1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the Purl package, a project by Jonathan H. Wage. |
5
|
|
|
* |
6
|
|
|
* (c) 2013 Jonathan H. Wage |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace Purl; |
13
|
|
|
|
14
|
|
|
use Pdp\Parser as PslParser; |
15
|
|
|
use Pdp\PublicSuffixListManager; |
16
|
|
|
|
17
|
|
|
/** |
18
|
|
|
* Url is a simple OO class for manipulating Urls in PHP. |
19
|
|
|
* |
20
|
|
|
* @author Jonathan H. Wage <[email protected]> |
21
|
|
|
* |
22
|
|
|
* @property string $scheme |
23
|
|
|
* @property string $host |
24
|
|
|
* @property integer $port |
25
|
|
|
* @property string $user |
26
|
|
|
* @property string $pass |
27
|
|
|
* @property \Purl\Path $path |
28
|
|
|
* @property \Purl\Query $query |
29
|
|
|
* @property \Purl\Fragment $fragment |
30
|
|
|
* @property string $publicSuffix |
31
|
|
|
* @property string $registerableDomain |
32
|
|
|
* @property string $subdomain |
33
|
|
|
* @property string $canonical |
34
|
|
|
* @property string $resource |
35
|
|
|
*/ |
36
|
|
|
class Url extends AbstractPart |
37
|
|
|
{ |
38
|
|
|
/** |
39
|
|
|
* @var string The original url string. |
40
|
|
|
*/ |
41
|
|
|
private $url; |
42
|
|
|
|
43
|
|
|
/** |
44
|
|
|
* @var ParserInterface |
45
|
|
|
*/ |
46
|
|
|
private $parser; |
47
|
|
|
|
48
|
|
|
/** |
49
|
|
|
* Construct a new Url instance. |
50
|
|
|
* |
51
|
|
|
* @param string $url |
52
|
|
|
* @param ParserInterface $parser |
53
|
|
|
*/ |
54
|
61 |
|
public function __construct($url = null, ParserInterface $parser = null) |
55
|
|
|
{ |
56
|
61 |
|
$this->data = array( |
57
|
61 |
|
'scheme' => null, |
58
|
61 |
|
'host' => null, |
59
|
61 |
|
'port' => null, |
60
|
61 |
|
'user' => null, |
61
|
61 |
|
'pass' => null, |
62
|
61 |
|
'path' => null, |
63
|
61 |
|
'query' => null, |
64
|
61 |
|
'fragment' => null, |
65
|
61 |
|
'publicSuffix' => null, |
66
|
61 |
|
'registerableDomain' => null, |
67
|
61 |
|
'subdomain' => null, |
68
|
61 |
|
'canonical' => null, |
69
|
|
|
'resource' => null |
70
|
61 |
|
); |
71
|
|
|
|
72
|
61 |
|
$this->partClassMap = array( |
73
|
61 |
|
'path' => 'Purl\Path', |
74
|
61 |
|
'query' => 'Purl\Query', |
75
|
|
|
'fragment' => 'Purl\Fragment' |
76
|
61 |
|
); |
77
|
|
|
|
78
|
61 |
|
$this->url = $url; |
79
|
61 |
|
$this->parser = $parser; |
80
|
61 |
|
} |
81
|
|
|
|
82
|
|
|
/** |
83
|
|
|
* Static convenience method for creating a new Url instance. |
84
|
|
|
* |
85
|
|
|
* @param string $url |
86
|
|
|
* @return Url |
87
|
|
|
*/ |
88
|
4 |
|
public static function parse($url) |
89
|
|
|
{ |
90
|
4 |
|
return new self($url); |
91
|
|
|
} |
92
|
|
|
|
93
|
|
|
/** |
94
|
|
|
* Extracts urls from a string of text. |
95
|
|
|
* |
96
|
|
|
* @param string $string |
97
|
|
|
* @return array $urls |
