summaryrefslogtreecommitdiff
path: root/includes/search/SearchUpdate.php
blob: 82a413e920c4b2e7e1d853a9d70af4d167c3fcf8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
<?php
/**
 * Search index updater
 *
 * See deferred.txt
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 * http://www.gnu.org/copyleft/gpl.html
 *
 * @file
 * @ingroup Search
 */

/**
 * Database independant search index updater
 *
 * @ingroup Search
 */
class SearchUpdate implements DeferrableUpdate {
	/**
	 * Page id being updated
	 * @var int
	 */
	private $id = 0;

	/**
	 * Title we're updating
	 * @var Title
	 */
	private $title;

	/**
	 * Content of the page (not text)
	 * @var Content|false
	 */
	private $content;

	/**
	 * Constructor
	 *
	 * @param int $id Page id to update
	 * @param Title|string $title Title of page to update
	 * @param Content|string|false $c Content of the page to update.
	 *  If a Content object, text will be gotten from it. String is for back-compat.
	 *  Passing false tells the backend to just update the title, not the content
	 */
	public function __construct( $id, $title, $c = false ) {
		if ( is_string( $title ) ) {
			$nt = Title::newFromText( $title );
		} else {
			$nt = $title;
		}

		if ( $nt ) {
			$this->id = $id;
			// is_string() check is back-compat for ApprovedRevs
			if ( is_string( $c ) ) {
				$this->content = new TextContent( $c );
			} else {
				$this->content = $c ?: false;
			}
			$this->title = $nt;
		} else {
			wfDebug( "SearchUpdate object created with invalid title '$title'\n" );
		}
	}

	/**
	 * Perform actual update for the entry
	 */
	public function doUpdate() {
		global $wgDisableSearchUpdate;

		if ( $wgDisableSearchUpdate || !$this->id ) {
			return;
		}

		wfProfileIn( __METHOD__ );

		$page = WikiPage::newFromId( $this->id, WikiPage::READ_LATEST );
		$indexTitle = Title::indexTitle( $this->title->getNamespace(), $this->title->getText() );

		foreach ( SearchEngine::getSearchTypes() as $type ) {
			$search = SearchEngine::create( $type );
			if ( !$search->supports( 'search-update' ) ) {
				continue;
			}

			$normalTitle = $search->normalizeText( $indexTitle );

			if ( $page === null ) {
				$search->delete( $this->id, $normalTitle );
				continue;
			} elseif ( $this->content === false ) {
				$search->updateTitle( $this->id, $normalTitle );
				continue;
			}

			$text = $search->getTextFromContent( $this->title, $this->content );
			if ( !$search->textAlreadyUpdatedForIndex() ) {
				$text = self::updateText( $text );
			}

			# Perform the actual update
			$search->update( $this->id, $normalTitle, $search->normalizeText( $text ) );
		}

		wfProfileOut( __METHOD__ );
	}

	/**
	 * Clean text for indexing. Only really suitable for indexing in databases.
	 * If you're using a real search engine, you'll probably want to override
	 * this behavior and do something nicer with the original wikitext.
	 */
	public static function updateText( $text ) {
		global $wgContLang;

		# Language-specific strip/conversion
		$text = $wgContLang->normalizeForSearch( $text );
		$lc = SearchEngine::legalSearchChars() . '&#;';

		wfProfileIn( __METHOD__ . '-regexps' );
		$text = preg_replace( "/<\\/?\\s*[A-Za-z][^>]*?>/",
			' ', $wgContLang->lc( " " . $text . " " ) ); # Strip HTML markup
		$text = preg_replace( "/(^|\\n)==\\s*([^\\n]+)\\s*==(\\s)/sD",
			"\\1\\2 \\2 \\2\\3", $text ); # Emphasize headings

		# Strip external URLs
		$uc = "A-Za-z0-9_\\/:.,~%\\-+&;#?!=()@\\x80-\\xFF";
		$protos = "http|https|ftp|mailto|news|gopher";
		$pat = "/(^|[^\\[])({$protos}):[{$uc}]+([^{$uc}]|$)/";
		$text = preg_replace( $pat, "\\1 \\3", $text );

		$p1 = "/([^\\[])\\[({$protos}):[{$uc}]+]/";
		$p2 = "/([^\\[])\\[({$protos}):[{$uc}]+\\s+([^\\]]+)]/";
		$text = preg_replace( $p1, "\\1 ", $text );
		$text = preg_replace( $p2, "\\1 \\3 ", $text );

		# Internal image links
		$pat2 = "/\\[\\[image:([{$uc}]+)\\.(gif|png|jpg|jpeg)([^{$uc}])/i";
		$text = preg_replace( $pat2, " \\1 \\3", $text );

		$text = preg_replace( "/([^{$lc}])([{$lc}]+)]]([a-z]+)/",
			"\\1\\2 \\2\\3", $text ); # Handle [[game]]s

		# Strip all remaining non-search characters
		$text = preg_replace( "/[^{$lc}]+/", " ", $text );

		# Handle 's, s'
		#
		#   $text = preg_replace( "/([{$lc}]+)'s /", "\\1 \\1's ", $text );
		#   $text = preg_replace( "/([{$lc}]+)s' /", "\\1s ", $text );
		#
		# These tail-anchored regexps are insanely slow. The worst case comes
		# when Japanese or Chinese text (ie, no word spacing) is written on
		# a wiki configured for Western UTF-8 mode. The Unicode characters are
		# expanded to hex codes and the "words" are very long paragraph-length
		# monstrosities. On a large page the above regexps may take over 20
		# seconds *each* on a 1GHz-level processor.
		#
		# Following are reversed versions which are consistently fast
		# (about 3 milliseconds on 1GHz-level processor).
		#
		$text = strrev( preg_replace( "/ s'([{$lc}]+)/", " s'\\1 \\1", strrev( $text ) ) );
		$text = strrev( preg_replace( "/ 's([{$lc}]+)/", " s\\1", strrev( $text ) ) );

		# Strip wiki '' and '''
		$text = preg_replace( "/''[']*/", " ", $text );
		wfProfileOut( __METHOD__ . '-regexps' );
		return $text;
	}
}