Completed
Push — master-stable ( 287111...36ed8c )
by
unknown
37:27 queued 29:06
created

sitemaps.php ➔ jetpack_sitemap_uri()   B

Complexity

Conditions 3
Paths 3

Size

Total Lines 24
Code Lines 10

Duplication

Lines 0
Ratio 0 %

Importance

Changes 0
Metric Value
cc 3
eloc 10
nc 3
nop 1
dl 0
loc 24
rs 8.9713
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
		/*
112
		 * Module parameters are stored as options in the database.
113
		 * This allows us to avoid having to process all of init
114
		 * before serving the sitemap data. The following actions
115
		 * process and store these filters.
116
		 */
117
118
		// Process filters and store location string for sitemap.
119
		add_action(
120
			'init',
121
			array( $this, 'callback_action_filter_sitemap_location' ),
122
			999
123
		);
124
125
		return;
126
	}
127
128
	/**
129
	 * Echo a raw string of given content-type.
130
	 *
131
	 * @access private
132
	 * @since 4.8.0
133
	 *
134
	 * @param string $the_content_type The content type to be served.
135
	 * @param string $the_content The string to be echoed.
136
	 */
137
	private function serve_raw_and_die( $the_content_type, $the_content ) {
138
		header( 'Content-Type: ' . $the_content_type . '; charset=UTF-8' );
139
140
		if ( '' === $the_content ) {
141
			wp_die(
142
				esc_html__( "No sitemap found. Maybe it's being generated. Please try again later.", 'jetpack' ),
143
				esc_html__( 'Sitemaps', 'jetpack' ),
144
				array(
145
					'response' => 404,
146
				)
147
			);
148
		}
149
150
		echo $the_content;
151
152
		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...
153
	}
154
155
	/**
156
	 * Callback to intercept sitemap url requests and serve sitemap files.
157
	 *
158
	 * @access public
159
	 * @since 4.8.0
160
	 */
161
	public function callback_action_catch_sitemap_urls() {
162
		// Regular expressions for sitemap URL routing.
163
		$regex = array(
164
			'master'        => '/^sitemap\.xml$/',
165
			'sitemap'       => '/^sitemap-[1-9][0-9]*\.xml$/',
166
			'index'         => '/^sitemap-index-[1-9][0-9]*\.xml$/',
167
			'sitemap-style' => '/^sitemap\.xsl$/',
168
			'index-style'   => '/^sitemap-index\.xsl$/',
169
			'image'         => '/^image-sitemap-[1-9][0-9]*\.xml$/',
170
			'image-index'   => '/^image-sitemap-index-[1-9][0-9]*\.xml$/',
171
			'image-style'   => '/^image-sitemap\.xsl$/',
172
			'video'         => '/^video-sitemap-[1-9][0-9]*\.xml$/',
173
			'video-index'   => '/^video-sitemap-index-[1-9][0-9]*\.xml$/',
174
			'video-style'   => '/^video-sitemap\.xsl$/',
175
			'news'          => '/^news-sitemap\.xml$/',
176
			'news-style'    => '/^news-sitemap\.xsl$/',
177
		);
178
179
		// The raw path(+query) of the requested URI.
180
		if ( isset( $_SERVER['REQUEST_URI'] ) ) { // WPCS: Input var okay.
181
			$raw_uri = sanitize_text_field(
182
				wp_unslash( $_SERVER['REQUEST_URI'] ) // WPCS: Input var okay.
183
			);
184
		} else {
185
			$raw_uri = '';
186
		}
187
188
		$request = $this->finder->recognize_sitemap_uri( $raw_uri );
189
190
		if ( isset( $request['sitemap_name'] ) ) {
191
192
			/**
193
			 * Filter the content type used to serve the sitemap XML files.
194
			 *
195
			 * @module sitemaps
196
			 *
197
			 * @since 3.9.0
198
			 *
199
			 * @param string $xml_content_type By default, it's 'text/xml'.
200
			 */
201
			$xml_content_type = apply_filters( 'jetpack_sitemap_content_type', 'text/xml' );
