| 311 |
dpurdie |
1 |
#############################################################################
|
|
|
2 |
# Pod/Parser.pm -- package which defines a base class for parsing POD docs.
|
|
|
3 |
#
|
|
|
4 |
# Copyright (C) 1996-2000 by Bradford Appleton. All rights reserved.
|
|
|
5 |
# This file is part of "PodParser". PodParser is free software;
|
|
|
6 |
# you can redistribute it and/or modify it under the same terms
|
|
|
7 |
# as Perl itself.
|
|
|
8 |
#############################################################################
|
|
|
9 |
|
|
|
10 |
|
|
|
11 |
package Pod::Parser;
|
|
|
12 |
use strict;
|
|
|
13 |
|
|
|
14 |
## These "variables" are used as local "glob aliases" for performance
|
|
|
15 |
use vars qw($VERSION @ISA %myData %myOpts @input_stack);
|
|
|
16 |
use JatsError;
|
|
|
17 |
$VERSION = '1.37'; ## Current version of this package
|
|
|
18 |
require 5.005; ## requires this Perl version or later
|
|
|
19 |
|
|
|
20 |
#############################################################################
|
|
|
21 |
|
|
|
22 |
=head1 NAME
|
|
|
23 |
|
|
|
24 |
Pod::Parser - base class for creating POD filters and translators
|
|
|
25 |
|
|
|
26 |
=head1 SYNOPSIS
|
|
|
27 |
|
|
|
28 |
use Pod::Parser;
|
|
|
29 |
|
|
|
30 |
package MyParser;
|
|
|
31 |
@ISA = qw(Pod::Parser);
|
|
|
32 |
|
|
|
33 |
sub command {
|
|
|
34 |
my ($parser, $command, $paragraph, $line_num) = @_;
|
|
|
35 |
## Interpret the command and its text; sample actions might be:
|
|
|
36 |
if ($command eq 'head1') { ... }
|
|
|
37 |
elsif ($command eq 'head2') { ... }
|
|
|
38 |
## ... other commands and their actions
|
|
|
39 |
my $out_fh = $parser->output_handle();
|
|
|
40 |
my $expansion = $parser->interpolate($paragraph, $line_num);
|
|
|
41 |
print $out_fh $expansion;
|
|
|
42 |
}
|
|
|
43 |
|
|
|
44 |
sub verbatim {
|
|
|
45 |
my ($parser, $paragraph, $line_num) = @_;
|
|
|
46 |
## Format verbatim paragraph; sample actions might be:
|
|
|
47 |
my $out_fh = $parser->output_handle();
|
|
|
48 |
print $out_fh $paragraph;
|
|
|
49 |
}
|
|
|
50 |
|
|
|
51 |
sub textblock {
|
|
|
52 |
my ($parser, $paragraph, $line_num) = @_;
|
|
|
53 |
## Translate/Format this block of text; sample actions might be:
|
|
|
54 |
my $out_fh = $parser->output_handle();
|
|
|
55 |
my $expansion = $parser->interpolate($paragraph, $line_num);
|
|
|
56 |
print $out_fh $expansion;
|
|
|
57 |
}
|
|
|
58 |
|
|
|
59 |
sub interior_sequence {
|
|
|
60 |
my ($parser, $seq_command, $seq_argument) = @_;
|
|
|
61 |
## Expand an interior sequence; sample actions might be:
|
|
|
62 |
return "*$seq_argument*" if ($seq_command eq 'B');
|
|
|
63 |
return "`$seq_argument'" if ($seq_command eq 'C');
|
|
|
64 |
return "_${seq_argument}_'" if ($seq_command eq 'I');
|
|
|
65 |
## ... other sequence commands and their resulting text
|
|
|
66 |
}
|
|
|
67 |
|
|
|
68 |
package main;
|
|
|
69 |
|
|
|
70 |
## Create a parser object and have it parse file whose name was
|
|
|
71 |
## given on the command-line (use STDIN if no files were given).
|
|
|
72 |
$parser = new MyParser();
|
|
|
73 |
$parser->parse_from_filehandle(\*STDIN) if (@ARGV == 0);
|
|
|
74 |
for (@ARGV) { $parser->parse_from_file($_); }
|
|
|
75 |
|
|
|
76 |
=head1 REQUIRES
|
|
|
77 |
|
|
|
78 |
perl5.005, Pod::InputObjects, Exporter, Symbol, Carp
|
|
|
79 |
|
|
|
80 |
=head1 EXPORTS
|
|
|
81 |
|
|
|
82 |
Nothing.
|
|
|
83 |
|
|
|
84 |
=head1 DESCRIPTION
|
|
|
85 |
|
|
|
86 |
B<Pod::Parser> is a base class for creating POD filters and translators.
|
|
|
87 |
It handles most of the effort involved with parsing the POD sections
|
|
|
88 |
from an input stream, leaving subclasses free to be concerned only with
|
|
|
89 |
performing the actual translation of text.
|
|
|
90 |
|
|
|
91 |
B<Pod::Parser> parses PODs, and makes method calls to handle the various
|
|
|
92 |
components of the POD. Subclasses of B<Pod::Parser> override these methods
|
|
|
93 |
to translate the POD into whatever output format they desire.
|
|
|
94 |
|
|
|
95 |
=head1 QUICK OVERVIEW
|
|
|
96 |
|
|
|
97 |
To create a POD filter for translating POD documentation into some other
|
|
|
98 |
format, you create a subclass of B<Pod::Parser> which typically overrides
|
|
|
99 |
just the base class implementation for the following methods:
|
|
|
100 |
|
|
|
101 |
=over 2
|
|
|
102 |
|
|
|
103 |
=item *
|
|
|
104 |
|
|
|
105 |
B<command()>
|
|
|
106 |
|
|
|
107 |
=item *
|
|
|
108 |
|
|
|
109 |
B<verbatim()>
|
|
|
110 |
|
|
|
111 |
=item *
|
|
|
112 |
|
|
|
113 |
B<textblock()>
|
|
|
114 |
|
|
|
115 |
=item *
|
|
|
116 |
|
|
|
117 |
B<interior_sequence()>
|
|
|
118 |
|
|
|
119 |
=back
|
|
|
120 |
|
|
|
121 |
You may also want to override the B<begin_input()> and B<end_input()>
|
|
|
122 |
methods for your subclass (to perform any needed per-file and/or
|
|
|
123 |
per-document initialization or cleanup).
|
|
|
124 |
|
|
|
125 |
If you need to perform any preprocessing of input before it is parsed
|
|
|
126 |
you may want to override one or more of B<preprocess_line()> and/or
|
|
|
127 |
B<preprocess_paragraph()>.
|
|
|
128 |
|
|
|
129 |
Sometimes it may be necessary to make more than one pass over the input
|
|
|
130 |
files. If this is the case you have several options. You can make the
|
|
|
131 |
first pass using B<Pod::Parser> and override your methods to store the
|
|
|
132 |
intermediate results in memory somewhere for the B<end_pod()> method to
|
|
|
133 |
process. You could use B<Pod::Parser> for several passes with an
|
|
|
134 |
appropriate state variable to control the operation for each pass. If
|
|
|
135 |
your input source can't be reset to start at the beginning, you can
|
|
|
136 |
store it in some other structure as a string or an array and have that
|
|
|
137 |
structure implement a B<getline()> method (which is all that
|
|
|
138 |
B<parse_from_filehandle()> uses to read input).
|
|
|
139 |
|
|
|
140 |
Feel free to add any member data fields you need to keep track of things
|
|
|
141 |
like current font, indentation, horizontal or vertical position, or
|
|
|
142 |
whatever else you like. Be sure to read L<"PRIVATE METHODS AND DATA">
|
|
|
143 |
to avoid name collisions.
|
|
|
144 |
|
|
|
145 |
For the most part, the B<Pod::Parser> base class should be able to
|
|
|
146 |
do most of the input parsing for you and leave you free to worry about
|
|
|
147 |
how to interpret the commands and translate the result.
|
|
|
148 |
|
|
|
149 |
Note that all we have described here in this quick overview is the
|
|
|
150 |
simplest most straightforward use of B<Pod::Parser> to do stream-based
|
|
|
151 |
parsing. It is also possible to use the B<Pod::Parser::parse_text> function
|
|
|
152 |
to do more sophisticated tree-based parsing. See L<"TREE-BASED PARSING">.
|
|
|
153 |
|
|
|
154 |
=head1 PARSING OPTIONS
|
|
|
155 |
|
|
|
156 |
A I<parse-option> is simply a named option of B<Pod::Parser> with a
|
|
|
157 |
value that corresponds to a certain specified behavior. These various
|
|
|
158 |
behaviors of B<Pod::Parser> may be enabled/disabled by setting
|
|
|
159 |
or unsetting one or more I<parse-options> using the B<parseopts()> method.
|
|
|
160 |
The set of currently accepted parse-options is as follows:
|
|
|
161 |
|
|
|
162 |
=over 3
|
|
|
163 |
|
|
|
164 |
=item B<-want_nonPODs> (default: unset)
|
|
|
165 |
|
|
|
166 |
Normally (by default) B<Pod::Parser> will only provide access to
|
|
|
167 |
the POD sections of the input. Input paragraphs that are not part
|
|
|
168 |
of the POD-format documentation are not made available to the caller
|
|
|
169 |
(not even using B<preprocess_paragraph()>). Setting this option to a
|
|
|
170 |
non-empty, non-zero value will allow B<preprocess_paragraph()> to see
|
|
|
171 |
non-POD sections of the input as well as POD sections. The B<cutting()>
|
|
|
172 |
method can be used to determine if the corresponding paragraph is a POD
|
|
|
173 |
paragraph, or some other input paragraph.
|
|
|
174 |
|
|
|
175 |
=item B<-process_cut_cmd> (default: unset)
|
|
|
176 |
|
|
|
177 |
Normally (by default) B<Pod::Parser> handles the C<=cut> POD directive
|
|
|
178 |
by itself and does not pass it on to the caller for processing. Setting
|
|
|
179 |
this option to a non-empty, non-zero value will cause B<Pod::Parser> to
|
|
|
180 |
pass the C<=cut> directive to the caller just like any other POD command
|
|
|
181 |
(and hence it may be processed by the B<command()> method).
|
|
|
182 |
|
|
|
183 |
B<Pod::Parser> will still interpret the C<=cut> directive to mean that
|
|
|
184 |
"cutting mode" has been (re)entered, but the caller will get a chance
|
|
|
185 |
to capture the actual C<=cut> paragraph itself for whatever purpose
|
|
|
186 |
it desires.
|
|
|
187 |
|
|
|
188 |
=item B<-warnings> (default: unset)
|
|
|
189 |
|
|
|
190 |
Normally (by default) B<Pod::Parser> recognizes a bare minimum of
|
|
|
191 |
pod syntax errors and warnings and issues diagnostic messages
|
|
|
192 |
for errors, but not for warnings. (Use B<Pod::Checker> to do more
|
|
|
193 |
thorough checking of POD syntax.) Setting this option to a non-empty,
|
|
|
194 |
non-zero value will cause B<Pod::Parser> to issue diagnostics for
|
|
|
195 |
the few warnings it recognizes as well as the errors.
|
|
|
196 |
|
|
|
197 |
=back
|
|
|
198 |
|
|
|
199 |
Please see L<"parseopts()"> for a complete description of the interface
|
|
|
200 |
for the setting and unsetting of parse-options.
|
|
|
201 |
|
|
|
202 |
=cut
|
|
|
203 |
|
|
|
204 |
#############################################################################
|
|
|
205 |
|
|
|
206 |
#use diagnostics;
|
|
|
207 |
use Pod::InputObjects;
|
|
|
208 |
use Carp;
|
|
|
209 |
use Exporter;
|
|
|
210 |
BEGIN {
|
|
|
211 |
if ($] < 5.006) {
|
|
|
212 |
require Symbol;
|
|
|
213 |
import Symbol;
|
|
|
214 |
}
|
|
|
215 |
}
|
|
|
216 |
@ISA = qw(Exporter);
|
|
|
217 |
|
|
|
218 |
#############################################################################
|
|
|
219 |
|
|
|
220 |
=head1 RECOMMENDED SUBROUTINE/METHOD OVERRIDES
|
|
|
221 |
|
|
|
222 |
B<Pod::Parser> provides several methods which most subclasses will probably
|
|
|
223 |
want to override. These methods are as follows:
|
|
|
224 |
|
|
|
225 |
=cut
|
|
|
226 |
|
|
|
227 |
##---------------------------------------------------------------------------
|
|
|
228 |
|
|
|
229 |
=head1 B<command()>
|
|
|
230 |
|
|
|
231 |
$parser->command($cmd,$text,$line_num,$pod_para);
|
|
|
232 |
|
|
|
233 |
This method should be overridden by subclasses to take the appropriate
|
|
|
234 |
action when a POD command paragraph (denoted by a line beginning with
|
|
|
235 |
"=") is encountered. When such a POD directive is seen in the input,
|
|
|
236 |
this method is called and is passed:
|
|
|
237 |
|
|
|
238 |
=over 3
|
|
|
239 |
|
|
|
240 |
=item C<$cmd>
|
|
|
241 |
|
|
|
242 |
the name of the command for this POD paragraph
|
|
|
243 |
|
|
|
244 |
=item C<$text>
|
|
|
245 |
|
|
|
246 |
the paragraph text for the given POD paragraph command.
