Commit | Line | Data |
ad712fff |
1 | # Pod::PlainText -- Convert POD data to formatted ASCII text. |
2 | # $Id: Text.pm,v 2.1 1999/09/20 11:53:33 eagle Exp $ |
3 | # |
4 | # Copyright 1999-2000 by Russ Allbery <rra@stanford.edu> |
5 | # |
6 | # This program is free software; you can redistribute it and/or modify it |
7 | # under the same terms as Perl itself. |
8 | # |
9 | # This module is intended to be a replacement for Pod::Text, and attempts to |
10 | # match its output except for some specific circumstances where other |
11 | # decisions seemed to produce better output. It uses Pod::Parser and is |
12 | # designed to be very easy to subclass. |
13 | |
14 | ############################################################################ |
15 | # Modules and declarations |
16 | ############################################################################ |
17 | |
18 | package Pod::PlainText; |
1bc4b319 |
19 | use strict; |
ad712fff |
20 | |
21 | require 5.005; |
22 | |
23 | use Carp qw(carp croak); |
24 | use Pod::Select (); |
25 | |
ad712fff |
26 | use vars qw(@ISA %ESCAPES $VERSION); |
27 | |
28 | # We inherit from Pod::Select instead of Pod::Parser so that we can be used |
29 | # by Pod::Usage. |
30 | @ISA = qw(Pod::Select); |
31 | |
1bc4b319 |
32 | $VERSION = '2.03'; |
ad712fff |
33 | |
1bc4b319 |
34 | BEGIN { |
35 | if ($] < 5.006) { |
36 | require Symbol; |
37 | import Symbol; |
38 | } |
39 | } |
ad712fff |
40 | |
41 | ############################################################################ |
42 | # Table of supported E<> escapes |
43 | ############################################################################ |
44 | |
45 | # This table is taken near verbatim from Pod::PlainText in Pod::Parser, |
46 | # which got it near verbatim from the original Pod::Text. It is therefore |
47 | # credited to Tom Christiansen, and I'm glad I didn't have to write it. :) |
48 | %ESCAPES = ( |
49 | 'amp' => '&', # ampersand |
50 | 'lt' => '<', # left chevron, less-than |
51 | 'gt' => '>', # right chevron, greater-than |
52 | 'quot' => '"', # double quote |
53 | |
54 | "Aacute" => "\xC1", # capital A, acute accent |
55 | "aacute" => "\xE1", # small a, acute accent |
56 | "Acirc" => "\xC2", # capital A, circumflex accent |
57 | "acirc" => "\xE2", # small a, circumflex accent |
58 | "AElig" => "\xC6", # capital AE diphthong (ligature) |
59 | "aelig" => "\xE6", # small ae diphthong (ligature) |
60 | "Agrave" => "\xC0", # capital A, grave accent |
61 | "agrave" => "\xE0", # small a, grave accent |
62 | "Aring" => "\xC5", # capital A, ring |
63 | "aring" => "\xE5", # small a, ring |
64 | "Atilde" => "\xC3", # capital A, tilde |
65 | "atilde" => "\xE3", # small a, tilde |
66 | "Auml" => "\xC4", # capital A, dieresis or umlaut mark |
67 | "auml" => "\xE4", # small a, dieresis or umlaut mark |
68 | "Ccedil" => "\xC7", # capital C, cedilla |
69 | "ccedil" => "\xE7", # small c, cedilla |
70 | "Eacute" => "\xC9", # capital E, acute accent |
71 | "eacute" => "\xE9", # small e, acute accent |
72 | "Ecirc" => "\xCA", # capital E, circumflex accent |
73 | "ecirc" => "\xEA", # small e, circumflex accent |
74 | "Egrave" => "\xC8", # capital E, grave accent |
75 | "egrave" => "\xE8", # small e, grave accent |
76 | "ETH" => "\xD0", # capital Eth, Icelandic |
77 | "eth" => "\xF0", # small eth, Icelandic |
78 | "Euml" => "\xCB", # capital E, dieresis or umlaut mark |
79 | "euml" => "\xEB", # small e, dieresis or umlaut mark |
80 | "Iacute" => "\xCD", # capital I, acute accent |
81 | "iacute" => "\xED", # small i, acute accent |
82 | "Icirc" => "\xCE", # capital I, circumflex accent |
