daily update
[binutils.git] / etc / texi2pod.pl
blob9696a12f3610a10d9579ea12cc6a6680a8d0905c
1 #! /usr/bin/perl -w
3 # Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation, Inc.
5 # This file is part of GCC.
7 # GCC is free software; you can redistribute it and/or modify
8 # it under the terms of the GNU General Public License as published by
9 # the Free Software Foundation; either version 2, or (at your option)
10 # any later version.
12 # GCC is distributed in the hope that it will be useful,
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU General Public License for more details.
17 # You should have received a copy of the GNU General Public License
18 # along with GCC; see the file COPYING. If not, write to
19 # the Free Software Foundation, 51 Franklin Street, Fifth Floor,
20 # Boston MA 02110-1301, USA.
22 # This does trivial (and I mean _trivial_) conversion of Texinfo
23 # markup to Perl POD format. It's intended to be used to extract
24 # something suitable for a manpage from a Texinfo document.
26 $output = 0;
27 $skipping = 0;
28 %sects = ();
29 $section = "";
30 @icstack = ();
31 @endwstack = ();
32 @skstack = ();
33 @instack = ();
34 $shift = "";
35 %defs = ();
36 $fnno = 1;
37 $inf = "";
38 $ibase = "";
40 while ($_ = shift) {
41 if (/^-D(.*)$/) {
42 if ($1 ne "") {
43 $flag = $1;
44 } else {
45 $flag = shift;
47 $value = "";
48 ($flag, $value) = ($flag =~ /^([^=]+)(?:=(.+))?/);
49 die "no flag specified for -D\n"
50 unless $flag ne "";
51 die "flags may only contain letters, digits, hyphens, dashes and underscores\n"
52 unless $flag =~ /^[a-zA-Z0-9_-]+$/;
53 $defs{$flag} = $value;
54 } elsif (/^-/) {
55 usage();
56 } else {
57 $in = $_, next unless defined $in;
58 $out = $_, next unless defined $out;
59 usage();
63 if (defined $in) {
64 $inf = gensym();
65 open($inf, "<$in") or die "opening \"$in\": $!\n";
66 $ibase = $1 if $in =~ m|^(.+)/[^/]+$|;
67 } else {
68 $inf = \*STDIN;
71 if (defined $out) {
72 open(STDOUT, ">$out") or die "opening \"$out\": $!\n";
75 while(defined $inf) {
76 while(<$inf>) {
77 # Certain commands are discarded without further processing.
78 /^\@(?:
79 [a-z]+index # @*index: useful only in complete manual
80 |need # @need: useful only in printed manual
81 |(?:end\s+)?group # @group .. @end group: ditto
82 |page # @page: ditto
83 |node # @node: useful only in .info file
84 |(?:end\s+)?ifnottex # @ifnottex .. @end ifnottex: use contents
85 )\b/x and next;
87 chomp;
89 # Look for filename and title markers.
90 /^\@setfilename\s+([^.]+)/ and $fn = $1, next;
91 /^\@settitle\s+([^.]+)/ and $tl = postprocess($1), next;
93 # Identify a man title but keep only the one we are interested in.
94 /^\@c\s+man\s+title\s+([A-Za-z0-9-]+)\s+(.+)/ and do {
95 if (exists $defs{$1}) {
96 $fn = $1;
97 $tl = postprocess($2);
99 next;
102 # Look for blocks surrounded by @c man begin SECTION ... @c man end.
103 # This really oughta be @ifman ... @end ifman and the like, but such
104 # would require rev'ing all other Texinfo translators.