|
|
|
247 |
|
|
|
248 |
=item C<$line_num>
|
|
|
249 |
|
|
|
250 |
the line-number of the beginning of the paragraph
|
|
|
251 |
|
|
|
252 |
=item C<$pod_para>
|
|
|
253 |
|
|
|
254 |
a reference to a C<Pod::Paragraph> object which contains further
|
|
|
255 |
information about the paragraph command (see L<Pod::InputObjects>
|
|
|
256 |
for details).
|
|
|
257 |
|
|
|
258 |
=back
|
|
|
259 |
|
|
|
260 |
B<Note> that this method I<is> called for C<=pod> paragraphs.
|
|
|
261 |
|
|
|
262 |
The base class implementation of this method simply treats the raw POD
|
|
|
263 |
command as normal block of paragraph text (invoking the B<textblock()>
|
|
|
264 |
method with the command paragraph).
|
|
|
265 |
|
|
|
266 |
=cut
|
|
|
267 |
|
|
|
268 |
sub command {
|
|
|
269 |
my ($self, $cmd, $text, $line_num, $pod_para) = @_;
|
|
|
270 |
## Just treat this like a textblock
|
|
|
271 |
$self->textblock($pod_para->raw_text(), $line_num, $pod_para);
|
|
|
272 |
}
|
|
|
273 |
|
|
|
274 |
##---------------------------------------------------------------------------
|
|
|
275 |
|
|
|
276 |
=head1 B<verbatim()>
|
|
|
277 |
|
|
|
278 |
$parser->verbatim($text,$line_num,$pod_para);
|
|
|
279 |
|
|
|
280 |
This method may be overridden by subclasses to take the appropriate
|
|
|
281 |
action when a block of verbatim text is encountered. It is passed the
|
|
|
282 |
following parameters:
|
|
|
283 |
|
|
|
284 |
=over 3
|
|
|
285 |
|
|
|
286 |
=item C<$text>
|
|
|
287 |
|
|
|
288 |
the block of text for the verbatim paragraph
|
|
|
289 |
|
|
|
290 |
=item C<$line_num>
|
|
|
291 |
|
|
|
292 |
the line-number of the beginning of the paragraph
|
|
|
293 |
|
|
|
294 |
=item C<$pod_para>
|
|
|
295 |
|
|
|
296 |
a reference to a C<Pod::Paragraph> object which contains further
|
|
|
297 |
information about the paragraph (see L<Pod::InputObjects>
|
|
|
298 |
for details).
|
|
|
299 |
|
|
|
300 |
=back
|
|
|
301 |
|
|
|
302 |
The base class implementation of this method simply prints the textblock
|
|
|
303 |
(unmodified) to the output filehandle.
|
|
|
304 |
|
|
|
305 |
=cut
|
|
|
306 |
|
|
|
307 |
sub verbatim {
|
|
|
308 |
my ($self, $text, $line_num, $pod_para) = @_;
|
|
|
309 |
my $out_fh = $self->{_OUTPUT};
|
|
|
310 |
print $out_fh $text;
|
|
|
311 |
}
|
|
|
312 |
|
|
|
313 |
##---------------------------------------------------------------------------
|
|
|
314 |
|
|
|
315 |
=head1 B<textblock()>
|
|
|
316 |
|
|
|
317 |
$parser->textblock($text,$line_num,$pod_para);
|
|
|
318 |
|
|
|
319 |
This method may be overridden by subclasses to take the appropriate
|
|
|
320 |
action when a normal block of POD text is encountered (although the base
|
|
|
321 |
class method will usually do what you want). It is passed the following
|
|
|
322 |
parameters:
|
|
|
323 |
|
|
|
324 |
=over 3
|
|
|
325 |
|
|
|
326 |
=item C<$text>
|
|
|
327 |
|
|
|
328 |
the block of text for the a POD paragraph
|
|
|
329 |
|
|
|
330 |
=item C<$line_num>
|
|
|
331 |
|
|
|
332 |
the line-number of the beginning of the paragraph
|
|
|
333 |
|
|
|
334 |
=item C<$pod_para>
|
|
|
335 |
|
|
|
336 |
a reference to a C<Pod::Paragraph> object which contains further
|
|
|
337 |
information about the paragraph (see L<Pod::InputObjects>
|
|
|
338 |
for details).
|
|
|
339 |
|
|
|
340 |
=back
|
|
|
341 |
|
|
|
342 |
In order to process interior sequences, subclasses implementations of
|
|
|
343 |
this method will probably want to invoke either B<interpolate()> or
|
|
|
344 |
B<parse_text()>, passing it the text block C<$text>, and the corresponding
|
|
|
345 |
line number in C<$line_num>, and then perform any desired processing upon
|
|
|
346 |
the returned result.
|
|
|
347 |
|
|
|
348 |
The base class implementation of this method simply prints the text block
|
|
|
349 |
as it occurred in the input stream).
|
|
|
350 |
|
|
|
351 |
=cut
|
|
|
352 |
|
|
|
353 |
sub textblock {
|
|
|
354 |
my ($self, $text, $line_num, $pod_para) = @_;
|
|
|
355 |
my $out_fh = $self->{_OUTPUT};
|
|
|
356 |
print $out_fh $self->interpolate($text, $line_num);
|
|
|
357 |
}
|
|
|
358 |
|
|
|
359 |
##---------------------------------------------------------------------------
|
|
|
360 |
|
|
|
361 |
=head1 B<interior_sequence()>
|
|
|
362 |
|
|
|
363 |
$parser->interior_sequence($seq_cmd,$seq_arg,$pod_seq);
|
|
|
364 |
|
|
|
365 |
This method should be overridden by subclasses to take the appropriate
|
|
|
366 |
action when an interior sequence is encountered. An interior sequence is
|
|
|
367 |
an embedded command within a block of text which appears as a command
|
|
|
368 |
name (usually a single uppercase character) followed immediately by a
|
|
|
369 |
string of text which is enclosed in angle brackets. This method is
|
|
|
370 |
passed the sequence command C<$seq_cmd> and the corresponding text
|
|
|
371 |
C<$seq_arg>. It is invoked by the B<interpolate()> method for each interior
|
|
|
372 |
sequence that occurs in the string that it is passed. It should return
|
|
|
373 |
the desired text string to be used in place of the interior sequence.
|
|
|
374 |
The C<$pod_seq> argument is a reference to a C<Pod::InteriorSequence>
|
|
|
375 |
object which contains further information about the interior sequence.
|
|
|
376 |
Please see L<Pod::InputObjects> for details if you need to access this
|
|
|
377 |
additional information.
|
|
|
378 |
|
|
|
379 |
Subclass implementations of this method may wish to invoke the
|
|
|
380 |
B<nested()> method of C<$pod_seq> to see if it is nested inside
|
|
|
381 |
some other interior-sequence (and if so, which kind).
|
|
|
382 |
|
|
|
383 |
The base class implementation of the B<interior_sequence()> method
|
|
|
384 |
simply returns the raw text of the interior sequence (as it occurred
|
|
|
385 |
in the input) to the caller.
|
|
|
386 |
|
|
|
387 |
=cut
|
|
|
388 |
|
|
|
389 |
sub interior_sequence {
|
|
|
390 |
my ($self, $seq_cmd, $seq_arg, $pod_seq) = @_;
|
|
|
391 |
## Just return the raw text of the interior sequence
|
|
|
392 |
return $pod_seq->raw_text();
|
|
|
393 |
}
|
|
|
394 |
|
|
|
395 |
#############################################################################
|
|
|
396 |
|
|
|
397 |
=head1 OPTIONAL SUBROUTINE/METHOD OVERRIDES
|
|
|
398 |
|
|
|
399 |
B<Pod::Parser> provides several methods which subclasses may want to override
|
|
|
400 |
to perform any special pre/post-processing. These methods do I<not> have to
|
|
|
401 |
be overridden, but it may be useful for subclasses to take advantage of them.
|
|
|
402 |
|
|
|
403 |
=cut
|
|
|
404 |
|
|
|
405 |
##---------------------------------------------------------------------------
|
|
|
406 |
|
|
|
407 |
=head1 B<new()>
|
|
|
408 |
|
|
|
409 |
my $parser = Pod::Parser->new();
|
|
|
410 |
|
|
|
411 |
This is the constructor for B<Pod::Parser> and its subclasses. You
|
|
|
412 |
I<do not> need to override this method! It is capable of constructing
|
|
|
413 |
subclass objects as well as base class objects, provided you use
|
|
|
414 |
any of the following constructor invocation styles:
|
|
|
415 |
|
|
|
416 |
my $parser1 = MyParser->new();
|
|
|
417 |
my $parser2 = new MyParser();
|
|
|
418 |
my $parser3 = $parser2->new();
|
|
|
419 |
|
|
|
420 |
where C<MyParser> is some subclass of B<Pod::Parser>.
|
|
|
421 |
|
|
|
422 |
Using the syntax C<MyParser::new()> to invoke the constructor is I<not>
|
|
|
423 |
recommended, but if you insist on being able to do this, then the
|
|
|
424 |
subclass I<will> need to override the B<new()> constructor method. If
|
|
|
425 |
you do override the constructor, you I<must> be sure to invoke the
|
|
|
426 |
B<initialize()> method of the newly blessed object.
|
|
|
427 |
|
|
|
428 |
Using any of the above invocations, the first argument to the
|
|
|
429 |
constructor is always the corresponding package name (or object
|
|
|
430 |
reference). No other arguments are required, but if desired, an
|
|
|
431 |
associative array (or hash-table) my be passed to the B<new()>
|
|
|
432 |
constructor, as in:
|
|
|
433 |
|
|
|
434 |
my $parser1 = MyParser->new( MYDATA => $value1, MOREDATA => $value2 );
|
|
|
435 |
my $parser2 = new MyParser( -myflag => 1 );
|
|
|
436 |
|
|
|
437 |
All arguments passed to the B<new()> constructor will be treated as
|
|
|
438 |
key/value pairs in a hash-table. The newly constructed object will be
|
|
|
439 |
initialized by copying the contents of the given hash-table (which may
|
|
|
440 |
have been empty). The B<new()> constructor for this class and all of its
|
|
|
441 |
subclasses returns a blessed reference to the initialized object (hash-table).
|
|
|
442 |
|
|
|
443 |
=cut
|
|
|
444 |
|
|
|
445 |
sub new {
|
|
|
446 |
## Determine if we were called via an object-ref or a classname
|
|
|
447 |
my ($this,%params) = @_;
|
|
|
448 |
my $class = ref($this) || $this;
|
|
|
449 |
## Any remaining arguments are treated as initial values for the
|
|
|
450 |
## hash that is used to represent this object.
|
|
|
451 |
my $self = { %params };
|
|
|
452 |
## Bless ourselves into the desired class and perform any initialization
|
|
|
453 |
bless $self, $class;
|
|
|
454 |
$self->initialize();
|
|
|
455 |
return $self;
|
|
|
456 |
}
|
|
|
457 |
|
|
|
458 |
##---------------------------------------------------------------------------
|
|
|
459 |
|
|
|
460 |
=head1 B<initialize()>
|
|
|
461 |
|
|
|
462 |
$parser->initialize();
|
|
|
463 |
|
|
|
464 |
This method performs any necessary object initialization. It takes no
|
|
|
465 |
arguments (other than the object instance of course, which is typically
|
|
|
466 |
copied to a local variable named C<$self>). If subclasses override this
|
|
|
467 |
method then they I<must> be sure to invoke C<$self-E<gt>SUPER::initialize()>.
|
|
|
468 |
|
|
|
469 |
=cut
|
|
|
470 |
|
|
|
471 |
sub initialize {
|
|
|
472 |
#my $self = shift;
|
|
|
473 |
#return;
|
|
|
474 |
}
|
|
|
475 |
|
|
|
476 |
##---------------------------------------------------------------------------
|
|
|
477 |
|
|
|
478 |
=head1 B<begin_pod()>
|
|
|
479 |
|
|
|
480 |
$parser->begin_pod();
|
|
|
481 |
|
|
|
482 |
This method is invoked at the beginning of processing for each POD
|
|
|
483 |
document that is encountered in the input. Subclasses should override
|
|
|
484 |
this method to perform any per-document initialization.
|
|
|
485 |
|
|
|
486 |
=cut
|
|
|
487 |
|
|
|
488 |
sub begin_pod {
|
|
|
489 |
#my $self = shift;
|
|
|
490 |
#return;
|
|
|
491 |
}
|
|
|
492 |
|
|
|
493 |
##---------------------------------------------------------------------------
|
|
|
494 |
|
|
|
495 |
=head1 B<begin_input()>
|
|
|
496 |
|
|
|
497 |
$parser->begin_input();
|
|
|
498 |
|
|
|
499 |
This method is invoked by B<parse_from_filehandle()> immediately I<before>
|
|
|
500 |
processing input from a filehandle. The base class implementation does
|
|
|
501 |
nothing, however, subclasses may override it to perform any per-file
|
|
|
502 |
initializations.
