'audio', 'video',
// CSS stylesheets aren't content
'style',
- // The [1] for references
+ // The [1] for references from Cite
'sup.reference',
- // The ↑ next to references in the references section
+ // The ↑ next to references in the references section from Cite
'.mw-cite-backlink',
// Headings are already indexed in their own field.
'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
'.autocollapse',
// Content explicitly decided to be not searchable by editors such
// as custom navigation templates.
- '.navigation-not-searchable'
+ '.navigation-not-searchable',
+ // User-facing interface code prompting the user to act from WikibaseMediaInfo
+ '.wbmi-entityview-emptyCaption',
];
/**
$this->openingText = $this->extractHeadingBeforeFirstHeading( $text );
- // Add extra spacing around break tags so text crammed together like<br>this
- // doesn't make one word.
- $text = str_replace( '<br', "\n<br", $text );
-
$formatter = new HtmlFormatter( $text );
// Strip elements from the page that we never want in the search text.