105 /^\@c\s+man\s+begin\s+([A-Z]+)\s+([A-Za-z0-9-]+)/ and do {
106 $output = 1 if exists $defs{$2};
107 $sect = $1;
108 next;
110 /^\@c\s+man\s+begin\s+([A-Z]+)/ and $sect = $1, $output = 1, next;
111 /^\@c\s+man\s+end/ and do {
112 $sects{$sect} = "" unless exists $sects{$sect};
113 $sects{$sect} .= postprocess($section);
114 $section = "";
115 $output = 0;
116 next;
119 # handle variables
120 /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and do {
121 $defs{$1} = $2;
122 next;
124 /^\@clear\s+([a-zA-Z0-9_-]+)/ and do {
125 delete $defs{$1};
126 next;
129 next unless $output;
131 # Discard comments. (Can't do it above, because then we'd never see
132 # @c man lines.)
133 /^\@c\b/ and next;
135 # End-block handler goes up here because it needs to operate even
136 # if we are skipping.
137 /^\@end\s+([a-z]+)/ and do {
138 # Ignore @end foo, where foo is not an operation which may
139 # cause us to skip, if we are presently skipping.
140 my $ended = $1;
141 next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu|iftex|copying)$/;
143 die "\@end $ended without \@$ended at line $.\n" unless defined $endw;
144 die "\@$endw ended by \@end $ended at line $.\n" unless $ended eq $endw;
146 $endw = pop @endwstack;
148 if ($ended =~ /^(?:ifset|ifclear|ignore|menu|iftex)$/) {
149 $skipping = pop @skstack;
150 next;
151 } elsif ($ended =~ /^(?:example|smallexample|display)$/) {
152 $shift = "";
153 $_ = ""; # need a paragraph break
154 } elsif ($ended =~ /^(?:itemize|enumerate|[fv]?table)$/) {
155 $_ = "\n=back\n";
156 $ic = pop @icstack;
157 } else {
158 die "unknown command \@end $ended at line $.\n";
162 # We must handle commands which can cause skipping even while we
163 # are skipping, otherwise we will not process nested conditionals
164 # correctly.
165 /^\@ifset\s+([a-zA-Z0-9_-]+)/ and do {
166 push @endwstack, $endw;
167 push @skstack, $skipping;
168 $endw = "ifset";
169 $skipping = 1 unless exists $defs{$1};
170 next;
173 /^\@ifclear\s+([a-zA-Z0-9_-]+)/ and do {
174 push @endwstack, $endw;
175 push @skstack, $skipping;
176 $endw = "ifclear";
177 $skipping = 1 if exists $defs{$1};
178 next;
181 /^\@(ignore|menu|iftex|copying)\b/ and do {
182 push @endwstack, $endw;
183 push @skstack, $skipping;
184 $endw = $1;
185 $skipping = 1;
186 next;
189 next if $skipping;
191 # Character entities. First the ones that can be replaced by raw text
192 # or discarded outright:
193 s/\@copyright\{\}/(c)/g;
194 s/\@dots\{\}/.../g;
195 s/\@enddots\{\}/..../g;
196 s/\@([.!? ])/$1/g;
197 s/\@[:-]//g;
198 s/\@bullet(?:\{\})?/*/g;
199 s/\@TeX\{\}/TeX/g;
200 s/\@pounds\{\}/\#/g;
201 s/\@minus(?:\{\})?/-/g;
202 s/\\,/,/g;
204 # Now the ones that have to be replaced by special escapes
205 # (which will be turned back into text by unmunge())
206 s/&/&amp;/g;
207 s/\@\{/&lbrace;/g;
208 s/\@\}/&rbrace;/g;
209 s/\@\@/&at;/g;
211 # Inside a verbatim block, handle @var specially.
212 if ($shift ne "") {
213 s/\@var\{([^\}]*)\}/<$1>/g;
216 # POD doesn't interpret E<> inside a verbatim block.
217 if ($shift eq "") {
218 s/</&lt;/g;
219 s/>/&gt;/g;
220 } else {
221 s/</&LT;/g;
222 s/>/&GT;/g;
225 # Single line command handlers.
227 /^\@include\s+(.+)$/ and do {
228 push @instack, $inf;
229 $inf = gensym();
230 $file = postprocess($1);
232 # Try cwd and $ibase.