|
|
|
503 |
|
|
|
504 |
Note that if multiple files are parsed for a single POD document
|
|
|
505 |
(perhaps the result of some future C<=include> directive) this method
|
|
|
506 |
is invoked for every file that is parsed. If you wish to perform certain
|
|
|
507 |
initializations once per document, then you should use B<begin_pod()>.
|
|
|
508 |
|
|
|
509 |
=cut
|
|
|
510 |
|
|
|
511 |
sub begin_input {
|
|
|
512 |
#my $self = shift;
|
|
|
513 |
#return;
|
|
|
514 |
}
|
|
|
515 |
|
|
|
516 |
##---------------------------------------------------------------------------
|
|
|
517 |
|
|
|
518 |
=head1 B<end_input()>
|
|
|
519 |
|
|
|
520 |
$parser->end_input();
|
|
|
521 |
|
|
|
522 |
This method is invoked by B<parse_from_filehandle()> immediately I<after>
|
|
|
523 |
processing input from a filehandle. The base class implementation does
|
|
|
524 |
nothing, however, subclasses may override it to perform any per-file
|
|
|
525 |
cleanup actions.
|
|
|
526 |
|
|
|
527 |
Please note that if multiple files are parsed for a single POD document
|
|
|
528 |
(perhaps the result of some kind of C<=include> directive) this method
|
|
|
529 |
is invoked for every file that is parsed. If you wish to perform certain
|
|
|
530 |
cleanup actions once per document, then you should use B<end_pod()>.
|
|
|
531 |
|
|
|
532 |
=cut
|
|
|
533 |
|
|
|
534 |
sub end_input {
|
|
|
535 |
#my $self = shift;
|
|
|
536 |
#return;
|
|
|
537 |
}
|
|
|
538 |
|
|
|
539 |
##---------------------------------------------------------------------------
|
|
|
540 |
|
|
|
541 |
=head1 B<end_pod()>
|
|
|
542 |
|
|
|
543 |
$parser->end_pod();
|
|
|
544 |
|
|
|
545 |
This method is invoked at the end of processing for each POD document
|
|
|
546 |
that is encountered in the input. Subclasses should override this method
|
|
|
547 |
to perform any per-document finalization.
|
|
|
548 |
|
|
|
549 |
=cut
|
|
|
550 |
|
|
|
551 |
sub end_pod {
|
|
|
552 |
#my $self = shift;
|
|
|
553 |
#return;
|
|
|
554 |
}
|
|
|
555 |
|
|
|
556 |
##---------------------------------------------------------------------------
|
|
|
557 |
|
|
|
558 |
=head1 B<preprocess_line()>
|
|
|
559 |
|
|
|
560 |
$textline = $parser->preprocess_line($text, $line_num);
|
|
|
561 |
|
|
|
562 |
This method should be overridden by subclasses that wish to perform
|
|
|
563 |
any kind of preprocessing for each I<line> of input (I<before> it has
|
|
|
564 |
been determined whether or not it is part of a POD paragraph). The
|
|
|
565 |
parameter C<$text> is the input line; and the parameter C<$line_num> is
|
|
|
566 |
the line number of the corresponding text line.
|
|
|
567 |
|
|
|
568 |
The value returned should correspond to the new text to use in its
|
|
|
569 |
place. If the empty string or an undefined value is returned then no
|
|
|
570 |
further processing will be performed for this line.
|
|
|
571 |
|
|
|
572 |
Please note that the B<preprocess_line()> method is invoked I<before>
|
|
|
573 |
the B<preprocess_paragraph()> method. After all (possibly preprocessed)
|
|
|
574 |
lines in a paragraph have been assembled together and it has been
|
|
|
575 |
determined that the paragraph is part of the POD documentation from one
|
|
|
576 |
of the selected sections, then B<preprocess_paragraph()> is invoked.
|
|
|
577 |
|
|
|
578 |
The base class implementation of this method returns the given text.
|
|
|
579 |
|
|
|
580 |
=cut
|
|
|
581 |
|
|
|
582 |
sub preprocess_line {
|
|
|
583 |
my ($self, $text, $line_num) = @_;
|
|
|
584 |
return $text;
|
|
|
585 |
}
|
|
|
586 |
|
|
|
587 |
##---------------------------------------------------------------------------
|
|
|
588 |
|
|
|
589 |
=head1 B<preprocess_paragraph()>
|
|
|
590 |
|
|
|
591 |
$textblock = $parser->preprocess_paragraph($text, $line_num);
|
|
|
592 |
|
|
|
593 |
This method should be overridden by subclasses that wish to perform any
|
|
|
594 |
kind of preprocessing for each block (paragraph) of POD documentation
|
|
|
595 |
that appears in the input stream. The parameter C<$text> is the POD
|
|
|
596 |
paragraph from the input file; and the parameter C<$line_num> is the
|
|
|
597 |
line number for the beginning of the corresponding paragraph.
|
|
|
598 |
|
|
|
599 |
The value returned should correspond to the new text to use in its
|
|
|
600 |
place If the empty string is returned or an undefined value is
|
|
|
601 |
returned, then the given C<$text> is ignored (not processed).
|
|
|
602 |
|
|
|
603 |
This method is invoked after gathering up all the lines in a paragraph
|
|
|
604 |
and after determining the cutting state of the paragraph,
|
|
|
605 |
but before trying to further parse or interpret them. After
|
|
|
606 |
B<preprocess_paragraph()> returns, the current cutting state (which
|
|
|
607 |
is returned by C<$self-E<gt>cutting()>) is examined. If it evaluates
|
|
|
608 |
to true then input text (including the given C<$text>) is cut (not
|
|
|
609 |
processed) until the next POD directive is encountered.
|
|
|
610 |
|
|
|
611 |
Please note that the B<preprocess_line()> method is invoked I<before>
|
|
|
612 |
the B<preprocess_paragraph()> method. After all (possibly preprocessed)
|
|
|
613 |
lines in a paragraph have been assembled together and either it has been
|
|
|
614 |
determined that the paragraph is part of the POD documentation from one
|
|
|
615 |
of the selected sections or the C<-want_nonPODs> option is true,
|
|
|
616 |
then B<preprocess_paragraph()> is invoked.
|
|
|
617 |
|
|
|
618 |
The base class implementation of this method returns the given text.
|
|
|
619 |
|
|
|
620 |
=cut
|
|
|
621 |
|
|
|
622 |
sub preprocess_paragraph {
|
|
|
623 |
my ($self, $text, $line_num) = @_;
|
|
|
624 |
return $text;
|
|
|
625 |
}
|
|
|
626 |
|
|
|
627 |
#############################################################################
|
|
|
628 |
|
|
|
629 |
=head1 METHODS FOR PARSING AND PROCESSING
|
|
|
630 |
|
|
|
631 |
B<Pod::Parser> provides several methods to process input text. These
|
|
|
632 |
methods typically won't need to be overridden (and in some cases they
|
|
|
633 |
can't be overridden), but subclasses may want to invoke them to exploit
|
|
|
634 |
their functionality.
|
|
|
635 |
|
|
|
636 |
=cut
|
|
|
637 |
|
|
|
638 |
##---------------------------------------------------------------------------
|
|
|
639 |
|
|
|
640 |
=head1 B<parse_text()>
|
|
|
641 |
|
|
|
642 |
$ptree1 = $parser->parse_text($text, $line_num);
|
|
|
643 |
$ptree2 = $parser->parse_text({%opts}, $text, $line_num);
|
|
|
644 |
$ptree3 = $parser->parse_text(\%opts, $text, $line_num);
|
|
|
645 |
|
|
|
646 |
This method is useful if you need to perform your own interpolation
|
|
|
647 |
of interior sequences and can't rely upon B<interpolate> to expand
|
|
|
648 |
them in simple bottom-up order.
|
|
|
649 |
|
|
|
650 |
The parameter C<$text> is a string or block of text to be parsed
|
|
|
651 |
for interior sequences; and the parameter C<$line_num> is the
|
|
|
652 |
line number corresponding to the beginning of C<$text>.
|
|
|
653 |
|
|
|
654 |
B<parse_text()> will parse the given text into a parse-tree of "nodes."
|
|
|
655 |
and interior-sequences. Each "node" in the parse tree is either a
|
|
|
656 |
text-string, or a B<Pod::InteriorSequence>. The result returned is a
|
|
|
657 |
parse-tree of type B<Pod::ParseTree>. Please see L<Pod::InputObjects>
|
|
|
658 |
for more information about B<Pod::InteriorSequence> and B<Pod::ParseTree>.
|
|
|
659 |
|
|
|
660 |
If desired, an optional hash-ref may be specified as the first argument
|
|
|
661 |
to customize certain aspects of the parse-tree that is created and
|
|
|
662 |
returned. The set of recognized option keywords are:
|
|
|
663 |
|
|
|
664 |
=over 3
|
|
|
665 |
|
|
|
666 |
=item B<-expand_seq> =E<gt> I<code-ref>|I<method-name>
|
|
|
667 |
|
|
|
668 |
Normally, the parse-tree returned by B<parse_text()> will contain an
|
|
|
669 |
unexpanded C<Pod::InteriorSequence> object for each interior-sequence
|
|
|
670 |
encountered. Specifying B<-expand_seq> tells B<parse_text()> to "expand"
|
|
|
671 |
every interior-sequence it sees by invoking the referenced function
|
|
|
672 |
(or named method of the parser object) and using the return value as the
|
|
|
673 |
expanded result.
|
|
|
674 |
|
|
|
675 |
If a subroutine reference was given, it is invoked as:
|
|
|
676 |
|
|
|
677 |
&$code_ref( $parser, $sequence )
|
|
|
678 |
|
|
|
679 |
and if a method-name was given, it is invoked as:
|
|
|
680 |
|
|
|
681 |
$parser->method_name( $sequence )
|
|
|
682 |
|
|
|
683 |
where C<$parser> is a reference to the parser object, and C<$sequence>
|
|
|
684 |
is a reference to the interior-sequence object.
|
|
|
685 |
[I<NOTE>: If the B<interior_sequence()> method is specified, then it is
|
|
|
686 |
invoked according to the interface specified in L<"interior_sequence()">].
|
|
|
687 |
|
|
|
688 |
=item B<-expand_text> =E<gt> I<code-ref>|I<method-name>
|
|
|
689 |
|
|
|
690 |
Normally, the parse-tree returned by B<parse_text()> will contain a
|
|
|
691 |
text-string for each contiguous sequence of characters outside of an
|
|
|
692 |
interior-sequence. Specifying B<-expand_text> tells B<parse_text()> to
|
|
|
693 |
"preprocess" every such text-string it sees by invoking the referenced
|
|
|
694 |
function (or named method of the parser object) and using the return value
|
|
|
695 |
as the preprocessed (or "expanded") result. [Note that if the result is
|
|
|
696 |
an interior-sequence, then it will I<not> be expanded as specified by the
|
|
|
697 |
B<-expand_seq> option; Any such recursive expansion needs to be handled by
|
|
|
698 |
the specified callback routine.]
|
|
|
699 |
|
|
|
700 |
If a subroutine reference was given, it is invoked as:
|
|
|
701 |
|
|
|
702 |
&$code_ref( $parser, $text, $ptree_node )
|
|
|
703 |
|
|
|
704 |
and if a method-name was given, it is invoked as:
|
|
|
705 |
|
|
|
706 |
$parser->method_name( $text, $ptree_node )
|
|
|
707 |
|
|
|
708 |
where C<$parser> is a reference to the parser object, C<$text> is the
|
|
|
709 |
text-string encountered, and C<$ptree_node> is a reference to the current
|
|
|
710 |
node in the parse-tree (usually an interior-sequence object or else the
|
|
|
711 |
top-level node of the parse-tree).
|
|
|
712 |
|
|
|
713 |
=item B<-expand_ptree> =E<gt> I<code-ref>|I<method-name>
|
|
|
714 |
|
|
|
715 |
Rather than returning a C<Pod::ParseTree>, pass the parse-tree as an
|
|
|
716 |
argument to the referenced subroutine (or named method of the parser
|
|
|
717 |
object) and return the result instead of the parse-tree object.
|
|
|
718 |
|
|
|
719 |
If a subroutine reference was given, it is invoked as:
|
|
|
720 |
|
|
|
721 |
&$code_ref( $parser, $ptree )
|
|
|
722 |
|
|
|
723 |
and if a method-name was given, it is invoked as:
|
|
|
724 |
|
|
|
725 |
$parser->method_name( $ptree )
|
|
|
726 |
|
|
|
727 |
where C<$parser> is a reference to the parser object, and C<$ptree>
|
|
|
728 |
is a reference to the parse-tree object.