83 | "icirc" => "\xEE", # small i, circumflex accent |
84 | "Igrave" => "\xCD", # capital I, grave accent |
85 | "igrave" => "\xED", # small i, grave accent |
86 | "Iuml" => "\xCF", # capital I, dieresis or umlaut mark |
87 | "iuml" => "\xEF", # small i, dieresis or umlaut mark |
88 | "Ntilde" => "\xD1", # capital N, tilde |
89 | "ntilde" => "\xF1", # small n, tilde |
90 | "Oacute" => "\xD3", # capital O, acute accent |
91 | "oacute" => "\xF3", # small o, acute accent |
92 | "Ocirc" => "\xD4", # capital O, circumflex accent |
93 | "ocirc" => "\xF4", # small o, circumflex accent |
94 | "Ograve" => "\xD2", # capital O, grave accent |
95 | "ograve" => "\xF2", # small o, grave accent |
96 | "Oslash" => "\xD8", # capital O, slash |
97 | "oslash" => "\xF8", # small o, slash |
98 | "Otilde" => "\xD5", # capital O, tilde |
99 | "otilde" => "\xF5", # small o, tilde |
100 | "Ouml" => "\xD6", # capital O, dieresis or umlaut mark |
101 | "ouml" => "\xF6", # small o, dieresis or umlaut mark |
102 | "szlig" => "\xDF", # small sharp s, German (sz ligature) |
103 | "THORN" => "\xDE", # capital THORN, Icelandic |
104 | "thorn" => "\xFE", # small thorn, Icelandic |
105 | "Uacute" => "\xDA", # capital U, acute accent |
106 | "uacute" => "\xFA", # small u, acute accent |
107 | "Ucirc" => "\xDB", # capital U, circumflex accent |
108 | "ucirc" => "\xFB", # small u, circumflex accent |
109 | "Ugrave" => "\xD9", # capital U, grave accent |
110 | "ugrave" => "\xF9", # small u, grave accent |
111 | "Uuml" => "\xDC", # capital U, dieresis or umlaut mark |
112 | "uuml" => "\xFC", # small u, dieresis or umlaut mark |
113 | "Yacute" => "\xDD", # capital Y, acute accent |
114 | "yacute" => "\xFD", # small y, acute accent |
115 | "yuml" => "\xFF", # small y, dieresis or umlaut mark |
116 | |
117 | "lchevron" => "\xAB", # left chevron (double less than) |
118 | "rchevron" => "\xBB", # right chevron (double greater than) |
119 | ); |
120 | |
121 | |
122 | ############################################################################ |
123 | # Initialization |
124 | ############################################################################ |
125 | |
126 | # Initialize the object. Must be sure to call our parent initializer. |
127 | sub initialize { |
128 | my $self = shift; |
129 | |
130 | $$self{alt} = 0 unless defined $$self{alt}; |
131 | $$self{indent} = 4 unless defined $$self{indent}; |
132 | $$self{loose} = 0 unless defined $$self{loose}; |
133 | $$self{sentence} = 0 unless defined $$self{sentence}; |
134 | $$self{width} = 76 unless defined $$self{width}; |
135 | |
136 | $$self{INDENTS} = []; # Stack of indentations. |
137 | $$self{MARGIN} = $$self{indent}; # Current left margin in spaces. |
138 | |
1bc4b319 |
139 | return $self->SUPER::initialize; |
ad712fff |
140 | } |
141 | |
142 | |
143 | ############################################################################ |
144 | # Core overrides |
145 | ############################################################################ |
146 | |
147 | # Called for each command paragraph. Gets the command, the associated |
148 | # paragraph, the line number, and a Pod::Paragraph object. Just dispatches |
149 | # the command to a method named the same as the command. =cut is handled |
150 | # internally by Pod::Parser. |
151 | sub command { |
152 | my $self = shift; |
153 | my $command = shift; |
154 | return if $command eq 'pod'; |
155 | return if ($$self{EXCLUDE} && $command ne 'end'); |
1bc4b319 |
156 | if (defined $$self{ITEM}) { |
157 | $self->item ("\n"); |
158 | local $_ = "\n"; |
