1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* This file is based on code of tecnickcom/TCPDF PDF library. |
5
|
|
|
* |
6
|
|
|
* Original author Nicola Asuni ([email protected]) and |
7
|
|
|
* contributors (https://github.com/tecnickcom/TCPDF/graphs/contributors). |
8
|
|
|
* |
9
|
|
|
* @see https://github.com/tecnickcom/TCPDF |
10
|
|
|
* |
11
|
|
|
* Original code was licensed on the terms of the LGPL v3. |
12
|
|
|
* |
13
|
|
|
* ------------------------------------------------------------------------------ |
14
|
|
|
* |
15
|
|
|
* @file This file is part of the PdfParser library. |
16
|
|
|
* |
17
|
|
|
* @author Konrad Abicht <[email protected]> |
18
|
|
|
* @date 2020-01-06 |
19
|
|
|
* |
20
|
|
|
* @license LGPLv3 |
21
|
|
|
* @url <https://github.com/smalot/pdfparser> |
22
|
|
|
* |
23
|
|
|
* PdfParser is a pdf library written in PHP, extraction oriented. |
24
|
|
|
* Copyright (C) 2017 - Sébastien MALOT <[email protected]> |
25
|
|
|
* |
26
|
|
|
* This program is free software: you can redistribute it and/or modify |
27
|
|
|
* it under the terms of the GNU Lesser General Public License as published by |
28
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
29
|
|
|
* (at your option) any later version. |
30
|
|
|
* |
31
|
|
|
* This program is distributed in the hope that it will be useful, |
32
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
33
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
34
|
|
|
* GNU Lesser General Public License for more details. |
35
|
|
|
* |
36
|
|
|
* You should have received a copy of the GNU Lesser General Public License |
37
|
|
|
* along with this program. |
38
|
|
|
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>. |
39
|
|
|
*/ |
40
|
|
|
|
41
|
|
|
namespace Smalot\PdfParser\RawData; |
42
|
|
|
|
43
|
|
|
use Exception; |
44
|
|
|
|
45
|
|
|
class FilterHelper |
46
|
|
|
{ |
47
|
|
|
protected $availableFilters = ['ASCIIHexDecode', 'ASCII85Decode', 'LZWDecode', 'FlateDecode', 'RunLengthDecode']; |
48
|
|
|
|
49
|
|
|
/** |
50
|
|
|
* Decode data using the specified filter type. |
51
|
|
|
* |
52
|
|
|
* @param string $filter Filter name |
53
|
|
|
* @param string $data Data to decode |
54
|
|
|
* |
55
|
|
|
* @return string Decoded data string |
56
|
|
|
* |
57
|
|
|
* @throws Exception if a certain decode function is not implemented yet |
58
|
|
|
*/ |
59
|
19 |
|
public function decodeFilter($filter, $data) |
60
|
|
|
{ |
61
|
|
|
switch ($filter) { |
62
|
19 |
|
case 'ASCIIHexDecode': |
63
|
|
|
return $this->decodeFilterASCIIHexDecode($data); |
64
|
|
|
|
65
|
19 |
|
case 'ASCII85Decode': |
66
|
|
|
return $this->decodeFilterASCII85Decode($data); |
67
|
|
|
|
68
|
19 |
|
case 'LZWDecode': |
69
|
|
|
return $this->decodeFilterLZWDecode($data); |
70
|
|
|
|
71
|
19 |
|
case 'FlateDecode': |
72
|
19 |
|
return $this->decodeFilterFlateDecode($data); |
73
|
|
|
|
74
|
|
|
