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\Parser; |
37
|
|
|
use Smalot\PdfParser\PDFObject; |
38
|
|
|
use Tests\Smalot\PdfParser\TestCase; |
39
|
|
|
|
40
|
|
|
class PDFObjectTest extends TestCase |
41
|
|
|
{ |
42
|
|
|
const TYPE = 't'; |
43
|
|
|
|
44
|
|
|
const OPERATOR = 'o'; |
45
|
|
|
|
46
|
|
|
const COMMAND = 'c'; |
47
|
|
|
|
48
|
|
|
protected function getPdfObjectInstance($document) |
49
|
|
|
{ |
50
|
|
|
return new PDFObject($document); |
51
|
|
|
} |
52
|
|
|
|
53
|
|
|
public function testGetCommandsText() |
54
|
|
|
{ |
55
|
|
|
$content = "/R14 30 Tf 0.999016 0 0 1 137.4 |
56
|
|
|
342.561 Tm |
57
|
|
|
[(A)-168.854( BC D)-220.905(\\(E\\))20.905<20>] |
58
|
|
|
TJ /R14 17.16 Tf <20> Tj |
59
|
|
|
0.999014 0 0 1 336.84 319.161 Tm T* ( \x00m)Tj |
60
|
|
|
/R14 20.04 Tf |
61
|
|
|
ET Q |
62
|
|
|
q -124.774 124.127 5.64213 5.67154 930.307 4436.95 cm |
63
|
|
|
BI"; |
64
|
|
|
|
65
|
|
|
$offset = 0; |
66
|
|
|
$parts = $this->getPdfObjectInstance(new Document())->getCommandsText($content, $offset); |
67
|
|
|
$reference = [ |
68
|
|
|
[ |
69
|
|
|
self::TYPE => '/', |
70
|
|
|
self::OPERATOR => 'Tf', |
71
|
|
|
self::COMMAND => 'R14 30', |
72
|
|
|
], |
73
|
|
|
[ |
74
|
|
|
self::TYPE => '', |
75
|
|
|
self::OPERATOR => 'Tm', |
76
|
|
|
self::COMMAND => "0.999016 0 0 1 137.4\n342.561", |
77
|
|
|
], |
78
|
|
|
[ |
79
|
|
|
self::TYPE => '[', |
80
|
|
|
self::OPERATOR => 'TJ', |
81
|
|
|
self::COMMAND => [ |
82
|
|
|
[ |
83
|
|
|
self::TYPE => '(', |
84
|
|
|
self::OPERATOR => '', |
85
|
|
|
self::COMMAND => 'A', |
86
|
|
|
], |
87
|
|
|
[ |
88
|
|
|
self::TYPE => 'n', |
89
|
|
|
self::OPERATOR => '', |
90
|
|
|
self::COMMAND => '-168.854', |
91
|
|
|
], |
92
|
|
|
[ |
93
|
|
|
self::TYPE => '(', |
94
|
|
|
self::OPERATOR => '', |
95
|
|
|
self::COMMAND => ' BC D', |
96
|
|
|
], |
97
|
|
|
[ |
98
|
|
|
self::TYPE => 'n', |
99
|
|
|
self::OPERATOR => '', |
100
|
|
|
self::COMMAND => '-220.905', |
101
|
|
|
], |
102
|
|
|
[ |
103
|
|
|
self::TYPE => '(', |
104
|
|
|
self::OPERATOR => '', |
105
|
|
|
self::COMMAND => '\\(E\\)', |
106
|
|
|
], |
107
|
|
|
[ |
108
|
|
|
self::TYPE => 'n', |
109
|
|
|
self::OPERATOR => '', |
110
|
|
|
self::COMMAND => '20.905', |
111
|
|
|
], |
112
|
|
|
[ |
113
|
|
|
self::TYPE => '<', |
114
|
|
|
self::OPERATOR => '', |
115
|
|
|
self::COMMAND => '20', |
116
|
|
|
], |
117
|
|
|
], |
118
|
|
|
], |
119
|
|
|
[ |
120
|
|
|
self::TYPE => '/', |
121
|
|
|
self::OPERATOR => 'Tf', |
122
|
|
|
self::COMMAND => 'R14 17.16', |
123
|
|
|
], |
124
|
|
|
[ |
125
|
|
|
self::TYPE => '<', |
126
|
|
|
self::OPERATOR => 'Tj', |
127
|
|
|
self::COMMAND => '20', |
128
|
|
|
], |
129
|
|
|
[ |
130
|
|
|
self::TYPE => '', |
131
|
|
|
self::OPERATOR => 'Tm', |
132
|
|
|
self::COMMAND => '0.999014 0 0 1 336.84 319.161', |
133
|
|
|
], |
134
|
|
|
[ |
135
|
|
|
self::TYPE => '', |
136
|
|
|
self::OPERATOR => 'T*', |
137
|
|
|
self::COMMAND => '', |
138
|
|
|
], |
139
|
|
|
[ |
140
|
|
|
self::TYPE => '(', |
141
|
|
|
self::OPERATOR => 'Tj', |
142
|
|
|
self::COMMAND => " \x00m", |
143
|
|
|
], |
144
|
|
|
[ |
145
|
|
|
self::TYPE => '/', |
146
|
|
|
self::OPERATOR => 'Tf', |
147
|
|
|
self::COMMAND => 'R14 20.04', |
148
|
|
|
], |
149
|
|
|
]; |
150
|
|
|
|
151
|
|
|
$this->assertEquals($parts, $reference); |
152
|
|
|
$this->assertEquals(172, $offset); |
153
|
|
|
} |
154
|
|
|
|
155
|
|
|
public function testCleanContent() |
156
|
|
|
{ |
157
|
|
|
$content = '/Shape <</MCID << /Font<8>>> BT >>BDC |
158
|
|
|
Q |
159
|
|
|
/CS0 cs 1 1 0 scn |
160
|
|
|
1 i |
161
|
|
|
/GS0 gs |
162
|
|
|
BT |
163
|
|
|
/TT0 1 Tf |
164
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
165
|
|
|
(Modificatio[ns] au \\(14\\) septembre 2009 ET 2010)Tj |
166
|
|
|
EMC |
167
|
|
|
(ABC) Tj |
168
|
|
|
|
169
|
|
|
[ (a)-4.5(b)6(c)8.8 ( fsdfsdfsdf[]sd) ] TD |
170
|
|
|
|
171
|
|
|
ET |
172
|
|
|
/Shape <</MCID 2 >>BDC |
173
|
|
|
q |
174
|
|
|
0.03 841'; |
175
|
|
|
|
176
|
|
|
$expected = '_____________________________________ |
177
|
|
|
Q |
178
|
|
|
/CS0 cs 1 1 0 scn |
179
|
|
|
1 i |
180
|
|
|
/GS0 gs |
181
|
|
|
BT |
182
|
|
|
/TT0 1 Tf |
183
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
184
|
|
|
(________________________________________________)Tj |
185
|
|
|
___ |
186
|
|
|
(___) Tj |
187
|
|
|
|
188
|
|
|
[_____________________________________] TD |
189
|
|
|
|
190
|
|
|
ET |
191
|
|
|
______________________ |
192
|
|
|
q |
193
|
|
|
0.03 841'; |
194
|
|
|
|
195
|
|
|
$cleaned = $this->getPdfObjectInstance(new Document())->cleanContent($content, '_'); |
196
|
|
|
|
197
|
|
|
$this->assertEquals($cleaned, $expected); |
198
|
|
|
} |
199
|
|
|
|
200
|
|
|
public function testGetSectionText() |
201
|
|
|
{ |
202
|
|
|
$content = '/Shape <</MCID 1 >>BDC |
203
|
|
|
Q |
204
|
|
|
/CS0 cs 1 1 0 scn |
205
|
|
|
1 i |
206
|
|
|
/GS0 gs |
207
|
|
|
BT |
208
|
|
|
/TT0 1 Tf |
209
|
|
|
0.0007 Tc 0.0018 Tw 0 Ts 100 Tz 0 Tr 24 0 0 24 51.3 639.26025 Tm |
210
|
|
|
(Mod BT atio[ns] au \\(14\\) septembre 2009 ET 2010)Tj |
211
|
|
|
EMC |
212
|
|
|
(ABC) Tj |
213
|
|
|
|
214
|
|
|
[ (a)-4.5(b) 6(c)8.8 ( fsdfsdfsdf[ sd) ] TD |
215
|
|
|
|
216
|
|
|
ET |
217
|
|
|
/Shape <</MCID [BT] >>BDC BT /TT1 1.5 Tf (BT )Tj ET |
218
|
|
|
q |
219
|
|
|
0.03 841'; |
220
|
|
|
|
221
|
|
|
$sections = $this->getPdfObjectInstance(new Document())->getSectionsText($content); |
222
|
|
|
|
223
|
|
|
$this->assertEquals( |
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
|
|
|
q'], |
232
|
|
|
$sections |
233
|
|
|
); |
234
|
|
|
} |
235
|
|
|
|
236
|
|
|
public function testGetFontSpaceLimitOnNull() |
237
|
|
|
{ |
238
|
|
|
$parser = new Parser(); |
239
|
|
|
|
240
|
|
|
$filename = __DIR__.'/../../samples/bugs/pr_403.pdf'; |
241
|
|
|
$pdf = $parser->parseFile($filename); |
242
|
|
|
$pages = $pdf->getPages(); |
243
|
|
|
|
244
|
|
|
foreach ($pages as $index => $page) |
245
|
|
|
{ |
246
|
|
|
$text = $page->getTextXY(181.56, 816.95, 5); //<- throw Call to a member function getFontSpaceLimit() on null |
|
|
|
|
247
|
|
|
} |
248
|
|
|
} |
249
|
|
|
} |
250
|
|
|
|