| 1 | .\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 |
| 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 "Pod::Parser 3" |
| 132 | .TH Pod::Parser 3 "2002-06-01" "perl v5.8.0" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Pod::Parser \- base class for creating POD filters and translators |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 1 |
| 138 | \& use Pod::Parser; |
| 139 | .Ve |
| 140 | .PP |
| 141 | .Vb 2 |
| 142 | \& package MyParser; |
| 143 | \& @ISA = qw(Pod::Parser); |
| 144 | .Ve |
| 145 | .PP |
| 146 | .Vb 10 |
| 147 | \& sub command { |
| 148 | \& my ($parser, $command, $paragraph, $line_num) = @_; |
| 149 | \& ## Interpret the command and its text; sample actions might be: |
| 150 | \& if ($command eq 'head1') { ... } |
| 151 | \& elsif ($command eq 'head2') { ... } |
| 152 | \& ## ... other commands and their actions |
| 153 | \& my $out_fh = $parser->output_handle(); |
| 154 | \& my $expansion = $parser->interpolate($paragraph, $line_num); |
| 155 | \& print $out_fh $expansion; |
| 156 | \& } |
| 157 | .Ve |
| 158 | .PP |
| 159 | .Vb 6 |
| 160 | \& sub verbatim { |
| 161 | \& my ($parser, $paragraph, $line_num) = @_; |
| 162 | \& ## Format verbatim paragraph; sample actions might be: |
| 163 | \& my $out_fh = $parser->output_handle(); |
| 164 | \& print $out_fh $paragraph; |
| 165 | \& } |
| 166 | .Ve |
| 167 | .PP |
| 168 | .Vb 7 |
| 169 | \& sub textblock { |
| 170 | \& my ($parser, $paragraph, $line_num) = @_; |
| 171 | \& ## Translate/Format this block of text; sample actions might be: |
| 172 | \& my $out_fh = $parser->output_handle(); |
| 173 | \& my $expansion = $parser->interpolate($paragraph, $line_num); |
| 174 | \& print $out_fh $expansion; |
| 175 | \& } |
| 176 | .Ve |
| 177 | .PP |
| 178 | .Vb 8 |
| 179 | \& sub interior_sequence { |
| 180 | \& my ($parser, $seq_command, $seq_argument) = @_; |
| 181 | \& ## Expand an interior sequence; sample actions might be: |
| 182 | \& return "*$seq_argument*" if ($seq_command eq 'B'); |
| 183 | \& return "`$seq_argument'" if ($seq_command eq 'C'); |
| 184 | \& return "_${seq_argument}_'" if ($seq_command eq 'I'); |
| 185 | \& ## ... other sequence commands and their resulting text |
| 186 | \& } |
| 187 | .Ve |
| 188 | .PP |
| 189 | .Vb 1 |
| 190 | \& package main; |
| 191 | .Ve |
| 192 | .PP |
| 193 | .Vb 5 |
| 194 | \& ## Create a parser object and have it parse file whose name was |
| 195 | \& ## given on the command-line (use STDIN if no files were given). |
| 196 | \& $parser = new MyParser(); |
| 197 | \& $parser->parse_from_filehandle(\e*STDIN) if (@ARGV == 0); |
| 198 | \& for (@ARGV) { $parser->parse_from_file($_); } |
| 199 | .Ve |
| 200 | .SH "REQUIRES" |
| 201 | .IX Header "REQUIRES" |
| 202 | perl5.005, Pod::InputObjects, Exporter, Symbol, Carp |
| 203 | .SH "EXPORTS" |
| 204 | .IX Header "EXPORTS" |
| 205 | Nothing. |
| 206 | .SH "DESCRIPTION" |
| 207 | .IX Header "DESCRIPTION" |
| 208 | \&\fBPod::Parser\fR is a base class for creating \s-1POD\s0 filters and translators. |
| 209 | It handles most of the effort involved with parsing the \s-1POD\s0 sections |
| 210 | from an input stream, leaving subclasses free to be concerned only with |
| 211 | performing the actual translation of text. |
| 212 | .PP |
| 213 | \&\fBPod::Parser\fR parses PODs, and makes method calls to handle the various |
| 214 | components of the \s-1POD\s0. Subclasses of \fBPod::Parser\fR override these methods |
| 215 | to translate the \s-1POD\s0 into whatever output format they desire. |
| 216 | .SH "QUICK OVERVIEW" |
| 217 | .IX Header "QUICK OVERVIEW" |
| 218 | To create a \s-1POD\s0 filter for translating \s-1POD\s0 documentation into some other |
| 219 | format, you create a subclass of \fBPod::Parser\fR which typically overrides |
| 220 | just the base class implementation for the following methods: |
| 221 | .IP "\(bu" 2 |
| 222 | \&\fB\f(BIcommand()\fB\fR |
| 223 | .IP "\(bu" 2 |
| 224 | \&\fB\f(BIverbatim()\fB\fR |
| 225 | .IP "\(bu" 2 |
| 226 | \&\fB\f(BItextblock()\fB\fR |
| 227 | .IP "\(bu" 2 |
| 228 | \&\fB\f(BIinterior_sequence()\fB\fR |
| 229 | .PP |
| 230 | You may also want to override the \fB\f(BIbegin_input()\fB\fR and \fB\f(BIend_input()\fB\fR |
| 231 | methods for your subclass (to perform any needed per-file and/or |
| 232 | per-document initialization or cleanup). |
| 233 | .PP |
| 234 | If you need to perform any preprocesssing of input before it is parsed |
| 235 | you may want to override one or more of \fB\f(BIpreprocess_line()\fB\fR and/or |
| 236 | \&\fB\f(BIpreprocess_paragraph()\fB\fR. |
| 237 | .PP |
| 238 | Sometimes it may be necessary to make more than one pass over the input |
| 239 | files. If this is the case you have several options. You can make the |
| 240 | first pass using \fBPod::Parser\fR and override your methods to store the |
| 241 | intermediate results in memory somewhere for the \fB\f(BIend_pod()\fB\fR method to |
| 242 | process. You could use \fBPod::Parser\fR for several passes with an |
| 243 | appropriate state variable to control the operation for each pass. If |
| 244 | your input source can't be reset to start at the beginning, you can |
| 245 | store it in some other structure as a string or an array and have that |
| 246 | structure implement a \fB\f(BIgetline()\fB\fR method (which is all that |
| 247 | \&\fB\f(BIparse_from_filehandle()\fB\fR uses to read input). |
| 248 | .PP |
| 249 | Feel free to add any member data fields you need to keep track of things |
| 250 | like current font, indentation, horizontal or vertical position, or |
| 251 | whatever else you like. Be sure to read \*(L"\s-1PRIVATE\s0 \s-1METHODS\s0 \s-1AND\s0 \s-1DATA\s0\*(R" |
| 252 | to avoid name collisions. |
| 253 | .PP |
| 254 | For the most part, the \fBPod::Parser\fR base class should be able to |
| 255 | do most of the input parsing for you and leave you free to worry about |
| 256 | how to intepret the commands and translate the result. |
| 257 | .PP |
| 258 | Note that all we have described here in this quick overview is the |
| 259 | simplest most straightforward use of \fBPod::Parser\fR to do stream-based |
