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
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
|
#!/usr/bin/env perl
package IkiWiki::Plugin::pandoc;
use warnings;
use strict;
use IkiWiki;
use FileHandle;
use IPC::Open2;
use File::Path qw/make_path/;
use JSON;
use Data::Dumper;
$Data::Dumper::Indent = 3;
my $fh = undef;
my $dh = undef;
my $fnm = undef;
my $f = undef;
my $next = 0;
my $base = '/tmp/pandoc';
mkdir($base);
# activate with 'generate_$format' in meta; turn on all with 'generate_all_formats'.
my %extra_formats = (
pdf => { ext=>'pdf', label=>'PDF', format=>'latex', extra=>[], order=>1 },
docx => { ext=>'docx', label=>'DOCX', format=>'docx', extra=>[], order=>2 },
odt => { ext=>'odt', label=>'ODT', format=>'odt', extra=>[], order=>3 },
beamer => { ext=>'beamer.pdf', label=>'Beamer', format=>'beamer', extra=>[], order=>4 },
revealjs => { ext=>'revealjs.html', label=>'RevealJS', format=>'revealjs', extra=>['--self-contained'], order=>5 },
epub => { ext=>'epub', label=>'EPUB', format=>'epub3', extra=>[], order=>6 },
latex => { ext=>'tex', label=>'LaTeX', format=>'latex', extra=>['--standalone'], order=>7 },
);
my @scalar_meta_keys = qw/
title date bibliography csl subtitle abstract summary description
version lang locale titlesort tag fripost_debug_inner
/;
my @list_meta_keys = qw/
author
/;
/;
sub debug_get_filename_prefix {
my $place = shift;
my $page = shift;
my $fnm_pfx = undef;
opendir($dh, $base) || die "Can't open $base: $!";
foreach $f (grep(/^[0-9][0-9]*/, readdir($dh))) {
$f =~ /^([0-9][0-9]*)\.(.*)$/;
$next = $1 + 1 if ($1 >= $next);
}
close($dh);
if ($page) {
$fnm_pfx = sprintf "%s/%.3d.%s.%s", $base, $next, $place,
$page =~ s/\//-/rg;
} else {
$fnm_pfx = sprintf "%s/%.3d.%s", $base, $next, $place;
}
return $fnm_pfx;
}
# DEBUG Print
print "D: First file read.\n";
$fnm = debug_get_filename_prefix ("verify");
open($fh, '>', $fnm) or die "Could not";
print $fh "Hej du glade på fil\n";
print $fh "Detta är filen i '/home/gustav/git/fripost/wiki/.ikiwiki/IkiWiki/Plugin'\n";
close $fh;
# END
sub import {
# DEBUG Print
print "D: Run import.\n";
my $fnm_pfx = debug_get_filename_prefix ("import","");
my $fnm = $fnm_pfx;
open($fh, '>', $fnm) or die "Could not open $fnm .";
print $fh "Import.\n";
close $fh;
# END
my $markdown_ext = $config{pandoc_markdown_ext} || "mdwn";
# May be both a string with a single value, a string containing commas or an arrayref
if ($markdown_ext =~ /,/) {
$markdown_ext = [split /\s*,\s*/, $markdown_ext];
}
hook(type => "getsetup", id => "pandoc", call => \&getsetup);
hook(type => "pagetemplate", id => "pandoc", call => \&pagetemplate);
hook(type => "pageactions", id => "pandoc", call => \&pageactions);
if (ref $markdown_ext eq 'ARRAY') {
foreach my $mde (@$markdown_ext) {
hook(type => 'htmlize', id => $mde,
call => sub{ htmlize("markdown", @_) });
}
} else {
hook(type => "htmlize", id => $markdown_ext,
call => sub { htmlize("markdown", @_) });
}
if ($config{pandoc_latex}) {
hook(type => "htmlize", id => "tex",
call => sub { htmlize("latex", @_) });
}
if ($config{pandoc_rst}) {
hook(type => "htmlize", id => "rst",
call => sub { htmlize("rst", @_) });
}
if ($config{pandoc_textile}) {
hook(type => "htmlize", id => "textile",
call => sub { htmlize("textile", @_) });
}
if ($config{pandoc_mediawiki}) {
hook(type => "htmlize", id => "mediawiki",
call => sub { htmlize("mediawiki", @_) });
}
if ($config{pandoc_opml}) {
hook(type => "htmlize", id => "opml",
call => sub { htmlize("opml", @_) });
}
if ($config{pandoc_org}) {
hook(type => "htmlize", id => "org",
