|
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
|
|
|
use Smalot\PdfParser\Encoding\WinAnsiEncoding; |
|
34
|
|
|
use Smalot\PdfParser\Exception\EncodingNotFoundException; |
|
35
|
|
|
|
|
36
|
|
|
/** |
|
37
|
|
|
* Class Font |
|
38
|
|
|
*/ |
|
39
|
|
|
class Font extends PDFObject |
|
40
|
|
|
{ |
|
41
|
|
|
const MISSING = '?'; |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* @var array |
|
45
|
|
|
*/ |
|
46
|
|
|
protected $table = null; |
|
47
|
|
|
|
|
48
|
|
|
/** |
|
49
|
|
|
* @var array |
|
50
|
|
|
*/ |
|
51
|
|
|
protected $tableSizes = null; |
|
52
|
|
|
|
|
53
|
|
|
/** |
|
54
|
|
|
* Caches results from uchr. |
|
55
|
|
|
* |
|
56
|
|
|
* @var array |
|
57
|
|
|
*/ |
|
58
|
|
|
private static $uchrCache = []; |
|
59
|
|
|
|
|
60
|
38 |
|
public function init() |
|
61
|
|
|
{ |
|
62
|
|
|
// Load translate table. |
|
63
|
38 |
|
$this->loadTranslateTable(); |
|
64
|
38 |
|
} |
|
65
|
|
|
|
|
66
|
2 |
|
public function getName(): string |
|
67
|
|
|
{ |
|
68
|
2 |
|
return $this->has('BaseFont') ? (string) $this->get('BaseFont') : '[Unknown]'; |
|
69
|
|
|
} |
|
70
|
|
|
|
|
71
|
2 |
|
public function getType(): string |
|
72
|
|
|
{ |
|
73
|
2 |
|
return (string) $this->header->get('Subtype'); |
|
74
|
|
|
} |
|
75
|
|
|
|
|
76
|
1 |
|
public function getDetails(bool $deep = true): array |
|
77
|
|
|
{ |
|
78
|
1 |
|
$details = []; |
|
79
|
|
|
|
|
80
|
1 |
|
$details['Name'] = $this->getName(); |
|
81
|
1 |
|
$details['Type'] = $this->getType(); |
|
82
|
1 |
|
$details['Encoding'] = ($this->has('Encoding') ? (string) $this->get('Encoding') : 'Ansi'); |
|
83
|
|
|
|
|
84
|
1 |
|
$details += parent::getDetails($deep); |
|
85
|
|
|
|
|
86
|
1 |
|
return $details; |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
|
|
/** |
|
90
|
|
|
* @return string|bool |
|
91
|
|
|
*/ |
|
92
|
22 |
|
public function translateChar(string $char, bool $use_default = true) |
|
93
|
|
|
{ |
|
94
|
22 |
|
$dec = hexdec(bin2hex($char)); |
|
95
|
|
|
|
|
96
|
22 |
|
if (\array_key_exists($dec, $this->table)) { |
|
97
|
19 |
|
return $this->table[$dec]; |
|
98
|
|
|
} |
|
99
|
|
|
|
|
100
|
|
|
// fallback for decoding single-byte ANSI characters that are not in the lookup table |
|
101
|
6 |
|
$fallbackDecoded = $char; |
|
102
|
|
|
if ( |
|
103
|
6 |
|
\strlen($char) < 2 |
|
104
|
6 |
|
&& $this->has('Encoding') |
|
105
|
6 |
|
&& $this->get('Encoding') instanceof Encoding |
|
|
|
|
|
|
106
|
|
|
) { |
|
107
|
|
|
try { |
|
108
|
2 |
|
if (WinAnsiEncoding::class === $this->get('Encoding')->__toString()) { |
|
109
|
1 |
|
$fallbackDecoded = self::uchr($dec); |
|
110
|
|
|
} |
|
111
|
1 |
|
} catch (EncodingNotFoundException $e) { |
|
112
|
|
|
// Encoding->getEncodingClass() throws EncodingNotFoundException when BaseEncoding doesn't exists |
|
113
|
|
|
// See table 5.11 on PDF 1.5 specs for more info |
|
114
|
|
|
} |
|
115
|
|
|
} |
|
116
|
|
|
|
|
117
|
6 |
|
return $use_default ? self::MISSING : $fallbackDecoded; |