| 260 | parsing. It is also possible to use the \fBPod::Parser::parse_text\fR function |
| 261 | to do more sophisticated tree-based parsing. See \*(L"\s-1TREE\-BASED\s0 \s-1PARSING\s0\*(R". |
| 262 | .SH "PARSING OPTIONS" |
| 263 | .IX Header "PARSING OPTIONS" |
| 264 | A \fIparse-option\fR is simply a named option of \fBPod::Parser\fR with a |
| 265 | value that corresponds to a certain specified behavior. These various |
| 266 | behaviors of \fBPod::Parser\fR may be enabled/disabled by setting |
| 267 | or unsetting one or more \fIparse-options\fR using the \fB\f(BIparseopts()\fB\fR method. |
| 268 | The set of currently accepted parse-options is as follows: |
| 269 | .IP "\fB\-want_nonPODs\fR (default: unset)" 3 |
| 270 | .IX Item "-want_nonPODs (default: unset)" |
| 271 | Normally (by default) \fBPod::Parser\fR will only provide access to |
| 272 | the \s-1POD\s0 sections of the input. Input paragraphs that are not part |
| 273 | of the POD-format documentation are not made available to the caller |
| 274 | (not even using \fB\f(BIpreprocess_paragraph()\fB\fR). Setting this option to a |
| 275 | non\-empty, non-zero value will allow \fB\f(BIpreprocess_paragraph()\fB\fR to see |
| 276 | non-POD sections of the input as well as \s-1POD\s0 sections. The \fB\f(BIcutting()\fB\fR |
| 277 | method can be used to determine if the corresponding paragraph is a \s-1POD\s0 |
| 278 | paragraph, or some other input paragraph. |
| 279 | .IP "\fB\-process_cut_cmd\fR (default: unset)" 3 |
| 280 | .IX Item "-process_cut_cmd (default: unset)" |
| 281 | Normally (by default) \fBPod::Parser\fR handles the \f(CW\*(C`=cut\*(C'\fR \s-1POD\s0 directive |
| 282 | by itself and does not pass it on to the caller for processing. Setting |
| 283 | this option to a non\-empty, non-zero value will cause \fBPod::Parser\fR to |
| 284 | pass the \f(CW\*(C`=cut\*(C'\fR directive to the caller just like any other \s-1POD\s0 command |
| 285 | (and hence it may be processed by the \fB\f(BIcommand()\fB\fR method). |
| 286 | .Sp |
| 287 | \&\fBPod::Parser\fR will still interpret the \f(CW\*(C`=cut\*(C'\fR directive to mean that |
| 288 | \&\*(L"cutting mode\*(R" has been (re)entered, but the caller will get a chance |
| 289 | to capture the actual \f(CW\*(C`=cut\*(C'\fR paragraph itself for whatever purpose |
| 290 | it desires. |
| 291 | .IP "\fB\-warnings\fR (default: unset)" 3 |
| 292 | .IX Item "-warnings (default: unset)" |
| 293 | Normally (by default) \fBPod::Parser\fR recognizes a bare minimum of |
| 294 | pod syntax errors and warnings and issues diagnostic messages |
| 295 | for errors, but not for warnings. (Use \fBPod::Checker\fR to do more |
| 296 | thorough checking of \s-1POD\s0 syntax.) Setting this option to a non\-empty, |
| 297 | non-zero value will cause \fBPod::Parser\fR to issue diagnostics for |
| 298 | the few warnings it recognizes as well as the errors. |
| 299 | .PP |
| 300 | Please see \*(L"\fIparseopts()\fR\*(R" for a complete description of the interface |
| 301 | for the setting and unsetting of parse\-options. |
| 302 | .SH "RECOMMENDED SUBROUTINE/METHOD OVERRIDES" |
| 303 | .IX Header "RECOMMENDED SUBROUTINE/METHOD OVERRIDES" |
| 304 | \&\fBPod::Parser\fR provides several methods which most subclasses will probably |
| 305 | want to override. These methods are as follows: |
| 306 | .SH "\fB\fP\f(BIcommand()\fP\fB\fP" |
| 307 | .IX Header "command()" |
| 308 | .Vb 1 |
| 309 | \& $parser->command($cmd,$text,$line_num,$pod_para); |
| 310 | .Ve |
| 311 | .PP |
| 312 | This method should be overridden by subclasses to take the appropriate |
| 313 | action when a \s-1POD\s0 command paragraph (denoted by a line beginning with |
| 314 | \&\*(L"=\*(R") is encountered. When such a \s-1POD\s0 directive is seen in the input, |
| 315 | this method is called and is passed: |
| 316 | .ie n .IP "$cmd" 3 |
| 317 | .el .IP "\f(CW$cmd\fR" 3 |
| 318 | .IX Item "$cmd" |
| 319 | the name of the command for this \s-1POD\s0 paragraph |
| 320 | .ie n .IP "$text" 3 |
| 321 | .el .IP "\f(CW$text\fR" 3 |
| 322 | .IX Item "$text" |
| 323 | the paragraph text for the given \s-1POD\s0 paragraph command. |
| 324 | .ie n .IP "$line_num" 3 |
| 325 | .el .IP "\f(CW$line_num\fR" 3 |
| 326 | .IX Item "$line_num" |
| 327 | the line-number of the beginning of the paragraph |
| 328 | .ie n .IP "$pod_para" 3 |
| 329 | .el .IP "\f(CW$pod_para\fR" 3 |
| 330 | .IX Item "$pod_para" |
| 331 | a reference to a \f(CW\*(C`Pod::Paragraph\*(C'\fR object which contains further |
| 332 | information about the paragraph command (see Pod::InputObjects |
| 333 | for details). |
| 334 | .PP |
| 335 | \&\fBNote\fR that this method \fIis\fR called for \f(CW\*(C`=pod\*(C'\fR paragraphs. |
| 336 | .PP |
| 337 | The base class implementation of this method simply treats the raw \s-1POD\s0 |
| 338 | command as normal block of paragraph text (invoking the \fB\f(BItextblock()\fB\fR |
| 339 | method with the command paragraph). |
| 340 | .SH "\fB\fP\f(BIverbatim()\fP\fB\fP" |
| 341 | .IX Header "verbatim()" |
| 342 | .Vb 1 |
| 343 | \& $parser->verbatim($text,$line_num,$pod_para); |
| 344 | .Ve |
| 345 | .PP |
| 346 | This method may be overridden by subclasses to take the appropriate |
| 347 | action when a block of verbatim text is encountered. It is passed the |
| 348 | following parameters: |
| 349 | .ie n .IP "$text" 3 |
| 350 | .el .IP "\f(CW$text\fR" 3 |
| 351 | .IX Item "$text" |
| 352 | the block of text for the verbatim paragraph |
| 353 | .ie n .IP "$line_num" 3 |
| 354 | .el .IP "\f(CW$line_num\fR" 3 |
| 355 | .IX Item "$line_num" |
| 356 | the line-number of the beginning of the paragraph |
| 357 | .ie n .IP "$pod_para" 3 |
| 358 | .el .IP "\f(CW$pod_para\fR" 3 |
| 359 | .IX Item "$pod_para" |
| 360 | a reference to a \f(CW\*(C`Pod::Paragraph\*(C'\fR object which contains further |
| 361 | information about the paragraph (see Pod::InputObjects |
| 362 | for details). |
| 363 | .PP |
| 364 | The base class implementation of this method simply prints the textblock |
| 365 | (unmodified) to the output filehandle. |
| 366 | .SH "\fB\fP\f(BItextblock()\fP\fB\fP" |
| 367 | .IX Header "textblock()" |
| 368 | .Vb 1 |
| 369 | \& $parser->textblock($text,$line_num,$pod_para); |