call => sub { htmlize("org", @_) });
}
}
sub getsetup () {
# DEBUG
print "D: Run getsetup.\n";
# END
return
plugin => {
safe => 1,
rebuild => 1,
},
pandoc_command => {
type => "string",
example => "/usr/local/bin/pandoc",
description => "Path to pandoc executable",
safe => 1,
rebuild => 0,
},
pandoc_citeproc => {
type => "string",
example => "/usr/local/bin/pandoc-citeproc",
description => "Path to pandoc-citeproc executable",
safe => 1,
rebuild => 0,
},
pandoc_markdown_ext => {
type => "string",
example => "mdwn,md,markdown",
description => "File extension(s) for Markdown files handled by Pandoc",
safe => 1,
rebuild => 1,
},
pandoc_markdown_fmt => {
type => "string",
example => "markdown",
description => "Format string to use when processing files handled by Pandoc.",
safe => 1,
rebuild => 1,
},
pandoc_latex => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of LaTeX documents (extension=tex)",
safe => 1,
rebuild => 1,
},
pandoc_rst => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of reStructuredText documents (extension=rst)",
safe => 1,
rebuild => 1,
},
pandoc_textile => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of Textile documents (extension=textile)",
safe => 1,
rebuild => 1,
},
pandoc_mediawiki => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of MediaWiki documents (extension=mediawiki)",
safe => 1,
rebuild => 1,
},
pandoc_org => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of Emacs org-mode documents (extension=org)",
safe => 1,
rebuild => 1,
},
pandoc_opml => {
type => "boolean",
example => 0,
description => "Enable Pandoc processing of OPML documents (extension=opml)",
safe => 1,
rebuild => 1,
},
pandoc_smart => {
type => "boolean",
example => 1,
description => "Use smart quotes, dashes, and ellipses",
safe => 1,
rebuild => 1,
},
pandoc_obfuscate => {
type => "boolean",
example => 1,
description => "Obfuscate emails",
safe => 1,
rebuild => 1,
},
pandoc_html5 => {
type => "boolean",
example => 0,
description => "Generate HTML5",
safe => 1,
rebuild => 1,
},
pandoc_ascii => {
type => "boolean",
example => 0,
description => "Generate ASCII instead of UTF8",
safe => 1,
rebuild => 1,
},
pandoc_html_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for html",
safe => 0,
rebuild => 0,
},
pandoc_numsect => {
type => "boolean",
example => 0,
description => "Number sections",
safe => 1,
rebuild => 1,
},
pandoc_sectdiv => {
type => "boolean",
example => 0,
description => "Attach IDs to section DIVs instead of Headers",
safe => 1,
rebuild => 1,
},
pandoc_codeclasses => {
type => "string",
example => "",
description => "Classes to use for indented code blocks",
safe => 1,
rebuild => 1,
},
pandoc_math => {
type => "string",
example => "mathjax",
description => "How to process TeX math (mathjax, katex, mathml, mathjs, latexmathml, asciimathml, mimetex, webtex)",
safe => 1,
rebuild => 1,
},
pandoc_math_custom_js => {
type => "string",
example => "",
description => "Link to local/custom javascript for math (or to server-side script for mimetex and webtex)",
safe => 1,
rebuild => 1,
},
pandoc_math_custom_css => {
type => "string",
example => "",
description => "Link to local/custom CSS for math (requires appropriate pandoc_math setting)",
safe => 1,
rebuild => 1,
},
pandoc_bibliography => {
type => "string",
example => "",
description => "Path to default bibliography file",
safe => 1,
rebuild => 1,
},
pandoc_csl => {
type => "string",
example => "",
description => "Path to CSL file (for references and bibliography)",
safe => 1,
rebuild => 1,
},
pandoc_csl_default_lang => {
