|
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 PHPi, 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 ElementDate |
|
39
|
|
|
*/ |
|
40
|
|
|
class ElementDate extends ElementString |
|
41
|
|
|
{ |
|
42
|
|
|
/** |
|
43
|
|
|
* @var array |
|
44
|
|
|
*/ |
|
45
|
|
|
protected static $formats = [ |
|
46
|
|
|
4 => 'Y', |
|
47
|
|
|
6 => 'Ym', |
|
48
|
|
|
8 => 'Ymd', |
|
49
|
|
|
10 => 'YmdH', |
|
50
|
|
|
12 => 'YmdHi', |
|
51
|
|
|
14 => 'YmdHis', |
|
52
|
|
|
15 => 'YmdHise', |
|
53
|
|
|
17 => 'YmdHisO', |
|
54
|
|
|
18 => 'YmdHisO', |
|
55
|
|
|
19 => 'YmdHisO', |
|
56
|
|
|
]; |
|
57
|
|
|
|
|
58
|
|
|
/** |
|
59
|
|
|
* @var string |
|
60
|
|
|
*/ |
|
61
|
|
|
protected $format = 'c'; |
|
62
|
|
|
|
|
63
|
|
|
/** |
|
64
|
|
|
* @var \DateTime |
|
65
|
|
|
*/ |
|
66
|
|
|
protected $value; |
|
67
|
|
|
|
|
68
|
47 |
|
public function __construct($value) |
|
69
|
|
|
{ |
|
70
|
47 |
|
if (!($value instanceof \DateTime)) { |
|
71
|
1 |
|
throw new \Exception('DateTime required.'); // FIXME: Sometimes strings are passed to this function |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
46 |
|
parent::__construct($value); |
|
75
|
46 |
|
} |
|
76
|
|
|
|
|
77
|
3 |
|
public function setFormat(string $format) |
|
78
|
|
|
{ |
|
79
|
3 |
|
$this->format = $format; |
|
80
|
3 |
|
} |
|
81
|
|
|
|
|
82
|
2 |
|
public function equals($value): bool |
|
83
|
|
|
{ |
|
84
|
2 |
|
if ($value instanceof \DateTime) { |
|
85
|
1 |
|
$timestamp = $value->getTimeStamp(); |
|
86
|
|
|
} else { |
|
87
|
2 |
|
$timestamp = strtotime($value); |
|
88
|
|
|
} |
|
89
|
|
|
|
|
90
|
2 |
|
return $timestamp == $this->value->getTimeStamp(); |
|
91
|
|
|
} |
|
92
|
|
|
|
|
93
|
41 |
|
public function __toString(): string |
|
94
|
|
|
{ |
|
95
|
41 |
|
return (string) $this->value->format($this->format); |
|
96
|
|
|
} |
|
97
|
|
|
|
|
98
|
|
|
/** |
|
99
|
|
|
* @return bool|ElementDate |
|
100
|
|
|
*/ |
|
101
|
48 |
|
public static function parse(string $content, Document $document = null, int &$offset = 0) |
|
|
|
|
|
|
102
|
|
|
{ |
|
103
|
48 |
|
if (preg_match('/^\s*\(D\:(?P<name>.*?)\)/s', $content, $match)) { |
|
104
|
42 |
|
$name = $match['name']; |
|
105
|
42 |
|
$name = str_replace("'", '', $name); |
|
106
|
42 |
|
$date = false; |
|
107
|
|
|
|
|
108
|
|
|
// Smallest format : Y |
|
109
|
|
|
// Full format : YmdHisP |
|
110
|
42 |
|
if (preg_match('/^\d{4}(\d{2}(\d{2}(\d{2}(\d{2}(\d{2}(Z(\d{2,4})?|[\+-]?\d{2}(\d{2})?)?)?)?)?)?)?$/', $name)) { |
|
111
|
42 |
|
if ($pos = strpos($name, 'Z')) { |
|
112
|
6 |
|
$name = substr($name, 0, $pos + 1); |
|
113
|
41 |
|
} elseif (18 == \strlen($name) && preg_match('/[^\+-]0000$/', $name)) { |
|
114
|
1 |
|
$name = substr($name, 0, -4).'+0000'; |
|
115
|
|
|
} |
|
116
|
|
|
|
|
117
|
42 |
|
$format = self::$formats[\strlen($name)]; |
|
118
|
42 |
|
$date = \DateTime::createFromFormat($format, $name, new \DateTimeZone('UTC')); |
|
119
|
|
|
} else { |
|
120
|
|
|
// special cases |
|
121
|
1 |
|
if (preg_match('/^\d{1,2}-\d{1,2}-\d{4},?\s+\d{2}:\d{2}:\d{2}[\+-]\d{4}$/', $name)) { |
|
122
|
1 |
|
$name = str_replace(',', '', $name); |
|
123
|
1 |
|
$format = 'n-j-Y H:i:sO'; |
|
124
|
1 |
|
$date = \DateTime::createFromFormat($format, $name, new \DateTimeZone('UTC')); |
|
125
|
|
|
} |
|
126
|
|
|
} |
|
127
|
|
|
|
|
128
|
42 |
|
if (!$date) { |
|
129
|
1 |
|
return false; |
|
130
|
|
|
} |
|
131
|
|
|
|
|
132
|
42 |
|
$offset += strpos($content, '(D:') + \strlen($match['name']) + 4; // 1 for '(D:' and ')' |
|
133
|
|
|
|
|
134
|
42 |
|
return new self($date); |
|
135
|
|
|
} |
|
136
|
|
|
|
|
137
|
48 |
|
return false; |
|
138
|
|
|
} |
|
139
|
|
|
} |
|
140
|
|
|
|
smalot /
pdfparser
Loading history...