forked from netwide-assembler/nasm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
rdsrc.pl
1221 lines (1142 loc) · 34.8 KB
/
rdsrc.pl
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
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/perl
## --------------------------------------------------------------------------
##
## Copyright 1996-2018 The NASM Authors - All Rights Reserved
## See the file AUTHORS included with the NASM distribution for
## the specific copyright holders.
##
## Redistribution and use in source and binary forms, with or without
## modification, are permitted provided that the following
## conditions are met:
##
## * Redistributions of source code must retain the above copyright
## notice, this list of conditions and the following disclaimer.
## * Redistributions in binary form must reproduce the above
## copyright notice, this list of conditions and the following
## disclaimer in the documentation and/or other materials provided
## with the distribution.
##
## THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
## CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
## INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
## MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
## DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
## CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
## SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
## NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
## LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
## HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
## CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
## OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
## EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
##
## --------------------------------------------------------------------------
# Read the source-form of the NASM manual and generate the various
# output forms.
# TODO:
#
# Ellipsis support would be nice.
# Source-form features:
# ---------------------
#
# Bullet \b
# Bullets the paragraph. Rest of paragraph is indented to cope. In
# HTML, consecutive groups of bulleted paragraphs become unordered
# lists.
#
# Indent \>
# Indents the paragraph equvalently to a bulleted paragraph. In HTML,
# an indented paragraph following a bulleted paragraph is included in the
# same list item.
#
# Blockquote \q
# Marks the paragraph as a block quote.
#
# Emphasis \e{foobar}
# produces `_foobar_' in text and italics in HTML, PS, RTF
#
# Inline code \c{foobar}
# produces ``foobar'' in text, and fixed-pitch font in HTML, PS, RTF
#
# Display code
# \c line one
# \c line two
# produces fixed-pitch font where appropriate, and doesn't break
# pages except sufficiently far into the middle of a display.
#
# Chapter, header and subheader
# \C{intro} Introduction
# \H{whatsnasm} What is NASM?
# \S{free} NASM Is Free
# dealt with as appropriate. Chapters begin on new sides, possibly
# even new _pages_. (Sub)?headers are good places to begin new
# pages. Just _after_ a (sub)?header isn't.
# The keywords can be substituted with \K and \k.
#
# Keyword \K{cintro} \k{cintro}
# Expands to `Chapter 1', `Section 1.1', `Section 1.1.1'. \K has an
# initial capital whereas \k doesn't. In HTML, will produce
# hyperlinks.
#
# Web link \W{http://foobar/}{text} or \W{mailto:me@here}\c{me@here}
# the \W prefix is ignored except in HTML; in HTML the last part
# becomes a hyperlink to the first part.
#
# Web URL \w{http://foobar/}
# equivalent to \W{http://foobar}\c{http://foobar/}.
#
# Literals \{ \} \\
# In case it's necessary, they expand to the real versions.
#
# Nonbreaking hyphen \-
# Need more be said?
#
# Source comment \#
# Causes everything after it on the line to be ignored by the
# source-form processor.
#
# Indexable word \i{foobar} (or \i\e{foobar} or \i\c{foobar}, equally)
# makes word appear in index, referenced to that point
# \i\c comes up in code style even in the index; \i\e doesn't come
# up in emphasised style.