type => "string",
example => "",
description => "Default language code (RFC 1766) for citations processing",
safe => 1,
rebuild => 1,
},
pandoc_filters => {
type => "string",
example => "",
description => "A comma-separated list of custom pandoc filters",
safe => 1,
rebuild => 1,
},
pandoc_latex_template => {
type => "string",
example => "",
description => "Path to pandoc template for LaTeX and normal PDF output",
safe => 1,
rebuild => 0,
},
pandoc_latex_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for LaTeX (and PDF) generation",
safe => 0,
rebuild => 0,
},
pandoc_beamer_template => {
type => "string",
example => "",
description => "Path to pandoc template for Beamer PDF output",
safe => 1,
rebuild => 0,
},
pandoc_beamer_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for Beamer PDF generation",
safe => 0,
rebuild => 0,
},
pandoc_pdf_export_cleanup => {
type => "boolean",
example => "0",
description => "Whether to clean up LaTeX auxiliary files after PDF generation",
safe => 0,
rebuild => 0,
},
pandoc_revealjs_template => {
type => "string",
example => "",
description => "Path to pandoc template for Reveal.js slides output",
safe => 1,
rebuild => 0,
},
pandoc_revealjs_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for Reveal.js slides generation",
safe => 0,
rebuild => 0,
},
pandoc_docx_template => {
type => "string",
example => "",
description => "Path to pandoc template for MS Word (docx) output",
safe => 1,
rebuild => 0,
},
pandoc_docx_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for DOCX generation",
safe => 0,
rebuild => 0,
},
pandoc_odt_template => {
type => "string",
example => "",
description => "Path to pandoc template for OpenDocument (odt) output",
safe => 1,
rebuild => 0,
},
pandoc_odt_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for ODT generation",
safe => 0,
rebuild => 0,
},
pandoc_epub_template => {
type => "string",
example => "",
description => "Path to pandoc template for EPUB3 output",
safe => 1,
rebuild => 0,
},
pandoc_epub_extra_options => {
type => "internal",
default => [],
description => "List of extra pandoc options for EPUB3 generation",
safe => 0,
rebuild => 0,
};
}
sub htmlize ($@) {
my $format = shift;
my %params = @_;
my $page = $params{page};
my $htmlformat = 'html';
local(*PANDOC_IN, *JSON_IN, *JSON_OUT, *PANDOC_OUT);
my @args = ();
# DEBUG Print params
print "D: Run htmlize for ", $page, "\n";
my $fnm_pfx = debug_get_filename_prefix ("htmlize", $page);
my $m = 0;
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "params";
open($fh, '>', $fnm) or die "Could not";
$Data::Dumper::Indent = 2;
print $fh Data::Dumper->Dump([\%params], ["params"]), "\n";
close $fh;
# END
# DEBUG Print half way pagestate pagestate
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "early-pagestate";
open($fh, '>>', $fnm);
print $fh Data::Dumper->Dump([$pagestate{$page}], ['pagestate']), "\n";
close $fh;
# END
# The default assumes pandoc is in PATH
my $command = $config{pandoc_command} || "pandoc";
if ($config{pandoc_smart}) {
push @args, '--smart';
}
if ($config{pandoc_obfuscate}) {
push @args, '--email-obfuscation=references';
} else {
push @args, '--email-obfuscation=none';
}
if ($config{pandoc_html5}) {
$htmlformat = 'html5';
}
if ($config{pandoc_ascii}) {
push @args, '--ascii';
}
if ($config{pandoc_numsect}) {
push @args, '--number-sections';
}
if ($config{pandoc_sectdiv}) {
push @args, '--section-divs';
}
if ($config{pandoc_codeclasses} && ($config{pandoc_codeclasses} ne "")) {
push @args, '--indented-code-classes=' . $config{pandoc_codeclasses};