| 370 | .Ve |
| 371 | .PP |
| 372 | This method may be overridden by subclasses to take the appropriate |
| 373 | action when a normal block of \s-1POD\s0 text is encountered (although the base |
| 374 | class method will usually do what you want). It is passed the following |
| 375 | parameters: |
| 376 | .ie n .IP "$text" 3 |
| 377 | .el .IP "\f(CW$text\fR" 3 |
| 378 | .IX Item "$text" |
| 379 | the block of text for the a \s-1POD\s0 paragraph |
| 380 | .ie n .IP "$line_num" 3 |
| 381 | .el .IP "\f(CW$line_num\fR" 3 |
| 382 | .IX Item "$line_num" |
| 383 | the line-number of the beginning of the paragraph |
| 384 | .ie n .IP "$pod_para" 3 |
| 385 | .el .IP "\f(CW$pod_para\fR" 3 |
| 386 | .IX Item "$pod_para" |
| 387 | a reference to a \f(CW\*(C`Pod::Paragraph\*(C'\fR object which contains further |
| 388 | information about the paragraph (see Pod::InputObjects |
| 389 | for details). |
| 390 | .PP |
| 391 | In order to process interior sequences, subclasses implementations of |
| 392 | this method will probably want to invoke either \fB\f(BIinterpolate()\fB\fR or |
| 393 | \&\fB\f(BIparse_text()\fB\fR, passing it the text block \f(CW$text\fR, and the corresponding |
| 394 | line number in \f(CW$line_num\fR, and then perform any desired processing upon |
| 395 | the returned result. |
| 396 | .PP |
| 397 | The base class implementation of this method simply prints the text block |
| 398 | as it occurred in the input stream). |
| 399 | .SH "\fB\fP\f(BIinterior_sequence()\fP\fB\fP" |
| 400 | .IX Header "interior_sequence()" |
| 401 | .Vb 1 |
| 402 | \& $parser->interior_sequence($seq_cmd,$seq_arg,$pod_seq); |
| 403 | .Ve |
| 404 | .PP |
| 405 | This method should be overridden by subclasses to take the appropriate |
| 406 | action when an interior sequence is encountered. An interior sequence is |
| 407 | an embedded command within a block of text which appears as a command |
| 408 | name (usually a single uppercase character) followed immediately by a |
| 409 | string of text which is enclosed in angle brackets. This method is |
| 410 | passed the sequence command \f(CW$seq_cmd\fR and the corresponding text |
| 411 | \&\f(CW$seq_arg\fR. It is invoked by the \fB\f(BIinterpolate()\fB\fR method for each interior |
| 412 | sequence that occurs in the string that it is passed. It should return |
| 413 | the desired text string to be used in place of the interior sequence. |
| 414 | The \f(CW$pod_seq\fR argument is a reference to a \f(CW\*(C`Pod::InteriorSequence\*(C'\fR |
| 415 | object which contains further information about the interior sequence. |
| 416 | Please see Pod::InputObjects for details if you need to access this |
| 417 | additional information. |
| 418 | .PP |
| 419 | Subclass implementations of this method may wish to invoke the |
| 420 | \&\fB\f(BInested()\fB\fR method of \f(CW$pod_seq\fR to see if it is nested inside |
| 421 | some other interior-sequence (and if so, which kind). |
| 422 | .PP |
| 423 | The base class implementation of the \fB\f(BIinterior_sequence()\fB\fR method |
| 424 | simply returns the raw text of the interior sequence (as it occurred |
| 425 | in the input) to the caller. |
| 426 | .SH "OPTIONAL SUBROUTINE/METHOD OVERRIDES" |
| 427 | .IX Header "OPTIONAL SUBROUTINE/METHOD OVERRIDES" |
| 428 | \&\fBPod::Parser\fR provides several methods which subclasses may want to override |
| 429 | to perform any special pre/post\-processing. These methods do \fInot\fR have to |
| 430 | be overridden, but it may be useful for subclasses to take advantage of them. |
| 431 | .SH "\fB\fP\f(BInew()\fP\fB\fP" |
| 432 | .IX Header "new()" |
| 433 | .Vb 1 |
| 434 | \& my $parser = Pod::Parser->new(); |
| 435 | .Ve |
| 436 | .PP |
| 437 | This is the constructor for \fBPod::Parser\fR and its subclasses. You |
| 438 | \&\fIdo not\fR need to override this method! It is capable of constructing |
| 439 | subclass objects as well as base class objects, provided you use |
| 440 | any of the following constructor invocation styles: |
| 441 | .PP |
| 442 | .Vb 3 |
| 443 | \& my $parser1 = MyParser->new(); |
| 444 | \& my $parser2 = new MyParser(); |
| 445 | \& my $parser3 = $parser2->new(); |
| 446 | .Ve |
| 447 | .PP |
| 448 | where \f(CW\*(C`MyParser\*(C'\fR is some subclass of \fBPod::Parser\fR. |
| 449 | .PP |
| 450 | Using the syntax \f(CW\*(C`MyParser::new()\*(C'\fR to invoke the constructor is \fInot\fR |
| 451 | recommended, but if you insist on being able to do this, then the |
| 452 | subclass \fIwill\fR need to override the \fB\f(BInew()\fB\fR constructor method. If |
| 453 | you do override the constructor, you \fImust\fR be sure to invoke the |
| 454 | \&\fB\f(BIinitialize()\fB\fR method of the newly blessed object. |
| 455 | .PP |
| 456 | Using any of the above invocations, the first argument to the |
| 457 | constructor is always the corresponding package name (or object |
| 458 | reference). No other arguments are required, but if desired, an |
| 459 | associative array (or hash\-table) my be passed to the \fB\f(BInew()\fB\fR |
| 460 | constructor, as in: |
| 461 | .PP |
| 462 | .Vb 2 |
| 463 | \& my $parser1 = MyParser->new( MYDATA => $value1, MOREDATA => $value2 ); |
| 464 | \& my $parser2 = new MyParser( -myflag => 1 ); |
| 465 | .Ve |
| 466 | .PP |
| 467 | All arguments passed to the \fB\f(BInew()\fB\fR constructor will be treated as |
| 468 | key/value pairs in a hash\-table. The newly constructed object will be |
| 469 | initialized by copying the contents of the given hash-table (which may |
| 470 | have been empty). The \fB\f(BInew()\fB\fR constructor for this class and all of its |
| 471 | subclasses returns a blessed reference to the initialized object (hash\-table). |
| 472 | .SH "\fB\fP\f(BIinitialize()\fP\fB\fP" |
| 473 | .IX Header "initialize()" |
| 474 | .Vb 1 |
| 475 | \& $parser->initialize(); |
| 476 | .Ve |
| 477 | .PP |
| 478 | This method performs any necessary object initialization. It takes no |
| 479 | arguments (other than the object instance of course, which is typically |
| 480 | copied to a local variable named \f(CW$self\fR). If subclasses override this |
