|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* @file |
|
5
|
|
|
* This file is part of the PdfParser library. |
|
6
|
|
|
* |
|
7
|
|
|
* @author Sébastien MALOT <[email protected]> |
|
8
|
|
|
* |
|
9
|
|
|
* @date 2017-01-03 |
|
10
|
|
|
* |
|
11
|
|
|
* @license LGPLv3 |
|
12
|
|
|
* |
|
13
|
|
|
* @url <https://github.com/smalot/pdfparser> |
|
14
|
|
|
* |
|
15
|
|
|
* PdfParser is a pdf library written in PHP, extraction oriented. |
|
16
|
|
|
* Copyright (C) 2017 - Sébastien MALOT <[email protected]> |
|
17
|
|
|
* |
|
18
|
|
|
* This program is free software: you can redistribute it and/or modify |
|
19
|
|
|
* it under the terms of the GNU Lesser General Public License as published by |
|
20
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
|
21
|
|
|
* (at your option) any later version. |
|
22
|
|
|
* |
|
23
|
|
|
* This program is distributed in the hope that it will be useful, |
|
24
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
25
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
26
|
|
|
* GNU Lesser General Public License for more details. |
|
27
|
|
|
* |
|
28
|
|
|
* You should have received a copy of the GNU Lesser General Public License |
|
29
|
|
|
* along with this program. |
|
30
|
|
|
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>. |
|
31
|
|
|
*/ |
|
32
|
|
|
|
|
33
|
|
|
namespace Smalot\PdfParser; |
|
34
|
|
|
|
|
35
|
|
|
use Smalot\PdfParser\XObject\Form; |
|
36
|
|
|
use Smalot\PdfParser\XObject\Image; |
|
37
|
|
|
|
|
38
|
|
|
/** |
|
39
|
|
|
* Class PDFObject |
|
40
|
|
|
*/ |
|
41
|
|
|
class PDFObject |
|
42
|
|
|
{ |
|
43
|
|
|
public const TYPE = 't'; |
|
44
|
|
|
|
|
45
|
|
|
public const OPERATOR = 'o'; |
|
46
|
|
|
|
|
47
|
|
|
public const COMMAND = 'c'; |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* The recursion stack. |
|
51
|
|
|
* |
|
52
|
|
|
* @var array |
|
53
|
|
|
*/ |
|
54
|
|
|
public static $recursionStack = []; |
|
55
|
|
|
|
|
56
|
|
|
/** |
|
57
|
|
|
* @var Document |
|
58
|
|
|
*/ |
|
59
|
|
|
protected $document; |
|
60
|
|
|
|
|
61
|
|
|
/** |
|
62
|
|
|
* @var Header |
|
63
|
|
|
*/ |
|
64
|
|
|
protected $header; |
|
65
|
|
|
|
|
66
|
|
|
/** |
|
67
|
|
|
* @var string |
|
68
|
|
|
*/ |
|
69
|
|
|
protected $content; |
|
70
|
|
|
|
|
71
|
|
|
/** |
|
72
|
|
|
* @var Config |
|
73
|
|
|
*/ |
|
74
|
|
|
protected $config; |
|
75
|
|
|
|
|
76
|
62 |
|
public function __construct( |
|
77
|
|
|
Document $document, |
|
78
|
|
|
Header $header = null, |
|
79
|
|
|
string $content = null, |
|
80
|
|
|
Config $config = null |
|
81
|
|
|
) { |
|
82
|
62 |
|
$this->document = $document; |
|
83
|
62 |
|
$this->header = $header ?? new Header(); |
|
84
|
62 |
|
$this->content = $content; |
|
85
|
62 |
|
$this->config = $config; |
|
86
|
62 |
|
} |
|
87
|
|
|
|
|
88
|
49 |
|
public function init() |
|
89
|
|
|
{ |
|
90
|
49 |
|
} |
|
91
|
|
|
|
|
92
|
3 |
|
public function getDocument(): Document |
|
93
|
|
|
{ |
|
94
|
3 |
|
return $this->document; |
|
95
|
|
|
} |
|
96
|
|
|
|
|
97
|
49 |
|
public function getHeader(): ?Header |
|
98
|
|
|
{ |
|
99
|
49 |
|
return $this->header; |
|
100
|
|
|
} |
|
101
|
|
|
|
|
102
|
3 |
|
public function getConfig(): ?Config |
|
103
|
|
|
{ |
|
104
|
3 |
|
return $this->config; |
|
105
|
|
|
} |
|
106
|
|
|
|
|
107
|
|
|
/** |
|
108
|
|
|
* @return Element|PDFObject|Header |
|
109
|
|
|
*/ |
|
110
|
50 |
|
public function get(string $name) |
|
111
|
|
|
{ |
|
112
|
50 |
|
return $this->header->get($name); |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
47 |
|
public function has(string $name): bool |
|
116
|
|
|
{ |
|
117
|
47 |
|
return $this->header->has($name); |
|
118
|
|
|
} |
