MediaWiki  REL1_31
SearchUpdate.php
Go to the documentation of this file.
1 <?php
27 
33 class SearchUpdate implements DeferrableUpdate {
35  private $id = 0;
36 
38  private $title;
39 
41  private $content;
42 
44  private $page;
45 
53  public function __construct( $id, $title, $c = false ) {
54  if ( is_string( $title ) ) {
55  $nt = Title::newFromText( $title );
56  } else {
57  $nt = $title;
58  }
59 
60  if ( $nt ) {
61  $this->id = $id;
62  // is_string() check is back-compat for ApprovedRevs
63  if ( is_string( $c ) ) {
64  $this->content = new TextContent( $c );
65  } else {
66  $this->content = $c ?: false;
67  }
68  $this->title = $nt;
69  } else {
70  wfDebug( "SearchUpdate object created with invalid title '$title'\n" );
71  }
72  }
73 
77  public function doUpdate() {
78  $config = MediaWikiServices::getInstance()->getSearchEngineConfig();
79 
80  if ( $config->getConfig()->get( 'DisableSearchUpdate' ) || !$this->id ) {
81  return;
82  }
83 
84  $seFactory = MediaWikiServices::getInstance()->getSearchEngineFactory();
85  foreach ( $config->getSearchTypes() as $type ) {
86  $search = $seFactory->create( $type );
87  if ( !$search->supports( 'search-update' ) ) {
88  continue;
89  }
90 
91  $normalTitle = $this->getNormalizedTitle( $search );
92 
93  if ( $this->getLatestPage() === null ) {
94  $search->delete( $this->id, $normalTitle );
95  continue;
96  } elseif ( $this->content === false ) {
97  $search->updateTitle( $this->id, $normalTitle );
98  continue;
99  }
100 
101  $text = $search->getTextFromContent( $this->title, $this->content );
102  if ( !$search->textAlreadyUpdatedForIndex() ) {
103  $text = $this->updateText( $text, $search );
104  }
105 
106  # Perform the actual update
107  $search->update( $this->id, $normalTitle, $search->normalizeText( $text ) );
108  }
109  }
110 
119  public function updateText( $text, SearchEngine $se = null ) {
121 
122  # Language-specific strip/conversion
123  $text = $wgContLang->normalizeForSearch( $text );
124  $se = $se ?: MediaWikiServices::getInstance()->newSearchEngine();
125  $lc = $se->legalSearchChars() . '&#;';
126 
127  $text = preg_replace( "/<\\/?\\s*[A-Za-z][^>]*?>/",
128  ' ', $wgContLang->lc( " " . $text . " " ) ); # Strip HTML markup
129  $text = preg_replace( "/(^|\\n)==\\s*([^\\n]+)\\s*==(\\s)/sD",
130  "\\1\\2 \\2 \\2\\3", $text ); # Emphasize headings
131 
132  # Strip external URLs
133  $uc = "A-Za-z0-9_\\/:.,~%\\-+&;#?!=()@\\x80-\\xFF";
134  $protos = "http|https|ftp|mailto|news|gopher";
135  $pat = "/(^|[^\\[])({$protos}):[{$uc}]+([^{$uc}]|$)/";
136  $text = preg_replace( $pat, "\\1 \\3", $text );
137 
138  $p1 = "/([^\\[])\\[({$protos}):[{$uc}]+]/";
139  $p2 = "/([^\\[])\\[({$protos}):[{$uc}]+\\s+([^\\]]+)]/";
140  $text = preg_replace( $p1, "\\1 ", $text );
141  $text = preg_replace( $p2, "\\1 \\3 ", $text );
142 
143  # Internal image links
144  $pat2 = "/\\[\\[image:([{$uc}]+)\\.(gif|png|jpg|jpeg)([^{$uc}])/i";
145  $text = preg_replace( $pat2, " \\1 \\3", $text );
146 
147  $text = preg_replace( "/([^{$lc}])([{$lc}]+)]]([a-z]+)/",
148  "\\1\\2 \\2\\3", $text ); # Handle [[game]]s
149 
150  # Strip all remaining non-search characters
151  $text = preg_replace( "/[^{$lc}]+/", " ", $text );
152 
169  $text = strrev( preg_replace( "/ s'([{$lc}]+)/", " s'\\1 \\1", strrev( $text ) ) );
170  $text = strrev( preg_replace( "/ 's([{$lc}]+)/", " s\\1", strrev( $text ) ) );
171 
172  # Strip wiki '' and '''
173  $text = preg_replace( "/''[']*/", " ", $text );
174 
175  return $text;
176  }
177 
187  private function getLatestPage() {
188  if ( !isset( $this->page ) ) {
189  $this->page = WikiPage::newFromID( $this->id, WikiPage::READ_LATEST );
190  }
191 
192  return $this->page;
193  }
194 
202  private function getNormalizedTitle( SearchEngine $search ) {
204 
205  $ns = $this->title->getNamespace();
206  $title = $this->title->getText();
207 
208  $lc = $search->legalSearchChars() . '&#;';
209  $t = $wgContLang->normalizeForSearch( $title );
210  $t = preg_replace( "/[^{$lc}]+/", ' ', $t );
211  $t = $wgContLang->lc( $t );
212 
213  # Handle 's, s'
214  $t = preg_replace( "/([{$lc}]+)'s( |$)/", "\\1 \\1's ", $t );
215  $t = preg_replace( "/([{$lc}]+)s'( |$)/", "\\1s ", $t );
216 
217  $t = preg_replace( "/\\s+/", ' ', $t );
218 
219  if ( $ns == NS_FILE ) {
220  $t = preg_replace( "/ (png|gif|jpg|jpeg|ogg)$/", "", $t );
221  }
222 
223  return $search->normalizeText( trim( $t ) );
224  }
225 }
SearchEngine\legalSearchChars
static legalSearchChars( $type=self::CHARS_ALL)
Get chars legal for search NOTE: usage as static is deprecated and preserved only as BC measure.
Definition: SearchEngine.php:221
Title\newFromText
static newFromText( $text, $defaultNamespace=NS_MAIN)
Create a new Title from text, such as what one would find in a link.
Definition: Title.php:273
use
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
Definition: APACHE-LICENSE-2.0.txt:10
content
per default it will return the text for text based content
Definition: contenthandler.txt:104
SearchUpdate\updateText
updateText( $text, SearchEngine $se=null)
Clean text for indexing.
Definition: SearchUpdate.php:119
SearchEngine\normalizeText
normalizeText( $string)
When overridden in derived class, performs database-specific conversions on text to be used for searc...
Definition: SearchEngine.php:155
SearchUpdate
Database independant search index updater.
Definition: SearchUpdate.php:33
WikiPage
Class representing a MediaWiki article and history.
Definition: WikiPage.php:37
NS_FILE
const NS_FILE
Definition: Defines.php:80
page
target page
Definition: All_system_messages.txt:1267
php
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency which acts as the top level factory for services in MediaWiki which can be used to gain access to default instances of various services MediaWikiServices however also allows new services to be defined and default services to be redefined Services are defined or redefined by providing a callback the instantiator that will return a new instance of the service When it will create an instance of MediaWikiServices and populate it with the services defined in the files listed by thereby bootstrapping the DI framework Per $wgServiceWiringFiles lists includes ServiceWiring php
Definition: injection.txt:37
title
title
Definition: parserTests.txt:219
global
when a variable name is used in a it is silently declared as a new masking the global
Definition: design.txt:95
wfDebug
wfDebug( $text, $dest='all', array $context=[])
Sends a line to the debug log if enabled or, optionally, to a comment in output.
Definition: GlobalFunctions.php:994
WikiPage\newFromID
static newFromID( $id, $from='fromdb')
Constructor from a page id.
Definition: WikiPage.php:153
SearchUpdate\$id
int $id
Page id being updated.
Definition: SearchUpdate.php:35
TextContent
Content object implementation for representing flat text.
Definition: TextContent.php:35
SearchEngine
Contain a class for special pages.
Definition: SearchEngine.php:34
Content
Base interface for content objects.
Definition: Content.php:34
Title
Represents a title within MediaWiki.
Definition: Title.php:39
SearchUpdate\$page
WikiPage $page
Definition: SearchUpdate.php:44
SearchUpdate\__construct
__construct( $id, $title, $c=false)
Definition: SearchUpdate.php:53
SearchUpdate\getLatestPage
getLatestPage()
Get WikiPage for the SearchUpdate $id using WikiPage::READ_LATEST and ensure using the same WikiPage ...
Definition: SearchUpdate.php:187
as
This document is intended to provide useful advice for parties seeking to redistribute MediaWiki to end users It s targeted particularly at maintainers for Linux since it s been observed that distribution packages of MediaWiki often break We ve consistently had to recommend that users seeking support use official tarballs instead of their distribution s and this often solves whatever problem the user is having It would be nice if this could such as
Definition: distributors.txt:22
SearchUpdate\$content
Content bool $content
Content of the page (not text)
Definition: SearchUpdate.php:41
SearchUpdate\getNormalizedTitle
getNormalizedTitle(SearchEngine $search)
Get a normalized string representation of a title suitable for including in a search index.
Definition: SearchUpdate.php:202
$t
$t
Definition: testCompression.php:69
DeferrableUpdate
Interface that deferrable updates should implement.
Definition: DeferrableUpdate.php:9
MediaWikiServices
injection txt This is an overview of how MediaWiki makes use of dependency injection The design described here grew from the discussion of RFC T384 The term dependency this means that anything an object needs to operate should be injected from the the object itself should only know narrow no concrete implementation of the logic it relies on The requirement to inject everything typically results in an architecture that based on two main types of and essentially stateless service objects that use other service objects to operate on the value objects As of the beginning MediaWiki is only starting to use the DI approach Much of the code still relies on global state or direct resulting in a highly cyclical dependency MediaWikiServices
Definition: injection.txt:25
SearchUpdate\$title
Title $title
Title we're updating.
Definition: SearchUpdate.php:38
SearchUpdate\doUpdate
doUpdate()
Perform actual update for the entry.
Definition: SearchUpdate.php:77
$wgContLang
this class mediates it Skin Encapsulates a look and feel for the wiki All of the functions that render HTML and make choices about how to render it are here and are called from various other places when and is meant to be subclassed with other skins that may override some of its functions The User object contains a reference to a and so rather than having a global skin object we just rely on the global User and get the skin with $wgUser and also has some character encoding functions and other locale stuff The current user interface language is instantiated as and the content language as $wgContLang
Definition: design.txt:57
$type
$type
Definition: testCompression.php:48