159 | $self->output($_) if($command eq 'back'); |
160 | } |
ad712fff |
161 | $command = 'cmd_' . $command; |
1bc4b319 |
162 | return $self->$command (@_); |
ad712fff |
163 | } |
164 | |
165 | # Called for a verbatim paragraph. Gets the paragraph, the line number, and |
166 | # a Pod::Paragraph object. Just output it verbatim, but with tabs converted |
167 | # to spaces. |
168 | sub verbatim { |
169 | my $self = shift; |
170 | return if $$self{EXCLUDE}; |
171 | $self->item if defined $$self{ITEM}; |
172 | local $_ = shift; |
173 | return if /^\s*$/; |
174 | s/^(\s*\S+)/(' ' x $$self{MARGIN}) . $1/gme; |
1bc4b319 |
175 | return $self->output($_); |
ad712fff |
176 | } |
177 | |
178 | # Called for a regular text block. Gets the paragraph, the line number, and |
179 | # a Pod::Paragraph object. Perform interpolation and output the results. |
180 | sub textblock { |
181 | my $self = shift; |
182 | return if $$self{EXCLUDE}; |
1bc4b319 |
183 | if($$self{VERBATIM}) { |
184 | $self->output($_[0]); |
185 | return; |
186 | } |
ad712fff |
187 | local $_ = shift; |
188 | my $line = shift; |
189 | |
190 | # Perform a little magic to collapse multiple L<> references. This is |
191 | # here mostly for backwards-compatibility. We'll just rewrite the whole |
192 | # thing into actual text at this part, bypassing the whole internal |
193 | # sequence parsing thing. |
194 | s{ |
195 | ( |
196 | L< # A link of the form L</something>. |
197 | / |
198 | ( |
199 | [:\w]+ # The item has to be a simple word... |
200 | (\(\))? # ...or simple function. |
201 | ) |
202 | > |
203 | ( |
204 | ,?\s+(and\s+)? # Allow lots of them, conjuncted. |
205 | L< |
206 | / |
207 | ( |
208 | [:\w]+ |
209 | (\(\))? |
210 | ) |
211 | > |
212 | )+ |
213 | ) |
214 | } { |
215 | local $_ = $1; |
216 | s%L</([^>]+)>%$1%g; |
217 | my @items = split /(?:,?\s+(?:and\s+)?)/; |
218 | my $string = "the "; |
219 | my $i; |
220 | for ($i = 0; $i < @items; $i++) { |
221 | $string .= $items[$i]; |
222 | $string .= ", " if @items > 2 && $i != $#items; |
223 | $string .= " and " if ($i == $#items - 1); |
224 | } |
225 | $string .= " entries elsewhere in this document"; |
226 | $string; |
227 | }gex; |
228 | |
229 | # Now actually interpolate and output the paragraph. |
230 | $_ = $self->interpolate ($_, $line); |
1bc4b319 |
231 | s/\s*$/\n/s; |
ad712fff |
232 | if (defined $$self{ITEM}) { |
233 | $self->item ($_ . "\n"); |
234 | } else { |
235 | $self->output ($self->reformat ($_ . "\n")); |
236 | } |
237 | } |
238 | |
239 | # Called for an interior sequence. Gets the command, argument, and a |
240 | # Pod::InteriorSequence object and is expected to return the resulting text. |
241 | # Calls code, bold, italic, file, and link to handle those types of |
242 | # sequences, and handles S<>, E<>, X<>, and Z<> directly. |
243 | sub interior_sequence { |
244 | my $self = shift; |
245 | my $command = shift; |
246 | local $_ = shift; |
247 | return '' if ($command eq 'X' || $command eq 'Z'); |
248 | |
249 | # Expand escapes into the actual character now, carping if invalid. |
250 | if ($command eq 'E') { |
251 | return $ESCAPES{$_} if defined $ESCAPES{$_}; |
252 | carp "Unknown escape: E<$_>"; |
253 | return "E<$_>"; |
254 | } |
255 | |
256 | # For all the other sequences, empty content produces no output. |
257 | return if $_ eq ''; |
258 | |
259 | # For S<>, compress all internal whitespace and then map spaces to \01. |
260 | # When we output the text, we'll map this back. |
261 | if ($command eq 'S') { |
262 | s/\s{2,}/ /g; |
263 | tr/ /\01/; |
264 | return $_; |
265 | } |
266 | |