}
# How to process math. Normally either mathjax or katex.
my %mathconf = map {($_=>"--$_")} qw(
jsmath mathjax latexmathml asciimathml mathml katex mimetex webtex
);
my %with_urls = qw/mimetex 1 webtex 1/;
my $mathopt = $1 if $config{pandoc_math} && $config{pandoc_math} =~ /(\w+)/;
my $custom_js = $config{pandoc_math_custom_js} || '';
# cleanup pandoc-prefixed keys from persistent meta
if (ref $pagestate{$page}{meta} eq 'HASH') {
my @delkeys = ();
foreach my $k (%{ $pagestate{$page}{meta} }) {
push @delkeys, $k if $k =~ /^pandoc_/;
}
delete $pagestate{$page}{meta}{$_} for @delkeys;
}
if ($mathopt && $mathconf{$mathopt}) {
if ($with_urls{$mathopt} && $custom_js) {
# In these cases, the 'custom js' is a misnomer: actually a server-side script
push @args, $mathconf{$mathopt} ."=". $custom_js;
} else {
push @args, $mathconf{$mathopt};
}
$pagestate{$page}{meta}{"pandoc_math"} = $mathopt;
$pagestate{$page}{meta}{"pandoc_math_$mathopt"} = 1;
$pagestate{$page}{meta}{"pandoc_math_custom_js"} = $custom_js if $custom_js;
}
# Convert to intermediate JSON format so that the title block
# can be parsed out
# We must omit the 'bibliography' parameter here, otherwise the list of
# references will be doubled.
my $markdown_fmt = $config{pandoc_markdown_fmt} || 'markdown';
my $to_json_pid = open2(*JSON_OUT, *PANDOC_OUT, $command,
'-f', $markdown_fmt,
'-t', 'json',
@args);
error("Unable to open $command") unless $to_json_pid;
# Workaround for perl bug (#376329)
require Encode;
my $content = Encode::encode_utf8($params{content});
# Protect inline plugin placeholders from being mangled by pandoc:
$content =~ s{<div class="inline" id="(\d+)"></div>}
{::INLINE::PLACEHOLDER::$1::}g;
print PANDOC_OUT $content;
close PANDOC_OUT;
my $json_content = <JSON_OUT>;
close JSON_OUT;
waitpid $to_json_pid, 0;
# Parse the title block out of the JSON and set the meta values
my $meta = undef;
my $decoded_json = decode_json($json_content);
# The representation of the meta block changed in pandoc version 1.18
if (ref $decoded_json eq 'HASH' && $decoded_json->{'meta'}) {
$meta = $decoded_json->{'meta'} || {}; # post-1.18 version
} elsif (ref $decoded_json eq 'ARRAY') {
$meta = $decoded_json->[0]->{'unMeta'} || {}; # pre-1.18 version
}
unless ($meta) {
warn "WARNING: Unexpected format for meta block. Incompatible version of Pandoc?\n";
}
# DEBUG Half way content which is plenty data
print "D: Pandoc command: ", " ", $command, " ", '-f', " ",
$markdown_fmt, " ", '-t', " ", 'json', " ", @args,
"\n";
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "early-content";
open($fh, '>>', $fnm);
print $fh Data::Dumper->Dump([$content], [qw(content)]), "\n";
print $fh Data::Dumper->Dump([$json_content], [qw(json_content)]), "\n";
print $fh Data::Dumper->Dump([$decoded_json], [qw(decoded_json)]), "\n";
print $fh Data::Dumper->Dump([$meta], [qw(meta)]), "\n";
close $fh;
# END
# Get some selected meta attributes, more specifically:
# (title date bibliography csl subtitle abstract summary description
# version lang locale references author [+ num_authors primary_author]),
# as well as some configuration options (generate_*, *_extra_options, *_template).
my @format_keys = grep { $_ ne 'pdf' } keys %extra_formats;
my %scalar_meta = map { ($_=>undef) } @scalar_meta_keys;
$scalar_meta{$_.'_template'} = undef for @format_keys;
my %bool_meta = map { ("generate_$_"=>0) } keys %extra_formats;
my %list_meta = map { ($_=>[]) } @list_meta_keys;
$list_meta{$_.'_extra_options'} = [] for @format_keys;
my $have_bibl = 0;
foreach my $k (keys %scalar_meta) {
next unless $meta->{$k};
$scalar_meta{$k} = compile_string($meta->{$k}->{c});
