1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
namespace CHMLib; |
4
|
|
|
|
5
|
|
|
use Exception; |
6
|
|
|
use CHMLib\Reader\Reader; |
7
|
|
|
use CHMLib\Reader\StringReader; |
8
|
|
|
use CHMLib\Exception\UnexpectedHeaderException; |
9
|
|
|
use CHMLib\Reader\FileReader; |
10
|
|
|
|
11
|
|
|
/** |
12
|
|
|
* Handle the contents of a CHM file. |
13
|
|
|
*/ |
14
|
|
|
class CHM |
15
|
|
|
{ |
16
|
|
|
/** |
17
|
|
|
* The reader that provides the data. |
18
|
|
|
* |
19
|
|
|
* @var \CHMLib\Reader\Reader |
20
|
|
|
*/ |
21
|
|
|
protected $reader; |
22
|
|
|
|
23
|
|
|
/** |
24
|
|
|
* The CHM initial header. |
25
|
|
|
* |
26
|
|
|
* @var \CHMLib\Header\ITSF |
27
|
|
|
*/ |
28
|
|
|
protected $itsf; |
29
|
|
|
|
30
|
|
|
/** |
31
|
|
|
* The directory listing header. |
32
|
|
|
* |
33
|
|
|
* @var \CHMLib\Header\ITSP |
34
|
|
|
*/ |
35
|
|
|
protected $itsp; |
36
|
|
|
|
37
|
|
|
/** |
38
|
|
|
* The entries found in this CHM. |
39
|
|
|
* |
40
|
|
|
* @var \CHMLib\Entry[] |
41
|
|
|
*/ |
42
|
|
|
protected $entries; |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* The data sections. |
46
|
|
|
* |
47
|
|
|
* @var \CHMLib\Section\Section[] |
48
|
|
|
*/ |
49
|
|
|
protected $sections; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* The TOC. |
53
|
|
|
* |
54
|
|
|
* @var \CHMLib\TOCIndex\Tree|null|false |
55
|
|
|
*/ |
56
|
|
|
protected $toc; |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* The index. |
60
|
|
|
* |
61
|
|
|
* @var \CHMLib\TOCIndex\Tree|null|false |
62
|
|
|
*/ |
63
|
|
|
protected $index; |
64
|
|
|
|
65
|
|
|
/** |
66
|
|
|
* Initializes the instance. |
67
|
|
|
* |
68
|
|
|
* @param \CHMLib\Reader\Reader $reader The reader that provides the data. |
69
|
|
|
* |
70
|
|
|
* @throws \Exception Throws an Exception in case of errors. |
71
|
|
|
*/ |
72
|
4 |
|
public function __construct(Reader $reader) |
73
|
|
|
{ |
74
|
4 |
|
$this->reader = $reader; |
75
|
4 |
|
$reader->setPosition(0); |
76
|
4 |
|
$this->itsf = new Header\ITSF($reader); |
77
|
4 |
|
if ($this->itsf->getSectionOffset() >= 0 && $this->itsf->getSectionLength() >= 16 /* === 24*/) { |
78
|
4 |
|
$reader->setPosition($this->itsf->getSectionOffset()); |
79
|
4 |
|
/* Unknown (510) */ $reader->readUInt32(); |
80
|
4 |
|
/* Unknown (0) */ $reader->readUInt32(); |
81
|
4 |
|
$totalLength = $reader->readUInt64(); |
82
|
4 |
|
if ($totalLength !== $reader->getLength()) { |
83
|
|
|
throw new Exception("Invalid CHM size: expected length $totalLength, current length {$reader->getLength()}"); |
84
|
|
|
} |
85
|
|
|
} |
86
|
4 |
|
$reader->setPosition($this->itsf->getDirectoryOffset()); |
87
|
4 |
|
$this->itsp = new Header\ITSP($reader); |
88
|
|
|
|
89
|
4 |
|
$expectedDirectoryLength = $this->itsf->getDirectoryLength(); |
90
|
4 |
|
$calculatedDirectoryLength = $this->itsp->getHeaderLength() + $this->itsp->getNumberOfDirectoryChunks() * $this->itsp->getDirectoryChunkSize(); |
