|
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 Smalot\PdfParser\Document; |
|
36
|
|
|
use Smalot\PdfParser\PDFObject; |
|
37
|
|
|
use Tests\Smalot\PdfParser\TestCase; |
|
38
|
|
|
|
|
39
|
|
|
class PDFObjectTest extends TestCase |
|
40
|
|
|
{ |
|
41
|
|
|
const TYPE = 't'; |
|
42
|
|
|
|
|
43
|
|
|
const OPERATOR = 'o'; |
|
44
|
|
|
|
|
45
|
|
|
const COMMAND = 'c'; |
|
46
|
|
|
|
|
47
|
|
|
protected function getPdfObjectInstance($document): PDFObject |
|
48
|
|
|
{ |
|
49
|
|
|
return new PDFObject($document); |
|
50
|
|
|
} |
|
51
|
|
|
|
|
52
|
|
|
public function testGetCommandsText(): void |
|
53
|
|
|
{ |
|
54
|
|
|
$content = "/R14 30 Tf 0.999016 0 0 1 137.4 |
|
55
|
|
|
342.561 Tm |
|
56
|
|
|
[(A)-168.854( BC D)-220.905(\\(E\\))20.905<20>] |
|
57
|
|
|
TJ /R14 17.16 Tf <20> Tj |
|
58
|
|
|
0.999014 0 0 1 336.84 319.161 Tm T* ( \x00m)Tj |
|
59
|
|
|
/R14 20.04 Tf |
|
60
|
|
|
ET Q |
|
61
|
|
|
q -124.774 124.127 5.64213 5.67154 930.307 4436.95 cm |
|
62
|
|
|
BI"; |
|
63
|
|
|
|
|
64
|
|
|
$offset = 0; |
|
65
|
|
|
$parts = $this->getPdfObjectInstance(new Document())->getCommandsText($content, $offset); |
|
66
|
|
|
$reference = [ |
|
67
|
|
|
[ |
|
68
|
|
|
self::TYPE => '/', |
|
69
|
|
|
self::OPERATOR => 'Tf', |
|
70
|
|
|
self::COMMAND => 'R14 30', |
|
71
|
|
|
], |
|
72
|
|
|
[ |
|
73
|
|
|
self::TYPE => '', |
|
74
|
|
|
self::OPERATOR => 'Tm', |
|
75
|
|
|
self::COMMAND => "0.999016 0 0 1 137.4\n342.561", |
|
76
|
|
|
], |
|
77
|
|
|
[ |
|
78
|
|
|
self::TYPE => '[', |
|
79
|
|
|
self::OPERATOR => 'TJ', |
|
80
|
|
|
self::COMMAND => [ |
|
81
|
|
|
[ |
|
82
|
|
|
self::TYPE => '(', |
|
83
|
|
|
self::OPERATOR => '', |
|
84
|
|
|
self::COMMAND => 'A', |
|
85
|
|
|
], |
|
86
|
|
|
[ |
|
87
|
|
|
self::TYPE => 'n', |
|
88
|
|
|
self::OPERATOR => '', |
|
89
|
|
|
self::COMMAND => '-168.854', |
|
90
|
|
|
], |
|
91
|
|
|
[ |
|
92
|
|
|
self::TYPE => '(', |
|
93
|
|
|
self::OPERATOR => '', |
|
94
|
|
|
self::COMMAND => ' BC D', |
|
95
|
|
|
], |
|
96
|
|
|
[ |
|
97
|
|
|
self::TYPE => 'n', |
|
98
|
|
|
self::OPERATOR => '', |
|
99
|
|
|
self::COMMAND => '-220.905', |
|
100
|
|
|
], |
|
101
|
|
|
[ |
|
102
|
|
|
self::TYPE => '(', |
|
103
|
|
|
self::OPERATOR => '', |
|
104
|
|
|
self::COMMAND => '\\(E\\)', |
|
105
|
|
|
], |
|
106
|
|
|
[ |
|
107
|
|
|
self::TYPE => 'n', |
|
108
|
|
|
self::OPERATOR => '', |
|
109
|
|
|
self::COMMAND => '20.905', |
|
110
|
|
|
], |
|
111
|
|
|
[ |
|
112
|
|
|
self::TYPE => '<', |
|
113
|
|
|
self::OPERATOR => '', |