|
118
|
|
|
} |
|
119
|
|
|
|
|
120
|
|
|
/** |
|
121
|
|
|
* Convert unicode character code to "utf-8" encoded string. |
|
122
|
|
|
*/ |
|
123
|
36 |
|
public static function uchr(int $code): string |
|
124
|
|
|
{ |
|
125
|
36 |
|
if (!isset(self::$uchrCache[$code])) { |
|
126
|
|
|
// html_entity_decode() will not work with UTF-16 or UTF-32 char entities, |
|
127
|
|
|
// therefore, we use mb_convert_encoding() instead |
|
128
|
13 |
|
self::$uchrCache[$code] = mb_convert_encoding("&#{$code};", 'UTF-8', 'HTML-ENTITIES'); |
|
129
|
|
|
} |
|
130
|
|
|
|
|
131
|
36 |
|
return self::$uchrCache[$code]; |
|
132
|
|
|
} |
|
133
|
|
|
|
|
134
|
|
|
/** |
|
135
|
|
|
* Init internal chars translation table by ToUnicode CMap. |
|
136
|
|
|
*/ |
|
137
|
38 |
|
public function loadTranslateTable(): array |
|
138
|
|
|
{ |
|
139
|
38 |
|
if (null !== $this->table) { |
|
140
|
1 |
|
return $this->table; |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
38 |
|
$this->table = []; |
|
144
|
38 |
|
$this->tableSizes = [ |
|
145
|
|
|
'from' => 1, |
|
146
|
|
|
'to' => 1, |
|
147
|
|
|
]; |
|
148
|
|
|
|
|
149
|
38 |
|
if ($this->has('ToUnicode')) { |
|
150
|
31 |
|
$content = $this->get('ToUnicode')->getContent(); |
|
151
|
31 |
|
$matches = []; |
|
152
|
|
|
|
|
153
|
|
|
// Support for multiple spacerange sections |
|
154
|
31 |
|
if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) { |
|
155
|
31 |
|
foreach ($matches['sections'] as $section) { |
|
156
|
31 |
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
157
|
|
|
|
|
158
|
31 |
|
preg_match_all($regexp, $section, $matches); |
|
159
|
|
|
|
|
160
|
31 |
|
$this->tableSizes = [ |
|
161
|
31 |
|
'from' => max(1, \strlen(current($matches['from'])) / 2), |
|
162
|
31 |
|
'to' => max(1, \strlen(current($matches['to'])) / 2), |
|
163
|
|
|
]; |
|
164
|
|
|
|
|
165
|
31 |
|
break; |
|
166
|
|
|
} |
|
167
|
|
|
} |
|
168
|
|
|
|
|
169
|
|
|
// Support for multiple bfchar sections |
|
170
|
31 |
|
if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) { |
|
171
|
13 |
|
foreach ($matches['sections'] as $section) { |
|
172
|
13 |
|
$regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
173
|
|
|
|
|
174
|
13 |
|
preg_match_all($regexp, $section, $matches); |
|
175
|
|
|
|
|
176
|
13 |
|
$this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2); |
|
177
|
|
|
|
|
178
|
13 |
|
foreach ($matches['from'] as $key => $from) { |
|
179
|
13 |
|
$parts = preg_split( |
|
180
|
13 |
|
'/([0-9A-F]{4})/i', |
|
181
|
13 |
|
$matches['to'][$key], |
|
182
|
13 |
|
0, |
|
183
|
13 |
|
\PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE |
|
184
|
|
|
); |
|
185
|
13 |
|
$text = ''; |
|
186
|
13 |
|
foreach ($parts as $part) { |
|
187
|
13 |
|
$text .= self::uchr(hexdec($part)); |
|
|
|
|
|
|
188
|
|
|
} |
|
189
|
13 |
|
$this->table[hexdec($from)] = $text; |
|
190
|
|
|
} |
|
191
|
|
|
} |
|
192
|
|
|
} |
|
193
|
|
|
|
|
194
|
|
|
