Merge "Handle missing namespace prefix in XML dumps more gracefully"
[lhc/web/wiklou.git] / includes / site / Site.php
1 <?php
2
3 /**
4 * Represents a single site.
5 *
6 * This program is free software; you can redistribute it and/or modify
7 * it under the terms of the GNU General Public License as published by
8 * the Free Software Foundation; either version 2 of the License, or
9 * (at your option) any later version.
10 *
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU General Public License for more details.
15 *
16 * You should have received a copy of the GNU General Public License along
17 * with this program; if not, write to the Free Software Foundation, Inc.,
18 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
19 * http://www.gnu.org/copyleft/gpl.html
20 *
21 * @since 1.21
22 *
23 * @file
24 * @ingroup Site
25 *
26 * @license GNU GPL v2+
27 * @author Jeroen De Dauw < jeroendedauw@gmail.com >
28 */
29 class Site implements Serializable {
30 const TYPE_UNKNOWN = 'unknown';
31 const TYPE_MEDIAWIKI = 'mediawiki';
32
33 const GROUP_NONE = 'none';
34
35 const ID_INTERWIKI = 'interwiki';
36 const ID_EQUIVALENT = 'equivalent';
37
38 const SOURCE_LOCAL = 'local';
39
40 const PATH_LINK = 'link';
41
42 /**
43 * A version ID that identifies the serialization structure used by getSerializationData()
44 * and unserialize(). This is useful for constructing cache keys in cases where the cache relies
45 * on serialization for storing the SiteList.
46 *
47 * @var string A string uniquely identifying the version of the serialization structure.
48 */
49 const SERIAL_VERSION_ID = '2013-01-23';
50
51 /**
52 * @since 1.21
53 *
54 * @var string|null
55 */
56 protected $globalId = null;
57
58 /**
59 * @since 1.21
60 *
61 * @var string
62 */
63 protected $type = self::TYPE_UNKNOWN;
64
65 /**
66 * @since 1.21
67 *
68 * @var string
69 */
70 protected $group = self::GROUP_NONE;
71
72 /**
73 * @since 1.21
74 *
75 * @var string
76 */
77 protected $source = self::SOURCE_LOCAL;
78
79 /**
80 * @since 1.21
81 *
82 * @var string|null
83 */
84 protected $languageCode = null;
85
86 /**
87 * Holds the local ids for this site.
88 * local id type => [ ids for this type (strings) ]
89 *
90 * @since 1.21
91 *
92 * @var array[]
93 */
94 protected $localIds = [];
95
96 /**
97 * @since 1.21
98 *
99 * @var array
100 */
101 protected $extraData = [];
102
103 /**
104 * @since 1.21
105 *
106 * @var array
107 */
108 protected $extraConfig = [];
109
110 /**
111 * @since 1.21
112 *
113 * @var bool
114 */
115 protected $forward = false;
116
117 /**
118 * @since 1.21
119 *
120 * @var int|null
121 */
122 protected $internalId = null;
123
124 /**
125 * Constructor.
126 *
127 * @since 1.21
128 *
129 * @param string $type
130 */
131 public function __construct( $type = self::TYPE_UNKNOWN ) {
132 $this->type = $type;
133 }
134
135 /**
136 * Returns the global site identifier (ie enwiktionary).
137 *
138 * @since 1.21
139 *
140 * @return string|null
141 */
142 public function getGlobalId() {
143 return $this->globalId;
144 }
145
146 /**
147 * Sets the global site identifier (ie enwiktionary).
148 *
149 * @since 1.21
150 *
151 * @param string|null $globalId
152 *
153 * @throws MWException
154 */
155 public function setGlobalId( $globalId ) {
156 if ( $globalId !== null && !is_string( $globalId ) ) {
157 throw new MWException( '$globalId needs to be string or null' );
158 }
159
160 $this->globalId = $globalId;
161 }
162
163 /**
164 * Returns the type of the site (ie mediawiki).
165 *
166 * @since 1.21
167 *
168 * @return string
169 */
170 public function getType() {
171 return $this->type;
172 }
173
174 /**
175 * Gets the group of the site (ie wikipedia).
176 *
177 * @since 1.21
178 *
179 * @return string
180 */
181 public function getGroup() {
182 return $this->group;
183 }
184
185 /**
186 * Sets the group of the site (ie wikipedia).