267 | # Anything else needs to get dispatched to another method. |
268 | if ($command eq 'B') { return $self->seq_b ($_) } |
269 | elsif ($command eq 'C') { return $self->seq_c ($_) } |
270 | elsif ($command eq 'F') { return $self->seq_f ($_) } |
271 | elsif ($command eq 'I') { return $self->seq_i ($_) } |
272 | elsif ($command eq 'L') { return $self->seq_l ($_) } |
273 | else { carp "Unknown sequence $command<$_>" } |
274 | } |
275 | |
276 | # Called for each paragraph that's actually part of the POD. We take |
277 | # advantage of this opportunity to untabify the input. |
278 | sub preprocess_paragraph { |
279 | my $self = shift; |
280 | local $_ = shift; |
281 | 1 while s/^(.*?)(\t+)/$1 . ' ' x (length ($2) * 8 - length ($1) % 8)/me; |
1bc4b319 |
282 | return $_; |
ad712fff |
283 | } |
284 | |
285 | |
286 | ############################################################################ |
287 | # Command paragraphs |
288 | ############################################################################ |
289 | |
290 | # All command paragraphs take the paragraph and the line number. |
291 | |
292 | # First level heading. |
293 | sub cmd_head1 { |
294 | my $self = shift; |
295 | local $_ = shift; |
1bc4b319 |
296 | s/\s+$//s; |
ad712fff |
297 | $_ = $self->interpolate ($_, shift); |
298 | if ($$self{alt}) { |
299 | $self->output ("\n==== $_ ====\n\n"); |
300 | } else { |
301 | $_ .= "\n" if $$self{loose}; |
302 | $self->output ($_ . "\n"); |
303 | } |
304 | } |
305 | |
306 | # Second level heading. |
307 | sub cmd_head2 { |
308 | my $self = shift; |
309 | local $_ = shift; |
1bc4b319 |
310 | s/\s+$//s; |
ad712fff |
311 | $_ = $self->interpolate ($_, shift); |
312 | if ($$self{alt}) { |
313 | $self->output ("\n== $_ ==\n\n"); |
314 | } else { |
1bc4b319 |
315 | $self->output (' ' x ($$self{indent} / 2) . $_ . "\n"); |
ad712fff |
316 | } |
317 | } |
318 | |
267d5541 |
319 | # third level heading - not strictly perlpodspec compliant |
320 | sub cmd_head3 { |
321 | my $self = shift; |
322 | local $_ = shift; |
1bc4b319 |
323 | s/\s+$//s; |
267d5541 |
324 | $_ = $self->interpolate ($_, shift); |
325 | if ($$self{alt}) { |
326 | $self->output ("\n= $_ =\n"); |
327 | } else { |
328 | $self->output (' ' x ($$self{indent}) . $_ . "\n"); |
329 | } |
330 | } |
331 | |
332 | # fourth level heading - not strictly perlpodspec compliant |
333 | # just like head3 |
334 | *cmd_head4 = \&cmd_head3; |
335 | |
ad712fff |
336 | # Start a list. |
337 | sub cmd_over { |
338 | my $self = shift; |
339 | local $_ = shift; |
340 | unless (/^[-+]?\d+\s+$/) { $_ = $$self{indent} } |
341 | push (@{ $$self{INDENTS} }, $$self{MARGIN}); |
342 | $$self{MARGIN} += ($_ + 0); |
343 | } |
344 | |
345 | # End a list. |
346 | sub cmd_back { |
347 | my $self = shift; |
348 | $$self{MARGIN} = pop @{ $$self{INDENTS} }; |
349 | unless (defined $$self{MARGIN}) { |
1bc4b319 |
350 | carp 'Unmatched =back'; |
ad712fff |
351 | $$self{MARGIN} = $$self{indent}; |
352 | } |
353 | } |
354 | |
355 | # An individual list item. |
356 | sub cmd_item { |
357 | my $self = shift; |
358 | if (defined $$self{ITEM}) { $self->item } |
359 | local $_ = shift; |
1bc4b319 |
360 | s/\s+$//s; |
ad712fff |
361 | $$self{ITEM} = $self->interpolate ($_); |
362 | } |
363 | |
364 | # Begin a block for a particular translator. Setting VERBATIM triggers |
365 | # special handling in textblock(). |
366 | sub cmd_begin { |
367 | my $self = shift; |
368 | local $_ = shift; |
369 | my ($kind) = /^(\S+)/ or return; |
370 | if ($kind eq 'text') { |
371 | $$self{VERBATIM} = 1; |
372 | } else { |
373 | $$self{EXCLUDE} = 1; |
374 | } |
375 | } |
