Completed
Push — update/sitemaps-libxml ( 89d83f...3ee9c2 )
by
unknown
10:58
created

callback_action_purge_data()   A

Complexity

Conditions 1
Paths 1

Size

Total Lines 4
Code Lines 3

Duplication

Lines 0
Ratio 0 %

Importance

Changes 0
Metric Value
cc 1
eloc 3
nc 1
nop 0
dl 0
loc 4
rs 10
c 0
b 0
f 0
1
<?php
2
/**
3
 * Generate sitemap files in base XML as well as some namespace extensions.
4
 *
5
 * This module generates two different base sitemaps.
6
 *
7
 * 1. sitemap.xml
8
 *    The basic sitemap is updated regularly by wp-cron. It is stored in the
9
 *    database and retrieved when requested. This sitemap aims to include canonical
10
 *    URLs for all published content and abide by the sitemap spec. This is the root
11
 *    of a tree of sitemap and sitemap index xml files, depending on the number of URLs.
12
 *
13
 *    By default the sitemap contains published posts of type 'post' and 'page', as
14
 *    well as the home url. To include other post types use the 'jetpack_sitemap_post_types'
15
 *    filter.
16
 *
17
 * @link http://sitemaps.org/protocol.php Base sitemaps protocol.
18
 * @link https://support.google.com/webmasters/answer/178636 Image sitemap extension.
19
 * @link https://developers.google.com/webmasters/videosearch/sitemaps Video sitemap extension.
20
 *
21
 * 2. news-sitemap.xml
22
 *    The news sitemap is generated on the fly when requested. It does not aim for
23
 *    completeness, instead including at most 1000 of the most recent published posts
24
 *    from the previous 2 days, per the news-sitemap spec.
25
 *
26
 * @link http://www.google.com/support/webmasters/bin/answer.py?answer=74288 News sitemap extension.
27
 *
28
 * @package Jetpack
29
 * @since 3.9.0
30
 * @since 4.8.0 Remove 1000 post limit.
31
 * @author Automattic
32
 */
33
34
require_once dirname( __FILE__ ) . '/sitemap-constants.php';
35
require_once dirname( __FILE__ ) . '/sitemap-buffer.php';
36
require_once dirname( __FILE__ ) . '/sitemap-stylist.php';
37
require_once dirname( __FILE__ ) . '/sitemap-librarian.php';
38
require_once dirname( __FILE__ ) . '/sitemap-finder.php';
39
require_once dirname( __FILE__ ) . '/sitemap-builder.php';
40
41
if ( defined( 'WP_DEBUG' ) && WP_DEBUG ) {
42
	require_once dirname( __FILE__ ) . '/sitemap-logger.php';
43
}
44
45
/**
46
 * Governs the generation, storage, and serving of sitemaps.
47
 *
48
 * @since 4.8.0
49
 */
50
class Jetpack_Sitemap_Manager {
51
52
	/**
53
	 * @see Jetpack_Sitemap_Librarian
54
	 * @since 4.8.0
55
	 * @var Jetpack_Sitemap_Librarian $librarian Librarian object for storing and retrieving sitemap data.
56
	 */
57
	private $librarian;
58
59
	/**
60
	 * @see Jetpack_Sitemap_Logger
61
	 * @since 4.8.0
62
	 * @var Jetpack_Sitemap_Logger $logger Logger object for reporting debug messages.
