summaryrefslogtreecommitdiff
path: root/macros/texinfo/texinfo/tp/Texinfo/Convert/NodeNameNormalization.pm
blob: 0886d9e20c8597dd8637ab742ef472022c50fb05 (plain)
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
# NodeNameNormalization.pm: output tree as normalized node name.
#
# Copyright 2010-2022 Free Software Foundation, Inc.
# 
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License,
# or (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
# 
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
# 
# Original author: Patrice Dumas <pertusus@free.fr>

# the rules for conversion are decribed in the Texinfo manual, for
# HTML crossrefs in the 'HTML Xref' node.

package Texinfo::Convert::NodeNameNormalization;

use 5.00405;
use strict;

# stop \s from matching non-ASCII spaces, etc.  \p{...} can still be
# used to match Unicode character classes.
use if $] >= 5.014, re => '/a';

# To check if there is no erroneous autovivification
#no autovivification qw(fetch delete exists store strict);

use Unicode::Normalize;
use Text::Unidecode;

# commands classes
use Texinfo::Commands;
# for nobrace_symbol_text
use Texinfo::Common;
# use the hashes and functions
use Texinfo::Convert::Unicode;
# reuse some conversion hashes and ascii_accent function
use Texinfo::Convert::Text;

require Exporter;
use vars qw($VERSION @ISA @EXPORT_OK %EXPORT_TAGS);
@ISA = qw(Exporter);

%EXPORT_TAGS = ( 'all' => [ qw(
  normalize_node
  transliterate_texinfo
  transliterate_protect_file_name
) ] );

@EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );

$VERSION = '7.0.2';


my %normalize_node_brace_no_arg_commands
  = %Texinfo::Convert::Text::text_brace_no_arg_commands;
foreach my $command (keys(%Texinfo::Convert::Unicode::unicode_character_brace_no_arg_commands)) {
  $normalize_node_brace_no_arg_commands{$command} =
     $Texinfo::Convert::Unicode::unicode_character_brace_no_arg_commands{$command};
}

my %normalize_node_nobrace_symbol_text
  = %Texinfo::Common::nobrace_symbol_text;
$normalize_node_nobrace_symbol_text{'*'} = ' ';

my %accent_commands = %Texinfo::Commands::accent_commands;

my %ignored_brace_commands;
foreach my $ignored_brace_command ('anchor', 'footnote', 'shortcaption',
       'caption', 'hyphenation', 'sortas', 'seealso', 'seeentry') {
  $ignored_brace_commands{$ignored_brace_command} = 1;
}

my %ignored_types;
foreach my $type ('ignorable_spaces_after_command', 'preamble_before_beginning',
            'spaces_at_end',
            'spaces_before_paragraph',
            'space_at_end_menu_node',
            'spaces_after_close_brace') {
  $ignored_types{$type} = 1;
}


sub normalize_node($)
{
  my $root = shift;
  my $result = _convert($root);
  $result = Unicode::Normalize::NFC($result);
  $result = _unicode_to_protected($result);
  $result = 'Top' if ($result =~ /^Top$/i);
  return $result;
}

sub transliterate_texinfo($;$)
{
  my $root = shift;
  my $no_unidecode = shift;
  my $result = _convert($root);
  $result = Unicode::Normalize::NFC($result);
  $result = _unicode_to_protected(
                _unicode_to_transliterate($result, $no_unidecode));
  return $result;
}

sub transliterate_protect_file_name($;$)
{
  my $input_text = shift;
  my $no_unidecode = shift;
  my $result = Unicode::Normalize::NFC($input_text);
  $result = _unicode_to_file_name(
                _unicode_to_transliterate($result, $no_unidecode));
  return $result;
}

sub convert_to_normalized($)
{
  my $root = shift;
  my $result = _convert($root);
}

sub _protect_unicode_char($)
{
  my $char = shift;
  if (exists($Texinfo::Convert::Unicode::unicode_simple_character_map{$char})) {
    return '_' . lc($Texinfo::Convert::Unicode::unicode_simple_character_map{$char});
  } else {
    if (ord($char) <= hex(0xFFFF)) {
      return '_' . lc(sprintf("%04x",ord($char)));
    } else {
      return '__' . lc(sprintf("%06x",ord($char)));
    }
  }
}

