| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "Text::Balanced 3perl" |
| 58 |
.TH Text::Balanced 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
Text::Balanced \- Extract delimited text sequences from strings. |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 11 |
| 68 |
\& use Text::Balanced qw ( |
| 69 |
\& extract_delimited |
| 70 |
\& extract_bracketed |
| 71 |
\& extract_quotelike |
| 72 |
\& extract_codeblock |
| 73 |
\& extract_variable |
| 74 |
\& extract_tagged |
| 75 |
\& extract_multiple |
| 76 |
\& gen_delimited_pat |
| 77 |
\& gen_extract_tagged |
| 78 |
\& ); |
| 79 |
\& |
| 80 |
\& # Extract the initial substring of $text that is delimited by |
| 81 |
\& # two (unescaped) instances of the first character in $delim. |
| 82 |
\& |
| 83 |
\& ($extracted, $remainder) = extract_delimited($text,$delim); |
| 84 |
\& |
| 85 |
\& # Extract the initial substring of $text that is bracketed |
| 86 |
\& # with a delimiter(s) specified by $delim (where the string |
| 87 |
\& # in $delim contains one or more of \*(Aq(){}[]<>\*(Aq). |
| 88 |
\& |
| 89 |
\& ($extracted, $remainder) = extract_bracketed($text,$delim); |
| 90 |
\& |
| 91 |
\& # Extract the initial substring of $text that is bounded by |
| 92 |
\& # an XML tag. |
| 93 |
\& |
| 94 |
\& ($extracted, $remainder) = extract_tagged($text); |
| 95 |
\& |
| 96 |
\& # Extract the initial substring of $text that is bounded by |
| 97 |
\& # a C<BEGIN>...C<END> pair. Don\*(Aqt allow nested C<BEGIN> tags |
| 98 |
\& |
| 99 |
\& ($extracted, $remainder) = |
| 100 |
\& extract_tagged($text,"BEGIN","END",undef,{bad=>["BEGIN"]}); |
| 101 |
\& |
| 102 |
\& # Extract the initial substring of $text that represents a |
| 103 |
\& # Perl "quote or quote\-like operation" |
| 104 |
\& |
| 105 |
\& ($extracted, $remainder) = extract_quotelike($text); |
| 106 |
\& |
| 107 |
\& # Extract the initial substring of $text that represents a block |
| 108 |
\& # of Perl code, bracketed by any of character(s) specified by $delim |
| 109 |
\& # (where the string $delim contains one or more of \*(Aq(){}[]<>\*(Aq). |
| 110 |
\& |
| 111 |
\& ($extracted, $remainder) = extract_codeblock($text,$delim); |
| 112 |
\& |
| 113 |
\& # Extract the initial substrings of $text that would be extracted by |
| 114 |
\& # one or more sequential applications of the specified functions |
| 115 |
\& # or regular expressions |
| 116 |
\& |
| 117 |
\& @extracted = extract_multiple($text, |
| 118 |
\& [ \e&extract_bracketed, |
| 119 |
\& \e&extract_quotelike, |
| 120 |
\& \e&some_other_extractor_sub, |
| 121 |
\& qr/[xyz]*/, |
| 122 |
\& \*(Aqliteral\*(Aq, |
| 123 |
\& ]); |
| 124 |
\& |
| 125 |
\& # Create a string representing an optimized pattern (a la Friedl) |
| 126 |
\& # that matches a substring delimited by any of the specified characters |
| 127 |
\& # (in this case: any type of quote or a slash) |
| 128 |
\& |
| 129 |
\& $patstring = gen_delimited_pat(q{\*(Aq"\`/}); |
| 130 |
\& |
| 131 |
\& # Generate a reference to an anonymous sub that is just like extract_tagged |
| 132 |
\& # but pre\-compiled and optimized for a specific pair of tags, and |
| 133 |
\& # consequently much faster (i.e. 3 times faster). It uses qr// for better |
| 134 |
\& # performance on repeated calls. |
| 135 |
\& |
| 136 |
\& $extract_head = gen_extract_tagged(\*(Aq<HEAD>\*(Aq,\*(Aq</HEAD>\*(Aq); |
| 137 |
\& ($extracted, $remainder) = $extract_head\->($text); |
| 138 |
.Ve |
| 139 |
.SH DESCRIPTION |
| 140 |
.IX Header "DESCRIPTION" |
| 141 |
The various \f(CW\*(C`extract_...\*(C'\fR subroutines may be used to |
| 142 |
extract a delimited substring, possibly after skipping a |
| 143 |
specified prefix string. By default, that prefix is |
| 144 |
optional whitespace (\f(CW\*(C`/\es*/\*(C'\fR), but you can change it to whatever |
| 145 |
you wish (see below). |
| 146 |
.PP |
| 147 |
The substring to be extracted must appear at the |
| 148 |
current \f(CW\*(C`pos\*(C'\fR location of the string's variable |
| 149 |
(or at index zero, if no \f(CW\*(C`pos\*(C'\fR position is defined). |
| 150 |
In other words, the \f(CW\*(C`extract_...\*(C'\fR subroutines \fIdon't\fR |
| 151 |
extract the first occurrence of a substring anywhere |
| 152 |
in a string (like an unanchored regex would). Rather, |
| 153 |
they extract an occurrence of the substring appearing |
| 154 |
immediately at the current matching position in the |
| 155 |
string (like a \f(CW\*(C`\eG\*(C'\fR\-anchored regex would). |
| 156 |
.SS "General Behaviour in List Contexts" |
| 157 |
.IX Subsection "General Behaviour in List Contexts" |
| 158 |
In a list context, all the subroutines return a list, the first three |
| 159 |
elements of which are always: |
| 160 |
.IP [0] 4 |
| 161 |
.IX Item "[0]" |
| 162 |
The extracted string, including the specified delimiters. |
| 163 |
If the extraction fails \f(CW\*(C`undef\*(C'\fR is returned. |
| 164 |
.IP [1] 4 |
| 165 |
.IX Item "[1]" |
| 166 |
The remainder of the input string (i.e. the characters after the |
| 167 |
extracted string). On failure, the entire string is returned. |
| 168 |
.IP [2] 4 |
| 169 |
.IX Item "[2]" |
| 170 |
The skipped prefix (i.e. the characters before the extracted string). |
| 171 |
On failure, \f(CW\*(C`undef\*(C'\fR is returned. |
| 172 |
.PP |
| 173 |
Note that in a list context, the contents of the original input text (the first |
| 174 |
argument) are not modified in any way. |
| 175 |
.PP |
| 176 |
However, if the input text was passed in a variable, that variable's |
| 177 |
\&\f(CW\*(C`pos\*(C'\fR value is updated to point at the first character after the |
| 178 |
extracted text. That means that in a list context the various |
| 179 |
subroutines can be used much like regular expressions. For example: |
| 180 |
.PP |
| 181 |
.Vb 4 |
| 182 |
\& while ( $next = (extract_quotelike($text))[0] ) |
| 183 |
\& { |
| 184 |
\& # process next quote\-like (in $next) |
| 185 |
\& } |
| 186 |
.Ve |
| 187 |
.SS "General Behaviour in Scalar and Void Contexts" |
| 188 |
.IX Subsection "General Behaviour in Scalar and Void Contexts" |
| 189 |
In a scalar context, the extracted string is returned, having first been |
| 190 |
removed from the input text. Thus, the following code also processes |
| 191 |
each quote-like operation, but actually removes them from \f(CW$text:\fR |
| 192 |
.PP |
| 193 |
.Vb 4 |
| 194 |
\& while ( $next = extract_quotelike($text) ) |
| 195 |
\& { |
| 196 |
\& # process next quote\-like (in $next) |
| 197 |
\& } |
| 198 |
.Ve |
| 199 |
.PP |
| 200 |
Note that if the input text is a read-only string (i.e. a literal), |
| 201 |
no attempt is made to remove the extracted text. |
| 202 |
.PP |
| 203 |
In a void context the behaviour of the extraction subroutines is |
| 204 |
exactly the same as in a scalar context, except (of course) that the |
| 205 |
extracted substring is not returned. |
| 206 |
.SS "A Note About Prefixes" |
| 207 |
.IX Subsection "A Note About Prefixes" |
| 208 |
Prefix patterns are matched without any trailing modifiers (\f(CW\*(C`/gimsox\*(C'\fR etc.) |
| 209 |
This can bite you if you're expecting a prefix specification like |
| 210 |
\&'.*?(?=<H1>)' to skip everything up to the first <H1> tag. Such a prefix |
| 211 |
pattern will only succeed if the <H1> tag is on the current line, since |
| 212 |
\&. normally doesn't match newlines. |
| 213 |
.PP |
| 214 |
To overcome this limitation, you need to turn on /s matching within |
| 215 |
the prefix pattern, using the \f(CW\*(C`(?s)\*(C'\fR directive: '(?s).*?(?=<H1>)' |
| 216 |
.SS Functions |
| 217 |
.IX Subsection "Functions" |
| 218 |
.ie n .IP """extract_delimited""" 4 |
| 219 |
.el .IP \f(CWextract_delimited\fR 4 |
| 220 |
.IX Item "extract_delimited" |
| 221 |
The \f(CW\*(C`extract_delimited\*(C'\fR function formalizes the common idiom |
| 222 |
of extracting a single-character-delimited substring from the start of |
| 223 |
a string. For example, to extract a single-quote delimited string, the |
| 224 |
following code is typically used: |
| 225 |
.Sp |
| 226 |
.Vb 2 |
| 227 |
\& ($remainder = $text) =~ s/\eA(\*(Aq(\e\e.|[^\*(Aq])*\*(Aq)//s; |
| 228 |
\& $extracted = $1; |
| 229 |
.Ve |
| 230 |
