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 = [ |
57
|
|
|
'scheme' => null, |
58
|
|
|
'host' => null, |
59
|
|
|
'port' => null, |
60
|
|
|
'user' => null, |
61
|
|
|
'pass' => null, |
62
|
|
|
'path' => null, |
63
|
|
|
'query' => null, |
64
|
|
|
'fragment' => null, |
65
|
|
|
'publicSuffix' => null, |
66
|
|
|
'registerableDomain' => null, |
67
|
|
|
'subdomain' => null, |
68
|
|
|
'canonical' => null, |
69
|
|
|
'resource' => null, |
70
|
|
|
]; |
71
|
|
|
|
72
|
61 |
|
$this->partClassMap = [ |
73
|
|
|
'path' => Path::class, |
74
|
|
|
'query' => Query::class, |
75
|
|
|
'fragment' => Fragment::class, |
76
|
|
|
]; |
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 $url |
86
|
|
|
* |
87
|
|
|
* @return Url |
88
|
|
|
*/ |
89
|
4 |
|
public static function parse($url): Url |
90
|
|
|
{ |
91
|
4 |
|
return new self($url); |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
/** |
95
|
|
|
* Extracts urls from a string of text. |
96
|
|
|
* |
97
|
|
|
* @param string $string |
98
|
|
|
* |
99
|
|
|
* @return array $urls |
100
|
|
|
*/ |
101
|
1 |
|
public static function extract($string): array |
102
|
|
|
{ |
103
|
1 |
|
$regex = "/(\bhttps?:\/\/[^\s()<>]+(?:\([\w]+\)|[^[:punct:]\s]|\/))/i"; |
104
|
|
|
|
105
|
1 |
|
preg_match_all($regex, $string, $matches); |
106
|
1 |
|
$urls = []; |
107
|
1 |
|
foreach ($matches[0] as $url) { |
108
|
1 |
|
$urls[] = self::parse($url); |
109
|
|
|
} |
110
|
|
|
|
111
|
1 |
|
return $urls; |
112
|
|
|
} |
113
|
|
|
|
114
|
|
|
/** |
115
|
|
|
* Creates an Url instance based on data available on $_SERVER variable. |
116
|
|
|
* |
117
|
|
|
* @return Url |
118
|
|
|
*/ |
119
|
1 |
|
public static function fromCurrent(): Url |
120
|
|
|
{ |
121
|
|
|
$scheme = ( |
122
|
1 |
|
(!empty($_SERVER['HTTPS']) && $_SERVER['HTTPS'] !== 'off') |
123
|
|
|
|| |
124
|
1 |
|
(isset($_SERVER['SERVER_PORT']) && $_SERVER['SERVER_PORT'] == 443) |
125
|
1 |
|
) ? 'https' : 'http'; |
126
|
|
|
|
127
|
1 |
|
$host = $_SERVER['HTTP_HOST']; |
128
|
1 |
|
$baseUrl = "$scheme://$host"; |
129
|
|
|
|
130
|
1 |
|
$url = new self($baseUrl); |
131
|
|
|
|
132
|
1 |
|
if (!empty($_SERVER['REQUEST_URI'])) { |
133
|
|
|
|
134
|
1 |
|
if (strpos($_SERVER['REQUEST_URI'], '?') !== false) { |
135
|
1 |
|
list($path, $query) = array_pad(explode('?', $_SERVER['REQUEST_URI'], 2), 2, null); |
136
|
|
|
} else { |
137
|
1 |
|
$path = $_SERVER['REQUEST_URI']; |
138
|
1 |
|
$query = ''; |
139
|
|
|
} |
140
|
|
|
|
141
|
1 |
|
$url->set('path', $path); |
142
|
1 |
|
$url->set('query', $query); |
143
|
|
|
} |
144
|
|
|
|
145
|
|
|
// Only set port if different from default (80 or 443) |
146
|
1 |
|
if (!empty($_SERVER['SERVER_PORT'])) { |
147
|
1 |
|
$port = $_SERVER['SERVER_PORT']; |
148
|
|
|
|
149
|
|
|
if ( |
150
|
1 |
|
($scheme == 'http' && $port != 80) |
151
|
|
|
|| |
152
|
1 |
|
($scheme == 'https' && $port != 443) |
153
|
|
|
) { |
154
|
1 |
|
$url->set('port', $port); |
155
|
|
|
} |
156
|
|
|
} |
157
|
|
|
|
158
|
|
|
// Authentication |
159
|
1 |
|