# NB! Note that this is potentially risky, since pagestate is sticky, and
# we only cleanup the pandoc_* values in {meta}.
$pagestate{$page}{meta}{$k} = $scalar_meta{$k};
$pagestate{$page}{meta}{"pandoc_$k"} = $pagestate{$page}{meta}{$k};
}
foreach my $k (keys %bool_meta) {
my $gen_all = $meta->{generate_all_formats} || {};
next unless $meta->{$k} || $gen_all->{c};
my $val = $meta->{$k} ? $meta->{$k}->{c} : $gen_all->{c};
# simplifies matters with JSON::(PP::)Boolean objects
$val = 1 if $val == 1 || $val eq 'true';
if (ref $val || $val =~ /^\s*(?:off|no|false|0)\s*$/i) {
$bool_meta{$k} = 0;
} else {
$bool_meta{$k} = 1;
$pagestate{$page}{meta}{"pandoc_$k"} = 1;
}
}
foreach my $k (keys %list_meta) {
next unless $meta->{$k};
$list_meta{$k} = unwrap_c($meta->{$k});
$list_meta{$k} = [$list_meta{$k}] unless ref $list_meta{$k} eq 'ARRAY';
$have_bibl = 1 if $k eq 'references';
$pagestate{$page}{meta}{"pandoc_$k"} = $list_meta{$k};
}
# Try to add other keys as scalars, with pandoc_ prefix only.
foreach my $k (keys %$meta) {
next if exists $scalar_meta{$k} || exists $list_meta{$k};
eval {
$pagestate{$page}{meta}{"pandoc_$k"} = compile_string($meta->{$k}->{c});
};
}
my $num_authors = scalar @{ $list_meta{author} };
$scalar_meta{num_authors} = $num_authors;
$pagestate{$page}{meta}{num_authors} = $num_authors;
if ($num_authors) {
$scalar_meta{primary_author} = $list_meta{author}->[0];
$pagestate{$page}{meta}{author} = join(', ', @{$list_meta{author}});
$pagestate{$page}{meta}{pandoc_primary_author} = $scalar_meta{primary_author}
}
# DEBUG
$pagestate{$page}{meta}{fripost_debug_label_1} = 'fripost debug value';
# END
# The bibliography may be set in a Meta block in the page or in the .setup file.
# If both are present, the Meta block has precedence.
for my $bibl ($scalar_meta{bibliography}, $config{pandoc_bibliography}) {
if ($bibl) {
$have_bibl = 1;
$pagestate{$page}{meta}{pandoc_bibliography} = $bibl;
push @args, '--bibliography='.$bibl;
last;
}
}
# Similarly for the CSL file...
for my $cslfile ($scalar_meta{csl}, $config{pandoc_csl}) {
if ($cslfile) {
$pagestate{$page}{meta}{pandoc_csl} = $cslfile;
push @args, '--csl='.$cslfile;
last;
}
}
# If a default CSL language is specified, add that to args,
# (unless it is overridden by meta)
unless ($scalar_meta{lang} || $scalar_meta{locale}) {
if ($config{pandoc_csl_default_lang}) {
push @args, "--metadata=lang:".$config{pandoc_csl_default_lang};
}
}
# Turn on the pandoc-citeproc filter if either global bibliography,
# local bibliography or a 'references' key in Meta is present.
if ($have_bibl) {
my $citeproc = $config{pandoc_citeproc} || 'pandoc-citeproc';
push @args, "--filter=$citeproc";