.Sp |
| 231 |
but with \f(CW\*(C`extract_delimited\*(C'\fR it can be simplified to: |
| 232 |
.Sp |
| 233 |
.Vb 1 |
| 234 |
\& ($extracted,$remainder) = extract_delimited($text, "\*(Aq"); |
| 235 |
.Ve |
| 236 |
.Sp |
| 237 |
\&\f(CW\*(C`extract_delimited\*(C'\fR takes up to four scalars (the input text, the |
| 238 |
delimiters, a prefix pattern to be skipped, and any escape characters) |
| 239 |
and extracts the initial substring of the text that |
| 240 |
is appropriately delimited. If the delimiter string has multiple |
| 241 |
characters, the first one encountered in the text is taken to delimit |
| 242 |
the substring. |
| 243 |
The third argument specifies a prefix pattern that is to be skipped |
| 244 |
(but must be present!) before the substring is extracted. |
| 245 |
The final argument specifies the escape character to be used for each |
| 246 |
delimiter. |
| 247 |
.Sp |
| 248 |
All arguments are optional. If the escape characters are not specified, |
| 249 |
every delimiter is escaped with a backslash (\f(CW\*(C`\e\*(C'\fR). |
| 250 |
If the prefix is not specified, the |
| 251 |
pattern \f(CW\*(Aq\es*\*(Aq\fR \- optional whitespace \- is used. If the delimiter set |
| 252 |
is also not specified, the set \f(CW\*(C`/["\*(Aq\`]/\*(C'\fR is used. If the text to be processed |
| 253 |
is not specified either, \f(CW$_\fR is used. |
| 254 |
.Sp |
| 255 |
In list context, \f(CW\*(C`extract_delimited\*(C'\fR returns a array of three |
| 256 |
elements, the extracted substring (\fIincluding the surrounding |
| 257 |
delimiters\fR), the remainder of the text, and the skipped prefix (if |
| 258 |
any). If a suitable delimited substring is not found, the first |
| 259 |
element of the array is the empty string, the second is the complete |
| 260 |
original text, and the prefix returned in the third element is an |
| 261 |
empty string. |
| 262 |
.Sp |
| 263 |
In a scalar context, just the extracted substring is returned. In |
| 264 |
a void context, the extracted substring (and any prefix) are simply |
| 265 |
removed from the beginning of the first argument. |
| 266 |
.Sp |
| 267 |
Examples: |
| 268 |
.Sp |
| 269 |
.Vb 1 |
| 270 |
\& # Remove a single\-quoted substring from the very beginning of $text: |
| 271 |
\& |
| 272 |
\& $substring = extract_delimited($text, "\*(Aq", \*(Aq\*(Aq); |
| 273 |
\& |
| 274 |
\& # Remove a single\-quoted Pascalish substring (i.e. one in which |
| 275 |
\& # doubling the quote character escapes it) from the very |
| 276 |
\& # beginning of $text: |
| 277 |
\& |
| 278 |
\& $substring = extract_delimited($text, "\*(Aq", \*(Aq\*(Aq, "\*(Aq"); |
| 279 |
\& |
| 280 |
\& # Extract a single\- or double\- quoted substring from the |
| 281 |
\& # beginning of $text, optionally after some whitespace |
| 282 |
\& # (note the list context to protect $text from modification): |
| 283 |
\& |
| 284 |
\& ($substring) = extract_delimited $text, q{"\*(Aq}; |
| 285 |
\& |
| 286 |
\& # Delete the substring delimited by the first \*(Aq/\*(Aq in $text: |
| 287 |
\& |
| 288 |
\& $text = join \*(Aq\*(Aq, (extract_delimited($text,\*(Aq/\*(Aq,\*(Aq[^/]*\*(Aq)[2,1]; |
| 289 |
.Ve |
| 290 |
.Sp |
| 291 |
Note that this last example is \fInot\fR the same as deleting the first |
| 292 |
quote-like pattern. For instance, if \f(CW$text\fR contained the string: |
| 293 |
.Sp |
| 294 |
.Vb 1 |
| 295 |
\& "if (\*(Aq./cmd\*(Aq =~ m/$UNIXCMD/s) { $cmd = $1; }" |
| 296 |
.Ve |
| 297 |
.Sp |
| 298 |
then after the deletion it would contain: |
| 299 |
.Sp |
| 300 |
.Vb 1 |
| 301 |
\& "if (\*(Aq.$UNIXCMD/s) { $cmd = $1; }" |
| 302 |
.Ve |
| 303 |
.Sp |
| 304 |
not: |
| 305 |
.Sp |
| 306 |
.Vb 1 |
| 307 |
\& "if (\*(Aq./cmd\*(Aq =~ ms) { $cmd = $1; }" |
| 308 |
.Ve |
| 309 |
.Sp |
| 310 |
See "extract_quotelike" for a (partial) solution to this problem. |
| 311 |
.ie n .IP """extract_bracketed""" 4 |
| 312 |
.el .IP \f(CWextract_bracketed\fR 4 |
| 313 |
.IX Item "extract_bracketed" |
| 314 |
Like \f(CW"extract_delimited"\fR, the \f(CW\*(C`extract_bracketed\*(C'\fR function takes |
| 315 |
up to three optional scalar arguments: a string to extract from, a delimiter |
| 316 |
specifier, and a prefix pattern. As before, a missing prefix defaults to |
| 317 |
optional whitespace and a missing text defaults to \f(CW$_\fR. However, a missing |
| 318 |
delimiter specifier defaults to \f(CW\*(Aq{}()[]<>\*(Aq\fR (see below). |
| 319 |
.Sp |
| 320 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR extracts a balanced-bracket-delimited |
| 321 |
substring (using any one (or more) of the user-specified delimiter |
| 322 |
brackets: '(..)', '{..}', '[..]', or '<..>'). Optionally it will also |
| 323 |
respect quoted unbalanced brackets (see below). |
| 324 |
.Sp |
| 325 |
A "delimiter bracket" is a bracket in list of delimiters passed as |
| 326 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR's second argument. Delimiter brackets are |
| 327 |
specified by giving either the left or right (or both!) versions |
| 328 |
of the required bracket(s). Note that the order in which |
| 329 |
two or more delimiter brackets are specified is not significant. |
| 330 |
.Sp |
| 331 |
A "balanced-bracket-delimited substring" is a substring bounded by |
| 332 |
matched brackets, such that any other (left or right) delimiter |
| 333 |
bracket \fIwithin\fR the substring is also matched by an opposite |
| 334 |
(right or left) delimiter bracket \fIat the same level of nesting\fR. Any |
| 335 |
type of bracket not in the delimiter list is treated as an ordinary |
| 336 |
character. |
| 337 |
.Sp |
| 338 |
In other words, each type of bracket specified as a delimiter must be |
| 339 |
balanced and correctly nested within the substring, and any other kind of |
| 340 |
("non-delimiter") bracket in the substring is ignored. |
| 341 |
.Sp |
| 342 |
For example, given the string: |
| 343 |
.Sp |
| 344 |
.Vb 1 |
| 345 |
\& $text = "{ an \*(Aq[irregularly :\-(] {} parenthesized >:\-)\*(Aq string }"; |
| 346 |
.Ve |
| 347 |
.Sp |
| 348 |
then a call to \f(CW\*(C`extract_bracketed\*(C'\fR in a list context: |
| 349 |
.Sp |
| 350 |
.Vb 1 |
| 351 |
\& @result = extract_bracketed( $text, \*(Aq{}\*(Aq ); |
| 352 |
.Ve |
| 353 |
.Sp |
| 354 |
would return: |
| 355 |
.Sp |
| 356 |
.Vb 1 |
| 357 |
\& ( "{ an \*(Aq[irregularly :\-(] {} parenthesized >:\-)\*(Aq string }" , "" , "" ) |
| 358 |
.Ve |
| 359 |
.Sp |
| 360 |
since both sets of \f(CW\*(Aq{..}\*(Aq\fR brackets are properly nested and evenly balanced. |
| 361 |
(In a scalar context just the first element of the array would be returned. In |
| 362 |
a void context, \f(CW$text\fR would be replaced by an empty string.) |
| 363 |
.Sp |
| 364 |
Likewise the call in: |
| 365 |
.Sp |
| 366 |
.Vb 1 |
| 367 |
\& @result = extract_bracketed( $text, \*(Aq{[\*(Aq ); |
| 368 |
.Ve |
| 369 |
.Sp |
| 370 |
would return the same result, since all sets of both types of specified |
| 371 |
delimiter brackets are correctly nested and balanced. |
| 372 |
.Sp |
| 373 |
However, the call in: |
| 374 |
.Sp |
| 375 |
.Vb 1 |
| 376 |
\& @result = extract_bracketed( $text, \*(Aq{([<\*(Aq ); |
| 377 |
.Ve |
| 378 |
.Sp |
| 379 |
would fail, returning: |
| 380 |
.Sp |
| 381 |
.Vb 1 |
| 382 |
\& ( undef , "{ an \*(Aq[irregularly :\-(] {} parenthesized >:\-)\*(Aq string }" ); |
| 383 |
.Ve |
| 384 |
.Sp |
| 385 |
because the embedded pairs of \f(CW\*(Aq(..)\*(Aq\fRs and \f(CW\*(Aq[..]\*(Aq\fRs are "cross-nested" and |
| 386 |
the embedded \f(CW\*(Aq>\*(Aq\fR is unbalanced. (In a scalar context, this call would |
| 387 |
return an empty string. In a void context, \f(CW$text\fR would be unchanged.) |
| 388 |
.Sp |
| 389 |
Note that the embedded single-quotes in the string don't help in this |
| 390 |
case, since they have not been specified as acceptable delimiters and are |
| 391 |
therefore treated as non-delimiter characters (and ignored). |
| 392 |
.Sp |
| 393 |
However, if a particular species of quote character is included in the |
| 394 |
delimiter specification, then that type of quote will be correctly handled. |
| 395 |
for example, if \f(CW$text\fR is: |
| 396 |
.Sp |
| 397 |
.Vb 1 |
| 398 |
\& $text = \*(Aq<A HREF=">>>>">link</A>\*(Aq; |