63
	 */
64
	private $logger;
65
66
	/**
67
	 * @see Jetpack_Sitemap_Finder
68
	 * @since 4.8.0
69
	 * @var Jetpack_Sitemap_Finder $finder Finder object for dealing with sitemap URIs.
70
	 */
71
	private $finder;
72
73
	/**
74
	 * Construct a new Jetpack_Sitemap_Manager.
75
	 *
76
	 * @access public
77
	 * @since 4.8.0
78
	 */
79
	public function __construct() {
80
		$this->librarian = new Jetpack_Sitemap_Librarian();
81
		$this->finder = new Jetpack_Sitemap_Finder();
82
83
		if ( defined( 'WP_DEBUG' ) && ( true === WP_DEBUG ) ) {
84
			$this->logger = new Jetpack_Sitemap_Logger();
85
		}
86
87
		// Add callback for sitemap URL handler.
88
		add_action(
89
			'init',
90
			array( $this, 'callback_action_catch_sitemap_urls' )
91
		);
92
93
		// Add generator to wp_cron task list.
94
		$this->schedule_sitemap_generation();
95
96
		// Add sitemap to robots.txt.
97
		add_action(
98
			'do_robotstxt',
99
			array( $this, 'callback_action_do_robotstxt' ),
100
			20
101
		);
102
103
		// The news sitemap is cached; here we add a callback to
104
		// flush the cached news sitemap when a post is published.
105
		add_action(
106
			'publish_post',
107
			array( $this, 'callback_action_flush_news_sitemap_cache' ),
108
			10
109
		);
110
111
		// In case we need to purge all sitemaps, we do this.
112
		add_action(
113
			'jetpack_sitemaps_purge_data',
114
			array( $this, 'callback_action_purge_data' )
115
		);
116
117
		/*
118
		 * Module parameters are stored as options in the database.
119
		 * This allows us to avoid having to process all of init
120
		 * before serving the sitemap data. The following actions
121
		 * process and store these filters.
122
		 */
123
124
		// Process filters and store location string for sitemap.
125
		add_action(
126
			'init',
127
			array( $this, 'callback_action_filter_sitemap_location' ),
128
			999
129
		);
130
131
		return;
132
	}
133
134
	/**
135
	 * Echo a raw string of given content-type.
136
	 *
137
	 * @access private
138
	 * @since 4.8.0
139
	 *
140
	 * @param string $the_content_type The content type to be served.
141
	 * @param string $the_content The string to be echoed.
142
	 */
143
	private function serve_raw_and_die( $the_content_type, $the_content ) {
144
		header( 'Content-Type: ' . $the_content_type . '; charset=UTF-8' );
145
146
		if ( '' === $the_content ) {
147
			wp_die(
148
				esc_html__( "No sitemap found. Maybe it's being generated. Please try again later.", 'jetpack' ),
149
				esc_html__( 'Sitemaps', 'jetpack' ),
150
				array(
151
					'response' => 404,
152
				)
153
			);
154
		}
155
156
		echo $the_content;
157
158
		die();
0 ignored issues
show
Coding Style Compatibility introduced by
The method serve_raw_and_die() contains an exit expression.