91
|
4 |
|
if ($expectedDirectoryLength !== $calculatedDirectoryLength) { |
92
|
|
|
throw new Exception("Unexpected directory list size (expected: $expectedDirectoryLength, calculated: $calculatedDirectoryLength)"); |
93
|
|
|
} |
94
|
|
|
|
95
|
4 |
|
$this->sections = array(); |
96
|
4 |
|
$this->sections[0] = new Section\UncompressedSection($this); |
97
|
|
|
|
98
|
4 |
|
$this->entries = $this->retrieveEntryList(); |
99
|
|
|
|
100
|
4 |
|
$this->retrieveSectionList(); |
101
|
|
|
|
102
|
4 |
|
$this->toc = null; |
103
|
4 |
|
$this->index = null; |
104
|
4 |
|
} |
105
|
|
|
|
106
|
|
|
/** |
107
|
|
|
* Destruct the instance. |
108
|
|
|
*/ |
109
|
|
|
public function __destruct() |
110
|
|
|
{ |
111
|
|
|
unset($this->reader); |
112
|
|
|
} |
113
|
|
|
|
114
|
|
|
/** |
115
|
|
|
* Create a new CHM instance reading a file. |
116
|
|
|
* |
117
|
|
|
* @param string $filename |
118
|
|
|
* |
119
|
|
|
* @return static |
120
|
|
|
*/ |
121
|
4 |
|
public static function fromFile($filename) |
122
|
|
|
{ |
123
|
4 |
|
$reader = new FileReader($filename); |
124
|
|
|
|
125
|
4 |
|
return new static($reader); |
126
|
|
|
} |
127
|
|
|
|
128
|
|
|
/** |
129
|
|
|
* Get the reader that provides the data. |
130
|
|
|
* |
131
|
|
|
* @return \CHMLib\Reader\Reader |
132
|
|
|
*/ |
133
|
486 |
|
public function getReader() |
134
|
|
|
{ |
135
|
486 |
|
return $this->reader; |
136
|
|
|
} |
137
|
|
|
|
138
|
|
|
/** |
139
|
|
|
* Get the CHM initial header. |
140
|
|
|
* |
141
|
|
|
* @return \CHMLib\Header\ITSF |
142
|
|
|
*/ |
143
|
4 |
|
public function getITSF() |
144
|
|
|
{ |
145
|
4 |
|
return $this->itsf; |
146
|
|
|
} |
147
|
|
|
|
148
|
|
|
/** |
149
|
|
|
* Get the directory listing header. |
150
|
|
|
* |
151
|
|
|
* @return \CHMLib\Header\ITSP |
152
|
|
|
*/ |
153
|
|
|
public function getITSP() |
154
|
|
|
{ |
155
|
|
|
return $this->itsp; |
156
|
|
|
} |
157
|
|
|
|
158
|
|
|
/** |
159
|
|
|
* Get an entry given its full path. |
160
|
|
|
* |
161
|
|
|
* @param string $path The full path of the entry to look for. |
162
|
|
|
* @param bool $caseSensitive Perform a case-sensitive search? |
163
|
|
|
* |
164
|
|
|
* @return \CHMLib\Entry|null |
165
|
|
|
*/ |
166
|
491 |
|
public function getEntryByPath($path, $caseSensitive = false) |
167
|
|
|
{ |
168
|
491 |
|
if (isset($this->entries[$path])) { |
169
|
491 |
|
return $this->entries[$path]; |
170
|
|
|
} |
171
|
|
|
if ($caseSensitive) { |
172
|
|
|
return null; |
173
|
|
|
} |
174
|
|
|
$entries = array_change_key_case($this->entries, CASE_LOWER); |
175
|
|
|
$path = strtolower($path); |
176
|
|
|
return isset($entries[$path]) ? $entries[$path] : null; |
177
|
|
|
} |
178
|
|
|
|
179
|
|
|
/** |
180
|
|
|
* Get the entries contained in this CHM. |
181
|
|
|
* |
182
|
|
|
* @param int|null $type One or more Entry::TYPE_... values (defaults to Entry::TYPE_FILE | Entry::TYPE_DIRECTORY if null). |
183
|
|
|
*/ |
184
|