sub _unicode_to_protected($)
{
  my $text = shift;
  my $result = '';
  while ($text ne '') {
    if ($text =~ s/^([A-Za-z0-9]+)//) {
      $result .= $1;
    } elsif ($text =~ s/^ +//) {
      $result .= '-';
    # with /a some special spaces are not caught without /s, maybe because they are
    # considered as newlines
    } elsif ($text =~ s/^(.)//s) {
      $result .= _protect_unicode_char($1);
    } else {
      warn "Bug: unknown character _unicode_to_protected (likely in infinite loop)\n";
      print STDERR "Text: !!$text!!\n";
      sleep 1;
    }
  }
  return $result;
}

sub _unicode_to_file_name($)
{
  my $text = shift;
  my $result = '';
  while ($text ne '') {
    if ($text =~ s/^([A-Za-z0-9_\.\-]+)//) {
      $result .= $1;
    } elsif ($text =~ s/^ +//) {
      $result .= '-';
    # /s is specified to caught special spaces considered as newlines too
    } elsif ($text =~ s/^(.)//s) {
      $result .= _protect_unicode_char($1);
    } else {
      warn "Bug: unknown character _unicode_to_file_name (likely in infinite loop)\n";
      print STDERR "Text: !!$text!!\n";
      sleep 1;
    }
  }
  return $result;
}

sub _unicode_to_transliterate($;$)
{
  my $text = shift;
  my $no_unidecode = shift;
  if (chomp($text)) {
     warn "Bug: end of line to transliterate: $text\n";
  }
  my $result = '';
  while ($text ne '') {
    if ($text =~ s/^([A-Za-z0-9 ]+)//) {
      $result .= $1;
    } elsif ($text =~ s/^(.)//s) {
      my $char = $1;
      if (exists($Texinfo::Convert::Unicode::unicode_simple_character_map{$char})) {
        $result .= $char;
      } elsif (ord($char) <= hex(0xFFFF)
               and exists($Texinfo::Convert::Unicode::transliterate_map{uc(sprintf("%04x",ord($char)))})) {
        $result .= $Texinfo::Convert::Unicode::transliterate_map{uc(sprintf("%04x",ord($char)))};
      } elsif (ord($char) <= hex(0xFFFF)
               and exists($Texinfo::Convert::Unicode::diacritics_accent_commands{uc(sprintf("%04x",ord($char)))})) {
        $result .= '';
      # in this case, we want to avoid calling unidecode, as we are sure
      # that there is no useful transliteration of the unicode character
      # instead we want to keep it as is.
      # This is the case, for example, for @exclamdown, is corresponds
      # with x00a1, but unidecode transliterates it to a !, we want
      # to avoid that and keep x00a1.
      } elsif (ord($char) <= hex(0xFFFF)
               and exists($Texinfo::Convert::Unicode::no_transliterate_map{uc(sprintf("%04x",ord($char)))})) {
        $result .= $char;
      } else {
        if ($no_unidecode) {
          if (ord($char) <= hex(0xFFFF)
              and exists ($Texinfo::Convert::Unicode::transliterate_accent_map{uc(sprintf("%04x",ord($char)))})) {
            $result .= $Texinfo::Convert::Unicode::transliterate_accent_map{uc(sprintf("%04x",ord($char)))};
          } else {
            $result .= $char;
          }
        } else {
          $result .= unidecode($char);
        }
      }
      #print STDERR " ($no_unidecode) $text -> CHAR: ".ord($char)." ".uc(sprintf("%04x",ord($char)))."\n$result\n";
    } else {
      warn "Bug: unknown character _unicode_to_transliterate (likely in infinite loop)\n";
      print STDERR "Text: !!$text!!\n";
      sleep 1;
    }
  }
  return $result;
}


sub _convert($;$);

sub _convert($;$)
{
  my $element = shift;
  my $in_sc = shift;

