\s-1PARA\s0\*(R"). |
| 1410 | .SH "AUTHOR" |
| 1411 | .IX Header "AUTHOR" |
| 1412 | Damian Conway (damian@conway.org) |
| 1413 | .SH "BUGS AND IRRITATIONS" |
| 1414 | .IX Header "BUGS AND IRRITATIONS" |
| 1415 | There are undoubtedly serious bugs lurking somewhere in this code, if |
| 1416 | only because parts of it give the impression of understanding a great deal |
| 1417 | more about Perl than they really do. |
| 1418 | .PP |
| 1419 | Bug reports and other feedback are most welcome. |
| 1420 | .SH "COPYRIGHT" |
| 1421 | .IX Header "COPYRIGHT" |
| 1422 | .Vb 3 |
| 1423 | \& Copyright (c) 1997-2001, Damian Conway. All Rights Reserved. |
| 1424 | \& This module is free software. It may be used, redistributed |
| 1425 | \& and/or modified under the same terms as Perl itself. |
| 1426 | .Ve |