|
114
|
|
|
self::COMMAND => '20', |
|
115
|
|
|
], |
|
116
|
|
|
], |
|
117
|
|
|
], |
|
118
|
|
|
[ |
|
119
|
|
|
self::TYPE => '/', |
|
120
|
|
|
self::OPERATOR => 'Tf', |
|
121
|
|
|
self::COMMAND => 'R14 17.16', |
|
122
|
|
|
], |
|
123
|
|
|
[ |
|
124
|
|
|
self::TYPE => '<', |
|
125
|
|
|
self::OPERATOR => 'Tj', |
|
126
|
|
|
self::COMMAND => '20', |
|
127
|
|
|
], |
|
128
|
|
|
[ |
|
129
|
|
|
self::TYPE => '', |
|
130
|
|
|
self::OPERATOR => 'Tm', |
|
131
|
|
|
self::COMMAND => '0.999014 0 0 1 336.84 319.161', |
|
132
|
|
|
], |
|
133
|
|
|
[ |
|
134
|
|
|
self::TYPE => '', |
|
135
|
|
|
self::OPERATOR => 'T*', |
|
136
|
|
|
self::COMMAND => '', |
|
137
|
|
|
], |
|
138
|
|
|
[ |
|
139
|
|
|
self::TYPE => '(', |
|
140
|
|
|
self::OPERATOR => 'Tj', |
|
141
|
|
|
self::COMMAND => " \x00m", |
|
142
|
|
|
], |
|
143
|
|
|
[ |
|
144
|
|
|
self::TYPE => '/', |
|
145
|
|
|
self::OPERATOR => 'Tf', |
|
146
|
|
|
self::COMMAND => 'R14 20.04', |
|
147
|
|
|
], |
|
148
|
|
|
]; |
|
149
|
|
|
|
|
150
|
|
|
$this->assertEquals($parts, $reference); |
|
151
|
|
|
$this->assertEquals(172, $offset); |
|
152
|
|
|
} |
|
153
|
|
|
|
|
154
|
|
|
public function testCleanContent(): void |
|
155
|
|
|
{ |
|
156
|
|
|
$content = '/Shape <</MCID << /Font<8>>> BT >>BDC |
|
157
|
|
|
Q |
|
158
|
|
|
/CS0 cs 1 1 0 scn |
|
159
|
|
|
1 i |
|
160
|
|
|
/GS0 gs |
|
161
|
|
|
BT |
|
162
|
|
|
/TT0 1 Tf |
|
163
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
|
164
|
|
|
(Modificatio[ns] au \\(14\\) septembre 2009 ET 2010)Tj |
|
165
|
|
|
EMC |
|
166
|
|
|
(ABC) Tj |
|
167
|
|
|
|
|
168
|
|
|
[ (a)-4.5(b)6(c)8.8 ( fsdfsdfsdf[]sd) ] TD |
|
169
|
|
|
|
|
170
|
|
|
ET |
|
171
|
|
|
/Shape <</MCID 2 >>BDC |
|
172
|
|
|
q |
|
173
|
|
|
0.03 841'; |
|
174
|
|
|
|
|
175
|
|
|
$expected = '_____________________________________ |
|
176
|
|
|
Q |
|
177
|
|
|
/CS0 cs 1 1 0 scn |
|
178
|
|
|
1 i |
|
179
|
|
|
/GS0 gs |
|
180
|
|
|
BT |
|
181
|
|
|
/TT0 1 Tf |
|
182
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
|
183
|
|
|
(________________________________________________)Tj |
|
184
|
|
|
___ |
|
185
|
|
|
(___) Tj |
|
186
|
|
|
|
|
187
|
|
|
[_____________________________________] TD |
|
188
|
|
|
|
|
189
|
|
|
ET |
|
190
|
|
|
______________________ |
|
191
|
|
|
q |
|
192
|
|
|
0.03 841'; |
|
193
|
|
|
|
|
194
|
|
|
$cleaned = $this->getPdfObjectInstance(new Document())->cleanContent($content, '_'); |
|
195
|
|
|
|
|
196
|
|
|
$this->assertEquals($cleaned, $expected); |
|
197
|
|
|
} |
|
198