98
|
|
|
*/ |
99
|
1 |
|
public static function extract($string) |
100
|
|
|
{ |
101
|
1 |
|
$regex = "/(\bhttps?:\/\/[^\s()<>]+(?:\([\w\d]+\)|[^[:punct:]\s]|\/))/i"; |
102
|
|
|
|
103
|
1 |
|
preg_match_all($regex, $string, $matches); |
104
|
1 |
|
$urls = array(); |
105
|
1 |
|
foreach ($matches[0] as $url) { |
106
|
1 |
|
$urls[] = self::parse($url); |
107
|
1 |
|
} |
108
|
|
|
|
109
|
1 |
|
return $urls; |
110
|
|
|
} |
111
|
|
|
|
112
|
|
|
/** |
113
|
|
|
* Creates an Url instance based on data available on $_SERVER variable. |
114
|
|
|
* |
115
|
|
|
* @return Url |
116
|
|
|
*/ |
117
|
1 |
|
public static function fromCurrent() |
|
|
|
|
118
|
|
|
{ |
119
|
|
|
$scheme = ( |
120
|
1 |
|
!empty($_SERVER['HTTPS']) && $_SERVER['HTTPS'] !== 'off' |
121
|
1 |
|
|| |
122
|
1 |
|
isset($_SERVER['SERVER_PORT']) && $_SERVER['SERVER_PORT'] == 443) ? 'https' : 'http'; |
123
|
|
|
|
124
|
1 |
|
$host = $_SERVER['HTTP_HOST']; |
125
|
1 |
|
$baseUrl = "$scheme://$host"; |
126
|
|
|
|
127
|
1 |
|
$url = new self($baseUrl); |
128
|
|
|
|
129
|
1 |
|
if (!empty($_SERVER['REQUEST_URI'])) { |
130
|
|
|
|
131
|
1 |
|
if (strpos($_SERVER['REQUEST_URI'], '?') !== false) { |
132
|
1 |
|
list($path, $query) = array_pad(explode('?', $_SERVER['REQUEST_URI'], 2), 2, null); |
133
|
1 |
|
} else { |
134
|
1 |
|
$path = $_SERVER['REQUEST_URI']; |
135
|
1 |
|
$query = ''; |
136
|
|
|
} |
137
|
|
|
|
138
|
1 |
|
$url->set('path', $path); |
139
|
1 |
|
$url->set('query', $query); |
140
|
1 |
|
} |
141
|
|
|
|
142
|
|
|
// Only set port if different from default (80 or 443) |
143
|
1 |
|
if (!empty($_SERVER['SERVER_PORT'])) { |
144
|
1 |
|
$port = $_SERVER['SERVER_PORT']; |
145
|
|
|
|
146
|
|
|
if ( |
147
|
1 |
|
($scheme == 'http' && $port != 80) |
148
|
|
|
|| |
149
|
1 |
|
($scheme == 'https' && $port != 443) |
150
|
1 |
|
) { |
151
|
1 |
|
$url->set('port', $port); |
152
|
1 |
|
} |
153
|
1 |
|
} |
154
|
|
|
|
155
|
|
|
// Authentication |
156
|
1 |
|
if (!empty($_SERVER['PHP_AUTH_USER'])) { |
157
|
1 |
|
$url->set('user', $_SERVER['PHP_AUTH_USER']); |
158
|
1 |
|
if (!empty($_SERVER['PHP_AUTH_PW'])) { |
159
|
1 |
|
$url->set('pass', $_SERVER['PHP_AUTH_PW']); |
160
|
1 |
|
} |
161
|
1 |
|
} |
162
|
|
|
|
163
|
1 |
|
return $url; |
164
|
|
|
} |
165
|
|
|
|
166
|
|
|
/** |
167
|
|
|
* Gets the ParserInterface instance used to parse this Url instance. |
168
|
|
|
* |
169
|
|
|
* @return ParserInterface |
170
|
|
|
*/ |
171
|
60 |
|
public function getParser() |
172
|
|
|
{ |
173
|
60 |
|
if ($this->parser === null) { |
174
|
59 |
|
$this->parser = self::createDefaultParser(); |
175
|
59 |
|
} |
176
|
|
|
|
177
|
60 |
|
return $this->parser; |
178
|
|
|
} |
179
|
|
|
|
180
|
|
|
/** |
181
|
|
|
* Sets the ParserInterface instance to use to parse this Url instance. |
