|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* @file This file is part of the PdfParser library. |
|
5
|
|
|
* |
|
6
|
|
|
* @author Konrad Abicht <[email protected]> |
|
7
|
|
|
* |
|
8
|
|
|
* @date 2020-06-01 |
|
9
|
|
|
* |
|
10
|
|
|
* @author Sébastien MALOT <[email protected]> |
|
11
|
|
|
* |
|
12
|
|
|
* @date 2017-01-03 |
|
13
|
|
|
* |
|
14
|
|
|
* @license LGPLv3 |
|
15
|
|
|
* |
|
16
|
|
|
* @url <https://github.com/smalot/pdfparser> |
|
17
|
|
|
* |
|
18
|
|
|
* PdfParser is a pdf library written in PHP, extraction oriented. |
|
19
|
|
|
* Copyright (C) 2017 - Sébastien MALOT <[email protected]> |
|
20
|
|
|
* |
|
21
|
|
|
* This program is free software: you can redistribute it and/or modify |
|
22
|
|
|
* it under the terms of the GNU Lesser General Public License as published by |
|
23
|
|
|
* the Free Software Foundation, either version 3 of the License, or |
|
24
|
|
|
* (at your option) any later version. |
|
25
|
|
|
* |
|
26
|
|
|
* This program is distributed in the hope that it will be useful, |
|
27
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
28
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
29
|
|
|
* GNU Lesser General Public License for more details. |
|
30
|
|
|
* |
|
31
|
|
|
* You should have received a copy of the GNU Lesser General Public License |
|
32
|
|
|
* along with this program. |
|
33
|
|
|
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>. |
|
34
|
|
|
*/ |
|
35
|
|
|
|
|
36
|
|
|
namespace PHPUnitTests\Integration; |
|
37
|
|
|
|
|
38
|
|
|
use PHPUnitTests\TestCase; |
|
39
|
|
|
use Smalot\PdfParser\Element; |
|
40
|
|
|
use Smalot\PdfParser\Element\ElementMissing; |
|
41
|
|
|
use Smalot\PdfParser\Element\ElementName; |
|
42
|
|
|
use Smalot\PdfParser\Header; |
|
43
|
|
|
use Smalot\PdfParser\Page; |
|
44
|
|
|
use Smalot\PdfParser\PDFObject; |
|
45
|
|
|
|
|
46
|
|
|
/** |
|
47
|
|
|
* Class Header |
|
48
|
|
|
*/ |
|
49
|
|
|
class HeaderTest extends TestCase |
|
50
|
|
|
{ |
|
51
|
|
|
/** |
|
52
|
|
|
* Checks that init function is called for each element. |
|
53
|
|
|
*/ |
|
54
|
|
|
public function testInitHappyPath(): void |
|
55
|
|
|
{ |
|
56
|
|
|
$element = $this->createMock(Element::class); |
|
57
|
|
|
$element->expects($this->exactly(1))->method('init'); |
|
58
|
|
|
|
|
59
|
|
|
$fixture = new Header([$element]); |
|
60
|
|
|
$fixture->init(); |
|
61
|
|
|
} |
|
62
|
|
|
|
|
63
|
|
|
/** |
|
64
|
|
|
* Checks buggy behavior if an element was given which is not of type Element. |
|
65
|
|
|
* |
|
66
|
|
|
* Problem was, it always called $element::init(), even if its not an object at all. |
|
67
|
|
|
* |
|
68
|
|
|
* @see https://github.com/smalot/pdfparser/issues/367 |
|
69
|
|
|
* |
|
70
|
|
|
* @doesNotPerformAssertions |
|
71
|
|
|
*/ |
|
72
|
|
|
public function testInitInvalidElement(): void |
|
73
|
|
|
{ |
|
74
|
|
|
$element = false; |
|
75
|
|
|
|
|
76
|
|
|
$fixture = new Header([$element]); |
|
77
|
|
|
$fixture->init(); |
|
78
|
|
|
} |
|
79
|
|
|
|
|
80
|
|
|
public function testParse(): void |
|
81
|
|
|
{ |
|
82
|
|
|
$document = $this->getDocumentInstance(); |
|
83
|
|
|
|
|
84
|
|
|
$content = '<</Type/Page/SubType/Text>>foo'; |
|
85
|
|
|
$position = 0; |
|
86
|
|
|
$header = Header::parse($content, $document, $position); |
|
87
|
|
|
|
|
88
|
|
|
$this->assertTrue($header instanceof Header); |
|
89
|
|
|
$this->assertEquals(27, $position); |
|
90
|
|
|
$this->assertEquals(2, \count($header->getElements())); |
|
91
|
|
|
|
|
92
|
|
|
// No header to parse |
|
93
|
|
|
$this->assertEquals('Page', (string) $header->get('Type')); |
|
94
|
|
|
$content = 'foo'; |
|
95
|
|
|
$position = 0; |
|
96
|
|
|
$header = Header::parse($content, $document, $position); |
|
97
|
|
|
|
|
98
|
|
|
$this->assertTrue($header instanceof Header); |
|
99
|
|
|
$this->assertEquals(0, $position); |
|
100
|
|
|
$this->assertEquals(0, \count($header->getElements())); |
|
101
|
|
|
|
|
102
|
|
|
$position = 0; |
|
103
|
|
|