An exit expression should only be used in rare cases. For example, if you write a short command line script.

In most cases however, using an exit expression makes the code untestable and often causes incompatibilities with other libraries. Thus, unless you are absolutely sure it is required here, we recommend to refactor your code to avoid its usage.

Loading history...
159
	}
160
161
	/**
162
	 * Callback to intercept sitemap url requests and serve sitemap files.
163
	 *
164
	 * @access public
165
	 * @since 4.8.0
166
	 */
167
	public function callback_action_catch_sitemap_urls() {
168
		// Regular expressions for sitemap URL routing.
169
		$regex = array(
170
			'master'        => '/^sitemap\.xml$/',
171
			'sitemap'       => '/^sitemap-[1-9][0-9]*\.xml$/',
172
			'index'         => '/^sitemap-index-[1-9][0-9]*\.xml$/',
173
			'sitemap-style' => '/^sitemap\.xsl$/',
174
			'index-style'   => '/^sitemap-index\.xsl$/',
175
			'image'         => '/^image-sitemap-[1-9][0-9]*\.xml$/',
176
			'image-index'   => '/^image-sitemap-index-[1-9][0-9]*\.xml$/',
177
			'image-style'   => '/^image-sitemap\.xsl$/',
178
			'video'         => '/^video-sitemap-[1-9][0-9]*\.xml$/',
179
			'video-index'   => '/^video-sitemap-index-[1-9][0-9]*\.xml$/',
180
			'video-style'   => '/^video-sitemap\.xsl$/',
181
			'news'          => '/^news-sitemap\.xml$/',
182
			'news-style'    => '/^news-sitemap\.xsl$/',
183
		);
184
185
		// The raw path(+query) of the requested URI.
186
		if ( isset( $_SERVER['REQUEST_URI'] ) ) { // WPCS: Input var okay.
187
			$raw_uri = sanitize_text_field(
188
				wp_unslash( $_SERVER['REQUEST_URI'] ) // WPCS: Input var okay.
189
			);
190
		} else {
191
			$raw_uri = '';
192
		}
193
194
		$request = $this->finder->recognize_sitemap_uri( $raw_uri );
195
196
		if ( isset( $request['sitemap_name'] ) ) {
197
198
			/**
199
			 * Filter the content type used to serve the sitemap XML files.
200
			 *
201
			 * @module sitemaps
202
			 *
203
			 * @since 3.9.0
204
			 *
205
			 * @param string $xml_content_type By default, it's 'text/xml'.
206
			 */
207
			$xml_content_type = apply_filters( 'jetpack_sitemap_content_type', 'text/xml' );
208
209
			// Catch master sitemap xml.
210
			if ( preg_match( $regex['master'], $request['sitemap_name'] ) ) {
211
				$this->serve_raw_and_die(
212
					$xml_content_type,
213
					$this->librarian->get_sitemap_text(
214
						jp_sitemap_filename( JP_MASTER_SITEMAP_TYPE, 0 ),
215
						JP_MASTER_SITEMAP_TYPE
216
					)
217
				);
218
			}
219
220
			// Catch sitemap xml.
221 View Code Duplication
			if ( preg_match( $regex['sitemap'], $request['sitemap_name'] ) ) {
222
				$this->serve_raw_and_die(
223
					$xml_content_type,
224
					$this->librarian->get_sitemap_text(
225
						$request['sitemap_name'],
226
						JP_PAGE_SITEMAP_TYPE
227
					)
228
				);
229
			}
230
231
			// Catch sitemap index xml.
232 View Code Duplication
			if ( preg_match( $regex['index'], $request['sitemap_name'] ) ) {
233
				$this->serve_raw_and_die(
234
					$xml_content_type,
235
					$this->librarian->get_sitemap_text(
236
						$request['sitemap_name'],
237
						JP_PAGE_SITEMAP_INDEX_TYPE
238
					)
239
				);
240
			}
241
242
			// Catch sitemap xsl.
243
			if ( preg_match( $regex['sitemap-style'], $request['sitemap_name'] ) ) {
244
				$this->serve_raw_and_die(
245
					'application/xml',
246
					Jetpack_Sitemap_Stylist::sitemap_xsl()
247
				);
248
			}
249
250
			// Catch sitemap index xsl.
251
			if ( preg_match( $regex['index-style'], $request['sitemap_name'] ) ) {
252
				$this->serve_raw_and_die(
253
					'application/xml',
254
					Jetpack_Sitemap_Stylist::sitemap_index_xsl()
255
				);
256
			}
257
258
			// Catch image sitemap xml.
259 View Code Duplication
			if ( preg_match( $regex['image'], $request['sitemap_name'] ) ) {
260
				$this->serve_raw_and_die(
261
					$xml_content_type,
262
					$this->librarian->get_sitemap_text(
263
						$request['sitemap_name'],
264
						JP_IMAGE_SITEMAP_TYPE
265
					)
266
				);
267
			}
268
269
			// Catch image sitemap index xml.
270 View Code Duplication
			if ( preg_match( $regex['image-index'], $request['sitemap_name'] ) ) {