182
|
|
|
* |
183
|
|
|
* @param ParserInterface $parser |
184
|
|
|
*/ |
185
|
1 |
|
public function setParser(ParserInterface $parser) |
186
|
|
|
{ |
187
|
1 |
|
$this->parser = $parser; |
188
|
1 |
|
} |
189
|
|
|
|
190
|
|
|
/** |
191
|
|
|
* Join this Url instance together with another Url instance or a string url. |
192
|
|
|
* |
193
|
|
|
* @param Url|string $url |
194
|
|
|
* @return Url |
195
|
|
|
*/ |
196
|
1 |
|
public function join($url) |
197
|
|
|
{ |
198
|
1 |
|
$this->initialize(); |
199
|
1 |
|
$parts = $this->getParser()->parseUrl($url); |
200
|
|
|
|
201
|
1 |
|
foreach ($parts as $partsKey => $partsValue) { |
202
|
1 |
|
if ($partsValue !== null) { |
203
|
1 |
|
$this->data[$partsKey] = $partsValue; |
204
|
1 |
|
} |
205
|
1 |
|
} |
206
|
|
|
|
207
|
1 |
|
foreach ($this->data as $key => &$value) { |
208
|
1 |
|
$value = $this->preparePartValue($key, $value); |
209
|
1 |
|
} |
210
|
|
|
|
211
|
1 |
|
return $this; |
212
|
|
|
} |
213
|
|
|
|
214
|
|
|
/** @noinspection PhpMissingParentCallCommonInspection */ |
215
|
|
|
/** |
216
|
|
|
* @inheritDoc |
217
|
|
|
* @override |
218
|
|
|
*/ |
219
|
8 |
|
public function set($key, $value) |
220
|
|
|
{ |
221
|
8 |
|
$this->initialize(); |
222
|
8 |
|
$this->data[$key] = $this->preparePartValue($key, $value); |
223
|
|
|
|
224
|
8 |
|
return $this; |
225
|
|
|
} |
226
|
|
|
|
227
|
|
|
/** |
228
|
|
|
* @param $string |
229
|
|
|
*/ |
230
|
1 |
|
public function setPathString($string) |
231
|
|
|
{ |
232
|
1 |
|
$this->set('path', $string); |
233
|
1 |
|
} |
234
|
|
|
|
235
|
|
|
/** |
236
|
|
|
* Set the Path instance. |
237
|
|
|
* |
238
|
|
|
* @param Path $path |
239
|
|
|
* |
240
|
|
|
* @return $this |
241
|
|
|
*/ |
242
|
1 |
|
public function setPath(Path $path) |
243
|
|
|
{ |
244
|
1 |
|
$this->data['path'] = $path; |
245
|
|
|
|
246
|
1 |
|
return $this; |
247
|
|
|
} |
248
|
|
|
|
249
|
|
|
/** |
250
|
|
|
* Get the Path instance. |
251
|
|
|
* |
252
|
|
|
* @return Path |
253
|
|
|
*/ |
254
|
|
|
public function getPath() |
255
|
|
|
{ |
256
|
|
|
$this->initialize(); |
257
|
|
|
return $this->data['path']; |
258
|
|
|
} |
259
|
|
|
|
260
|
|
|
/** |
261
|
|
|
* @param $string |
262
|
|
|
*/ |
263
|
1 |
|
public function setQueryString($string) |
264
|
|
|
{ |
265
|
1 |
|
$this->set('query', $string); |
266
|
1 |
|
} |
267
|
|
|
|
268
|
|
|
/** |
269
|
|
|
* Set the Query instance. |
270
|
|
|
* |
271
|
|
|
* @param Query $query |
272
|
|
|
* |
273
|
|
|
* @return $this |
274
|
|
|
*/ |
275
|
2 |
|
public function setQuery(Query $query) |
276
|
|
|
{ |
277
|
2 |
|
$this->data['query'] = $query; |
278
|
|
|
|
279
|
2 |
|
return $this; |
280
|
|
|
} |
281
|
|
|
|
282
|
|
|
/** |
283
|
|
|
* Get the Query instance. |
284
|
|
|
* |
285
|
|
|