| 399 |
.Ve |
| 400 |
.Sp |
| 401 |
then |
| 402 |
.Sp |
| 403 |
.Vb 1 |
| 404 |
\& @result = extract_bracketed( $text, \*(Aq<">\*(Aq ); |
| 405 |
.Ve |
| 406 |
.Sp |
| 407 |
returns: |
| 408 |
.Sp |
| 409 |
.Vb 1 |
| 410 |
\& ( \*(Aq<A HREF=">>>>">\*(Aq, \*(Aqlink</A>\*(Aq, "" ) |
| 411 |
.Ve |
| 412 |
.Sp |
| 413 |
as expected. Without the specification of \f(CW\*(C`"\*(C'\fR as an embedded quoter: |
| 414 |
.Sp |
| 415 |
.Vb 1 |
| 416 |
\& @result = extract_bracketed( $text, \*(Aq<>\*(Aq ); |
| 417 |
.Ve |
| 418 |
.Sp |
| 419 |
the result would be: |
| 420 |
.Sp |
| 421 |
.Vb 1 |
| 422 |
\& ( \*(Aq<A HREF=">\*(Aq, \*(Aq>>>">link</A>\*(Aq, "" ) |
| 423 |
.Ve |
| 424 |
.Sp |
| 425 |
In addition to the quote delimiters \f(CW\*(C`\*(Aq\*(C'\fR, \f(CW\*(C`"\*(C'\fR, and \f(CW\*(C`\`\*(C'\fR, full Perl quote-like |
| 426 |
quoting (i.e. q{string}, qq{string}, etc) can be specified by including the |
| 427 |
letter 'q' as a delimiter. Hence: |
| 428 |
.Sp |
| 429 |
.Vb 1 |
| 430 |
\& @result = extract_bracketed( $text, \*(Aq<q>\*(Aq ); |
| 431 |
.Ve |
| 432 |
.Sp |
| 433 |
would correctly match something like this: |
| 434 |
.Sp |
| 435 |
.Vb 1 |
| 436 |
\& $text = \*(Aq<leftop: conj /and/ conj>\*(Aq; |
| 437 |
.Ve |
| 438 |
.Sp |
| 439 |
See also: \f(CW"extract_quotelike"\fR and \f(CW"extract_codeblock"\fR. |
| 440 |
.ie n .IP """extract_variable""" 4 |
| 441 |
.el .IP \f(CWextract_variable\fR 4 |
| 442 |
.IX Item "extract_variable" |
| 443 |
\&\f(CW\*(C`extract_variable\*(C'\fR extracts any valid Perl variable or |
| 444 |
variable-involved expression, including scalars, arrays, hashes, array |
| 445 |
accesses, hash look-ups, method calls through objects, subroutine calls |
| 446 |
through subroutine references, etc. |
| 447 |
.Sp |
| 448 |
The subroutine takes up to two optional arguments: |
| 449 |
.RS 4 |
| 450 |
.IP 1. 4 |
| 451 |
A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 452 |
.IP 2. 4 |
| 453 |
A string specifying a pattern to be matched as a prefix (which is to be |
| 454 |
skipped). If omitted, optional whitespace is skipped. |
| 455 |
.RE |
| 456 |
.RS 4 |
| 457 |
.Sp |
| 458 |
On success in a list context, an array of 3 elements is returned. The |
| 459 |
elements are: |
| 460 |
.IP [0] 4 |
| 461 |
.IX Item "[0]" |
| 462 |
the extracted variable, or variablish expression |
| 463 |
.IP [1] 4 |
| 464 |
.IX Item "[1]" |
| 465 |
the remainder of the input text, |
| 466 |
.IP [2] 4 |
| 467 |
.IX Item "[2]" |
| 468 |
the prefix substring (if any), |
| 469 |
.RE |
| 470 |
.RS 4 |
| 471 |
.Sp |
| 472 |
On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 473 |
.Sp |
| 474 |
In a scalar context, \f(CW\*(C`extract_variable\*(C'\fR returns just the complete |
| 475 |
substring that matched a variablish expression. \f(CW\*(C`undef\*(C'\fR is returned on |
| 476 |
failure. In addition, the original input text has the returned substring |
| 477 |
(and any prefix) removed from it. |
| 478 |
.Sp |
| 479 |
In a void context, the input text just has the matched substring (and |
| 480 |
any specified prefix) removed. |
| 481 |
.RE |
| 482 |
.ie n .IP """extract_tagged""" 4 |
| 483 |
.el .IP \f(CWextract_tagged\fR 4 |
| 484 |
.IX Item "extract_tagged" |
| 485 |
\&\f(CW\*(C`extract_tagged\*(C'\fR extracts and segments text between (balanced) |
| 486 |
specified tags. |
| 487 |
.Sp |
| 488 |
The subroutine takes up to five optional arguments: |
| 489 |
.RS 4 |
| 490 |
.IP 1. 4 |
| 491 |
A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 492 |
.IP 2. 4 |
| 493 |
A string specifying a pattern (i.e. regex) to be matched as the opening tag. |
| 494 |
If the pattern string is omitted (or \f(CW\*(C`undef\*(C'\fR) then a pattern |
| 495 |
that matches any standard XML tag is used. |
| 496 |
.IP 3. 4 |
| 497 |
A string specifying a pattern to be matched at the closing tag. |
| 498 |
If the pattern string is omitted (or \f(CW\*(C`undef\*(C'\fR) then the closing |
| 499 |
tag is constructed by inserting a \f(CW\*(C`/\*(C'\fR after any leading bracket |
| 500 |
characters in the actual opening tag that was matched (\fInot\fR the pattern |
| 501 |
that matched the tag). For example, if the opening tag pattern |
| 502 |
is specified as \f(CW\*(Aq{{\ew+}}\*(Aq\fR and actually matched the opening tag |
| 503 |
\&\f(CW"{{DATA}}"\fR, then the constructed closing tag would be \f(CW"{{/DATA}}"\fR. |
| 504 |
.IP 4. 4 |
| 505 |
A string specifying a pattern to be matched as a prefix (which is to be |
| 506 |
skipped). If omitted, optional whitespace is skipped. |
| 507 |
.IP 5. 4 |
| 508 |
A hash reference containing various parsing options (see below) |
| 509 |
.RE |
| 510 |
.RS 4 |
| 511 |
.Sp |
| 512 |
The various options that can be specified are: |
| 513 |
.ie n .IP """reject => $listref""" 4 |
| 514 |
.el .IP "\f(CWreject => $listref\fR" 4 |
| 515 |
.IX Item "reject => $listref" |
| 516 |
The list reference contains one or more strings specifying patterns |
| 517 |
that must \fInot\fR appear within the tagged text. |
| 518 |
.Sp |
| 519 |
For example, to extract |
| 520 |
an HTML link (which should not contain nested links) use: |
| 521 |
.Sp |
| 522 |
.Vb 1 |
| 523 |
\& extract_tagged($text, \*(Aq<A>\*(Aq, \*(Aq</A>\*(Aq, undef, {reject => [\*(Aq<A>\*(Aq]} ); |
| 524 |
.Ve |
| 525 |
.ie n .IP """ignore => $listref""" 4 |
| 526 |
.el .IP "\f(CWignore => $listref\fR" 4 |
| 527 |
.IX Item "ignore => $listref" |
| 528 |
The list reference contains one or more strings specifying patterns |
| 529 |
that are \fInot\fR to be treated as nested tags within the tagged text |
| 530 |
(even if they would match the start tag pattern). |
| 531 |
.Sp |
| 532 |
For example, to extract an arbitrary XML tag, but ignore "empty" elements: |
| 533 |
.Sp |
| 534 |
.Vb 1 |
| 535 |
\& extract_tagged($text, undef, undef, undef, {ignore => [\*(Aq<[^>]*/>\*(Aq]} ); |
| 536 |
.Ve |
| 537 |
.Sp |
| 538 |
(also see "gen_delimited_pat" below). |
| 539 |
.ie n .IP """fail => $str""" 4 |
| 540 |
.el .IP "\f(CWfail => $str\fR" 4 |
| 541 |
.IX Item "fail => $str" |
| 542 |
The \f(CW\*(C`fail\*(C'\fR option indicates the action to be taken if a matching end |
| 543 |
tag is not encountered (i.e. before the end of the string or some |
| 544 |
\&\f(CW\*(C`reject\*(C'\fR pattern matches). By default, a failure to match a closing |
| 545 |
tag causes \f(CW\*(C`extract_tagged\*(C'\fR to immediately fail. |
| 546 |
.Sp |
| 547 |
However, if the string value associated with <reject> is "MAX", then |
| 548 |
\&\f(CW\*(C`extract_tagged\*(C'\fR returns the complete text up to the point of failure. |
| 549 |
If the string is "PARA", \f(CW\*(C`extract_tagged\*(C'\fR returns only the first paragraph |
| 550 |
after the tag (up to the first line that is either empty or contains |
| 551 |
only whitespace characters). |
| 552 |
If the string is "", the default behaviour (i.e. failure) is reinstated. |
| 553 |
.Sp |
| 554 |
For example, suppose the start tag "/para" introduces a paragraph, which then |
| 555 |
continues until the next "/endpara" tag or until another "/para" tag is |
| 556 |
encountered: |
| 557 |
.Sp |
| 558 |
.Vb 1 |
| 559 |
\& $text = "/para line 1\en\enline 3\en/para line 4"; |
| 560 |
\& |
| 561 |
\& extract_tagged($text, \*(Aq/para\*(Aq, \*(Aq/endpara\*(Aq, undef, |
| 562 |
\& {reject => \*(Aq/para\*(Aq, fail => MAX ); |
| 563 |
\& |
| 564 |
\& # EXTRACTED: "/para line 1\en\enline 3\en" |
| 565 |
.Ve |
| 566 |
.Sp |
| 567 |
Suppose instead, that if no matching "/endpara" tag is found, the "/para" |
| 568 |
tag refers only to the immediately following paragraph: |
| 569 |
.Sp |
| 570 |
.Vb 1 |
| 571 |
\& $text = "/para line 1\en\enline 3\en/para line 4"; |
| 572 |
\& |
| 573 |
\& extract_tagged($text, \*(Aq/para\*(Aq, \*(Aq/endpara\*(Aq, undef, |
| 574 |
\& {reject => \*(Aq/para\*(Aq, fail => MAX ); |
| 575 |
\& |
| 576 |
\& # EXTRACTED: "/para line 1\en" |
| 577 |
.Ve |
| 578 |
.Sp |
| 579 |
Note that the specified \f(CW\*(C`fail\*(C'\fR behaviour applies to nested tags as well. |
| 580 |
.RE |
| 581 |
.RS 4 |
| 582 |
.Sp |
| 583 |
On success in a list context, an array of 6 elements is returned. The elements are: |
| 584 |
.IP [0] 4 |
| 585 |