|
|
|
729 |
|
|
|
730 |
=back
|
|
|
731 |
|
|
|
732 |
=cut
|
|
|
733 |
|
|
|
734 |
sub parse_text {
|
|
|
735 |
my $self = shift;
|
|
|
736 |
local $_ = '';
|
|
|
737 |
|
|
|
738 |
## Get options and set any defaults
|
|
|
739 |
my %opts = (ref $_[0]) ? %{ shift() } : ();
|
|
|
740 |
my $expand_seq = $opts{'-expand_seq'} || undef;
|
|
|
741 |
my $expand_text = $opts{'-expand_text'} || undef;
|
|
|
742 |
my $expand_ptree = $opts{'-expand_ptree'} || undef;
|
|
|
743 |
|
|
|
744 |
my $text = shift;
|
|
|
745 |
my $line = shift;
|
|
|
746 |
my $file = $self->input_file();
|
|
|
747 |
my $cmd = "";
|
|
|
748 |
|
|
|
749 |
## Convert method calls into closures, for our convenience
|
|
|
750 |
my $xseq_sub = $expand_seq;
|
|
|
751 |
my $xtext_sub = $expand_text;
|
|
|
752 |
my $xptree_sub = $expand_ptree;
|
|
|
753 |
if (defined $expand_seq and $expand_seq eq 'interior_sequence') {
|
|
|
754 |
## If 'interior_sequence' is the method to use, we have to pass
|
|
|
755 |
## more than just the sequence object, we also need to pass the
|
|
|
756 |
## sequence name and text.
|
|
|
757 |
$xseq_sub = sub {
|
|
|
758 |
my ($sself, $iseq) = @_;
|
|
|
759 |
my $args = join('', $iseq->parse_tree->children);
|
|
|
760 |
return $sself->interior_sequence($iseq->name, $args, $iseq);
|
|
|
761 |
};
|
|
|
762 |
}
|
|
|
763 |
ref $xseq_sub or $xseq_sub = sub { shift()->$expand_seq(@_) };
|
|
|
764 |
ref $xtext_sub or $xtext_sub = sub { shift()->$expand_text(@_) };
|
|
|
765 |
ref $xptree_sub or $xptree_sub = sub { shift()->$expand_ptree(@_) };
|
|
|
766 |
|
|
|
767 |
## Keep track of the "current" interior sequence, and maintain a stack
|
|
|
768 |
## of "in progress" sequences.
|
|
|
769 |
##
|
|
|
770 |
## NOTE that we push our own "accumulator" at the very beginning of the
|
|
|
771 |
## stack. It's really a parse-tree, not a sequence; but it implements
|
|
|
772 |
## the methods we need so we can use it to gather-up all the sequences
|
|
|
773 |
## and strings we parse. Thus, by the end of our parsing, it should be
|
|
|
774 |
## the only thing left on our stack and all we have to do is return it!
|
|
|
775 |
##
|
|
|
776 |
my $seq = Pod::ParseTree->new();
|
|
|
777 |
my @seq_stack = ($seq);
|
|
|
778 |
my ($ldelim, $rdelim) = ('', '');
|
|
|
779 |
|
|
|
780 |
## Iterate over all sequence starts text (NOTE: split with
|
|
|
781 |
## capturing parens keeps the delimiters)
|
|
|
782 |
$_ = $text;
|
|
|
783 |
my @tokens = split /([A-Z]<(?:<+\s)?)/;
|
|
|
784 |
while ( @tokens ) {
|
|
|
785 |
$_ = shift @tokens;
|
|
|
786 |
## Look for the beginning of a sequence
|
|
|
787 |
if ( /^([A-Z])(<(?:<+\s)?)$/ ) {
|
|
|
788 |
## Push a new sequence onto the stack of those "in-progress"
|
|
|
789 |
my $ldelim_orig;
|
|
|
790 |
($cmd, $ldelim_orig) = ($1, $2);
|
|
|
791 |
($ldelim = $ldelim_orig) =~ s/\s+$//;
|
|
|
792 |
($rdelim = $ldelim) =~ tr/</>/;
|
|
|
793 |
$seq = Pod::InteriorSequence->new(
|
|
|
794 |
-name => $cmd,
|
|
|
795 |
-ldelim => $ldelim_orig, -rdelim => $rdelim,
|
|
|
796 |
-file => $file, -line => $line
|
|
|
797 |
);
|
|
|
798 |
(@seq_stack > 1) and $seq->nested($seq_stack[-1]);
|
|
|
799 |
push @seq_stack, $seq;
|
|
|
800 |
}
|
|
|
801 |
## Look for sequence ending
|
|
|
802 |
elsif ( @seq_stack > 1 ) {
|
|
|
803 |
## Make sure we match the right kind of closing delimiter
|
|
|
804 |
my ($seq_end, $post_seq) = ('', '');
|
|
|
805 |
if ( ($ldelim eq '<' and /\A(.*?)(>)/s)
|
|
|
806 |
or /\A(.*?)(\s+$rdelim)/s )
|
|
|
807 |
{
|
|
|
808 |
## Found end-of-sequence, capture the interior and the
|
|
|
809 |
## closing the delimiter, and put the rest back on the
|
|
|
810 |
## token-list
|
|
|
811 |
$post_seq = substr($_, length($1) + length($2));
|
|
|
812 |
($_, $seq_end) = ($1, $2);
|
|
|
813 |
(length $post_seq) and unshift @tokens, $post_seq;
|
|
|
814 |
}
|
|
|
815 |
if (length) {
|
|
|
816 |
## In the middle of a sequence, append this text to it, and
|
|
|
817 |
## dont forget to "expand" it if that's what the caller wanted
|
|
|
818 |
$seq->append($expand_text ? &$xtext_sub($self,$_,$seq) : $_);
|
|
|
819 |
$_ .= $seq_end;
|
|
|
820 |
}
|
|
|
821 |
if (length $seq_end) {
|
|
|
822 |
## End of current sequence, record terminating delimiter
|
|
|
823 |
$seq->rdelim($seq_end);
|
|
|
824 |
## Pop it off the stack of "in progress" sequences
|
|
|
825 |
pop @seq_stack;
|
|
|
826 |
## Append result to its parent in current parse tree
|
|
|
827 |
$seq_stack[-1]->append($expand_seq ? &$xseq_sub($self,$seq)
|
|
|
828 |
: $seq);
|
|
|
829 |
## Remember the current cmd-name and left-delimiter
|
|
|
830 |
if(@seq_stack > 1) {
|
|
|
831 |
$cmd = $seq_stack[-1]->name;
|
|
|
832 |
$ldelim = $seq_stack[-1]->ldelim;
|
|
|
833 |
$rdelim = $seq_stack[-1]->rdelim;
|
|
|
834 |
} else {
|
|
|
835 |
$cmd = $ldelim = $rdelim = '';
|
|
|
836 |
}
|
|
|
837 |
}
|
|
|
838 |
}
|
|
|
839 |
elsif (length) {
|
|
|
840 |
## In the middle of a sequence, append this text to it, and
|
|
|
841 |
## dont forget to "expand" it if that's what the caller wanted
|
|
|
842 |
$seq->append($expand_text ? &$xtext_sub($self,$_,$seq) : $_);
|
|
|
843 |
}
|
|
|
844 |
## Keep track of line count
|
|
|
845 |
$line += s/\r*\n//;
|
|
|
846 |
## Remember the "current" sequence
|
|
|
847 |
$seq = $seq_stack[-1];
|
|
|
848 |
}
|
|
|
849 |
|
|
|
850 |
## Handle unterminated sequences
|
|
|
851 |
my $errorsub = (@seq_stack > 1) ? $self->errorsub() : undef;
|
|
|
852 |
while (@seq_stack > 1) {
|
|
|
853 |
($cmd, $file, $line) = ($seq->name, $seq->file_line);
|
|
|
854 |
$ldelim = $seq->ldelim;
|
|
|
855 |
($rdelim = $ldelim) =~ tr/</>/;
|
|
|
856 |
$rdelim =~ s/^(\S+)(\s*)$/$2$1/;
|
|
|
857 |
pop @seq_stack;
|
|
|
858 |
my $errmsg = "*** ERROR: unterminated ${cmd}${ldelim}...${rdelim}".
|
|
|
859 |
" at line $line in file $file\n";
|
|
|
860 |
(ref $errorsub) and &{$errorsub}($errmsg)
|
|
|
861 |
or (defined $errorsub) and $self->$errorsub($errmsg)
|
|
|
862 |
or carp($errmsg);
|
|
|
863 |
$seq_stack[-1]->append($expand_seq ? &$xseq_sub($self,$seq) : $seq);
|
|
|
864 |
$seq = $seq_stack[-1];
|
|
|
865 |
}
|
|
|
866 |
|
|
|
867 |
## Return the resulting parse-tree
|
|
|
868 |
my $ptree = (pop @seq_stack)->parse_tree;
|
|
|
869 |
return $expand_ptree ? &$xptree_sub($self, $ptree) : $ptree;
|
|
|
870 |
}
|
|
|
871 |
|
|
|
872 |
##---------------------------------------------------------------------------
|
|
|
873 |
|
|
|
874 |
=head1 B<interpolate()>
|
|
|
875 |
|
|
|
876 |
$textblock = $parser->interpolate($text, $line_num);
|
|
|
877 |
|
|
|
878 |
This method translates all text (including any embedded interior sequences)
|
|
|
879 |
in the given text string C<$text> and returns the interpolated result. The
|
|
|
880 |
parameter C<$line_num> is the line number corresponding to the beginning
|
|
|
881 |
of C<$text>.
|
|
|
882 |
|
|
|
883 |
B<interpolate()> merely invokes a private method to recursively expand
|
|
|
884 |
nested interior sequences in bottom-up order (innermost sequences are
|
|
|
885 |
expanded first). If there is a need to expand nested sequences in
|
|
|
886 |
some alternate order, use B<parse_text> instead.
|
|
|
887 |
|
|
|
888 |
=cut
|
|
|
889 |
|
|
|
890 |
sub interpolate {
|
|
|
891 |
my($self, $text, $line_num) = @_;
|
|
|
892 |
my %parse_opts = ( -expand_seq => 'interior_sequence' );
|
|
|
893 |
my $ptree = $self->parse_text( \%parse_opts, $text, $line_num );
|
|
|
894 |
return join '', $ptree->children();
|
|
|
895 |
}
|
|
|
896 |
|
|
|
897 |
##---------------------------------------------------------------------------
|
|
|
898 |
|
|
|
899 |
=begin __PRIVATE__
|
|
|
900 |
|
|
|
901 |
=head1 B<parse_paragraph()>
|
|
|
902 |
|
|
|
903 |
$parser->parse_paragraph($text, $line_num);
|
|
|
904 |
|
|
|
905 |
This method takes the text of a POD paragraph to be processed, along
|
|
|
906 |
with its corresponding line number, and invokes the appropriate method
|
|
|
907 |
(one of B<command()>, B<verbatim()>, or B<textblock()>).
|
|
|
908 |
|
|
|
909 |
For performance reasons, this method is invoked directly without any
|
|
|
910 |
dynamic lookup; Hence subclasses may I<not> override it!
