|
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\Element; |
|
34
|
|
|
|
|
35
|
|
|
use Smalot\PdfParser\Document; |
|
36
|
|
|
use Smalot\PdfParser\Element; |
|
37
|
|
|
use Smalot\PdfParser\Font; |
|
38
|
|
|
|
|
39
|
|
|
/** |
|
40
|
|
|
* Class ElementString |
|
41
|
|
|
*/ |
|
42
|
|
|
class ElementString extends Element |
|
43
|
|
|
{ |
|
44
|
54 |
|
public function __construct($value) |
|
45
|
|
|
{ |
|
46
|
54 |
|
parent::__construct($value, null); |
|
47
|
54 |
|
} |
|
48
|
|
|
|
|
49
|
2 |
|
public function equals($value): bool |
|
50
|
|
|
{ |
|
51
|
2 |
|
return $value == $this->value; |
|
52
|
|
|
} |
|
53
|
|
|
|
|
54
|
|
|
/** |
|
55
|
|
|
* @return bool|ElementString |
|
56
|
|
|
*/ |
|
57
|
48 |
|
public static function parse(string $content, Document $document = null, int &$offset = 0) |
|
|
|
|
|
|
58
|
|
|
{ |
|
59
|
48 |
|
if (preg_match('/^\s*\((?P<name>.*)/s', $content, $match)) { |
|
60
|
45 |
|
$name = $match['name']; |
|
61
|
|
|
|
|
62
|
|
|
// Find next ')' not escaped. |
|
63
|
45 |
|
$cur_start_text = $start_search_end = 0; |
|
64
|
45 |
|
while (false !== ($cur_start_pos = strpos($name, ')', $start_search_end))) { |
|
65
|
45 |
|
$cur_extract = substr($name, $cur_start_text, $cur_start_pos - $cur_start_text); |
|
66
|
45 |
|
preg_match('/(?P<escape>[\\\]*)$/s', $cur_extract, $match); |
|
67
|
45 |
|
if (!(\strlen($match['escape']) % 2)) { |
|
68
|
45 |
|
break; |
|
69
|
|
|
} |
|
70
|
7 |
|
$start_search_end = $cur_start_pos + 1; |
|
71
|
|
|
} |
|
72
|
|
|
|
|
73
|
|
|
// Extract string. |
|
74
|
45 |
|
$name = substr($name, 0, (int) $cur_start_pos); |
|
75
|
45 |
|
$offset += strpos($content, '(') + $cur_start_pos + 2; // 2 for '(' and ')' |
|
76
|
45 |
|
$name = str_replace( |
|
77
|
45 |
|
['\\\\', '\\ ', '\\/', '\(', '\)', '\n', '\r', '\t'], |
|
78
|
45 |
|
['\\', ' ', '/', '(', ')', "\n", "\r", "\t"], |
|
79
|
|
|
$name |
|
80
|
|
|
); |
|
81
|
|
|
|
|
82
|
|
|
// Decode string. |
|
83
|
45 |
|
$name = Font::decodeOctal($name); |
|
84
|
45 |
|
$name = Font::decodeEntities($name); |
|
85
|
45 |
|
$name = Font::decodeHexadecimal($name, false); |
|
86
|
45 |
|
$name = Font::decodeUnicode($name); |
|
87
|
|
|
|
|
88
|
45 |
|
return new self($name); |
|
89
|
|
|
} |
|
90
|
|
|
|
|
91
|
17 |
|
return false; |
|
92
|
|
|
} |
|
93
|
|
|
} |
|
94
|
|
|
|
smalot /
pdfparser
Loading history...