233 open($inf, "<" . $file)
234 or open($inf, "<" . $ibase . "/" . $file)
235 or die "cannot open $file or $ibase/$file: $!\n";
236 next;
239 /^\@(?:section|unnumbered|unnumberedsec|center)\s+(.+)$/
240 and $_ = "\n=head2 $1\n";
241 /^\@subsection\s+(.+)$/
242 and $_ = "\n=head3 $1\n";
244 # Block command handlers:
245 /^\@itemize(?:\s+(\@[a-z]+|\*|-))?/ and do {
246 push @endwstack, $endw;
247 push @icstack, $ic;
248 if (defined $1) {
249 $ic = $1;
250 } else {
251 $ic = '@bullet';
253 $_ = "\n=over 4\n";
254 $endw = "itemize";
257 /^\@enumerate(?:\s+([a-zA-Z0-9]+))?/ and do {
258 push @endwstack, $endw;
259 push @icstack, $ic;
260 if (defined $1) {
261 $ic = $1 . ".";
262 } else {
263 $ic = "1.";
265 $_ = "\n=over 4\n";
266 $endw = "enumerate";
269 /^\@([fv]?table)\s+(\@[a-z]+)/ and do {
270 push @endwstack, $endw;
271 push @icstack, $ic;
272 $endw = $1;
273 $ic = $2;
274 $ic =~ s/\@(?:samp|strong|key|gcctabopt|env)/B/;
275 $ic =~ s/\@(?:code|kbd)/C/;
276 $ic =~ s/\@(?:dfn|var|emph|cite|i)/I/;
277 $ic =~ s/\@(?:file)/F/;
278 $_ = "\n=over 4\n";
281 /^\@((?:small)?example|display)/ and do {
282 push @endwstack, $endw;
283 $endw = $1;
284 $shift = "\t";
285 $_ = ""; # need a paragraph break
288 /^\@itemx?\s*(.+)?$/ and do {
289 if (defined $1) {
290 # Entity escapes prevent munging by the <> processing below.
291 $_ = "\n=item $ic\&LT;$1\&GT;\n";
292 } else {
293 $_ = "\n=item $ic\n";
294 $ic =~ y/A-Ya-y/B-Zb-z/;
295 $ic =~ s/(\d+)/$1 + 1/eg;
299 $section .= $shift.$_."\n";
301 # End of current file.
302 close($inf);
303 $inf = pop @instack;
306 die "No filename or title\n" unless defined $fn && defined $tl;
308 $sects{NAME} = "$fn \- $tl\n";
309 $sects{FOOTNOTES} .= "=back\n" if exists $sects{FOOTNOTES};
311 for $sect (qw(NAME SYNOPSIS DESCRIPTION OPTIONS ENVIRONMENT FILES
312 BUGS NOTES FOOTNOTES SEEALSO AUTHOR COPYRIGHT)) {
313 if(exists $sects{$sect}) {
314 $head = $sect;
315 $head =~ s/SEEALSO/SEE ALSO/;
316 print "=head1 $head\n\n";
317 print scalar unmunge ($sects{$sect});
318 print "\n";
322 sub usage
324 die "usage: $0 [-D toggle...] [infile [outfile]]\n";
327 sub postprocess
329 local $_ = $_[0];
331 # @value{foo} is replaced by whatever 'foo' is defined as.
332 while (m/(\@value\{([a-zA-Z0-9_-]+)\})/g) {
333 if (! exists $defs{$2}) {
334 print STDERR "Option $2 not defined\n";
335 s/\Q$1\E//;
336 } else {
337 $value = $defs{$2};
338 s/\Q$1\E/$value/;
342 # Formatting commands.
343 # Temporary escape for @r.