376 | |
377 | # End a block for a particular translator. We assume that all =begin/=end |
378 | # pairs are properly closed. |
379 | sub cmd_end { |
380 | my $self = shift; |
381 | $$self{EXCLUDE} = 0; |
382 | $$self{VERBATIM} = 0; |
1bc4b319 |
383 | } |
ad712fff |
384 | |
385 | # One paragraph for a particular translator. Ignore it unless it's intended |
386 | # for text, in which case we treat it as a verbatim text block. |
387 | sub cmd_for { |
388 | my $self = shift; |
389 | local $_ = shift; |
390 | my $line = shift; |
391 | return unless s/^text\b[ \t]*\n?//; |
392 | $self->verbatim ($_, $line); |
393 | } |
394 | |
395 | |
396 | ############################################################################ |
397 | # Interior sequences |
398 | ############################################################################ |
399 | |
400 | # The simple formatting ones. These are here mostly so that subclasses can |
401 | # override them and do more complicated things. |
402 | sub seq_b { return $_[0]{alt} ? "``$_[1]''" : $_[1] } |
403 | sub seq_c { return $_[0]{alt} ? "``$_[1]''" : "`$_[1]'" } |
404 | sub seq_f { return $_[0]{alt} ? "\"$_[1]\"" : $_[1] } |
405 | sub seq_i { return '*' . $_[1] . '*' } |
406 | |
407 | # The complicated one. Handle links. Since this is plain text, we can't |
408 | # actually make any real links, so this is all to figure out what text we |
409 | # print out. |
410 | sub seq_l { |
411 | my $self = shift; |
412 | local $_ = shift; |
413 | |
414 | # Smash whitespace in case we were split across multiple lines. |
415 | s/\s+/ /g; |
416 | |
417 | # If we were given any explicit text, just output it. |
418 | if (/^([^|]+)\|/) { return $1 } |
419 | |
420 | # Okay, leading and trailing whitespace isn't important; get rid of it. |
421 | s/^\s+//; |
422 | s/\s+$//; |
423 | |
424 | # Default to using the whole content of the link entry as a section |
425 | # name. Note that L<manpage/> forces a manpage interpretation, as does |
426 | # something looking like L<manpage(section)>. The latter is an |
427 | # enhancement over the original Pod::Text. |
428 | my ($manpage, $section) = ('', $_); |
aaa799f9 |
429 | if (/^(?:https?|ftp|news):/) { |
430 | # a URL |
431 | return $_; |
432 | } elsif (/^"\s*(.*?)\s*"$/) { |
ad712fff |
433 | $section = '"' . $1 . '"'; |
434 | } elsif (m/^[-:.\w]+(?:\(\S+\))?$/) { |
435 | ($manpage, $section) = ($_, ''); |
1bc4b319 |
436 | } elsif (m{/}) { |
ad712fff |
437 | ($manpage, $section) = split (/\s*\/\s*/, $_, 2); |
438 | } |
439 | |
ad712fff |
440 | my $text = ''; |
aaa799f9 |
441 | # Now build the actual output text. |
ad712fff |
442 | if (!length $section) { |
443 | $text = "the $manpage manpage" if length $manpage; |
444 | } elsif ($section =~ /^[:\w]+(?:\(\))?/) { |
445 | $text .= 'the ' . $section . ' entry'; |
446 | $text .= (length $manpage) ? " in the $manpage manpage" |
1bc4b319 |
447 | : ' elsewhere in this document'; |
ad712fff |
448 | } else { |
449 | $section =~ s/^\"\s*//; |
450 | $section =~ s/\s*\"$//; |
451 | $text .= 'the section on "' . $section . '"'; |
452 | $text .= " in the $manpage manpage" if length $manpage; |
453 | } |
1bc4b319 |
454 | return $text; |
ad712fff |
455 | } |
456 | |
457 | |
458 | ############################################################################ |
459 | # List handling |
460 | ############################################################################ |
461 | |
462 | # This method is called whenever an =item command is complete (in other |
463 | # words, we've seen its associated paragraph or know for certain that it |