$content = "<</CreationDate(D:20100309184803+01'00')/Author(Utilisateur)/Creator(PScript5.dll Version 5.2.2)/Producer(Acrobat Distiller 7.0.5 \(Windows\))/ModDate(D:20100310104810+01'00')/Title(Microsoft Word - CLEMI.docx)>>"; |
|
104
|
|
|
Header::parse($content, $document, $position); |
|
105
|
|
|
$this->assertEquals(212, $position); |
|
106
|
|
|
|
|
107
|
|
|
$position = 0; |
|
108
|
|
|
$content = '[5 0 R ] foo'; |
|
109
|
|
|
$header = Header::parse($content, $document, $position); |
|
110
|
|
|
$this->assertEquals(8, $position); |
|
111
|
|
|
$this->assertEquals(1, \count($header->getElements())); |
|
112
|
|
|
} |
|
113
|
|
|
|
|
114
|
|
|
public function testGetElements(): void |
|
115
|
|
|
{ |
|
116
|
|
|
$document = $this->getDocumentInstance(); |
|
117
|
|
|
|
|
118
|
|
|
$content = '<</Type/Page/Subtype/Text>>foo'; |
|
119
|
|
|
$position = 0; |
|
120
|
|
|
$header = Header::parse($content, $document, $position); |
|
121
|
|
|
|
|
122
|
|
|
$elements = $header->getElements(); |
|
123
|
|
|
$this->assertEquals(2, \count($elements)); |
|
124
|
|
|
$this->assertTrue(current($elements) instanceof ElementName); |
|
125
|
|
|
|
|
126
|
|
|
$types = $header->getElementTypes(); |
|
127
|
|
|
$this->assertTrue(\is_array($types)); |
|
128
|
|
|
$this->assertEquals(ElementName::class, $types['Type']); |
|
129
|
|
|
$this->assertEquals(ElementName::class, $types['Subtype']); |
|
130
|
|
|
} |
|
131
|
|
|
|
|
132
|
|
|
public function testHas(): void |
|
133
|
|
|
{ |
|
134
|
|
|
$document = $this->getDocumentInstance(); |
|
135
|
|
|
|
|
136
|
|
|
$content = '<</Type/Page/SubType/Text/Font 5 0 R>>foo'; |
|
137
|
|
|
$position = 0; |
|
138
|
|
|
$header = Header::parse($content, $document, $position); |
|
139
|
|
|
|
|
140
|
|
|
$this->assertTrue($header->has('Type')); |
|
141
|
|
|
$this->assertTrue($header->has('SubType')); |
|
142
|
|
|
$this->assertTrue($header->has('Font')); |
|
143
|
|
|
$this->assertFalse($header->has('Text')); |
|
144
|
|
|
} |
|
145
|
|
|
|
|
146
|
|
|
public function testGet(): void |
|
147
|
|
|
{ |
|
148
|
|
|
$document = $this->getDocumentInstance(); |
|
149
|
|
|
|
|
150
|
|
|
$content = '<</Type/Page/SubType/Text/Font 5 0 R/Resources 8 0 R>>foo'; |
|
151
|
|
|
$position = 0; |
|
152
|
|
|
$header = Header::parse($content, $document, $position); |
|
153
|
|
|
$object = new Page($document, $header); |
|
154
|
|
|
$document->setObjects(['5_0' => $object]); |
|
155
|
|
|
|
|
156
|
|
|
$this->assertTrue($header->get('Type') instanceof ElementName); |
|
157
|
|
|
$this->assertTrue($header->get('SubType') instanceof ElementName); |
|
158
|
|
|
$this->assertTrue($header->get('Font') instanceof Page); |
|
159
|
|
|
$this->assertTrue($header->get('Image') instanceof ElementMissing); |
|
160
|
|
|
$this->assertTrue($header->get('Resources') instanceof ElementMissing); |
|
161
|
|
|
|
|
162
|
|
|
/** |
|
163
|
|
|
* A double forward slash in the header's content results in a falsy element |
|
164
|
|
|
* that should be parsed to ElementMissing instead. |
|
165
|
|
|
* |
|
166
|
|
|
* @see https://github.com/smalot/pdfparser/pull/525 |
|
167
|
|
|
*/ |
|
168
|
|
|
$content = '<</Type/Page/SubType//Text>>foo'; |
|
169
|
|
|
$position = 0; |
|
170
|
|
|
$header = Header::parse($content, $document, $position); |
|
171
|
|
|
|
|
172
|
|
|
$this->assertTrue($header->get('SubType') instanceof ElementMissing); |
|
173
|
|
|
} |
|
174
|
|
|
|
|
175
|
|
|
public function testResolveXRef(): void |
|
176
|
|
|
{ |
|
177
|
|
|
$document = $this->getDocumentInstance(); |
|
178
|
|
|
$content = '<</Type/Page/SubType/Text/Font 5 0 R/Resources 8 0 R>>foo'; |
|
179
|
|
|
$position = 0; |
|
180
|
|
|
$header = Header::parse($content, $document, $position); |
|
181
|
|
|
$object = new Page($document, $header); |
|
182
|
|
|
$document->setObjects(['5_0' => $object]); |
|
183
|
|
|
|
|
184
|
|
|
$this->assertTrue($header->get('Font') instanceof PDFObject); |
|
185
|
|
|
|
|
186
|
|
|
$header = $header->get('Resources'); |
|
187
|
|
|
$this->assertTrue($header instanceof ElementMissing); |
|
188
|
|
|
} |
|
189
|
|
|
} |
|
190
|
|
|
|
smalot /
pdfparser