case 'RunLengthDecode': |
75
|
|
|
return $this->decodeFilterRunLengthDecode($data); |
76
|
|
|
|
77
|
|
|
case 'CCITTFaxDecode': |
78
|
|
|
throw new Exception('Decode CCITTFaxDecode not implemented yet.'); |
79
|
|
|
case 'JBIG2Decode': |
80
|
|
|
throw new Exception('Decode JBIG2Decode not implemented yet.'); |
81
|
|
|
case 'DCTDecode': |
82
|
|
|
throw new Exception('Decode DCTDecode not implemented yet.'); |
83
|
|
|
case 'JPXDecode': |
84
|
|
|
throw new Exception('Decode JPXDecode not implemented yet.'); |
85
|
|
|
case 'Crypt': |
86
|
|
|
throw new Exception('Decode Crypt not implemented yet.'); |
87
|
|
|
default: |
88
|
|
|
return $data; |
89
|
|
|
} |
90
|
|
|
} |
91
|
|
|
|
92
|
|
|
/** |
93
|
|
|
* ASCIIHexDecode |
94
|
|
|
* |
95
|
|
|
* Decodes data encoded in an ASCII hexadecimal representation, reproducing the original binary data. |
96
|
|
|
* |
97
|
|
|
* @param string $data Data to decode |
98
|
|
|
* |
99
|
|
|
* @return string data string |
100
|
|
|
*/ |
101
|
|
|
protected function decodeFilterASCIIHexDecode($data) |
102
|
|
|
{ |
103
|
|
|
// all white-space characters shall be ignored |
104
|
|
|
$data = preg_replace('/[\s]/', '', $data); |
105
|
|
|
// check for EOD character: GREATER-THAN SIGN (3Eh) |
106
|
|
|
$eod = strpos($data, '>'); |
107
|
|
|
if (false !== $eod) { |
108
|
|
|
// remove EOD and extra data (if any) |
109
|
|
|
$data = substr($data, 0, $eod); |
110
|
|
|
$eod = true; |
111
|
|
|
} |
112
|
|
|
// get data length |
113
|
|
|
$data_length = \strlen($data); |
114
|
|
|
if (0 != ($data_length % 2)) { |
115
|
|
|
// odd number of hexadecimal digits |
116
|
|
|
if ($eod) { |
117
|
|
|
// EOD shall behave as if a 0 (zero) followed the last digit |
118
|
|
|
$data = substr($data, 0, -1).'0'.substr($data, -1); |
119
|
|
|
} else { |
120
|
|
|
throw new Exception('decodeFilterASCIIHexDecode: invalid code'); |
121
|
|
|
} |
122
|
|
|
} |
123
|
|
|
// check for invalid characters |
124
|
|
|
if (preg_match('/[^a-fA-F\d]/', $data) > 0) { |
125
|
|
|
throw new Exception('decodeFilterASCIIHexDecode: invalid code'); |
126
|
|
|
} |
127
|
|
|
// get one byte of binary data for each pair of ASCII hexadecimal digits |
128
|
|
|
$decoded = pack('H*', $data); |
129
|
|
|
|
130
|
|
|
return $decoded; |
131
|
|
|
} |
132
|
|
|
|
133
|
|
|
/** |
134
|
|
|
* ASCII85Decode |
135
|
|
|
* |
136
|
|
|
* Decodes data encoded in an ASCII base-85 representation, reproducing the original binary data. |
137
|
|
|
* |
138
|
|
|
* @param string $data Data to decode |
139
|
|
|
* |
140
|
|
|
* @return string data string |
141
|
|
|
*/ |
142
|
|
|
protected function decodeFilterASCII85Decode($data) |
143
|
|
|
{ |
144
|
|
|
// initialize string to return |
145
|
|
|
$decoded = ''; |
146
|
|
|
// all white-space characters shall be ignored |
147
|
|
|
$data = preg_replace('/[\s]/', '', $data); |
148
|
|
|
// remove start sequence 2-character sequence <~ (3Ch)(7Eh) |