|
|
|
911 |
|
|
|
912 |
=end __PRIVATE__
|
|
|
913 |
|
|
|
914 |
=cut
|
|
|
915 |
|
|
|
916 |
sub parse_paragraph {
|
|
|
917 |
my ($self, $text, $line_num) = @_;
|
|
|
918 |
local *myData = $self; ## alias to avoid deref-ing overhead
|
|
|
919 |
local *myOpts = ($myData{_PARSEOPTS} ||= {}); ## get parse-options
|
|
|
920 |
local $_;
|
|
|
921 |
|
|
|
922 |
## See if we want to preprocess nonPOD paragraphs as well as POD ones.
|
|
|
923 |
my $wantNonPods = $myOpts{'-want_nonPODs'};
|
|
|
924 |
|
|
|
925 |
## Update cutting status
|
|
|
926 |
$myData{_CUTTING} = 0 if $text =~ /^={1,2}\S/;
|
|
|
927 |
|
|
|
928 |
## Perform any desired preprocessing if we wanted it this early
|
|
|
929 |
$wantNonPods and $text = $self->preprocess_paragraph($text, $line_num);
|
|
|
930 |
|
|
|
931 |
## Ignore up until next POD directive if we are cutting
|
|
|
932 |
return if $myData{_CUTTING};
|
|
|
933 |
|
|
|
934 |
## Now we know this is block of text in a POD section!
|
|
|
935 |
|
|
|
936 |
##-----------------------------------------------------------------
|
|
|
937 |
## This is a hook (hack ;-) for Pod::Select to do its thing without
|
|
|
938 |
## having to override methods, but also without Pod::Parser assuming
|
|
|
939 |
## $self is an instance of Pod::Select (if the _SELECTED_SECTIONS
|
|
|
940 |
## field exists then we assume there is an is_selected() method for
|
|
|
941 |
## us to invoke (calling $self->can('is_selected') could verify this
|
|
|
942 |
## but that is more overhead than I want to incur)
|
|
|
943 |
##-----------------------------------------------------------------
|
|
|
944 |
|
|
|
945 |
## Ignore this block if it isnt in one of the selected sections
|
|
|
946 |
if (exists $myData{_SELECTED_SECTIONS}) {
|
|
|
947 |
$self->is_selected($text) or return ($myData{_CUTTING} = 1);
|
|
|
948 |
}
|
|
|
949 |
|
|
|
950 |
## If we havent already, perform any desired preprocessing and
|
|
|
951 |
## then re-check the "cutting" state
|
|
|
952 |
unless ($wantNonPods) {
|
|
|
953 |
$text = $self->preprocess_paragraph($text, $line_num);
|
|
|
954 |
return 1 unless ((defined $text) and (length $text));
|
|
|
955 |
return 1 if ($myData{_CUTTING});
|
|
|
956 |
}
|
|
|
957 |
|
|
|
958 |
## Look for one of the three types of paragraphs
|
|
|
959 |
my ($pfx, $cmd, $arg, $sep) = ('', '', '', '');
|
|
|
960 |
my $pod_para = undef;
|
|
|
961 |
if ($text =~ /^(={1,2})(?=\S)/) {
|
|
|
962 |
## Looks like a command paragraph. Capture the command prefix used
|
|
|
963 |
## ("=" or "=="), as well as the command-name, its paragraph text,
|
|
|
964 |
## and whatever sequence of characters was used to separate them
|
|
|
965 |
$pfx = $1;
|
|
|
966 |
$_ = substr($text, length $pfx);
|
|
|
967 |
($cmd, $sep, $text) = split /(\s+)/, $_, 2;
|
|
|
968 |
## If this is a "cut" directive then we dont need to do anything
|
|
|
969 |
## except return to "cutting" mode.
|
|
|
970 |
if ($cmd eq 'cut') {
|
|
|
971 |
$myData{_CUTTING} = 1;
|
|
|
972 |
return unless $myOpts{'-process_cut_cmd'};
|
|
|
973 |
}
|
|
|
974 |
}
|
|
|
975 |
## Save the attributes indicating how the command was specified.
|
|
|
976 |
$pod_para = new Pod::Paragraph(
|
|
|
977 |
-name => $cmd,
|
|
|
978 |
-text => $text,
|
|
|
979 |
-prefix => $pfx,
|
|
|
980 |
-separator => $sep,
|
|
|
981 |
-file => $myData{_INFILE},
|
|
|
982 |
-line => $line_num
|
|
|
983 |
);
|
|
|
984 |
# ## Invoke appropriate callbacks
|
|
|
985 |
# if (exists $myData{_CALLBACKS}) {
|
|
|
986 |
# ## Look through the callback list, invoke callbacks,
|
|
|
987 |
# ## then see if we need to do the default actions
|
|
|
988 |
# ## (invoke_callbacks will return true if we do).
|
|
|
989 |
# return 1 unless $self->invoke_callbacks($cmd, $text, $line_num, $pod_para);
|
|
|
990 |
# }
|
|
|
991 |
|
|
|
992 |
# If the last paragraph ended in whitespace, and we're not between verbatim blocks, carp
|
|
|
993 |
if ($myData{_WHITESPACE} and $myOpts{'-warnings'}
|
|
|
994 |
and not ($text =~ /^\s+/ and ($myData{_PREVIOUS}||"") eq "verbatim")) {
|
|
|
995 |
my $errorsub = $self->errorsub();
|
|
|
996 |
my $line = $line_num - 1;
|
|
|
997 |
my $errmsg = "*** WARNING: line containing nothing but whitespace".
|
|
|
998 |
" in paragraph at line $line in file $myData{_INFILE}\n";
|
|
|
999 |
(ref $errorsub) and &{$errorsub}($errmsg)
|
|
|
1000 |
or (defined $errorsub) and $self->$errorsub($errmsg)
|
|
|
1001 |
or carp($errmsg);
|
|
|
1002 |
}
|
|
|
1003 |
|
|
|
1004 |
if (length $cmd) {
|
|
|
1005 |
## A command paragraph
|
|
|
1006 |
$self->command($cmd, $text, $line_num, $pod_para);
|
|
|
1007 |
$myData{_PREVIOUS} = $cmd;
|
|
|
1008 |
}
|
|
|
1009 |
elsif ($text =~ /^\s+/) {
|
|
|
1010 |
## Indented text - must be a verbatim paragraph
|
|
|
1011 |
$self->verbatim($text, $line_num, $pod_para);
|
|
|
1012 |
$myData{_PREVIOUS} = "verbatim";
|
|
|
1013 |
}
|
|
|
1014 |
else {
|
|
|
1015 |
## Looks like an ordinary block of text
|
|
|
1016 |
$self->textblock($text, $line_num, $pod_para);
|
|
|
1017 |
$myData{_PREVIOUS} = "textblock";
|
|
|
1018 |
}
|
|
|
1019 |
|
|
|
1020 |
# Update the whitespace for the next time around
|
|
|
1021 |
$myData{_WHITESPACE} = $text =~ /^[^\S\r\n]+\Z/m ? 1 : 0;
|
|
|
1022 |
|
|
|
1023 |
return 1;
|
|
|
1024 |
}
|
|
|
1025 |
|
|
|
1026 |
##---------------------------------------------------------------------------
|
|
|
1027 |
|
|
|
1028 |
=head1 B<parse_from_filehandle()>
|
|
|
1029 |
|
|
|
1030 |
$parser->parse_from_filehandle($in_fh,$out_fh);
|
|
|
1031 |
|
|
|
1032 |
This method takes an input filehandle (which is assumed to already be
|
|
|
1033 |
opened for reading) and reads the entire input stream looking for blocks
|
|
|
1034 |
(paragraphs) of POD documentation to be processed. If no first argument
|
|
|
1035 |
is given the default input filehandle C<STDIN> is used.
|
|
|
1036 |
|
|
|
1037 |
The C<$in_fh> parameter may be any object that provides a B<getline()>
|
|
|
1038 |
method to retrieve a single line of input text (hence, an appropriate
|
|
|
1039 |
wrapper object could be used to parse PODs from a single string or an
|
|
|
1040 |
array of strings).
|
|
|
1041 |
|
|
|
1042 |
Using C<$in_fh-E<gt>getline()>, input is read line-by-line and assembled
|
|
|
1043 |
into paragraphs or "blocks" (which are separated by lines containing
|
|
|
1044 |
nothing but whitespace). For each block of POD documentation
|
|
|
1045 |
encountered it will invoke a method to parse the given paragraph.
|
|
|
1046 |
|
|
|
1047 |
If a second argument is given then it should correspond to a filehandle where
|
|
|
1048 |
output should be sent (otherwise the default output filehandle is
|
|
|
1049 |
C<STDOUT> if no output filehandle is currently in use).
|
|
|
1050 |
|
|
|
1051 |
B<NOTE:> For performance reasons, this method caches the input stream at
|
|
|
1052 |
the top of the stack in a local variable. Any attempts by clients to
|
|
|
1053 |
change the stack contents during processing when in the midst executing
|
|
|
1054 |
of this method I<will not affect> the input stream used by the current
|
|
|
1055 |
invocation of this method.
|
|
|
1056 |
|
|
|
1057 |
This method does I<not> usually need to be overridden by subclasses.
|
|
|
1058 |
|
|
|
1059 |
=cut
|
|
|
1060 |
|
|
|
1061 |
sub parse_from_filehandle {
|
|
|
1062 |
my $self = shift;
|
|
|
1063 |
my %opts = (ref $_[0] eq 'HASH') ? %{ shift() } : ();
|
|
|
1064 |
my ($in_fh, $out_fh) = @_;
|
|
|
1065 |
$in_fh = \*STDIN unless ($in_fh);
|
|
|
1066 |
local *myData = $self; ## alias to avoid deref-ing overhead
|
|
|
1067 |
local *myOpts = ($myData{_PARSEOPTS} ||= {}); ## get parse-options
|
|
|
1068 |
local $_;
|
|
|
1069 |
|
|
|
1070 |
## Put this stream at the top of the stack and do beginning-of-input
|
|
|
1071 |
## processing. NOTE that $in_fh might be reset during this process.
|
|
|
1072 |
my $topstream = $self->_push_input_stream($in_fh, $out_fh);
|
|
|
1073 |
(exists $opts{-cutting}) and $self->cutting( $opts{-cutting} );
|
|
|
1074 |
|
|
|
1075 |
## Initialize line/paragraph
|
|
|
1076 |
my ($textline, $paragraph) = ('', '');
|
|
|
1077 |
my ($nlines, $plines) = (0, 0);
|
|
|
1078 |
|
|
|
1079 |
## Use <$fh> instead of $fh->getline where possible (for speed)
|
|
|
1080 |
$_ = ref $in_fh;
|
|
|
1081 |
my $tied_fh = (/^(?:GLOB|FileHandle|IO::\w+)$/ or tied $in_fh);
|
|
|
1082 |
|
|
|
1083 |
## Read paragraphs line-by-line
|
|
|
1084 |
while (defined ($textline = $tied_fh ? <$in_fh> : $in_fh->getline)) {
|
|
|
1085 |
$textline = $self->preprocess_line($textline, ++$nlines);
|
|
|
1086 |
next unless ((defined $textline) && (length $textline));
|
|
|
1087 |
|
|
|
1088 |
if ((! length $paragraph) && ($textline =~ /^==/)) {
|
|
|
1089 |
## '==' denotes a one-line command paragraph
|
|
|
1090 |
$paragraph = $textline;
|
|
|
1091 |
$plines = 1;
|
|
|
1092 |
$textline = '';
|
|
|
1093 |
} else {
|
|
|
1094 |
## Append this line to the current paragraph
|
|
|
1095 |
$paragraph .= $textline;
|
|
|
1096 |
++$plines;
|
|
|
1097 |
}
|
|
|
1098 |
|
|
|
1099 |
## See if this line is blank and ends the current paragraph.
|
|
|
1100 |
## If it isnt, then keep iterating until it is.
|
|
|
1101 |
next unless (($textline =~ /^([^\S\r\n]*)[\r\n]*$/)
|
|
|
1102 |
&& (length $paragraph));
|
|
|
1103 |
|
|
|
1104 |
## Now process the paragraph
|
|
|
1105 |
parse_paragraph($self, $paragraph, ($nlines - $plines) + 1);
|
|
|
1106 |
$paragraph = '';
|
|
|
1107 |
$plines = 0;
|
|
|
1108 |
}
|
|
|
1109 |
## Dont forget about the last paragraph in the file
|
|
|
1110 |
if (length $paragraph) {
|
|
|
1111 |
parse_paragraph($self, $paragraph, ($nlines - $plines) + 1)
|
|
|
1112 |
}
|
|
|
1113 |
|
|
|
1114 |
## Now pop the input stream off the top of the input stack.
|
|
|
1115 |
$self->_pop_input_stream();
|
|
|
1116 |
}
|
|
|
1117 |
|
|
|
1118 |
##---------------------------------------------------------------------------
|
|
|
1119 |
|
|
|
1120 |
=head1 B<parse_from_file()>
|
|
|
1121 |
|
|
|
1122 |
$parser->parse_from_file($filename,$outfile);
|
|
|
1123 |
|
|
|
1124 |
This method takes a filename and does the following:
|
|
|
1125 |
|
|
|
1126 |
=over 2
|
|
|
1127 |
|
|
|
1128 |
=item *
|
|
|
1129 |
|
|
|
1130 |
opens the input and output files for reading
|
|
|
1131 |
(creating the appropriate filehandles)
|
|
|
1132 |
|
|
|
1133 |
=item *
|
|
|
1134 |
|
|
|
1135 |
invokes the B<parse_from_filehandle()> method passing it the
|
|
|
1136 |
corresponding input and output filehandles.
|
|
|
1137 |
|
|
|
1138 |
=item *
|
|
|
1139 |
|
|
|
1140 |
closes the input and output files.
|
|
|
1141 |
|
|
|
1142 |
=back
|
|
|
1143 |
|
|
|
1144 |
If the special input filename "-" or "<&STDIN" is given then the STDIN
|
|
|
1145 |
filehandle is used for input (and no open or close is performed). If no
|
|
|
1146 |
input filename is specified then "-" is implied. Filehandle references,
|
|
|
1147 |
or objects that support the regular IO operations (like C<E<lt>$fhE<gt>>
|
|
|
1148 |
or C<$fh-<Egt>getline>) are also accepted; the handles must already be
|
|
|
1149 |
opened.
|
|
|
1150 |
|
|
|
1151 |
If a second argument is given then it should be the name of the desired
|
|
|
1152 |
output file. If the special output filename "-" or ">&STDOUT" is given
|
|
|
1153 |
then the STDOUT filehandle is used for output (and no open or close is
|
|
|
1154 |
performed). If the special output filename ">&STDERR" is given then the
|
|
|
1155 |
STDERR filehandle is used for output (and no open or close is
|
|
|
1156 |
performed). If no output filehandle is currently in use and no output
|
|
|
1157 |
filename is specified, then "-" is implied.