3 |
|
public function getEntries($type = null) |
185
|
|
|
{ |
186
|
3 |
|
if ($type === null) { |
187
|
|
|
$type = Entry::TYPE_FILE | Entry::TYPE_DIRECTORY; |
188
|
|
|
} |
189
|
3 |
|
$result = array(); |
190
|
3 |
|
foreach ($this->entries as $entry) { |
191
|
3 |
|
if (($entry->getType() & $type) !== 0) { |
192
|
3 |
|
$result[] = $entry; |
193
|
|
|
} |
194
|
|
|
} |
195
|
|
|
|
196
|
3 |
|
return $result; |
197
|
|
|
} |
198
|
|
|
|
199
|
|
|
/** |
200
|
|
|
* Return a section given its index. |
201
|
|
|
* |
202
|
|
|
* @param int $i |
203
|
|
|
* |
204
|
|
|
* @return \CHMLib\Section\Section|null |
205
|
|
|
*/ |
206
|
491 |
|
public function getSectionByIndex($i) |
207
|
|
|
{ |
208
|
491 |
|
return isset($this->sections[$i]) ? $this->sections[$i] : null; |
209
|
|
|
} |
210
|
|
|
|
211
|
|
|
/** |
212
|
|
|
* Retrieve the list of the entries contained in this CHM. |
213
|
|
|
* |
214
|
|
|
* @throws \Exception Throws an Exception in case of errors. |
215
|
|
|
* |
216
|
|
|
* @return \CHMLib\Entry[] |
217
|
|
|
*/ |
218
|
4 |
|
protected function retrieveEntryList() |
219
|
|
|
{ |
220
|
4 |
|
$result = array(); |
221
|
4 |
|
$chunkOffset = $this->itsf->getDirectoryOffset() + $this->itsp->getHeaderLength(); |
222
|
4 |
|
$chunkSize = $this->itsp->getDirectoryChunkSize(); |
223
|
4 |
|
for ($i = $this->itsp->getFirstPMGLChunkNumber(), $l = $this->itsp->getLastPMGLChunkNumber(); $i <= $l; ++$i) { |
224
|
4 |
|
$offset = $chunkOffset + $i * $chunkSize; |
225
|
4 |
|
$this->reader->setPosition($offset); |
226
|
|
|
try { |
227
|
4 |
|
$pmgl = new Header\PMGL($this->reader); |
228
|
|
|
} catch (UnexpectedHeaderException $x) { |
229
|
|
|
if ($x->getFoundHeader() !== 'PMGI') { |
230
|
|
|
throw $x; |
231
|
|
|
} |
232
|
|
|
$this->reader->setPosition($offset); |
233
|
|
|
new Header\PMGI($this->reader); |
234
|
|
|
$pmgl = null; |
235
|
|
|
} |
236
|
4 |
|
if ($pmgl !== null) { |
237
|
4 |
|
$end = $offset + $chunkSize - $pmgl->getFreeSpace(); |
238
|
4 |
|
$cur = $this->reader->getPosition(); |
239
|
4 |
|
while ($cur < $end) { |
240
|
4 |
|
$this->reader->setPosition($cur); |
241
|
4 |
|
$entry = new Entry($this); |
242
|
4 |
|
$result[$entry->getPath()] = $entry; |
243
|
4 |
|
$cur = $this->reader->getPosition(); |
244
|
|
|
} |
245
|
|
|
} |
246
|
|
|
} |
247
|
|
|
|
248
|
4 |
|
return $result; |
249
|
|
|
} |
250
|
|
|
|
251
|
|
|
/** |
252
|
|
|
* Retrieve the list of the data sections contained in this CHM. |
253
|
|
|
* |
254
|
|
|
* @throws \Exception Throws an Exception in case of errors. |
255
|
|
|
*/ |
256
|
4 |
|
protected function retrieveSectionList() |
257
|
|
|
{ |
258
|
4 |
|
$nameList = $this->getEntryByPath('::DataSpace/NameList'); |
259
|
|
|
|
260
|
4 |
|
if ($nameList === null) { |
261
|
|
|
throw new Exception("Missing required entry: '::DataSpace/NameList'"); |
262
|
|
|
} |
263
|
4 |
|
if ($nameList->getContentSectionIndex() !== 0) { |
264
|
|
|