| 481 | method then they \fImust\fR be sure to invoke \f(CW\*(C`$self\->SUPER::initialize()\*(C'\fR. |
| 482 | .SH "\fB\fP\f(BIbegin_pod()\fP\fB\fP" |
| 483 | .IX Header "begin_pod()" |
| 484 | .Vb 1 |
| 485 | \& $parser->begin_pod(); |
| 486 | .Ve |
| 487 | .PP |
| 488 | This method is invoked at the beginning of processing for each \s-1POD\s0 |
| 489 | document that is encountered in the input. Subclasses should override |
| 490 | this method to perform any per-document initialization. |
| 491 | .SH "\fB\fP\f(BIbegin_input()\fP\fB\fP" |
| 492 | .IX Header "begin_input()" |
| 493 | .Vb 1 |
| 494 | \& $parser->begin_input(); |
| 495 | .Ve |
| 496 | .PP |
| 497 | This method is invoked by \fB\f(BIparse_from_filehandle()\fB\fR immediately \fIbefore\fR |
| 498 | processing input from a filehandle. The base class implementation does |
| 499 | nothing, however, subclasses may override it to perform any per-file |
| 500 | initializations. |
| 501 | .PP |
| 502 | Note that if multiple files are parsed for a single \s-1POD\s0 document |
| 503 | (perhaps the result of some future \f(CW\*(C`=include\*(C'\fR directive) this method |
| 504 | is invoked for every file that is parsed. If you wish to perform certain |
| 505 | initializations once per document, then you should use \fB\f(BIbegin_pod()\fB\fR. |
| 506 | .SH "\fB\fP\f(BIend_input()\fP\fB\fP" |
| 507 | .IX Header "end_input()" |
| 508 | .Vb 1 |
| 509 | \& $parser->end_input(); |
| 510 | .Ve |
| 511 | .PP |
| 512 | This method is invoked by \fB\f(BIparse_from_filehandle()\fB\fR immediately \fIafter\fR |
| 513 | processing input from a filehandle. The base class implementation does |
| 514 | nothing, however, subclasses may override it to perform any per-file |
| 515 | cleanup actions. |
| 516 | .PP |
| 517 | Please note that if multiple files are parsed for a single \s-1POD\s0 document |
| 518 | (perhaps the result of some kind of \f(CW\*(C`=include\*(C'\fR directive) this method |
| 519 | is invoked for every file that is parsed. If you wish to perform certain |
| 520 | cleanup actions once per document, then you should use \fB\f(BIend_pod()\fB\fR. |
| 521 | .SH "\fB\fP\f(BIend_pod()\fP\fB\fP" |
| 522 | .IX Header "end_pod()" |
| 523 | .Vb 1 |
| 524 | \& $parser->end_pod(); |
| 525 | .Ve |
| 526 | .PP |
| 527 | This method is invoked at the end of processing for each \s-1POD\s0 document |
| 528 | that is encountered in the input. Subclasses should override this method |
| 529 | to perform any per-document finalization. |
| 530 | .SH "\fB\fP\f(BIpreprocess_line()\fP\fB\fP" |
| 531 | .IX Header "preprocess_line()" |
| 532 | .Vb 1 |
| 533 | \& $textline = $parser->preprocess_line($text, $line_num); |
| 534 | .Ve |
| 535 | .PP |
| 536 | This method should be overridden by subclasses that wish to perform |
| 537 | any kind of preprocessing for each \fIline\fR of input (\fIbefore\fR it has |
| 538 | been determined whether or not it is part of a \s-1POD\s0 paragraph). The |
| 539 | parameter \f(CW$text\fR is the input line; and the parameter \f(CW$line_num\fR is |
| 540 | the line number of the corresponding text line. |
| 541 | .PP |
| 542 | The value returned should correspond to the new text to use in its |
| 543 | place. If the empty string or an undefined value is returned then no |
| 544 | further processing will be performed for this line. |
| 545 | .PP |
| 546 | Please note that the \fB\f(BIpreprocess_line()\fB\fR method is invoked \fIbefore\fR |
| 547 | the \fB\f(BIpreprocess_paragraph()\fB\fR method. After all (possibly preprocessed) |
| 548 | lines in a paragraph have been assembled together and it has been |
| 549 | determined that the paragraph is part of the \s-1POD\s0 documentation from one |
| 550 | of the selected sections, then \fB\f(BIpreprocess_paragraph()\fB\fR is invoked. |
| 551 | .PP |
| 552 | The base class implementation of this method returns the given text. |
| 553 | .SH "\fB\fP\f(BIpreprocess_paragraph()\fP\fB\fP" |
| 554 | .IX Header "preprocess_paragraph()" |
| 555 | .Vb 1 |
| 556 | \& $textblock = $parser->preprocess_paragraph($text, $line_num); |
| 557 | .Ve |
| 558 | .PP |
| 559 | This method should be overridden by subclasses that wish to perform any |
| 560 | kind of preprocessing for each block (paragraph) of \s-1POD\s0 documentation |
| 561 | that appears in the input stream. The parameter \f(CW$text\fR is the \s-1POD\s0 |
| 562 | paragraph from the input file; and the parameter \f(CW$line_num\fR is the |
| 563 | line number for the beginning of the corresponding paragraph. |
| 564 | .PP |
| 565 | The value returned should correspond to the new text to use in its |
| 566 | place If the empty string is returned or an undefined value is |
| 567 | returned, then the given \f(CW$text\fR is ignored (not processed). |
| 568 | .PP |
| 569 | This method is invoked after gathering up all the lines in a paragraph |
| 570 | and after determining the cutting state of the paragraph, |
| 571 | but before trying to further parse or interpret them. After |
| 572 | \&\fB\f(BIpreprocess_paragraph()\fB\fR returns, the current cutting state (which |
| 573 | is returned by \f(CW\*(C`$self\->cutting()\*(C'\fR) is examined. If it evaluates |
| 574 | to true then input text (including the given \f(CW$text\fR) is cut (not |
| 575 | processed) until the next \s-1POD\s0 directive is encountered. |
| 576 | .PP |
| 577 | Please note that the \fB\f(BIpreprocess_line()\fB\fR method is invoked \fIbefore\fR |
| 578 | the \fB\f(BIpreprocess_paragraph()\fB\fR method. After all (possibly preprocessed) |
| 579 | lines in a paragraph have been assembled together and either it has been |
| 580 | determined that the paragraph is part of the \s-1POD\s0 documentation from one |
| 581 | of the selected sections or the \f(CW\*(C`\-want_nonPODs\*(C'\fR option is true, |
| 582 | then \fB\f(BIpreprocess_paragraph()\fB\fR is invoked. |
| 583 | .PP |
| 584 | The base class implementation of this method returns the given text. |
| 585 | .SH "METHODS FOR PARSING AND PROCESSING" |
| 586 | .IX Header "METHODS FOR PARSING AND PROCESSING" |
| 587 | \&\fBPod::Parser\fR provides several methods to process input text. These |
| 588 | methods typically won't need to be overridden (and in some cases they |
