1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* @file This file is part of the PdfParser library. |
5
|
|
|
* |
6
|
|
|
* @author Konrad Abicht <[email protected]> |
7
|
|
|
* @date 2020-06-01 |
8
|
|
|
* |
9
|
|
|
* @author Sébastien MALOT <[email protected]> |
10
|
|
|
* @date 2017-01-03 |
11
|
|
|
* |
12
|
|
|
* @license LGPLv3 |
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 Tests\Smalot\PdfParser\Integration; |
34
|
|
|
|
35
|
|
|
use Exception; |
36
|
|
|
use Smalot\PdfParser\Document; |
37
|
|
|
use Smalot\PdfParser\Parser; |
38
|
|
|
use Smalot\PdfParser\XObject\Image; |
39
|
|
|
use Tests\Smalot\PdfParser\TestCase; |
40
|
|
|
|
41
|
|
|
class ParserTest extends TestCase |
42
|
|
|
{ |
43
|
|
|
public function setUp() |
44
|
|
|
{ |
45
|
|
|
parent::setUp(); |
46
|
|
|
|
47
|
|
|
$this->fixture = new Parser(); |
48
|
|
|
} |
49
|
|
|
|
50
|
|
|
public function testParseFile() |
51
|
|
|
{ |
52
|
|
|
$directory = $this->rootDir.'/samples/bugs'; |
53
|
|
|
|
54
|
|
|
if (is_dir($directory)) { |
55
|
|
|
$files = scandir($directory); |
56
|
|
|
|
57
|
|
|
foreach ($files as $file) { |
58
|
|
|
if (preg_match('/^.*\.pdf$/i', $file)) { |
59
|
|
|
try { |
60
|
|
|
$document = $this->fixture->parseFile($directory.'/'.$file); |
61
|
|
|
$pages = $document->getPages(); |
62
|
|
|
$this->assertTrue(0 < \count($pages)); |
63
|
|
|
|
64
|
|
|
foreach ($pages as $page) { |
65
|
|
|
$content = $page->getText(); |
66
|
|
|
$this->assertTrue(0 < \strlen($content)); |
67
|
|
|
} |
68
|
|
|
} catch (Exception $e) { |
69
|
|
|
if ( |
70
|
|
|
'Secured pdf file are currently not supported.' !== $e->getMessage() |
71
|
|
|
&& 0 != strpos($e->getMessage(), 'TCPDF_PARSER') |
72
|
|
|
) { |
73
|
|
|
throw $e; |
74
|
|
|
} |
75
|
|
|
} |
76
|
|
|
} |
77
|
|
|
} |
78
|
|
|
} |
79
|
|
|
} |
80
|
|
|
|
81
|
|
|
/** |
82
|
|
|
* Test that issue related pdf can now be parsed |
83
|
|
|
* |
84
|
|
|
* @see https://github.com/smalot/pdfparser/issues/267 |
85
|
|
|
*/ |
86
|
|
|
public function testIssue267() |
87
|
|
|
{ |
88
|
|
|
$filename = $this->rootDir.'/samples/bugs/Issue267_array_access_on_int.pdf'; |
89
|
|
|
|
90
|
|
|
$document = $this->fixture->parseFile($filename); |
91
|
|
|
|
92
|
|
|
$this->assertEquals(Image::class, \get_class($document->getObjectById('128_0'))); |
93
|
|
|
$this->assertStringContainsString('4 von 4', $document->getText()); |
94
|
|
|
} |
95
|
|
|
|
96
|
|
|
public function docProvider() |
97
|
|
|
{ |
98
|
|
|
return [ |
99
|
|
|
'adobe-compressed-pdf16.pdf' => ['adobe-compressed-pdf16.pdf'], |
100
|
|
|
'adobe-converted-pdf16.pdf' => ['adobe-converted-pdf16.pdf'], |
101
|
|
|
'google-docs-export-pdf15.pdf' => ['google-docs-export-pdf15.pdf'], |
102
|
|
|
]; |
103
|
|
|
} |
104
|
|
|
|
105
|
|
|
/** |
106
|
|
|
* @dataProvider docProvider |
107
|
|
|
*/ |
108
|
|
|
public function testParserForDifferentSource($testDoc) |
109
|
|
|
{ |
110
|
|
|
$filename = $this->rootDir."/samples/$testDoc"; |
111
|
|
|
|
112
|
|
|
/** @var Document $document */ |
113
|
|
|
$document = $this->fixture->parseFile($filename); |
114
|
|
|
|
115
|
|
|
$this->assertStringContainsString('Test document', $document->getText()); |
116
|
|
|
$this->assertStringContainsString('Test mono', $document->getText()); |
117
|
|
|
|
118
|
|
|
$i = 0; |
119
|
|
|
foreach ($document->getObjects() as $object) { |
120
|
|
|
if (Image::class === \get_class($object)) { |
121
|
|
|
++$i; |
122
|
|
|
} |
123
|
|
|
} |
124
|
|
|
$this->assertEquals(1, $i, 'Asserting has exactly one image'); |
125
|
|
|
} |
126
|
|
|
|
127
|
|
|
/** |
128
|
|
|
* @see https://github.com/smalot/pdfparser/issues/201 |
129
|
|
|
*/ |
130
|
|
|
public function testIssue201() |
131
|
|
|
{ |
132
|
|
|
$filename = $this->rootDir.'/samples/bugs/issue201.pdf'; |
133
|
|
|
|
134
|
|
|
/** @var Document $document */ |
135
|
|
|
$document = $this->fixture->parseFile($filename); |
136
|
|
|
|
137
|
|
|
$this->assertStringContainsString('The pdf995 suite of products', $document->getText()); |
138
|
|
|
} |
139
|
|
|
} |
140
|
|
|
|