.IX Item "[0]" |
| 586 |
the extracted tagged substring (including the outermost tags), |
| 587 |
.IP [1] 4 |
| 588 |
.IX Item "[1]" |
| 589 |
the remainder of the input text, |
| 590 |
.IP [2] 4 |
| 591 |
.IX Item "[2]" |
| 592 |
the prefix substring (if any), |
| 593 |
.IP [3] 4 |
| 594 |
.IX Item "[3]" |
| 595 |
the opening tag |
| 596 |
.IP [4] 4 |
| 597 |
.IX Item "[4]" |
| 598 |
the text between the opening and closing tags |
| 599 |
.IP [5] 4 |
| 600 |
.IX Item "[5]" |
| 601 |
the closing tag (or "" if no closing tag was found) |
| 602 |
.RE |
| 603 |
.RS 4 |
| 604 |
.Sp |
| 605 |
On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 606 |
.Sp |
| 607 |
In a scalar context, \f(CW\*(C`extract_tagged\*(C'\fR returns just the complete |
| 608 |
substring that matched a tagged text (including the start and end |
| 609 |
tags). \f(CW\*(C`undef\*(C'\fR is returned on failure. In addition, the original input |
| 610 |
text has the returned substring (and any prefix) removed from it. |
| 611 |
.Sp |
| 612 |
In a void context, the input text just has the matched substring (and |
| 613 |
any specified prefix) removed. |
| 614 |
.RE |
| 615 |
.ie n .IP """gen_extract_tagged""" 4 |
| 616 |
.el .IP \f(CWgen_extract_tagged\fR 4 |
| 617 |
.IX Item "gen_extract_tagged" |
| 618 |
\&\f(CW\*(C`gen_extract_tagged\*(C'\fR generates a new anonymous subroutine which |
| 619 |
extracts text between (balanced) specified tags. In other words, |
| 620 |
it generates a function identical in function to \f(CW\*(C`extract_tagged\*(C'\fR. |
| 621 |
.Sp |
| 622 |
The difference between \f(CW\*(C`extract_tagged\*(C'\fR and the anonymous |
| 623 |
subroutines generated by |
| 624 |
\&\f(CW\*(C`gen_extract_tagged\*(C'\fR, is that those generated subroutines: |
| 625 |
.RS 4 |
| 626 |
.IP \(bu 4 |
| 627 |
do not have to reparse tag specification or parsing options every time |
| 628 |
they are called (whereas \f(CW\*(C`extract_tagged\*(C'\fR has to effectively rebuild |
| 629 |
its tag parser on every call); |
| 630 |
.IP \(bu 4 |
| 631 |
make use of the new qr// construct to pre-compile the regexes they use |
| 632 |
(whereas \f(CW\*(C`extract_tagged\*(C'\fR uses standard string variable interpolation |
| 633 |
to create tag-matching patterns). |
| 634 |
.RE |
| 635 |
.RS 4 |
| 636 |
.Sp |
| 637 |
The subroutine takes up to four optional arguments (the same set as |
| 638 |
\&\f(CW\*(C`extract_tagged\*(C'\fR except for the string to be processed). It returns |
| 639 |
a reference to a subroutine which in turn takes a single argument (the text to |
| 640 |
be extracted from). |
| 641 |
.Sp |
| 642 |
In other words, the implementation of \f(CW\*(C`extract_tagged\*(C'\fR is exactly |
| 643 |
equivalent to: |
| 644 |
.Sp |
| 645 |
.Vb 6 |
| 646 |
\& sub extract_tagged |
| 647 |
\& { |
| 648 |
\& my $text = shift; |
| 649 |
\& $extractor = gen_extract_tagged(@_); |
| 650 |
\& return $extractor\->($text); |
| 651 |
\& } |
| 652 |
.Ve |
| 653 |
.Sp |
| 654 |
(although \f(CW\*(C`extract_tagged\*(C'\fR is not currently implemented that way). |
| 655 |
.Sp |
| 656 |
Using \f(CW\*(C`gen_extract_tagged\*(C'\fR to create extraction functions for specific tags |
| 657 |
is a good idea if those functions are going to be called more than once, since |
| 658 |
their performance is typically twice as good as the more general-purpose |
| 659 |
\&\f(CW\*(C`extract_tagged\*(C'\fR. |
| 660 |
.RE |
| 661 |
.ie n .IP """extract_quotelike""" 4 |
| 662 |
.el .IP \f(CWextract_quotelike\fR 4 |
| 663 |
.IX Item "extract_quotelike" |
| 664 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR attempts to recognize, extract, and segment any |
| 665 |
one of the various Perl quotes and quotelike operators (see |
| 666 |
\&\fBperlop\fR\|(3)) Nested backslashed delimiters, embedded balanced bracket |
| 667 |
delimiters (for the quotelike operators), and trailing modifiers are |
| 668 |
all caught. For example, in: |
| 669 |
.Sp |
| 670 |
.Vb 1 |
| 671 |
\& extract_quotelike \*(Aqq # an octothorpe: \e# (not the end of the q!) #\*(Aq |
| 672 |
\& |
| 673 |
\& extract_quotelike \*(Aq "You said, \e"Use sed\e"." \*(Aq |
| 674 |
\& |
| 675 |
\& extract_quotelike \*(Aq s{([A\-Z]{1,8}\e.[A\-Z]{3})} /\eL$1\eE/; \*(Aq |
| 676 |
\& |
| 677 |
\& extract_quotelike \*(Aq tr/\e\e\e/\e\e\e\e/\e\e\e//ds; \*(Aq |
| 678 |
.Ve |
| 679 |
.Sp |
| 680 |
the full Perl quotelike operations are all extracted correctly. |
| 681 |
.Sp |
| 682 |
Note too that, when using the /x modifier on a regex, any comment |
| 683 |
containing the current pattern delimiter will cause the regex to be |
| 684 |
immediately terminated. In other words: |
| 685 |
.Sp |
| 686 |
.Vb 5 |
| 687 |
\& \*(Aqm / |
| 688 |
\& (?i) # CASE INSENSITIVE |
| 689 |
\& [a\-z_] # LEADING ALPHABETIC/UNDERSCORE |
| 690 |
\& [a\-z0\-9]* # FOLLOWED BY ANY NUMBER OF ALPHANUMERICS |
| 691 |
\& /x\*(Aq |
| 692 |
.Ve |
| 693 |
.Sp |
| 694 |
will be extracted as if it were: |
| 695 |
.Sp |
| 696 |
.Vb 3 |
| 697 |
\& \*(Aqm / |
| 698 |
\& (?i) # CASE INSENSITIVE |
| 699 |
\& [a\-z_] # LEADING ALPHABETIC/\*(Aq |
| 700 |
.Ve |
| 701 |
.Sp |
| 702 |
This behaviour is identical to that of the actual compiler. |
| 703 |
.Sp |
| 704 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR takes two arguments: the text to be processed and |
| 705 |
a prefix to be matched at the very beginning of the text. If no prefix |
| 706 |
is specified, optional whitespace is the default. If no text is given, |
| 707 |
\&\f(CW$_\fR is used. |
| 708 |
.Sp |
| 709 |
In a list context, an array of 11 elements is returned. The elements are: |
| 710 |
.RS 4 |
| 711 |
.IP [0] 4 |
| 712 |
.IX Item "[0]" |
| 713 |
the extracted quotelike substring (including trailing modifiers), |
| 714 |
.IP [1] 4 |
| 715 |
.IX Item "[1]" |
| 716 |
the remainder of the input text, |
| 717 |
.IP [2] 4 |
| 718 |
.IX Item "[2]" |
| 719 |
the prefix substring (if any), |
| 720 |
.IP [3] 4 |
| 721 |
.IX Item "[3]" |
| 722 |
the name of the quotelike operator (if any), |
| 723 |
.IP [4] 4 |
| 724 |
.IX Item "[4]" |
| 725 |
the left delimiter of the first block of the operation, |
| 726 |
.IP [5] 4 |
| 727 |
.IX Item "[5]" |
| 728 |
the text of the first block of the operation |
| 729 |
(that is, the contents of |
| 730 |
a quote, the regex of a match or substitution or the target list of a |
| 731 |
translation), |
| 732 |
.IP [6] 4 |
| 733 |
.IX Item "[6]" |
| 734 |
the right delimiter of the first block of the operation, |
| 735 |
.IP [7] 4 |
| 736 |
.IX Item "[7]" |
| 737 |
the left delimiter of the second block of the operation |
| 738 |
(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), |
| 739 |
.IP [8] 4 |
| 740 |
.IX Item "[8]" |
| 741 |
the text of the second block of the operation |
| 742 |
(that is, the replacement of a substitution or the translation list |
| 743 |
of a translation), |
| 744 |
.IP [9] 4 |
| 745 |
.IX Item "[9]" |
| 746 |
the right delimiter of the second block of the operation (if any), |
| 747 |
.IP [10] 4 |
| 748 |
.IX Item "[10]" |
| 749 |
the trailing modifiers on the operation (if any). |
| 750 |
.RE |
| 751 |
.RS 4 |
| 752 |
.Sp |
| 753 |
For each of the fields marked "(if any)" the default value on success is |
| 754 |
an empty string. |
| 755 |
On failure, all of these values (except the remaining text) are \f(CW\*(C`undef\*(C'\fR. |
| 756 |
.Sp |
| 757 |
In a scalar context, \f(CW\*(C`extract_quotelike\*(C'\fR returns just the complete substring |
| 758 |
that matched a quotelike operation (or \f(CW\*(C`undef\*(C'\fR on failure). In a scalar or |
| 759 |
void context, the input text has the same substring (and any specified |
| 760 |
prefix) removed. |
| 761 |
.Sp |
| 762 |
Examples: |
| 763 |
.Sp |
| 764 |
.Vb 1 |
| 765 |
\& # Remove the first quotelike literal that appears in text |
| 766 |
\& |
| 767 |
\& $quotelike = extract_quotelike($text,\*(Aq.*?\*(Aq); |
| 768 |
\& |
| 769 |
\& # Replace one or more leading whitespace\-separated quotelike |
| 770 |
\& # literals in $_ with "<QLL>" |
| 771 |
\& |
| 772 |
\& do { $_ = join \*(Aq<QLL>\*(Aq, (extract_quotelike)[2,1] } until $@; |
| 773 |
\& |
| 774 |
\& |
| 775 |
\& # Isolate the search pattern in a quotelike operation from $text |