| 589 | can't be overridden), but subclasses may want to invoke them to exploit |
| 590 | their functionality. |
| 591 | .SH "\fB\fP\f(BIparse_text()\fP\fB\fP" |
| 592 | .IX Header "parse_text()" |
| 593 | .Vb 3 |
| 594 | \& $ptree1 = $parser->parse_text($text, $line_num); |
| 595 | \& $ptree2 = $parser->parse_text({%opts}, $text, $line_num); |
| 596 | \& $ptree3 = $parser->parse_text(\e%opts, $text, $line_num); |
| 597 | .Ve |
| 598 | .PP |
| 599 | This method is useful if you need to perform your own interpolation |
| 600 | of interior sequences and can't rely upon \fBinterpolate\fR to expand |
| 601 | them in simple bottom-up order. |
| 602 | .PP |
| 603 | The parameter \f(CW$text\fR is a string or block of text to be parsed |
| 604 | for interior sequences; and the parameter \f(CW$line_num\fR is the |
| 605 | line number curresponding to the beginning of \f(CW$text\fR. |
| 606 | .PP |
| 607 | \&\fB\f(BIparse_text()\fB\fR will parse the given text into a parse-tree of \*(L"nodes.\*(R" |
| 608 | and interior\-sequences. Each \*(L"node\*(R" in the parse tree is either a |
| 609 | text\-string, or a \fBPod::InteriorSequence\fR. The result returned is a |
| 610 | parse-tree of type \fBPod::ParseTree\fR. Please see Pod::InputObjects |
| 611 | for more information about \fBPod::InteriorSequence\fR and \fBPod::ParseTree\fR. |
| 612 | .PP |
| 613 | If desired, an optional hash-ref may be specified as the first argument |
| 614 | to customize certain aspects of the parse-tree that is created and |
| 615 | returned. The set of recognized option keywords are: |
| 616 | .IP "\fB\-expand_seq\fR => \fIcode-ref\fR|\fImethod-name\fR" 3 |
| 617 | .IX Item "-expand_seq => code-ref|method-name" |
| 618 | Normally, the parse-tree returned by \fB\f(BIparse_text()\fB\fR will contain an |
| 619 | unexpanded \f(CW\*(C`Pod::InteriorSequence\*(C'\fR object for each interior-sequence |
| 620 | encountered. Specifying \fB\-expand_seq\fR tells \fB\f(BIparse_text()\fB\fR to \*(L"expand\*(R" |
| 621 | every interior-sequence it sees by invoking the referenced function |
| 622 | (or named method of the parser object) and using the return value as the |
| 623 | expanded result. |
| 624 | .Sp |
| 625 | If a subroutine reference was given, it is invoked as: |
| 626 | .Sp |
| 627 | .Vb 1 |
| 628 | \& &$code_ref( $parser, $sequence ) |
| 629 | .Ve |
| 630 | .Sp |
| 631 | and if a method-name was given, it is invoked as: |
| 632 | .Sp |
| 633 | .Vb 1 |
| 634 | \& $parser->method_name( $sequence ) |
| 635 | .Ve |
| 636 | .Sp |
| 637 | where \f(CW$parser\fR is a reference to the parser object, and \f(CW$sequence\fR |
| 638 | is a reference to the interior-sequence object. |
| 639 | [\fI\s-1NOTE\s0\fR: If the \fB\f(BIinterior_sequence()\fB\fR method is specified, then it is |
| 640 | invoked according to the interface specified in \*(L"\fIinterior_sequence()\fR\*(R"]. |
| 641 | .IP "\fB\-expand_text\fR => \fIcode-ref\fR|\fImethod-name\fR" 3 |
| 642 | .IX Item "-expand_text => code-ref|method-name" |
| 643 | Normally, the parse-tree returned by \fB\f(BIparse_text()\fB\fR will contain a |
| 644 | text-string for each contiguous sequence of characters outside of an |
| 645 | interior\-sequence. Specifying \fB\-expand_text\fR tells \fB\f(BIparse_text()\fB\fR to |
| 646 | \&\*(L"preprocess\*(R" every such text-string it sees by invoking the referenced |
| 647 | function (or named method of the parser object) and using the return value |
| 648 | as the preprocessed (or \*(L"expanded\*(R") result. [Note that if the result is |
| 649 | an interior\-sequence, then it will \fInot\fR be expanded as specified by the |
| 650 | \&\fB\-expand_seq\fR option; Any such recursive expansion needs to be handled by |
| 651 | the specified callback routine.] |
| 652 | .Sp |
| 653 | If a subroutine reference was given, it is invoked as: |
| 654 | .Sp |
| 655 | .Vb 1 |
| 656 | \& &$code_ref( $parser, $text, $ptree_node ) |
| 657 | .Ve |
| 658 | .Sp |
| 659 | and if a method-name was given, it is invoked as: |
| 660 | .Sp |
| 661 | .Vb 1 |
| 662 | \& $parser->method_name( $text, $ptree_node ) |
| 663 | .Ve |
| 664 | .Sp |
| 665 | where \f(CW$parser\fR is a reference to the parser object, \f(CW$text\fR is the |
| 666 | text-string encountered, and \f(CW$ptree_node\fR is a reference to the current |
| 667 | node in the parse-tree (usually an interior-sequence object or else the |
| 668 | top-level node of the parse\-tree). |
| 669 | .IP "\fB\-expand_ptree\fR => \fIcode-ref\fR|\fImethod-name\fR" 3 |
| 670 | .IX Item "-expand_ptree => code-ref|method-name" |
| 671 | Rather than returning a \f(CW\*(C`Pod::ParseTree\*(C'\fR, pass the parse-tree as an |
| 672 | argument to the referenced subroutine (or named method of the parser |
| 673 | object) and return the result instead of the parse-tree object. |
| 674 | .Sp |
| 675 | If a subroutine reference was given, it is invoked as: |
| 676 | .Sp |
| 677 | .Vb 1 |
| 678 | \& &$code_ref( $parser, $ptree ) |
| 679 | .Ve |
| 680 | .Sp |
| 681 | and if a method-name was given, it is invoked as: |
| 682 | .Sp |
| 683 | .Vb 1 |
| 684 | \& $parser->method_name( $ptree ) |
| 685 | .Ve |
| 686 | .Sp |
| 687 | where \f(CW$parser\fR is a reference to the parser object, and \f(CW$ptree\fR |
| 688 | is a reference to the parse-tree object. |
| 689 | .SH "\fB\fP\f(BIinterpolate()\fP\fB\fP" |
| 690 | .IX Header "interpolate()" |
| 691 | .Vb 1 |
| 692 | \& $textblock = $parser->interpolate($text, $line_num); |
| 693 | .Ve |
| 694 | .PP |
| 695 | This method translates all text (including any embedded interior sequences) |
| 696 | in the given text string \f(CW$text\fR and returns the interpolated result. The |
| 697 | parameter \f(CW$line_num\fR is the line number corresponding to the beginning |
| 698 | of \f(CW$text\fR. |
| 699 | .PP |
| 700 | \&\fB\f(BIinterpolate()\fB\fR merely invokes a private method to recursively expand |
| 701 | nested interior sequences in bottom-up order (innermost sequences are |
| 702 | expanded first). If there is a need to expand nested sequences in |
| 703 | some alternate order, use \fBparse_text\fR instead. |
| 704 | .SH "\fB\fP\f(BIparse_from_filehandle()\fP\fB\fP" |
