includes/search/ParserOutputSearchDataExtractor.php

   1 <?php
   2
   3 namespace MediaWiki\Search;
   4
   5 use Category;
   6 use ParserOutput;
   7 use 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 ( $parserOutput->getCategoryLinks() as $key ) {
  41                         $categories[] = Category::newFromName( $key )->getTitle()->getText();
  42                 }
  43
  44                 return $categories;
  45         }
  46
  47         /**
  48          * Get a list of external links from ParserOutput, as an array of strings.
  49          *
  50          * @param ParserOutput $parserOutput
  51          * @return string[]
  52          */
  53         public function getExternalLinks( ParserOutput $parserOutput ) {
  54                 return array_keys( $parserOutput->getExternalLinks() );
  55         }
  56
  57         /**
  58          * Get a list of outgoing wiki links (including interwiki links), as
  59          * an array of prefixed title strings.
  60          *
  61          * @param ParserOutput $parserOutput
  62          * @return string[]
  63          */
  64         public function getOutgoingLinks( ParserOutput $parserOutput ) {
  65                 $outgoingLinks = [];
  66
  67                 foreach ( $parserOutput->getLinks() as $linkedNamespace => $namespaceLinks ) {
  68                         foreach ( array_keys( $namespaceLinks ) as $linkedDbKey ) {
  69                                 $outgoingLinks[] =
  70                                         Title::makeTitle( $linkedNamespace, $linkedDbKey )->getPrefixedDBkey();
  71                         }
  72                 }
  73
  74                 return $outgoingLinks;
  75         }
  76
  77         /**
  78          * Get a list of templates used in the ParserOutput content, as prefixed title strings
  79          *
  80          * @param ParserOutput $parserOutput
  81          * @return string[]
  82          */
  83         public function getTemplates( ParserOutput $parserOutput ) {
  84                 $templates = [];
  85
  86                 foreach ( $parserOutput->getTemplates() as $tNS => $templatesInNS ) {
  87                         foreach ( array_keys( $templatesInNS ) as $tDbKey ) {
  88                                 $templateTitle = Title::makeTitle( $tNS, $tDbKey );
  89                                 $templates[] = $templateTitle->getPrefixedText();
  90                         }
  91                 }
  92
  93                 return $templates;
  94         }
  95
  96 }