1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* PHP Domain Parser: Public Suffix List based URL parsing. |
5
|
|
|
* |
6
|
|
|
* @link http://github.com/jeremykendall/php-domain-parser for the canonical source repository |
7
|
|
|
* |
8
|
|
|
* @copyright Copyright (c) 2014 Jeremy Kendall (http://about.me/jeremykendall) |
9
|
|
|
* @license http://github.com/jeremykendall/php-domain-parser/blob/master/LICENSE MIT License |
10
|
|
|
*/ |
11
|
|
|
namespace Pdp; |
12
|
|
|
|
13
|
|
|
use TrueBV\Punycode; |
14
|
|
|
|
15
|
|
|
/** |
16
|
|
|
* Public Suffix List Manager. |
17
|
|
|
* |
18
|
|
|
* This class obtains, writes, caches, and returns text and PHP representations |
19
|
|
|
* of the Public Suffix List |
20
|
|
|
*/ |
21
|
|
|
class PublicSuffixListManager |
22
|
|
|
{ |
23
|
|
|
const PDP_PSL_TEXT_FILE = 'public-suffix-list.txt'; |
24
|
|
|
const PDP_PSL_PHP_FILE = 'public-suffix-list.php'; |
25
|
|
|
|
26
|
|
|
/** |
27
|
|
|
* @var string Public Suffix List URL |
28
|
|
|
*/ |
29
|
|
|
protected $publicSuffixListUrl = 'https://publicsuffix.org/list/effective_tld_names.dat'; |
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* @var string Directory where text and php versions of list will be cached |
33
|
|
|
*/ |
34
|
|
|
protected $cacheDir; |
35
|
|
|
|
36
|
|
|
/** |
37
|
|
|
* @var PublicSuffixList Public Suffix List |
38
|
|
|
*/ |
39
|
|
|
protected $list; |
40
|
|
|
|
41
|
|
|
/** |
42
|
|
|
* @var \Pdp\HttpAdapter\HttpAdapterInterface Http adapter |
43
|
|
|
*/ |
44
|
|
|
protected $httpAdapter; |
45
|
|
|
|
46
|
|
|
/** |
47
|
|
|
* Public constructor. |
48
|
|
|
* |
49
|
|
|
* @param string $cacheDir Optional cache directory |
50
|
|
|
*/ |
51
|
11 |
|
public function __construct($cacheDir = null) |
52
|
|
|
{ |
53
|
11 |
|
if (null === $cacheDir) { |
54
|
1 |
|
$cacheDir = realpath( |
55
|
1 |
|
dirname(dirname(__DIR__)) . DIRECTORY_SEPARATOR . 'data' |
56
|
1 |
|
); |
57
|
1 |
|
} |
58
|
|
|
|
59
|
11 |
|
$this->cacheDir = $cacheDir; |
60
|
11 |
|
} |
61
|
|
|
|
62
|
|
|
/** |
63
|
|
|
* Downloads Public Suffix List and writes text cache and PHP cache. If these files |
64
|
|
|
* already exist, they will be overwritten. |
65
|
|
|
*/ |
66
|
1 |
|
public function refreshPublicSuffixList() |
67
|
|
|
{ |
68
|
1 |
|
$this->fetchListFromSource(); |
69
|
1 |
|
$publicSuffixListArray = $this->parseListToArray( |
70
|
1 |
|
$this->cacheDir . '/' . self::PDP_PSL_TEXT_FILE |
71
|
1 |
|
); |
72
|
1 |
|
$this->writePhpCache($publicSuffixListArray); |
73
|
1 |
|
} |
74
|
|
|
|
75
|
|
|
/** |
76
|
|
|
* Obtain Public Suffix List from its online source and write to cache dir. |
77
|
|
|
* |
78
|
|
|
* @return int Number of bytes that were written to the file |
79
|
|
|
*/ |
80
|
2 |
|
public function fetchListFromSource() |