|
|
|
|
|
199
|
|
|
public function testGetSectionText(): void |
|
200
|
|
|
{ |
|
201
|
|
|
$content = '/Shape <</MCID 1 >>BDC |
|
202
|
|
|
Q |
|
203
|
|
|
/CS0 cs 1 1 0 scn |
|
204
|
|
|
1 i |
|
205
|
|
|
/GS0 gs |
|
206
|
|
|
BT |
|
207
|
|
|
/TT0 1 Tf |
|
208
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
|
209
|
|
|
(Mod BT atio[ns] au \\(14\\) septembre 2009 ET 2010)Tj |
|
210
|
|
|
EMC |
|
211
|
|
|
(ABC) Tj |
|
212
|
|
|
|
|
213
|
|
|
[ (a)-4.5(b) 6(c)8.8 ( fsdfsdfsdf[ sd) ] TD |
|
214
|
|
|
|
|
215
|
|
|
ET |
|
216
|
|
|
/Shape <</MCID [BT] >>BDC BT /TT1 1.5 Tf (BT )Tj ET |
|
217
|
|
|
q |
|
218
|
|
|
0.03 841'; |
|
219
|
|
|
|
|
220
|
|
|
$sections = $this->getPdfObjectInstance(new Document())->getSectionsText($content); |
|
221
|
|
|
|
|
222
|
|
|
$this->assertEquals( |
|
223
|
|
|
['Q |
|
224
|
|
|
/TT0 1 Tf |
|
225
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
|
226
|
|
|
(Mod BT atio[ns] au \(14\) septembre 2009 ET 2010)Tj |
|
227
|
|
|
EMC |
|
228
|
|
|
(ABC) Tj |
|
229
|
|
|
|
|
230
|
|
|
[ (a)-4.5(b) 6(c)8.8 ( fsdfsdfsdf[ sd) ] TD', '/TT1 1.5 Tf (BT )Tj'], |
|
231
|
|
|
$sections |
|
232
|
|
|
); |
|
233
|
|
|
} |
|
234
|
|
|
|
|
235
|
|
|
/** |
|
236
|
|
|
* Tests behavior with reversed chars instruction. |
|
237
|
|
|
* |
|
238
|
|
|
* @see: https://github.com/smalot/pdfparser/issues/398 |
|
239
|
|
|
*/ |
|
240
|
|
|
public function testReversedChars(): void |
|
241
|
|
|
{ |
|
242
|
|
|
$filename = $this->rootDir.'/samples/bugs/Issue398.pdf'; |
|
243
|
|
|
|
|
244
|
|
|
$parser = $this->getParserInstance(); |
|
245
|
|
|
$document = $parser->parseFile($filename); |
|
246
|
|
|
$pages = $document->getPages(); |
|
247
|
|
|
|
|
248
|
|
|
$this->assertStringContainsString('שלומי טסט', $pages[0]->getText()); |
|
249
|
|
|
} |
|
250
|
|
|
|
|
251
|
|
|
/** |
|
252
|
|
|
* Tests Tf commands are outside the text block |
|
253
|
|
|
* |
|
254
|
|
|
* @see: https://github.com/smalot/pdfparser/issues/542 |
|
255
|
|
|
*/ |
|
256
|
|
|
public function testIssue542(): void |
|
257
|
|
|
{ |
|
258
|
|
|
$filename = $this->rootDir.'/samples/bugs/Issue542.pdf'; |
|
259
|
|
|
|
|
260
|
|
|
$parser = $this->getParserInstance(); |
|
261
|
|
|
$document = $parser->parseFile($filename); |
|
262
|
|
|
$pages = $document->getPages(); |
|
263
|
|
|
|
|
264
|
|
|
$this->assertStringContainsString("Timbre imprimé sur laposte.frFRANCESD : 87000639942948A\nLettre verte \n\nMax 50g\nFRANCE ", $pages[0]->getText()); |
|
265
|
|
|
} |
|
266
|
|
|
} |
|
267
|
|
|
|