|
|
|
1158 |
Alternatively, filehandle references or objects that support the regular
|
|
|
1159 |
IO operations (like C<print>, e.g. L<IO::String>) are also accepted;
|
|
|
1160 |
the object must already be opened.
|
|
|
1161 |
|
|
|
1162 |
This method does I<not> usually need to be overridden by subclasses.
|
|
|
1163 |
|
|
|
1164 |
=cut
|
|
|
1165 |
|
|
|
1166 |
sub parse_from_file {
|
|
|
1167 |
my $self = shift;
|
|
|
1168 |
my %opts = (ref $_[0] eq 'HASH') ? %{ shift() } : ();
|
|
|
1169 |
my ($infile, $outfile) = @_;
|
|
|
1170 |
my ($in_fh, $out_fh);
|
|
|
1171 |
if ($] < 5.006) {
|
|
|
1172 |
($in_fh, $out_fh) = (gensym(), gensym());
|
|
|
1173 |
}
|
|
|
1174 |
my ($close_input, $close_output) = (0, 0);
|
|
|
1175 |
local *myData = $self;
|
|
|
1176 |
local *_;
|
|
|
1177 |
|
|
|
1178 |
## Is $infile a filename or a (possibly implied) filehandle
|
|
|
1179 |
if (defined $infile && ref $infile) {
|
|
|
1180 |
if (ref($infile) =~ /^(SCALAR|ARRAY|HASH|CODE|REF)$/) {
|
|
|
1181 |
croak "Input from $1 reference not supported!\n";
|
|
|
1182 |
}
|
|
|
1183 |
## Must be a filehandle-ref (or else assume its a ref to an object
|
|
|
1184 |
## that supports the common IO read operations).
|
|
|
1185 |
$myData{_INFILE} = ${$infile};
|
|
|
1186 |
$in_fh = $infile;
|
|
|
1187 |
}
|
|
|
1188 |
elsif (!defined($infile) || !length($infile) || ($infile eq '-')
|
|
|
1189 |
|| ($infile =~ /^<&(?:STDIN|0)$/i))
|
|
|
1190 |
{
|
|
|
1191 |
## Not a filename, just a string implying STDIN
|
|
|
1192 |
$infile ||= '-';
|
|
|
1193 |
$myData{_INFILE} = '<standard input>';
|
|
|
1194 |
$in_fh = \*STDIN;
|
|
|
1195 |
}
|
|
|
1196 |
else {
|
|
|
1197 |
## We have a filename, open it for reading
|
|
|
1198 |
$myData{_INFILE} = $infile;
|
|
|
1199 |
open($in_fh, "< $infile") or
|
|
|
1200 |
croak "Can't open $infile for reading: $!\n";
|
|
|
1201 |
$close_input = 1;
|
|
|
1202 |
}
|
|
|
1203 |
|
|
|
1204 |
## NOTE: we need to be *very* careful when "defaulting" the output
|
|
|
1205 |
## file. We only want to use a default if this is the beginning of
|
|
|
1206 |
## the entire document (but *not* if this is an included file). We
|
|
|
1207 |
## determine this by seeing if the input stream stack has been set-up
|
|
|
1208 |
## already
|
|
|
1209 |
|
|
|
1210 |
## Is $outfile a filename, a (possibly implied) filehandle, maybe a ref?
|
|
|
1211 |
if (ref $outfile) {
|
|
|
1212 |
## we need to check for ref() first, as other checks involve reading
|
|
|
1213 |
if (ref($outfile) =~ /^(ARRAY|HASH|CODE)$/) {
|
|
|
1214 |
croak "Output to $1 reference not supported!\n";
|
|
|
1215 |
}
|
|
|
1216 |
elsif (ref($outfile) eq 'SCALAR') {
|
|
|
1217 |
# # NOTE: IO::String isn't a part of the perl distribution,
|
|
|
1218 |
# # so probably we shouldn't support this case...
|
|
|
1219 |
# require IO::String;
|
|
|
1220 |
# $myData{_OUTFILE} = "$outfile";
|
|
|
1221 |
# $out_fh = IO::String->new($outfile);
|
|
|
1222 |
croak "Output to SCALAR reference not supported!\n";
|
|
|
1223 |
}
|
|
|
1224 |
else {
|
|
|
1225 |
## Must be a filehandle-ref (or else assume its a ref to an
|
|
|
1226 |
## object that supports the common IO write operations).
|
|
|
1227 |
$myData{_OUTFILE} = ${$outfile};
|
|
|
1228 |
$out_fh = $outfile;
|
|
|
1229 |
}
|
|
|
1230 |
}
|
|
|
1231 |
elsif (!defined($outfile) || !length($outfile) || ($outfile eq '-')
|
|
|
1232 |
|| ($outfile =~ /^>&?(?:STDOUT|1)$/i))
|
|
|
1233 |
{
|
|
|
1234 |
if (defined $myData{_TOP_STREAM}) {
|
|
|
1235 |
$out_fh = $myData{_OUTPUT};
|
|
|
1236 |
}
|
|
|
1237 |
else {
|
|
|
1238 |
## Not a filename, just a string implying STDOUT
|
|
|
1239 |
$outfile ||= '-';
|
|
|
1240 |
$myData{_OUTFILE} = '<standard output>';
|
|
|
1241 |
$out_fh = \*STDOUT;
|
|
|
1242 |
}
|
|
|
1243 |
}
|
|
|
1244 |
elsif ($outfile =~ /^>&(STDERR|2)$/i) {
|
|
|
1245 |
## Not a filename, just a string implying STDERR
|
|
|
1246 |
$myData{_OUTFILE} = '<standard error>';
|
|
|
1247 |
$out_fh = \*STDERR;
|
|
|
1248 |
}
|
|
|
1249 |
else {
|
|
|
1250 |
## We have a filename, open it for writing
|
|
|
1251 |
$myData{_OUTFILE} = $outfile;
|
|
|
1252 |
(-d $outfile) and croak "$outfile is a directory, not POD input!\n";
|
|
|
1253 |
open($out_fh, "> $outfile") or
|
|
|
1254 |
croak "Can't open $outfile for writing: $!\n";
|
|
|
1255 |
$close_output = 1;
|
|
|
1256 |
}
|
|
|
1257 |
|
|
|
1258 |
## Whew! That was a lot of work to set up reasonably/robust behavior
|
|
|
1259 |
## in the case of a non-filename for reading and writing. Now we just
|
|
|
1260 |
## have to parse the input and close the handles when we're finished.
|
|
|
1261 |
$self->parse_from_filehandle(\%opts, $in_fh, $out_fh);
|
|
|
1262 |
|
|
|
1263 |
$close_input and
|
|
|
1264 |
close($in_fh) || croak "Can't close $infile after reading: $!\n";
|
|
|
1265 |
$close_output and
|
|
|
1266 |
close($out_fh) || croak "Can't close $outfile after writing: $!\n";
|
|
|
1267 |
}
|
|
|
1268 |
|
|
|
1269 |
#############################################################################
|
|
|
1270 |
|
|
|
1271 |
=head1 ACCESSOR METHODS
|
|
|
1272 |
|
|
|
1273 |
Clients of B<Pod::Parser> should use the following methods to access
|
|
|
1274 |
instance data fields:
|
|
|
1275 |
|
|
|
1276 |
=cut
|
|
|
1277 |
|
|
|
1278 |
##---------------------------------------------------------------------------
|
|
|
1279 |
|
|
|
1280 |
=head1 B<errorsub()>
|
|
|
1281 |
|
|
|
1282 |
$parser->errorsub("method_name");
|
|
|
1283 |
$parser->errorsub(\&warn_user);
|
|
|
1284 |
$parser->errorsub(sub { print STDERR, @_ });
|
|
|
1285 |
|
|
|
1286 |
Specifies the method or subroutine to use when printing error messages
|
|
|
1287 |
about POD syntax. The supplied method/subroutine I<must> return TRUE upon
|
|
|
1288 |
successful printing of the message. If C<undef> is given, then the B<carp>
|
|
|
1289 |
builtin is used to issue error messages (this is the default behavior).
|
|
|
1290 |
|
|
|
1291 |
my $errorsub = $parser->errorsub()
|
|
|
1292 |
my $errmsg = "This is an error message!\n"
|
|
|
1293 |
(ref $errorsub) and &{$errorsub}($errmsg)
|
|
|
1294 |
or (defined $errorsub) and $parser->$errorsub($errmsg)
|
|
|
1295 |
or carp($errmsg);
|
|
|
1296 |
|
|
|
1297 |
Returns a method name, or else a reference to the user-supplied subroutine
|
|
|
1298 |
used to print error messages. Returns C<undef> if the B<carp> builtin
|
|
|
1299 |
is used to issue error messages (this is the default behavior).
|
|
|
1300 |
|
|
|
1301 |
=cut
|
|
|
1302 |
|
|
|
1303 |
sub errorsub {
|
|
|
1304 |
return (@_ > 1) ? ($_[0]->{_ERRORSUB} = $_[1]) : $_[0]->{_ERRORSUB};
|
|
|
1305 |
}
|
|
|
1306 |
|
|
|
1307 |
##---------------------------------------------------------------------------
|
|
|
1308 |
|
|
|
1309 |
=head1 B<cutting()>
|
|
|
1310 |
|
|
|
1311 |
$boolean = $parser->cutting();
|
|
|
1312 |
|
|
|
1313 |
Returns the current C<cutting> state: a boolean-valued scalar which
|
|
|
1314 |
evaluates to true if text from the input file is currently being "cut"
|
|
|
1315 |
(meaning it is I<not> considered part of the POD document).
|
|
|
1316 |
|
|
|
1317 |
$parser->cutting($boolean);
|
|
|
1318 |
|
|
|
1319 |
Sets the current C<cutting> state to the given value and returns the
|
|
|
1320 |
result.
|
|
|
1321 |
|
|
|
1322 |
=cut
|
|
|
1323 |
|
|
|
1324 |
sub cutting {
|
|
|
1325 |
return (@_ > 1) ? ($_[0]->{_CUTTING} = $_[1]) : $_[0]->{_CUTTING};
|
|
|
1326 |
}
|
|
|
1327 |
|
|
|
1328 |
##---------------------------------------------------------------------------
|
|
|
1329 |
|
|
|
1330 |
##---------------------------------------------------------------------------
|
|
|
1331 |
|
|
|
1332 |
=head1 B<parseopts()>
|
|
|
1333 |
|
|
|
1334 |
When invoked with no additional arguments, B<parseopts> returns a hashtable
|
|
|
1335 |
of all the current parsing options.
|
|
|
1336 |
|
|
|
1337 |
## See if we are parsing non-POD sections as well as POD ones
|
|
|
1338 |
my %opts = $parser->parseopts();
|
|
|
1339 |
$opts{'-want_nonPODs}' and print "-want_nonPODs\n";
|
|
|
1340 |
|
|
|
1341 |
When invoked using a single string, B<parseopts> treats the string as the
|
|
|
1342 |
name of a parse-option and returns its corresponding value if it exists
|
|
|
1343 |
(returns C<undef> if it doesn't).
|
|
|
1344 |
|
|
|
1345 |
## Did we ask to see '=cut' paragraphs?
|
|
|
1346 |
my $want_cut = $parser->parseopts('-process_cut_cmd');
|
|
|
1347 |
$want_cut and print "-process_cut_cmd\n";
|
|
|
1348 |
|
|
|
1349 |
When invoked with multiple arguments, B<parseopts> treats them as
|
|
|
1350 |
key/value pairs and the specified parse-option names are set to the
|
|
|
1351 |
given values. Any unspecified parse-options are unaffected.
|
|
|
1352 |
|
|
|
1353 |
## Set them back to the default
|
|
|
1354 |
$parser->parseopts(-warnings => 0);
|
|
|
1355 |
|
|
|
1356 |
When passed a single hash-ref, B<parseopts> uses that hash to completely
|
|
|
1357 |
reset the existing parse-options, all previous parse-option values
|
|
|
1358 |
are lost.
|
|
|
1359 |
|
|
|
1360 |
## Reset all options to default
|
|
|
1361 |
$parser->parseopts( { } );
|
|
|
1362 |
|
|
|
1363 |
See L<"PARSING OPTIONS"> for more information on the name and meaning of each
|
|
|
1364 |
parse-option currently recognized.