#
# Indexable non-displayed word \I{foobar} or \I\c{foobar}
# just as \i{foobar} except that nothing is displayed for it
#
# Index rewrite
# \IR{foobar} \c{foobar} operator, uses of
# tidies up the appearance in the index of something the \i or \I
# operator was applied to
#
# Index alias
# \IA{foobar}{bazquux}
# aliases one index tag (as might be supplied to \i or \I) to
# another, so that \I{foobar} has the effect of \I{bazquux}, and
# \i{foobar} has the effect of \I{bazquux}foobar
#
# Metadata/macros
# \M{key}{something}
# defines document metadata, such as authorship, title and copyright;
# different output formats use this differently.
# \m{key}
# insert the {something} string associated with metadata {key}
#
# Include subfile
# \& filename
# includes filename. Recursion is allowed. Must be on a separate line.
#
use File::Spec;
@include_path = ();
$out_path = File::Spec->curdir();
my %srcfiles; # For dependencies
my $depend_path;
while ($ARGV[0] =~ /^-/) {
my $opt = shift @ARGV;
if ($opt eq '-d') {
$diag = 1;
} elsif ($opt =~ /^\-M(.*)$/) {
$depend_path = $1;
} elsif ($opt =~ /^\-[Ii](.*)$/) {
push(@include_path, $1);
} elsif ($opt =~ /^\-[Oo](.*)$/) {
$out_path = $1;
}
}
$out_format = shift(@ARGV);
@files = @ARGV;
@files = ('-') unless(scalar(@files));
$| = 1;
$tstruct_previtem = $node = "Top";
$nodes = ($node);
$tstruct_level{$tstruct_previtem} = 0;
$tstruct_last[$tstruct_level{$tstruct_previtem}] = $tstruct_previtem;
$MAXLEVEL = 10; # really 3, but play safe ;-)
# Read the file; pass a paragraph at a time to the paragraph processor.
$pname = [];
@pnames = @pflags = ();
$para = undef;
foreach $file (@files) {
&include($file);
}
&got_para($para);
print "$outfile: done.\n";
# Now we've read in the entire document and we know what all the
# heading keywords refer to. Go through and fix up the \k references.
print "$outfile: Fixing up cross-references...\n";
&fixup_xrefs;
# Sort the index tags, according to the slightly odd order I've decided on.
print "$outfile: sorting index tags...\n";
&indexsort;
# Make output directory if necessary
mkdir($out_path);
if ($diag) {
print "$outfile: writing index-diagnostic file...\n";
&indexdiag;
}
# OK. Write out the various output files.
my $outfile;
if ($out_format eq 'txt') {
$outfile = 'nasmdoc.txt';
print "$outfile: producing text output...\n";
&write_txt;
} elsif ($out_format eq 'html') {
$outfile = 'nasmdoc0.html';
print "$outfile: producing HTML output...\n";
&write_html;
} elsif ($out_format eq 'dip') {
$outfile = 'nasmdoc.dip';
print "$outfile: producing Documentation Intermediate Paragraphs...\n";
&write_dip;
} else {
die "$0: unknown output format: $out_format\n";
}
if (defined($depend_path)) {
# Write dependencies
print "$outfile: writing dependencies\n";
open(my $dep, '>', $depend_path)
or die "$outfile: $depend_path: $!\n";
if ($out_path ne File::Spec->curdir()) {
$outfile = File::Spec->catfile($out_path, $outfile);
}
my $o = $outfile.' :';
my $ol = length($o);
foreach my $sf (sort(keys(%srcfiles))) {
my $l = length($sf);
if ($l + $ol > 77) {
print $dep $o, " \\\n";
$o = '';
$ol = 0;
}
$o .= ' '.$sf;
$ol += $l+1;
}
print $dep $o, "\n\n";
close($dep);
}
print "$outfile: done.\n";
sub untabify($) {
my($s) = @_;
my $o = '';
my($c, $i, $p);
$p = 0;
for ($i = 0; $i < length($s); $i++) {
$c = substr($s, $i, 1);
if ($c eq "\t") {
do {
$o .= ' ';
$p++;
} while ($p & 7);
} else {
$o .= $c;
$p++;
}
}
return $o;
}
sub read_line {
local $_ = shift;
$_ = &untabify($_);
if (/\\& (\S+)/) {
&include($1);
} else {
&get_para($_);
}
}
sub get_para($_) {
chomp;
if (!/\S/ || /^\\(IA|IR|M)/) { # special case: \IA \IR \M imply new-paragraph
&got_para($para);
$para = undef;
}
if (/\S/) {
s/(^|[^\\])\\#.*$/\1/; # strip comments
$para .= " " . $_;
}
}
sub include {
my $name = shift;
my $F;
if ($name eq '-') {
open($F, '<&', \*STDIN); # stdin
print "$outfile: reading stdin...\n";
} else {
my $found = 0;
foreach my $idir ( File::Spec->curdir, @include_path ) {
my $fpath = File::Spec->catfile($idir, $name);
