|
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\Document; |
|
40
|
|
|
use Smalot\PdfParser\Parser; |
|
41
|
|
|
|
|
42
|
|
|
/** |
|
43
|
|
|
* Document related tests which are related to certain issues. |
|
44
|
|
|
*/ |
|
45
|
|
|
class DocumentIssueFocusTest extends TestCase |
|
46
|
|
|
{ |
|
47
|
|
|
/** |
|
48
|
|
|
* Tests getText method without a given page limit. |
|
49
|
|
|
* |
|
50
|
|
|
* @see https://github.com/smalot/pdfparser/pull/562 |
|
51
|
|
|
*/ |
|
52
|
|
|
public function testGetTextNoPageLimit(): void |
|
53
|
|
|
{ |
|
54
|
|
|
$document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/Issue331.pdf'); |
|
55
|
|
|
|
|
56
|
|
|
self::assertStringContainsString('Medeni Usul ve İcra İflas Hukuku', $document->getText()); |
|
57
|
|
|
} |
|
58
|
|
|
|
|
59
|
|
|
/** |
|
60
|
|
|
* Tests getText method with a given page limit. |
|
61
|
|
|
* |
|
62
|
|
|
* @see https://github.com/smalot/pdfparser/pull/562 |
|
63
|
|
|
*/ |
|
64
|
|
|
public function testGetTextWithPageLimit(): void |
|
65
|
|
|
{ |
|
66
|
|
|
$document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/Issue331.pdf'); |
|
67
|
|
|
|
|
68
|
|
|
// given text is on page 2, it has to be ignored because of that |
|
69
|
|
|
self::assertStringNotContainsString('Medeni Usul ve İcra İflas Hukuku', $document->getText(1)); |
|
70
|
|
|
} |
|
71
|
|
|
|
|
72
|
|
|
/** |
|
73
|
|
|
* Tests extraction of XMP Metadata vs. getHeader() data. |
|
74
|
|
|
* |
|
75
|
|
|
* @see https://github.com/smalot/pdfparser/pull/606 |
|
76
|
|
|
*/ |
|
77
|
|
|
public function testExtractXMPMetadata(): void |
|
78
|
|
|
{ |
|
79
|
|
|
$document = (new Parser())->parseFile($this->rootDir.'/samples/XMP_Metadata.pdf'); |
|
80
|
|
|
|
|
81
|
|
|
$details = $document->getDetails(); |
|
82
|
|
|
|
|
83
|
|
|
// Test that the dc:title data was extracted from the XMP |
|
84
|
|
|
// Metadata. |
|
85
|
|
|
self::assertStringContainsString("Enhance PdfParser\u{2019}s Metadata Capabilities", $details['dc:title']); |
|
86
|
|
|
} |
|
87
|
|
|
|
|
88
|
|
|
/** |
|
89
|
|
|
* Tests PDFDocEncoding decode of Document Properties |
|
90
|
|
|
* |
|
91
|
|
|
* @see https://github.com/smalot/pdfparser/issues/609 |
|
92
|
|
|
*/ |
|
93
|
|
|
public function testPDFDocEncodingDecode(): void |
|
94
|
|
|
{ |
|
95
|
|
|
$document = (new Parser())->parseFile($this->rootDir.'/samples/bugs/Issue609.pdf'); |
|
96
|
|
|
|
|
97
|
|
|
$details = $document->getDetails(); |
|
98
|
|
|
|
|
99
|
|
|
// These test that Adobe-inserted \r are removed from a UTF-8 |
|
100
|
|
|
// escaped metadata string, and the surrounding characters are |
|
101
|
|
|
// repaired |
|
102
|
|
|
$testKeywords = '˘ˇˆ˙˝˛˞˜•†‡…—–ƒ⁄‹›−‰„“”‘’‚™fiflŁŒŠŸŽıłœšž€¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'; |
|
103
|
|
|
self::assertStringContainsString($testKeywords, $details['Keywords']); |
|
104
|
|
|
|
|
105
|
|
|
$testKeywords = 'added line-feeds often destroy multibyte characters'; |
|
106
|
|
|
self::assertStringContainsString($testKeywords, $details['Keywords']); |
|
107
|
|
|
|
|
108
|
|
|
// This tests that the PDFDocEncoding characters that differ |
|
109
|
|
|
// from CP-1252 are decoded to their correct UTF-8 code points |
|
110
|
|
|
// as well as removing \r line-feeds |
|
111
|
|
|
$testSubject = '•†‡…—–ƒ⁄‹›−‰„“”‘’‚™ŁŒŠŸŽıłœšž'; |
|
112
|
|
|
self::assertStringContainsString($testSubject, $details['Subject']); |
|
113
|
|
|
} |
|
114
|
|
|
} |
|
115
|
|
|
|
smalot /
pdfparser
