mirror of
https://gerrit.wikimedia.org/r/mediawiki/extensions/Description2
synced 2024-11-27 16:10:05 +00:00
b73fe26c29
Separating the extract algorithm from integration code. This results in a slightly cleaner code structure (at least in my opinion) and enables adding alternate algorithms without devolving into spaghetti. The DescriptionProvider (name of the new base interface) is exposed as a service through dependency injection to avoid factories. The implementation can be swapped at service instantiation time. Depends-On: I73c61ce045dcf31ac1ca5888f1548de8fd8b56ff Change-Id: I97fd065c9554837747021ba9fff26005e33270f4
37 lines
985 B
PHP
37 lines
985 B
PHP
<?php
|
|
|
|
namespace MediaWiki\Extension\Description2;
|
|
|
|
class SimpleDescriptionProvider implements DescriptionProvider {
|
|
|
|
/**
|
|
* Extracts description from the HTML representation of a page.
|
|
*
|
|
* The algorithm:
|
|
* 1. Removes all <table> elements and their contents.
|
|
* 2. Selects all <p> elements.
|
|
* 3. Iterates over those paragraphs, strips out all HTML tags and trims white-space around.
|
|
* 4. Then the first non-empty paragraph is picked as the result.
|
|
*
|
|
* @param string $text
|
|
* @return string
|
|
*/
|
|
public function derive( string $text ): ?string {
|
|
$pattern = '%<table\b[^>]*+>(?:(?R)|[^<]*+(?:(?!</?table\b)<[^<]*+)*+)*+</table>%i';
|
|
$myText = preg_replace( $pattern, '', $text );
|
|
|
|
$paragraphs = [];
|
|
if ( preg_match_all( '#<p>.*?</p>#is', $myText, $paragraphs ) ) {
|
|
foreach ( $paragraphs[0] as $paragraph ) {
|
|
$paragraph = trim( strip_tags( $paragraph ) );
|
|
if ( !$paragraph ) {
|
|
continue;
|
|
}
|
|
return $paragraph;
|
|
}
|
|
}
|
|
|
|
return null;
|
|
}
|
|
}
|