202
203
			// Catch master sitemap xml.
204
			if ( preg_match( $regex['master'], $request['sitemap_name'] ) ) {
205
				$this->serve_raw_and_die(
206
					$xml_content_type,
207
					$this->librarian->get_sitemap_text(
208
						jp_sitemap_filename( JP_MASTER_SITEMAP_TYPE, 0 ),
209
						JP_MASTER_SITEMAP_TYPE
210
					)
211
				);
212
			}
213
214
			// Catch sitemap xml.
215 View Code Duplication
			if ( preg_match( $regex['sitemap'], $request['sitemap_name'] ) ) {
216
				$this->serve_raw_and_die(
217
					$xml_content_type,
218
					$this->librarian->get_sitemap_text(
219
						$request['sitemap_name'],
220
						JP_PAGE_SITEMAP_TYPE
221
					)
222
				);
223
			}
224
225
			// Catch sitemap index xml.
226 View Code Duplication
			if ( preg_match( $regex['index'], $request['sitemap_name'] ) ) {
227
				$this->serve_raw_and_die(
228
					$xml_content_type,
229
					$this->librarian->get_sitemap_text(
230
						$request['sitemap_name'],
231
						JP_PAGE_SITEMAP_INDEX_TYPE
232
					)
233
				);
234
			}
235
236
			// Catch sitemap xsl.
237
			if ( preg_match( $regex['sitemap-style'], $request['sitemap_name'] ) ) {
238
				$this->serve_raw_and_die(
239
					'application/xml',
240
					Jetpack_Sitemap_Stylist::sitemap_xsl()
241
				);
242
			}
243
244
			// Catch sitemap index xsl.
245
			if ( preg_match( $regex['index-style'], $request['sitemap_name'] ) ) {
246
				$this->serve_raw_and_die(
247
					'application/xml',
248
					Jetpack_Sitemap_Stylist::sitemap_index_xsl()
249
				);
250
			}
251
252
			// Catch image sitemap xml.
253 View Code Duplication
			if ( preg_match( $regex['image'], $request['sitemap_name'] ) ) {
254
				$this->serve_raw_and_die(
255
					$xml_content_type,
256
					$this->librarian->get_sitemap_text(
257
						$request['sitemap_name'],
258
						JP_IMAGE_SITEMAP_TYPE
259
					)
260
				);
261
			}
262
263
			// Catch image sitemap index xml.
264 View Code Duplication
			if ( preg_match( $regex['image-index'], $request['sitemap_name'] ) ) {
265
				$this->serve_raw_and_die(
266
					$xml_content_type,
267
					$this->librarian->get_sitemap_text(
268
						$request['sitemap_name'],
269
						JP_IMAGE_SITEMAP_INDEX_TYPE
270
					)
271
				);
272
			}
273
274
			// Catch image sitemap xsl.
275
			if ( preg_match( $regex['image-style'], $request['sitemap_name'] ) ) {
276
				$this->serve_raw_and_die(
277
					'application/xml',
278
					Jetpack_Sitemap_Stylist::image_sitemap_xsl()
279
				);
280
			}
281
282
			// Catch video sitemap xml.
283 View Code Duplication
			if ( preg_match( $regex['video'], $request['sitemap_name'] ) ) {
284
				$this->serve_raw_and_die(
285
					$xml_content_type,
286
					$this->librarian->get_sitemap_text(
287
						$request['sitemap_name'],
288
						JP_VIDEO_SITEMAP_TYPE
289
					)
290
				);
291
			}
292
293
			// Catch video sitemap index xml.
294 View Code Duplication
			if ( preg_match( $regex['video-index'], $request['sitemap_name'] ) ) {
295
				$this->serve_raw_and_die(
296
					$xml_content_type,
297
					$this->librarian->get_sitemap_text(
298
						$request['sitemap_name'],
299
						JP_VIDEO_SITEMAP_INDEX_TYPE
300
					)
301
				);
302
			}
303
304
			// Catch video sitemap xsl.
305
			if ( preg_match( $regex['video-style'], $request['sitemap_name'] ) ) {
306
				$this->serve_raw_and_die(
307
					'application/xml',
308
					Jetpack_Sitemap_Stylist::video_sitemap_xsl()