| 705 | .IX Header "parse_from_filehandle()" |
| 706 | .Vb 1 |
| 707 | \& $parser->parse_from_filehandle($in_fh,$out_fh); |
| 708 | .Ve |
| 709 | .PP |
| 710 | This method takes an input filehandle (which is assumed to already be |
| 711 | opened for reading) and reads the entire input stream looking for blocks |
| 712 | (paragraphs) of \s-1POD\s0 documentation to be processed. If no first argument |
| 713 | is given the default input filehandle \f(CW\*(C`STDIN\*(C'\fR is used. |
| 714 | .PP |
| 715 | The \f(CW$in_fh\fR parameter may be any object that provides a \fB\f(BIgetline()\fB\fR |
| 716 | method to retrieve a single line of input text (hence, an appropriate |
| 717 | wrapper object could be used to parse PODs from a single string or an |
| 718 | array of strings). |
| 719 | .PP |
| 720 | Using \f(CW\*(C`$in_fh\->getline()\*(C'\fR, input is read line-by-line and assembled |
| 721 | into paragraphs or \*(L"blocks\*(R" (which are separated by lines containing |
| 722 | nothing but whitespace). For each block of \s-1POD\s0 documentation |
| 723 | encountered it will invoke a method to parse the given paragraph. |
| 724 | .PP |
| 725 | If a second argument is given then it should correspond to a filehandle where |
| 726 | output should be sent (otherwise the default output filehandle is |
| 727 | \&\f(CW\*(C`STDOUT\*(C'\fR if no output filehandle is currently in use). |
| 728 | .PP |
| 729 | \&\fB\s-1NOTE:\s0\fR For performance reasons, this method caches the input stream at |
| 730 | the top of the stack in a local variable. Any attempts by clients to |
| 731 | change the stack contents during processing when in the midst executing |
| 732 | of this method \fIwill not affect\fR the input stream used by the current |
| 733 | invocation of this method. |
| 734 | .PP |
| 735 | This method does \fInot\fR usually need to be overridden by subclasses. |
| 736 | .SH "\fB\fP\f(BIparse_from_file()\fP\fB\fP" |
| 737 | .IX Header "parse_from_file()" |
| 738 | .Vb 1 |
| 739 | \& $parser->parse_from_file($filename,$outfile); |
| 740 | .Ve |
| 741 | .PP |
| 742 | This method takes a filename and does the following: |
| 743 | .IP "\(bu" 2 |
| 744 | opens the input and output files for reading |
| 745 | (creating the appropriate filehandles) |
| 746 | .IP "\(bu" 2 |
| 747 | invokes the \fB\f(BIparse_from_filehandle()\fB\fR method passing it the |
| 748 | corresponding input and output filehandles. |
| 749 | .IP "\(bu" 2 |
| 750 | closes the input and output files. |
| 751 | .PP |
| 752 | If the special input filename \*(L"\-\*(R" or \*(L"<&STDIN\*(R" is given then the \s-1STDIN\s0 |
| 753 | filehandle is used for input (and no open or close is performed). If no |
| 754 | input filename is specified then \*(L"\-\*(R" is implied. |
| 755 | .PP |
| 756 | If a second argument is given then it should be the name of the desired |
| 757 | output file. If the special output filename \*(L"\-\*(R" or \*(L">&STDOUT\*(R" is given |
| 758 | then the \s-1STDOUT\s0 filehandle is used for output (and no open or close is |
| 759 | performed). If the special output filename \*(L">&STDERR\*(R" is given then the |
| 760 | \&\s-1STDERR\s0 filehandle is used for output (and no open or close is |
| 761 | performed). If no output filehandle is currently in use and no output |
| 762 | filename is specified, then \*(L"\-\*(R" is implied. |
| 763 | .PP |
| 764 | This method does \fInot\fR usually need to be overridden by subclasses. |
| 765 | .SH "ACCESSOR METHODS" |
| 766 | .IX Header "ACCESSOR METHODS" |
| 767 | Clients of \fBPod::Parser\fR should use the following methods to access |
| 768 | instance data fields: |
| 769 | .SH "\fB\fP\f(BIerrorsub()\fP\fB\fP" |
| 770 | .IX Header "errorsub()" |
| 771 | .Vb 3 |
| 772 | \& $parser->errorsub("method_name"); |
| 773 | \& $parser->errorsub(\e&warn_user); |
| 774 | \& $parser->errorsub(sub { print STDERR, @_ }); |
| 775 | .Ve |
| 776 | .PP |
| 777 | Specifies the method or subroutine to use when printing error messages |
| 778 | about \s-1POD\s0 syntax. The supplied method/subroutine \fImust\fR return \s-1TRUE\s0 upon |
| 779 | successful printing of the message. If \f(CW\*(C`undef\*(C'\fR is given, then the \fBwarn\fR |
| 780 | builtin is used to issue error messages (this is the default behavior). |
| 781 | .PP |
| 782 | .Vb 5 |
| 783 | \& my $errorsub = $parser->errorsub() |
| 784 | \& my $errmsg = "This is an error message!\en" |
| 785 | \& (ref $errorsub) and &{$errorsub}($errmsg) |
| 786 | \& or (defined $errorsub) and $parser->$errorsub($errmsg) |
| 787 | \& or warn($errmsg); |
| 788 | .Ve |
| 789 | .PP |
| 790 | Returns a method name, or else a reference to the user-supplied subroutine |
| 791 | used to print error messages. Returns \f(CW\*(C`undef\*(C'\fR if the \fBwarn\fR builtin |
| 792 | is used to issue error messages (this is the default behavior). |
| 793 | .SH "\fB\fP\f(BIcutting()\fP\fB\fP" |
| 794 | .IX Header "cutting()" |
| 795 | .Vb 1 |
| 796 | \& $boolean = $parser->cutting(); |
| 797 | .Ve |
| 798 | .PP |
| 799 | Returns the current \f(CW\*(C`cutting\*(C'\fR state: a boolean-valued scalar which |
| 800 | evaluates to true if text from the input file is currently being \*(L"cut\*(R" |
| 801 | (meaning it is \fInot\fR considered part of the \s-1POD\s0 document). |
| 802 | .PP |
| 803 | .Vb 1 |
| 804 | \& $parser->cutting($boolean); |
| 805 | .Ve |
| 806 | .PP |
| 807 | Sets the current \f(CW\*(C`cutting\*(C'\fR state to the given value and returns the |
| 808 | result. |
| 809 | .SH "\fB\fP\f(BIparseopts()\fP\fB\fP" |
| 810 | .IX Header "parseopts()" |
| 811 | When invoked with no additional arguments, \fBparseopts\fR returns a hashtable |
| 812 | of all the current parsing options. |
| 813 | .PP |
| 814 | .Vb 3 |
| 815 | \& ## See if we are parsing non-POD sections as well as POD ones |
| 816 | \& my %opts = $parser->parseopts(); |
| 817 | \& $opts{'-want_nonPODs}' and print "-want_nonPODs\en"; |
| 818 | .Ve |
| 819 | .PP |
| 820 | When invoked using a single string, \fBparseopts\fR treats the string as the |
| 821 | name of a parse-option and returns its corresponding value if it exists |
