-
Notifications
You must be signed in to change notification settings - Fork 138
/
POD2HTML.pm
753 lines (527 loc) · 17.5 KB
/
POD2HTML.pm
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
# Copyright (C) 2004-2012, Parrot Foundation.
=head1 NAME
Parrot::Docs::POD2HTML - POD to HTML formatter
=head1 SYNOPSIS
use Parrot::Docs::POD2HTML;
=head1 DESCRIPTION
C<Parrot::Docs::POD2HTML> subclasses C<Pod::Simple::HTML> to provide
various Parrot-specific formatting features, such as linking
C<CE<lt>Parrot::I<Module>E<gt>> and C<FE<lt>I<file>E<gt>>, and using the
Parrot house-style provided by C<Parrot::HTMLPage>.
=head2 Instance Methods
=over
=cut
package Parrot::Docs::POD2HTML;
use strict;
use warnings;
use base qw( Pod::Simple::HTML );
# This is just here to keep Pod::Simple::HTML's version_tag_comment() happy.
our $VERSION = '1.0';
use Parrot::Docs::HTMLPage;
use Parrot::Distribution;
use Parrot::BuildUtil;
use Parrot::Config;
=item C<new()>
Extend C<Pod::Simple::HTML> method to accept PIR and PASM sections that
contain example code, which will be put into a <pre> HTML element.
=cut
sub new {
my $new = shift->SUPER::new(@_);
$new->accept_targets(qw(
PIR PASM PIR_FRAGMENT
PIR_INVALID PIR_TODO
PASM_INVALID PASM_TODO
PIR_FRAGMENT_INVALID
));
delete(@{$new->{'Tagmap'}}{'Data','/Data'});
return $new;
}
=item C<do_beginning()>
Reimplements the C<Pod::Simple::HTML> method to add a header to the start
of the document.
=cut
sub do_beginning {
my $self = shift;
# We have to do this because it has the side effect of setting
# content_seen.
$self->get_short_title();
return unless $self->content_seen;
# Suppress the warning in the tests.
$self->{RESOURCES_URL} = '' unless $self->{RESOURCES_URL};
$self->{NAV_BAR} = '' unless $self->{NAV_BAR};
my $title = $self->{'Title'};
esc($title);
print { $self->{'output_fh'} }
Parrot::Docs::HTMLPage->header( $title, $self->{NAV_BAR}, $self->{RESOURCES_URL} );
$self->version_tag_comment;
return 1;
}
=item C<do_middle()>
Does the middle of the document. This splits up the long C<do_middle()>
method in C<Pod:Simple::HTML>, calling the various C<process_*> methods
below. This makes it easier to where the custom bits of Parrot-specific
formatting have to be inserted.
=cut
sub do_middle {
my $self = shift;
my $token;
my $type;
$self->{STACK} = [];
$self->{DONT_WRAP} = 0;
while ( $token = $self->get_token ) {
$type = $token->type;
if ( $type eq 'start' ) {
$self->process_start_token($token);
}
elsif ( $type eq 'end' ) {
$self->process_end_token($token);
}
elsif ( $type eq 'text' ) {
$self->process_text_token($token);
}
}
return 1;
}
=item C<process_start_token($token)>
Process a start token.
=cut
sub process_start_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
if ( $tagname eq 'L' ) {
$self->process_link_start_token($token);
}
elsif ( $tagname eq 'F' ) {
$self->process_file_start_token($token);
}
elsif ( $tagname eq 'C' ) {
$self->process_code_start_token($token);
}
elsif ( $tagname eq 'item-text' or $tagname =~ m/^head\d$/s ) {
$self->process_item_text_or_head_start_token($token);
}
elsif ( $tagname eq 'Data' ) {
$self->process_data_start_token($token);
}
elsif ( $tagname eq 'for' ) {
$self->process_for_start_token($token);
}
else {
$self->process_other_start_token($token);
}
}
=item C<process_link_start_token($token)>
Processes the link start token.
=cut
sub process_link_start_token {
my $self = shift;
my $token = shift;
my $text = $self->do_link($token);
esc($text);
if ( defined $text and length $text ) {
print { $self->{'output_fh'} } "<a href='$text'>";
}
else {
print { $self->{'output_fh'} } "<a>";
}
}
=item C<process_code_start_token($token)>
Processes the code start token. If the code text is the name of a Parrot
Perl module, and the current documentation file is not the file for that
module, then the documentation file for the module is linked to.