// Support for multiple bfrange sections |
|
195
|
31 |
|
if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) { |
|
196
|
24 |
|
foreach ($matches['sections'] as $section) { |
|
197
|
|
|
// Support for : <srcCode1> <srcCode2> <dstString> |
|
198
|
24 |
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *<(?P<offset>[0-9A-F]+)>[ \r\n]+/is'; |
|
199
|
|
|
|
|
200
|
24 |
|
preg_match_all($regexp, $section, $matches); |
|
201
|
|
|
|
|
202
|
24 |
|
foreach ($matches['from'] as $key => $from) { |
|
203
|
24 |
|
$char_from = hexdec($from); |
|
204
|
24 |
|
$char_to = hexdec($matches['to'][$key]); |
|
205
|
24 |
|
$offset = hexdec($matches['offset'][$key]); |
|
206
|
|
|
|
|
207
|
24 |
|
for ($char = $char_from; $char <= $char_to; ++$char) { |
|
208
|
24 |
|
$this->table[$char] = self::uchr($char - $char_from + $offset); |
|
209
|
|
|
} |
|
210
|
|
|
} |
|
211
|
|
|
|
|
212
|
|
|
// Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>] |
|
213
|
|
|
// Some PDF file has 2-byte Unicode values on new lines > added \r\n |
|
214
|
24 |
|
$regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *\[(?P<strings>[\r\n<>0-9A-F ]+)\][ \r\n]+/is'; |
|
215
|
|
|
|
|
216
|
24 |
|
preg_match_all($regexp, $section, $matches); |
|
217
|
|
|
|
|
218
|
24 |
|
foreach ($matches['from'] as $key => $from) { |
|
219
|
1 |
|
$char_from = hexdec($from); |
|
220
|
1 |
|
$strings = []; |
|
221
|
|
|
|
|
222
|
1 |
|
preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $matches['strings'][$key], $strings); |
|
223
|
|
|
|
|
224
|
1 |
|
foreach ($strings['string'] as $position => $string) { |
|
225
|
1 |
|
$parts = preg_split( |
|
226
|
1 |
|
'/([0-9A-F]{4})/i', |
|
227
|
|
|
$string, |
|
228
|
1 |
|
0, |
|
229
|
1 |
|
\PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE |
|
230
|
|
|
); |
|
231
|
1 |
|
$text = ''; |
|
232
|
1 |
|
foreach ($parts as $part) { |
|
233
|
1 |
|
$text .= self::uchr(hexdec($part)); |
|
234
|
|
|
} |
|
235
|
1 |
|
$this->table[$char_from + $position] = $text; |
|
236
|
|
|
} |
|
237
|
|
|
} |
|
238
|
|
|
} |
|
239
|
|
|
} |
|
240
|
|
|
} |
|
241
|
|
|
|
|
242
|
38 |
|
return $this->table; |
|
243
|
|
|
} |
|
244
|
|
|
|
|
245
|
|
|
/** |
|
246
|
|
|
* Set custom char translation table where: |
|
247
|
|
|
* - key - integer character code; |
|
248
|
|
|
* - value - "utf-8" encoded value; |
|
249
|
|
|
* |
|
250
|
|
|
* @return void |
|
251
|
|
|
*/ |
|
252
|
1 |
|
public function setTable(array $table) |
|
253
|
|
|
{ |
|
254
|
1 |
|
$this->table = $table; |
|
255
|
1 |
|
} |
|
256
|
|
|
|
|
257
|
|
|
/** |
|
258
|
|
|
* Decode hexadecimal encoded string. If $add_braces is true result value would be wrapped by parentheses. |
|
259
|
|
|
*/ |
|
260
|
41 |
|
public static function decodeHexadecimal(string $hexa, bool $add_braces = false): string |
|
261
|
|
|
{ |
|
262
|
|
|
// Special shortcut for XML content. |
|
263
|
41 |
|
if (false !== stripos($hexa, '<?xml')) { |
|
264
|
2 |
|
return $hexa; |
|
265
|
|
|
} |
|
266
|
|
|
|