187 *
188 * @since 1.21
189 *
190 * @param string $group
191 *
192 * @throws MWException
193 */
194 public function setGroup( $group ) {
195 if ( !is_string( $group ) ) {
196 throw new MWException( '$group needs to be a string' );
197 }
198
199 $this->group = $group;
200 }
201
202 /**
203 * Returns the source of the site data (ie 'local', 'wikidata', 'my-magical-repo').
204 *
205 * @since 1.21
206 *
207 * @return string
208 */
209 public function getSource() {
210 return $this->source;
211 }
212
213 /**
214 * Sets the source of the site data (ie 'local', 'wikidata', 'my-magical-repo').
215 *
216 * @since 1.21
217 *
218 * @param string $source
219 *
220 * @throws MWException
221 */
222 public function setSource( $source ) {
223 if ( !is_string( $source ) ) {
224 throw new MWException( '$source needs to be a string' );
225 }
226
227 $this->source = $source;
228 }
229
230 /**
231 * Gets if site.tld/path/key:pageTitle should forward users to the page on
232 * the actual site, where "key" is the local identifier.
233 *
234 * @since 1.21
235 *
236 * @return bool
237 */
238 public function shouldForward() {
239 return $this->forward;
240 }
241
242 /**
243 * Sets if site.tld/path/key:pageTitle should forward users to the page on
244 * the actual site, where "key" is the local identifier.
245 *
246 * @since 1.21
247 *
248 * @param bool $shouldForward
249 *
250 * @throws MWException
251 */
252 public function setForward( $shouldForward ) {
253 if ( !is_bool( $shouldForward ) ) {
254 throw new MWException( '$shouldForward needs to be a boolean' );
255 }
256
257 $this->forward = $shouldForward;
258 }
259
260 /**
261 * Returns the domain of the site, ie en.wikipedia.org
262 * Or false if it's not known.
263 *
264 * @since 1.21
265 *
266 * @return string|null
267 */
268 public function getDomain() {
269 $path = $this->getLinkPath();
270
271 if ( $path === null ) {
272 return null;
273 }
274
275 return parse_url( $path, PHP_URL_HOST );
276 }
277
278 /**
279 * Returns the protocol of the site.
280 *
281 * @since 1.21
282 *
283 * @throws MWException
284 * @return string
285 */
286 public function getProtocol() {
287 $path = $this->getLinkPath();
288
289 if ( $path === null ) {
290 return '';
291 }
292
293 $protocol = parse_url( $path, PHP_URL_SCHEME );
294
295 // Malformed URL
296 if ( $protocol === false ) {
297 throw new MWException( "failed to parse URL '$path'" );
298 }
299
300 // No schema
301 if ( $protocol === null ) {
302 // Used for protocol relative URLs
303 $protocol = '';
304 }
305
306 return $protocol;
307 }
308
309 /**
310 * Sets the path used to construct links with.
311 * Shall be equivalent to setPath( getLinkPathType(), $fullUrl ).
312 *
313 * @param string $fullUrl
314 *
315 * @since 1.21
316 *
317 * @throws MWException
318 */
319 public function setLinkPath( $fullUrl ) {
320 $type = $this->getLinkPathType();
321
322 if ( $type === null ) {
323 throw new MWException( "This Site does not support link paths." );
324 }
325
326 $this->setPath( $type, $fullUrl );
327 }
328
329 /**
330 * Returns the path used to construct links with or false if there is no such path.
331 *
332 * Shall be equivalent to getPath( getLinkPathType() ).
333 *
334 * @return string|null
335 */
336 public function getLinkPath() {
337 $type = $this->getLinkPathType();
338 return $type === null ? null: $this->getPath( $type );
339 }
340
341 /**
342 * Returns the main path type, that is the type of the path that should
343 * generally be used to construct links to the target site.
344 *
345 * This default implementation returns Site::PATH_LINK as the default path
346 * type. Subclasses can override this to define a different default path
347 * type, or return false to disable site links.
348 *
349 * @since 1.21
350 *
351 * @return string|null
352 */
353 public function getLinkPathType() {
354 return self::PATH_LINK;
355 }
356
357 /**
358 * Returns the full URL for the given page on the site.
359 * Or false if the needed information is not known.