81
|
|
|
{ |
82
|
2 |
|
$publicSuffixList = $this->getHttpAdapter()->getContent($this->publicSuffixListUrl); |
83
|
|
|
|
84
|
2 |
|
return $this->write(self::PDP_PSL_TEXT_FILE, $publicSuffixList); |
85
|
|
|
} |
86
|
|
|
|
87
|
|
|
/** |
88
|
|
|
* Parses text representation of list to associative, multidimensional array. |
89
|
|
|
* |
90
|
|
|
* This method is based heavily on the code found in generateEffectiveTLDs.php |
91
|
|
|
* |
92
|
|
|
* @link https://github.com/usrflo/registered-domain-libs/blob/master/generateEffectiveTLDs.php |
93
|
|
|
* A copy of the Apache License, Version 2.0, is provided with this |
94
|
|
|
* distribution |
95
|
|
|
* |
96
|
|
|
* @param string $textFile Public Suffix List text filename |
97
|
|
|
* |
98
|
|
|
* @return array Associative, multidimensional array representation of the |
99
|
|
|
* public suffx list |
100
|
|
|
* |
101
|
|
|
* @throws \Exception Throws \Exception if unable to read file |
102
|
|
|
*/ |
103
|
4 |
|
public function parseListToArray($textFile) |
104
|
|
|
{ |
105
|
|
|
/** @noinspection PhpUsageOfSilenceOperatorInspection */ |
106
|
4 |
|
$fp = @fopen($textFile, 'r'); |
107
|
4 |
|
if (!$fp || !flock($fp, LOCK_SH)) { |
108
|
1 |
|
throw new \Exception("Cannot read '$textFile'"); |
109
|
|
|
} |
110
|
|
|
|
111
|
3 |
|
$data = file( |
112
|
3 |
|
$textFile, |
113
|
3 |
|
FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES |
114
|
3 |
|
); |
115
|
|
|
|
116
|
3 |
|
flock($fp, LOCK_UN); |
117
|
3 |
|
fclose($fp); |
118
|
|
|
|
119
|
3 |
|
$data = array_filter( |
120
|
3 |
|
$data, |
121
|
3 |
|
function ($line) { |
122
|
3 |
|
return false === strpos($line, '//'); |
123
|
|
|
} |
124
|
3 |
|
); |
125
|
|
|
|
126
|
3 |
|
$publicSuffixListArray = array(); |
127
|
|
|
|
128
|
3 |
|
foreach ($data as $line) { |
129
|
3 |
|
$ruleParts = explode('.', $line); |
130
|
3 |
|
$this->buildArray($publicSuffixListArray, $ruleParts); |
131
|
3 |
|
} |
132
|
|
|
|
133
|
3 |
|
return $publicSuffixListArray; |
134
|
|
|
} |
135
|
|
|
|
136
|
|
|
/** |
137
|
|
|
* Recursive method to build the array representation of the Public Suffix List. |
138
|
|
|
* |
139
|
|
|
* This method is based heavily on the code found in generateEffectiveTLDs.php |
140
|
|
|
* |
141
|
|
|
* @link https://github.com/usrflo/registered-domain-libs/blob/master/generateEffectiveTLDs.php |
142
|
|
|
* A copy of the Apache License, Version 2.0, is provided with this |
143
|
|
|
* distribution |
144
|
|
|
* |
145
|
|
|
* @param array $publicSuffixListArray Initially an empty array, this eventually |
146
|
|
|
* becomes the array representation of the Public Suffix List |
147
|
|
|
* @param array $ruleParts One line (rule) from the Public Suffix List |
148
|
|
|
* exploded on '.', or the remaining portion of that array during recursion |