464 | # doesn't have one). It gets the paragraph associated with the item as an |
465 | # argument. If that argument is empty, just output the item tag; if it |
466 | # contains a newline, output the item tag followed by the newline. |
467 | # Otherwise, see if there's enough room for us to output the item tag in the |
468 | # margin of the text or if we have to put it on a separate line. |
469 | sub item { |
470 | my $self = shift; |
471 | local $_ = shift; |
472 | my $tag = $$self{ITEM}; |
473 | unless (defined $tag) { |
1bc4b319 |
474 | carp 'item called without tag'; |
ad712fff |
475 | return; |
476 | } |
477 | undef $$self{ITEM}; |
478 | my $indent = $$self{INDENTS}[-1]; |
479 | unless (defined $indent) { $indent = $$self{indent} } |
480 | my $space = ' ' x $indent; |
481 | $space =~ s/^ /:/ if $$self{alt}; |
482 | if (!$_ || /^\s+$/ || ($$self{MARGIN} - $indent < length ($tag) + 1)) { |
483 | my $margin = $$self{MARGIN}; |
484 | $$self{MARGIN} = $indent; |
485 | my $output = $self->reformat ($tag); |
486 | $output =~ s/\n*$/\n/; |
487 | $self->output ($output); |
488 | $$self{MARGIN} = $margin; |
489 | $self->output ($self->reformat ($_)) if /\S/; |
490 | } else { |
491 | $_ = $self->reformat ($_); |
492 | s/^ /:/ if ($$self{alt} && $indent > 0); |
493 | my $tagspace = ' ' x length $tag; |
1bc4b319 |
494 | s/^($space)$tagspace/$1$tag/ or carp 'Bizarre space in item'; |
ad712fff |
495 | $self->output ($_); |
496 | } |
497 | } |
498 | |
499 | |
500 | ############################################################################ |
501 | # Output formatting |
502 | ############################################################################ |
503 | |
504 | # Wrap a line, indenting by the current left margin. We can't use |
505 | # Text::Wrap because it plays games with tabs. We can't use formline, even |
506 | # though we'd really like to, because it screws up non-printing characters. |
507 | # So we have to do the wrapping ourselves. |
508 | sub wrap { |
509 | my $self = shift; |
510 | local $_ = shift; |
511 | my $output = ''; |
512 | my $spaces = ' ' x $$self{MARGIN}; |
513 | my $width = $$self{width} - $$self{MARGIN}; |
514 | while (length > $width) { |
515 | if (s/^([^\n]{0,$width})\s+// || s/^([^\n]{$width})//) { |
516 | $output .= $spaces . $1 . "\n"; |
517 | } else { |
518 | last; |
519 | } |
520 | } |
521 | $output .= $spaces . $_; |
522 | $output =~ s/\s+$/\n\n/; |
1bc4b319 |
523 | return $output; |
ad712fff |
524 | } |
525 | |
526 | # Reformat a paragraph of text for the current margin. Takes the text to |
527 | # reformat and returns the formatted text. |
528 | sub reformat { |
529 | my $self = shift; |
530 | local $_ = shift; |
531 | |
532 | # If we're trying to preserve two spaces after sentences, do some |
533 | # munging to support that. Otherwise, smash all repeated whitespace. |
534 | if ($$self{sentence}) { |
535 | s/ +$//mg; |
536 | s/\.\n/. \n/g; |
537 | s/\n/ /g; |
538 | s/ +/ /g; |
539 | } else { |
540 | s/\s+/ /g; |
541 | } |
1bc4b319 |
542 | return $self->wrap($_); |
ad712fff |
543 | } |
544 | |
545 | # Output text to the output device. |
546 | sub output { $_[1] =~ tr/\01/ /; print { $_[0]->output_handle } $_[1] } |
547 | |
548 | |
549 | ############################################################################ |
550 | # Backwards compatibility |
551 | ############################################################################ |
552 | |
553 | # The old Pod::Text module did everything in a pod2text() function. This |
554 | # tries to provide the same interface for legacy applications. |
555 | sub pod2text { |