if (open($F, '<', $fpath)) {
# Assume that make uses VPATH for the input search path,
# and so dependencies should not include the search directory.
$srcfiles{$name}++;
$found = 1;
print "$outfile: reading $fpath...\n";
last;
}
}
die "$0:$outfile: Cannot open $name: $!\n" unless ($found);
}
while (defined($_ = <$F>)) {
&read_line($_);
}
close($F);
}
sub got_para {
local ($_) = @_;
my $pflags = "", $i, $w, $l, $t;
my $para = [];
return if !/\S/;
# Replace metadata macros
while (/^(.*)\\m\{([^\}]*)\}(.*)$/) {
if (defined($metadata{$2})) {
$_ = $1.$metadata{$2}.$3;
} else {
$_ = $1.$2.$3;
}
}
# Strip off _leading_ spaces, then determine type of paragraph.
s/^\s*//;
$irewrite = undef;
if (/^\\c[^{]/) {
# A code paragraph. The paragraph-array will contain the simple
# strings which form each line of the paragraph.
$pflags = "code";
while (/^\\c (([^\\]|\\[^c])*)(.*)$/) {
$l = $1;
$_ = $3;
$l =~ s/\\\{/\{/g;
$l =~ s/\\\}/}/g;
$l =~ s/\\\\/\\/g;
push @$para, $l;
}
$_ = ''; # suppress word-by-word code
} elsif (/^\\C/) {
# A chapter heading. Define the keyword and allocate a chapter
# number.
$cnum++;
$hnum = 0;
$snum = 0;
$xref = "chapter-$cnum";
$pflags = "chap $cnum :$xref";
die "$outfile: badly formatted chapter heading: $_\n" if !/^\\C\{([^\}]*)\}\s*(.*)$/;
$refs{$1} = "chapter $cnum";
$node = "Chapter $cnum";
&add_item($node, 1, $para);
$xrefnodes{$node} = $xref; $nodexrefs{$xref} = $node;
$xrefs{$1} = $xref;
$_ = $2;
# the standard word-by-word code will happen next
} elsif (/^\\A/) {
# An appendix heading. Define the keyword and allocate an appendix
# letter.
$cnum++;
$cnum = 'A' if $cnum =~ /[0-9]+/;
$hnum = 0;
$snum = 0;
$xref = "appendix-$cnum";
$pflags = "appn $cnum :$xref";
die "$outfile: badly formatted appendix heading: $_\n" if !/^\\A\{([^\}]*)}\s*(.*)$/;
$refs{$1} = "appendix $cnum";
$node = "Appendix $cnum";
&add_item($node, 1, $para);
$xrefnodes{$node} = $xref; $nodexrefs{$xref} = $node;
$xrefs{$1} = $xref;
$_ = $2;
# the standard word-by-word code will happen next
} elsif (/^\\H/) {
# A major heading. Define the keyword and allocate a section number.
$hnum++;
$snum = 0;
$xref = "section-$cnum.$hnum";
$pflags = "head $cnum.$hnum :$xref";
die "$outfile: badly formatted heading: $_\n" if !/^\\[HP]\{([^\}]*)\}\s*(.*)$/;
$refs{$1} = "section $cnum.$hnum";
$node = "Section $cnum.$hnum";
&add_item($node, 2, $para);
$xrefnodes{$node} = $xref; $nodexrefs{$xref} = $node;
$xrefs{$1} = $xref;
$_ = $2;
# the standard word-by-word code will happen next
} elsif (/^\\S/) {
# A sub-heading. Define the keyword and allocate a section number.
$snum++;
$xref = "section-$cnum.$hnum.$snum";
$pflags = "subh $cnum.$hnum.$snum :$xref";
die "$outfile: badly formatted subheading: $_\n" if !/^\\S\{([^\}]*)\}\s*(.*)$/;
$refs{$1} = "section $cnum.$hnum.$snum";
$node = "Section $cnum.$hnum.$snum";
&add_item($node, 3, $para);
$xrefnodes{$node} = $xref; $nodexrefs{$xref} = $node;
$xrefs{$1} = $xref;
$_ = $2;
# the standard word-by-word code will happen next
} elsif (/^\\IR/) {
# An index-rewrite.
die "$outfile: badly formatted index rewrite: $_\n" if !/^\\IR\{([^\}]*)\}\s*(.*)$/;
$irewrite = $1;
$_ = $2;
# the standard word-by-word code will happen next
} elsif (/^\\IA/) {
# An index-alias.
die "$outfile: badly formatted index alias: $_\n" if !/^\\IA\{([^\}]*)}\{([^\}]*)\}\s*$/;
$idxalias{$1} = $2;
return; # avoid word-by-word code
} elsif (/^\\M/) {
# Metadata
die "$outfile: badly formed metadata: $_\n" if !/^\\M\{([^\}]*)}\{([^\}]*)\}\s*$/;
$metadata{$1} = $2;
return; # avoid word-by-word code
} elsif (/^\\([b\>q])/) {
# An indented paragraph of some sort. Strip off the initial \b and let the
# word-by-word code take care of the rest.
my %ipar = (
'b' => 'bull',
'>' => 'indt',
'q' => 'bquo',
);
$pflags = $ipar{$1};
s/^\\[b\>q]\s*//;
} else {
# A normal paragraph. Just set $pflags: the word-by-word code does
# the rest.
$pflags = "norm";
}
# The word-by-word code: unless @$para is already defined (which it
# will be in the case of a code paragraph), split the paragraph up
# into words and push each on @$para.
#
# Each thing pushed on @$para should have a two-character type
# code followed by the text.
#
# Type codes are:
# "n " for normal
# "da" for an en dash
# "dm" for an em desh
# "es" for first emphasised word in emphasised bit
# "e " for emphasised in mid-emphasised-bit
# "ee" for last emphasised word in emphasised bit
# "eo" for single (only) emphasised word
# "c " for code
# "k " for cross-ref
# "kK" for capitalised cross-ref
# "w " for Web link
# "wc" for code-type Web link
# "x " for beginning of resolved cross-ref; generates no visible output,
# and the text is the cross-reference code
# "xe" for end of resolved cross-ref; text is same as for "x ".
# "i " for point to be indexed: the text is the internal index into the
# index-items arrays
# "sp" for space
while (/\S/) {
s/^\s*//, push @$para, "sp" if /^\s/;
$indexing = $qindex = 0;
if (/^(\\[iI])?\\c/) {
$qindex = 1 if $1 eq "\\I";
$indexing = 1, s/^\\[iI]// if $1;
s/^\\c//;
die "$outfile: badly formatted \\c: \\c$_\n" if !/\{(([^\\}]|\\.)*)\}(.*)$/;
$w = $1;
$_ = $3;
$w =~ s/\\\{/\{/g;
$w =~ s/\\\}/\}/g;
$w =~ s/\\-/-/g;
$w =~ s/\\\\/\\/g;
push(@$para, addidx($node, $w, "c $w")) if ($indexing);
push(@$para, "c $w") if (!$qindex);
} elsif (/^\\[iIe]/) {
/^(\\[iI])?(\\e)?/;
$emph = 0;
$qindex = 1 if $1 eq "\\I";
$indexing = 1, $type = "\\i" if $1;
$emph = 1, $type = "\\e" if $2;
s/^(\\[iI])?(\\e?)//;
die "$outfile: badly formatted $type: $type$_\n" if !/\{(([^\\}]|\\.)*)\}(.*)$/;
$w = $1;
$_ = $3;
$w =~ s/\\\{/\{/g;
$w =~ s/\\\}/\}/g;
$w =~ s/\\-/-/g;
$w =~ s/\\\\/\\/g;
$t = $emph ? "es" : "n ";
@ientry = ();
@pentry = ();
foreach $i (split /\s+/,$w) { # \e and \i can be multiple words
push @pentry, "$t$i","sp";
($ii=$i) =~ tr/A-Z/a-z/, push @ientry,"n $ii","sp";
$t = $emph ? "e " : "n ";
}
if ($indexing) {
$w =~ tr/A-Z/a-z/;
pop @ientry; # remove final space
push(@$para, addidx($node, $w, @ientry));
}
if (!$qindex) {
pop @pentry; # remove final space
if (substr($pentry[-1],0,2) eq 'es') {
substr($pentry[-1],0,2) = 'eo';
} elsif ($emph) {
substr($pentry[-1],0,2) = 'ee';
}
push(@$para, @pentry);
}
} elsif (/^\\[kK]/) {
$t = "k ";
$t = "kK" if /^\\K/;
s/^\\[kK]//;
die "$outfile: badly formatted \\k: \\k$_\n" if !/\{([^\}]*)\}(.*)$/;
$_ = $2;
push @$para,"$t$1";
} elsif (/^\\[Ww]/) {
if (/^\\w/) {
die "$outfile: badly formatted \\w: $_\n"
if !/^\\w(\\i)?\{([^\\}]*)\}(.*)$/;
$l = $2;
$w = $2;
$indexing = $1;
$c = 1;
$_ = $3;
} else {
die "$outfile: badly formatted \\W: $_\n"
if !/^\\W\{([^\\}]*)\}(\\i)?(\\c)?\{(([^\\}]|\\.)*)\}(.*)$/;
$l = $1;
$w = $4;
$_ = $6;
$indexing = $2;
$c = $3;
}
$t = $c ? 'wc' : 'w ';
$w =~ s/\\\{/\{/g;
$w =~ s/\\\}/\}/g;
$w =~ s/\\-/-/g;
$w =~ s/\\\\/\\/g;
push(@$para, addidx($node, $w, "c $w")) if $indexing;
push(@$para, "$t<$l>$w");
} else {
die "$outfile: what the hell? $_\n" if !/^(([^\s\\\-]|\\[\\{}\-])*-?)(.*)$/;
die "$outfile: painful death! $_\n" if !length $1;
$w = $1;
$_ = $3;
$w =~ s/\\\{/\{/g;
$w =~ s/\\\}/\}/g;
$w =~ s/\\-/-/g;
$w =~ s/\\\\/\\/g;
if ($w eq '--') {
push @$para, 'dm';
} elsif ($w eq '-') {
push @$para, 'da';
} else {
push @$para,"n $w";
}
}
}
if ($irewrite ne undef) {
addidx(undef, $irewrite, @$para);
} else {
push @pnames, $para;
push @pflags, $pflags;
}
}
sub addidx($$@) {
my($node, $text, @ientry) = @_;
$text = $idxalias{$text} || $text;
if (!exists($idxmap{$text})) {
$idxmap{$text} = [@ientry];
$idxdup{$text} = [$text];
} elsif (!defined($node)) {
my $dummy = sprintf('%s #%05d', $text, $#{$idxdup{$text}} + 2);
$idxmap{$dummy} = [@ientry];
push(@{$idxdup{$text}}, $dummy);
}
return undef if (!defined($node));
return map { $idxnodes{$node,$_} = 1; "i $_" } @{$idxdup{$text}};
}
sub indexsort {
my $iitem, $ientry, $i, $piitem, $pcval, $cval, $clrcval;
@itags = map { # get back the original data as the 1st elt of each list
$_->[0]
} sort { # compare auxiliary (non-first) elements of lists
my $d = 0;
for (my $i = 1; defined($a->[$i]) || defined($b->[$i]); $i++) {
$d = $a->[$i] cmp $b->[$i];
last if ($d);
}
$d
} map { # transform array into list of 3-element lists
my $ientry = $idxmap{$_};
my $b = lc(join(' ', map { substr($_,2) } @$ientry));
$b =~ s/([][(){}]+|\B,)//g;
$b =~ s/\s+/ /g;
my $a = $b;
$a =~ s/([[:alpha:]])/Z$1/g;
# From this point on [A-Z] means an already classed character
# Try to sort numbers in numerical order (e.g. 8 before 16)
while ($a =~ /^(|.*?[^A-Z])(\d+)(\.\d+)?(.*)$/) {
my $p = $1; my $s = $4;
my $nn = ('0' x (24 - length($2))) . $2 . $3;
$nn =~ s/(.)/D$1/g;
$a = $p . $nn . $s;
}
$a =~ s/([^A-Z\s])/A$1/g;
my $c = join(' ', map { substr($_,0,2) } @$ientry);
my $v = [$_, $a, $b, $_, $c];
$v
} keys %idxmap;
# Having done that, check for comma-hood.
$cval = 0;
foreach $iitem (@itags) {
$ientry = $idxmap{$iitem};
$clrcval = 1;
$pcval = $cval;
FL:for ($i=0; $i <= $#$ientry; $i++) {
if ($$ientry[$i] =~ /^(n .*,)(.*)/) {
$$ientry[$i] = $1;
splice @$ientry,$i+1,0,"n $2" if length $2;
$commapos{$iitem} = $i+1;
$cval = join("\002", @$ientry[0..$i]);
$clrcval = 0;
last FL;
}
}
$cval = undef if $clrcval;
$commanext{$iitem} = $commaafter{$piitem} = 1
if $cval and ($cval eq $pcval);
$piitem = $iitem;
}
}
sub indexdiag {
my $iitem,$ientry,$w,$ww,$foo,$node;
open INDEXDIAG, '>', File::Spec->catfile($out_path, 'index.diag');
foreach $iitem (@itags) {
$ientry = $idxmap{$iitem};
print INDEXDIAG "<$iitem> ";
foreach $w (@$ientry) {
$ww = &word_txt($w);
print INDEXDIAG $ww unless $ww eq "\001";
}
print INDEXDIAG ":";
$foo = " ";
foreach $node (@nodes) {
(print INDEXDIAG $foo,$node), $foo = ", " if $idxnodes{$node,$iitem};
}
print INDEXDIAG "\n";
}
close INDEXDIAG;
}
sub fixup_xrefs {
my $pname, $p, $i, $j, $k, $caps, @repl;
for ($p=0; $p<=$#pnames; $p++) {
next if $pflags[$p] eq "code";
$pname = $pnames[$p];
for ($i=$#$pname; $i >= 0; $i--) {
$k = $$pname[$i];
if ($k =~ /^k/) {
$caps = ($k =~ /^kK/);
$k = substr($k,2);
$repl = $refs{$k};
die "$outfile: undefined keyword `$k'\n" unless $repl;
substr($repl,0,1) =~ tr/a-z/A-Z/ if $caps;
@repl = ();
push @repl,"x $xrefs{$k}";
foreach $j (split /\s+/,$repl) {
push @repl,"n $j";
push @repl,"sp";
}
pop @repl; # remove final space
push @repl,"xe$xrefs{$k}";
splice @$pname,$i,1,@repl;
}
}
}
}
sub write_txt {
# This is called from the top level, so I won't bother using
# my or local.
# Open file.
print "writing file...";
open TEXT, '>', File::Spec->catfile($out_path, 'nasmdoc.txt');
select TEXT;
# Preamble.
$title = $metadata{'title'};
$spaces = ' ' x ((75-(length $title))/2);
($underscore = $title) =~ s/./=/g;
print "$spaces$title\n$spaces$underscore\n";
for ($para = 0; $para <= $#pnames; $para++) {
$pname = $pnames[$para];
$pflags = $pflags[$para];
$ptype = substr($pflags,0,4);
print "\n"; # always one of these before a new paragraph
if ($ptype eq "chap") {
# Chapter heading. "Chapter N: Title" followed by a line of
# minus signs.
$pflags =~ /chap (.*) :(.*)/;
$title = "Chapter $1: ";
foreach $i (@$pname) {
$ww = &word_txt($i);
$title .= $ww unless $ww eq "\001";
}
print "$title\n";
$title =~ s/./-/g;
print "$title\n";
} elsif ($ptype eq "appn") {
# Appendix heading. "Appendix N: Title" followed by a line of
# minus signs.
$pflags =~ /appn (.*) :(.*)/;
$title = "Appendix $1: ";
foreach $i (@$pname) {
$ww = &word_txt($i);
$title .= $ww unless $ww eq "\001";
}
print "$title\n";
$title =~ s/./-/g;
print "$title\n";
} elsif ($ptype eq "head" || $ptype eq "subh") {
# Heading or subheading. Just a number and some text.
$pflags =~ /.... (.*) :(.*)/;
$title = sprintf "%6s ", $1;
foreach $i (@$pname) {
$ww = &word_txt($i);
$title .= $ww unless $ww eq "\001";
}
print "$title\n";
} elsif ($ptype eq "code") {
# Code paragraph. Emit each line with a seven character indent.
my $maxlen = 80;
foreach $i (@$pname) {
warn "code line longer than $maxlen chars: $i\n"
if ( length($i) > $maxlen );
print ' 'x7, $i, "\n";
}
} elsif ($ptype =~ /^(norm|bull|indt|bquo)$/) {
# Ordinary paragraph, optionally indented. We wrap, with ragged
# 75-char right margin and either 7 or 11 char left margin
# depending on bullets.
if ($ptype ne 'norm') {
$line = ' 'x7 . (($ptype eq 'bull') ? '(*) ' : ' ');
$next = ' 'x11;
} else {
$line = $next = ' 'x7;
}
@a = @$pname;
$wd = $wprev = '';
do {
do { $w = &word_txt(shift @a) } while $w eq "\001"; # nasty hack
$wd .= $wprev;
if ($wprev =~ /-$/ || $w eq ' ' || $w eq '' || $w eq undef) {
if (length ($line . $wd) > 75) {
$line =~ s/\s*$//; # trim trailing spaces
print "$line\n";
$line = $next;
$wd =~ s/^\s*//; # trim leading spaces
}
$line .= $wd;
$wd = '';
}
$wprev = $w;
} while ($w ne '' && $w ne undef);
if ($line =~ /\S/) {
$line =~ s/\s*$//; # trim trailing spaces
print "$line\n";
}
}
}
# Close file.
select STDOUT;
close TEXT;
}
sub word_txt {
my ($w) = @_;
my $wtype, $wmajt;
return undef if $w eq '' || $w eq undef;
$wtype = substr($w,0,2);
$wmajt = substr($wtype,0,1);
$w = substr($w,2);
$w =~ s/<.*>// if $wmajt eq "w"; # remove web links
if ($wmajt eq "n" || $wtype eq "e " || $wtype eq "w ") {
return $w;
} elsif ($wtype eq "sp") {
return ' ';
} elsif ($wtype eq 'da' || $wtype eq 'dm') {
return '-';
} elsif ($wmajt eq "c" || $wtype eq "wc") {
return "`${w}'";
} elsif ($wtype eq "es") {
return "_${w}";
} elsif ($wtype eq "ee") {
return "${w}_";
} elsif ($wtype eq "eo") {
return "_${w}_";
} elsif ($wmajt eq "x" || $wmajt eq "i") {
return "\001";
} else {
die "$outfile: panic in word_txt: $wtype$w\n";
}
}
sub html_filename($) {
my($node) = @_;
(my $number = lc($xrefnodes{$node})) =~ s/.*-//;
my $fname="nasmdocx.html";
substr($fname,8 - length $number, length $number) = $number;
return $fname;
}
sub write_html {
# This is called from the top level, so I won't bother using
# my or local.
# Write contents file. Just the preamble, then a menu of links to the
# separate chapter files and the nodes therein.
print "writing contents file...";
open TEXT, '>', File::Spec->catfile($out_path, 'nasmdoc0.html');
select TEXT;
undef $html_nav_last;
$html_nav_next = $tstruct_next{'Top'};
&html_preamble(0);
print "<p>This manual documents NASM, the Netwide Assembler: an assembler\n";
print "targeting the Intel x86 series of processors, with portable source.\n</p>";
print "<div class=\"toc\">\n";
$level = 0;
for ($node = $tstruct_next{'Top'}; $node; $node = $tstruct_next{$node}) {
my $lastlevel = $level;
while ($tstruct_level{$node} < $level) {
print "</li>\n</ol>\n";
$level--;
}
while ($tstruct_level{$node} > $level) {
print "<ol class=\"toc", ++$level, "\">\n";
}
if ($lastlevel >= $level) {
print "</li>\n";
}
$level = $tstruct_level{$node};
if ($level == 1) {
$link = $fname = html_filename($node);
} else {
# Use the preceding filename plus a marker point.
$link = $fname . "#$xrefnodes{$node}";
}
$pname = $tstruct_pname{$node};
$title = plist_to_html(@$pname);
print "<li class=\"toc${level}\">\n";
print "<span class=\"node\">$node: </span><a href=\"$link\">$title</a>\n";
}
while ($level--) {
print "</li>\n</ol>\n";
}
print "</div>\n";
print "</body>\n";
print "</html>\n";
select STDOUT;
close TEXT;
# Open a null file, to ensure output (eg random &html_jumppoints calls)
# goes _somewhere_.
print "writing chapter files...";
open TEXT, '>', File::Spec->devnull();
select TEXT;
undef $html_nav_last;
undef $html_nav_next;
$in_list = 0;
$in_bquo = 0;
$in_code = 0;
for ($para = 0; $para <= $#pnames; $para++) {
$pname = $pnames[$para];
$pflags = $pflags[$para];
$ptype = substr($pflags,0,4);
$in_code = 0, print "</pre>\n" if ($in_code && $ptype ne 'code');
$in_list = 0, print "</li>\n</ul>\n" if ($in_list && $ptype !~ /^(bull|indt|code)$/);
$in_bquo = 0, print "</blockquote>\n" if ($in_bquo && $ptype ne 'bquo');
$endtag = '';
if ($ptype eq "chap") {
# Chapter heading. Begin a new file.
$pflags =~ /chap (.*) :(.*)/;
$title = "Chapter $1: ";
$xref = $2;
&html_postamble; select STDOUT; close TEXT;
$html_nav_last = $chapternode;
$chapternode = $nodexrefs{$xref};
$html_nav_next = $tstruct_mnext{$chapternode};
open(TEXT, '>', File::Spec->catfile($out_path, html_filename($chapternode)));
select TEXT;
&html_preamble(1);
foreach $i (@$pname) {
$ww = &word_html($i);
$title .= $ww unless $ww eq "\001";
}
$h = "<h2 id=\"$xref\">$title</h2>\n";
print $h; print FULL $h;
} elsif ($ptype eq "appn") {
# Appendix heading. Begin a new file.
$pflags =~ /appn (.*) :(.*)/;
$title = "Appendix $1: ";
$xref = $2;
&html_postamble; select STDOUT; close TEXT;
$html_nav_last = $chapternode;
$chapternode = $nodexrefs{$xref};
$html_nav_next = $tstruct_mnext{$chapternode};
open(TEXT, '>', File::Spec->catfile($out_path, html_filename($chapternode)));
select TEXT;
&html_preamble(1);
foreach $i (@$pname) {
$ww = &word_html($i);
$title .= $ww unless $ww eq "\001";
}
print "<h2 id=\"$xref\">$title</h2>\n";
} elsif ($ptype eq "head" || $ptype eq "subh") {
# Heading or subheading.
$pflags =~ /.... (.*) :(.*)/;
$hdr = ($ptype eq "subh" ? "h4" : "h3");
$title = $1 . " ";
$xref = $2;
foreach $i (@$pname) {
$ww = &word_html($i);
$title .= $ww unless $ww eq "\001";
}
print "<$hdr id=\"$xref\">$title</$hdr>\n";
} elsif ($ptype eq "code") {
# Code paragraph.
$in_code = 1, print "<pre>" unless $in_code;
print "\n";
foreach $i (@$pname) {
$w = $i;
$w =~ s/&/&/g;
$w =~ s/</</g;
$w =~ s/>/>/g;
print $w, "\n";
}
} elsif ($ptype =~ /^(norm|bull|indt|bquo)$/) {
# Ordinary paragraph, optionally indented.
if ($ptype eq 'bull') {
if (!$in_list) {
$in_list = 1;
print "<ul>\n";
} else {
print "</li>\n";
}
print "<li>\n";
$line = '<p>';
$endtag = '</p>';
} elsif ($ptype eq 'indt') {
if (!$in_list) {
$in_list = 1;
print "<ul>\n";
print "<li class=\"indt\">\n"; # This is such a hack
}
$line = '<p>';
$endtag = '</p>';
} elsif ($ptype eq 'bquo') {
$in_bquo = 1, print "<blockquote>\n" unless $in_bquo;
$line = '<p>';
$endtag = '</p>';
} else {
$line = '<p>';
$endtag = '</p>';
}
@a = @$pname;
$wd = $wprev = '';
do {
do { $w = &word_html(shift @a) } while $w eq "\001"; # nasty hack
$wd .= $wprev;
if ($w eq ' ' || $w eq '' || $w eq undef) {
if (length ($line . $wd) > 75) {
$line =~ s/\s*$//; # trim trailing spaces
print "$line\n";
$line = '';
$wd =~ s/^\s*//; # trim leading spaces
}
$line .= $wd;
$wd = '';
}
$wprev = $w;