| 776 |
\& |
| 777 |
\& ($op,$pat) = (extract_quotelike $text)[3,5]; |
| 778 |
\& if ($op =~ /[ms]/) |
| 779 |
\& { |
| 780 |
\& print "search pattern: $pat\en"; |
| 781 |
\& } |
| 782 |
\& else |
| 783 |
\& { |
| 784 |
\& print "$op is not a pattern matching operation\en"; |
| 785 |
\& } |
| 786 |
.Ve |
| 787 |
.RE |
| 788 |
.ie n .IP """extract_quotelike""" 4 |
| 789 |
.el .IP \f(CWextract_quotelike\fR 4 |
| 790 |
.IX Item "extract_quotelike" |
| 791 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR can successfully extract "here documents" from an input |
| 792 |
string, but with an important caveat in list contexts. |
| 793 |
.Sp |
| 794 |
Unlike other types of quote-like literals, a here document is rarely |
| 795 |
a contiguous substring. For example, a typical piece of code using |
| 796 |
here document might look like this: |
| 797 |
.Sp |
| 798 |
.Vb 4 |
| 799 |
\& <<\*(AqEOMSG\*(Aq || die; |
| 800 |
\& This is the message. |
| 801 |
\& EOMSG |
| 802 |
\& exit; |
| 803 |
.Ve |
| 804 |
.Sp |
| 805 |
Given this as an input string in a scalar context, \f(CW\*(C`extract_quotelike\*(C'\fR |
| 806 |
would correctly return the string "<<'EOMSG'\enThis is the message.\enEOMSG", |
| 807 |
leaving the string " || die;\enexit;" in the original variable. In other words, |
| 808 |
the two separate pieces of the here document are successfully extracted and |
| 809 |
concatenated. |
| 810 |
.Sp |
| 811 |
In a list context, \f(CW\*(C`extract_quotelike\*(C'\fR would return the list |
| 812 |
.RS 4 |
| 813 |
.IP [0] 4 |
| 814 |
.IX Item "[0]" |
| 815 |
"<<'EOMSG'\enThis is the message.\enEOMSG\en" (i.e. the full extracted here document, |
| 816 |
including fore and aft delimiters), |
| 817 |
.IP [1] 4 |
| 818 |
.IX Item "[1]" |
| 819 |
" || die;\enexit;" (i.e. the remainder of the input text, concatenated), |
| 820 |
.IP [2] 4 |
| 821 |
.IX Item "[2]" |
| 822 |
"" (i.e. the prefix substring \-\- trivial in this case), |
| 823 |
.IP [3] 4 |
| 824 |
.IX Item "[3]" |
| 825 |
"<<" (i.e. the "name" of the quotelike operator) |
| 826 |
.IP [4] 4 |
| 827 |
.IX Item "[4]" |
| 828 |
"'EOMSG'" (i.e. the left delimiter of the here document, including any quotes), |
| 829 |
.IP [5] 4 |
| 830 |
.IX Item "[5]" |
| 831 |
"This is the message.\en" (i.e. the text of the here document), |
| 832 |
.IP [6] 4 |
| 833 |
.IX Item "[6]" |
| 834 |
"EOMSG" (i.e. the right delimiter of the here document), |
| 835 |
.IP [7..10] 4 |
| 836 |
.IX Item "[7..10]" |
| 837 |
"" (a here document has no second left delimiter, second text, second right |
| 838 |
delimiter, or trailing modifiers). |
| 839 |
.RE |
| 840 |
.RS 4 |
| 841 |
.Sp |
| 842 |
However, the matching position of the input variable would be set to |
| 843 |
"exit;" (i.e. \fIafter\fR the closing delimiter of the here document), |
| 844 |
which would cause the earlier " || die;\enexit;" to be skipped in any |
| 845 |
sequence of code fragment extractions. |
| 846 |
.Sp |
| 847 |
To avoid this problem, when it encounters a here document whilst |
| 848 |
extracting from a modifiable string, \f(CW\*(C`extract_quotelike\*(C'\fR silently |
| 849 |
rearranges the string to an equivalent piece of Perl: |
| 850 |
.Sp |
| 851 |
.Vb 5 |
| 852 |
\& <<\*(AqEOMSG\*(Aq |
| 853 |
\& This is the message. |
| 854 |
\& EOMSG |
| 855 |
\& || die; |
| 856 |
\& exit; |
| 857 |
.Ve |
| 858 |
.Sp |
| 859 |
in which the here document \fIis\fR contiguous. It still leaves the |
| 860 |
matching position after the here document, but now the rest of the line |
| 861 |
on which the here document starts is not skipped. |
| 862 |
.Sp |
| 863 |
To prevent <extract_quotelike> from mucking about with the input in this way |
| 864 |
(this is the only case where a list-context \f(CW\*(C`extract_quotelike\*(C'\fR does so), |
| 865 |
you can pass the input variable as an interpolated literal: |
| 866 |
.Sp |
| 867 |
.Vb 1 |
| 868 |
\& $quotelike = extract_quotelike("$var"); |
| 869 |
.Ve |
| 870 |
.RE |
| 871 |
.ie n .IP """extract_codeblock""" 4 |
| 872 |
.el .IP \f(CWextract_codeblock\fR 4 |
| 873 |
.IX Item "extract_codeblock" |
| 874 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR attempts to recognize and extract a balanced |
| 875 |
bracket delimited substring that may contain unbalanced brackets |
| 876 |
inside Perl quotes or quotelike operations. That is, \f(CW\*(C`extract_codeblock\*(C'\fR |
| 877 |
is like a combination of \f(CW"extract_bracketed"\fR and |
| 878 |
\&\f(CW"extract_quotelike"\fR. |
| 879 |
.Sp |
| 880 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR takes the same initial three parameters as \f(CW\*(C`extract_bracketed\*(C'\fR: |
| 881 |
a text to process, a set of delimiter brackets to look for, and a prefix to |
| 882 |
match first. It also takes an optional fourth parameter, which allows the |
| 883 |
outermost delimiter brackets to be specified separately (see below), |
| 884 |
and a fifth parameter used only by Parse::RecDescent. |
| 885 |
.Sp |
| 886 |
Omitting the first argument (input text) means process \f(CW$_\fR instead. |
| 887 |
Omitting the second argument (delimiter brackets) indicates that only \f(CW\*(Aq{\*(Aq\fR is to be used. |
| 888 |
Omitting the third argument (prefix argument) implies optional whitespace at the start. |
| 889 |
Omitting the fourth argument (outermost delimiter brackets) indicates that the |
| 890 |
value of the second argument is to be used for the outermost delimiters. |
| 891 |
.Sp |
| 892 |
Once the prefix and the outermost opening delimiter bracket have been |
| 893 |
recognized, code blocks are extracted by stepping through the input text and |
| 894 |
trying the following alternatives in sequence: |
| 895 |
.RS 4 |
| 896 |
.IP 1. 4 |
| 897 |
Try and match a closing delimiter bracket. If the bracket was the same |
| 898 |
species as the last opening bracket, return the substring to that |
| 899 |
point. If the bracket was mismatched, return an error. |
| 900 |
.IP 2. 4 |
| 901 |
Try to match a quote or quotelike operator. If found, call |
| 902 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR to eat it. If \f(CW\*(C`extract_quotelike\*(C'\fR fails, return |
| 903 |
the error it returned. Otherwise go back to step 1. |
| 904 |
.IP 3. 4 |
| 905 |
Try to match an opening delimiter bracket. If found, call |
| 906 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR recursively to eat the embedded block. If the |
| 907 |
recursive call fails, return an error. Otherwise, go back to step 1. |
| 908 |
.IP 4. 4 |
| 909 |
Unconditionally match a bareword or any other single character, and |
| 910 |
then go back to step 1. |
| 911 |
.RE |
| 912 |
.RS 4 |
| 913 |
.Sp |
| 914 |
Examples: |
| 915 |
.Sp |
| 916 |
.Vb 1 |
| 917 |
\& # Find a while loop in the text |
| 918 |
\& |
| 919 |
\& if ($text =~ s/.*?while\es*\e{/{/) |
| 920 |
\& { |
| 921 |
\& $loop = "while " . extract_codeblock($text); |
| 922 |
\& } |
| 923 |
\& |
| 924 |
\& # Remove the first round\-bracketed list (which may include |
| 925 |
\& # round\- or curly\-bracketed code blocks or quotelike operators) |
| 926 |
\& |
| 927 |
\& extract_codeblock $text, "(){}", \*(Aq[^(]*\*(Aq; |
| 928 |
.Ve |
| 929 |
.Sp |
| 930 |
The ability to specify a different outermost delimiter bracket is useful |
| 931 |
in some circumstances. For example, in the Parse::RecDescent module, |
| 932 |
parser actions which are to be performed only on a successful parse |
| 933 |
are specified using a \f(CW\*(C`<defer:...>\*(C'\fR directive. For example: |
| 934 |
.Sp |
| 935 |
.Vb 2 |
| 936 |
\& sentence: subject verb object |
| 937 |
\& <defer: {$::theVerb = $item{verb}} > |
| 938 |
.Ve |
| 939 |
.Sp |
| 940 |
Parse::RecDescent uses \f(CW\*(C`extract_codeblock($text, \*(Aq{}<>\*(Aq)\*(C'\fR to extract the code |
| 941 |
within the \f(CW\*(C`<defer:...>\*(C'\fR directive, but there's a problem. |
| 942 |
.Sp |
| 943 |
A deferred action like this: |
| 944 |
.Sp |
| 945 |
.Vb 1 |
| 946 |
\& <defer: {if ($count>10) {$count\-\-}} > |
| 947 |
.Ve |
| 948 |
.Sp |
| 949 |
will be incorrectly parsed as: |
| 950 |
.Sp |
| 951 |
.Vb 1 |
| 952 |
\& <defer: {if ($count> |
| 953 |
.Ve |
| 954 |
.Sp |