  return '' if (($element->{'type'} and $ignored_types{$element->{'type'}})
          or ($element->{'cmdname'}
             and ($ignored_brace_commands{$element->{'cmdname'}}
             # here ignore the line commands
                 or ($element->{'args'} and $element->{'args'}->[0]
                     and $element->{'args'}->[0]->{'type'}
                     and ($element->{'args'}->[0]->{'type'} eq 'line_arg'
                         or $element->{'args'}->[0]->{'type'} eq 'misc_arg')))));
  my $result = '';
  if (defined($element->{'text'})) {
    $result = $element->{'text'};
    $result =~ s/\s+/ /g;
    $result = uc($result) if ($in_sc);
  }
  if ($element->{'cmdname'}) {
    my $command = $element->{'cmdname'};
    if (defined($normalize_node_nobrace_symbol_text{$element->{'cmdname'}})) {
      return $normalize_node_nobrace_symbol_text{$element->{'cmdname'}};
    } elsif (defined($normalize_node_brace_no_arg_commands{$element->{'cmdname'}})) {
      $command = $element->{'extra'}->{'clickstyle'}
         if ($element->{'extra'}
          and defined($element->{'extra'}->{'clickstyle'})
          and defined($normalize_node_brace_no_arg_commands{$element->{'extra'}->{'clickstyle'}}));
      my $result = $normalize_node_brace_no_arg_commands{$command};
      if ($in_sc and $Texinfo::Commands::letter_no_arg_commands{$command}) {
        $result = uc($result);
      }
      return $result;
    # commands with braces
    } elsif ($accent_commands{$element->{'cmdname'}}) {
      return '' if (!$element->{'args'});
      my $accent_text = _convert($element->{'args'}->[0]);
      my $accented_char
        = Texinfo::Convert::Unicode::unicode_accent($accent_text,
                                                    $element);
      if (!defined($accented_char)) {
        # In this case, the node normalization do not follow the specification,
        # but we cannot do better
        $accented_char = Texinfo::Convert::Text::ascii_accent($accent_text,
                                                              $element);
      }
      if ($in_sc) {
        return uc ($accented_char);
      } else {
        return $accented_char;
      }
    #} elsif ($element->{'cmdname'} eq 'image') {
    #  return _convert($element->{'args'}->[0]);
    } elsif ($Texinfo::Commands::ref_commands{$element->{'cmdname'}}) {
      my @args_try_order;
      if ($element->{'cmdname'} eq 'inforef') {
        @args_try_order = (0, 1, 2);
      } else {
        @args_try_order = (0, 1, 2, 4, 3);
      }
      foreach my $index (@args_try_order) {
        if (defined($element->{'args'}->[$index])) {
          my $text = _convert($element->{'args'}->[$index]);
          return $text if (defined($text) and $text =~ /\S/);
        }
      }
      return '';
    # Here all the commands with args are processed, if they have
    # more than one arg the first one is used.
    } elsif ($element->{'args'} and $element->{'args'}->[0]
           and (($element->{'args'}->[0]->{'type'}
                and $element->{'args'}->[0]->{'type'} eq 'brace_command_arg')
                or $element->{'cmdname'} eq 'math')) {
      my $sc = 1 if ($element->{'cmdname'} eq 'sc' or $in_sc);
      return _convert($element->{'args'}->[0], $sc);
    }
  }
  if ($element->{'contents'}) {
    foreach my $content (@{$element->{'contents'}}) {
      $result .= _convert($content, $in_sc);
    }
  }
  $result = '{'.$result.'}'
     if ($element->{'type'} and $element->{'type'} eq 'bracketed');
  return $result;
}

# Called from Texinfo::ParserNonXS and Texinfo::XS::parsetexi::Parsetexi.
# This should be considered an internal function of the parsers for all
# purposes, it is here to avoid code duplication.
# Sets $self->{'nodes'} and $self->{'labels'} based on $self->{'targets'}.
sub set_nodes_list_labels($$$)
{
  my $self = shift;
  my $registrar = shift;
  my $configuration_information = shift;

  $self->{'nodes'} = [];
  my %labels = ();
  if (defined $self->{'targets'}) {
    for my $target (@{$self->{'targets'}}) {
      if ($target->{'cmdname'} eq 'node') {
        if ($target->{'extra'}->{'nodes_manuals'}) {
          for my $node_manual (@{$target->{'extra'}{'nodes_manuals'}}) {
            if (defined $node_manual
                  and defined $node_manual->{'node_content'}) {
              my $normalized = Texinfo::Convert::NodeNameNormalization::normalize_node(
                                    {'contents' => $node_manual->{'node_content'}});
              $node_manual->{'normalized'} = $normalized;
            }
          }
        }
      }
      if (defined $target->{'extra'}
            and defined $target->{'extra'}->{'node_content'}) {
        my $normalized = Texinfo::Convert::NodeNameNormalization::normalize_node(
                             {'contents' => $target->{'extra'}->{'node_content'}});