|
119
|
|
|
|
|
120
|
3 |
|
public function getDetails(bool $deep = true): array |
|
121
|
|
|
{ |
|
122
|
3 |
|
return $this->header->getDetails($deep); |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
38 |
|
public function getContent(): ?string |
|
126
|
|
|
{ |
|
127
|
38 |
|
return $this->content; |
|
128
|
|
|
} |
|
129
|
|
|
|
|
130
|
32 |
|
public function cleanContent(string $content, string $char = 'X') |
|
131
|
|
|
{ |
|
132
|
32 |
|
$char = $char[0]; |
|
133
|
32 |
|
$content = str_replace(['\\\\', '\\)', '\\('], $char.$char, $content); |
|
134
|
|
|
|
|
135
|
|
|
// Remove image bloc with binary content |
|
136
|
32 |
|
preg_match_all('/\s(BI\s.*?(\sID\s).*?(\sEI))\s/s', $content, $matches, \PREG_OFFSET_CAPTURE); |
|
137
|
32 |
|
foreach ($matches[0] as $part) { |
|
138
|
|
|
$content = substr_replace($content, str_repeat($char, \strlen($part[0])), $part[1], \strlen($part[0])); |
|
139
|
|
|
} |
|
140
|
|
|
|
|
141
|
|
|
// Clean content in square brackets [.....] |
|
142
|
32 |
|
preg_match_all('/\[((\(.*?\)|[0-9\.\-\s]*)*)\]/s', $content, $matches, \PREG_OFFSET_CAPTURE); |
|
|
|
|
|
|
143
|
32 |
|
foreach ($matches[1] as $part) { |
|
144
|
22 |
|
$content = substr_replace($content, str_repeat($char, \strlen($part[0])), $part[1], \strlen($part[0])); |
|
145
|
|
|
} |
|
146
|
|
|
|
|
147
|
|
|
// Clean content in round brackets (.....) |
|
148
|
32 |
|
preg_match_all('/\((.*?)\)/s', $content, $matches, \PREG_OFFSET_CAPTURE); |
|
149
|
32 |
|
foreach ($matches[1] as $part) { |
|
150
|
21 |
|
$content = substr_replace($content, str_repeat($char, \strlen($part[0])), $part[1], \strlen($part[0])); |
|
151
|
|
|
} |
|
152
|
|
|
|
|
153
|
|
|
// Clean structure |
|
154
|
32 |
|
if ($parts = preg_split('/(<|>)/s', $content, -1, \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE)) { |
|
|
|
|
|
|
155
|
32 |
|
$content = ''; |
|
156
|
32 |
|
$level = 0; |
|
157
|
32 |
|
foreach ($parts as $part) { |
|
158
|
32 |
|
if ('<' == $part) { |
|
159
|
18 |
|
++$level; |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
32 |
|
$content .= (0 == $level ? $part : str_repeat($char, \strlen($part))); |
|
163
|
|
|
|
|
164
|
32 |
|
if ('>' == $part) { |
|
165
|
18 |
|
--$level; |
|
166
|
|
|
} |
|
167
|
|
|
} |
|
168
|
|
|
} |
|
169
|
|
|
|
|
170
|
|
|
// Clean BDC and EMC markup |
|
171
|
32 |
|
preg_match_all( |
|
172
|
32 |
|
'/(\/[A-Za-z0-9\_]*\s*'.preg_quote($char).'*BDC)/s', |
|
173
|
|
|
$content, |
|
174
|
|
|
$matches, |
|
175
|
32 |
|
\PREG_OFFSET_CAPTURE |
|
176
|
|
|
); |
|
177
|
32 |
|
foreach ($matches[1] as $part) { |
|
178
|
7 |
|
$content = substr_replace($content, str_repeat($char, \strlen($part[0])), $part[1], \strlen($part[0])); |
|
179
|
|
|
} |
|
180
|
|
|
|
|
181
|
32 |
|
preg_match_all('/\s(EMC)\s/s', $content, $matches, \PREG_OFFSET_CAPTURE); |
|
182
|
32 |
|
foreach ($matches[1] as $part) { |
|
183
|
11 |
|
$content = substr_replace($content, str_repeat($char, \strlen($part[0])), $part[1], \strlen($part[0])); |
|
184
|
|
|
} |
|
185
|
|
|
|
|
186
|
32 |
|
return $content; |
|
187
|
|
|
} |
|
188
|
|
|
|
|
189
|
31 |
|
public function getSectionsText(?string $content): array |
|
190
|
|
|
{ |
|
191
|
31 |
|
$sections = []; |
|
192
|
31 |
|
$content = ' '.$content.' '; |
|
193
|
31 |
|
$textCleaned = $this->cleanContent($content, '_'); |
|
194
|
|
|
|
|
195
|
|
|
// Extract text blocks. |
|
196
|
31 |
|
if (preg_match_all('/(\sQ)?\s+BT[\s|\(|\[]+(.*?)\s*ET(\sq)?/s', $textCleaned, $matches, \PREG_OFFSET_CAPTURE)) { |
|
|
|
|
|
|
197
|
29 |
|
foreach ($matches[2] as $pos => $part) { |
|
198
|
29 |
|
$text = $part[0]; |
|
199
|
29 |
|
if ('' === $text) { |
|
200
|
|
|
continue; |
|
201
|
|