| 955 |
because the "less than" operator is interpreted as a closing delimiter. |
| 956 |
.Sp |
| 957 |
But, by extracting the directive using |
| 958 |
\&\f(CW\*(C`extract_codeblock($text,\ \*(Aq{}\*(Aq,\ undef,\ \*(Aq<>\*(Aq)\*(C'\fR |
| 959 |
the '>' character is only treated as a delimited at the outermost |
| 960 |
level of the code block, so the directive is parsed correctly. |
| 961 |
.RE |
| 962 |
.ie n .IP """extract_multiple""" 4 |
| 963 |
.el .IP \f(CWextract_multiple\fR 4 |
| 964 |
.IX Item "extract_multiple" |
| 965 |
The \f(CW\*(C`extract_multiple\*(C'\fR subroutine takes a string to be processed and a |
| 966 |
list of extractors (subroutines or regular expressions) to apply to that string. |
| 967 |
.Sp |
| 968 |
In an array context \f(CW\*(C`extract_multiple\*(C'\fR returns an array of substrings |
| 969 |
of the original string, as extracted by the specified extractors. |
| 970 |
In a scalar context, \f(CW\*(C`extract_multiple\*(C'\fR returns the first |
| 971 |
substring successfully extracted from the original string. In both |
| 972 |
scalar and void contexts the original string has the first successfully |
| 973 |
extracted substring removed from it. In all contexts |
| 974 |
\&\f(CW\*(C`extract_multiple\*(C'\fR starts at the current \f(CW\*(C`pos\*(C'\fR of the string, and |
| 975 |
sets that \f(CW\*(C`pos\*(C'\fR appropriately after it matches. |
| 976 |
.Sp |
| 977 |
Hence, the aim of a call to \f(CW\*(C`extract_multiple\*(C'\fR in a list context |
| 978 |
is to split the processed string into as many non-overlapping fields as |
| 979 |
possible, by repeatedly applying each of the specified extractors |
| 980 |
to the remainder of the string. Thus \f(CW\*(C`extract_multiple\*(C'\fR is |
| 981 |
a generalized form of Perl's \f(CW\*(C`split\*(C'\fR subroutine. |
| 982 |
.Sp |
| 983 |
The subroutine takes up to four optional arguments: |
| 984 |
.RS 4 |
| 985 |
.IP 1. 4 |
| 986 |
A string to be processed (\f(CW$_\fR if the string is omitted or \f(CW\*(C`undef\*(C'\fR) |
| 987 |
.IP 2. 4 |
| 988 |
A reference to a list of subroutine references and/or qr// objects and/or |
| 989 |
literal strings and/or hash references, specifying the extractors |
| 990 |
to be used to split the string. If this argument is omitted (or |
| 991 |
\&\f(CW\*(C`undef\*(C'\fR) the list: |
| 992 |
.Sp |
| 993 |
.Vb 5 |
| 994 |
\& [ |
| 995 |
\& sub { extract_variable($_[0], \*(Aq\*(Aq) }, |
| 996 |
\& sub { extract_quotelike($_[0],\*(Aq\*(Aq) }, |
| 997 |
\& sub { extract_codeblock($_[0],\*(Aq{}\*(Aq,\*(Aq\*(Aq) }, |
| 998 |
\& ] |
| 999 |
.Ve |
| 1000 |
.Sp |
| 1001 |
is used. |
| 1002 |
.IP 3. 4 |
| 1003 |
An number specifying the maximum number of fields to return. If this |
| 1004 |
argument is omitted (or \f(CW\*(C`undef\*(C'\fR), split continues as long as possible. |
| 1005 |
.Sp |
| 1006 |
If the third argument is \fIN\fR, then extraction continues until \fIN\fR fields |
| 1007 |
have been successfully extracted, or until the string has been completely |
| 1008 |
processed. |
| 1009 |
.Sp |
| 1010 |
Note that in scalar and void contexts the value of this argument is |
| 1011 |
automatically reset to 1 (under \f(CW\*(C`\-w\*(C'\fR, a warning is issued if the argument |
| 1012 |
has to be reset). |
| 1013 |
.IP 4. 4 |
| 1014 |
A value indicating whether unmatched substrings (see below) within the |
| 1015 |
text should be skipped or returned as fields. If the value is true, |
| 1016 |
such substrings are skipped. Otherwise, they are returned. |
| 1017 |
.RE |
| 1018 |
.RS 4 |
| 1019 |
.Sp |
| 1020 |
The extraction process works by applying each extractor in |
| 1021 |
sequence to the text string. |
| 1022 |
.Sp |
| 1023 |
If the extractor is a subroutine it is called in a list context and is |
| 1024 |
expected to return a list of a single element, namely the extracted |
| 1025 |
text. It may optionally also return two further arguments: a string |
| 1026 |
representing the text left after extraction (like $' for a pattern |
| 1027 |
match), and a string representing any prefix skipped before the |
| 1028 |
extraction (like $` in a pattern match). Note that this is designed |
| 1029 |
to facilitate the use of other Text::Balanced subroutines with |
| 1030 |
\&\f(CW\*(C`extract_multiple\*(C'\fR. Note too that the value returned by an extractor |
| 1031 |
subroutine need not bear any relationship to the corresponding substring |
| 1032 |
of the original text (see examples below). |
| 1033 |
.Sp |
| 1034 |
If the extractor is a precompiled regular expression or a string, |
| 1035 |
it is matched against the text in a scalar context with a leading |
| 1036 |
\&'\eG' and the gc modifiers enabled. The extracted value is either |
| 1037 |
\&\f(CW$1\fR if that variable is defined after the match, or else the |
| 1038 |
complete match (i.e. $&). |
| 1039 |
.Sp |
| 1040 |
If the extractor is a hash reference, it must contain exactly one element. |
| 1041 |
The value of that element is one of the |
| 1042 |
above extractor types (subroutine reference, regular expression, or string). |
| 1043 |
The key of that element is the name of a class into which the successful |
| 1044 |
return value of the extractor will be blessed. |
| 1045 |
.Sp |
| 1046 |
If an extractor returns a defined value, that value is immediately |
| 1047 |
treated as the next extracted field and pushed onto the list of fields. |
| 1048 |
If the extractor was specified in a hash reference, the field is also |
| 1049 |
blessed into the appropriate class, |
| 1050 |
.Sp |
| 1051 |
If the extractor fails to match (in the case of a regex extractor), or returns an empty list or an undefined value (in the case of a subroutine extractor), it is |
| 1052 |
assumed to have failed to extract. |
| 1053 |
If none of the extractor subroutines succeeds, then one |
| 1054 |
character is extracted from the start of the text and the extraction |
| 1055 |
subroutines reapplied. Characters which are thus removed are accumulated and |
| 1056 |
eventually become the next field (unless the fourth argument is true, in which |
| 1057 |
case they are discarded). |
| 1058 |
.Sp |
| 1059 |
For example, the following extracts substrings that are valid Perl variables: |
| 1060 |
.Sp |
| 1061 |
.Vb 3 |
| 1062 |
\& @fields = extract_multiple($text, |
| 1063 |
\& [ sub { extract_variable($_[0]) } ], |
| 1064 |
\& undef, 1); |
| 1065 |
.Ve |
| 1066 |
.Sp |
| 1067 |
This example separates a text into fields which are quote delimited, |
| 1068 |
curly bracketed, and anything else. The delimited and bracketed |
| 1069 |
parts are also blessed to identify them (the "anything else" is unblessed): |
| 1070 |
.Sp |
| 1071 |
.Vb 5 |
| 1072 |
\& @fields = extract_multiple($text, |
| 1073 |
\& [ |
| 1074 |
\& { Delim => sub { extract_delimited($_[0],q{\*(Aq"}) } }, |
| 1075 |
\& { Brack => sub { extract_bracketed($_[0],\*(Aq{}\*(Aq) } }, |
| 1076 |
\& ]); |
| 1077 |
.Ve |
| 1078 |
.Sp |
| 1079 |
This call extracts the next single substring that is a valid Perl quotelike |
| 1080 |
operator (and removes it from \f(CW$text\fR): |
| 1081 |
.Sp |
| 1082 |
.Vb 4 |
| 1083 |
\& $quotelike = extract_multiple($text, |
| 1084 |
\& [ |
| 1085 |
\& sub { extract_quotelike($_[0]) }, |
| 1086 |
\& ], undef, 1); |
| 1087 |
.Ve |
| 1088 |
.Sp |
| 1089 |
Finally, here is yet another way to do comma-separated value parsing: |
| 1090 |
.Sp |
| 1091 |
.Vb 8 |
| 1092 |
\& $csv_text = "a,\*(Aqx b\*(Aq,c"; |
| 1093 |
\& @fields = extract_multiple($csv_text, |
| 1094 |
\& [ |
| 1095 |
\& sub { extract_delimited($_[0],q{\*(Aq"}) }, |
| 1096 |
\& qr/([^,]+)/, |
| 1097 |
\& ], |
| 1098 |
\& undef,1); |
| 1099 |
\& # @fields is now (\*(Aqa\*(Aq, "\*(Aqx b\*(Aq", \*(Aqc\*(Aq) |
| 1100 |
.Ve |
| 1101 |
.Sp |
| 1102 |
The list in the second argument means: |
| 1103 |
\&\fI"Try and extract a ' or " delimited string, otherwise extract anything up to a comma..."\fR. |
| 1104 |
The undef third argument means: |
| 1105 |
\&\fI"...as many times as possible..."\fR, |
| 1106 |
and the true value in the fourth argument means |
| 1107 |
\&\fI"...discarding anything else that appears (i.e. the commas)"\fR. |
| 1108 |
.Sp |
| 1109 |
