1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* @file |
5
|
|
|
* This file is part of the PdfParser library. |
6
|
|
|
* |
7
|
|
|
* @author Sébastien MALOT <[email protected]> |
8
|
|
|
* @date 2017-01-03 |
9
|
|
|
* |
10
|
|
|
* @license LGPLv3 |
11
|
|
|
* @url <https://github.com/smalot/pdfparser> |
12
|
|
|
* |
13
|
|
|
* PdfParser is a pdf library written in PHP, extraction oriented. |
14
|
|
|
* Copyright (C) 2017 - Sébastien MALOT <[email protected]> |
15
|
|
|
* |
16
|
|
|
* This program is free software: you can redistribute it and/or modify |
17
|
|
|
* it under the terms of the GNU Lesser General Public License as published by |
18
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
19
|
|
|
* (at your option) any later version. |
20
|
|
|
* |
21
|
|
|
* This program is distributed in the hope that it will be useful, |
22
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
23
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
24
|
|
|
* GNU Lesser General Public License for more details. |
25
|
|
|
* |
26
|
|
|
* You should have received a copy of the GNU Lesser General Public License |
27
|
|
|
* along with this program. |
28
|
|
|
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>. |
29
|
|
|
*/ |
30
|
|
|
|
31
|
|
|
namespace Smalot\PdfParser; |
32
|
|
|
|
33
|
|
|
/** |
34
|
|
|
* Class Font |
35
|
|
|
*/ |
36
|
|
|
class Font extends PDFObject |
37
|
|
|
{ |
38
|
|
|
const MISSING = '?'; |
39
|
|
|
|
40
|
|
|
/** |
41
|
|
|
* @var array |
42
|
|
|
*/ |
43
|
|
|
protected $table = null; |
44
|
|
|
|
45
|
|
|
/** |
46
|
|
|
* @var array |
47
|
|
|
*/ |
48
|
|
|
protected $tableSizes = null; |
49
|
|
|
|
50
|
|
|
public function init() |
51
|
|
|
{ |
52
|
|
|
// Load translate table. |
53
|
|
|
$this->loadTranslateTable(); |
54
|
|
|
} |
55
|
|
|
|
56
|
|
|
/** |
57
|
|
|
* @return string |
58
|
|
|
*/ |
59
|
|
|
public function getName() |
60
|
|
|
{ |
61
|
|
|
return $this->has('BaseFont') ? (string) $this->get('BaseFont') : '[Unknown]'; |
62
|
|
|
} |
63
|
|
|
|
64
|
|
|
/** |
65
|
|
|
* @return string |
66
|
|
|
*/ |
67
|
|
|
public function getType() |
68
|
|
|
{ |
69
|
|
|
return (string) $this->header->get('Subtype'); |
70
|
|
|
} |
71
|
|
|
|
72
|
|
|
/** |
73
|
|
|
* @return array |
74
|
|
|
*/ |
75
|
|
|
public function getDetails($deep = true) |
76
|
|
|
{ |
77
|
|
|
$details = []; |
78
|
|
|
|
79
|
|
|
$details['Name'] = $this->getName(); |
80
|
|
|
$details['Type'] = $this->getType(); |
81
|
|
|
$details['Encoding'] = ($this->has('Encoding') ? (string) $this->get('Encoding') : 'Ansi'); |
82
|
|
|
|
83
|
|
|
$details += parent::getDetails($deep); |
84
|
|
|
|
85
|
|
|
return $details; |
86
|
|
|
} |
87
|
|
|
|
88
|
|
|
/** |
89
|
|
|
* @param string $char |
90
|
|
|
* @param bool $use_default |
91
|
|
|
* |
92
|
|
|
* @return string|bool |
93
|
|
|
*/ |
94
|
|
|
public function translateChar($char, $use_default = true) |
95
|
|
|
{ |
96
|
|
|
$dec = hexdec(bin2hex($char)); |
97
|
|
|
|
98
|
|
|
if (\array_key_exists($dec, $this->table)) { |
99
|
|
|
return $this->table[$dec]; |