if (!empty($_SERVER['PHP_AUTH_USER'])) { |
160
|
1 |
|
$url->set('user', $_SERVER['PHP_AUTH_USER']); |
161
|
1 |
|
if (!empty($_SERVER['PHP_AUTH_PW'])) { |
162
|
1 |
|
$url->set('pass', $_SERVER['PHP_AUTH_PW']); |
163
|
|
|
} |
164
|
|
|
} |
165
|
|
|
|
166
|
1 |
|
return $url; |
167
|
|
|
} |
168
|
|
|
|
169
|
|
|
/** |
170
|
|
|
* Gets the ParserInterface instance used to parse this Url instance. |
171
|
|
|
* |
172
|
|
|
* @return ParserInterface |
173
|
|
|
*/ |
174
|
60 |
|
public function getParser(): ParserInterface |
175
|
|
|
{ |
176
|
60 |
|
if ($this->parser === null) { |
177
|
59 |
|
$this->parser = self::createDefaultParser(); |
178
|
|
|
} |
179
|
|
|
|
180
|
60 |
|
return $this->parser; |
181
|
|
|
} |
182
|
|
|
|
183
|
|
|
/** |
184
|
|
|
* Sets the ParserInterface instance to use to parse this Url instance. |
185
|
|
|
* |
186
|
|
|
* @param ParserInterface $parser |
187
|
|
|
*/ |
188
|
1 |
|
public function setParser(ParserInterface $parser) |
189
|
|
|
{ |
190
|
1 |
|
$this->parser = $parser; |
191
|
1 |
|
} |
192
|
|
|
|
193
|
|
|
/** |
194
|
|
|
* Join this Url instance together with another Url instance or a string url. |
195
|
|
|
* |
196
|
|
|
* @param Url|string $url |
197
|
|
|
* |
198
|
|
|
* @return Url |
199
|
|
|
*/ |
200
|
1 |
|
public function join($url): Url |
201
|
|
|
{ |
202
|
1 |
|
$this->initialize(); |
203
|
1 |
|
$parts = $this->getParser()->parseUrl($url); |
204
|
|
|
|
205
|
1 |
|
foreach ($parts as $partsKey => $partsValue) { |
206
|
1 |
|
if ($partsValue !== null) { |
207
|
1 |
|
$this->data[$partsKey] = $partsValue; |
208
|
|
|
} |
209
|
|
|
} |
210
|
|
|
|
211
|
1 |
|
foreach ($this->data as $key => &$value) { |
212
|
1 |
|
$value = $this->preparePartValue($key, $value); |
213
|
|
|
} |
214
|
|
|
|
215
|
1 |
|
return $this; |
216
|
|
|
} |
217
|
|
|
|
218
|
|
|
/** @noinspection PhpMissingParentCallCommonInspection */ |
219
|
|
|
/** |
220
|
|
|
* @inheritDoc |
221
|
|
|
* @override |
222
|
|
|
*/ |
223
|
8 |
|
public function set($key, $value) |
224
|
|
|
{ |
225
|
8 |
|
$this->initialize(); |
226
|
8 |
|
$this->data[$key] = $this->preparePartValue($key, $value); |
227
|
|
|
|
228
|
8 |
|
return $this; |
229
|
|
|
} |
230
|
|
|
|
231
|
|
|
/** |
232
|
|
|
* @param $string |
233
|
|
|
*/ |
234
|
1 |
|
public function setPathString($string) |
235
|
|
|
{ |
236
|
1 |
|
$this->set('path', $string); |
237
|
1 |
|
} |
238
|
|
|
|
239
|
|
|
/** |
240
|
|
|
* Set the Path instance. |
241
|
|
|
* |
242
|
|
|
* @param Path $path |
243
|
|
|
* |
244
|
|
|
* @return $this |
245
|
|
|
*/ |
246
|
1 |
|
public function setPath(Path $path) |
247
|
|
|
{ |
248
|
1 |
|
$this->data['path'] = $path; |
249
|
|
|
|
250
|
1 |
|
return $this; |
251
|
|
|
} |
252
|
|
|
|
253
|
|
|
/** |
254
|
|
|
* Get the Path instance. |
255
|
|
|
* |
256
|
|
|
* @return Path |
257
|
|
|
*/ |
258
|
|
|
public function getPath(): Path |
259
|
|
|
{ |
260
|
|
|
$this->initialize(); |
261
|
|
|
|
262
|
|
|
return $this->data['path']; |
263
|
|
|
} |
264
|
|
|
|
265
|
|
|
/** |
266
|
|
|
* @param $string |