| 822 | (returns \f(CW\*(C`undef\*(C'\fR if it doesn't). |
| 823 | .PP |
| 824 | .Vb 3 |
| 825 | \& ## Did we ask to see '=cut' paragraphs? |
| 826 | \& my $want_cut = $parser->parseopts('-process_cut_cmd'); |
| 827 | \& $want_cut and print "-process_cut_cmd\en"; |
| 828 | .Ve |
| 829 | .PP |
| 830 | When invoked with multiple arguments, \fBparseopts\fR treats them as |
| 831 | key/value pairs and the specified parse-option names are set to the |
| 832 | given values. Any unspecified parse-options are unaffected. |
| 833 | .PP |
| 834 | .Vb 2 |
| 835 | \& ## Set them back to the default |
| 836 | \& $parser->parseopts(-warnings => 0); |
| 837 | .Ve |
| 838 | .PP |
| 839 | When passed a single hash\-ref, \fBparseopts\fR uses that hash to completely |
| 840 | reset the existing parse\-options, all previous parse-option values |
| 841 | are lost. |
| 842 | .PP |
| 843 | .Vb 2 |
| 844 | \& ## Reset all options to default |
| 845 | \& $parser->parseopts( { } ); |
| 846 | .Ve |
| 847 | .PP |
| 848 | See \*(L"\s-1PARSING\s0 \s-1OPTIONS\s0\*(R" for more information on the name and meaning of each |
| 849 | parse-option currently recognized. |
| 850 | .SH "\fB\fP\f(BIoutput_file()\fP\fB\fP" |
| 851 | .IX Header "output_file()" |
| 852 | .Vb 1 |
| 853 | \& $fname = $parser->output_file(); |
| 854 | .Ve |
| 855 | .PP |
| 856 | Returns the name of the output file being written. |
| 857 | .SH "\fB\fP\f(BIoutput_handle()\fP\fB\fP" |
| 858 | .IX Header "output_handle()" |
| 859 | .Vb 1 |
| 860 | \& $fhandle = $parser->output_handle(); |
| 861 | .Ve |
| 862 | .PP |
| 863 | Returns the output filehandle object. |
| 864 | .SH "\fB\fP\f(BIinput_file()\fP\fB\fP" |
| 865 | .IX Header "input_file()" |
| 866 | .Vb 1 |
| 867 | \& $fname = $parser->input_file(); |
| 868 | .Ve |
| 869 | .PP |
| 870 | Returns the name of the input file being read. |
| 871 | .SH "\fB\fP\f(BIinput_handle()\fP\fB\fP" |
| 872 | .IX Header "input_handle()" |
| 873 | .Vb 1 |
| 874 | \& $fhandle = $parser->input_handle(); |
| 875 | .Ve |
| 876 | .PP |
| 877 | Returns the current input filehandle object. |
| 878 | .SH "PRIVATE METHODS AND DATA" |
| 879 | .IX Header "PRIVATE METHODS AND DATA" |
| 880 | \&\fBPod::Parser\fR makes use of several internal methods and data fields |
| 881 | which clients should not need to see or use. For the sake of avoiding |
| 882 | name collisions for client data and methods, these methods and fields |
| 883 | are briefly discussed here. Determined hackers may obtain further |
| 884 | information about them by reading the \fBPod::Parser\fR source code. |
| 885 | .PP |
| 886 | Private data fields are stored in the hash-object whose reference is |
| 887 | returned by the \fB\f(BInew()\fB\fR constructor for this class. The names of all |
| 888 | private methods and data-fields used by \fBPod::Parser\fR begin with a |
| 889 | prefix of \*(L"_\*(R" and match the regular expression \f(CW\*(C`/^_\ew+$/\*(C'\fR. |
| 890 | .SH "TREE-BASED PARSING" |
| 891 | .IX Header "TREE-BASED PARSING" |
| 892 | If straightforward stream-based parsing wont meet your needs (as is |
| 893 | likely the case for tasks such as translating PODs into structured |
| 894 | markup languages like \s-1HTML\s0 and \s-1XML\s0) then you may need to take the |
| 895 | tree-based approach. Rather than doing everything in one pass and |
| 896 | calling the \fB\f(BIinterpolate()\fB\fR method to expand sequences into text, it |
| 897 | may be desirable to instead create a parse-tree using the \fB\f(BIparse_text()\fB\fR |
| 898 | method to return a tree-like structure which may contain an ordered |
| 899 | list of children (each of which may be a text\-string, or a similar |
| 900 | tree-like structure). |
| 901 | .PP |
| 902 | Pay special attention to \*(L"\s-1METHODS\s0 \s-1FOR\s0 \s-1PARSING\s0 \s-1AND\s0 \s-1PROCESSING\s0\*(R" and |
| 903 | to the objects described in Pod::InputObjects. The former describes |
| 904 | the gory details and parameters for how to customize and extend the |
| 905 | parsing behavior of \fBPod::Parser\fR. \fBPod::InputObjects\fR provides |
| 906 | several objects that may all be used interchangeably as parse\-trees. The |
| 907 | most obvious one is the \fBPod::ParseTree\fR object. It defines the basic |
| 908 | interface and functionality that all things trying to be a \s-1POD\s0 parse-tree |
| 909 | should do. A \fBPod::ParseTree\fR is defined such that each \*(L"node\*(R" may be a |
| 910 | text\-string, or a reference to another parse\-tree. Each \fBPod::Paragraph\fR |
| 911 | object and each \fBPod::InteriorSequence\fR object also supports the basic |
| 912 | parse-tree interface. |
| 913 | .PP |
| 914 | The \fB\f(BIparse_text()\fB\fR method takes a given paragraph of text, and |
| 915 | returns a parse-tree that contains one or more children, each of which |
| 916 | may be a text\-string, or an InteriorSequence object. There are also |
| 917 | callback-options that may be passed to \fB\f(BIparse_text()\fB\fR to customize |
| 918 | the way it expands or transforms interior\-sequences, as well as the |
| 919 | returned result. These callbacks can be used to create a parse-tree |
| 920 | with custom-made objects (which may or may not support the parse-tree |
| 921 | interface, depending on how you choose to do it). |
| 922 | .PP |
| 923 | If you wish to turn an entire \s-1POD\s0 document into a parse\-tree, that process |
| 924 | is fairly straightforward. The \fB\f(BIparse_text()\fB\fR method is the key to doing |
| 925 | this successfully. Every paragraph-callback (i.e. the polymorphic methods |
| 926 | for \fB\f(BIcommand()\fB\fR, \fB\f(BIverbatim()\fB\fR, and \fB\f(BItextblock()\fB\fR paragraphs) takes |
| 927 | a \fBPod::Paragraph\fR object as an argument. Each paragraph object has a |
| 928 | \&\fB\f(BIparse_tree()\fB\fR method that can be used to get or set a corresponding |
| 929 | parse\-tree. So for each of those paragraph-callback methods, simply call |
| 930 | \&\fB\f(BIparse_text()\fB\fR with the options you desire, and then use the returned |
| 931 | parse-tree to assign to the given paragraph object. |
| 932 | .PP |
| 933 | That gives you a parse-tree for each paragraph \- so now all you need is |
