This file is indexed.

/usr/share/perl5/Image/ExifTool/HTML.pm is in libimage-exiftool-perl 8.60-2.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
#------------------------------------------------------------------------------
# File:         HTML.pm
#
# Description:  Read HTML meta information
#
# Revisions:    01/30/2007 - P. Harvey Created
#
# References:   1) http://www.w3.org/TR/html4/
#               2) http://www.daisy.org/publications/specifications/daisy_202.html
#               3) http://vancouver-webpages.com/META/metatags.detail.html
#               4) http://www.html-reference.com/META.htm
#------------------------------------------------------------------------------

package Image::ExifTool::HTML;

use strict;
use vars qw($VERSION @ISA @EXPORT_OK);
use Image::ExifTool qw(:DataAccess :Utils);
use Image::ExifTool::PostScript;
use Image::ExifTool::XMP qw(EscapeXML UnescapeXML);
require Exporter;

$VERSION = '1.11';
@ISA = qw(Exporter);
@EXPORT_OK = qw(EscapeHTML UnescapeHTML);

sub SetHTMLCharset($$);

# convert HTML charset (lower case) to ExifTool Charset name
my %htmlCharset = (
    macintosh     => 'MacRoman',
   'iso-8859-1'   => 'Latin',
   'utf-8'        => 'UTF8',
   'windows-1252' => 'Latin',
);

# HTML 4 character entity references
my %entityNum = (
    'quot'   => 34,   'eth'    => 240,  'lsquo'  => 8216,
    'amp'    => 38,   'ntilde' => 241,  'rsquo'  => 8217,
    'apos'   => 39,   'ograve' => 242,  'sbquo'  => 8218,
    'lt'     => 60,   'oacute' => 243,  'ldquo'  => 8220,
    'gt'     => 62,   'ocirc'  => 244,  'rdquo'  => 8221,
    'nbsp'   => 160,  'otilde' => 245,  'bdquo'  => 8222,
    'iexcl'  => 161,  'ouml'   => 246,  'dagger' => 8224,
    'cent'   => 162,  'divide' => 247,  'Dagger' => 8225,
    'pound'  => 163,  'oslash' => 248,  'bull'   => 8226,
    'curren' => 164,  'ugrave' => 249,  'hellip' => 8230,
    'yen'    => 165,  'uacute' => 250,  'permil' => 8240,
    'brvbar' => 166,  'ucirc'  => 251,  'prime'  => 8242,
    'sect'   => 167,  'uuml'   => 252,  'Prime'  => 8243,
    'uml'    => 168,  'yacute' => 253,  'lsaquo' => 8249,
    'copy'   => 169,  'thorn'  => 254,  'rsaquo' => 8250,
    'ordf'   => 170,  'yuml'   => 255,  'oline'  => 8254,
    'laquo'  => 171,  'OElig'  => 338,  'frasl'  => 8260,
    'not'    => 172,  'oelig'  => 339,  'euro'   => 8364,
    'shy'    => 173,  'Scaron' => 352,  'image'  => 8465,
    'reg'    => 174,  'scaron' => 353,  'weierp' => 8472,
    'macr'   => 175,  'Yuml'   => 376,  'real'   => 8476,
    'deg'    => 176,  'fnof'   => 402,  'trade'  => 8482,
    'plusmn' => 177,  'circ'   => 710,  'alefsym'=> 8501,
    'sup2'   => 178,  'tilde'  => 732,  'larr'   => 8592,
    'sup3'   => 179,  'Alpha'  => 913,  'uarr'   => 8593,
    'acute'  => 180,  'Beta'   => 914,  'rarr'   => 8594,
    'micro'  => 181,  'Gamma'  => 915,  'darr'   => 8595,
    'para'   => 182,  'Delta'  => 916,  'harr'   => 8596,
    'middot' => 183,  'Epsilon'=> 917,  'crarr'  => 8629,
    'cedil'  => 184,  'Zeta'   => 918,  'lArr'   => 8656,
    'sup1'   => 185,  'Eta'    => 919,  'uArr'   => 8657,
    'ordm'   => 186,  'Theta'  => 920,  'rArr'   => 8658,
    'raquo'  => 187,  'Iota'   => 921,  'dArr'   => 8659,
    'frac14' => 188,  'Kappa'  => 922,  'hArr'   => 8660,
    'frac12' => 189,  'Lambda' => 923,  'forall' => 8704,
    'frac34' => 190,  'Mu'     => 924,  'part'   => 8706,
    'iquest' => 191,  'Nu'     => 925,  'exist'  => 8707,
    'Agrave' => 192,  'Xi'     => 926,  'empty'  => 8709,
    'Aacute' => 193,  'Omicron'=> 927,  'nabla'  => 8711,
    'Acirc'  => 194,  'Pi'     => 928,  'isin'   => 8712,
    'Atilde' => 195,  'Rho'    => 929,  'notin'  => 8713,
    'Auml'   => 196,  'Sigma'  => 931,  'ni'     => 8715,
    'Aring'  => 197,  'Tau'    => 932,  'prod'   => 8719,
    'AElig'  => 198,  'Upsilon'=> 933,  'sum'    => 8721,
    'Ccedil' => 199,  'Phi'    => 934,  'minus'  => 8722,
    'Egrave' => 200,  'Chi'    => 935,  'lowast' => 8727,
    'Eacute' => 201,  'Psi'    => 936,  'radic'  => 8730,
    'Ecirc'  => 202,  'Omega'  => 937,  'prop'   => 8733,
    'Euml'   => 203,  'alpha'  => 945,  'infin'  => 8734,
    'Igrave' => 204,  'beta'   => 946,  'ang'    => 8736,
    'Iacute' => 205,  'gamma'  => 947,  'and'    => 8743,
    'Icirc'  => 206,  'delta'  => 948,  'or'     => 8744,
    'Iuml'   => 207,  'epsilon'=> 949,  'cap'    => 8745,
    'ETH'    => 208,  'zeta'   => 950,  'cup'    => 8746,
    'Ntilde' => 209,  'eta'    => 951,  'int'    => 8747,
    'Ograve' => 210,  'theta'  => 952,  'there4' => 8756,
    'Oacute' => 211,  'iota'   => 953,  'sim'    => 8764,
    'Ocirc'  => 212,  'kappa'  => 954,  'cong'   => 8773,
    'Otilde' => 213,  'lambda' => 955,  'asymp'  => 8776,
    'Ouml'   => 214,  'mu'     => 956,  'ne'     => 8800,
    'times'  => 215,  'nu'     => 957,  'equiv'  => 8801,
    'Oslash' => 216,  'xi'     => 958,  'le'     => 8804,
    'Ugrave' => 217,  'omicron'=> 959,  'ge'     => 8805,
    'Uacute' => 218,  'pi'     => 960,  'sub'    => 8834,
    'Ucirc'  => 219,  'rho'    => 961,  'sup'    => 8835,
    'Uuml'   => 220,  'sigmaf' => 962,  'nsub'   => 8836,
    'Yacute' => 221,  'sigma'  => 963,  'sube'   => 8838,
    'THORN'  => 222,  'tau'    => 964,  'supe'   => 8839,
    'szlig'  => 223,  'upsilon'=> 965,  'oplus'  => 8853,
    'agrave' => 224,  'phi'    => 966,  'otimes' => 8855,
    'aacute' => 225,  'chi'    => 967,  'perp'   => 8869,
    'acirc'  => 226,  'psi'    => 968,  'sdot'   => 8901,
    'atilde' => 227,  'omega'  => 969,  'lceil'  => 8968,
    'auml'   => 228,  'thetasym'=>977,  'rceil'  => 8969,
    'aring'  => 229,  'upsih'  => 978,  'lfloor' => 8970,
    'aelig'  => 230,  'piv'    => 982,  'rfloor' => 8971,
    'ccedil' => 231,  'ensp'   => 8194, 'lang'   => 9001,
    'egrave' => 232,  'emsp'   => 8195, 'rang'   => 9002,
    'eacute' => 233,  'thinsp' => 8201, 'loz'    => 9674,
    'ecirc'  => 234,  'zwnj'   => 8204, 'spades' => 9824,
    'euml'   => 235,  'zwj'    => 8205, 'clubs'  => 9827,
    'igrave' => 236,  'lrm'    => 8206, 'hearts' => 9829,
    'iacute' => 237,  'rlm'    => 8207, 'diams'  => 9830,
    'icirc'  => 238,  'ndash'  => 8211,
    'iuml'   => 239,  'mdash'  => 8212,
);
my %entityName; # look up entity names by number (built as necessary)

# HTML info
# (tag ID's are case insensitive and must be all lower case in tables)
%Image::ExifTool::HTML::Main = (
    GROUPS => { 2 => 'Document' },
    NOTES => q{
        Meta information extracted from the header of HTML and XHTML files.  This is
        a mix of information found in the C<META> elements, C<XML> element, and the
        C<TITLE> element.
    },
    dc => {
        Name => 'DC',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::dc' },
    },
    ncc => {
        Name => 'NCC',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::ncc' },
    },
    prod => {
        Name => 'Prod',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::prod' },
    },
    vw96 => {
        Name => 'VW96',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::vw96' },
    },
   'http-equiv' => {
        Name => 'HTTP-equiv',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::equiv' },
    },
    o => {
        Name => 'Office',
        SubDirectory => { TagTable => 'Image::ExifTool::HTML::Office' },
    },
    abstract        => { },
    author          => { },
    classification  => { },
    copyright       => { },
    description     => { },
    distribution    => { },
   'doc-class'      => { Name => 'DocClass' },
   'doc-rights'     => { Name => 'DocRights' },
   'doc-type'       => { Name => 'DocType' },
    formatter       => { },
    generator       => { },
    googlebot       => { Name => 'GoogleBot' },
    keywords        => { List => 1 },
    mssmarttagspreventparsing => { Name => 'NoMSSmartTags' },
    originator      => { },
    owner           => { },
    progid          => { Name => 'ProgID' },
    rating          => { },
    refresh         => { },
   'resource-type'  => { Name => 'ResourceType' },
   'revisit-after'  => { Name => 'RevisitAfter' },
    robots          => { List => 1 },
    title           => { Notes => "the only extracted tag which isn't from an HTML META element" },
);

# ref 2
%Image::ExifTool::HTML::dc = (
    GROUPS => { 1 => 'HTML-dc', 2 => 'Document' },
    NOTES => 'Dublin Core schema tags (also used in XMP).',
    contributor => { Groups => { 2 => 'Author' }, List => 'Bag' },
    coverage    => { },
    creator     => { Groups => { 2 => 'Author' }, List => 'Seq' },
    date        => {
        Groups => { 2 => 'Time'   },
        List => 'Seq',
        PrintConv => '$self->ConvertDateTime($val)',
    },
    description => { },
   'format'     => { },
    identifier  => { },
    language    => { List => 'Bag' },
    publisher   => { Groups => { 2 => 'Author' }, List => 'Bag' },
    relation    => { List => 'Bag' },
    rights      => { Groups => { 2 => 'Author' } },
    source      => { Groups => { 2 => 'Author' } },
    subject     => { List => 'Bag' },
    title       => { },
    type        => { List => 'Bag' },
);

# ref 2
%Image::ExifTool::HTML::ncc = (
    GROUPS => { 1 => 'HTML-ncc', 2 => 'Document' },
    charset         => { Name => 'CharacterSet' }, # name changed to avoid conflict with -charset option
    depth           => { },
    files           => { },
    footnotes       => { },
    generator       => { },
    kbytesize       => { Name => 'KByteSize' },
    maxpagenormal   => { Name => 'MaxPageNormal' },
    multimediatype  => { Name => 'MultimediaType' },
    narrator        => { },
    pagefront       => { Name => 'PageFront' },
    pagenormal      => { Name => 'PageNormal' },
    pagespecial     => { Name => 'PageSpecial' },
    prodnotes       => { Name => 'ProdNotes' },
    producer        => { },
    produceddate    => { Name => 'ProducedDate', Groups => { 2 => 'Time' } }, # YYYY-mm-dd
    revision        => { },
    revisiondate    => { Name => 'RevisionDate', Groups => { 2 => 'Time' } },
    setinfo         => { Name => 'SetInfo' },
    sidebars        => { },
    sourcedate      => { Name => 'SourceDate', Groups => { 2 => 'Time' } },
    sourceedition   => { Name => 'SourceEdition' },
    sourcepublisher => { Name => 'SourcePublisher' },
    sourcerights    => { Name => 'SourceRights' },
    sourcetitle     => { Name => 'SourceTitle' },
    tocitems        => { Name => 'TOCItems' },
    totaltime       => { Name => 'Duration' }, # HH:MM:SS
);