|
267
|
41 |
|
$text = ''; |
|
268
|
41 |
|
$parts = preg_split('/(<[a-f0-9]+>)/si', $hexa, -1, \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE); |
|
269
|
|
|
|
|
270
|
41 |
|
foreach ($parts as $part) { |
|
271
|
41 |
|
if (preg_match('/^<.*>$/s', $part) && false === stripos($part, '<?xml')) { |
|
272
|
|
|
// strip line breaks |
|
273
|
13 |
|
$part = preg_replace("/[\r\n]/", '', $part); |
|
274
|
13 |
|
$part = trim($part, '<>'); |
|
275
|
13 |
|
if ($add_braces) { |
|
276
|
1 |
|
$text .= '('; |
|
277
|
|
|
} |
|
278
|
|
|
|
|
279
|
13 |
|
$part = pack('H*', $part); |
|
280
|
13 |
|
$text .= ($add_braces ? preg_replace('/\\\/s', '\\\\\\', $part) : $part); |
|
281
|
|
|
|
|
282
|
13 |
|
if ($add_braces) { |
|
283
|
13 |
|
$text .= ')'; |
|
284
|
|
|
} |
|
285
|
|
|
} else { |
|
286
|
41 |
|
$text .= $part; |
|
287
|
|
|
} |
|
288
|
|
|
} |
|
289
|
|
|
|
|
290
|
41 |
|
return $text; |
|
291
|
|
|
} |
|
292
|
|
|
|
|
293
|
|
|
/** |
|
294
|
|
|
* Decode string with octal-decoded chunks. |
|
295
|
|
|
*/ |
|
296
|
41 |
|
public static function decodeOctal(string $text): string |
|
297
|
|
|
{ |
|
298
|
41 |
|
$parts = preg_split('/(\\\\[0-7]{3})/s', $text, -1, \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE); |
|
299
|
41 |
|
$text = ''; |
|
300
|
|
|
|
|
301
|
41 |
|
foreach ($parts as $part) { |
|
302
|
41 |
|
if (preg_match('/^\\\\[0-7]{3}$/', $part)) { |
|
303
|
18 |
|
$text .= \chr(octdec(trim($part, '\\'))); |
|
|
|
|
|
|
304
|
|
|
} else { |
|
305
|
41 |
|
$text .= $part; |
|
306
|
|
|
} |
|
307
|
|
|
} |
|
308
|
|
|
|
|
309
|
41 |
|
return $text; |
|
310
|
|
|
} |
|
311
|
|
|
|
|
312
|
|
|
/** |
|
313
|
|
|
* Decode string with html entity encoded chars. |
|
314
|
|
|
*/ |
|
315
|
55 |
|
public static function decodeEntities(string $text): string |
|
316
|
|
|
{ |
|
317
|
55 |
|
$parts = preg_split('/(#\d{2})/s', $text, -1, \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE); |
|
318
|
55 |
|
$text = ''; |
|
319
|
|
|
|
|
320
|
55 |
|
foreach ($parts as $part) { |
|
321
|
55 |
|
if (preg_match('/^#\d{2}$/', $part)) { |
|
322
|
5 |
|
$text .= \chr(hexdec(trim($part, '#'))); |
|
|
|
|
|
|
323
|
|
|
} else { |
|
324
|
55 |
|
$text .= $part; |
|
325
|
|
|
} |
|
326
|
|
|
} |
|
327
|
|
|
|
|
328
|
55 |
|
return $text; |
|
329
|
|
|
} |
|
330
|
|
|
|
|
331
|
|
|
/** |
|
332
|
|
|
* Check if given string is Unicode text (by BOM); |
|
333
|
|
|
* If true - decode to "utf-8" encoded string. |
|
334
|
|
|
* Otherwise - return text as is. |
|
335
|
|
|
* |
|
336
|
|
|
* @todo Rename in next major release to make the name correspond to reality (for ex. decodeIfUnicode()) |
|
337
|
|
|
*/ |
|
338
|
41 |
|
public static function decodeUnicode(string $text): string |
|
339
|
|
|
{ |
|
340
|
41 |
|
if (preg_match('/^\xFE\xFF/i', $text)) { |
|
341
|
|
|
// Strip U+FEFF byte order marker. |
|
342
|
25 |
|
$decode = substr($text, 2); |
|
343
|
25 |
|
$text = ''; |
|
344
|
25 |
|
$length = \strlen($decode); |