149
|
|
|
*/ |
150
|
3 |
|
public function buildArray(array &$publicSuffixListArray, array $ruleParts) |
151
|
|
|
{ |
152
|
3 |
|
$isDomain = true; |
153
|
|
|
|
154
|
3 |
|
$part = array_pop($ruleParts); |
155
|
|
|
|
156
|
|
|
// Adheres to canonicalization rule from the "Formal Algorithm" section |
157
|
|
|
// of https://publicsuffix.org/list/ |
158
|
|
|
// "The domain and all rules must be canonicalized in the normal way |
159
|
|
|
// for hostnames - lower-case, Punycode (RFC 3492)." |
160
|
3 |
|
$punycode = new Punycode(); |
161
|
3 |
|
$part = $punycode->encode($part); |
162
|
|
|
|
163
|
3 |
|
if (strpos($part, '!') === 0) { |
164
|
3 |
|
$part = substr($part, 1); |
165
|
3 |
|
$isDomain = false; |
166
|
3 |
|
} |
167
|
|
|
|
168
|
3 |
|
if (!isset($publicSuffixListArray[$part])) { |
169
|
3 |
|
if ($isDomain) { |
170
|
3 |
|
$publicSuffixListArray[$part] = array(); |
171
|
3 |
|
} else { |
172
|
3 |
|
$publicSuffixListArray[$part] = array('!' => ''); |
173
|
|
|
} |
174
|
3 |
|
} |
175
|
|
|
|
176
|
3 |
|
if ($isDomain && count($ruleParts) > 0) { |
177
|
3 |
|
$this->buildArray($publicSuffixListArray[$part], $ruleParts); |
178
|
3 |
|
} |
179
|
3 |
|
} |
180
|
|
|
|
181
|
|
|
/** |
182
|
|
|
* Writes php array representation of the Public Suffix List to disk. |
183
|
|
|
* |
184
|
|
|
* @param array $publicSuffixList Array representation of the Public Suffix List |
185
|
|
|
* |
186
|
|
|
* @return int Number of bytes that were written to the file |
187
|
|
|
*/ |
188
|
3 |
|
public function writePhpCache(array $publicSuffixList) |
189
|
|
|
{ |
190
|
3 |
|
$data = '<?php' . PHP_EOL . 'static $data = ' . var_export($publicSuffixList, true) . '; $result =& $data; unset($data); return $result;'; |
191
|
|
|
|
192
|
3 |
|
return $this->write(self::PDP_PSL_PHP_FILE, $data); |
193
|
|
|
} |
194
|
|
|
|
195
|
|
|
/** |
196
|
|
|
* Gets Public Suffix List. |
197
|
|
|
* |
198
|
|
|
* @return PublicSuffixList Instance of Public Suffix List |
199
|
|
|
* |
200
|
|
|
* @throws \Exception Throws \Exception if unable to read file |
201
|
|
|
*/ |
202
|
3 |
|
public function getList() |
203
|
|
|
{ |
204
|
3 |
|
$phpFile = $this->cacheDir . '/' . self::PDP_PSL_PHP_FILE; |
205
|
|
|
|
206
|
3 |
|
if (!file_exists($phpFile)) { |
207
|
1 |
|
$this->refreshPublicSuffixList(); |
208
|
1 |
|
} |
209
|
|
|
|
210
|
3 |
|
$this->list = $this->getListFromFile($phpFile); |
211
|
|
|
|
212
|
3 |
|
return $this->list; |
213
|
|
|
} |
214
|
|
|
|
215
|
|
|
/** |
216
|
|
|
* Retrieves public suffix list from file after obtaining a shared lock. |
217
|
|
|
* |
218
|
|
|
* @return PublicSuffixList Instance of Public Suffix List |
219
|
|
|
* |
220
|
|
|
* @throws \Exception Throws \Exception if unable to read file |
221
|
|
|
*/ |
222
|
4 |
|