267
|
|
|
*/ |
268
|
1 |
|
public function setQueryString($string) |
269
|
|
|
{ |
270
|
1 |
|
$this->set('query', $string); |
271
|
1 |
|
} |
272
|
|
|
|
273
|
|
|
/** |
274
|
|
|
* Set the Query instance. |
275
|
|
|
* |
276
|
|
|
* @param Query $query |
277
|
|
|
* |
278
|
|
|
* @return $this |
279
|
|
|
*/ |
280
|
2 |
|
public function setQuery(Query $query) |
281
|
|
|
{ |
282
|
2 |
|
$this->data['query'] = $query; |
283
|
|
|
|
284
|
2 |
|
return $this; |
285
|
|
|
} |
286
|
|
|
|
287
|
|
|
/** |
288
|
|
|
* Get the Query instance. |
289
|
|
|
* |
290
|
|
|
* @return Query |
291
|
|
|
*/ |
292
|
|
|
public function getQuery(): Query |
293
|
|
|
{ |
294
|
|
|
$this->initialize(); |
295
|
|
|
|
296
|
|
|
return $this->data['query']; |
297
|
|
|
} |
298
|
|
|
|
299
|
|
|
/** |
300
|
|
|
* @param $string |
301
|
|
|
*/ |
302
|
1 |
|
public function setFragmentString($string) |
303
|
|
|
{ |
304
|
1 |
|
$this->set('fragment', $string); |
305
|
1 |
|
} |
306
|
|
|
|
307
|
|
|
/** |
308
|
|
|
* Set the Fragment instance. |
309
|
|
|
* |
310
|
|
|
* @param Fragment $fragment |
311
|
|
|
* |
312
|
|
|
* @return $this |
313
|
|
|
*/ |
314
|
2 |
|
public function setFragment(Fragment $fragment) |
315
|
|
|
{ |
316
|
2 |
|
$this->data['fragment'] = $fragment; |
317
|
|
|
|
318
|
2 |
|
return $this; |
319
|
|
|
} |
320
|
|
|
|
321
|
|
|
/** |
322
|
|
|
* Get the Fragment instance. |
323
|
|
|
* |
324
|
|
|
* @return Fragment |
325
|
|
|
*/ |
326
|
|
|
public function getFragment(): Fragment |
327
|
|
|
{ |
328
|
|
|
$this->initialize(); |
329
|
|
|
|
330
|
|
|
return $this->data['fragment']; |
331
|
|
|
} |
332
|
|
|
|
333
|
|
|
/** |
334
|
|
|
* Gets the netloc part of the Url. It is the user, pass, host and port returned as a string. |
335
|
|
|
* |
336
|
|
|
* @return string |
337
|
|
|
*/ |
338
|
1 |
|
public function getNetloc(): string |
339
|
|
|
{ |
340
|
1 |
|
$this->initialize(); |
341
|
|
|
|
342
|
1 |
|
return ($this->user && $this->pass |
343
|
1 |
|
? $this->user . ($this->pass |
344
|
1 |
|
? ':' . $this->pass : '') . '@' |
345
|
1 |
|
: '') . $this->host . ($this->port |
346
|
1 |
|
? ':' . $this->port : ''); |
347
|
|
|
} |
348
|
|
|
|
349
|
|
|
/** |
350
|
|
|
* Builds a string url from this Url instance internal data and returns it. |
351
|
|
|
* |
352
|
|
|
* @return string |
353
|
|
|
*/ |
354
|
18 |
|
public function getUrl(): string |
355
|
|
|
{ |
356
|
18 |
|
$this->initialize(); |
357
|
|
|
|
358
|
18 |
|
$parts = \array_map( |
359
|
18 |
|
function ($value) { |
360
|
18 |
|
return (string)$value; |
361
|
18 |
|
}, |
362
|
18 |
|
$this->data |
363
|
|
|
); |
364
|
|
|
|
365
|
18 |
|
if (!$this->isAbsolute()) { |
366
|
1 |
|
return self::httpBuildUrlRelative($parts); |
367
|
|
|
} |
368
|
|
|
|
369
|
17 |
|
return self::httpBuildUrl($parts); |
370
|
|
|
} |
371
|
|
|
|
372
|
|
|
/** |
373
|
|
|
* Set the string url for this Url instance and sets initialized to false. |
374
|
|
|
* |
375
|
|
|
* @param string |
376
|
|
|
*/ |
377
|
2 |
|
public function setUrl($url) |
378
|
