|
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 Test\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
|
|
|
* Parsing certain PDFs may lead to following notices: |
|
83
|
|
|
* |
|
84
|
|
|
* Notice: Trying to access array offset on value of type int |
|
85
|
|
|
* |
|
86
|
|
|
* and to an exception: |
|
87
|
|
|
* |
|
88
|
|
|
* Missing catalog. |
|
89
|
|
|
* |
|
90
|
|
|
* @see https://github.com/smalot/pdfparser/issues/267 |
|
91
|
|
|
*/ |
|
92
|
|
|
public function testIssue267() |
|
93
|
|
|
{ |
|
94
|
|
|
$this->expectException(Exception::class); |
|
95
|
|
|
$this->expectExceptionMessage('Missing catalog.'); |
|
96
|
|
|
|
|
97
|
|
|
$filename = $this->rootDir.'/samples/bugs/Issue267_array_access_on_int.pdf'; |
|
98
|
|
|
|
|
99
|
|
|
$document = $this->fixture->parseFile($filename); |
|
100
|
|
|
|
|
101
|
|
|
// triggers the exception |
|
102
|
|
|
$document->getPages(); |
|
103
|
|
|
} |
|
104
|
|
|
|
|
105
|
|
|
public function docProvider() |
|
106
|
|
|
{ |
|
107
|
|
|
return [ |
|
108
|
|
|
'adobe-compressed-pdf16.pdf' => ['adobe-compressed-pdf16.pdf'], |
|
109
|
|
|
'adobe-converted-pdf16.pdf' => ['adobe-converted-pdf16.pdf'], |
|
110
|
|
|
'google-docs-export-pdf15.pdf' => ['google-docs-export-pdf15.pdf'], |
|
111
|
|
|
]; |
|
112
|
|
|
} |
|
113
|
|
|
|
|
114
|
|
|
/** |
|
115
|
|
|
* @dataProvider docProvider |
|
116
|
|
|
*/ |
|
117
|
|
|
public function testParserForDifferentSource($testDoc) |
|
118
|
|
|
{ |
|
119
|
|
|
$filename = $this->rootDir."/samples/$testDoc"; |
|
120
|
|
|
|
|
121
|
|
|
/** @var Document $document */ |
|
122
|
|
|
$document = $this->fixture->parseFile($filename); |
|
123
|
|
|
|
|
124
|
|
|
$this->assertStringContainsString('Test document', $document->getText()); |
|
125
|
|
|
$this->assertStringContainsString('Test mono', $document->getText()); |
|
126
|
|
|
|
|
127
|
|
|
$i = 0; |
|
128
|
|
|
foreach ($document->getObjects() as $object) { |
|
129
|
|
|
if (Image::class === \get_class($object)) { |
|
130
|
|
|
++$i; |
|
131
|
|
|
} |
|
132
|
|
|
} |
|
133
|
|
|
$this->assertEquals(1, $i, 'Asserting has exactly one image'); |
|
134
|
|
|
} |
|
135
|
|
|
|
|
136
|
|
|
public function testIssue201() |
|
137
|
|
|
{ |
|
138
|
|
|
$filename = $this->rootDir.'/samples/bugs/issue201.pdf'; |
|
139
|
|
|
|
|
140
|
|
|
/** @var Document $document */ |
|
141
|
|
|
$document = $this->fixture->parseFile($filename); |
|
142
|
|
|
|
|
143
|
|
|
$this->assertStringContainsString('The pdf995 suite of products', $document->getText()); |
|
144
|
|
|
} |
|
145
|
|
|
} |
|
146
|
|
|
|
smalot /
pdfparser