|
} |
|
202
|
29 |
|
$offset = $part[1]; |
|
203
|
29 |
|
$section = substr($content, $offset, \strlen($text)); |
|
204
|
|
|
|
|
205
|
|
|
// Removes BDC and EMC markup. |
|
206
|
29 |
|
$section = preg_replace('/(\/[A-Za-z0-9]+\s*<<.*?)(>>\s*BDC)(.*?)(EMC\s+)/s', '${3}', $section.' '); |
|
207
|
|
|
|
|
208
|
|
|
// Add Q and q flags if detected around BT/ET. |
|
209
|
|
|
// @see: https://github.com/smalot/pdfparser/issues/387 |
|
210
|
29 |
|
$section = trim((!empty($matches[1][$pos][0]) ? "Q\n" : '').$section).(!empty($matches[3][$pos][0]) ? "\nq" : ''); |
|
211
|
|
|
|
|
212
|
29 |
|
$sections[] = $section; |
|
213
|
|
|
} |
|
214
|
|
|
} |
|
215
|
|
|
|
|
216
|
|
|
// Extract 'do' commands. |
|
217
|
31 |
|
if (preg_match_all('/(\/[A-Za-z0-9\.\-_]+\s+Do)\s/s', $textCleaned, $matches, \PREG_OFFSET_CAPTURE)) { |
|
218
|
4 |
|
foreach ($matches[1] as $part) { |
|
219
|
4 |
|
$text = $part[0]; |
|
220
|
4 |
|
$offset = $part[1]; |
|
221
|
4 |
|
$section = substr($content, $offset, \strlen($text)); |
|
222
|
|
|
|
|
223
|
4 |
|
$sections[] = $section; |
|
224
|
|
|
} |
|
225
|
|
|
} |
|
226
|
|
|
|
|
227
|
31 |
|
return $sections; |
|
228
|
|
|
} |
|
229
|
|
|
|
|
230
|
20 |
|
private function getDefaultFont(Page $page = null): Font |
|
231
|
|
|
{ |
|
232
|
20 |
|
$fonts = []; |
|
233
|
20 |
|
if (null !== $page) { |
|
234
|
19 |
|
$fonts = $page->getFonts(); |
|
235
|
|
|
} |
|
236
|
|
|
|
|
237
|
20 |
|
$firstFont = $this->document->getFirstFont(); |
|
238
|
20 |
|
if (null !== $firstFont) { |
|
239
|
18 |
|
$fonts[] = $firstFont; |
|
240
|
|
|
} |
|
241
|
|
|
|
|
242
|
20 |
|
if (\count($fonts) > 0) { |
|
243
|
18 |
|
return reset($fonts); |
|
244
|
|
|
} |
|
245
|
|
|
|
|
246
|
2 |
|
return new Font($this->document, null, null, $this->config); |
|
247
|
|
|
} |
|
248
|
|
|
|
|
249
|
|
|
private function getTJUsingFontFallback(Font $font, array $command, Page $page = null): string |
|
250
|
|
|
{ |
|
251
|
|
|
$orig_text = $font->decodeText($command); |
|
252
|
20 |
|
$text = $orig_text; |
|
253
|
|
|
|
|
254
|
20 |
|
// If we make this a Config option, we can add a check if it's |
|
255
|
20 |
|
// enabled here. |
|
256
|
20 |
|
if (null !== $page) { |
|
257
|
20 |
|
$font_ids = array_keys($page->getFonts()); |
|
258
|
|
|
|
|
259
|
20 |
|
// If the decoded text contains UTF-8 control characters |
|
260
|
20 |
|
// then the font page being used is probably the wrong one. |
|
261
|
|
|
// Loop through the rest of the fonts to see if we can get |
|
262
|
20 |
|
// a good decode. |
|
263
|
|
|
while (preg_match('/[\x00-\x1f\x7f]/u', $text)) { |
|
264
|
20 |
|
// If we're out of font IDs, then give up and use the |
|
265
|
18 |
|
// original string |
|
266
|
18 |
|
if (0 == \count($font_ids)) { |
|
267
|
18 |
|
return $orig_text; |
|
268
|
|
|
} |
|
269
|
18 |
|
|
|
270
|
18 |
|
// Try the next font ID |
|
271
|
18 |
|
$font = $page->getFont(array_shift($font_ids)); |
|
272
|
1 |
|
$text = $font->decodeText($command); |
|
273
|
1 |
|
} |
|
274
|
|
|
} |
|
275
|
1 |
|
|
|
276
|
|
|
return $text; |
|
277
|
|
|
} |
|
278
|
18 |
|
|
|
279
|
5 |
|
/** |
|
280
|
|
|
* @throws \Exception |
|
281
|
|
|
*/ |
|
282
|
18 |
|
public function getText(Page $page = null): string |
|
283
|
15 |
|
{ |
|
284
|
15 |
|
$result = ''; |
|
285
|
15 |
|
$sections = $this->getSectionsText($this->content); |
|
286
|
15 |
|
$current_font = $this->getDefaultFont($page); |
|
287
|
15 |
|
$clipped_font = $current_font; |
|
288
|
|
|
|
|
289
|
|
|
$current_position_td = ['x' => false, 'y' => false]; |
|
290
|
11 |
|
$current_position_tm = ['x' => false, 'y' => false]; |
|
291
|
15 |
|
|
|
292
|
15 |
|
self::$recursionStack[] = $this->getUniqueId(); |
|
293
|
|
|
|
|
294
|
12 |
|
foreach ($sections as $section) { |
|
295
|
|
|
$commands = $this->getCommandsText($section); |
|
296
|
15 |
|
$reverse_text = false; |
|
297
|
15 |
|
$text = ''; |
|
298
|
|
|
|
|
299
|
|
|
foreach ($commands as $command) { |
|
300
|
18 |
|
switch ($command[self::OPERATOR]) { |
|
301
|
3 |
|
case 'BMC': |
|
302
|
3 |
|
if ('ReversedChars' == $command[self::COMMAND]) { |
|
303
|
3 |
|
$reverse_text = true; |
|
304
|
3 |
|
} |
|
305
|
3 |
|
break; |
|
306
|
|
|
|
|
307
|
|
|
// set character spacing |
|
308
|
|
|
case 'Tc': |
|
309
|
3 |
|
break; |
|
310
|
|
|
|
|
311
|
18 |
|
// move text current point |
|
312
|
18 |
|
case 'Td': |
|
313
|
18 |
|
$args = preg_split('/\s/s', $command[self::COMMAND]); |
|
314
|
18 |
|
$y = array_pop($args); |
|
315
|
18 |
|
$x = array_pop($args); |
|
316
|
|
|
if (((float) $x <= 0) |
|
317
|
|
|
|| (false !== $current_position_td['y'] && (float) $y < (float) $current_position_td['y']) |
|
318
|
|
|
) { |
|
319
|
|
|
// vertical offset |
|
320
|
|
|
$text .= "\n"; |
|
321
|
18 |
|
} elseif (false !== $current_position_td['x'] && (float) $x > (float) |
|
322
|
16 |
|
$current_position_td['x'] |
|
323
|
|
|
) { |
|
324
|
|
|
$text .= $this->config->getHorizontalOffset(); |
|
325
|
18 |
|
} |
|
326
|
|
|
$current_position_td = ['x' => $x, 'y' => $y]; |
|
327
|
18 |
|
break; |
|
328
|
|
|
|
|
329
|
5 |
|
// move text current point and set leading |
|
330
|
5 |
|
case 'TD': |
|
331
|
|
|
$args = preg_split('/\s/s', $command[self::COMMAND]); |
|
332
|
18 |
|
$y = array_pop($args); |
|
333
|
|
|
$x = array_pop($args); |
|
334
|
6 |
|
if ((float) $y < 0) { |
|
335
|
6 |
|
$text .= "\n"; |
|
336
|
|
|
} elseif ((float) $x <= 0) { |
|
337
|
18 |
|
$text .= ' '; |
|
338
|
18 |
|
} |
|
339
|
13 |
|
break; |
|
340
|
|
|
|
|
341
|
17 |
|
case 'Tf': |
|
342
|
18 |
|
list($id) = preg_split('/\s/s', $command[self::COMMAND]); |
|
343
|
18 |
|
$id = trim($id, '/'); |
|
344
|
18 |
|
if (null !== $page) { |
|
345
|
|
|
$new_font = $page->getFont($id); |
|
346
|
|
|
// If an invalid font ID is given, do not update the font. |
|
347
|
15 |
|
// This should theoretically never happen, as the PDF spec states for the Tf operator: |
|
348
|
1 |
|
// "The specified font value shall match a resource name in the Font entry of the default resource dictionary" |
|
349
|
1 |
|
// (https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/PDF32000_2008.pdf, page 435) |
|
350
|
|
|
// But we want to make sure that malformed PDFs do not simply crash. |
|
351
|
15 |
|
if (null !== $new_font) { |
|
352
|
14 |
|
$current_font = $new_font; |
|
353
|
14 |
|
} |
|
354
|
14 |
|
} |
|
355
|
14 |
|
break; |
|
356
|
14 |
|
|
|
357
|
14 |
|
case 'Q': |
|
358
|
12 |
|
// Use clip: restore font. |
|
359
|
|
|
$current_font = $clipped_font; |
|
360
|
|
|
break; |
|
361
|
14 |
|
|
|
362
|
14 |
|
case 'q': |
|
363
|
14 |
|
// Use clip: save font. |
|
364
|
10 |
|
$clipped_font = $current_font; |
|
365
|
|
|
break; |
|
366
|
|
|
|
|
367
|
14 |
|
case "'": |
|
368
|
14 |
|
case 'Tj': |
|
369
|
|
|
$command[self::COMMAND] = [$command]; |
|
370
|
|
|
// no break |
|
371
|
12 |
|
case 'TJ': |
|
372
|
|
|
$text .= $this->getTJUsingFontFallback( |
|
373
|
|
|
$current_font, |
|
374
|
|
|
$command[self::COMMAND], |
|
375
|
12 |
|
$page |
|
376
|
4 |
|
); |
|
377
|
|
|
break; |
|
378
|
|
|
|
|
379
|
12 |
|
// set leading |
|
380
|
|
|
case 'TL': |
|
381
|
|
|
$text .= ' '; |
|
382
|
|
|
break; |
|
383
|
|
|
|
|
384
|
12 |
|
case 'Tm': |
|
385
|
4 |
|
$args = preg_split('/\s/s', $command[self::COMMAND]); |
|
386
|
4 |
|
$y = array_pop($args); |
|
387
|
|
|
$x = array_pop($args); |
|
388
|
11 |
|