|
345
|
|
|
|
|
346
|
25 |
|
for ($i = 0; $i < $length; $i += 2) { |
|
347
|
25 |
|
$text .= self::uchr(hexdec(bin2hex(substr($decode, $i, 2)))); |
|
|
|
|
|
|
348
|
|
|
} |
|
349
|
|
|
} |
|
350
|
|
|
|
|
351
|
41 |
|
return $text; |
|
352
|
|
|
} |
|
353
|
|
|
|
|
354
|
|
|
/** |
|
355
|
|
|
* @todo Deprecated, use $this->config->getFontSpaceLimit() instead. |
|
356
|
|
|
*/ |
|
357
|
20 |
|
protected function getFontSpaceLimit(): int |
|
358
|
|
|
{ |
|
359
|
20 |
|
return $this->config->getFontSpaceLimit(); |
|
360
|
|
|
} |
|
361
|
|
|
|
|
362
|
|
|
/** |
|
363
|
|
|
* Decode text by commands array. |
|
364
|
|
|
*/ |
|
365
|
20 |
|
public function decodeText(array $commands): string |
|
366
|
|
|
{ |
|
367
|
20 |
|
$word_position = 0; |
|
368
|
20 |
|
$words = []; |
|
369
|
20 |
|
$font_space = $this->getFontSpaceLimit(); |
|
370
|
|
|
|
|
371
|
20 |
|
foreach ($commands as $command) { |
|
372
|
20 |
|
switch ($command[PDFObject::TYPE]) { |
|
373
|
20 |
|
case 'n': |
|
374
|
16 |
|
if ((float) (trim($command[PDFObject::COMMAND])) < $font_space) { |
|
375
|
8 |
|
$word_position = \count($words); |
|
376
|
|
|
} |
|
377
|
16 |
|
continue 2; |
|
378
|
20 |
|
case '<': |
|
379
|
|
|
// Decode hexadecimal. |
|
380
|
11 |
|
$text = self::decodeHexadecimal('<'.$command[PDFObject::COMMAND].'>'); |
|
381
|
11 |
|
break; |
|
382
|
|
|
|
|
383
|
|
|
default: |
|
384
|
|
|
// Decode octal (if necessary). |
|
385
|
13 |
|
$text = self::decodeOctal($command[PDFObject::COMMAND]); |
|
386
|
|
|
} |
|
387
|
|
|
|
|
388
|
|
|
// replace escaped chars |
|
389
|
20 |
|
$text = str_replace( |
|
390
|
20 |
|
['\\\\', '\(', '\)', '\n', '\r', '\t', '\f', '\ '], |
|
391
|
20 |
|
['\\', '(', ')', "\n", "\r", "\t", "\f", ' '], |
|
392
|
|
|
$text |
|
393
|
|
|
); |
|
394
|
|
|
|
|
395
|
|
|
// add content to result string |
|
396
|
20 |
|
if (isset($words[$word_position])) { |
|
397
|
16 |
|
$words[$word_position] .= $text; |
|
398
|
|
|
} else { |
|
399
|
20 |
|
$words[$word_position] = $text; |
|
400
|
|
|
} |
|
401
|
|
|
} |
|
402
|
|
|
|
|
403
|
20 |
|
foreach ($words as &$word) { |
|
404
|
20 |
|
$word = $this->decodeContent($word); |
|
405
|
|
|
} |
|
406
|
|
|
|
|
407
|
20 |
|
return implode(' ', $words); |
|
408
|
|
|
} |
|
409
|
|
|
|
|
410
|
|
|
/** |
|
411
|
|
|
* @param bool $unicode This parameter is deprecated and might be removed in a future release |
|
412
|
|
|
*/ |
|
413
|
24 |
|
public function decodeContent(string $text, ?bool &$unicode = null): string |
|
414
|
|
|
{ |
|
415
|
24 |
|
if ($this->has('ToUnicode')) { |
|
416
|
19 |
|
$bytes = $this->tableSizes['from']; |
|
417
|
|
|
|
|
418
|
19 |
|
if ($bytes) { |
|
419
|
19 |
|
$result = ''; |
|
420
|
19 |
|
$length = \strlen($text); |
|
421
|
|
|
|
|
422
|
19 |
|
for ($i = 0; $i < $length; $i += $bytes) { |
|
423
|
19 |
|
$char = substr($text, $i, $bytes); |
|
424
|
|
|
|
|
425
|
19 |
|
if (false !== ($decoded = $this->translateChar($char, false))) { |
|