|
|
{ |
379
|
2 |
|
$this->initialized = false; |
380
|
2 |
|
$this->data = []; |
381
|
2 |
|
$this->url = $url; |
382
|
2 |
|
} |
383
|
|
|
|
384
|
|
|
/** |
385
|
|
|
* Checks if the Url instance is absolute or not. |
386
|
|
|
* |
387
|
|
|
* @return boolean |
388
|
|
|
*/ |
389
|
19 |
|
public function isAbsolute(): bool |
390
|
|
|
{ |
391
|
19 |
|
$this->initialize(); |
392
|
|
|
|
393
|
19 |
|
return $this->scheme && $this->host; |
394
|
|
|
} |
395
|
|
|
|
396
|
|
|
/** |
397
|
|
|
* @inheritDoc |
398
|
|
|
*/ |
399
|
15 |
|
public function __toString() |
400
|
|
|
{ |
401
|
15 |
|
return $this->getUrl(); |
402
|
|
|
} |
403
|
|
|
|
404
|
|
|
/** |
405
|
|
|
* @inheritDoc |
406
|
|
|
*/ |
407
|
59 |
|
protected function doInitialize() |
408
|
|
|
{ |
409
|
59 |
|
$parts = $this->getParser()->parseUrl($this->url); |
410
|
|
|
|
411
|
59 |
|
foreach ($parts as $k => $v) { |
412
|
59 |
|
if (!isset($this->data[$k])) { |
413
|
59 |
|
$this->data[$k] = $v; |
414
|
|
|
} |
415
|
|
|
} |
416
|
|
|
|
417
|
59 |
|
foreach ($this->data as $key => &$value) { |
418
|
59 |
|
$value = $this->preparePartValue($key, $value); |
419
|
|
|
} |
420
|
59 |
|
} |
421
|
|
|
|
422
|
|
|
/** |
423
|
|
|
* Reconstructs a string URL from an array of parts. |
424
|
|
|
* |
425
|
|
|
* @param array $parts |
426
|
|
|
* |
427
|
|
|
* @return string $url |
428
|
|
|
*/ |
429
|
17 |
|
private static function httpBuildUrl(array $parts): string |
430
|
|
|
{ |
431
|
17 |
|
$relative = self::httpBuildUrlRelative($parts); |
432
|
|
|
|
433
|
17 |
|
return sprintf( |
434
|
17 |
|
'%s://%s%s%s%s', |
435
|
17 |
|
$parts['scheme'], |
436
|
17 |
|
$parts['user'] ? sprintf('%s%s@', $parts['user'], $parts['pass'] ? sprintf(':%s', $parts['pass']) : '') : '', |
437
|
17 |
|
$parts['host'], |
438
|
17 |
|
$parts['port'] ? sprintf(':%d', $parts['port']) : '', |
439
|
17 |
|
$relative |
440
|
|
|
); |
441
|
|
|
} |
442
|
|
|
|
443
|
|
|
/** |
444
|
|
|
* Reconstructs relative part of URL from an array of parts. |
445
|
|
|
* |
446
|
|
|
* @param array $parts |
447
|
|
|
* |
448
|
|
|
* @return string $url |
449
|
|
|
*/ |
450
|
18 |
|
private static function httpBuildUrlRelative(array $parts): string |
451
|
|
|
{ |
452
|
18 |
|
$parts['path'] = ltrim($parts['path'], '/'); |
453
|
|
|
|
454
|
18 |
|
return sprintf( |
455
|
18 |
|
'/%s%s%s', |
456
|
18 |
|
$parts['path'] ? $parts['path'] : '', |
457
|
18 |
|
$parts['query'] ? '?' . $parts['query'] : '', |
458
|
18 |
|
$parts['fragment'] ? '#' . $parts['fragment'] : '' |
459
|
|
|
); |
460
|
|
|
} |
461
|
|
|
|
462
|
|
|
/** |
463
|
|
|
* Creates the default Parser instance to parse urls. |
464
|
|
|
* |
465
|
|
|
* @return Parser |
466
|
|
|
*/ |
467
|
59 |
|
private static function createDefaultParser(): Parser |
468
|
|
|
{ |
469
|
59 |
|
$pslManager = new PublicSuffixListManager(dirname(dirname(__DIR__)) . '/data'); |
470
|
59 |
|
$pslParser = new PslParser($pslManager->getList()); |
471
|
|
|
|
472
|
59 |
|
return new Parser($pslParser); |
473
|
|
|
} |
474
|
|
|
} |
475
|
|
|
|