}
# Other pandoc filters. Note that currently there is no way to
# configure a filter to run before pandoc-citeproc has done its work.
if ($config{pandoc_filters}) {
my @filters = split /\s*,\s*/, $config{pandoc_filters};
s/^["']//g for @filters; # get rid of enclosing quotes
foreach my $filter (@filters) {
push @args, "--filter=$filter";
}
}
# html_extra_options my be set in Meta block in the page or in the .setup
# file. If both are present, the Meta block has precedence, even if it is
# an empty list
my @html_args = @args;
if (ref $meta->{html_extra_options}{c} eq 'ARRAY') {
if (ref unwrap_c($meta->{html_extra_options}{c}) eq 'ARRAY') {
push @html_args, @{unwrap_c($meta->{html_extra_options}{c})};
} else {
push @html_args, unwrap_c($meta->{html_extra_options}{c});
}
} elsif (ref $config{'pandoc_html_extra_options'} eq 'ARRAY') {
push @html_args, @{$config{'pandoc_html_extra_options'}};
}
my $to_html_pid = open2(*PANDOC_IN, *JSON_IN, $command,
'-f', 'json',
'-t', $htmlformat,
@html_args);
error("Unable to open $command") unless $to_html_pid;
$pagestate{$page}{pandoc_extra_formats} = {};
foreach my $ext (keys %extra_formats) {
if ($bool_meta{"generate_$ext"}) {
export_file($page, $ext, $json_content, $command, @args);
} else {
remove_exported_file($page, $ext);
}
}
print JSON_IN $json_content;
close JSON_IN;
my @html = <PANDOC_IN>;
close PANDOC_IN;
waitpid $to_html_pid, 0;
print "D: Pandoc command: ", " ", $command, " ", '-f', " ",
'json', " ", '-t', $htmlformat, " ", @html_args, "\n";
$content = Encode::decode_utf8(join('', @html));
# Reinstate placeholders for inline plugin:
$content =~ s{::INLINE::PLACEHOLDER::(\d+)::}
{<div class="inline" id="$1"></div>}g;
# DEBUG Print meta
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "meta";
open($fh, '>>', $fnm) or die "Could not";
print $fh "\n";
print $fh Data::Dumper->Dump([\%scalar_meta], [qw(scalar_meta)]), "\n";
print $fh Data::Dumper->Dump([\%bool_meta], [qw(bool_meta)]), "\n";
print $fh Data::Dumper->Dump([\%list_meta], [qw(list_meta)]), "\n";
close $fh;
# END
# DEBUG Print pagestate again
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "return-pagestate";
open($fh, '>>', $fnm);
print $fh Data::Dumper->Dump([$pagestate{$page}], ['pagestate']), "\n";
close $fh;
# END
# DEBUG Print return content
$fnm = sprintf "%s.%.1d.%s", $fnm_pfx, $m++, "return-content";
open($fh, '>>', $fnm);
print $fh Dumper($content), "\n";
close $fh;
# END
# DEBUG
print "D: Return htmlize.\n";
# END
return $content;
}
sub pagetemplate (@) {
my %params = @_;
my $page = $params{page};
my $template = $params{template};
# DEBUG
my $filename = $template->{'options'}{'filename'};
$filename =~ /^.*\/([a-z]*).tmpl$/;
my $filenamebase = $1;
print "D: Run pagetemplate for $page and $filenamebase \n";
# END
foreach my $k (keys %{$pagestate{$page}{meta}}) {
next unless
(grep {/^$k$/} (@scalar_meta_keys, @list_meta_keys)) ||
($k =~ /^(pandoc_)/);
$template->param($k => $pagestate{$page}{meta}{$k});
}
# DEBUG Print pagetemplate data
my $fnm_pfx = debug_get_filename_prefix ("pagetemplate", $page);
my $m = 0;
my $fnm = sprintf "%s.%s.%.1d.%s", $fnm_pfx, $filenamebase, $m++, "template";
open($fh, '>', $fnm) or die "Could not";
print $fh Data::Dumper->Dump([$template->{'mtime'}], ["mtime"]), "\n";
print $fh Data::Dumper->Dump([$template->{'options'}], ['options']), "\n";
print $fh Data::Dumper->Dump(
[$template->{'param_map'}], ['param_map']), "\n";
print $fh Data::Dumper->Dump(
[$template->{'parse_stack'}], ['parse_stack']),"\n";
close $fh;
$fnm = sprintf "%s.%s.%.1d.%s", $fnm_pfx, $filenamebase, $m++, "output";
open($fh, '>', $fnm) or die "Could not";
print $fh $template->output();
close $fh;
# END
return $template;
}
sub pageactions {
my %args = @_;
my $page = $args{page};
print "D: Run pageactions for ", $page, "\n";
my @links = ();
return unless $pagestate{$page}{pandoc_extra_formats};
my @exts = sort {
$extra_formats{$a}->{order} <=> $extra_formats{$b}->{order}
} keys %{ $pagestate{$page}{pandoc_extra_formats} };
foreach my $ext (@exts) {
my $url = $pagestate{$page}{pandoc_extra_formats}{$ext};
next unless $url;
my $label = $extra_formats{$ext}->{label} || $ext;
push @links, qq[
<a href="$url"
class="extra-format-link"
title="Download $label version of this page"
target="_blank">$label</a>
];
}
return @links;
}
sub export_file {
my ($page, $ext, $json_content, $command, @args) = @_;
# DEBUG
print "D: Run export_file for $page.\n";
# END
my ($export_path, $export_url) = _export_file_path_and_url($page, $ext);
my $subdir = $1 if $export_path =~ /(.*)\//;
my @extra_args = @{ $extra_formats{$ext}->{extra} };
my $eopt = $ext eq 'pdf' ? 'latex' : $ext;