271
				$this->serve_raw_and_die(
272
					$xml_content_type,
273
					$this->librarian->get_sitemap_text(
274
						$request['sitemap_name'],
275
						JP_IMAGE_SITEMAP_INDEX_TYPE
276
					)
277
				);
278
			}
279
280
			// Catch image sitemap xsl.
281
			if ( preg_match( $regex['image-style'], $request['sitemap_name'] ) ) {
282
				$this->serve_raw_and_die(
283
					'application/xml',
284
					Jetpack_Sitemap_Stylist::image_sitemap_xsl()
285
				);
286
			}
287
288
			// Catch video sitemap xml.
289 View Code Duplication
			if ( preg_match( $regex['video'], $request['sitemap_name'] ) ) {
290
				$this->serve_raw_and_die(
291
					$xml_content_type,
292
					$this->librarian->get_sitemap_text(
293
						$request['sitemap_name'],
294
						JP_VIDEO_SITEMAP_TYPE
295
					)
296
				);
297
			}
298
299
			// Catch video sitemap index xml.
300 View Code Duplication
			if ( preg_match( $regex['video-index'], $request['sitemap_name'] ) ) {
301
				$this->serve_raw_and_die(
302
					$xml_content_type,
303
					$this->librarian->get_sitemap_text(
304
						$request['sitemap_name'],
305
						JP_VIDEO_SITEMAP_INDEX_TYPE
306
					)
307
				);
308
			}
309
310
			// Catch video sitemap xsl.
311
			if ( preg_match( $regex['video-style'], $request['sitemap_name'] ) ) {
312
				$this->serve_raw_and_die(
313
					'application/xml',
314
					Jetpack_Sitemap_Stylist::video_sitemap_xsl()
315
				);
316
			}
317
318
			// Catch news sitemap xml.
319
			if ( preg_match( $regex['news'], $request['sitemap_name'] ) ) {
320
				$sitemap_builder = new Jetpack_Sitemap_Builder();
321
				$this->serve_raw_and_die(
322
					$xml_content_type,
323
					$sitemap_builder->news_sitemap_xml()
324
				);
325
			}
326
327
			// Catch news sitemap xsl.
328
			if ( preg_match( $regex['news-style'], $request['sitemap_name'] ) ) {
329
				$this->serve_raw_and_die(
330
					'application/xml',
331
					Jetpack_Sitemap_Stylist::news_sitemap_xsl()
332
				);
333
			}
334
		}
335
336
		// URL did not match any sitemap patterns.
337
		return;
338
	}
339
340
	/**
341
	 * Callback for adding sitemap-interval to the list of schedules.
342
	 *
343
	 * @access public
344
	 * @since 4.8.0
345
	 *
346
	 * @param array $schedules The array of WP_Cron schedules.
347
	 *
348
	 * @return array The updated array of WP_Cron schedules.
349
	 */
350
	public function callback_add_sitemap_schedule( $schedules ) {
351
		$schedules['sitemap-interval'] = array(
352
			'interval' => JP_SITEMAP_INTERVAL,
353
			'display'  => __( 'Sitemap Interval', 'jetpack' ),
354
		);
355
		return $schedules;
356
	}
357
358
	/**
359
	 * Add actions to schedule sitemap generation.
360
	 * Should only be called once, in the constructor.
361
	 *
362
	 * @access private
363
	 * @since 4.8.0
364
	 */
365
	private function schedule_sitemap_generation() {
366
		// Add cron schedule.
367
		add_filter( 'cron_schedules', array( $this, 'callback_add_sitemap_schedule' ) );
368
369
		$sitemap_builder = new Jetpack_Sitemap_Builder();
370
371
		add_action(
372
			'jp_sitemap_cron_hook',
373
			array( $sitemap_builder, 'update_sitemap' )
374
		);
375
376
		if ( ! wp_next_scheduled( 'jp_sitemap_cron_hook' ) ) {
377
			wp_schedule_event(
378
				time(),
379
				'sitemap-interval',
380
				'jp_sitemap_cron_hook'
381
			);
382
		}
383
384
		return;
385
	}
386
387
	/**
388
	 * Callback to add sitemap to robots.txt.
389
	 *
390
	 * @access public
391
	 * @since 4.8.0
392
	 */
393
	public function callback_action_do_robotstxt() {
394
395
		/**
396
		 * Filter whether to make the default sitemap discoverable to robots or not. Default true.
397
		 *
398
		 * @module sitemaps
399
		 * @since 3.9.0
400
		 *
401
		 * @param bool $discover_sitemap Make default sitemap discoverable to robots.
402
		 */
403
		$discover_sitemap = apply_filters( 'jetpack_sitemap_generate', true );
404
405 View Code Duplication
		if ( true === $discover_sitemap ) {
406
			$sitemap_url      = $this->finder->construct_sitemap_url( 'sitemap.xml' );
0 ignored issues
show
Coding Style introduced by
Equals sign not aligned correctly; expected 1 space but found 6 spaces