* @return Query |
286
|
|
|
*/ |
287
|
|
|
public function getQuery() |
288
|
|
|
{ |
289
|
|
|
$this->initialize(); |
290
|
|
|
return $this->data['query']; |
291
|
|
|
} |
292
|
|
|
|
293
|
|
|
/** |
294
|
|
|
* @param $string |
295
|
|
|
*/ |
296
|
1 |
|
public function setFragmentString($string) |
297
|
|
|
{ |
298
|
1 |
|
$this->set('fragment', $string); |
299
|
1 |
|
} |
300
|
|
|
|
301
|
|
|
/** |
302
|
|
|
* Set the Fragment instance. |
303
|
|
|
* |
304
|
|
|
* @param Fragment $fragment |
305
|
|
|
* |
306
|
|
|
* @return $this |
307
|
|
|
*/ |
308
|
2 |
|
public function setFragment(Fragment $fragment) |
309
|
|
|
{ |
310
|
2 |
|
$this->data['fragment'] = $fragment; |
311
|
|
|
|
312
|
2 |
|
return $this; |
313
|
|
|
} |
314
|
|
|
|
315
|
|
|
/** |
316
|
|
|
* Get the Fragment instance. |
317
|
|
|
* |
318
|
|
|
* @return Fragment |
319
|
|
|
*/ |
320
|
|
|
public function getFragment() |
321
|
|
|
{ |
322
|
|
|
$this->initialize(); |
323
|
|
|
return $this->data['fragment']; |
324
|
|
|
} |
325
|
|
|
|
326
|
|
|
/** |
327
|
|
|
* Gets the netloc part of the Url. It is the user, pass, host and port returned as a string. |
328
|
|
|
* |
329
|
|
|
* @return string |
330
|
|
|
*/ |
331
|
1 |
|
public function getNetloc() |
332
|
|
|
{ |
333
|
1 |
|
$this->initialize(); |
334
|
|
|
|
335
|
1 |
|
return ($this->user && $this->pass |
336
|
1 |
|
? $this->user.($this->pass |
337
|
1 |
|
? ':'.$this->pass : '').'@' |
338
|
1 |
|
: '').$this->host.($this->port |
339
|
1 |
|
? ':'.$this->port : ''); |
340
|
|
|
} |
341
|
|
|
|
342
|
|
|
/** |
343
|
|
|
* Builds a string url from this Url instance internal data and returns it. |
344
|
|
|
* |
345
|
|
|
* @return string |
346
|
|
|
*/ |
347
|
18 |
|
public function getUrl() |
348
|
|
|
{ |
349
|
18 |
|
$this->initialize(); |
350
|
|
|
|
351
|
18 |
|
$parts = array_map( |
352
|
18 |
|
function ($value) { |
353
|
18 |
|
return (string) $value; |
354
|
18 |
|
}, |
355
|
18 |
|
$this->data |
356
|
18 |
|
); |
357
|
|
|
|
358
|
18 |
|
if (!$this->isAbsolute()) { |
359
|
1 |
|
return self::httpBuildUrlRelative($parts); |
360
|
|
|
} |
361
|
|
|
|
362
|
17 |
|
return self::httpBuildUrl($parts); |
363
|
|
|
} |
364
|
|
|
|
365
|
|
|
/** |
366
|
|
|
* Set the string url for this Url instance and sets initialized to false. |
367
|
|
|
* |
368
|
|
|
* @param string |
369
|
|
|
*/ |
370
|
2 |
|
public function setUrl($url) |
371
|
|
|
{ |
372
|
2 |
|
$this->initialized = false; |
373
|
2 |
|
$this->data = array(); |
374
|
2 |
|
$this->url = $url; |
375
|
2 |
|
} |
376
|
|
|
|
377
|
|
|
/** |
378
|
|
|
* Checks if the Url instance is absolute or not. |
379
|
|
|
* |
380
|
|
|
* @return boolean |
381
|
|
|
*/ |
382
|
19 |
|
public function isAbsolute() |
383
|
|
|
{ |
384
|
19 |
|
$this->initialize(); |