100
|
|
|
} |
101
|
|
|
|
102
|
|
|
return $use_default ? self::MISSING : $char; |
103
|
|
|
} |
104
|
|
|
|
105
|
|
|
/** |
106
|
|
|
* @param int $code |
107
|
|
|
* |
108
|
|
|
* @return string |
109
|
|
|
*/ |
110
|
|
|
public static function uchr($code) |
111
|
|
|
{ |
112
|
|
|
return html_entity_decode('&#'.((int) $code).';', ENT_NOQUOTES, 'UTF-8'); |
113
|
|
|
} |
114
|
|
|
|
115
|
|
|
/** |
116
|
|
|
* @return array |
117
|
|
|
*/ |
118
|
|
|
public function loadTranslateTable() |
119
|
|
|
{ |
120
|
|
|
if (null !== $this->table) { |
121
|
|
|
return $this->table; |
122
|
|
|
} |
123
|
|
|
|
124
|
|
|
$this->table = []; |
125
|
|
|
$this->tableSizes = [ |
126
|
|
|
'from' => 1, |
127
|
|
|
'to' => 1, |
128
|
|
|
]; |
129
|
|
|
|
130
|
|
|
if ($this->has('ToUnicode')) { |
131
|
|
|
$content = $this->get('ToUnicode')->getContent(); |
132
|
|
|
$matches = []; |
133
|
|
|
|
134
|
|
|
// Support for multiple spacerange sections |
135
|
|
|
if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) { |
136
|
|
|
foreach ($matches['sections'] as $section) { |
137
|
|
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
138
|
|
|
|
139
|
|
|
preg_match_all($regexp, $section, $matches); |
140
|
|
|
|
141
|
|
|
$this->tableSizes = [ |
142
|
|
|
'from' => max(1, \strlen(current($matches['from'])) / 2), |
143
|
|
|
'to' => max(1, \strlen(current($matches['to'])) / 2), |
144
|
|
|
]; |
145
|
|
|
|
146
|
|
|
break; |
147
|
|
|
} |
148
|
|
|
} |
149
|
|
|
|
150
|
|
|
// Support for multiple bfchar sections |
151
|
|
|
if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) { |
152
|
|
|
foreach ($matches['sections'] as $section) { |
153
|
|
|
$regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
154
|
|
|
|
155
|
|
|
preg_match_all($regexp, $section, $matches); |
156
|
|
|
|
157
|
|
|
$this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2); |
158
|
|
|
|
159
|
|
|
foreach ($matches['from'] as $key => $from) { |
160
|
|
|
$parts = preg_split( |
161
|
|
|
'/([0-9A-F]{4})/i', |
162
|
|
|
$matches['to'][$key], |
163
|
|
|
0, |
164
|
|
|
PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
165
|
|
|
); |
166
|
|
|
$text = ''; |
167
|
|
|
foreach ($parts as $part) { |
168
|
|
|
$text .= self::uchr(hexdec($part)); |
|
|
|
|
169
|
|
|
} |
170
|
|
|
$this->table[hexdec($from)] = $text; |
171
|
|
|
} |
172
|
|
|
} |
173
|
|
|
} |
174
|
|
|
|
175
|
|
|
// Support for multiple bfrange sections |
176
|
|
|
if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) { |
177
|
|
|
foreach ($matches['sections'] as $section) { |
178
|
|
|
// Support for : <srcCode1> <srcCode2> <dstString> |
179
|
|
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *<(?P<offset>[0-9A-F]+)>[ \r\n]+/is'; |
180
|
|
|
|
181
|
|
|
preg_match_all($regexp, $section, $matches); |
182
|
|
|
|
183
|
|
|
foreach ($matches['from'] as $key => $from) { |
184
|
|
|
$char_from = hexdec($from); |
185
|
|
|
$char_to = hexdec($matches['to'][$key]); |
186
|
|
|
$offset = hexdec($matches['offset'][$key]); |
187
|
|
|
|
188
|
|
|
for ($char = $char_from; $char <= $char_to; ++$char) { |
189
|
|
|
$this->table[$char] = self::uchr($char - $char_from + $offset); |
190
|
|
|
} |
191
|
|
|
} |
192
|
|
|
|
193
|
|
|
// Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>] |
194
|
|
|
// Some PDF file has 2-byte Unicode values on new lines > added \r\n |
195
|
|
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *\[(?P<strings>[\r\n<>0-9A-F ]+)\][ \r\n]+/is'; |
196
|
|
|
|
197
|
|
|
preg_match_all($regexp, $section, $matches); |
198
|
|
|
|
199
|
|
|
foreach ($matches['from'] as $key => $from) { |
200
|
|
|
$char_from = hexdec($from); |
201
|
|
|
$strings = []; |
202
|
|
|
|
203
|
|
|
preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $matches['strings'][$key], $strings); |
204
|
|
|
|
205
|
|
|
foreach ($strings['string'] as $position => $string) { |
206
|
|
|
$parts = preg_split( |
207
|
|
|
'/([0-9A-F]{4})/i', |
208
|
|
|
$string, |
209
|
|
|
0, |
210
|
|
|
PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
211
|
|
|
); |
212
|
|
|
$text = ''; |
213
|
|
|
foreach ($parts as $part) { |
214
|
|
|
$text .= self::uchr(hexdec($part)); |
215
|
|
|
} |
216
|
|
|
$this->table[$char_from + $position] = $text; |
217
|
|
|
} |
218
|
|
|
} |
219
|
|
|
} |
220
|
|
|
} |
221
|
|
|
} |
222
|
|
|
|
223
|
|
|
return $this->table; |
224
|
|
|
} |
225
|
|
|
|
226
|
|
|
/** |
227
|
|
|
* @param array $table |
228
|
|
|
*/ |
229
|
|
|
public function setTable($table) |
230
|
|
|
{ |
231
|
|
|
$this->table = $table; |
232
|
|
|
} |
233
|
|
|
|
234
|
|
|
/** |
235
|
|
|
* @param string $hexa |
236
|
|
|
* @param bool $add_braces |
237
|
|
|
* |
238
|
|
|
* @return string |
239
|
|
|
*/ |
240
|
|
|
public static function decodeHexadecimal($hexa, $add_braces = false) |
241
|
|
|
{ |
242
|
|
|
// Special shortcut for XML content. |
243
|
|
|
if (false !== stripos($hexa, '<?xml')) { |
244
|
|
|
return $hexa; |
245
|
|
|
} |
246
|
|
|
|
247
|
|
|
$text = ''; |
248
|
|
|
$parts = preg_split('/(<[a-f0-9]+>)/si', $hexa, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
249
|
|
|
|
250
|
|
|
foreach ($parts as $part) { |
251
|
|
|
if (preg_match('/^<.*>$/', $part) && false === stripos($part, '<?xml')) { |
252
|
|
|
$part = trim($part, '<>'); |
253
|
|
|
if ($add_braces) { |
254
|
|
|
$text .= '('; |
255
|
|
|
} |
256
|
|
|
|
257
|
|
|
$part = pack('H*', $part); |
258
|
|
|
$text .= ($add_braces ? preg_replace('/\\\/s', '\\\\\\', $part) : $part); |
259
|
|
|
|
260
|
|
|
if ($add_braces) { |
261
|
|
|
$text .= ')'; |
262
|
|
|
} |
263
|
|
|
} else { |
264
|
|
|
$text .= $part; |
265
|
|
|
} |
266
|
|
|
} |
267
|
|
|
|
268
|
|
|
return $text; |
269
|
|
|
} |
270
|
|
|
|
271
|
|
|
/** |
272
|
|
|
* @param string $text |
273
|
|
|
* |
274
|
|
|
* @return string |
275
|
|
|
*/ |
276
|
|
|
public static function decodeOctal($text) |
277
|
|
|
{ |
278
|
|
|
$parts = preg_split('/(\\\\\d{3})/s', $text, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
279
|
|
|
$text = ''; |
280
|
|
|
|
281
|
|
|
foreach ($parts as $part) { |
282
|
|
|
if (preg_match('/^\\\\\d{3}$/', $part)) { |
283
|
|
|
$text .= \chr(octdec(trim($part, '\\'))); |
|
|
|
|
284
|
|
|
} else { |
285
|
|
|
$text .= $part; |
286
|
|
|
} |
287
|
|
|
} |
288
|
|
|
|
289
|
|
|
return $text; |
290
|
|
|
} |
291
|
|
|
|
292
|
|
|
/** |
293
|
|
|
* @param string $text |
294
|
|
|
* |
295
|
|
|
* @return string |
296
|
|
|
*/ |
297
|
|
|
public static function decodeEntities($text) |
298
|
|
|
{ |
299
|
|
|
$parts = preg_split('/(#\d{2})/s', $text, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
300
|
|
|
$text = ''; |
301
|
|
|
|
302
|
|
|
foreach ($parts as $part) { |
303
|
|
|
if (preg_match('/^#\d{2}$/', $part)) { |
304
|
|
|
$text .= \chr(hexdec(trim($part, '#'))); |
|
|
|
|
305
|
|
|
} else { |
306
|
|
|
$text .= $part; |
307
|
|
|
} |
308
|
|
|
} |
309
|
|
|
|
310
|
|
|
return $text; |
311
|
|
|
} |
312
|
|
|
|
313
|
|
|
/** |
314
|
|
|
* @param string $text |
315
|
|
|
* |
316
|
|
|
* @return string |
317
|
|
|
*/ |
318
|
|
|
public static function decodeUnicode($text) |
319
|
|
|
{ |
320
|
|
|
if (preg_match('/^\xFE\xFF/i', $text)) { |
321
|
|
|
// Strip U+FEFF byte order marker. |
322
|
|
|
$decode = substr($text, 2); |
323
|
|
|
$text = ''; |
324
|
|
|
$length = \strlen($decode); |
325
|
|
|
|
326
|
|
|
for ($i = 0; $i < $length; $i += 2) { |
327
|
|
|
$text .= self::uchr(hexdec(bin2hex(substr($decode, $i, 2)))); |
|
|
|
|
328
|
|
|
} |
329
|
|
|
} |
330
|
|
|
|
331
|
|
|
return $text; |
332
|
|
|
} |
333
|
|
|
|
334
|
|
|
/** |
335
|
|
|
* @return int |
336
|
|
|
*/ |
337
|
|
|
protected function getFontSpaceLimit() |
338
|
|
|
{ |
339
|
|
|
return -50; |
340
|
|
|
} |
341
|
|
|
|
342
|
|
|
/** |
343
|
|
|
* @param array $commands |
344
|
|
|
* |
345
|
|
|
* @return string |
346
|
|
|
*/ |
347
|
|
|
public function decodeText($commands) |
348
|
|
|
{ |
349
|
|
|
$text = ''; |
350
|
|
|
$word_position = 0; |
351
|
|
|
$words = array(); |
352
|
|
|
$font_space = $this->getFontSpaceLimit(); |
353
|
|
|
|
354
|
|
|
foreach ($commands as $command) { |
355
|
|
|
switch ($command[PDFObject::TYPE]) { |
356
|
|
|
case 'n': |
357
|
|
|
if ((float) (trim($command[PDFObject::COMMAND])) < $font_space) { |
358
|
|
|
$word_position = \count($words); |
359
|
|
|
} |
360
|
|
|
continue 2; |
361
|
|
|
|
362
|
|
|
case '<': |
363
|
|
|
// Decode hexadecimal. |
364
|
|
|
$text = self::decodeHexadecimal('<' . $command[PDFObject::COMMAND] . '>'); |
365
|
|
|
break; |
366
|
|
|
|
367
|
|
|
default: |
368
|
|
|
// Decode octal (if necessary). |
369
|
|
|
$text = self::decodeOctal($command[PDFObject::COMMAND]); |
370
|
|
|
} |
371
|
|
|
|
372
|
|
|
// replace escaped chars |
373
|
|
|
$text = stripcslashes($text); |
374
|
|
|
|
375
|
|
|
// add content to result string |
376
|
|
|
if (isset($words[$word_position])) { |
377
|
|
|
$words[$word_position] .= $text; |
378
|
|
|
} else { |
379
|
|
|
$words[$word_position] = $text; |
380
|
|
|
} |
381
|
|
|
} |
382
|
|
|
|
383
|
|
|
foreach ($words as &$word) { |
384
|
|
|
$word = $this->decodeContent($word); |
385
|
|
|
} |
386
|
|
|
|
387
|
|
|
return implode(' ', $words); |
388
|
|
|
} |
389
|
|
|
|
390
|
|
|
/** |
391
|
|
|
* @param string $text |
392
|
|
|
* @param bool $unicode |
393
|
|
|
* |
394
|
|
|
* @return string |
395
|
|
|
*/ |
396
|
|
|
public function decodeContent($text) |
397
|
|
|
{ |
398
|
|
|
if ($this->has('ToUnicode')) { |
399
|
|
|
$bytes = $this->tableSizes['from']; |
400
|
|
|
|
401
|
|
|
if ($bytes) { |
402
|
|
|
$result = ''; |
403
|
|
|
$length = \strlen($text); |
404
|
|
|
|
405
|
|
|
for ($i = 0; $i < $length; $i += $bytes) { |
406
|
|
|
$char = substr($text, $i, $bytes); |
407
|
|
|
|
408
|
|
|
if (false !== ($decoded = $this->translateChar($char, false))) { |
409
|
|
|
$char = $decoded; |
410
|
|
|
} elseif ($this->has('DescendantFonts')) { |
411
|
|
|
if ($this->get('DescendantFonts') instanceof PDFObject) { |
412
|
|
|
$fonts = $this->get('DescendantFonts')->getHeader()->getElements(); |
|
|
|
|
413
|
|
|
} else { |
414
|
|
|
$fonts = $this->get('DescendantFonts')->getContent(); |
415
|
|
|
} |
416
|
|
|
$decoded = false; |
417
|
|
|
|
418
|
|
|
foreach ($fonts as $font) { |
419
|
|
|
if ($font instanceof self) { |
420
|
|
|
if (false !== ($decoded = $font->translateChar($char, false))) { |
421
|
|
|
$decoded = mb_convert_encoding($decoded, 'UTF-8', 'Windows-1252'); |
|
|
|
|
422
|
|
|
break; |
423
|
|
|
} |
424
|
|
|
} |
425
|
|
|
} |
426
|
|
|
|
427
|
|
|
if (false !== $decoded) { |
428
|
|
|
$char = $decoded; |
429
|
|
|
} else { |
430
|
|
|
$char = mb_convert_encoding($char, 'UTF-8', 'Windows-1252'); |
431
|
|
|
} |
432
|
|
|
} else { |
433
|
|
|
$char = self::MISSING; |
434
|
|
|
} |
435
|
|
|
|
436
|
|
|
$result .= $char; |
437
|
|
|
} |
438
|
|
|
|
439
|
|
|
$text = $result; |
440
|
|
|
} |
441
|
|
|
} elseif ($this->has('Encoding') && $this->get('Encoding') instanceof Encoding) { |
|
|
|
|
442
|
|
|
/** @var Encoding $encoding */ |
443
|
|
|
$encoding = $this->get('Encoding'); |
444
|
|
|
$unicode = mb_check_encoding($text, "UTF-8"); |
445
|
|
|
$result = ''; |
446
|
|
|
if ($unicode) { |
447
|
|
|
$chars = preg_split( |
448
|
|
|
'//s' . ($unicode ? 'u' : ''), |
449
|
|
|
$text, |
450
|
|
|
-1, |
451
|
|
|
PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY |
452
|
|
|
); |
453
|
|
|
|
454
|
|
|
foreach ($chars as $char) { |
455
|
|
|
$dec_av = hexdec(bin2hex($char)); |
456
|
|
|
$dec_ap = $encoding->translateChar($dec_av); |
457
|
|
|
$result .= self::uchr($dec_ap); |
458
|
|
|
} |
459
|
|
|
} else { |
460
|
|
|
$length = strlen($text); |
461
|
|
|
|
462
|
|
|
for ($i = 0; $i < $length; $i++) { |
463
|
|
|
$dec_av = hexdec(bin2hex($text[$i])); |
464
|
|
|
$dec_ap = $encoding->translateChar($dec_av); |
465
|
|
|
$result .= self::uchr($dec_ap); |
466
|
|
|
} |
467
|
|
|
|
468
|
|
|
} |
469
|
|
|
$text = $result; |
470
|
|
|
} elseif ($this->get('Encoding') instanceof Element && |
471
|
|
|
$this->get('Encoding')->equals('MacRomanEncoding')) { |
472
|
|
|
$text = mb_convert_encoding($text, 'UTF-8', 'Mac'); |
473
|
|
|
} else { |
474
|
|
|
$text = mb_convert_encoding($text, 'UTF-8', 'Windows-1252'); |
475
|
|
|
} |
476
|
|
|
|
477
|
|
|
return $text; |
478
|
|
|
} |
479
|
|
|
} |
480
|
|
|
|