If you wanted the commas preserved as separate fields (i.e. like split |
| 1110 |
does if your split pattern has capturing parentheses), you would |
| 1111 |
just make the last parameter undefined (or remove it). |
| 1112 |
.RE |
| 1113 |
.ie n .IP """gen_delimited_pat""" 4 |
| 1114 |
.el .IP \f(CWgen_delimited_pat\fR 4 |
| 1115 |
.IX Item "gen_delimited_pat" |
| 1116 |
The \f(CW\*(C`gen_delimited_pat\*(C'\fR subroutine takes a single (string) argument and |
| 1117 |
builds a Friedl-style optimized regex that matches a string delimited |
| 1118 |
by any one of the characters in the single argument. For example: |
| 1119 |
.Sp |
| 1120 |
.Vb 1 |
| 1121 |
\& gen_delimited_pat(q{\*(Aq"}) |
| 1122 |
.Ve |
| 1123 |
.Sp |
| 1124 |
returns the regex: |
| 1125 |
.Sp |
| 1126 |
.Vb 1 |
| 1127 |
\& (?:\e"(?:\e\e\e"|(?!\e").)*\e"|\e\*(Aq(?:\e\e\e\*(Aq|(?!\e\*(Aq).)*\e\*(Aq) |
| 1128 |
.Ve |
| 1129 |
.Sp |
| 1130 |
Note that the specified delimiters are automatically quotemeta'd. |
| 1131 |
.Sp |
| 1132 |
A typical use of \f(CW\*(C`gen_delimited_pat\*(C'\fR would be to build special purpose tags |
| 1133 |
for \f(CW\*(C`extract_tagged\*(C'\fR. For example, to properly ignore "empty" XML elements |
| 1134 |
(which might contain quoted strings): |
| 1135 |
.Sp |
| 1136 |
.Vb 1 |
| 1137 |
\& my $empty_tag = \*(Aq<(\*(Aq . gen_delimited_pat(q{\*(Aq"}) . \*(Aq|.)+/>\*(Aq; |
| 1138 |
\& |
| 1139 |
\& extract_tagged($text, undef, undef, undef, {ignore => [$empty_tag]} ); |
| 1140 |
.Ve |
| 1141 |
.Sp |
| 1142 |
\&\f(CW\*(C`gen_delimited_pat\*(C'\fR may also be called with an optional second argument, |
| 1143 |
which specifies the "escape" character(s) to be used for each delimiter. |
| 1144 |
For example to match a Pascal-style string (where ' is the delimiter |
| 1145 |
and '' is a literal ' within the string): |
| 1146 |
.Sp |
| 1147 |
.Vb 1 |
| 1148 |
\& gen_delimited_pat(q{\*(Aq},q{\*(Aq}); |
| 1149 |
.Ve |
| 1150 |
.Sp |
| 1151 |
Different escape characters can be specified for different delimiters. |
| 1152 |
For example, to specify that '/' is the escape for single quotes |
| 1153 |
and '%' is the escape for double quotes: |
| 1154 |
.Sp |
| 1155 |
.Vb 1 |
| 1156 |
\& gen_delimited_pat(q{\*(Aq"},q{/%}); |
| 1157 |
.Ve |
| 1158 |
.Sp |
| 1159 |
If more delimiters than escape chars are specified, the last escape char |
| 1160 |
is used for the remaining delimiters. |
| 1161 |
If no escape char is specified for a given specified delimiter, '\e' is used. |
| 1162 |
.ie n .IP """delimited_pat""" 4 |
| 1163 |
.el .IP \f(CWdelimited_pat\fR 4 |
| 1164 |
.IX Item "delimited_pat" |
| 1165 |
Note that \f(CW\*(C`gen_delimited_pat\*(C'\fR was previously called \f(CW\*(C`delimited_pat\*(C'\fR. |
| 1166 |
That name may still be used, but is now deprecated. |
| 1167 |
.SH DIAGNOSTICS |
| 1168 |
.IX Header "DIAGNOSTICS" |
| 1169 |
In a list context, all the functions return \f(CW\*(C`(undef,$original_text)\*(C'\fR |
| 1170 |
on failure. In a scalar context, failure is indicated by returning \f(CW\*(C`undef\*(C'\fR |
| 1171 |
(in this case the input text is not modified in any way). |
| 1172 |
.PP |
| 1173 |
In addition, on failure in \fIany\fR context, the \f(CW$@\fR variable is set. |
| 1174 |
Accessing \f(CW\*(C`$@\->{error}\*(C'\fR returns one of the error diagnostics listed |
| 1175 |
below. |
| 1176 |
Accessing \f(CW\*(C`$@\->{pos}\*(C'\fR returns the offset into the original string at |
| 1177 |
which the error was detected (although not necessarily where it occurred!) |
| 1178 |
Printing \f(CW$@\fR directly produces the error message, with the offset appended. |
| 1179 |
On success, the \f(CW$@\fR variable is guaranteed to be \f(CW\*(C`undef\*(C'\fR. |
| 1180 |
.PP |
| 1181 |
The available diagnostics are: |
| 1182 |
.ie n .IP """Did not find a suitable bracket: ""%s""""" 4 |
| 1183 |
.el .IP "\f(CWDid not find a suitable bracket: ""%s""\fR" 4 |
| 1184 |
.IX Item "Did not find a suitable bracket: ""%s""" |
| 1185 |
The delimiter provided to \f(CW\*(C`extract_bracketed\*(C'\fR was not one of |
| 1186 |
\&\f(CW\*(Aq()[]<>{}\*(Aq\fR. |
| 1187 |
.ie n .IP """Did not find prefix: /%s/""" 4 |
| 1188 |
.el .IP "\f(CWDid not find prefix: /%s/\fR" 4 |
| 1189 |
.IX Item "Did not find prefix: /%s/" |
| 1190 |
A non-optional prefix was specified but wasn't found at the start of the text. |
| 1191 |
.ie n .IP """Did not find opening bracket after prefix: ""%s""""" 4 |
| 1192 |
.el .IP "\f(CWDid not find opening bracket after prefix: ""%s""\fR" 4 |
| 1193 |
.IX Item "Did not find opening bracket after prefix: ""%s""" |
| 1194 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR was expecting a |
| 1195 |
particular kind of bracket at the start of the text, and didn't find it. |
| 1196 |
.ie n .IP """No quotelike operator found after prefix: ""%s""""" 4 |
| 1197 |
.el .IP "\f(CWNo quotelike operator found after prefix: ""%s""\fR" 4 |
| 1198 |
.IX Item "No quotelike operator found after prefix: ""%s""" |
| 1199 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR didn't find one of the quotelike operators \f(CW\*(C`q\*(C'\fR, |
| 1200 |
\&\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 |
| 1201 |
it was extracting. |
| 1202 |
.ie n .IP """Unmatched closing bracket: ""%c""""" 4 |
| 1203 |
.el .IP "\f(CWUnmatched closing bracket: ""%c""\fR" 4 |
| 1204 |
.IX Item "Unmatched closing bracket: ""%c""" |
| 1205 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR encountered |
| 1206 |
a closing bracket where none was expected. |
| 1207 |
.ie n .IP """Unmatched opening bracket(s): ""%s""""" 4 |
| 1208 |
.el .IP "\f(CWUnmatched opening bracket(s): ""%s""\fR" 4 |
| 1209 |
.IX Item "Unmatched opening bracket(s): ""%s""" |
| 1210 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR ran |
| 1211 |
out of characters in the text before closing one or more levels of nested |
| 1212 |
brackets. |
| 1213 |
.ie n .IP """Unmatched embedded quote (%s)""" 4 |
| 1214 |
.el .IP "\f(CWUnmatched embedded quote (%s)\fR" 4 |
| 1215 |
.IX Item "Unmatched embedded quote (%s)" |
| 1216 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR attempted to match an embedded quoted substring, but |
| 1217 |
failed to find a closing quote to match it. |
| 1218 |
.ie n .IP """Did not find closing delimiter to match \*(Aq%s\*(Aq""" 4 |
| 1219 |
.el .IP "\f(CWDid not find closing delimiter to match \*(Aq%s\*(Aq\fR" 4 |
| 1220 |
.IX Item "Did not find closing delimiter to match %s" |
| 1221 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR was unable to find a closing delimiter to match the |
| 1222 |
one that opened the quote-like operation. |
| 1223 |
.ie n .IP """Mismatched closing bracket: expected ""%c"" but found ""%s""""" 4 |
| 1224 |
.el .IP "\f(CWMismatched closing bracket: expected ""%c"" but found ""%s""\fR" 4 |
| 1225 |
.IX Item "Mismatched closing bracket: expected ""%c"" but found ""%s""" |
| 1226 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR, \f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR found |
| 1227 |
a valid bracket delimiter, but it was the wrong species. This usually |
| 1228 |
indicates a nesting error, but may indicate incorrect quoting or escaping. |
| 1229 |
.ie n .IP """No block delimiter found after quotelike ""%s""""" 4 |
| 1230 |
.el .IP "\f(CWNo block delimiter found after quotelike ""%s""\fR" 4 |
| 1231 |
.IX Item "No block delimiter found after quotelike ""%s""" |
| 1232 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR or \f(CW\*(C`extract_codeblock\*(C'\fR found one of the |
| 1233 |
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 |
| 1234 |
without a suitable block after it. |
| 1235 |
.ie n .IP """Did not find leading dereferencer""" 4 |
| 1236 |
.el .IP "\f(CWDid not find leading dereferencer\fR" 4 |
| 1237 |
.IX Item "Did not find leading dereferencer" |
| 1238 |
\&\f(CW\*(C`extract_variable\*(C'\fR was expecting one of '$', '@', or '%' at the start of |
| 1239 |
a variable, but didn't find any of them. |
| 1240 |
.ie n .IP """Bad identifier after dereferencer""" 4 |
| 1241 |
.el .IP "\f(CWBad identifier after dereferencer\fR" 4 |
| 1242 |
.IX Item "Bad identifier after dereferencer" |
| 1243 |