344 s/\@r\{([^\}]*)\}/R<$1>/g;
345 s/\@(?:dfn|var|emph|cite|i)\{([^\}]*)\}/I<$1>/g;
346 s/\@(?:code|kbd)\{([^\}]*)\}/C<$1>/g;
347 s/\@(?:gccoptlist|samp|strong|key|option|env|command|b)\{([^\}]*)\}/B<$1>/g;
348 s/\@sc\{([^\}]*)\}/\U$1/g;
349 s/\@file\{([^\}]*)\}/F<$1>/g;
350 s/\@w\{([^\}]*)\}/S<$1>/g;
351 s/\@(?:dmn|math)\{([^\}]*)\}/$1/g;
353 # keep references of the form @ref{...}, print them bold
354 s/\@(?:ref)\{([^\}]*)\}/B<$1>/g;
356 # Change double single quotes to double quotes.
357 s/''/"/g;
358 s/``/"/g;
360 # Cross references are thrown away, as are @noindent and @refill.
361 # (@noindent is impossible in .pod, and @refill is unnecessary.)
362 # @* is also impossible in .pod; we discard it and any newline that
363 # follows it. Similarly, our macro @gol must be discarded.
365 s/\(?\@xref\{(?:[^\}]*)\}(?:[^.<]|(?:<[^<>]*>))*\.\)?//g;
366 s/\s+\(\@pxref\{(?:[^\}]*)\}\)//g;
367 s/;\s+\@pxref\{(?:[^\}]*)\}//g;
368 s/\@noindent\s*//g;
369 s/\@refill//g;
370 s/\@gol//g;
371 s/\@\*\s*\n?//g;
373 # @uref can take one, two, or three arguments, with different
374 # semantics each time. @url and @email are just like @uref with
375 # one argument, for our purposes.
376 s/\@(?:uref|url|email)\{([^\},]*)\}/&lt;B<$1>&gt;/g;
377 s/\@uref\{([^\},]*),([^\},]*)\}/$2 (C<$1>)/g;
378 s/\@uref\{([^\},]*),([^\},]*),([^\},]*)\}/$3/g;
380 # Un-escape <> at this point.
381 s/&LT;/</g;
382 s/&GT;/>/g;
384 # Now un-nest all B<>, I<>, R<>. Theoretically we could have
385 # indefinitely deep nesting; in practice, one level suffices.
386 1 while s/([BIR])<([^<>]*)([BIR])<([^<>]*)>/$1<$2>$3<$4>$1</g;
388 # Replace R<...> with bare ...; eliminate empty markup, B<>;
389 # shift white space at the ends of [BI]<...> expressions outside
390 # the expression.
391 s/R<([^<>]*)>/$1/g;
392 s/[BI]<>//g;
393 s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g;
394 s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g;
396 # Extract footnotes. This has to be done after all other
397 # processing because otherwise the regexp will choke on formatting
398 # inside @footnote.
399 while (/\@footnote/g) {
400 s/\@footnote\{([^\}]+)\}/[$fnno]/;
401 add_footnote($1, $fnno);
402 $fnno++;
405 return $_;
408 sub unmunge
410 # Replace escaped symbols with their equivalents.
411 local $_ = $_[0];
413 s/&lt;/E<lt>/g;
414 s/&gt;/E<gt>/g;
415 s/&lbrace;/\{/g;
416 s/&rbrace;/\}/g;
417 s/&at;/\@/g;
418 s/&amp;/&/g;
419 return $_;
422 sub add_footnote
424 unless (exists $sects{FOOTNOTES}) {
425 $sects{FOOTNOTES} = "\n=over 4\n\n";
428 $sects{FOOTNOTES} .= "=item $fnno.\n\n"; $fnno++;
429 $sects{FOOTNOTES} .= $_[0];
430 $sects{FOOTNOTES} .= "\n\n";
433 # stolen from Symbol.pm
435 my $genseq = 0;
436 sub gensym
438 my $name = "GEN" . $genseq++;
439 my $ref = \*{$name};
440 delete $::{$name};
441 return $ref;