# Note that template in meta OVERRIDES template in config,
# while extra_options in meta are ADDED to extra_options in config.
my $template = $pagestate{$page}{meta}{"pandoc_".$eopt."_template"}
|| $config{"pandoc_".$eopt."_template"} || '';
if ($template) {
push @extra_args, ($ext =~ /^(docx|odt)$/
? "--reference-$ext=$template"
: "--template=$template");
}
my $conf_extra = $config{"pandoc_".$eopt."_extra_options"};
my $conf_extra_custom = $pagestate{$page}{meta}{"pandoc_".$eopt."_extra_options"};
foreach my $cnf ($conf_extra, $conf_extra_custom) {
if (ref $cnf eq 'ARRAY' && @$cnf) {
push @extra_args, @$cnf;
}
}
my $pdf_cleanup = 0;
if (defined $pagestate{$page}{meta}{"pandoc_pdf_export_cleanup"}) {
$pdf_cleanup = $pagestate{$page}{meta}{"pandoc_pdf_export_cleanup"};
} elsif ($config{"pandoc_pdf_export_cleanup"}) {
$pdf_cleanup = 1;
}
# If the user has asked for native LaTeX bibliography handling in the
# extra_args for this export format (using --biblatex or --natbib),
# some extra care is needed. Among other things, we need an external
# tool for PDF generation. In this case, $indirect_pdf will be true.
my %maybe_non_citeproc = qw/latex 1 pdf 1 beamer 1/;
my $indirect_pdf = 0;
if ($maybe_non_citeproc{$ext} && grep { /^(?:--biblatex|--natbib)$/ } @extra_args) {
$indirect_pdf = 1 unless $ext eq 'latex'; # both for pdf and beamer
@args = grep { ! /--filter=.*pandoc-citeproc/ } @args;
}
eval {
if ($subdir && !-d $subdir) {
make_path($subdir) or die "Could not make_path $subdir: $!";
}
my $to_format = $extra_formats{$ext}->{format} || $ext;
my $tmp_export_path = $export_path;
$tmp_export_path =~ s/\.pdf$/.tex/ if $indirect_pdf;
open(EXPORT, "|-",
$command,
'-f' => 'json',
'-t' => $to_format,
'-o' => $tmp_export_path,
@args, @extra_args) or die "Could not open pipe for $ext: $!";
print EXPORT $json_content;
close EXPORT or die "Could not close pipe for $ext: $!";
print "D: Pandoc command: ", " ", $command, " ", '-f' =>
'json', " ", '-t' => $to_format, " ", '-o' =>
$tmp_export_path, " ", @args, " ", @extra_args;
if ($indirect_pdf && $tmp_export_path ne $export_path) {
my @latexmk_args = qw(-quiet -silent);
if (grep { /xelatex/ } @extra_args) {
push @latexmk_args, '-xelatex';
} elsif (grep { /lualatex/ } @extra_args) {
push @latexmk_args, '-lualatex';
} else {
push @latexmk_args, '-pdf';
}
chdir $subdir or die "Could not chdir to $subdir: $!";
my $plain_fn = $1 if $tmp_export_path =~ /([^\/]+)$/;
$plain_fn =~ s/\.tex//;
system('latexmk', @latexmk_args, $plain_fn) == 0
or die "Could not run latexmk for pdf generation ($export_path): $!";
if ($pdf_cleanup) {
system('latexmk', '-c', '-quiet', '-silent', $plain_fn) == 0
or die "Could not run latexmk for cleanup ($export_path): $!";