=cut
sub process_code_start_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
# We make the code tags in items bold because they are almost
# always part of function and arguments, or constants listings
#Êand should stand out.
print { $self->{'output_fh'} } '<b>' if $self->{IN_ITEM_TEXT};
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname};
my $next = $self->get_token;
unless ( $next->type eq 'text' ) {
$self->unget_token($next);
return;
}
my $text = $next->text;
if ( $text =~ /^Parrot::/ ) {
my $href = $self->href_for_perl_module($text);
esc($text);
if ($href) {
$text = "<a href='$href'>$text</a>";
}
}
else {
esc($text);
}
print { $self->{'output_fh'} } $text;
}
=item C<process_file_start_token($token)>
Processes the file start token. If the text of the next token is a file
path and that file contains POD, then a link will be made to that file's
documentation file.
=cut
sub process_file_start_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
my $next = $self->get_token;
if ( $next->type eq 'text' ) {
my $text = $next->text;
my $dist = Parrot::Distribution->new;
# Only link to files that will have HTML pages.
if (
$dist->relative_path_is_file($text)
# A little bit of a hack to avoid config template files.
and $text !~ /\.in$/ and $dist->file_with_relative_path($text)->contains_pod
)
{
my $path = $self->append_html_suffix($text);
my $file = $self->{TARGET}->file_with_relative_path($path);
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname}
. $self->html_link( $self->{DOCS_FILE}->parent->relative_path($file), esc($text) );
}
else {
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname} . esc($text);
}
}
else {
$self->unget_token($next);
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname};
}
}
=item C<process_item_text_or_head_start_token($token)>
Process the item text or head start token.
=cut
sub process_item_text_or_head_start_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname} || return;
if ( $tagname eq 'item-text' ) {
$self->{IN_ITEM_TEXT} = 1;
}
my @to_unget;
# Get all the contained tokens, including the end token.
while (1) {
push @to_unget, $self->get_token;
last
if $to_unget[-1]->is_end
and $to_unget[-1]->tagname eq $tagname;
}
# Convert them into an anchor name;
my $name = $self->linearize_tokens(@to_unget);
if ( defined $name ) {
$name =~ tr/ /_/;
print { $self->{'output_fh'} } qq(<a name="), esc($name), qq("\n>);
}
else {
print { $self->{'output_fh'} } "<a\n>";
}
$self->unget_token(@to_unget);
}
=item C<process_data_start_token($token)>
Processes a data start token.
=cut
sub process_data_start_token {
my $self = shift;
my $token = shift;
my $next = $self->get_token;
return unless defined $next;
unless ( $next->type eq 'text' ) {
$self->unget_token($next);
return;
}
if ($self->{IN_CODE_BLOCK}) {
print { $self->{'output_fh'} } $next->text;
}
else {
print { $self->{'output_fh'} } "\n" . $next->text . "\n";
}
}
=item C<process_for_start_token($token)>
Processes a for start token.
=cut
sub process_for_start_token {
my $self = shift;
my $token = shift;
my $target = $token->attr("target");
if ($target =~ m/^(PIR|PASM)/) {
print { $self->{'output_fh'} } '<pre>';
$self->{IN_CODE_BLOCK} = 1;
}
}
=item C<process_other_start_token($token)>
Processes a start token not processable by the above methods.
=cut
sub process_other_start_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
if ( $tagname =~ m/^over-(.+)$/s ) {
push @{ $self->{STACK} }, $1;
}
elsif ( $tagname eq 'Para' ) {
$tagname = 'Para_item'
if @{ $self->{STACK} } and $self->{STACK}->[-1] eq 'text';
}
print { $self->{'output_fh'} } $self->{'Tagmap'}{$tagname} || return;
++$self->{DONT_WRAP}
if $tagname eq 'Verbatim'
or $tagname eq "VerbatimFormatted"
or $tagname eq 'X';
}
=item C<process_end_token($token)>
Processes an end token.
