includes/search/ParserOutputSearchDataExtractor.php

   1 <?php
   2
   3 namespace MediaWiki\Search;
   4
   5 use MediaWiki\Parser\ParserOutput;
   6 use MediaWiki\Parser\ParserOutputLinkTypes;
   7 use MediaWiki\Title\Title;
   8
   9 /**
  10  * Extracts data from ParserOutput for indexing in the search engine.
  11  *
  12  * This program is free software; you can redistribute it and/or modify
  13  * it under the terms of the GNU General Public License as published by
  14  * the Free Software Foundation; either version 2 of the License, or
  15  * (at your option) any later version.
  16  *
  17  * This program is distributed in the hope that it will be useful,
  18  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  19  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  20  * GNU General Public License for more details.
  21  *
  22  * You should have received a copy of the GNU General Public License along
  23  * with this program; if not, write to the Free Software Foundation, Inc.,
  24  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  25  * http://www.gnu.org/copyleft/gpl.html
  26  *
  27  * @since 1.28
  28  */
  29 class ParserOutputSearchDataExtractor {
  30
  31         /**
  32          * Get a list of categories, as an array with title text strings.
  33          *
  34          * @param ParserOutput $parserOutput
  35          * @return string[]
  36          */
  37         public function getCategories( ParserOutput $parserOutput ) {
  38                 $categories = [];
  39
  40                 foreach (
  41                         $parserOutput->getLinkList( ParserOutputLinkTypes::CATEGORY )
  42                         as [ 'link' => $link ]
  43                 ) {
  44                         $categories[] = $link->getText();
  45                 }
  46
  47                 return $categories;
  48         }
  49
  50         /**
  51          * Get a list of external links from ParserOutput, as an array of strings.
  52          *
  53          * @param ParserOutput $parserOutput
  54          * @return string[]
  55          */
  56         public function getExternalLinks( ParserOutput $parserOutput ) {
  57                 return array_keys( $parserOutput->getExternalLinks() );
  58         }
  59
  60         /**
  61          * Get a list of outgoing wiki links (including interwiki links), as
  62          * an array of prefixed title strings.
  63          *
  64          * @param ParserOutput $parserOutput
  65          * @return string[]
  66          */
  67         public function getOutgoingLinks( ParserOutput $parserOutput ) {
  68                 $outgoingLinks = [];
  69
  70                 foreach (
  71                         $parserOutput->getLinkList( ParserOutputLinkTypes::LOCAL )
  72                         as [ 'link' => $link ]
  73                 ) {
  74                         // XXX should use a TitleFormatter
  75                         // XXX why is this a DBkey when all of the others are text?
  76                         $outgoingLinks[] =
  77                                 Title::newFromLinkTarget( $link )->getPrefixedDBkey();
  78                 }
  79
  80                 return $outgoingLinks;
  81         }
  82
  83         /**
  84          * Get a list of templates used in the ParserOutput content, as prefixed title strings
  85          *
  86          * @param ParserOutput $parserOutput
  87          * @return string[]
  88          */
  89         public function getTemplates( ParserOutput $parserOutput ) {
  90                 $templates = [];
  91
  92                 foreach (
  93                         $parserOutput->getLinkList( ParserOutputLinkTypes::TEMPLATE )
  94                         as [ 'link' => $link ]
  95                 ) {
  96                         // XXX should use a TitleFormatter
  97                         $templates[] =
  98                                 Title::newFromLinkTarget( $link )->getPrefixedText();
  99                 }
 100
 101                 return $templates;
 102         }
 103
 104 }