556 | my @args; |
557 | |
558 | # This is really ugly; I hate doing option parsing in the middle of a |
559 | # module. But the old Pod::Text module supported passing flags to its |
560 | # entry function, so handle -a and -<number>. |
561 | while ($_[0] =~ /^-/) { |
562 | my $flag = shift; |
563 | if ($flag eq '-a') { push (@args, alt => 1) } |
564 | elsif ($flag =~ /^-(\d+)$/) { push (@args, width => $1) } |
565 | else { |
566 | unshift (@_, $flag); |
567 | last; |
568 | } |
569 | } |
570 | |
571 | # Now that we know what arguments we're using, create the parser. |
572 | my $parser = Pod::PlainText->new (@args); |
573 | |
574 | # If two arguments were given, the second argument is going to be a file |
575 | # handle. That means we want to call parse_from_filehandle(), which |
576 | # means we need to turn the first argument into a file handle. Magic |
577 | # open will handle the <&STDIN case automagically. |
578 | if (defined $_[1]) { |
1bc4b319 |
579 | my $infh; |
580 | if ($] < 5.006) { |
581 | $infh = gensym(); |
582 | } |
583 | unless (open ($infh, $_[0])) { |
ad712fff |
584 | croak ("Can't open $_[0] for reading: $!\n"); |
ad712fff |
585 | } |
1bc4b319 |
586 | $_[0] = $infh; |
ad712fff |
587 | return $parser->parse_from_filehandle (@_); |
588 | } else { |
589 | return $parser->parse_from_file (@_); |
590 | } |
591 | } |
592 | |
593 | |
594 | ############################################################################ |
595 | # Module return value and documentation |
596 | ############################################################################ |
597 | |
598 | 1; |
599 | __END__ |
600 | |
601 | =head1 NAME |
602 | |
603 | Pod::PlainText - Convert POD data to formatted ASCII text |
604 | |
605 | =head1 SYNOPSIS |
606 | |
607 | use Pod::PlainText; |
608 | my $parser = Pod::PlainText->new (sentence => 0, width => 78); |
609 | |
610 | # Read POD from STDIN and write to STDOUT. |
611 | $parser->parse_from_filehandle; |
612 | |
613 | # Read POD from file.pod and write to file.txt. |
614 | $parser->parse_from_file ('file.pod', 'file.txt'); |
615 | |
616 | =head1 DESCRIPTION |
617 | |
618 | Pod::PlainText is a module that can convert documentation in the POD format (the |
619 | preferred language for documenting Perl) into formatted ASCII. It uses no |
620 | special formatting controls or codes whatsoever, and its output is therefore |
621 | suitable for nearly any device. |
622 | |
623 | As a derived class from Pod::Parser, Pod::PlainText supports the same methods and |
624 | interfaces. See L<Pod::Parser> for all the details; briefly, one creates a |
625 | new parser with C<Pod::PlainText-E<gt>new()> and then calls either |
626 | parse_from_filehandle() or parse_from_file(). |
627 | |
628 | new() can take options, in the form of key/value pairs, that control the |
629 | behavior of the parser. The currently recognized options are: |
630 | |
631 | =over 4 |
632 | |
633 | =item alt |
634 | |
635 | If set to a true value, selects an alternate output format that, among other |
636 | things, uses a different heading style and marks C<=item> entries with a |
637 | colon in the left margin. Defaults to false. |
638 | |
639 | =item indent |
640 | |
641 | The number of spaces to indent regular text, and the default indentation for |
642 | C<=over> blocks. Defaults to 4. |
643 | |
644 | =item loose |
645 | |
646 | If set to a true value, a blank line is printed after a C<=head1> heading. |
647 | If set to false (the default), no blank line is printed after C<=head1>, |
648 | although one is still printed after C<=head2>. This is the default because |