=cut
sub process_end_token {
my $self = shift;
my $token = shift;
my $tagname = $token->tagname;
if ( $tagname =~ m/^over-/s ) {
pop @{ $self->{STACK} };
}
elsif ( $tagname eq 'Para' ) {
$tagname = 'Para_item'
if @{ $self->{STACK} } and $self->{STACK}->[-1] eq 'text';
}
elsif ( $tagname eq 'C' ) {
# See the note in process_code_start_token() above.
print { $self->{'output_fh'} } '</b>' if $self->{IN_ITEM_TEXT};
}
elsif ( $tagname eq 'item-text' ) {
$self->{IN_ITEM_TEXT} = 0;
}
elsif ( $tagname eq 'for' ) {
print { $self->{'output_fh'} } '</pre>' if $self->{IN_CODE_BLOCK};
$self->{IN_CODE_BLOCK} = 0;
}
print { $self->{'output_fh'} } $self->{'Tagmap'}{"/$tagname"} || return;
--$self->{DONT_WRAP} if $tagname eq 'Verbatim' or $tagname eq 'X';
}
=item C<process_text_token($token)>
Processes the specified text token. URLs which are not in link tags
are linked here for convenience.
=cut
sub process_text_token {
my $self = shift;
my $token = shift;
my $text = $token->text;
esc($text);
$text =~ s/([\?\!\"\'\.\,]) /$1\n/g unless $self->{DONT_WRAP};
# URLs not in L<>.
$text =~ s|(http://[^\s)]+)|<a href="$1">$1</a>|gs;
print { $self->{'output_fh'} } $text;
}
=item C<do_pod_link($link)>
This is reimplemented here to avoid a bug in C<Pod::Simple::HTML>.
=cut
sub do_pod_link {
my $self = shift;
my $link = shift;
my $to = $link->attr('to');
my $section = $link->attr('section');
return
unless ( defined $to and length $to )
or ( defined $section and length $section );
if ( defined $to and length $to ) {
$to = $self->resolve_pod_page_link( $to, $section );
return unless defined $to and length $to;
}
if ( defined $section and length( $section .= '' ) ) {
$section =~ tr/ /_/;
$section =~ tr/\x00-\x1F\x80-\x9F//d if 'A' eq chr(65);
$section = $self->unicode_escape_url($section);
# Turn char 1234 into "(1234)"
$section = '_' unless length $section;
}
foreach my $it ( $to, $section ) {
next unless defined $it;
$it =~ s/([^\x00-\xFF])/join '', map sprintf('%%%02X',$_), unpack 'C*', $1/eg;
$it =~
s/([^\._abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789])/sprintf('%%%02X',ord($1))/eg;
# Yes, stipulate the list without a range, so that this can work right on
# all charsets that this module happens to run under.
# Altho, hmm, what about that ord? Presumably that won't work right
# under non-ASCII charsets. Something should be done about that.
}
# Pod::Simple::HTML bug was here.
my $out;
$out = $to if defined $to and length $to;
$out .= "#" . $section if defined $section and length $section;
return unless length $out;
return $out;
}
=item C<resolve_pod_page_link($to, $section)>
Resolves the POD link. Perl modules are converted to paths.
=cut
sub resolve_pod_page_link {
my $self = shift;
my $to = shift;
my $section = shift;
if ( $to =~ /^Parrot::/ ) {
my $href = $self->href_for_perl_module($to);
# This gets corrupted somewhere down the line, with
# Parrot/PackFile/ConstTable.pm.html being turned into
# Parrot/PackFile%2FConstTable.pm.html and thus breaking
# the CSS and images somehow.
return $href if defined $href;
}
return 'TODO';
}
=item C<href_for_perl_module($module)>
Returns the path to the Perl module's HTML file relative to the current
documentation page. Currently only F<lib/Parrot> modules are linkable.
Returns C<undef> if the current documentation file is the file for the
module.
=cut
sub href_for_perl_module {
my $self = shift;
my $module = shift;
# This is not very obvious, so let me explain. We get the file
# for the module, then we take its path relative to the
# distribution, then we append the HTML suffix and get the
# docs file. Once we have that all we need is the relative
# path from the current directory to the file and return that
# as the link.
my $dist = Parrot::Distribution->new;
my $file = $dist->file_for_perl_module($module);
return if not $file or not $file->contains_pod;
my $path = $self->append_html_suffix( $dist->relative_path($file) );
# This is the docs file for the module.
$file = $self->{TARGET}->file_with_relative_path($path);
# There's no point in linking to the file you are already in.
return if $file == $self->{DOCS_FILE};
return $self->href_path( $self->{DOCS_FILE}->parent->relative_path($file) );
}
=item C<do_end()>
Reimplements the C<Pod::Simple::HTML> method to add a footer to the end
of the document.