throw new Exception("The content of the entry '{$nameList->getPath()}' should be in section 0, but it's in section {$nameList->getContentSection()}"); |
|
|
|
|
265
|
|
|
} |
266
|
|
|
|
267
|
4 |
|
$nameListReader = new StringReader($nameList->getContents()); |
268
|
4 |
|
/* Length */ $nameListReader->readUInt16(); |
269
|
4 |
|
$numSections = $nameListReader->readUInt16(); |
270
|
4 |
|
if ($numSections === 0) { |
271
|
|
|
throw new Exception('No content section defined.'); |
272
|
|
|
} |
273
|
4 |
|
for ($i = 0; $i < $numSections; ++$i) { |
274
|
4 |
|
$nameLength = $nameListReader->readUInt16(); |
275
|
4 |
|
$utf16name = $nameListReader->readString($nameLength * 2); |
276
|
4 |
|
$nameListReader->readUInt16(); |
277
|
4 |
|
$name = iconv('UTF-16LE', 'UTF-8', $utf16name); |
278
|
4 |
|
switch ($name) { |
279
|
4 |
|
case 'Uncompressed': |
280
|
4 |
|
break; |
281
|
4 |
|
case 'MSCompressed': |
282
|
4 |
|
if ($i === 0) { |
283
|
|
|
throw new Exception('First data section should be Uncompressed'); |
284
|
|
|
} else { |
285
|
4 |
|
$this->sections[$i] = new Section\MSCompressedSection($this); |
286
|
|
|
} |
287
|
4 |
|
break; |
288
|
|
|
default: |
289
|
|
|
throw new Exception("Unknown data section: $name"); |
290
|
|
|
} |
291
|
|
|
} |
292
|
4 |
|
} |
293
|
|
|
|
294
|
|
|
/** |
295
|
|
|
* Get the TOC of this CHM file (if available). |
296
|
|
|
* |
297
|
|
|
* @return \CHMLib\TOCIndex\Tree|null |
298
|
|
|
*/ |
299
|
1 |
View Code Duplication |
public function getTOC() |
|
|
|
|
300
|
|
|
{ |
301
|
1 |
|
if ($this->toc === null) { |
302
|
1 |
|
$r = false; |
303
|
1 |
|
foreach ($this->entries as $entry) { |
304
|
1 |
|
if ($entry->isFile() && strcasecmp(substr($entry->getPath(), -4), '.hhc') === 0) { |
305
|
1 |
|
$r = TOCIndex\Tree::fromString($this, $entry->getContents()); |
306
|
1 |
|
break; |
307
|
|
|
} |
308
|
|
|
} |
309
|
1 |
|
$this->toc = $r; |
310
|
|
|
} |
311
|
|
|
|
312
|
1 |
|
return ($this->toc === false) ? null : $this->toc; |
313
|
|
|
} |
314
|
|
|
|
315
|
|
|
/** |
316
|
|
|
* Get the index of this CHM file (if available). |
317
|
|
|
* |
318
|
|
|
* @return \CHMLib\TOCIndex\Tree|null |
319
|
|
|
*/ |
320
|
|
View Code Duplication |
public function getIndex() |
|
|
|
|
321
|
|
|
{ |
322
|
|
|
if ($this->index === null) { |
323
|
|
|
$r = false; |
324
|
|
|
foreach ($this->entries as $entry) { |
325
|
|
|
if ($entry->isFile() && strcasecmp(substr($entry->getPath(), -4), '.hhk') === 0) { |
326
|
|
|
$r = TOCIndex\Tree::fromString($this, $entry->getContents()); |
327
|
|
|
break; |
328
|
|
|
} |
329
|
|
|
} |
330
|
|
|
$this->index = $r; |
331
|
|
|
} |
332
|
|
|
|
333
|
|
|
return ($this->index === false) ? null : $this->index; |
334
|
|
|
} |
335
|
|
|
} |
336
|
|
|
|
This check marks calls to methods that do not seem to exist on an object.
This is most likely the result of a method being renamed without all references to it being renamed likewise.