        if ($normalized !~ /[^-]/) {
          $registrar->line_error($configuration_information,
               sprintf(__("empty node name after expansion `%s'"),
                     Texinfo::Convert::Texinfo::convert_to_texinfo({'contents'
                                   => $target->{'extra'}->{'node_content'}})),
                            $target->{'source_info'});
          delete $target->{'extra'}->{'node_content'};
        } else {
          if (defined $labels{$normalized}) {
            $registrar->line_error($configuration_information,
              sprintf(__("\@%s `%s' previously defined"),
                         $target->{'cmdname'},
                   Texinfo::Convert::Texinfo::convert_to_texinfo({'contents'
                                    => $target->{'extra'}->{'node_content'}})),
                               $target->{'source_info'});
            $registrar->line_error($configuration_information,
              sprintf(__("here is the previous definition as \@%s"),
                               $labels{$normalized}->{'cmdname'}),
                       $labels{$normalized}->{'source_info'});
            delete $target->{'extra'}->{'node_content'};
          } else {
            $labels{$normalized} = $target;
            $target->{'extra'}->{'normalized'} = $normalized;
            if ($target->{'cmdname'} eq 'node') {
              if ($target->{'extra'}
                  and $target->{'extra'}{'node_argument'}) {
                $target->{'extra'}{'node_argument'}{'normalized'}
                  = $normalized;
              }
              push @{$self->{'nodes'}}, $target;
            }
          }
        }
      } else {
        if ($target->{'cmdname'} eq 'node') {
          $registrar->line_error($configuration_information,
               sprintf(__("empty argument in \@%s"),
                  $target->{'cmdname'}), $target->{'source_info'});
          delete $target->{'extra'}->{'node_content'};
        }
      }
    }
  }
  $self->{'labels'} = \%labels;
}
1;

__END__

=head1 NAME

Texinfo::Convert::NodeNameNormalization - Normalize and transliterate Texinfo trees

=head1 SYNOPSIS

  use Texinfo::Convert::NodeNameNormalization qw(normalize_node
                                              transliterate_texinfo);

  my $normalized = normalize_node({'contents' => $node_contents});

  my $file_name = transliterate_texinfo({'contents'
                                            => $section_contents});

=head1 NOTES

The Texinfo Perl module main purpose is to be used in C<texi2any> to convert
Texinfo to other formats.  There is no promise of API stability.

=head1 DESCRIPTION

C<Texinfo::Convert::NodeNameNormalization> allows to normalize node names,
with C<normalize_node> following the specification described in the
Texinfo manual I<HTML Xref> node.  This is usefull each time one want a
unique identifier for Texinfo content that is only composed of letter,
digits, C<-> and C<_>.  In L<Texinfo::Parser>, C<normalize_node> is used
for C<@node>, C<@float> and C<@anchor> names normalization, but also C<@float>
types and C<@acronym> and C<@abbr> first argument.

It is also possible to transliterate non-ASCII letters, instead of mangling
them, with C<transliterate_texinfo>, losing the uniqueness feature of
normalized node names.

Another method, C<transliterate_protect_file_name> transliterates non-ASCII
letters and protect characters that should not appear on file names.

=head1 METHODS

=over

=item $partially_normalized = convert_to_normalized($tree)
X<C<convert_to_normalized>>

The Texinfo I<$tree> is returned as a string, with @-commands and spaces
normalized as described in the Texinfo manual I<HTML Xref> node.  ASCII
7-bit characters other than spaces and non-ASCII characters are left as
is in the resulting string.

=item $normalized = normalize_node($tree)
X<C<normalize_node>>

The Texinfo I<$tree> is returned as a string, normalized as described in the
Texinfo manual I<HTML Xref> node.

The result will be poor for Texinfo trees which are not @-command arguments
(on an @-command line or in braces), for instance if the tree contains
C<@node> or block commands.

=item $transliterated = transliterate_texinfo($tree, $no_unidecode)
X<C<transliterate_texinfo>>

The Texinfo I<$tree> is returned as a string, with non-ASCII letters
transliterated as ASCII, but otherwise similar with C<normalize_node>
output.  If the optional I<$no_unidecode> argument is set, C<Text::Unidecode>
is not used for characters whose transliteration is not built-in.

=item $file_name = transliterate_protect_file_name($string, $no_unidecode)
X<C<transliterate_protect_file_name>>

The string I<$string> is returned with non-ASCII letters transliterated as
ASCII, and ASCII characters not safe in file names protected as in
node normalization.  If the optional I<$no_unidecode> argument is set,
C<Text::Unidecode> is not used for characters whose transliteration is not
built-in.

=back

=head1 AUTHOR

Patrice Dumas, E<lt>pertusus@free.frE<gt>

=head1 COPYRIGHT AND LICENSE

Copyright 2010- Free Software Foundation, Inc.  See the source file for
all copyright years.

This library is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or (at
your option) any later version.

=cut