649 | it's the expected formatting for manual pages; if you're formatting |
650 | arbitrary text documents, setting this to true may result in more pleasing |
651 | output. |
652 | |
653 | =item sentence |
654 | |
655 | If set to a true value, Pod::PlainText will assume that each sentence ends in two |
656 | spaces, and will try to preserve that spacing. If set to false, all |
657 | consecutive whitespace in non-verbatim paragraphs is compressed into a |
658 | single space. Defaults to true. |
659 | |
660 | =item width |
661 | |
662 | The column at which to wrap text on the right-hand side. Defaults to 76. |
663 | |
664 | =back |
665 | |
666 | The standard Pod::Parser method parse_from_filehandle() takes up to two |
667 | arguments, the first being the file handle to read POD from and the second |
668 | being the file handle to write the formatted output to. The first defaults |
669 | to STDIN if not given, and the second defaults to STDOUT. The method |
670 | parse_from_file() is almost identical, except that its two arguments are the |
671 | input and output disk files instead. See L<Pod::Parser> for the specific |
672 | details. |
673 | |
674 | =head1 DIAGNOSTICS |
675 | |
676 | =over 4 |
677 | |
678 | =item Bizarre space in item |
679 | |
680 | (W) Something has gone wrong in internal C<=item> processing. This message |
681 | indicates a bug in Pod::PlainText; you should never see it. |
682 | |
683 | =item Can't open %s for reading: %s |
684 | |
685 | (F) Pod::PlainText was invoked via the compatibility mode pod2text() interface |
686 | and the input file it was given could not be opened. |
687 | |
688 | =item Unknown escape: %s |
689 | |
690 | (W) The POD source contained an C<EE<lt>E<gt>> escape that Pod::PlainText didn't |
691 | know about. |
692 | |
693 | =item Unknown sequence: %s |
694 | |
695 | (W) The POD source contained a non-standard internal sequence (something of |
696 | the form C<XE<lt>E<gt>>) that Pod::PlainText didn't know about. |
697 | |
698 | =item Unmatched =back |
699 | |
700 | (W) Pod::PlainText encountered a C<=back> command that didn't correspond to an |
701 | C<=over> command. |
702 | |
703 | =back |
704 | |
705 | =head1 RESTRICTIONS |
706 | |
707 | Embedded Ctrl-As (octal 001) in the input will be mapped to spaces on |
708 | output, due to an internal implementation detail. |
709 | |
710 | =head1 NOTES |
711 | |
712 | This is a replacement for an earlier Pod::Text module written by Tom |
713 | Christiansen. It has a revamped interface, since it now uses Pod::Parser, |
714 | but an interface roughly compatible with the old Pod::Text::pod2text() |
715 | function is still available. Please change to the new calling convention, |
716 | though. |
717 | |
718 | The original Pod::Text contained code to do formatting via termcap |
719 | sequences, although it wasn't turned on by default and it was problematic to |
720 | get it to work at all. This rewrite doesn't even try to do that, but a |
721 | subclass of it does. Look for L<Pod::Text::Termcap|Pod::Text::Termcap>. |
722 | |
723 | =head1 SEE ALSO |
724 | |
725 | L<Pod::Parser|Pod::Parser>, L<Pod::Text::Termcap|Pod::Text::Termcap>, |
726 | pod2text(1) |
727 | |
728 | =head1 AUTHOR |
729 | |
aaa799f9 |
730 | Please report bugs using L<http://rt.cpan.org>. |
731 | |
ad712fff |
732 | Russ Allbery E<lt>rra@stanford.eduE<gt>, based I<very> heavily on the |
733 | original Pod::Text by Tom Christiansen E<lt>tchrist@mox.perl.comE<gt> and |
734 | its conversion to Pod::Parser by Brad Appleton |
735 | E<lt>bradapp@enteract.comE<gt>. |
736 | |
737 | =cut |