public function getListFromFile($phpFile) |
223
|
|
|
{ |
224
|
|
|
/** @noinspection PhpUsageOfSilenceOperatorInspection */ |
225
|
4 |
|
$fp = @fopen($phpFile, 'r'); |
226
|
4 |
|
if (!$fp || !flock($fp, LOCK_SH)) { |
227
|
1 |
|
throw new \Exception("Cannot read '$phpFile'"); |
228
|
|
|
} |
229
|
|
|
|
230
|
|
|
/** @noinspection PhpIncludeInspection */ |
231
|
3 |
|
$list = new PublicSuffixList( |
232
|
|
|
require $phpFile |
233
|
3 |
|
); |
234
|
|
|
|
235
|
3 |
|
flock($fp, LOCK_UN); |
236
|
3 |
|
fclose($fp); |
237
|
|
|
|
238
|
3 |
|
return $list; |
239
|
|
|
} |
240
|
|
|
|
241
|
|
|
/** |
242
|
|
|
* Writes to file after obtaining an exclusive lock. |
243
|
|
|
* |
244
|
|
|
* @param string $filename Filename in cache dir where data will be written |
245
|
|
|
* @param mixed $data Data to write |
246
|
|
|
* |
247
|
|
|
* @return int Number of bytes that were written to the file |
248
|
|
|
* |
249
|
|
|
* @throws \Exception Throws \Exception if unable to write file |
250
|
|
|
*/ |
251
|
4 |
|
protected function write($filename, $data) |
252
|
|
|
{ |
253
|
4 |
|
$filePath = $this->cacheDir . '/' . $filename; |
254
|
|
|
|
255
|
|
|
// open with 'c' and truncate file only after obtaining a lock |
256
|
|
|
/** @noinspection PhpUsageOfSilenceOperatorInspection */ |
257
|
4 |
|
$fp = @fopen($filePath, 'c'); |
258
|
|
|
$result = $fp |
259
|
4 |
|
&& flock($fp, LOCK_EX) |
260
|
4 |
|
&& ftruncate($fp, 0) |
261
|
4 |
|
&& fwrite($fp, $data) !== false |
262
|
4 |
|
&& fflush($fp); |
263
|
|
|
|
264
|
4 |
|
if (!$result) { |
265
|
1 |
|
$fp && fclose($fp); |
266
|
1 |
|
throw new \Exception("Cannot write to '$filePath'"); |
267
|
|
|
} |
268
|
|
|
|
269
|
3 |
|
flock($fp, LOCK_UN); |
270
|
3 |
|
fclose($fp); |
271
|
|
|
|
272
|
3 |
|
return $result; |
273
|
|
|
} |
274
|
|
|
|
275
|
|
|
/** |
276
|
|
|
* Returns http adapter. Returns default http adapter if one is not set. |
277
|
|
|
* |
278
|
|
|
* @return \Pdp\HttpAdapter\HttpAdapterInterface Http adapter |
279
|
|
|
*/ |
280
|
3 |
|
public function getHttpAdapter() |
281
|
|
|
{ |
282
|
3 |
|
if ($this->httpAdapter === null) { |
283
|
1 |
|
if (extension_loaded('curl')) { |
284
|
1 |
|
$this->httpAdapter = new HttpAdapter\CurlHttpAdapter(); |
285
|
1 |
|
} else { |
286
|
|
|
$this->httpAdapter = new HttpAdapter\PhpHttpAdapter(); |
287
|
|
|
} |
288
|
1 |
|
} |
289
|
|
|
|
290
|
3 |
|
return $this->httpAdapter; |
291
|
|
|
} |
292
|
|
|
|
293
|
|
|
/** |
294
|
|
|
* Sets http adapter. |
295
|
|
|
* |
296
|
|
|
* @param \Pdp\HttpAdapter\HttpAdapterInterface $httpAdapter |
297
|
|
|
*/ |
298
|
11 |
|
public function setHttpAdapter(HttpAdapter\HttpAdapterInterface $httpAdapter) |
299
|
|
|
{ |
300
|
11 |
|
$this->httpAdapter = $httpAdapter; |
301
|
11 |
|
} |
302
|
|
|
} |
303
|
|
|
|