# ref 3
%Image::ExifTool::HTML::vw96 = (
    GROUPS => { 1 => 'HTML-vw96', 2 => 'Document' },
    objecttype      => { Name => 'ObjectType' },
);

# ref 2
%Image::ExifTool::HTML::prod = (
    GROUPS => { 1 => 'HTML-prod', 2 => 'Document' },
    reclocation     => { Name => 'RecLocation' },
    recengineer     => { Name => 'RecEngineer' },
);

# ref 3/4
%Image::ExifTool::HTML::equiv = (
    GROUPS => { 1 => 'HTTP-equiv', 2 => 'Document' },
    NOTES => 'These tags have a family 1 group name of "HTTP-equiv".',
   'cache-control'       => { Name => 'CacheControl' },
   'content-disposition' => { Name => 'ContentDisposition' },
   'content-language'    => { Name => 'ContentLanguage' },
   'content-script-type' => { Name => 'ContentScriptType' },
   'content-style-type'  => { Name => 'ContentStyleType' },
    # note: setting the HTMLCharset like this will miss any tags which come earlier
   'content-type'        => { Name => 'ContentType', RawConv => \&SetHTMLCharset },
   'default-style'       => { Name => 'DefaultStyle' },
    expires              => { },
   'ext-cache'           => { Name => 'ExtCache' },
    imagetoolbar         => { Name => 'ImageToolbar' },
    lotus                => { },
   'page-enter'          => { Name => 'PageEnter' },
   'page-exit'           => { Name => 'PageExit' },
   'pics-label'          => { Name => 'PicsLabel' },
    pragma               => { },
    refresh              => { },
   'reply-to'            => { Name => 'ReplyTo' },
   'set-cookie'          => { Name => 'SetCookie' },
   'site-enter'          => { Name => 'SiteEnter' },
   'site-exit'           => { Name => 'SiteExit' },
    vary                 => { },
   'window-target'       => { Name => 'WindowTarget' },
);

# MS Office namespace (ref PH)
%Image::ExifTool::HTML::Office = (
    GROUPS => { 1 => 'HTML-office', 2 => 'Document' },
    NOTES => 'Tags written by Microsoft Office applications.',
    Subject     => { },
    Author      => { Groups => { 2 => 'Author' } },
    Keywords    => { },
    Description => { },
    Template    => { },
    LastAuthor  => { Groups => { 2 => 'Author' } },
    Revision    => { Name => 'RevisionNumber' },
    TotalTime   => { Name => 'TotalEditTime',   PrintConv => 'ConvertTimeSpan($val, 60)' },
    Created     => {
        Name => 'CreateDate',
        Groups => { 2 => 'Time' },
        ValueConv => 'Image::ExifTool::XMP::ConvertXMPDate($val)',
        PrintConv => '$self->ConvertDateTime($val)',
    },
    LastSaved   => {
        Name => 'ModifyDate',
        Groups => { 2 => 'Time' },
        ValueConv => 'Image::ExifTool::XMP::ConvertXMPDate($val)',
        PrintConv => '$self->ConvertDateTime($val)',
    },
    LastSaved   => {
        Name => 'ModifyDate',
        Groups => { 2 => 'Time' },
        ValueConv => 'Image::ExifTool::XMP::ConvertXMPDate($val)',
        PrintConv => '$self->ConvertDateTime($val)',
    },
    LastPrinted => {
        Name => 'LastPrinted',
        Groups => { 2 => 'Time' },
        ValueConv => 'Image::ExifTool::XMP::ConvertXMPDate($val)',
        PrintConv => '$self->ConvertDateTime($val)',
    },
    Pages       => { },
    Words       => { },
    Characters  => { },
    Category    => { },
    Manager     => { },
    Company     => { },
    Lines       => { },
    Paragraphs  => { },
    CharactersWithSpaces => { },
    Version     => { Name => 'RevisionNumber' },
);

#------------------------------------------------------------------------------
# Set HTMLCharset member based on content type
# Inputs: 0) content type string, 1) ExifTool ref
# Returns: original string
sub SetHTMLCharset($$)
{
    my ($val, $exifTool) = @_;
    $$exifTool{HTMLCharset} = $htmlCharset{lc $1} if $val =~ /charset=['"]?([-\w]+)/;
    return $val;
}

#------------------------------------------------------------------------------
# Convert single UTF-8 character to HTML character reference
# Inputs: 0) UTF-8 character sequence
# Returns: HTML character reference (ie. "&quot;");
# Note: Must be called via EscapeHTML to load name lookup
sub EscapeChar($)
{
    my $ch = shift;
    my $val;
    if ($] < 5.006001) {
        ($val) = Image::ExifTool::UnpackUTF8($ch);
    } else {
        # the meaning of "U0" is reversed as of Perl 5.10.0!
        ($val) = unpack($] < 5.010000 ? 'U0U' : 'C0U', $ch);
    }
    return '?' unless defined $val;
    return "&$entityName{$val};" if $entityName{$val};
    return sprintf('&#x%x;',$val);
}

#------------------------------------------------------------------------------
# Escape any special characters for HTML
# Inputs: 0) UTF-8 string to be escaped
# Returns: escaped string
sub EscapeHTML($)
{
    my $str = shift;
    # escape XML characters
    $str = EscapeXML($str);
    # escape other special characters if they exist
    if ($str =~ /[\x80-\xff]/) {
        # generate entity name lookup if necessary
        unless (%entityName) {
            local $_;
            foreach (keys %entityNum) {
                $entityName{$entityNum{$_}} = $_;
            }
            delete $entityName{39};  # 'apos' is not valid HTML
        }
        # suppress warnings
        local $SIG{'__WARN__'} = sub { 1 };
        # escape any non-ascii characters for HTML
        $str =~ s/([\xc2-\xf7][\x80-\xbf]+)/EscapeChar($1)/sge;
    }
    return $str;
}

#------------------------------------------------------------------------------
# Unescape all HTML character references
# Inputs: 0) string to be unescaped
# Returns: unescaped string
sub UnescapeHTML($)
{
    return UnescapeXML(shift, \%entityNum);
}

#------------------------------------------------------------------------------
# Extract information from a HTML file
# Inputs: 0) ExifTool object reference, 1) DirInfo reference
# Returns: 1 on success, 0 if this wasn't a valid HTML file
sub ProcessHTML($$)
{
    my ($exifTool, $dirInfo) = @_;
    my $raf = $$dirInfo{RAF};
    my $buff;

    # validate HTML or XHTML file
    $raf->Read($buff, 256) or return 0;
    $buff =~ /^<(!DOCTYPE\s+HTML|HTML|\?xml)/i or return 0;
    $buff =~ /<(!DOCTYPE\s+)?HTML/i or return 0 if $1 eq '?xml';
    $exifTool->SetFileType();

    $raf->Seek(0,0) or $exifTool->Warn('Seek error'), return 1;

    local $/ = Image::ExifTool::PostScript::GetInputRecordSeparator($raf);
    $/ or $exifTool->Warn('Invalid HTML data'), return 1;

    # extract header information
    my $doc;
    while ($raf->ReadLine($buff)) {
        if (not defined $doc) {
            # look for 'head' element
            next unless $buff =~ /<head\b/ig;
            $doc = substr($buff, pos($buff));
            next;
        }
        $doc .= $buff;
        last if $buff =~ m{</head>}i;
    }
    return 1 unless defined $doc;

    # process all elements in header
    my $tagTablePtr = GetTagTable('Image::ExifTool::HTML::Main');
    for (;;) {
        last unless $doc =~ m{<([\w:.-]+)(.*?)>}sg;
        my ($tagName, $attrs) = ($1, $2);
        my $tag = lc($tagName);
        my ($val, $grp);
        unless ($attrs =~ m{/$}) {  # self-contained XHTML tags end in '/>'
            # look for element close
            my $pos = pos($doc);
            my $close = "</$tagName>";
            # the following doesn't work on Solaris Perl 5.6.1 due to Perl bug:
            # if ($doc =~ m{(.*?)</$tagName>}sg) {
            #     $val = $1;
            if ($doc =~ m{$close}sg) {
                $val = substr($doc, $pos, pos($doc)-$pos-length($close));
            } else {
                pos($doc) = $pos;
                next unless $tag eq 'meta'; # META tags don't need to be closed
            }
        }
        my $table = $tagTablePtr;
        if ($tag eq 'meta') {
            # parse HTML META element
            undef $tag;
            # tag name is in NAME or HTTP-EQUIV attribute
            if ($attrs =~ /name=['"]?([\w:.-]+)/si) {
                $tagName = $1;
            } elsif ($attrs =~ /http-equiv=['"]?([\w:.-]+)/si) {
                $tagName = "HTTP-equiv.$1";
            } else {
                next;   # no name
            }
            $tag = lc($tagName);
            # tag value is in CONTENT attribute
            $val = $2 if $attrs =~ /content=(['"])(.*?)\1/si;
            next unless $tag and defined $val;
            # isolate group name (separator is '.' in HTML, but ':' in ref 2)
            if ($tag =~ /^([\w-]+)[:.]([\w-]+)/) {
                ($grp, $tag) = ($1, $2);
                my $tagInfo = $exifTool->GetTagInfo($tagTablePtr, $grp);
                if ($tagInfo and $$tagInfo{SubDirectory}) {
                    $table = GetTagTable($tagInfo->{SubDirectory}->{TagTable});
                } else {
                    $tag = "$grp.$tag";
                }
            }
        } elsif ($tag eq 'xml') {
            $exifTool->VPrint(0, "Parsing XML\n");
            # parse XML tags (quick-and-dirty)
            my $xml = $val;
            while ($xml =~ /<([\w-]+):([\w-]+)(\s.*?)?>([^<]*?)<\/\1:\2>/g) {
                ($grp, $tag, $val) = ($1, $2, $4);
                my $tagInfo = $exifTool->GetTagInfo($tagTablePtr, $grp);
                next unless $tagInfo and $$tagInfo{SubDirectory};
                $table = GetTagTable($tagInfo->{SubDirectory}->{TagTable});
                unless ($$table{$tag}) {
                    my $name = ucfirst $tag;
                    $name =~ s/_x([0-9a-f]{4})_/chr(hex($1))/gie; # convert hex codes
                    $name =~ s/\s(.)/\U$1/g;     # capitalize all words in tag name
                    $name =~ tr/-_a-zA-Z0-9//dc; # remove illegal characters (also hex code wide chars)
                    Image::ExifTool::AddTagToTable($table, $tag, { Name => $name });
                    $exifTool->VPrint(0, "  [adding $tag '$name']\n");
                }
                $val = $exifTool->Decode($val, $$exifTool{HTMLCharset}) if $$exifTool{HTMLCharset};
                $exifTool->HandleTag($table, $tag, UnescapeXML($val));
            }
            next;
        } else {
            # the only other element we process is TITLE
            next unless $tag eq 'title';
        }
        unless ($$table{$tag}) {
            my $name = $tagName;
            $name =~ s/\W+(\w)/\u$1/sg;
            my $info = { Name => $name, Groups => { 0 => 'HTML' } };
            $info->{Groups}->{1} = ($grp eq 'http-equiv' ? 'HTTP-equiv' : "HTML-$grp") if $grp;
            Image::ExifTool::AddTagToTable($table, $tag, $info);
            $exifTool->VPrint(0, "  [adding $tag '$tagName']\n");
        }
        # recode if necessary
        $val = $exifTool->Decode($val, $$exifTool{HTMLCharset}) if $$exifTool{HTMLCharset};
        $val =~ s{\s*$/\s*}{ }sg;   # replace linefeeds and indenting spaces
        $val = UnescapeHTML($val);  # unescape HTML character references
        $exifTool->HandleTag($table, $tag, $val);
    }
    return 1;
}

1;  # end

__END__

=head1 NAME

Image::ExifTool::HTML - Read HTML meta information

=head1 SYNOPSIS

This module is used by Image::ExifTool

=head1 DESCRIPTION

This module contains routines required by Image::ExifTool to extract
meta information from HTML documents.

=head1 AUTHOR

Copyright 2003-2011, Phil Harvey (phil at owl.phy.queensu.ca)

This library is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.

=head1 REFERENCES

=over 4

=item L<http://www.w3.org/TR/html4/>

=item L<http://www.daisy.org/publications/specifications/daisy_202.html>

=item L<http://vancouver-webpages.com/META/metatags.detail.html>

=item L<http://www.html-reference.com/META.htm>

=back

=head1 SEE ALSO

L<Image::ExifTool::TagNames/HTML Tags>,
L<Image::ExifTool(3pm)|Image::ExifTool>

=cut