if (false !== $current_position_tm['x']) { |
|
389
|
|
|
$delta = abs((float) $x - (float) $current_position_tm['x']); |
|
390
|
|
|
if ($delta > 10) { |
|
391
|
11 |
|
$text .= "\t"; |
|
392
|
4 |
|
} |
|
393
|
4 |
|
} |
|
394
|
4 |
|
if (false !== $current_position_tm['y']) { |
|
395
|
4 |
|
$delta = abs((float) $y - (float) $current_position_tm['y']); |
|
396
|
|
|
if ($delta > 10) { |
|
397
|
|
|
$text .= "\n"; |
|
398
|
4 |
|
} |
|
399
|
|
|
} |
|
400
|
4 |
|
$current_position_tm = ['x' => $x, 'y' => $y]; |
|
401
|
|
|
break; |
|
402
|
|
|
|
|
403
|
4 |
|
// set super/subscripting text rise |
|
404
|
|
|
case 'Ts': |
|
405
|
9 |
|
break; |
|
406
|
8 |
|
|
|
407
|
2 |
|
// set word spacing |
|
408
|
|
|
case 'Tw': |
|
409
|
8 |
|
break; |
|
410
|
|
|
|
|
411
|
|
|
// set horizontal scaling |
|
412
|
8 |
|
case 'Tz': |
|
413
|
|
|
$text .= "\n"; |
|
414
|
|
|
break; |
|
415
|
8 |
|
|
|
416
|
3 |
|
// move to start of next line |
|
417
|
|
|
case 'T*': |
|
418
|
8 |
|
$text .= "\n"; |
|
419
|
3 |
|
break; |
|
420
|
|
|
|
|
421
|
7 |
|
case 'Da': |
|
422
|
|
|
break; |
|
423
|
|
|
|
|
424
|
7 |
|
case 'Do': |
|
425
|
7 |
|
if (null !== $page) { |
|
426
|
|
|
$args = preg_split('/\s/s', $command[self::COMMAND]); |
|
427
|
|
|
$id = trim(array_pop($args), '/ '); |
|
428
|
7 |
|
$xobject = $page->getXObject($id); |
|
429
|
7 |
|
|
|
430
|
1 |
|
// @todo $xobject could be a ElementXRef object, which would then throw an error |
|
431
|
|
|
if (\is_object($xobject) && $xobject instanceof self && !\in_array($xobject->getUniqueId(), self::$recursionStack)) { |
|
432
|
6 |
|
// Not a circular reference. |
|
433
|
|
|
$text .= $xobject->getText($page); |
|
434
|
|
|
} |
|
435
|
6 |
|
} |
|
436
|
6 |
|
break; |
|
437
|
|
|
|
|
438
|
|
|
case 'rg': |
|
439
|
|
|
case 'RG': |
|
440
|
|
|
break; |
|
441
|
|
|
|
|
442
|
|
|
case 're': |
|
443
|
|
|
break; |
|
444
|
|
|
|
|
445
|
18 |
|
case 'co': |
|
446
|
1 |
|
break; |
|
447
|
1 |
|
|
|
448
|
|
|
case 'cs': |
|
449
|
|
|
break; |
|
450
|
18 |
|
|
|
451
|
|
|
case 'gs': |
|
452
|
|
|
break; |
|
453
|
20 |
|
|
|
454
|
|
|
case 'en': |
|
455
|
|
|
break; |
|
456
|
|
|
|
|
457
|
|
|
case 'sc': |
|
458
|
|
|
case 'SC': |
|
459
|
6 |
|
break; |
|
460
|
|
|
|
|
461
|
6 |
|
case 'g': |
|
462
|
6 |
|
case 'G': |
|
463
|
6 |
|
break; |
|
464
|
|
|
|
|
465
|
6 |
|
case 'V': |
|
466
|
6 |
|
break; |
|
467
|
|
|
|
|
468
|
6 |
|
case 'vo': |
|
469
|
6 |
|
case 'Vo': |
|
470
|
|
|
break; |
|
471
|
6 |
|
|
|
472
|
3 |
|
default: |
|
473
|
|
|
} |
|
474
|
|
|
} |
|
475
|
6 |
|
|
|
476
|
6 |
|
// Fix Hebrew and other reverse text oriented languages. |
|
477
|
|
|
// @see: https://github.com/smalot/pdfparser/issues/398 |
|
478
|
|
|
if ($reverse_text) { |
|
479
|
6 |
|
$chars = mb_str_split($text, 1, mb_internal_encoding()); |
|
|
|
|
|
|
480
|
|
|
$text = implode('', array_reverse($chars)); |
|
481
|
|
|
} |
|
482
|
6 |
|
|
|
483
|
6 |
|
$result .= $text; |
|
484
|
6 |
|
} |
|
485
|
6 |
|
|
|
486
|
6 |
|
return $result.' '; |
|
487
|
|
|
} |
|
488
|
6 |
|
|
|
489
|
|
|
/** |
|
490
|
6 |
|
* @throws \Exception |
|
491
|
6 |
|
*/ |
|
492
|
5 |
|
public function getTextArray(Page $page = null): array |
|
493
|
|
|
{ |
|
494
|
6 |
|
$text = []; |
|
495
|
6 |
|
$sections = $this->getSectionsText($this->content); |
|
496
|
6 |
|
$current_font = new Font($this->document, null, null, $this->config); |
|
497
|
6 |
|
|
|
498
|
|
|
foreach ($sections as $section) { |
|
499
|
|
|
$commands = $this->getCommandsText($section); |
|
500
|
5 |
|
|
|
501
|
4 |
|
foreach ($commands as $command) { |
|
502
|
|
|
switch ($command[self::OPERATOR]) { |
|
503
|
5 |
|
// set character spacing |
|
504
|
4 |
|
case 'Tc': |
|
505
|