# These files are apparently not cleaned up by latexmk -c.
foreach ('run.xml', 'bbl') {
my $fn = "$subdir/$plain_fn.$_";
unlink($fn) if -f $fn;
}
}
}
$pagestate{$page}{pandoc_extra_formats}{$ext} = $export_url;
};
if ($@) {
warn "EXPORT ERROR FOR $page (format: $ext): $@\n";
}
}
sub remove_exported_file {
my ($page, $ext) = @_;
my ($export_path, $export_url) = _export_file_path_and_url($page, $ext);
if (-f $export_path) {
eval { unlink $export_path or die "Could not unlink $export_path: $!" };
if ($@) {
warn "WARNING: remove_exported_file; page=$page, ext=$ext: $@\n";
}
# DEBUG
print "D: remove_exported_file: ",
"file removed for $page and $ext: $export_path.\n";
# END
}
}
sub _export_file_path_and_url {
my ($page, $ext) = @_;
# the html file will end up in "$destdir/$page/index.html",
# while e.g. a pdf will be in "$destdir/$page/$page_minus_dirs.pdf".
my $extension = $extra_formats{$ext}->{ext} || $ext;
my $destdir = $config{destdir} || '.';
my $page_minus_dirs = $1 if $page =~ /([^\/]*)$/;
$page_minus_dirs ||= 'index';
my $export_path = "$destdir/$page/$page_minus_dirs.$extension";
my $export_url = $config{url};
$export_url .= "/" unless $export_url =~ /\/$/;
$export_url .= "$page/$page_minus_dirs.$extension";
return ($export_path, $export_url);
}
## compile_string and unwrap_c are used to make the meta data structures
## easier to work with for perl.
sub compile_string {
# Partially represents an item from the data structure in meta as a string.
my @uncompiled = @_;
return $uncompiled[0] if @uncompiled==1 && !ref($uncompiled[0]);
@uncompiled = @{$uncompiled[0]} if @uncompiled==1 && ref $uncompiled[0] eq 'ARRAY';
my $compiled_string = '';
foreach my $word_or_space (@uncompiled) {
next unless ref $word_or_space eq 'HASH';
my $type = $word_or_space->{'t'} || '';
$compiled_string .= compile_string(@{ $word_or_space->{c} }) if $type eq 'MetaInlines';
next unless $type eq 'Str' || $type eq 'Space' || $type eq 'MetaString';
$compiled_string .= $type eq 'Space' ? ' ' : $word_or_space->{c};
}
return $compiled_string;
}
sub unwrap_c {
# Unwrap pandoc's MetaLists, MetaInlines, etc.
# Finds the deepest-level scalar value for 'c' in the data structure.
# Lists with one element are replaced with the scalar, lists with more
# than one element are returned as an arrayref containing scalars.
#
# Elements containing hash as keys are unwrapped. That is to
# support *MetaList* containing *MetaMap* with keys pointing to
# *MetaInlines*. Reference are examples of that structure. (hash unwrap)
#
my $container = shift;
if (ref $container eq 'ARRAY' && @$container > 1) {
if (ref $container->[0] eq 'HASH' && $container->[0]->{t} =~ /^(?:Str|Space)$/) {
# handles scalar author fields
return join('', map { compile_string($_) } @$container);
} else {
return [map {unwrap_c($_)} @$container];
}
} elsif (ref $container eq 'ARRAY' && @$container) {
return unwrap_c($container->[0]);
} elsif (ref $container eq 'ARRAY') {
return;
} elsif (ref $container eq 'HASH' && $container->{c}) {
return unwrap_c($container->{c});
} elsif (ref $container eq 'HASH' && keys $container->%*) { # (hash unwrap)
return {map { $_ => unwrap_c($container->{$_}) } keys $container->%*};
} elsif (ref $container) {
return;
} else {
return $container;
}
}
1;
|