149
|
|
|
if (false !== strpos($data, '<~')) { |
150
|
|
|
// remove EOD and extra data (if any) |
151
|
|
|
$data = substr($data, 2); |
152
|
|
|
} |
153
|
|
|
// check for EOD: 2-character sequence ~> (7Eh)(3Eh) |
154
|
|
|
$eod = strpos($data, '~>'); |
155
|
|
|
if (false !== $eod) { |
156
|
|
|
// remove EOD and extra data (if any) |
157
|
|
|
$data = substr($data, 0, $eod); |
158
|
|
|
} |
159
|
|
|
// data length |
160
|
|
|
$data_length = \strlen($data); |
161
|
|
|
// check for invalid characters |
162
|
|
|
if (preg_match('/[^\x21-\x75,\x74]/', $data) > 0) { |
163
|
|
|
throw new Exception('decodeFilterASCII85Decode: invalid code'); |
164
|
|
|
} |
165
|
|
|
// z sequence |
166
|
|
|
$zseq = \chr(0).\chr(0).\chr(0).\chr(0); |
167
|
|
|
// position inside a group of 4 bytes (0-3) |
168
|
|
|
$group_pos = 0; |
169
|
|
|
$tuple = 0; |
170
|
|
|
$pow85 = [(85 * 85 * 85 * 85), (85 * 85 * 85), (85 * 85), 85, 1]; |
171
|
|
|
|
172
|
|
|
// for each byte |
173
|
|
|
for ($i = 0; $i < $data_length; ++$i) { |
174
|
|
|
// get char value |
175
|
|
|
$char = \ord($data[$i]); |
176
|
|
|
if (122 == $char) { // 'z' |
177
|
|
|
if (0 == $group_pos) { |
178
|
|
|
$decoded .= $zseq; |
179
|
|
|
} else { |
180
|
|
|
throw new Exception('decodeFilterASCII85Decode: invalid code'); |
181
|
|
|
} |
182
|
|
|
} else { |
183
|
|
|
// the value represented by a group of 5 characters should never be greater than 2^32 - 1 |
184
|
|
|
$tuple += (($char - 33) * $pow85[$group_pos]); |
185
|
|
|
if (4 == $group_pos) { |
186
|
|
|
$decoded .= \chr($tuple >> 24).\chr($tuple >> 16).\chr($tuple >> 8).\chr($tuple); |
187
|
|
|
$tuple = 0; |
188
|
|
|
$group_pos = 0; |
189
|
|
|
} else { |
190
|
|
|
++$group_pos; |
191
|
|
|
} |
192
|
|
|
} |
193
|
|
|
} |
194
|
|
|
if ($group_pos > 1) { |
195
|
|
|
$tuple += $pow85[($group_pos - 1)]; |
196
|
|
|
} |
197
|
|
|
// last tuple (if any) |
198
|
|
|
switch ($group_pos) { |
199
|
|
|
case 4: |
200
|
|
|
$decoded .= \chr($tuple >> 24).\chr($tuple >> 16).\chr($tuple >> 8); |
201
|
|
|
break; |
202
|
|
|
|
203
|
|
|
case 3: |
204
|
|
|
$decoded .= \chr($tuple >> 24).\chr($tuple >> 16); |
205
|
|
|
break; |
206
|
|
|
|
207
|
|
|
case 2: |
208
|
|
|
$decoded .= \chr($tuple >> 24); |
209
|
|
|
break; |
210
|
|
|
|
211
|
|
|
case 1: |
212
|
|
|
throw new Exception('decodeFilterASCII85Decode: invalid code'); |
213
|
|
|
break; |
214
|
|
|
} |
215
|
|
|
|
216
|
|
|
return $decoded; |
217
|
|
|
} |
218
|
|
|
|
219
|
|
|
/** |
220
|
|
|
* FlateDecode |
221
|
|
|
* |
222
|
|
|
* Decompresses data encoded using the zlib/deflate compression method, reproducing the original text or binary data. |
223
|
|
|
* |
224
|
|
|
* @param string $data Data to decode |
225
|
|
|
* |
226
|
|
|
* @return string data string |
227
|
|
|
*/ |
228
|
|
|
protected function decodeFilterFlateDecode($data) |
229
|
|
|
{ |
230
|
|
|
/* |
231
|
|
|
* gzuncompress may throw a not catchable E_WARNING in case of an error (like $data is empty) |
232
|
|
|
* the following set_error_handler changes an E_WARNING to an E_ERROR, which is catchable. |
233
|
|
|
*/ |
234
|
19 |
|
set_error_handler(function ($errNo, $errStr) { |
235
|
3 |
|
if (E_WARNING === $errNo) { |
236
|
3 |
|
throw new Exception($errStr); |
237
|
|
|
} else { |
238
|
|
|
// fallback to default php error handler |
239
|
|
|
return false; |
240
|
|
|
} |
241
|
19 |
|
}); |
242
|
|
|
|
243
|
|
|
// initialize string to return |
244
|
|
|
try { |
245
|
19 |
|
$decoded = gzuncompress($data); |
246
|
17 |
|
if (false === $decoded) { |
247
|
17 |
|
throw new Exception('decodeFilterFlateDecode: invalid code'); |
248
|
|
|
} |
249
|
3 |
|
} catch (Exception $e) { |
250
|
3 |
|
throw $e; |
251
|
17 |
|
} finally { |
252
|
|
|
// Restore old handler just in case it was customized outside of PDFParser. |
253
|
19 |
|
restore_error_handler(); |
254
|
|
|
} |
255
|
|
|
|
256
|
17 |
|
return $decoded; |
257
|
|
|
} |
258
|
|
|
|
259
|
|
|
/** |
260
|
|
|
* LZWDecode |
261
|
|
|
* |
262
|
|
|
* Decompresses data encoded using the LZW (Lempel-Ziv-Welch) adaptive compression method, reproducing the original text or binary data. |
263
|
|
|
* |
264
|
|
|
* @param string $data Data to decode |
265
|
|
|
* |
266
|
|
|
* @return string Data string |
267
|
|
|
*/ |
268
|
|
|
protected function decodeFilterLZWDecode($data) |
269
|
|
|
{ |
270
|
|
|
// initialize string to return |
271
|
|
|
$decoded = ''; |
272
|
|
|
// data length |
273
|
|
|
$data_length = \strlen($data); |
274
|
|
|
// convert string to binary string |
275
|
|
|
$bitstring = ''; |
276
|
|
|
for ($i = 0; $i < $data_length; ++$i) { |
277
|
|
|
$bitstring .= sprintf('%08b', \ord($data[$i])); |
278
|
|
|
} |
279
|
|
|
// get the number of bits |
280
|
|
|
$data_length = \strlen($bitstring); |
281
|
|
|
// initialize code length in bits |
282
|
|
|
$bitlen = 9; |
283
|
|
|
// initialize dictionary index |
284
|
|
|
$dix = 258; |
285
|
|
|
// initialize the dictionary (with the first 256 entries). |
286
|
|
|
$dictionary = []; |
287
|
|
|
for ($i = 0; $i < 256; ++$i) { |
288
|
|
|
$dictionary[$i] = \chr($i); |
289
|
|
|
} |
290
|
|
|
// previous val |
291
|
|
|
$prev_index = 0; |
292
|
|
|
// while we encounter EOD marker (257), read code_length bits |
293
|
|
|
while (($data_length > 0) and (257 != ($index = bindec(substr($bitstring, 0, $bitlen))))) { |
294
|
|
|
// remove read bits from string |
295
|
|
|
$bitstring = substr($bitstring, $bitlen); |
296
|
|
|
// update number of bits |
297
|
|
|
$data_length -= $bitlen; |
298
|
|
|
if (256 == $index) { // clear-table marker |
299
|
|
|
// reset code length in bits |
300
|
|
|
$bitlen = 9; |
301
|
|
|
// reset dictionary index |
302
|
|
|
$dix = 258; |
303
|
|
|
$prev_index = 256; |
304
|
|
|
// reset the dictionary (with the first 256 entries). |
305
|
|
|
$dictionary = []; |
306
|
|
|
for ($i = 0; $i < 256; ++$i) { |
307
|
|
|
$dictionary[$i] = \chr($i); |
308
|
|
|
} |
309
|
|
|
} elseif (256 == $prev_index) { |
310
|
|
|
// first entry |
311
|
|
|
$decoded .= $dictionary[$index]; |
312
|
|
|
$prev_index = $index; |
313
|
|
|
} else { |
314
|
|
|
// check if index exist in the dictionary |
315
|
|
|
if ($index < $dix) { |
316
|
|
|
// index exist on dictionary |
317
|
|
|
$decoded .= $dictionary[$index]; |
318
|
|
|
$dic_val = $dictionary[$prev_index].$dictionary[$index][0]; |
319
|
|
|
// store current index |
320
|
|
|
$prev_index = $index; |
321
|
|
|
} else { |
322
|
|
|
// index do not exist on dictionary |
323
|
|
|
$dic_val = $dictionary[$prev_index].$dictionary[$prev_index][0]; |
324
|
|
|
$decoded .= $dic_val; |
325
|
|
|
} |
326
|
|
|
// update dictionary |
327
|
|
|
$dictionary[$dix] = $dic_val; |
328
|
|
|
++$dix; |
329
|
|
|
// change bit length by case |
330
|
|
|
if (2047 == $dix) { |
331
|
|
|
$bitlen = 12; |
332
|
|
|
} elseif (1023 == $dix) { |
333
|
|
|
$bitlen = 11; |
334
|
|
|
} elseif (511 == $dix) { |
335
|
|
|
$bitlen = 10; |
336
|
|
|
} |
337
|
|
|
} |
338
|
|
|
} |
339
|
|
|
|
340
|
|
|
return $decoded; |
341
|
|
|
} |
342
|
|
|
|
343
|
|
|
/** |
344
|
|
|
* RunLengthDecode |
345
|
|
|
* |
346
|
|
|
* Decompresses data encoded using a byte-oriented run-length encoding algorithm. |
347
|
|
|
* |
348
|
|
|
* @param string $data Data to decode |
349
|
|
|
* |
350
|
|
|
* @return string |
351
|
|
|
*/ |
352
|
|
|
protected function decodeFilterRunLengthDecode($data) |
353
|
|
|
{ |
354
|
|
|
// initialize string to return |
355
|
|
|
$decoded = ''; |
356
|
|
|
// data length |
357
|
|
|
$data_length = \strlen($data); |
358
|
|
|
$i = 0; |
359
|
|
|
while ($i < $data_length) { |
360
|
|
|
// get current byte value |
361
|
|
|
$byte = \ord($data[$i]); |
362
|
|
|
if (128 == $byte) { |
363
|
|
|
// a length value of 128 denote EOD |
364
|
|
|
break; |
365
|
|
|
} elseif ($byte < 128) { |
366
|
|
|
// if the length byte is in the range 0 to 127 |
367
|
|
|
// the following length + 1 (1 to 128) bytes shall be copied literally during decompression |
368
|
|
|
$decoded .= substr($data, ($i + 1), ($byte + 1)); |
369
|
|
|
// move to next block |
370
|
|
|
$i += ($byte + 2); |
371
|
|
|
} else { |
372
|
|
|
// if length is in the range 129 to 255, |
373
|
|
|
// the following single byte shall be copied 257 - length (2 to 128) times during decompression |
374
|
|
|
$decoded .= str_repeat($data[($i + 1)], (257 - $byte)); |
375
|
|
|
// move to next block |
376
|
|
|
$i += 2; |
377
|
|
|
} |
378
|
|
|
} |
379
|
|
|
|
380
|
|
|
return $decoded; |
381
|
|
|
} |
382
|
|
|
|
383
|
|
|
/** |
384
|
|
|
* @return array list of available filters |
385
|
|
|
*/ |
386
|
16 |
|
public function getAvailableFilters() |
387
|
|
|
{ |
388
|
16 |
|
return $this->availableFilters; |
389
|
|
|
} |
390
|
|
|
} |
391
|
|
|
|