=cut
sub do_end {
my $self = shift;
print { $self->{'output_fh'} } Parrot::Docs::HTMLPage->footer( '', $self->{RESOURCES_URL} );
return 1;
}
=item C<html_for_file($file)>
Returns the HTML for the specified file.
=cut
sub html_for_file {
my $self = shift;
my $file = shift;
my $string = "";
$self->output_string( \$string );
$self->parse_file( $file->path );
return $string;
}
=item C<write_html($source, $target, $rel_path, $item)>
Writes an HTML version of the file specified by C<$rel_path> in
C<$source> to the equivalent location in C<$target>.
=cut
sub write_html {
my $self = shift;
my $source = shift;
my $target = shift;
my $rel_path = shift;
my $item = shift;
my $file = $source->file_with_relative_path($rel_path);
return unless $file->contains_pod;
$self->{TARGET} = $target;
# Use our own method for consistency.
$self->{'Title'} = $file->title;
$rel_path = $self->append_html_suffix($rel_path);
my $docs_file = $target->file_with_relative_path($rel_path);
$self->{DOCS_FILE} = $docs_file;
$rel_path = $self->href_path( $docs_file->parent->relative_path( $target->parent_path ) );
my $name = $target->name;
# This is a cheat because we know that all top-level sections
# have their indexes in the root directory - but it works.
$self->{NAV_BAR} = $item->html_navigation("$rel_path/$name");
$self->{RESOURCES_URL} = "$rel_path/resources";
$docs_file->write( $self->html_for_file($file) );
unless ($self->{TESTING}) {
my $path = File::Spec->abs2rel(
File::Spec->catfile($docs_file->{PATH}), $PConfig{build_dir});
chdir "..";
add_to_generated($path, "[main]", "html");
chdir "docs";
}
}
=item C<append_html_suffix($path)>
Returns C<$path> with and HTML file suffix added.
=cut
sub append_html_suffix {
my $self = shift;
my $path = shift;
return $path . '.html';
}
=item C<html_link($href, $text)>
Returns an HTML anchor with the specified "href".
=cut
sub html_link {
my $self = shift;
my $href = $self->href_path(shift);
my $text = shift || $href;
return "<a href=\"$href\">$text</a>";
}
=item href_path($path)
Converts the path for use in an "href".
Sequences of backslashes are converted to forward slash.
=cut
sub href_path {
my $self = shift;
my $path = shift;
$path =~ s|\\+|/|go;
return $path;
}
=back
=head2 Functions
=over 4
=item C<esc(@strings)>
=item C<esc($string)>
Reimplemented here to silence a C<Pod::Simple::HTML> warning.
=cut
sub esc {
if ( defined wantarray ) {
if (wantarray) {
@_ = splice @_; # break aliasing
}
else {
my $x = shift;
# Pod::Simple::HTML didn't check this.
return $x unless $x;
$x =~
s/([^\n\t !\#\$\%\(\)\*\+,\.\~\/\:\;=\?\@\[\\\]\^_\`\{\|\}abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789])/'&#'.(ord($1)).';'/eg;
return $x;
}
}
foreach my $x (@_) {
# Pod::Simple::HTML didn't check this.
next unless $x;
# Escape things very cautiously:
$x =~
s/([^\n\t !\#\$\%\(\)\*\+,\.\~\/\:\;=\?\@\[\\\]\^_\`\{\|\}abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789])/'&#'.(ord($1)).';'/eg;
# Leave out "- so that "--" won't make it thru in X-generated comments
# with text in them.
# Yes, stipulate the list without a range, so that this can work right on
# all charsets that this module happens to run under.
# Altho, hmm, what about that ord? Presumably that won't work right
# under non-ASCII charsets. Something should be done about that.
}
return @_;
}
=back
=head1 HISTORY
In order to avoid modifying C<Pod:Simple::HTML>, large sections of its code
have been copied here, and then refactored and adjusted to enable various bits
of Parrot-specific behaviour.
=cut
1;
# Local Variables:
# mode: cperl
# cperl-indent-level: 4
# fill-column: 100
# End:
# vim: expandtab shiftwidth=4: