1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
|
<?php
/////////////////////////////////////////////////////////////////
/// getID3() by James Heinrich <info@getid3.org> //
// available at https://github.com/JamesHeinrich/getID3 //
// or https://www.getid3.org //
// or http://getid3.sourceforge.net //
// see readme.txt for more details //
/////////////////////////////////////////////////////////////////
// //
// module.misc.pdf.php //
// module for analyzing PDF files //
// dependencies: NONE //
// ///
/////////////////////////////////////////////////////////////////
if (!defined('GETID3_INCLUDEPATH')) { // prevent path-exposing attacks that access modules directly on public webservers
exit;
}
class getid3_pdf extends getid3_handler
{
public $returnXREF = false; // return full details of PDF Cross-Reference Table (XREF)
/**
* @return bool
*/
public function Analyze() {
$info = &$this->getid3->info;
$this->fseek(0);
if (preg_match('#^%PDF-([0-9\\.]+)$#', rtrim($this->fgets()), $matches)) {
$info['pdf']['header']['version'] = floatval($matches[1]);
$info['fileformat'] = 'pdf';
// the PDF Cross-Reference Table (XREF) is located near the end of the file
// the starting offset is specified in the penultimate section, on the two lines just before "%%EOF"
// the first line is "startxref", the second line is the byte offset of the XREF.
// We know the length of "%%EOF" and "startxref", but the offset could be 2-10 bytes,
// and we're not sure if the line ends are one or two bytes, so we might find "startxref" as little as 18(?) bytes
// from EOF, but it could 30 bytes, so we start 40 bytes back just to be safe and do a search for the data we want.
$this->fseek(-40, SEEK_END);
if (preg_match('#[\r\n]startxref[ \r\n]+([0-9]+)[ \r\n]+#', $this->fread(40), $matches)) {
$info['pdf']['trailer']['startxref'] = intval($matches[1]);
$this->parseXREF($info['pdf']['trailer']['startxref']);
if (!empty($info['pdf']['xref']['offset'])) {
while (!$this->feof() && (max(array_keys($info['pdf']['xref']['offset'])) > $info['pdf']['xref']['count'])) {
// suspect that there may be another XREF entry somewhere in the file, brute-force scan for it
/*
// starting at last known entry of main XREF table
$this->fseek(max($info['pdf']['xref']['offset']));
*/
// starting at the beginning of the file
$this->fseek(0);
while (!$this->feof()) {
$XREFoffset = $this->ftell();
if (rtrim($this->fgets()) == 'xref') {
if (empty($info['pdf']['xref']['xref_offsets']) || !in_array($XREFoffset, $info['pdf']['xref']['xref_offsets'])) {
$this->parseXREF($XREFoffset);
break;
}
}
}
}
foreach ($info['pdf']['xref']['offset'] as $objectNumber => $offset) {
if ($info['pdf']['xref']['entry'][$objectNumber] == 'f') {
// "free" object means "deleted", ignore
continue;
}
$this->fseek($offset);
$line = rtrim($this->fgets());
if (preg_match('#^'.$objectNumber.' ([0-9]+) obj#', $line, $matches)) {
if (strlen($line) > strlen($matches[0])) {
// object header line not actually on its own line, rewind file pointer to start reading data
$this->fseek($offset + strlen($matches[0]));
}
$objectData = '';
while (true) {
$line = $this->fgets();
if (rtrim($line) == 'endobj') {
break;
}
$objectData .= $line;
}
if (preg_match('#^<<[\r\n\s]*(/Type|/Pages|/Parent [0-9]+ [0-9]+ [A-Z]|/Count [0-9]+|/Kids *\\[[0-9A-Z ]+\\]|[\r\n\s])+[\r\n\s]*>>#', $objectData, $matches)) {
if (preg_match('#/Count ([0-9]+)#', $objectData, $matches)) {
$info['pdf']['pages'] = (int) $matches[1];
break; // for now this is the only data we're looking for in the PDF not need to loop through every object in the file (and a large PDF may contain MANY objects). And it MAY be possible that there are other objects elsewhere in the file that define additional (or removed?) pages
}
}
} else {
$this->error('Unexpected structure "'.$line.'" at offset '.$offset);
break;
}
}
if (!$this->returnXREF) {
unset($info['pdf']['xref']['offset'], $info['pdf']['xref']['generation'], $info['pdf']['xref']['entry']);
}
} else {
$this->error('Did not find "xref" at offset '.$info['pdf']['trailer']['startxref']);
}
} else {
$this->error('Did not find "startxref" in the last 40 bytes of the PDF');
}
$this->warning('PDF parsing incomplete in this version of getID3() ['.$this->getid3->version().']');
return true;
}
$this->error('Did not find "%PDF" at the beginning of the PDF');
return false;
}
/**
* @return bool
*/
private function parseXREF($XREFoffset) {
$info = &$this->getid3->info;
$this->fseek($XREFoffset);
if (rtrim($this->fgets()) == 'xref') {
$info['pdf']['xref']['xref_offsets'][$XREFoffset] = $XREFoffset;
list($firstObjectNumber, $XREFcount) = explode(' ', rtrim($this->fgets()));
$XREFcount = (int) $XREFcount;
$info['pdf']['xref']['count'] = $XREFcount + (!empty($info['pdf']['xref']['count']) ? $info['pdf']['xref']['count'] : 0);
for ($i = 0; $i < $XREFcount; $i++) {
$line = rtrim($this->fgets());
if (preg_match('#^([0-9]+) ([0-9]+) ([nf])$#', $line, $matches)) {
$info['pdf']['xref']['offset'][($firstObjectNumber + $i)] = (int) $matches[1];
$info['pdf']['xref']['generation'][($firstObjectNumber + $i)] = (int) $matches[2];
$info['pdf']['xref']['entry'][($firstObjectNumber + $i)] = $matches[3];
} else {
$this->error('failed to parse XREF entry #'.$i.' in XREF table at offset '.$XREFoffset);
return false;
}
}
sort($info['pdf']['xref']['xref_offsets']);
return true;
}
$this->warning('failed to find expected XREF structure at offset '.$XREFoffset);
return false;
}
}
|
