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\Element\ElementArray; |
||
36 | use Smalot\PdfParser\Element\ElementBoolean; |
||
37 | use Smalot\PdfParser\Element\ElementDate; |
||
38 | use Smalot\PdfParser\Element\ElementHexa; |
||
39 | use Smalot\PdfParser\Element\ElementName; |
||
40 | use Smalot\PdfParser\Element\ElementNull; |
||
41 | use Smalot\PdfParser\Element\ElementNumeric; |
||
42 | use Smalot\PdfParser\Element\ElementString; |
||
43 | use Smalot\PdfParser\Element\ElementStruct; |
||
44 | use Smalot\PdfParser\Element\ElementXRef; |
||
45 | |||
46 | /** |
||
47 | * Class Element |
||
48 | */ |
||
49 | class Element |
||
50 | { |
||
51 | /** |
||
52 | * @var Document|null |
||
53 | */ |
||
54 | protected $document; |
||
55 | |||
56 | protected $value; |
||
57 | |||
58 | 138 | public function __construct($value, ?Document $document = null) |
|
59 | { |
||
60 | 138 | $this->value = $value; |
|
61 | 138 | $this->document = $document; |
|
62 | } |
||
63 | |||
64 | 74 | public function init() |
|
65 | { |
||
66 | 74 | } |
|
67 | |||
68 | 7 | public function equals($value): bool |
|
69 | { |
||
70 | 7 | return $value == $this->value; |
|
71 | } |
||
72 | |||
73 | 11 | public function contains($value): bool |
|
74 | { |
||
75 | 11 | if (\is_array($this->value)) { |
|
76 | /** @var Element $val */ |
||
77 | 4 | foreach ($this->value as $val) { |
|
78 | 4 | if ($val->equals($value)) { |
|
79 | 4 | return true; |
|
80 | } |
||
81 | } |
||
82 | |||
83 | 3 | return false; |
|
84 | } |
||
85 | |||
86 | 7 | return $this->equals($value); |
|
87 | } |
||
88 | |||
89 | 106 | public function getContent() |
|
90 | { |
||
91 | 106 | return $this->value; |
|
92 | } |
||
93 | |||
94 | 70 | public function __toString(): string |
|
95 | { |
||
96 | 70 | return (string) $this->value; |
|
97 | } |
||
98 | |||
99 | 32 | public static function parse(string $content, ?Document $document = null, int &$position = 0) |
|
100 | { |
||
101 | 32 | $args = \func_get_args(); |
|
102 | 32 | $only_values = isset($args[3]) ? $args[3] : false; |
|
103 | 32 | $content = trim($content); |
|
104 | 32 | $values = []; |
|
105 | |||
106 | do { |
||
107 | 32 | $old_position = $position; |
|
108 | |||
109 | 32 | if (!$only_values) { |
|
110 | 30 | if (!preg_match('/\G\s*(?P<name>\/[A-Z#0-9\._]+)(?P<value>.*)/si', $content, $match, 0, $position)) { |
|
111 | 3 | break; |
|
112 | } else { |
||
113 | 30 | $name = preg_replace_callback( |
|
114 | 30 | '/#([0-9a-f]{2})/i', |
|
115 | 30 | function ($m) { |
|
116 | 1 | return \chr(base_convert($m[1], 16, 10)); |
|
0 ignored issues
–
show
Bug
introduced
by
![]() |
|||
117 | 30 | }, |
|
118 | 30 | ltrim($match['name'], '/') |
|
119 | 30 | ); |
|
120 | 30 | $value = $match['value']; |
|
121 | 30 | $position = strpos($content, $value, $position + \strlen($match['name'])); |
|
122 | } |
||
123 | } else { |
||
124 | 22 | $name = \count($values); |
|
125 | 22 | $value = substr($content, $position); |
|
126 | } |
||
127 | |||
128 | 32 | if ($element = ElementName::parse($value, $document, $position)) { |
|
129 | 30 | $values[$name] = $element; |
|
130 | 26 | } elseif ($element = ElementXRef::parse($value, $document, $position)) { |
|
131 | 23 | $values[$name] = $element; |
|
132 | 23 | } elseif ($element = ElementNumeric::parse($value, $document, $position)) { |
|
133 | 20 | $values[$name] = $element; |
|
134 | 21 | } elseif ($element = ElementStruct::parse($value, $document, $position)) { |
|
135 | 14 | $values[$name] = $element; |
|
136 | 21 | } elseif ($element = ElementBoolean::parse($value, $document, $position)) { |
|
137 | 3 | $values[$name] = $element; |
|
138 | 21 | } elseif ($element = ElementNull::parse($value, $document, $position)) { |
|
139 | 4 | $values[$name] = $element; |
|
140 | 21 | } elseif ($element = ElementDate::parse($value, $document, $position)) { |
|
141 | 13 | $values[$name] = $element; |
|
142 | 21 | } elseif ($element = ElementString::parse($value, $document, $position)) { |
|
143 | 18 | $values[$name] = $element; |
|
144 | 20 | } elseif ($element = ElementHexa::parse($value, $document, $position)) { |
|
145 | 2 | $values[$name] = $element; |
|
146 | 20 | } elseif ($element = ElementArray::parse($value, $document, $position)) { |
|
147 | 19 | $values[$name] = $element; |
|
148 | } else { |
||
149 | 5 | $position = $old_position; |
|
150 | 5 | break; |
|
151 | } |
||
152 | 32 | } while ($position < \strlen($content)); |
|
153 | |||
154 | 32 | return $values; |
|
155 | } |
||
156 | } |
||
157 |