MediaWiki  REL1_31
WikiTextStructure.php
Go to the documentation of this file.
1 <?php
2 
3 use HtmlFormatter\HtmlFormatter;
4 
12  private $openingText;
16  private $allText;
20  private $auxText = [];
24  private $parserOutput;
25 
30  // "it looks like you don't have javascript enabled..." – do not need to index
31  'audio', 'video',
32  // CSS stylesheets aren't content
33  'style',
34  // The [1] for references
35  'sup.reference',
36  // The ↑ next to references in the references section
37  '.mw-cite-backlink',
38  // Headings are already indexed in their own field.
39  'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
40  // Collapsed fields are hidden by default so we don't want them showing up.
41  '.autocollapse',
42  // Content explicitly decided to be not searchable by editors such
43  // as custom navigation templates.
44  '.navigation-not-searchable'
45  ];
46 
51  // Thumbnail captions aren't really part of the text proper
52  '.thumbcaption',
53  // Neither are tables
54  'table',
55  // Common style for "See also:".
56  '.rellink',
57  // Common style for calling out helpful links at the top of the article.
58  '.dablink',
59  // New class users can use to mark stuff as auxiliary to searches.
60  '.searchaux',
61  ];
62 
66  public function __construct( ParserOutput $parserOutput ) {
67  $this->parserOutput = $parserOutput;
68  }
69 
83  public function headings() {
84  $headings = [];
85  $ignoredHeadings = $this->getIgnoredHeadings();
86  foreach ( $this->parserOutput->getSections() as $heading ) {
87  $heading = $heading[ 'line' ];
88 
89  // Some wikis wrap the brackets in a span:
90  // https://en.wikipedia.org/wiki/MediaWiki:Cite_reference_link
91  $heading = preg_replace( '/<\/?span>/', '', $heading );
92  // Normalize [] so the following regexp would work.
93  $heading = preg_replace( [ '/&#91;/', '/&#93;/' ], [ '[', ']' ], $heading );
94  $heading = preg_replace( '/<sup>\s*\[\s*\d+\s*\]\s*<\/sup>/is', '', $heading );
95 
96  // Strip tags from the heading or else we'll display them (escaped) in search results
97  $heading = trim( Sanitizer::stripAllTags( $heading ) );
98 
99  // Note that we don't take the level of the heading into account - all headings are equal.
100  // Except the ones we ignore.
101  if ( !in_array( $heading, $ignoredHeadings ) ) {
102  $headings[] = $heading;
103  }
104  }
105  return $headings;
106  }
107 
115  public static function parseSettingsInMessage( $message ) {
116  $lines = explode( "\n", $message );
117  $lines = preg_replace( '/#.*$/', '', $lines ); // Remove comments
118  $lines = array_map( 'trim', $lines ); // Remove extra spaces
119  $lines = array_filter( $lines ); // Remove empty lines
120  return $lines;
121  }
122 
127  private function getIgnoredHeadings() {
128  static $ignoredHeadings = null;
129  if ( $ignoredHeadings === null ) {
130  $ignoredHeadings = [];
131  $source = wfMessage( 'search-ignored-headings' )->inContentLanguage();
132  if ( $source->isBlank() ) {
133  // Try old version too, just in case
134  $source = wfMessage( 'cirrussearch-ignored-headings' )->inContentLanguage();
135  }
136  if ( !$source->isDisabled() ) {
138  $ignoredHeadings = $lines; // Now we just have headings!
139  }
140  }
141  return $ignoredHeadings;
142  }
143 
147  private function extractWikitextParts() {
148  if ( !is_null( $this->allText ) ) {
149  return;
150  }
151  $text = $this->parserOutput->getText( [
152  'enableSectionEditTokens' => false,
153  'allowTOC' => false,
154  ] );
155  if ( strlen( $text ) == 0 ) {
156  $this->allText = "";
157  // empty text - nothing to seek here
158  return;
159  }
160  $opening = null;
161 
162  $this->openingText = $this->extractHeadingBeforeFirstHeading( $text );
163 
164  // Add extra spacing around break tags so text crammed together like<br>this
165  // doesn't make one word.
166  $text = str_replace( '<br', "\n<br", $text );
167 
168  $formatter = new HtmlFormatter( $text );
169 
170  // Strip elements from the page that we never want in the search text.
171  $formatter->remove( $this->excludedElementSelectors );
172  $formatter->filterContent();
173 
174  // Strip elements from the page that are auxiliary text. These will still be
175  // searched but matches will be ranked lower and non-auxiliary matches will be
176  // preferred in highlighting.
177  $formatter->remove( $this->auxiliaryElementSelectors );
178  $auxiliaryElements = $formatter->filterContent();
179  $this->allText = trim( Sanitizer::stripAllTags( $formatter->getText() ) );
180  foreach ( $auxiliaryElements as $auxiliaryElement ) {
181  $this->auxText[] =
182  trim( Sanitizer::stripAllTags( $formatter->getText( $auxiliaryElement ) ) );
183  }
184  }
185 
191  private function extractHeadingBeforeFirstHeading( $text ) {
192  $matches = [];
193  if ( !preg_match( '/<h[123456]>/', $text, $matches, PREG_OFFSET_CAPTURE ) ) {
194  // There isn't a first heading so we interpret this as the article
195  // being entirely without heading.
196  return null;
197  }
198  $text = substr( $text, 0, $matches[ 0 ][ 1 ] );
199  if ( !$text ) {
200  // There isn't any text before the first heading so we declare there isn't
201  // a first heading.
202  return null;
203  }
204 
205  $formatter = new HtmlFormatter( $text );
206  $formatter->remove( $this->excludedElementSelectors );
207  $formatter->remove( $this->auxiliaryElementSelectors );
208  $formatter->filterContent();
209  $text = trim( Sanitizer::stripAllTags( $formatter->getText() ) );
210 
211  if ( !$text ) {
212  // There isn't any text after filtering before the first heading so we declare
213  // that there isn't a first heading.
214  return null;
215  }
216 
217  return $text;
218  }
219 
224  public function getOpeningText() {
225  $this->extractWikitextParts();
226  return $this->openingText;
227  }
228 
233  public function getMainText() {
234  $this->extractWikitextParts();
235  return $this->allText;
236  }
237 
242  public function getAuxiliaryText() {
243  $this->extractWikitextParts();
244  return $this->auxText;
245  }
246 
251  public function getDefaultSort() {
252  return $this->parserOutput->getProperty( 'defaultsort' );
253  }
254 }
WikiTextStructure\parseSettingsInMessage
static parseSettingsInMessage( $message)
Parse a message content into an array.
Definition: WikiTextStructure.php:115
ParserOutput
Definition: ParserOutput.php:25
use
Apache License January AND DISTRIBUTION Definitions License shall mean the terms and conditions for use
Definition: APACHE-LICENSE-2.0.txt:10
Sanitizer\stripAllTags
static stripAllTags( $html)
Take a fragment of (potentially invalid) HTML and return a version with any tags removed,...
Definition: Sanitizer.php:1981
WikiTextStructure\getAuxiliaryText
getAuxiliaryText()
Get auxiliary text.
Definition: WikiTextStructure.php:242
WikiTextStructure\getMainText
getMainText()
Get main text.
Definition: WikiTextStructure.php:233
wfMessage
either a unescaped string or a HtmlArmor object after in associative array form externallinks including delete and has completed for all link tables whether this was an auto creation default is conds Array Extra conditions for the No matching items in log is displayed if loglist is empty msgKey Array If you want a nice box with a set this to the key of the message First element is the message additional optional elements are parameters for the key that are processed with wfMessage() -> params() ->parseAsBlock() - offset Set to overwrite offset parameter in $wgRequest set to '' to unset offset - wrap String Wrap the message in html(usually something like "&lt
WikiTextStructure\headings
headings()
Get headings on the page.
Definition: WikiTextStructure.php:83
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
$matches
$matches
Definition: NoLocalSettings.php:24
WikiTextStructure\$allText
string $allText
Definition: WikiTextStructure.php:16
WikiTextStructure\extractHeadingBeforeFirstHeading
extractHeadingBeforeFirstHeading( $text)
Get text before first heading.
Definition: WikiTextStructure.php:191
WikiTextStructure\extractWikitextParts
extractWikitextParts()
Extract parts of the text - opening, main and auxiliary.
Definition: WikiTextStructure.php:147
$lines
$lines
Definition: router.php:61
WikiTextStructure\$auxText
string[] $auxText
Definition: WikiTextStructure.php:20
WikiTextStructure\$openingText
string $openingText
Definition: WikiTextStructure.php:12
WikiTextStructure\getDefaultSort
getDefaultSort()
Get the defaultsort property.
Definition: WikiTextStructure.php:251
WikiTextStructure\$excludedElementSelectors
string[] $excludedElementSelectors
selectors to elements that are excluded entirely from search
Definition: WikiTextStructure.php:29
WikiTextStructure\getIgnoredHeadings
getIgnoredHeadings()
Get list of heading to ignore.
Definition: WikiTextStructure.php:127
WikiTextStructure\__construct
__construct(ParserOutput $parserOutput)
Definition: WikiTextStructure.php:66
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
$source
$source
Definition: mwdoc-filter.php:46
WikiTextStructure
Class allowing to explore structure of parsed wikitext.
Definition: WikiTextStructure.php:8
WikiTextStructure\$auxiliaryElementSelectors
string[] $auxiliaryElementSelectors
selectors to elements that are considered auxiliary to article text for search
Definition: WikiTextStructure.php:50
WikiTextStructure\getOpeningText
getOpeningText()
Get opening text.
Definition: WikiTextStructure.php:224
WikiTextStructure\$parserOutput
ParserOutput $parserOutput
Definition: WikiTextStructure.php:24