This check looks for improperly formatted assignments.

Every assignment must have exactly one space before and one space after the equals operator.

To illustrate:

$a = "a";
$ab = "ab";
$abc = "abc";

will have no issues, while

$a   = "a";
$ab  = "ab";
$abc = "abc";

will report issues in lines 1 and 2.

Loading history...
407
			echo 'Sitemap: ' . esc_url( $sitemap_url ) . "\n";
408
		}
409
410
		/**
411
		 * Filter whether to make the news sitemap discoverable to robots or not. Default true.
412
		 *
413
		 * @module sitemaps
414
		 * @since 3.9.0
415
		 *
416
		 * @param bool $discover_news_sitemap Make default news sitemap discoverable to robots.
417
		 */
418
		$discover_news_sitemap = apply_filters( 'jetpack_news_sitemap_generate', true );
419
420 View Code Duplication
		if ( true === $discover_news_sitemap ) {
421
			$news_sitemap_url = $this->finder->construct_sitemap_url( 'news-sitemap.xml' );
422
			echo 'Sitemap: ' . esc_url( $news_sitemap_url ) . "\n";
423
		}
424
425
		return;
426
	}
427
428
	/**
429
	 * Callback to delete the news sitemap cache.
430
	 *
431
	 * @access public
432
	 * @since 4.8.0
433
	 */
434
	public function callback_action_flush_news_sitemap_cache() {
435
		delete_transient( 'jetpack_news_sitemap_xml' );
436
	}
437
438
	/**
439
	 * Callback for resetting stored sitemap data.
440
	 *
441
	 * @access public
442
	 * @since 5.3.0
443
	 */
444
	public function callback_action_purge_data() {
445
		$this->callback_action_flush_news_sitemap_cache();
446
		$this->librarian->delete_all_stored_sitemap_data();
447
	}
448
449
	/**
450
	 * Callback to set the sitemap location.
451
	 *
452
	 * @access public
453
	 * @since 4.8.0
454
	 */
455
	public function callback_action_filter_sitemap_location() {
456
		update_option(
457
			'jetpack_sitemap_location',
458
			/**
459
			 * Additional path for sitemap URIs. Default value is empty.
460
			 *
461
			 * This string is any additional path fragment you want included between
462
			 * the home URL and the sitemap filenames. Exactly how this fragment is
463
			 * interpreted depends on your permalink settings. For example:
464
			 *
465
			 *   Pretty permalinks:
466
			 *     home_url() . jetpack_sitemap_location . '/sitemap.xml'
467
			 *
468
			 *   Plain ("ugly") permalinks:
469
			 *     home_url() . jetpack_sitemap_location . '/?jetpack-sitemap=sitemap.xml'
470
			 *
471
			 *   PATHINFO permalinks:
472
			 *     home_url() . '/index.php' . jetpack_sitemap_location . '/sitemap.xml'
473
			 *
474
			 * where 'sitemap.xml' is the name of a specific sitemap file.
475
			 * The value of this filter must be a valid path fragment per RFC 3986;
476
			 * in particular it must either be empty or begin with a '/'.
477
			 * Also take care that any restrictions on sitemap location imposed by
478
			 * the sitemap protocol are satisfied.
479
			 *
480
			 * The result of this filter is stored in an option, 'jetpack_sitemap_location';
481
			 * that option is what gets read when the sitemap location is needed.
482
			 * This way we don't have to wait for init to finish before building sitemaps.
483
			 *
484
			 * @link https://tools.ietf.org/html/rfc3986#section-3.3 RFC 3986
485
			 * @link http://www.sitemaps.org/ The sitemap protocol
486
			 *
487
			 * @since 4.8.0
488
			 */
489
			apply_filters(
490
				'jetpack_sitemap_location',
491
				''
492
			)
493
		);
494
495
		return;
496
	}
497
498
} // End Jetpack_Sitemap_Manager class.
499
500
new Jetpack_Sitemap_Manager();
501
502
/**
503
 * Absolute URL of the current blog's sitemap.
504
 *
505
 * @module sitemaps
506
 *
507
 * @since  3.9.0
508
 * @since  4.8.1 Code uses method found in Jetpack_Sitemap_Finder::construct_sitemap_url in 4.8.0.
509
 *                It has been moved here to avoid fatal errors with other plugins that were expecting to find this function.
510
 *
511
 * @param string $filename Sitemap file name. Defaults to 'sitemap.xml', the initial sitemaps page.
512
 *
513
 * @return string Sitemap URL.
514
 */
515
function jetpack_sitemap_uri( $filename = 'sitemap.xml' ) {
516
	global $wp_rewrite;
517
518
	$location = Jetpack_Options::get_option_and_ensure_autoload( 'jetpack_sitemap_location', '' );
519
520
	if ( $wp_rewrite->using_index_permalinks() ) {
521
		$sitemap_url = home_url( '/index.php' . $location . '/' . $filename );
522
	} elseif ( $wp_rewrite->using_permalinks() ) {
523
		$sitemap_url = home_url( $location . '/' . $filename );
524
	} else {
525
		$sitemap_url = home_url( $location . '/?jetpack-sitemap=' . $filename );
526
	}
527
528
	/**
529
	 * Filter sitemap URL relative to home URL.
530
	 *
531
	 * @module sitemaps
532
	 *
533
	 * @since 3.9.0
534
	 *
535
	 * @param string $sitemap_url Sitemap URL.
536
	 */
537
	return apply_filters( 'jetpack_sitemap_location', $sitemap_url );
538
}