|
|
|
1365 |
|
|
|
1366 |
=cut
|
|
|
1367 |
|
|
|
1368 |
sub parseopts {
|
|
|
1369 |
local *myData = shift;
|
|
|
1370 |
local *myOpts = ($myData{_PARSEOPTS} ||= {});
|
|
|
1371 |
return %myOpts if (@_ == 0);
|
|
|
1372 |
if (@_ == 1) {
|
|
|
1373 |
local $_ = shift;
|
|
|
1374 |
return ref($_) ? $myData{_PARSEOPTS} = $_ : $myOpts{$_};
|
|
|
1375 |
}
|
|
|
1376 |
my @newOpts = (%myOpts, @_);
|
|
|
1377 |
$myData{_PARSEOPTS} = { @newOpts };
|
|
|
1378 |
}
|
|
|
1379 |
|
|
|
1380 |
##---------------------------------------------------------------------------
|
|
|
1381 |
|
|
|
1382 |
=head1 B<output_file()>
|
|
|
1383 |
|
|
|
1384 |
$fname = $parser->output_file();
|
|
|
1385 |
|
|
|
1386 |
Returns the name of the output file being written.
|
|
|
1387 |
|
|
|
1388 |
=cut
|
|
|
1389 |
|
|
|
1390 |
sub output_file {
|
|
|
1391 |
return $_[0]->{_OUTFILE};
|
|
|
1392 |
}
|
|
|
1393 |
|
|
|
1394 |
##---------------------------------------------------------------------------
|
|
|
1395 |
|
|
|
1396 |
=head1 B<output_handle()>
|
|
|
1397 |
|
|
|
1398 |
$fhandle = $parser->output_handle();
|
|
|
1399 |
|
|
|
1400 |
Returns the output filehandle object.
|
|
|
1401 |
|
|
|
1402 |
=cut
|
|
|
1403 |
|
|
|
1404 |
sub output_handle {
|
|
|
1405 |
return $_[0]->{_OUTPUT};
|
|
|
1406 |
}
|
|
|
1407 |
|
|
|
1408 |
##---------------------------------------------------------------------------
|
|
|
1409 |
|
|
|
1410 |
=head1 B<input_file()>
|
|
|
1411 |
|
|
|
1412 |
$fname = $parser->input_file();
|
|
|
1413 |
|
|
|
1414 |
Returns the name of the input file being read.
|
|
|
1415 |
|
|
|
1416 |
=cut
|
|
|
1417 |
|
|
|
1418 |
sub input_file {
|
|
|
1419 |
return $_[0]->{_INFILE};
|
|
|
1420 |
}
|
|
|
1421 |
|
|
|
1422 |
##---------------------------------------------------------------------------
|
|
|
1423 |
|
|
|
1424 |
=head1 B<input_handle()>
|
|
|
1425 |
|
|
|
1426 |
$fhandle = $parser->input_handle();
|
|
|
1427 |
|
|
|
1428 |
Returns the current input filehandle object.
|
|
|
1429 |
|
|
|
1430 |
=cut
|
|
|
1431 |
|
|
|
1432 |
sub input_handle {
|
|
|
1433 |
return $_[0]->{_INPUT};
|
|
|
1434 |
}
|
|
|
1435 |
|
|
|
1436 |
##---------------------------------------------------------------------------
|
|
|
1437 |
|
|
|
1438 |
=begin __PRIVATE__
|
|
|
1439 |
|
|
|
1440 |
=head1 B<input_streams()>
|
|
|
1441 |
|
|
|
1442 |
$listref = $parser->input_streams();
|
|
|
1443 |
|
|
|
1444 |
Returns a reference to an array which corresponds to the stack of all
|
|
|
1445 |
the input streams that are currently in the middle of being parsed.
|
|
|
1446 |
|
|
|
1447 |
While parsing an input stream, it is possible to invoke
|
|
|
1448 |
B<parse_from_file()> or B<parse_from_filehandle()> to parse a new input
|
|
|
1449 |
stream and then return to parsing the previous input stream. Each input
|
|
|
1450 |
stream to be parsed is pushed onto the end of this input stack
|
|
|
1451 |
before any of its input is read. The input stream that is currently
|
|
|
1452 |
being parsed is always at the end (or top) of the input stack. When an
|
|
|
1453 |
input stream has been exhausted, it is popped off the end of the
|
|
|
1454 |
input stack.
|
|
|
1455 |
|
|
|
1456 |
Each element on this input stack is a reference to C<Pod::InputSource>
|
|
|
1457 |
object. Please see L<Pod::InputObjects> for more details.
|
|
|
1458 |
|
|
|
1459 |
This method might be invoked when printing diagnostic messages, for example,
|
|
|
1460 |
to obtain the name and line number of the all input files that are currently
|
|
|
1461 |
being processed.
|
|
|
1462 |
|
|
|
1463 |
=end __PRIVATE__
|
|
|
1464 |
|
|
|
1465 |
=cut
|
|
|
1466 |
|
|
|
1467 |
sub input_streams {
|
|
|
1468 |
return $_[0]->{_INPUT_STREAMS};
|
|
|
1469 |
}
|
|
|
1470 |
|
|
|
1471 |
##---------------------------------------------------------------------------
|
|
|
1472 |
|
|
|
1473 |
=begin __PRIVATE__
|
|
|
1474 |
|
|
|
1475 |
=head1 B<top_stream()>
|
|
|
1476 |
|
|
|
1477 |
$hashref = $parser->top_stream();
|
|
|
1478 |
|
|
|
1479 |
Returns a reference to the hash-table that represents the element
|
|
|
1480 |
that is currently at the top (end) of the input stream stack
|
|
|
1481 |
(see L<"input_streams()">). The return value will be the C<undef>
|
|
|
1482 |
if the input stack is empty.
|
|
|
1483 |
|
|
|
1484 |
This method might be used when printing diagnostic messages, for example,
|
|
|
1485 |
to obtain the name and line number of the current input file.
|
|
|
1486 |
|
|
|
1487 |
=end __PRIVATE__
|
|
|
1488 |
|
|
|
1489 |
=cut
|
|
|
1490 |
|
|
|
1491 |
sub top_stream {
|
|
|
1492 |
return $_[0]->{_TOP_STREAM} || undef;
|
|
|
1493 |
}
|
|
|
1494 |
|
|
|
1495 |
#############################################################################
|
|
|
1496 |
|
|
|
1497 |
=head1 PRIVATE METHODS AND DATA
|
|
|
1498 |
|
|
|
1499 |
B<Pod::Parser> makes use of several internal methods and data fields
|
|
|
1500 |
which clients should not need to see or use. For the sake of avoiding
|
|
|
1501 |
name collisions for client data and methods, these methods and fields
|
|
|
1502 |
are briefly discussed here. Determined hackers may obtain further
|
|
|
1503 |
information about them by reading the B<Pod::Parser> source code.
|
|
|
1504 |
|
|
|
1505 |
Private data fields are stored in the hash-object whose reference is
|
|
|
1506 |
returned by the B<new()> constructor for this class. The names of all
|
|
|
1507 |
private methods and data-fields used by B<Pod::Parser> begin with a
|
|
|
1508 |
prefix of "_" and match the regular expression C</^_\w+$/>.
|
|
|
1509 |
|
|
|
1510 |
=cut
|
|
|
1511 |
|
|
|
1512 |
##---------------------------------------------------------------------------
|
|
|
1513 |
|
|
|
1514 |
=begin _PRIVATE_
|
|
|
1515 |
|
|
|
1516 |
=head1 B<_push_input_stream()>
|
|
|
1517 |
|
|
|
1518 |
$hashref = $parser->_push_input_stream($in_fh,$out_fh);
|
|
|
1519 |
|
|
|
1520 |
This method will push the given input stream on the input stack and
|
|
|
1521 |
perform any necessary beginning-of-document or beginning-of-file
|
|
|
1522 |
processing. The argument C<$in_fh> is the input stream filehandle to
|
|
|
1523 |
push, and C<$out_fh> is the corresponding output filehandle to use (if
|
|
|
1524 |
it is not given or is undefined, then the current output stream is used,
|
|
|
1525 |
which defaults to standard output if it doesnt exist yet).
|
|
|
1526 |
|
|
|
1527 |
The value returned will be reference to the hash-table that represents
|
|
|
1528 |
the new top of the input stream stack. I<Please Note> that it is
|
|
|
1529 |
possible for this method to use default values for the input and output
|
|
|
1530 |
file handles. If this happens, you will need to look at the C<INPUT>
|
|
|
1531 |
and C<OUTPUT> instance data members to determine their new values.
|
|
|
1532 |
|
|
|
1533 |
=end _PRIVATE_
|
|
|
1534 |
|
|
|
1535 |
=cut
|
|
|
1536 |
|
|
|
1537 |
sub _push_input_stream {
|
|
|
1538 |
my ($self, $in_fh, $out_fh) = @_;
|
|
|
1539 |
local *myData = $self;
|
|
|
1540 |
|
|
|
1541 |
## Initialize stuff for the entire document if this is *not*
|
|
|
1542 |
## an included file.
|
|
|
1543 |
##
|
|
|
1544 |
## NOTE: we need to be *very* careful when "defaulting" the output
|
|
|
1545 |
## filehandle. We only want to use a default value if this is the
|
|
|
1546 |
## beginning of the entire document (but *not* if this is an included
|
|
|
1547 |
## file).
|
|
|
1548 |
unless (defined $myData{_TOP_STREAM}) {
|
|
|
1549 |
$out_fh = \*STDOUT unless (defined $out_fh);
|
|
|
1550 |
$myData{_CUTTING} = 1; ## current "cutting" state
|
|
|
1551 |
$myData{_INPUT_STREAMS} = []; ## stack of all input streams
|
|
|
1552 |
}
|
|
|
1553 |
|
|
|
1554 |
## Initialize input indicators
|
|
|
1555 |
$myData{_OUTFILE} = '(unknown)' unless (defined $myData{_OUTFILE});
|
|
|
1556 |
$myData{_OUTPUT} = $out_fh if (defined $out_fh);
|
|
|
1557 |
$in_fh = \*STDIN unless (defined $in_fh);
|
|
|
1558 |
$myData{_INFILE} = '(unknown)' unless (defined $myData{_INFILE});
|
|
|
1559 |
$myData{_INPUT} = $in_fh;
|
|
|
1560 |
my $input_top = $myData{_TOP_STREAM}
|
|
|
1561 |
= new Pod::InputSource(
|
|
|
1562 |
-name => $myData{_INFILE},
|
|
|
1563 |
-handle => $in_fh,
|
|
|
1564 |
-was_cutting => $myData{_CUTTING}
|
|
|
1565 |
);
|
|
|
1566 |
local *input_stack = $myData{_INPUT_STREAMS};
|
|
|
1567 |
push(@input_stack, $input_top);
|
|
|
1568 |
|
|
|
1569 |
## Perform beginning-of-document and/or beginning-of-input processing
|
|
|
1570 |
$self->begin_pod() if (@input_stack == 1);
|
|
|
1571 |
$self->begin_input();
|
|
|
1572 |
|
|
|
1573 |
return $input_top;
|
|
|
1574 |
}
|
|
|
1575 |
|
|
|
1576 |
##---------------------------------------------------------------------------
|
|
|
1577 |
|
|
|
1578 |
=begin _PRIVATE_
|
|
|
1579 |
|
|
|
1580 |
=head1 B<_pop_input_stream()>
|
|
|
1581 |
|
|
|
1582 |
$hashref = $parser->_pop_input_stream();
|
|
|
1583 |
|
|
|
1584 |
This takes no arguments. It will perform any necessary end-of-file or
|
|
|
1585 |
end-of-document processing and then pop the current input stream from
|
|
|
1586 |
the top of the input stack.
|
|
|
1587 |
|
|
|
1588 |
The value returned will be reference to the hash-table that represents
|
|
|
1589 |
the new top of the input stream stack.
|
|
|
1590 |
|
|
|
1591 |
=end _PRIVATE_
|
|
|
1592 |
|
|
|
1593 |
=cut
|
|
|
1594 |
|
|
|
1595 |
sub _pop_input_stream {
|
|
|
1596 |
my ($self) = @_;
|
|
|
1597 |
local *myData = $self;
|
|
|
1598 |
local *input_stack = $myData{_INPUT_STREAMS};
|
|
|
1599 |
|
|
|
1600 |
## Perform end-of-input and/or end-of-document processing
|
|
|
1601 |
$self->end_input() if (@input_stack > 0);
|
|
|
1602 |
$self->end_pod() if (@input_stack == 1);
|
|
|
1603 |
|
|
|
1604 |
## Restore cutting state to whatever it was before we started
|
|
|
1605 |
## parsing this file.
|
|
|
1606 |
my $old_top = pop(@input_stack);
|
|
|
1607 |
$myData{_CUTTING} = $old_top->was_cutting();
|
|
|
1608 |
|
|
|
1609 |
## Dont forget to reset the input indicators
|
|
|
1610 |
my $input_top = undef;
|
|
|
1611 |
if (@input_stack > 0) {
|
|
|
1612 |
$input_top = $myData{_TOP_STREAM} = $input_stack[-1];
|
|
|
1613 |
$myData{_INFILE} = $input_top->name();
|
|
|
1614 |
$myData{_INPUT} = $input_top->handle();
|
|
|
1615 |
} else {
|
|
|
1616 |
delete $myData{_TOP_STREAM};
|
|
|
1617 |
delete $myData{_INPUT_STREAMS};
|
|
|
1618 |
}
|
|
|
1619 |
|
|
|
1620 |
return $input_top;
|
|
|
1621 |
}
|
|
|
1622 |
|
|
|
1623 |
#############################################################################
|
|
|
1624 |
|
|
|
1625 |
=head1 TREE-BASED PARSING
|
|
|
1626 |
|
|
|
1627 |
If straightforward stream-based parsing wont meet your needs (as is
|
|
|
1628 |
likely the case for tasks such as translating PODs into structured
|
|
|
1629 |
markup languages like HTML and XML) then you may need to take the
|
|
|
1630 |
tree-based approach. Rather than doing everything in one pass and
|
|
|
1631 |
calling the B<interpolate()> method to expand sequences into text, it
|
|
|
1632 |
may be desirable to instead create a parse-tree using the B<parse_text()>
|
|
|
1633 |
method to return a tree-like structure which may contain an ordered
|
|
|
1634 |
list of children (each of which may be a text-string, or a similar
|
|
|
1635 |
tree-like structure).
