MediaWiki  master
SearchOracle.php
Go to the documentation of this file.
1 <?php
28 
34  private $reservedWords = [
35  'ABOUT' => 1,
36  'ACCUM' => 1,
37  'AND' => 1,
38  'BT' => 1,
39  'BTG' => 1,
40  'BTI' => 1,
41  'BTP' => 1,
42  'FUZZY' => 1,
43  'HASPATH' => 1,
44  'INPATH' => 1,
45  'MINUS' => 1,
46  'NEAR' => 1,
47  'NOT' => 1,
48  'NT' => 1,
49  'NTG' => 1,
50  'NTI' => 1,
51  'NTP' => 1,
52  'OR' => 1,
53  'PT' => 1,
54  'RT' => 1,
55  'SQE' => 1,
56  'SYN' => 1,
57  'TR' => 1,
58  'TRSYN' => 1,
59  'TT' => 1,
60  'WITHIN' => 1,
61  ];
62 
69  protected function doSearchTextInDB( $term ) {
70  if ( $term == '' ) {
71  return new SqlSearchResultSet( false, '' );
72  }
73 
74  $resultSet = $this->db->query( $this->getQuery( $this->filter( $term ), true ) );
75  return new SqlSearchResultSet( $resultSet, $this->searchTerms );
76  }
77 
84  protected function doSearchTitleInDB( $term ) {
85  if ( $term == '' ) {
86  return new SqlSearchResultSet( false, '' );
87  }
88 
89  $resultSet = $this->db->query( $this->getQuery( $this->filter( $term ), false ) );
90  return new SqlSearchResultSet( $resultSet, $this->searchTerms );
91  }
92 
97  private function queryNamespaces() {
98  if ( is_null( $this->namespaces ) ) {
99  return '';
100  }
101  if ( $this->namespaces === [] ) {
102  $namespaces = '0';
103  } else {
104  $namespaces = $this->db->makeList( $this->namespaces );
105  }
106  return 'AND page_namespace IN (' . $namespaces . ')';
107  }
108 
116  private function queryLimit( $sql ) {
117  return $this->db->limitResult( $sql, $this->limit, $this->offset );
118  }
119 
128  function queryRanking( $filteredTerm, $fulltext ) {
129  return ' ORDER BY score(1)';
130  }
131 
139  private function getQuery( $filteredTerm, $fulltext ) {
140  return $this->queryLimit( $this->queryMain( $filteredTerm, $fulltext ) . ' ' .
141  $this->queryNamespaces() . ' ' .
142  $this->queryRanking( $filteredTerm, $fulltext ) . ' ' );
143  }
144 
150  private function getIndexField( $fulltext ) {
151  return $fulltext ? 'si_text' : 'si_title';
152  }
153 
161  function queryMain( $filteredTerm, $fulltext ) {
162  $match = $this->parseQuery( $filteredTerm, $fulltext );
163  $page = $this->db->tableName( 'page' );
164  $searchindex = $this->db->tableName( 'searchindex' );
165  return 'SELECT page_id, page_namespace, page_title ' .
166  "FROM $page,$searchindex " .
167  'WHERE page_id=si_page AND ' . $match;
168  }
169 
177  private function parseQuery( $filteredText, $fulltext ) {
178  $lc = $this->legalSearchChars( self::CHARS_NO_SYNTAX );
179  $this->searchTerms = [];
180 
181  # @todo FIXME: This doesn't handle parenthetical expressions.
182  $m = [];
183  $searchon = '';
184  if ( preg_match_all( '/([-+<>~]?)(([' . $lc . ']+)(\*?)|"[^"]*")/',
185  $filteredText, $m, PREG_SET_ORDER ) ) {
186  foreach ( $m as $terms ) {
187  // Search terms in all variant forms, only
188  // apply on wiki with LanguageConverter
189  $temp_terms = MediaWikiServices::getInstance()->getContentLanguage()->
190  autoConvertToAllVariants( $terms[2] );
191  if ( is_array( $temp_terms ) ) {
192  $temp_terms = array_unique( array_values( $temp_terms ) );
193  foreach ( $temp_terms as $t ) {
194  $searchon .= ( $terms[1] == '-' ? ' ~' : ' & ' ) . $this->escapeTerm( $t );
195  }
196  } else {
197  $searchon .= ( $terms[1] == '-' ? ' ~' : ' & ' ) . $this->escapeTerm( $terms[2] );
198  }
199  if ( !empty( $terms[3] ) ) {
200  $regexp = preg_quote( $terms[3], '/' );
201  if ( $terms[4] ) {
202  $regexp .= "[0-9A-Za-z_]+";
203  }
204  } else {
205  $regexp = preg_quote( str_replace( '"', '', $terms[2] ), '/' );
206  }
207  $this->searchTerms[] = $regexp;
208  }
209  }
210 
211  $searchon = $this->db->addQuotes( ltrim( $searchon, ' &' ) );
212  $field = $this->getIndexField( $fulltext );
213  return " CONTAINS($field, $searchon, 1) > 0 ";
214  }
215 
216  private function escapeTerm( $t ) {
217  $t = MediaWikiServices::getInstance()->getContentLanguage()->normalizeForSearch( $t );
218  $t = isset( $this->reservedWords[strtoupper( $t )] ) ? '{' . $t . '}' : $t;
219  $t = preg_replace( '/^"(.*)"$/', '($1)', $t );
220  $t = preg_replace( '/([-&|])/', '\\\\$1', $t );
221  return $t;
222  }
223 
232  function update( $id, $title, $text ) {
233  $dbw = wfGetDB( DB_MASTER );
234  $dbw->replace( 'searchindex',
235  [ 'si_page' ],
236  [
237  'si_page' => $id,
238  'si_title' => $title,
239  'si_text' => $text
240  ], 'SearchOracle::update' );
241 
242  // Sync the index
243  // We need to specify the DB name (i.e. user/schema) here so that
244  // it can work from the installer, where
245  // ALTER SESSION SET CURRENT_SCHEMA = ...
246  // was used.
247  $dbw->query( "CALL ctx_ddl.sync_index(" .
248  $dbw->addQuotes( $dbw->getDBname() . '.' . $dbw->tableName( 'si_text_idx', 'raw' ) ) . ")" );
249  $dbw->query( "CALL ctx_ddl.sync_index(" .
250  $dbw->addQuotes( $dbw->getDBname() . '.' . $dbw->tableName( 'si_title_idx', 'raw' ) ) . ")" );
251  }
252 
260  function updateTitle( $id, $title ) {
261  $dbw = wfGetDB( DB_MASTER );
262 
263  $dbw->update( 'searchindex',
264  [ 'si_title' => $title ],
265  [ 'si_page' => $id ],
266  'SearchOracle::updateTitle',
267  [] );
268  }
269 
270  public function legalSearchChars( $type = self::CHARS_ALL ) {
271  $searchChars = parent::legalSearchChars( $type );
272  if ( $type === self::CHARS_ALL ) {
273  $searchChars = "\"" . $searchChars;
274  }
275  return $searchChars;
276  }
277 }
update( $id, $title, $text)
Create or update the search index record for the given page.
legalSearchChars( $type=self::CHARS_ALL)
getQuery( $filteredTerm, $fulltext)
Construct the full SQL query to do the search.
whereas SearchGetNearMatch runs after $term
Definition: hooks.txt:2875
to move a page</td >< td > &*You are moving the page across namespaces
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
queryNamespaces()
Return a partial WHERE clause to limit the search to the given namespaces.
wfGetDB( $db, $groups=[], $wiki=false)
Get a Database object.
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:23
const DB_MASTER
Definition: defines.php:26
Search engine hook base class for Oracle (ConText).
doSearchTitleInDB( $term)
Perform a title-only search query and return a result set.
updateTitle( $id, $title)
Update a search index record&#39;s title only.
This class is used for different SQL-based search engines shipped with MediaWiki. ...
doSearchTextInDB( $term)
Perform a full text search query and return a result set.
namespace and then decline to actually register it file or subcat img or subcat $title
Definition: hooks.txt:925
parseQuery( $filteredText, $fulltext)
Parse a user input search string, and return an SQL fragment to be used as part of a WHERE clause...
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:9
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:35
int [] null $namespaces
getIndexField( $fulltext)
Picks which field to index on, depending on what type of query.
filter( $text)
Return a &#39;cleaned up&#39; search string.
queryMain( $filteredTerm, $fulltext)
Get the base part of the search query.
Base search engine base class for database-backed searches.
queryRanking( $filteredTerm, $fulltext)
Does not do anything for generic search engine subclasses may define this though. ...
queryLimit( $sql)
Return a LIMIT clause to limit results on the query.