|
|
break; |
|
506
|
|
|
|
|
507
|
5 |
|
// move text current point |
|
508
|
|
|
case 'Td': |
|
509
|
|
|
break; |
|
510
|
|
|
|
|
511
|
5 |
|
// move text current point and set leading |
|
512
|
2 |
|
case 'TD': |
|
513
|
|
|
break; |
|
514
|
|
|
|
|
515
|
5 |
|
case 'Tf': |
|
516
|
|
|
if (null !== $page) { |
|
517
|
|
|
list($id) = preg_split('/\s/s', $command[self::COMMAND]); |
|
518
|
|
|
$id = trim($id, '/'); |
|
519
|
|
|
$current_font = $page->getFont($id); |
|
520
|
5 |
|
} |
|
521
|
|
|
break; |
|
522
|
4 |
|
|
|
523
|
|
|
case "'": |
|
524
|
4 |
|
case 'Tj': |
|
525
|
|
|
$command[self::COMMAND] = [$command]; |
|
526
|
|
|
// no break |
|
527
|
4 |
|
case 'TJ': |
|
528
|
|
|
$text[] = $this->getTJUsingFontFallback( |
|
529
|
|
|
$current_font, |
|
530
|
|
|
$command[self::COMMAND], |
|
531
|
|
|
$page |
|
532
|
|
|
); |
|
533
|
|
|
break; |
|
534
|
|
|
|
|
535
|
|
|
// set leading |
|
536
|
|
|
case 'TL': |
|
537
|
4 |
|
break; |
|
538
|
4 |
|
|
|
539
|
2 |
|
case 'Tm': |
|
540
|
|
|
break; |
|
541
|
4 |
|
|
|
542
|
|
|
// set super/subscripting text rise |
|
543
|
|
|
case 'Ts': |
|
544
|
4 |
|
break; |
|
545
|
|
|
|
|
546
|
|
|
// set word spacing |
|
547
|
4 |
|
case 'Tw': |
|
548
|
|
|
break; |
|
549
|
|
|
|
|
550
|
4 |
|
// set horizontal scaling |
|
551
|
1 |
|
case 'Tz': |
|
552
|
|
|
// $text .= "\n"; |
|
553
|
4 |
|
break; |
|
554
|
|
|
|
|
555
|
|
|
// move to start of next line |
|
556
|
4 |
|
case 'T*': |
|
557
|
4 |
|
// $text .= "\n"; |
|
558
|
|
|
break; |
|
559
|
|
|
|
|
560
|
4 |
|
case 'Da': |
|
561
|
4 |
|
break; |
|
562
|
2 |
|
|
|
563
|
|
|
case 'Do': |
|
564
|
2 |
|
if (null !== $page) { |
|
565
|
|
|
$args = preg_split('/\s/s', $command[self::COMMAND]); |
|
566
|
|
|
$id = trim(array_pop($args), '/ '); |
|
567
|
2 |
|
if ($xobject = $page->getXObject($id)) { |
|
568
|
2 |
|
$text[] = $xobject->getText($page); |
|
569
|
|
|
} |
|
570
|
|
|
} |
|
571
|
|
|
break; |
|
572
|
|
|
|
|
573
|
|
|
case 'rg': |
|
574
|
|
|
case 'RG': |
|
575
|
|
|
break; |
|
576
|
6 |
|
|
|
577
|
|
|
case 're': |
|
578
|
|
|
break; |
|
579
|
29 |
|
|
|
580
|
|
|
case 'co': |
|
581
|
29 |
|
break; |
|
582
|
|
|
|
|
583
|
29 |
|
case 'cs': |
|
584
|
29 |
|
break; |
|
585
|
29 |
|
|
|
586
|
|
|
case 'gs': |
|
587
|
29 |
|
break; |
|
588
|
29 |
|
|
|
589
|
29 |
|
case 'en': |
|
590
|
|
|
break; |
|
591
|
29 |
|
|
|
592
|
29 |
|
case 'sc': |
|
593
|
29 |
|
case 'SC': |
|
594
|
29 |
|
break; |
|
595
|
29 |
|
|
|
596
|
29 |
|
case 'g': |
|
597
|
|
|
case 'G': |
|
598
|
|
|
break; |
|
599
|
|
|
|
|
600
|
29 |
|
case 'V': |
|
601
|
29 |
|
break; |
|
602
|
29 |
|
|
|
603
|
11 |
|
case 'vo': |
|
604
|
11 |
|
case 'Vo': |
|
605
|
11 |
|
break; |
|
606
|
|
|
|
|
607
|
|
|
default: |
|
608
|
|
|
} |
|
609
|
11 |
|
} |
|
610
|
11 |
|
} |
|
611
|
11 |
|
|
|
612
|
|
|
return $text; |
|
613
|
29 |
|
} |
|
614
|
|
|
|
|
615
|
29 |
|
public function getCommandsText(string $text_part, int &$offset = 0): array |
|
616
|
29 |
|
{ |
|
617
|
|
|
$commands = $matches = []; |
|
618
|
25 |
|
|
|
619
|
25 |
|
while ($offset < \strlen($text_part)) { |
|
620
|
25 |
|
$offset += strspn($text_part, "\x00\x09\x0a\x0c\x0d\x20", $offset); |
|
621
|
|
|
$char = $text_part[$offset]; |
|
622
|
25 |
|
|
|
623
|
|
|
$operator = ''; |
|
624
|
25 |
|
$type = ''; |
|
625
|
25 |
|
$command = false; |
|
626
|
25 |
|
|
|
627
|
|
|
switch ($char) { |
|
628
|
|
|
case '/': |
|
629
|
25 |
|
$type = $char; |
|
630
|
25 |
|
if (preg_match( |
|
631
|
|
|
'/\G\/([A-Z0-9\._,\+-]+\s+[0-9.\-]+)\s+([A-Z]+)\s*/si', |
|
632
|
25 |
|
$text_part, |
|
633
|
|
|
$matches, |
|
634
|
29 |
|
0, |
|
635
|
29 |
|
$offset |
|
636
|
|
|
) |
|
637
|
14 |
|
) { |
|
638
|
14 |
|
$operator = $matches[2]; |
|
639
|
14 |
|
$command = $matches[1]; |
|
640
|
14 |
|
$offset += \strlen($matches[0]); |
|
641
|
14 |
|
} elseif (preg_match( |
|
642
|
14 |
|
'/\G\/([A-Z0-9\._,\+-]+)\s+([A-Z]+)\s*/si', |
|
643
|
|
|
$text_part, |
|
644
|
|
|
$matches, |
|
645
|
14 |
|
0, |
|
646
|
9 |
|
$offset |
|
647
|
9 |
|
) |
|
648
|
|
|
) { |
|
649
|
14 |
|
$operator = $matches[2]; |
|
650
|
|
|
$command = $matches[1]; |
|
651
|
29 |
|
$offset += \strlen($matches[0]); |
|
652
|
29 |
|
} |
|
653
|
22 |
|
break; |
|
654
|
22 |
|
|
|
655
|
22 |
|
case '[': |
|
656
|
22 |
|
case ']': |
|
657
|
22 |
|
// array object |
|
658
|
22 |
|
$type = $char; |
|
659
|
22 |
|
if ('[' == $char) { |
|
660
|
|
|
++$offset; |
|
661
|
|
|
// get elements |
|
662
|
22 |
|
$command = $this->getCommandsText($text_part, $offset); |
|
663
|
22 |
|
|
|
664
|
22 |
|
if (preg_match( |
|
665
|
|
|
'/\G\s*[A-Z]{1,2}\s*/si', |
|
666
|
|
|
$text_part, |
|
667
|
16 |
|
$matches, |
|
668
|
16 |
|
0, |
|
669
|
|
|
$offset |
|
670
|
22 |
|
) |
|
671
|
|
|
) { |
|
672
|
|
|
$operator = trim($matches[0]); |
|
673
|
|
|
$offset += \strlen($matches[0]); |
|
674
|
|
|
} |
|
675
|
22 |
|
} else { |
|
676
|
|
|
++$offset; |
|
677
|
22 |
|
break; |
|
678
|
22 |
|
} |
|
679
|
|
|
break; |
|
680
|
22 |
|
|
|
681
|
|
|
case '<': |
|
682
|
22 |
|
case '>': |
|
683
|
22 |
|
// array object |
|
684
|
|
|
$type = $char; |
|
685
|
22 |
|
++$offset; |
|
686
|
18 |
|
if ('<' == $char) { |
|
687
|
18 |
|
$strpos = strpos($text_part, '>', $offset); |
|
688
|
|
|
$command = substr($text_part, $offset, $strpos - $offset); |
|
689
|
|
|
$offset = $strpos + 1; |
|
690
|
22 |
|
} |
|
691
|
|
|
|
|
692
|
|
|
if (preg_match( |
|
693
|
29 |
|
'/\G\s*[A-Z]{1,2}\s*/si', |
|
694
|
1 |
|
$text_part, |
|
695
|
29 |
|
$matches, |
|
696
|
29 |
|
0, |
|
697
|
29 |
|
$offset |
|
698
|
|
|
) |
|
699
|
|
|
) { |
|
700
|
|
|
$operator = trim($matches[0]); |
|
701
|
29 |
|
$offset += \strlen($matches[0]); |
|
702
|
29 |
|
} |
|
703
|
29 |
|
break; |
|
704
|
24 |
|
|
|
705
|
22 |
|
case '(': |
|
706
|
22 |
|
case ')': |
|
707
|
22 |
|
++$offset; |
|
708
|
17 |
|
$type = $char; |
|
709
|
17 |
|
$strpos = $offset; |
|
710
|
17 |
|
if ('(' == $char) { |
|
711
|
17 |
|
$open_bracket = 1; |
|
712
|
17 |
|
while ($open_bracket > 0) { |
|
713
|
|
|
if (!isset($text_part[$strpos])) { |
|
714
|
|
|
break; |
|
715
|
|
|
} |
|
716
|
29 |
|
$ch = $text_part[$strpos]; |
|
717
|
29 |
|
switch ($ch) { |
|
718
|
29 |
|
case '\\': |
|
719
|
29 |
|
// REVERSE SOLIDUS (5Ch) (Backslash) |
|
720
|
29 |
|
// skip next character |
|
721
|
|
|
++$strpos; |
|
722
|
|
|
break; |
|
723
|
25 |
|
|
|
724
|
|
|
case '(': |
|
725
|
|
|
// LEFT PARENHESIS (28h) |
|
726
|
|
|
++$open_bracket; |
|
727
|
29 |
|
break; |
|
728
|
|
|
|
|
729
|
|
|
case ')': |
|
730
|
42 |
|
// RIGHT PARENTHESIS (29h) |
|
731
|
|
|
--$open_bracket; |
|
732
|
|
|
break; |
|
733
|
|
|
} |
|
734
|
|
|
++$strpos; |
|
735
|
|
|
} |
|
736
|
42 |
|
$command = substr($text_part, $offset, $strpos - $offset - 1); |
|
737
|
42 |
|
$offset = $strpos; |
|
738
|
8 |
|
|
|
739
|
8 |
|
if (preg_match( |
|
740
|
3 |
|
'/\G\s*([A-Z\']{1,2})\s*/si', |
|
741
|
|
|
$text_part, |
|
742
|
6 |
|
$matches, |
|
743
|
6 |
|
0, |
|
744
|
|
|
$offset |
|
745
|
|
|
) |
|
746
|
|
|
) { |
|
747
|
|
|
$operator = $matches[1]; |
|
748
|
42 |
|
$offset += \strlen($matches[0]); |
|
749
|
41 |
|
} |
|
750
|
|
|
} |
|
751
|
42 |
|
break; |
|
752
|
41 |
|
|
|
753
|
|
|
default: |
|
754
|
42 |
|
if ('ET' == substr($text_part, $offset, 2)) { |
|
755
|
6 |
|
break; |
|
756
|
|
|
} elseif (preg_match( |
|
757
|
42 |
|
'/\G\s*(?P<data>([0-9\.\-]+\s*?)+)\s+(?P<id>[A-Z]{1,3})\s*/si', |