|
|
|
1636 |
|
|
|
1637 |
Pay special attention to L<"METHODS FOR PARSING AND PROCESSING"> and
|
|
|
1638 |
to the objects described in L<Pod::InputObjects>. The former describes
|
|
|
1639 |
the gory details and parameters for how to customize and extend the
|
|
|
1640 |
parsing behavior of B<Pod::Parser>. B<Pod::InputObjects> provides
|
|
|
1641 |
several objects that may all be used interchangeably as parse-trees. The
|
|
|
1642 |
most obvious one is the B<Pod::ParseTree> object. It defines the basic
|
|
|
1643 |
interface and functionality that all things trying to be a POD parse-tree
|
|
|
1644 |
should do. A B<Pod::ParseTree> is defined such that each "node" may be a
|
|
|
1645 |
text-string, or a reference to another parse-tree. Each B<Pod::Paragraph>
|
|
|
1646 |
object and each B<Pod::InteriorSequence> object also supports the basic
|
|
|
1647 |
parse-tree interface.
|
|
|
1648 |
|
|
|
1649 |
The B<parse_text()> method takes a given paragraph of text, and
|
|
|
1650 |
returns a parse-tree that contains one or more children, each of which
|
|
|
1651 |
may be a text-string, or an InteriorSequence object. There are also
|
|
|
1652 |
callback-options that may be passed to B<parse_text()> to customize
|
|
|
1653 |
the way it expands or transforms interior-sequences, as well as the
|
|
|
1654 |
returned result. These callbacks can be used to create a parse-tree
|
|
|
1655 |
with custom-made objects (which may or may not support the parse-tree
|
|
|
1656 |
interface, depending on how you choose to do it).
|
|
|
1657 |
|
|
|
1658 |
If you wish to turn an entire POD document into a parse-tree, that process
|
|
|
1659 |
is fairly straightforward. The B<parse_text()> method is the key to doing
|
|
|
1660 |
this successfully. Every paragraph-callback (i.e. the polymorphic methods
|
|
|
1661 |
for B<command()>, B<verbatim()>, and B<textblock()> paragraphs) takes
|
|
|
1662 |
a B<Pod::Paragraph> object as an argument. Each paragraph object has a
|
|
|
1663 |
B<parse_tree()> method that can be used to get or set a corresponding
|
|
|
1664 |
parse-tree. So for each of those paragraph-callback methods, simply call
|
|
|
1665 |
B<parse_text()> with the options you desire, and then use the returned
|
|
|
1666 |
parse-tree to assign to the given paragraph object.
|
|
|
1667 |
|
|
|
1668 |
That gives you a parse-tree for each paragraph - so now all you need is
|
|
|
1669 |
an ordered list of paragraphs. You can maintain that yourself as a data
|
|
|
1670 |
element in the object/hash. The most straightforward way would be simply
|
|
|
1671 |
to use an array-ref, with the desired set of custom "options" for each
|
|
|
1672 |
invocation of B<parse_text>. Let's assume the desired option-set is
|
|
|
1673 |
given by the hash C<%options>. Then we might do something like the
|
|
|
1674 |
following:
|
|
|
1675 |
|
|
|
1676 |
package MyPodParserTree;
|
|
|
1677 |
|
|
|
1678 |
@ISA = qw( Pod::Parser );
|
|
|
1679 |
|
|
|
1680 |
...
|
|
|
1681 |
|
|
|
1682 |
sub begin_pod {
|
|
|
1683 |
my $self = shift;
|
|
|
1684 |
$self->{'-paragraphs'} = []; ## initialize paragraph list
|
|
|
1685 |
}
|
|
|
1686 |
|
|
|
1687 |
sub command {
|
|
|
1688 |
my ($parser, $command, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1689 |
my $ptree = $parser->parse_text({%options}, $paragraph, ...);
|
|
|
1690 |
$pod_para->parse_tree( $ptree );
|
|
|
1691 |
push @{ $self->{'-paragraphs'} }, $pod_para;
|
|
|
1692 |
}
|
|
|
1693 |
|
|
|
1694 |
sub verbatim {
|
|
|
1695 |
my ($parser, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1696 |
push @{ $self->{'-paragraphs'} }, $pod_para;
|
|
|
1697 |
}
|
|
|
1698 |
|
|
|
1699 |
sub textblock {
|
|
|
1700 |
my ($parser, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1701 |
my $ptree = $parser->parse_text({%options}, $paragraph, ...);
|
|
|
1702 |
$pod_para->parse_tree( $ptree );
|
|
|
1703 |
push @{ $self->{'-paragraphs'} }, $pod_para;
|
|
|
1704 |
}
|
|
|
1705 |
|
|
|
1706 |
...
|
|
|
1707 |
|
|
|
1708 |
package main;
|
|
|
1709 |
...
|
|
|
1710 |
my $parser = new MyPodParserTree(...);
|
|
|
1711 |
$parser->parse_from_file(...);
|
|
|
1712 |
my $paragraphs_ref = $parser->{'-paragraphs'};
|
|
|
1713 |
|
|
|
1714 |
Of course, in this module-author's humble opinion, I'd be more inclined to
|
|
|
1715 |
use the existing B<Pod::ParseTree> object than a simple array. That way
|
|
|
1716 |
everything in it, paragraphs and sequences, all respond to the same core
|
|
|
1717 |
interface for all parse-tree nodes. The result would look something like:
|
|
|
1718 |
|
|
|
1719 |
package MyPodParserTree2;
|
|
|
1720 |
|
|
|
1721 |
...
|
|
|
1722 |
|
|
|
1723 |
sub begin_pod {
|
|
|
1724 |
my $self = shift;
|
|
|
1725 |
$self->{'-ptree'} = new Pod::ParseTree; ## initialize parse-tree
|
|
|
1726 |
}
|
|
|
1727 |
|
|
|
1728 |
sub parse_tree {
|
|
|
1729 |
## convenience method to get/set the parse-tree for the entire POD
|
|
|
1730 |
(@_ > 1) and $_[0]->{'-ptree'} = $_[1];
|
|
|
1731 |
return $_[0]->{'-ptree'};
|
|
|
1732 |
}
|
|
|
1733 |
|
|
|
1734 |
sub command {
|
|
|
1735 |
my ($parser, $command, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1736 |
my $ptree = $parser->parse_text({<<options>>}, $paragraph, ...);
|
|
|
1737 |
$pod_para->parse_tree( $ptree );
|
|
|
1738 |
$parser->parse_tree()->append( $pod_para );
|
|
|
1739 |
}
|
|
|
1740 |
|
|
|
1741 |
sub verbatim {
|
|
|
1742 |
my ($parser, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1743 |
$parser->parse_tree()->append( $pod_para );
|
|
|
1744 |
}
|
|
|
1745 |
|
|
|
1746 |
sub textblock {
|
|
|
1747 |
my ($parser, $paragraph, $line_num, $pod_para) = @_;
|
|
|
1748 |
my $ptree = $parser->parse_text({<<options>>}, $paragraph, ...);
|
|
|
1749 |
$pod_para->parse_tree( $ptree );
|
|
|
1750 |
$parser->parse_tree()->append( $pod_para );
|
|
|
1751 |
}
|
|
|
1752 |
|
|
|
1753 |
...
|
|
|
1754 |
|
|
|
1755 |
package main;
|
|
|
1756 |
...
|
|
|
1757 |
my $parser = new MyPodParserTree2(...);
|
|
|
1758 |
$parser->parse_from_file(...);
|
|
|
1759 |
my $ptree = $parser->parse_tree;
|
|
|
1760 |
...
|
|
|
1761 |
|
|
|
1762 |
Now you have the entire POD document as one great big parse-tree. You
|
|
|
1763 |
can even use the B<-expand_seq> option to B<parse_text> to insert
|
|
|
1764 |
whole different kinds of objects. Just don't expect B<Pod::Parser>
|
|
|
1765 |
to know what to do with them after that. That will need to be in your
|
|
|
1766 |
code. Or, alternatively, you can insert any object you like so long as
|
|
|
1767 |
it conforms to the B<Pod::ParseTree> interface.
|
|
|
1768 |
|
|
|
1769 |
One could use this to create subclasses of B<Pod::Paragraphs> and
|
|
|
1770 |
B<Pod::InteriorSequences> for specific commands (or to create your own
|
|
|
1771 |
custom node-types in the parse-tree) and add some kind of B<emit()>
|
|
|
1772 |
method to each custom node/subclass object in the tree. Then all you'd
|
|
|
1773 |
need to do is recursively walk the tree in the desired order, processing
|
|
|
1774 |
the children (most likely from left to right) by formatting them if
|
|
|
1775 |
they are text-strings, or by calling their B<emit()> method if they
|
|
|
1776 |
are objects/references.
|
|
|
1777 |
|
|
|
1778 |
=head1 CAVEATS
|
|
|
1779 |
|
|
|
1780 |
Please note that POD has the notion of "paragraphs": this is something
|
|
|
1781 |
starting I<after> a blank (read: empty) line, with the single exception
|
|
|
1782 |
of the file start, which is also starting a paragraph. That means that
|
|
|
1783 |
especially a command (e.g. C<=head1>) I<must> be preceded with a blank
|
|
|
1784 |
line; C<__END__> is I<not> a blank line.
|
|
|
1785 |
|
|
|
1786 |
=head1 SEE ALSO
|
|
|
1787 |
|
|
|
1788 |
L<Pod::InputObjects>, L<Pod::Select>
|
|
|
1789 |
|
|
|
1790 |
B<Pod::InputObjects> defines POD input objects corresponding to
|
|
|
1791 |
command paragraphs, parse-trees, and interior-sequences.
|
|
|
1792 |
|
|
|
1793 |
B<Pod::Select> is a subclass of B<Pod::Parser> which provides the ability
|
|
|
1794 |
to selectively include and/or exclude sections of a POD document from being
|
|
|
1795 |
translated based upon the current heading, subheading, subsubheading, etc.
|
|
|
1796 |
|
|
|
1797 |
=for __PRIVATE__
|
|
|
1798 |
B<Pod::Callbacks> is a subclass of B<Pod::Parser> which gives its users
|
|
|
1799 |
the ability the employ I<callback functions> instead of, or in addition
|
|
|
1800 |
to, overriding methods of the base class.
|
|
|
1801 |
|
|
|
1802 |
=for __PRIVATE__
|
|
|
1803 |
B<Pod::Select> and B<Pod::Callbacks> do not override any
|
|
|
1804 |
methods nor do they define any new methods with the same name. Because
|
|
|
1805 |
of this, they may I<both> be used (in combination) as a base class of
|
|
|
1806 |
the same subclass in order to combine their functionality without
|
|
|
1807 |
causing any namespace clashes due to multiple inheritance.
|
|
|
1808 |
|
|
|
1809 |
=head1 AUTHOR
|
|
|
1810 |
|
|
|
1811 |
Please report bugs using L<http://rt.cpan.org>.
|
|
|
1812 |
|
|
|
1813 |
Brad Appleton E<lt>bradapp@enteract.comE<gt>
|
|
|
1814 |
|
|
|
1815 |
Based on code for B<Pod::Text> written by
|
|
|
1816 |
Tom Christiansen E<lt>tchrist@mox.perl.comE<gt>
|
|
|
1817 |
|
|
|
1818 |
=head1 LICENSE
|
|
|
1819 |
|
|
|
1820 |
Pod-Parser is free software; you can redistribute it and/or modify it
|
|
|
1821 |
under the terms of the Artistic License distributed with Perl version
|
|
|
1822 |
5.000 or (at your option) any later version. Please refer to the
|
|
|
1823 |
Artistic License that came with your Perl distribution for more
|
|
|
1824 |
details. If your version of Perl was not distributed under the
|
|
|
1825 |
terms of the Artistic License, than you may distribute PodParser
|
|
|
1826 |
under the same terms as Perl itself.
|
|
|
1827 |
|
|
|
1828 |
=cut
|
|
|
1829 |
|
|
|
1830 |
1;
|
|
|
1831 |
# vim: ts=4 sw=4 et
|