309
				);
310
			}
311
312
			// Catch news sitemap xml.
313
			if ( preg_match( $regex['news'], $request['sitemap_name'] ) ) {
314
				$sitemap_builder = new Jetpack_Sitemap_Builder();
315
				$this->serve_raw_and_die(
316
					$xml_content_type,
317
					$sitemap_builder->news_sitemap_xml()
318
				);
319
			}
320
321
			// Catch news sitemap xsl.
322
			if ( preg_match( $regex['news-style'], $request['sitemap_name'] ) ) {
323
				$this->serve_raw_and_die(
324
					'application/xml',
325
					Jetpack_Sitemap_Stylist::news_sitemap_xsl()
326
				);
327
			}
328
		}
329
330
		// URL did not match any sitemap patterns.
331
		return;
332
	}
333
334
	/**
335
	 * Callback for adding sitemap-interval to the list of schedules.
336
	 *
337
	 * @access public
338
	 * @since 4.8.0
339
	 *
340
	 * @param array $schedules The array of WP_Cron schedules.
341
	 *
342
	 * @return array The updated array of WP_Cron schedules.
343
	 */
344
	public function callback_add_sitemap_schedule( $schedules ) {
345
		$schedules['sitemap-interval'] = array(
346
			'interval' => JP_SITEMAP_INTERVAL,
347
			'display'  => __( 'Sitemap Interval', 'jetpack' ),
348
		);
349
		return $schedules;
350
	}
351
352
	/**
353
	 * Add actions to schedule sitemap generation.
354
	 * Should only be called once, in the constructor.
355
	 *
356
	 * @access private
357
	 * @since 4.8.0
358
	 */
359
	private function schedule_sitemap_generation() {
360
		// Add cron schedule.
361
		add_filter( 'cron_schedules', array( $this, 'callback_add_sitemap_schedule' ) );
362
363
		$sitemap_builder = new Jetpack_Sitemap_Builder();
364
365
		add_action(
366
			'jp_sitemap_cron_hook',
367
			array( $sitemap_builder, 'update_sitemap' )
368
		);
369
370
		if ( ! wp_next_scheduled( 'jp_sitemap_cron_hook' ) ) {
371
			wp_schedule_event(
372
				time(),
373
				'sitemap-interval',
374
				'jp_sitemap_cron_hook'
375
			);
376
		}
377
378
		return;
379
	}
380
381
	/**
382
	 * Callback to add sitemap to robots.txt.
383
	 *
384
	 * @access public
385
	 * @since 4.8.0
386
	 */
387
	public function callback_action_do_robotstxt() {
388
389
		/**
390
		 * Filter whether to make the default sitemap discoverable to robots or not. Default true.
391
		 *
392
		 * @module sitemaps
393
		 * @since 3.9.0
394
		 *
395
		 * @param bool $discover_sitemap Make default sitemap discoverable to robots.
396
		 */
397
		$discover_sitemap = apply_filters( 'jetpack_sitemap_generate', true );
398
399 View Code Duplication
		if ( true === $discover_sitemap ) {
400
			$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...
401
			echo 'Sitemap: ' . esc_url( $sitemap_url ) . "\n";
402
		}
403
404
		/**
405
		 * Filter whether to make the news sitemap discoverable to robots or not. Default true.
406
		 *
407
		 * @module sitemaps
408
		 * @since 3.9.0
409
		 *
410
		 * @param bool $discover_news_sitemap Make default news sitemap discoverable to robots.
411
		 */
412
		$discover_news_sitemap = apply_filters( 'jetpack_news_sitemap_generate', true );
413
414 View Code Duplication
		if ( true === $discover_news_sitemap ) {
415
			$news_sitemap_url = $this->finder->construct_sitemap_url( 'news-sitemap.xml' );
416
			echo 'Sitemap: ' . esc_url( $news_sitemap_url ) . "\n";
417
		}
418
419
		return;
420
	}
421
422
	/**
423
	 * Callback to delete the news sitemap cache.
424
	 *
425
	 * @access public
426
	 * @since 4.8.0
427
	 */
428
	public function callback_action_flush_news_sitemap_cache() {
429
		delete_transient( 'jetpack_news_sitemap_xml' );
430
	}
431
432
	/**
433
	 * Callback to set the sitemap location.
434
	 *
435
	 * @access public
436
	 * @since 4.8.0
437
	 */
438
	public function callback_action_filter_sitemap_location() {
439
		update_option(
440
			'jetpack_sitemap_location',
441
			/**
442
			 * Additional path for sitemap URIs. Default value is empty.
443
			 *
444
			 * This string is any additional path fragment you want included between
445
			 * the home URL and the sitemap filenames. Exactly how this fragment is
446
			 * interpreted depends on your permalink settings. For example:
447
			 *
448
			 *   Pretty permalinks:
449
			 *     home_url() . jetpack_sitemap_location . '/sitemap.xml'
450
			 *
451
			 *   Plain ("ugly") permalinks:
452
			 *     home_url() . jetpack_sitemap_location . '/?jetpack-sitemap=sitemap.xml'
453
			 *
454
			 *   PATHINFO permalinks:
455
			 *     home_url() . '/index.php' . jetpack_sitemap_location . '/sitemap.xml'
456
			 *
457
			 * where 'sitemap.xml' is the name of a specific sitemap file.
458
			 * The value of this filter must be a valid path fragment per RFC 3986;
459
			 * in particular it must either be empty or begin with a '/'.
460
			 * Also take care that any restrictions on sitemap location imposed by
461
			 * the sitemap protocol are satisfied.
462
			 *
463
			 * The result of this filter is stored in an option, 'jetpack_sitemap_location';
464
			 * that option is what gets read when the sitemap location is needed.
465
			 * This way we don't have to wait for init to finish before building sitemaps.
466
			 *
467
			 * @link https://tools.ietf.org/html/rfc3986#section-3.3 RFC 3986
468
			 * @link http://www.sitemaps.org/ The sitemap protocol
469
			 *
470
			 * @since 4.8.0
471
			 */
472
			apply_filters(
473
				'jetpack_sitemap_location',
474
				''
475
			)
476
		);
477
478
		return;
479
	}
480
481
} // End Jetpack_Sitemap_Manager class.
482
483
new Jetpack_Sitemap_Manager();
484
485
/**
486
 * Absolute URL of the current blog's sitemap.
487
 *
488
 * @module sitemaps
489
 *
490
 * @since  3.9.0
491
 * @since  4.8.1 Code uses method found in Jetpack_Sitemap_Finder::construct_sitemap_url in 4.8.0.
492
 *                It has been moved here to avoid fatal errors with other plugins that were expecting to find this function.
493
 *
494
 * @param string $filename Sitemap file name. Defaults to 'sitemap.xml', the initial sitemaps page.
495
 *
496
 * @return string Sitemap URL.
497
 */
498
function jetpack_sitemap_uri( $filename = 'sitemap.xml' ) {
499
	global $wp_rewrite;
500
501
	$location = Jetpack_Options::get_option_and_ensure_autoload( 'jetpack_sitemap_location', '' );
502
503
	if ( $wp_rewrite->using_index_permalinks() ) {
504
		$sitemap_url = home_url( '/index.php' . $location . '/' . $filename );
505
	} elseif ( $wp_rewrite->using_permalinks() ) {
506
		$sitemap_url = home_url( $location . '/' . $filename );
507
	} else {
508
		$sitemap_url = home_url( $location . '/?jetpack-sitemap=' . $filename );
509
	}
510
511
	/**
512
	 * Filter sitemap URL relative to home URL.
513
	 *
514
	 * @module sitemaps
515
	 *
516
	 * @since 3.9.0
517
	 *
518
	 * @param string $sitemap_url Sitemap URL.
519
	 */
520
	return apply_filters( 'jetpack_sitemap_location', $sitemap_url );
521
}