|
758
|
41 |
|
$text_part, |
|
759
|
41 |
|
$matches, |
|
760
|
|
|
0, |
|
761
|
41 |
|
$offset |
|
762
|
41 |
|
) |
|
763
|
|
|
) { |
|
764
|
|
|
$operator = trim($matches['id']); |
|
765
|
|
|
$command = trim($matches['data']); |
|
766
|
|
|
$offset += \strlen($matches[0]); |
|
767
|
|
|
} elseif (preg_match( |
|
768
|
42 |
|
'/\G\s*([0-9\.\-]+\s*?)+\s*/si', |
|
769
|
|
|
$text_part, |
|
770
|
|
|
$matches, |
|
771
|
|
|
0, |
|
772
|
|
|
$offset |
|
773
|
|
|
) |
|
774
|
|
|
) { |
|
775
|
20 |
|
$type = 'n'; |
|
776
|
|
|
$command = trim($matches[0]); |
|
777
|
20 |
|
$offset += \strlen($matches[0]); |
|
778
|
|
|
} elseif (preg_match( |
|
779
|
|
|
'/\G\s*([A-Z\*]+)\s*/si', |
|
780
|
|
|
$text_part, |
|
781
|
|
|
$matches, |
|
782
|
|
|
0, |
|
783
|
|
|
$offset |
|
784
|
|
|
) |
|
785
|
|
|
) { |
|
786
|
|
|
$type = ''; |
|
787
|
|
|
$operator = $matches[1]; |
|
788
|
|
|
$command = ''; |
|
789
|
|
|
$offset += \strlen($matches[0]); |
|
790
|
|
|
} |
|
791
|
|
|
} |
|
792
|
|
|
|
|
793
|
|
|
if (false !== $command) { |
|
794
|
|
|
$commands[] = [ |
|
795
|
|
|
self::TYPE => $type, |
|
796
|
|
|
self::OPERATOR => $operator, |
|
797
|
|
|
self::COMMAND => $command, |
|
798
|
|
|
]; |
|
799
|
|
|
} else { |
|
800
|
|
|
break; |
|
801
|
|
|
} |
|
802
|
|
|
} |
|
803
|
|
|
|
|
804
|
|
|
return $commands; |
|
805
|
|
|
} |
|
806
|
|
|
|
|
807
|
|
|
public static function factory( |
|
808
|
|
|
Document $document, |
|
809
|
|
|
Header $header, |
|
810
|
|
|
?string $content, |
|
811
|
|
|
Config $config = null |
|
812
|
|
|
): self { |
|
813
|
|
|
switch ($header->get('Type')->getContent()) { |
|
814
|
|
|
case 'XObject': |
|
815
|
|
|
switch ($header->get('Subtype')->getContent()) { |
|
816
|
|
|
case 'Image': |
|
817
|
|
|
return new Image($document, $header, $config->getRetainImageContent() ? $content : null, $config); |
|
|
|
|
|
|
818
|
|
|
|
|
819
|
|
|
case 'Form': |
|
820
|
|
|
return new Form($document, $header, $content, $config); |
|
821
|
|
|
} |
|
822
|
|
|
|
|
823
|
|
|
return new self($document, $header, $content, $config); |
|
824
|
|
|
|
|
825
|
|
|
case 'Pages': |
|
826
|
|
|
return new Pages($document, $header, $content, $config); |
|
827
|
|
|
|
|
828
|
|
|
case 'Page': |
|
829
|
|
|
return new Page($document, $header, $content, $config); |
|
830
|
|
|
|
|
831
|
|
|
case 'Encoding': |
|
832
|
|
|
return new Encoding($document, $header, $content, $config); |
|
833
|
|
|
|
|
834
|
|
|
case 'Font': |
|
835
|
|
|
$subtype = $header->get('Subtype')->getContent(); |
|
836
|
|
|
$classname = '\Smalot\PdfParser\Font\Font'.$subtype; |
|
837
|
|
|
|
|
838
|
|
|
if (class_exists($classname)) { |
|
839
|
|
|
return new $classname($document, $header, $content, $config); |
|
840
|
|
|
} |
|
841
|
|
|
|
|
842
|
|
|
return new Font($document, $header, $content, $config); |
|
843
|
|
|
|
|
844
|
|
|
default: |
|
845
|
|
|
return new self($document, $header, $content, $config); |
|
846
|
|
|
} |
|
847
|
|
|
} |
|
848
|
|
|
|
|
849
|
|
|
/** |
|
850
|
|
|
* Returns unique id identifying the object. |
|
851
|
|
|
*/ |
|
852
|
|
|
protected function getUniqueId(): string |
|
853
|
|
|
{ |
|
854
|
|
|
return spl_object_hash($this); |
|
855
|
|
|
} |
|
856
|
|
|
} |
|
857
|
|
|
|
smalot /
pdfparser
Loading history...
This check compares calls to functions or methods with their respective definitions. If the call has more arguments than are defined, it raises an issue.
If a function is defined several times with a different number of parameters, the check may pick up the wrong definition and report false positives. One codebase where this has been known to happen is Wordpress. Please note the @ignore annotation hint above.