360 *
361 * This generated URL is usually based upon the path returned by getLinkPath(),
362 * but this is not a requirement.
363 *
364 * This implementation returns a URL constructed using the path returned by getLinkPath().
365 *
366 * @since 1.21
367 *
368 * @param bool|string $pageName
369 *
370 * @return string|bool
371 */
372 public function getPageUrl( $pageName = false ) {
373 $url = $this->getLinkPath();
374
375 if ( $url === false ) {
376 return false;
377 }
378
379 if ( $pageName !== false ) {
380 $url = str_replace( '$1', rawurlencode( $pageName ), $url );
381 }
382
383 return $url;
384 }
385
386 /**
387 * Returns $pageName without changes.
388 * Subclasses may override this to apply some kind of normalization.
389 *
390 * @see Site::normalizePageName
391 *
392 * @since 1.21
393 *
394 * @param string $pageName
395 *
396 * @return string
397 */
398 public function normalizePageName( $pageName ) {
399 return $pageName;
400 }
401
402 /**
403 * Returns the type specific fields.
404 *
405 * @since 1.21
406 *
407 * @return array
408 */
409 public function getExtraData() {
410 return $this->extraData;
411 }
412
413 /**
414 * Sets the type specific fields.
415 *
416 * @since 1.21
417 *
418 * @param array $extraData
419 */
420 public function setExtraData( array $extraData ) {
421 $this->extraData = $extraData;
422 }
423
424 /**
425 * Returns the type specific config.
426 *
427 * @since 1.21
428 *
429 * @return array
430 */
431 public function getExtraConfig() {
432 return $this->extraConfig;
433 }
434
435 /**
436 * Sets the type specific config.
437 *
438 * @since 1.21
439 *
440 * @param array $extraConfig
441 */
442 public function setExtraConfig( array $extraConfig ) {
443 $this->extraConfig = $extraConfig;
444 }
445
446 /**
447 * Returns language code of the sites primary language.
448 * Or null if it's not known.
449 *
450 * @since 1.21
451 *
452 * @return string|null
453 */
454 public function getLanguageCode() {
455 return $this->languageCode;
456 }
457
458 /**
459 * Sets language code of the sites primary language.
460 *
461 * @since 1.21
462 *
463 * @param string $languageCode
464 */
465 public function setLanguageCode( $languageCode ) {
466 if ( !Language::isValidCode( $languageCode ) ) {
467 throw new InvalidArgumentException( "$languageCode is not a valid language code." );
468 }
469 $this->languageCode = $languageCode;
470 }
471
472 /**
473 * Returns the set internal identifier for the site.
474 *
475 * @since 1.21
476 *
477 * @return string|null
478 */
479 public function getInternalId() {
480 return $this->internalId;
481 }
482
483 /**
484 * Sets the internal identifier for the site.
485 * This typically is a primary key in a db table.
486 *
487 * @since 1.21
488 *
489 * @param int|null $internalId
490 */
491 public function setInternalId( $internalId = null ) {
492 $this->internalId = $internalId;
493 }
494
495 /**
496 * Adds a local identifier.
497 *
498 * @since 1.21
499 *
500 * @param string $type
501 * @param string $identifier
502 */
503 public function addLocalId( $type, $identifier ) {
504 if ( $this->localIds === false ) {
505 $this->localIds = [];
506 }
507
508 if ( !array_key_exists( $type, $this->localIds ) ) {
509 $this->localIds[$type] = [];
510 }
511
512 if ( !in_array( $identifier, $this->localIds[$type] ) ) {
513 $this->localIds[$type][] = $identifier;
514 }
515 }
516
517 /**
518 * Adds an interwiki id to the site.
519 *
520 * @since 1.21
521 *
522 * @param string $identifier
523 */
524 public function addInterwikiId( $identifier ) {
525 $this->addLocalId( self::ID_INTERWIKI, $identifier );
526 }
527
528 /**
529 * Adds a navigation id to the site.
530 *
531 * @since 1.21
532 *
533 * @param string $identifier
534 */
535 public function addNavigationId( $identifier ) {
536 $this->addLocalId( self::ID_EQUIVALENT, $identifier );
537 }
538
539 /**
540 * Returns the interwiki link identifiers that can be used for this site.
541 *
542 * @since 1.21
543 *
544 * @return string[]
545 */
546 public function getInterwikiIds() {
547 return array_key_exists( self::ID_INTERWIKI, $this->localIds )
548 ? $this->localIds[self::ID_INTERWIKI]
549 : [];
550 }
551
552 /**
553 * Returns the equivalent link identifiers that can be used to make
554 * the site show up in interfaces such as the "language links" section.
555 *
556 * @since 1.21
557 *
558 * @return string[]
559 */
560 public function getNavigationIds() {
561 return array_key_exists( self::ID_EQUIVALENT, $this->localIds )
562 ? $this->localIds[self::ID_EQUIVALENT] :
563 [];
564 }
565
566 /**
567 * Returns all local ids
568 *
569 * @since 1.21
570 *
571 * @return array[]
572 */
573 public function getLocalIds() {
574 return $this->localIds;
575 }
576
577 /**
578 * Sets the path used to construct links with.
579 * Shall be equivalent to setPath( getLinkPathType(), $fullUrl ).
580 *
581 * @since 1.21
582 *
583 * @param string $pathType
584 * @param string $fullUrl
585 *
586 * @throws MWException
587 */
588 public function setPath( $pathType, $fullUrl ) {
589 if ( !is_string( $fullUrl ) ) {
590 throw new MWException( '$fullUrl needs to be a string' );
591 }
592
593 if ( !array_key_exists( 'paths', $this->extraData ) ) {
594 $this->extraData['paths'] = [];
595 }
596
597 $this->extraData['paths'][$pathType] = $fullUrl;
598 }
599
600 /**
601 * Returns the path of the provided type or false if there is no such path.
602 *
603 * @since 1.21
604 *
605 * @param string $pathType
606 *
607 * @return string|null
608 */
609 public function getPath( $pathType ) {
610 $paths = $this->getAllPaths();
611 return array_key_exists( $pathType, $paths ) ? $paths[$pathType] : null;
612 }
613
614 /**
615 * Returns the paths as associative array.
616 * The keys are path types, the values are the path urls.
617 *
618 * @since 1.21
619 *
620 * @return string[]
621 */
622 public function getAllPaths() {
623 return array_key_exists( 'paths', $this->extraData ) ? $this->extraData['paths'] : [];
624 }
625
626 /**
627 * Removes the path of the provided type if it's set.
628 *
629 * @since 1.21
630 *
631 * @param string $pathType
632 */
633 public function removePath( $pathType ) {
634 if ( array_key_exists( 'paths', $this->extraData ) ) {
635 unset( $this->extraData['paths'][$pathType] );
636 }
637 }
638
639 /**
640 * @since 1.21
641 *
642 * @param string $siteType
643 *
644 * @return Site
645 */
646 public static function newForType( $siteType ) {
647 global $wgSiteTypes;
648
649 if ( array_key_exists( $siteType, $wgSiteTypes ) ) {
650 return new $wgSiteTypes[$siteType]();
651 }
652
653 return new Site();
654 }
655
656 /**
657 * @see Serializable::serialize
658 *
659 * @since 1.21
660 *
661 * @return string
662 */
663 public function serialize() {
664 $fields = [
665 'globalid' => $this->globalId,
666 'type' => $this->type,
667 'group' => $this->group,
668 'source' => $this->source,
669 'language' => $this->languageCode,
670 'localids' => $this->localIds,
671 'config' => $this->extraConfig,
672 'data' => $this->extraData,
673 'forward' => $this->forward,
674 'internalid' => $this->internalId,
675
676 ];
677
678 return serialize( $fields );
679 }
680
681 /**
682 * @see Serializable::unserialize
683 *
684 * @since 1.21
685 *
686 * @param string $serialized
687 */
688 public function unserialize( $serialized ) {
689 $fields = unserialize( $serialized );
690
691 $this->__construct( $fields['type'] );
692
693 $this->setGlobalId( $fields['globalid'] );
694 $this->setGroup( $fields['group'] );
695 $this->setSource( $fields['source'] );
696 $this->setLanguageCode( $fields['language'] );
697 $this->localIds = $fields['localids'];
698 $this->setExtraConfig( $fields['config'] );
699 $this->setExtraData( $fields['data'] );
700 $this->setForward( $fields['forward'] );
701 $this->setInternalId( $fields['internalid'] );
702 }
703 }