\&\f(CW\*(C`extract_variable\*(C'\fR found a '$', '@', or '%' indicating a variable, but that |
| 1244 |
character was not followed by a legal Perl identifier. |
| 1245 |
.ie n .IP """Did not find expected opening bracket at %s""" 4 |
| 1246 |
.el .IP "\f(CWDid not find expected opening bracket at %s\fR" 4 |
| 1247 |
.IX Item "Did not find expected opening bracket at %s" |
| 1248 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR failed to find any of the outermost opening brackets |
| 1249 |
that were specified. |
| 1250 |
.ie n .IP """Improperly nested codeblock at %s""" 4 |
| 1251 |
.el .IP "\f(CWImproperly nested codeblock at %s\fR" 4 |
| 1252 |
.IX Item "Improperly nested codeblock at %s" |
| 1253 |
A nested code block was found that started with a delimiter that was specified |
| 1254 |
as being only to be used as an outermost bracket. |
| 1255 |
.ie n .IP """Missing second block for quotelike ""%s""""" 4 |
| 1256 |
.el .IP "\f(CWMissing second block for quotelike ""%s""\fR" 4 |
| 1257 |
.IX Item "Missing second block for quotelike ""%s""" |
| 1258 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR or \f(CW\*(C`extract_quotelike\*(C'\fR found one of the |
| 1259 |
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. |
| 1260 |
.ie n .IP """No match found for opening bracket""" 4 |
| 1261 |
.el .IP "\f(CWNo match found for opening bracket\fR" 4 |
| 1262 |
.IX Item "No match found for opening bracket" |
| 1263 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR failed to find a closing bracket to match the outermost |
| 1264 |
opening bracket. |
| 1265 |
.ie n .IP """Did not find opening tag: /%s/""" 4 |
| 1266 |
.el .IP "\f(CWDid not find opening tag: /%s/\fR" 4 |
| 1267 |
.IX Item "Did not find opening tag: /%s/" |
| 1268 |
\&\f(CW\*(C`extract_tagged\*(C'\fR did not find a suitable opening tag (after any specified |
| 1269 |
prefix was removed). |
| 1270 |
.ie n .IP """Unable to construct closing tag to match: /%s/""" 4 |
| 1271 |
.el .IP "\f(CWUnable to construct closing tag to match: /%s/\fR" 4 |
| 1272 |
.IX Item "Unable to construct closing tag to match: /%s/" |
| 1273 |
\&\f(CW\*(C`extract_tagged\*(C'\fR matched the specified opening tag and tried to |
| 1274 |
modify the matched text to produce a matching closing tag (because |
| 1275 |
none was specified). It failed to generate the closing tag, almost |
| 1276 |
certainly because the opening tag did not start with a |
| 1277 |
bracket of some kind. |
| 1278 |
.ie n .IP """Found invalid nested tag: %s""" 4 |
| 1279 |
.el .IP "\f(CWFound invalid nested tag: %s\fR" 4 |
| 1280 |
.IX Item "Found invalid nested tag: %s" |
| 1281 |
\&\f(CW\*(C`extract_tagged\*(C'\fR found a nested tag that appeared in the "reject" list |
| 1282 |
(and the failure mode was not "MAX" or "PARA"). |
| 1283 |
.ie n .IP """Found unbalanced nested tag: %s""" 4 |
| 1284 |
.el .IP "\f(CWFound unbalanced nested tag: %s\fR" 4 |
| 1285 |
.IX Item "Found unbalanced nested tag: %s" |
| 1286 |
\&\f(CW\*(C`extract_tagged\*(C'\fR found a nested opening tag that was not matched by a |
| 1287 |
corresponding nested closing tag (and the failure mode was not "MAX" or "PARA"). |
| 1288 |
.ie n .IP """Did not find closing tag""" 4 |
| 1289 |
.el .IP "\f(CWDid not find closing tag\fR" 4 |
| 1290 |
.IX Item "Did not find closing tag" |
| 1291 |
\&\f(CW\*(C`extract_tagged\*(C'\fR reached the end of the text without finding a closing tag |
| 1292 |
to match the original opening tag (and the failure mode was not |
| 1293 |
"MAX" or "PARA"). |
| 1294 |
.SH EXPORTS |
| 1295 |
.IX Header "EXPORTS" |
| 1296 |
The following symbols are, or can be, exported by this module: |
| 1297 |
.IP "Default Exports" 4 |
| 1298 |
.IX Item "Default Exports" |
| 1299 |
\&\fINone\fR. |
| 1300 |
.IP "Optional Exports" 4 |
| 1301 |
.IX Item "Optional Exports" |
| 1302 |
\&\f(CW\*(C`extract_delimited\*(C'\fR, |
| 1303 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR, |
| 1304 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR, |
| 1305 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR, |
| 1306 |
\&\f(CW\*(C`extract_variable\*(C'\fR, |
| 1307 |
\&\f(CW\*(C`extract_tagged\*(C'\fR, |
| 1308 |
\&\f(CW\*(C`extract_multiple\*(C'\fR, |
| 1309 |
\&\f(CW\*(C`gen_delimited_pat\*(C'\fR, |
| 1310 |
\&\f(CW\*(C`gen_extract_tagged\*(C'\fR, |
| 1311 |
\&\f(CW\*(C`delimited_pat\*(C'\fR. |
| 1312 |
.IP "Export Tags" 4 |
| 1313 |
.IX Item "Export Tags" |
| 1314 |
.RS 4 |
| 1315 |
.PD 0 |
| 1316 |
.ie n .IP """:ALL""" 4 |
| 1317 |
.el .IP \f(CW:ALL\fR 4 |
| 1318 |
.IX Item ":ALL" |
| 1319 |
.PD |
| 1320 |
\&\f(CW\*(C`extract_delimited\*(C'\fR, |
| 1321 |
\&\f(CW\*(C`extract_bracketed\*(C'\fR, |
| 1322 |
\&\f(CW\*(C`extract_quotelike\*(C'\fR, |
| 1323 |
\&\f(CW\*(C`extract_codeblock\*(C'\fR, |
| 1324 |
\&\f(CW\*(C`extract_variable\*(C'\fR, |
| 1325 |
\&\f(CW\*(C`extract_tagged\*(C'\fR, |
| 1326 |
\&\f(CW\*(C`extract_multiple\*(C'\fR, |
| 1327 |
\&\f(CW\*(C`gen_delimited_pat\*(C'\fR, |
| 1328 |
\&\f(CW\*(C`gen_extract_tagged\*(C'\fR, |
| 1329 |
\&\f(CW\*(C`delimited_pat\*(C'\fR. |
| 1330 |
.RE |
| 1331 |
.RS 4 |
| 1332 |
.RE |
| 1333 |
.SH "KNOWN BUGS" |
| 1334 |
.IX Header "KNOWN BUGS" |
| 1335 |
See <https://rt.cpan.org/Dist/Display.html?Status=Active&Queue=Text\-Balanced>. |
| 1336 |
.SH FEEDBACK |
| 1337 |
.IX Header "FEEDBACK" |
| 1338 |
Patches, bug reports, suggestions or any other feedback is welcome. |
| 1339 |
.PP |
| 1340 |
Patches can be sent as GitHub pull requests at |
| 1341 |
<https://github.com/steve\-m\-hay/Text\-Balanced/pulls>. |
| 1342 |
.PP |
| 1343 |
Bug reports and suggestions can be made on the CPAN Request Tracker at |
| 1344 |
<https://rt.cpan.org/Public/Bug/Report.html?Queue=Text\-Balanced>. |
| 1345 |
.PP |
| 1346 |
Currently active requests on the CPAN Request Tracker can be viewed at |
| 1347 |
<https://rt.cpan.org/Public/Dist/Display.html?Status=Active;Queue=Text\-Balanced>. |
| 1348 |
.PP |
| 1349 |
Please test this distribution. See CPAN Testers Reports at |
| 1350 |
<https://www.cpantesters.org/> for details of how to get involved. |
| 1351 |
.PP |
| 1352 |
Previous test results on CPAN Testers Reports can be viewed at |
| 1353 |
<https://www.cpantesters.org/distro/T/Text\-Balanced.html>. |
| 1354 |
.PP |
| 1355 |
Please rate this distribution on CPAN Ratings at |
| 1356 |
<https://cpanratings.perl.org/rate/?distribution=Text\-Balanced>. |
| 1357 |
.SH AVAILABILITY |
| 1358 |
.IX Header "AVAILABILITY" |
| 1359 |
The latest version of this module is available from CPAN (see |
| 1360 |
"CPAN" in perlmodlib for details) at |
| 1361 |
.PP |
| 1362 |
<https://metacpan.org/release/Text\-Balanced> or |
| 1363 |
.PP |
| 1364 |
<https://www.cpan.org/authors/id/S/SH/SHAY/> or |
| 1365 |
.PP |
| 1366 |
<https://www.cpan.org/modules/by\-module/Text/>. |
| 1367 |
.PP |
| 1368 |
The latest source code is available from GitHub at |
| 1369 |
<https://github.com/steve\-m\-hay/Text\-Balanced>. |
| 1370 |
.SH INSTALLATION |
| 1371 |
.IX Header "INSTALLATION" |
| 1372 |
See the \fIINSTALL\fR file. |
| 1373 |
.SH AUTHOR |
| 1374 |
.IX Header "AUTHOR" |
| 1375 |
Damian Conway <[email protected] <mailto:[email protected]>>. |
| 1376 |
.PP |
| 1377 |
Steve Hay <[email protected] <mailto:[email protected]>> is now maintaining |
| 1378 |
Text::Balanced as of version 2.03. |
| 1379 |
.SH COPYRIGHT |
| 1380 |
.IX Header "COPYRIGHT" |
| 1381 |
Copyright (C) 1997\-2001 Damian Conway. All rights reserved. |
| 1382 |
.PP |
| 1383 |
Copyright (C) 2009 Adam Kennedy. |
| 1384 |
.PP |
| 1385 |
Copyright (C) 2015, 2020, 2022 Steve Hay and other contributors. All rights |
| 1386 |
reserved. |
| 1387 |
.SH LICENCE |
| 1388 |
.IX Header "LICENCE" |
| 1389 |
This module is free software; you can redistribute it and/or modify it under the |
| 1390 |
same terms as Perl itself, i.e. under the terms of either the GNU General Public |
| 1391 |
License or the Artistic License, as specified in the \fILICENCE\fR file. |
| 1392 |
.SH VERSION |
| 1393 |
.IX Header "VERSION" |
| 1394 |
Version 2.06 |
| 1395 |
.SH DATE |
| 1396 |
.IX Header "DATE" |
| 1397 |
05 Jun 2022 |
| 1398 |
.SH HISTORY |
| 1399 |
.IX Header "HISTORY" |
| 1400 |
See the \fIChanges\fR file. |