|
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
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* Class ElementHexa |
|
39
|
|
|
*/ |
|
40
|
|
|
class ElementHexa extends ElementString |
|
41
|
|
|
{ |
|
42
|
|
|
/** |
|
43
|
|
|
* @return bool|ElementHexa|ElementDate |
|
44
|
|
|
*/ |
|
45
|
17 |
|
public static function parse(string $content, Document $document = null, int &$offset = 0) |
|
|
|
|
|
|
46
|
|
|
{ |
|
47
|
17 |
|
if (preg_match('/^\s*\<(?P<name>[A-F0-9]+)\>/is', $content, $match)) { |
|
48
|
2 |
|
$name = $match['name']; |
|
49
|
2 |
|
$offset += strpos($content, '<'.$name) + \strlen($name) + 2; // 1 for '>' |
|
50
|
|
|
// repackage string as standard |
|
51
|
2 |
|
$name = '('.self::decode($name).')'; |
|
52
|
2 |
|
$element = ElementDate::parse($name, $document); |
|
53
|
|
|
|
|
54
|
2 |
|
if (!$element) { |
|
55
|
2 |
|
$element = ElementString::parse($name, $document); |
|
56
|
|
|
} |
|
57
|
|
|
|
|
58
|
2 |
|
return $element; |
|
59
|
|
|
} |
|
60
|
|
|
|
|
61
|
17 |
|
return false; |
|
62
|
|
|
} |
|
63
|
|
|
|
|
64
|
20 |
|
public static function decode(string $value): string |
|
65
|
|
|
{ |
|
66
|
20 |
|
$text = ''; |
|
67
|
20 |
|
$length = \strlen($value); |
|
68
|
|
|
|
|
69
|
20 |
|
if ('00' === substr($value, 0, 2)) { |
|
70
|
4 |
|
for ($i = 0; $i < $length; $i += 4) { |
|
71
|
4 |
|
$hex = substr($value, $i, 4); |
|
72
|
4 |
|
$text .= '&#'.str_pad(hexdec($hex), 4, '0', \STR_PAD_LEFT).';'; |
|
73
|
|
|
} |
|
74
|
|
|
} else { |
|
75
|
19 |
|
for ($i = 0; $i < $length; $i += 2) { |
|
76
|
19 |
|
$hex = substr($value, $i, 2); |
|
77
|
19 |
|
$text .= \chr(hexdec($hex)); |
|
78
|
|
|
} |
|
79
|
|
|
} |
|
80
|
|
|
|
|
81
|
20 |
|
$text = html_entity_decode($text, \ENT_NOQUOTES, 'UTF-8'); |
|
82
|
|
|
|
|
83
|
20 |
|
return $text; |
|
84
|
|
|
} |
|
85
|
|
|
} |
|
86
|
|
|
|
smalot /
pdfparser
Loading history...