| 934 | an ordered list of paragraphs. You can maintain that yourself as a data |
| 935 | element in the object/hash. The most straightforward way would be simply |
| 936 | to use an array\-ref, with the desired set of custom \*(L"options\*(R" for each |
| 937 | invocation of \fBparse_text\fR. Let's assume the desired option-set is |
| 938 | given by the hash \f(CW%options\fR. Then we might do something like the |
| 939 | following: |
| 940 | .PP |
| 941 | .Vb 1 |
| 942 | \& package MyPodParserTree; |
| 943 | .Ve |
| 944 | .PP |
| 945 | .Vb 1 |
| 946 | \& @ISA = qw( Pod::Parser ); |
| 947 | .Ve |
| 948 | .PP |
| 949 | .Vb 1 |
| 950 | \& ... |
| 951 | .Ve |
| 952 | .PP |
| 953 | .Vb 4 |
| 954 | \& sub begin_pod { |
| 955 | \& my $self = shift; |
| 956 | \& $self->{'-paragraphs'} = []; ## initialize paragraph list |
| 957 | \& } |
| 958 | .Ve |
| 959 | .PP |
| 960 | .Vb 6 |
| 961 | \& sub command { |
| 962 | \& my ($parser, $command, $paragraph, $line_num, $pod_para) = @_; |
| 963 | \& my $ptree = $parser->parse_text({%options}, $paragraph, ...); |
| 964 | \& $pod_para->parse_tree( $ptree ); |
| 965 | \& push @{ $self->{'-paragraphs'} }, $pod_para; |
| 966 | \& } |
| 967 | .Ve |
| 968 | .PP |
| 969 | .Vb 4 |
| 970 | \& sub verbatim { |
| 971 | \& my ($parser, $paragraph, $line_num, $pod_para) = @_; |
| 972 | \& push @{ $self->{'-paragraphs'} }, $pod_para; |
| 973 | \& } |
| 974 | .Ve |
| 975 | .PP |
| 976 | .Vb 6 |
| 977 | \& sub textblock { |
| 978 | \& my ($parser, $paragraph, $line_num, $pod_para) = @_; |
| 979 | \& my $ptree = $parser->parse_text({%options}, $paragraph, ...); |
| 980 | \& $pod_para->parse_tree( $ptree ); |
| 981 | \& push @{ $self->{'-paragraphs'} }, $pod_para; |
| 982 | \& } |
| 983 | .Ve |
| 984 | .PP |
| 985 | .Vb 1 |
| 986 | \& ... |
| 987 | .Ve |
| 988 | .PP |
| 989 | .Vb 5 |
| 990 | \& package main; |
| 991 | \& ... |
| 992 | \& my $parser = new MyPodParserTree(...); |
| 993 | \& $parser->parse_from_file(...); |
| 994 | \& my $paragraphs_ref = $parser->{'-paragraphs'}; |
| 995 | .Ve |
| 996 | .PP |
| 997 | Of course, in this module\-author's humble opinion, I'd be more inclined to |
| 998 | use the existing \fBPod::ParseTree\fR object than a simple array. That way |
| 999 | everything in it, paragraphs and sequences, all respond to the same core |
| 1000 | interface for all parse-tree nodes. The result would look something like: |
| 1001 | .PP |
| 1002 | .Vb 1 |
| 1003 | \& package MyPodParserTree2; |
| 1004 | .Ve |
| 1005 | .PP |
| 1006 | .Vb 1 |
| 1007 | \& ... |
| 1008 | .Ve |
| 1009 | .PP |
| 1010 | .Vb 4 |
| 1011 | \& sub begin_pod { |
| 1012 | \& my $self = shift; |
| 1013 | \& $self->{'-ptree'} = new Pod::ParseTree; ## initialize parse-tree |
| 1014 | \& } |
| 1015 | .Ve |
| 1016 | .PP |
| 1017 | .Vb 5 |
| 1018 | \& sub parse_tree { |
| 1019 | \& ## convenience method to get/set the parse-tree for the entire POD |
| 1020 | \& (@_ > 1) and $_[0]->{'-ptree'} = $_[1]; |
| 1021 | \& return $_[0]->{'-ptree'}; |
| 1022 | \& } |
| 1023 | .Ve |
| 1024 | .PP |
| 1025 | .Vb 6 |
| 1026 | \& sub command { |
| 1027 | \& my ($parser, $command, $paragraph, $line_num, $pod_para) = @_; |
| 1028 | \& my $ptree = $parser->parse_text({<<options>>}, $paragraph, ...); |
| 1029 | \& $pod_para->parse_tree( $ptree ); |
| 1030 | \& $parser->parse_tree()->append( $pod_para ); |
| 1031 | \& } |
| 1032 | .Ve |
| 1033 | .PP |
| 1034 | .Vb 4 |
| 1035 | \& sub verbatim { |
| 1036 | \& my ($parser, $paragraph, $line_num, $pod_para) = @_; |
| 1037 | \& $parser->parse_tree()->append( $pod_para ); |
| 1038 | \& } |
| 1039 | .Ve |
| 1040 | .PP |
| 1041 | .Vb 6 |
| 1042 | \& sub textblock { |
| 1043 | \& my ($parser, $paragraph, $line_num, $pod_para) = @_; |
| 1044 | \& my $ptree = $parser->parse_text({<<options>>}, $paragraph, ...); |
| 1045 | \& $pod_para->parse_tree( $ptree ); |
| 1046 | \& $parser->parse_tree()->append( $pod_para ); |
| 1047 | \& } |
| 1048 | .Ve |
| 1049 | .PP |
| 1050 | .Vb 1 |
| 1051 | \& ... |
| 1052 | .Ve |
| 1053 | .PP |
| 1054 | .Vb 6 |
| 1055 | \& package main; |
| 1056 | \& ... |
| 1057 | \& my $parser = new MyPodParserTree2(...); |
| 1058 | \& $parser->parse_from_file(...); |
| 1059 | \& my $ptree = $parser->parse_tree; |
| 1060 | \& ... |
| 1061 | .Ve |
| 1062 | .PP |
| 1063 | Now you have the entire \s-1POD\s0 document as one great big parse\-tree. You |
| 1064 | can even use the \fB\-expand_seq\fR option to \fBparse_text\fR to insert |
| 1065 | whole different kinds of objects. Just don't expect \fBPod::Parser\fR |
| 1066 | to know what to do with them after that. That will need to be in your |
| 1067 | code. Or, alternatively, you can insert any object you like so long as |
| 1068 | it conforms to the \fBPod::ParseTree\fR interface. |
| 1069 | .PP |
| 1070 | One could use this to create subclasses of \fBPod::Paragraphs\fR and |
| 1071 | \&\fBPod::InteriorSequences\fR for specific commands (or to create your own |
| 1072 | custom node-types in the parse\-tree) and add some kind of \fB\f(BIemit()\fB\fR |
| 1073 | method to each custom node/subclass object in the tree. Then all you'd |
| 1074 | need to do is recursively walk the tree in the desired order, processing |
| 1075 | the children (most likely from left to right) by formatting them if |
| 1076 | they are text\-strings, or by calling their \fB\f(BIemit()\fB\fR method if they |
| 1077 | are objects/references. |
| 1078 | .SH "SEE ALSO" |
| 1079 | .IX Header "SEE ALSO" |
| 1080 | Pod::InputObjects, Pod::Select |
| 1081 | .PP |
| 1082 | \&\fBPod::InputObjects\fR defines \s-1POD\s0 input objects corresponding to |
| 1083 | command paragraphs, parse\-trees, and interior\-sequences. |
| 1084 | .PP |
| 1085 | \&\fBPod::Select\fR is a subclass of \fBPod::Parser\fR which provides the ability |
| 1086 | to selectively include and/or exclude sections of a \s-1POD\s0 document from being |
| 1087 | translated based upon the current heading, subheading, subsubheading, etc. |
| 1088 | .SH "AUTHOR" |
| 1089 | .IX Header "AUTHOR" |
| 1090 | Brad Appleton <bradapp@enteract.com> |
| 1091 | .PP |
| 1092 | Based on code for \fBPod::Text\fR written by |
| 1093 | Tom Christiansen <tchrist@mox.perl.com> |