426
|
19 |
|
$char = $decoded; |
|
427
|
|
|
} elseif ($this->has('DescendantFonts')) { |
|
428
|
|
|
if ($this->get('DescendantFonts') instanceof PDFObject) { |
|
429
|
|
|
$fonts = $this->get('DescendantFonts')->getHeader()->getElements(); |
|
|
|
|
|
|
430
|
|
|
} else { |
|
431
|
|
|
$fonts = $this->get('DescendantFonts')->getContent(); |
|
432
|
|
|
} |
|
433
|
|
|
$decoded = false; |
|
434
|
|
|
|
|
435
|
|
|
foreach ($fonts as $font) { |
|
436
|
|
|
if ($font instanceof self) { |
|
437
|
|
|
if (false !== ($decoded = $font->translateChar($char, false))) { |
|
438
|
|
|
$decoded = mb_convert_encoding($decoded, 'UTF-8', 'Windows-1252'); |
|
|
|
|
|
|
439
|
|
|
break; |
|
440
|
|
|
} |
|
441
|
|
|
} |
|
442
|
|
|
} |
|
443
|
|
|
|
|
444
|
|
|
if (false !== $decoded) { |
|
445
|
|
|
$char = $decoded; |
|
446
|
|
|
} else { |
|
447
|
|
|
$char = mb_convert_encoding($char, 'UTF-8', 'Windows-1252'); |
|
448
|
|
|
} |
|
449
|
|
|
} else { |
|
450
|
|
|
$char = self::MISSING; |
|
451
|
|
|
} |
|
452
|
|
|
|
|
453
|
19 |
|
$result .= $char; |
|
454
|
|
|
} |
|
455
|
|
|
|
|
456
|
19 |
|
$text = $result; |
|
457
|
|
|
} |
|
458
|
16 |
|
} elseif ($this->has('Encoding') && $this->get('Encoding') instanceof Encoding) { |
|
|
|
|
|
|
459
|
|
|
/** @var Encoding $encoding */ |
|
460
|
3 |
|
$encoding = $this->get('Encoding'); |
|
461
|
3 |
|
$unicode = mb_check_encoding($text, 'UTF-8'); |
|
462
|
3 |
|
$result = ''; |
|
463
|
3 |
|
if ($unicode) { |
|
464
|
2 |
|
$chars = preg_split( |
|
465
|
2 |
|
'//s'.($unicode ? 'u' : ''), |
|
466
|
|
|
$text, |
|
467
|
2 |
|
-1, |
|
468
|
2 |
|
\PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY |
|
469
|
|
|
); |
|
470
|
|
|
|
|
471
|
2 |
|
foreach ($chars as $char) { |
|
472
|
2 |
|
$dec_av = hexdec(bin2hex($char)); |
|
473
|
2 |
|
$dec_ap = $encoding->translateChar($dec_av); |
|
474
|
2 |
|
$result .= self::uchr($dec_ap ?? $dec_av); |
|
475
|
|
|
} |
|
476
|
|
|
} else { |
|
477
|
3 |
|
$length = \strlen($text); |
|
478
|
|
|
|
|
479
|
3 |
|
for ($i = 0; $i < $length; ++$i) { |
|
480
|
3 |
|
$dec_av = hexdec(bin2hex($text[$i])); |
|
481
|
3 |
|
$dec_ap = $encoding->translateChar($dec_av); |
|
482
|
3 |
|
$result .= self::uchr($dec_ap ?? $dec_av); |
|
483
|
|
|
} |
|
484
|
|
|
} |
|
485
|
3 |
|
$text = $result; |
|
486
|
14 |
|
} elseif ($this->get('Encoding') instanceof Element && |
|
487
|
14 |
|
$this->get('Encoding')->equals('MacRomanEncoding')) { |
|
488
|
|
|
// mb_convert_encoding does not support MacRoman/macintosh, |
|
489
|
|
|
// so we use iconv() here |
|
490
|
1 |
|
$text = iconv('macintosh', 'UTF-8', $text); |
|
491
|
14 |
|
} elseif (!mb_check_encoding($text, 'UTF-8')) { |
|
492
|
|
|
// don't double-encode strings already in UTF-8 |
|
493
|
6 |
|
$text = mb_convert_encoding($text, 'UTF-8', 'Windows-1252'); |
|
494
|
|
|
} |
|
495
|
|
|
|
|
496
|
24 |
|
return $text; |
|
|
|
|
|
|
497
|
|
|
} |
|
498
|
|
|
} |
|
499
|
|
|
|
smalot /
pdfparser
Loading history...