385
|
|
|
|
386
|
19 |
|
return $this->scheme && $this->host; |
387
|
|
|
} |
388
|
|
|
|
389
|
|
|
/** |
390
|
|
|
* @inheritDoc |
391
|
|
|
*/ |
392
|
15 |
|
public function __toString() |
393
|
|
|
{ |
394
|
15 |
|
return $this->getUrl(); |
395
|
|
|
} |
396
|
|
|
|
397
|
|
|
/** |
398
|
|
|
* @inheritDoc |
399
|
|
|
*/ |
400
|
59 |
|
protected function doInitialize() |
401
|
|
|
{ |
402
|
59 |
|
$parts = $this->getParser()->parseUrl($this->url); |
403
|
|
|
|
404
|
59 |
|
foreach ($parts as $k => $v) { |
405
|
59 |
|
if (!isset($this->data[$k])) { |
406
|
59 |
|
$this->data[$k] = $v; |
407
|
59 |
|
} |
408
|
59 |
|
} |
409
|
|
|
|
410
|
59 |
|
foreach ($this->data as $key => &$value) { |
411
|
59 |
|
$value = $this->preparePartValue($key, $value); |
412
|
59 |
|
} |
413
|
59 |
|
} |
414
|
|
|
|
415
|
|
|
/** |
416
|
|
|
* Reconstructs a string URL from an array of parts. |
417
|
|
|
* |
418
|
|
|
* @param array $parts |
419
|
|
|
* @return string $url |
420
|
|
|
*/ |
421
|
17 |
|
private static function httpBuildUrl(array $parts) |
422
|
|
|
{ |
423
|
17 |
|
$relative = self::httpBuildUrlRelative($parts); |
424
|
|
|
|
425
|
17 |
|
return sprintf('%s://%s%s%s%s', |
426
|
17 |
|
$parts['scheme'], |
427
|
17 |
|
$parts['user'] ? sprintf('%s%s@', $parts['user'], $parts['pass'] ? sprintf(':%s', $parts['pass']) : '') : '', |
428
|
17 |
|
$parts['host'], |
429
|
17 |
|
$parts['port'] ? sprintf(':%d', $parts['port']) : '', |
430
|
|
|
$relative |
431
|
17 |
|
); |
432
|
|
|
} |
433
|
|
|
|
434
|
|
|
/** |
435
|
|
|
* Reconstructs relative part of URL from an array of parts. |
436
|
|
|
* |
437
|
|
|
* @param array $parts |
438
|
|
|
* @return string $url |
439
|
|
|
*/ |
440
|
18 |
|
private static function httpBuildUrlRelative(array $parts) |
441
|
|
|
{ |
442
|
18 |
|
$parts['path'] = ltrim($parts['path'], '/'); |
443
|
|
|
|
444
|
18 |
|
return sprintf('/%s%s%s', |
445
|
18 |
|
$parts['path'] ? $parts['path'] : '', |
446
|
18 |
|
$parts['query'] ? '?'.$parts['query'] : '', |
447
|
18 |
|
$parts['fragment'] ? '#'.$parts['fragment'] : '' |
448
|
18 |
|
); |
449
|
|
|
} |
450
|
|
|
|
451
|
|
|
/** |
452
|
|
|
* Creates the default Parser instance to parse urls. |
453
|
|
|
* |
454
|
|
|
* @return Parser |
455
|
|
|
*/ |
456
|
59 |
|
private static function createDefaultParser() |
457
|
|
|
{ |
458
|
59 |
|
$pslManager = new PublicSuffixListManager(dirname(dirname(__DIR__)) . '/data'); |
459
|
59 |
|
$pslParser = new PslParser($pslManager->getList()); |
460
|
|
|
|
461
|
59 |
|
return new Parser($pslParser); |
462
|
|
|
} |
463
|
|
|
} |
464
|
|
|
|
Instead of super-globals, we recommend to explicitly inject the dependencies of your class. This makes your code less dependent on global state and it becomes generally more testable: