mediawiki-extensions-Discus.../tests/phpunit/TestUtils.php
Bartosz Dziewoński 5a07139249 CommentFormatterTest: Avoid re-serializing the HTML
The code we're testing already produces a string of serialized HTML,
no need to parse and re-serialize it.

Also, we recently learned that the precise format matters here
(T274709), and now this test *actually* covers the fix for that bug.
Follow-up to 5b26e9664b.

As a downside, this test might now spuriously fail if the format of
the output of Parsoid's XMLSerializer changes. Hopefully that won't
happen too often.

Change-Id: I69b514f545e47dcb437fb39a83edb8e2f19ed99b
2021-03-01 21:30:28 +01:00

137 lines
3.6 KiB
PHP

<?php
namespace MediaWiki\Extension\DiscussionTools\Tests;
use DOMDocument;
use DOMElement;
use MediaWiki\Extension\DiscussionTools\CommentParser;
use MediaWiki\MediaWikiServices;
use Wikimedia\Parsoid\Utils\DOMCompat;
use Wikimedia\Parsoid\Utils\DOMUtils;
trait TestUtils {
/**
* Create a DOMDocument from a string
*
* @param string $html
* @return DOMDocument
*/
protected static function createDocument( string $html ) : DOMDocument {
$doc = DOMUtils::parseHTML( $html );
$doc->preserveWhiteSpace = false;
return $doc;
}
/**
* Get text from path
*
* @param string $relativePath
* @return string
*/
protected static function getText( string $relativePath ) : string {
return file_get_contents( __DIR__ . '/../' . $relativePath );
}
/**
* Write text to path
*
* @param string $relativePath
* @param string $text
*/
protected static function overwriteTextFile( string $relativePath, string $text ) : void {
file_put_contents( __DIR__ . '/../' . $relativePath, $text );
}
/**
* Get parsed JSON from path
*
* @param string $relativePath
* @param bool $assoc See json_decode()
* @return array
*/
protected static function getJson( string $relativePath, bool $assoc = true ) : array {
$json = json_decode(
file_get_contents( __DIR__ . '/' . $relativePath ),
$assoc
);
return $json;
}
/**
* Write JSON to path
*
* @param string $relativePath
* @param array $data
*/
protected static function overwriteJsonFile( string $relativePath, array $data ) : void {
$json = json_encode( $data, JSON_PRETTY_PRINT | JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE );
// Tabs instead of 4 spaces
$json = preg_replace( '/(?:\G|^) {4}/m', "\t", $json );
file_put_contents( __DIR__ . '/' . $relativePath, $json . "\n" );
}
/**
* Get HTML from path
*
* @param string $relativePath
* @return string
*/
protected static function getHtml( string $relativePath ) : string {
$html = file_get_contents( __DIR__ . '/../' . $relativePath );
// Remove all but the body tags from full Parsoid docs
if ( strpos( $html, '<body' ) !== false ) {
preg_match( '`(<body[^>]*>)(.*)(</body>)`s', $html, $match );
$html = "<div>$match[2]</div>";
}
return $html;
}
/**
* Write HTML to path
*
* @param string $relPath
* @param DOMDocument $doc
* @param string $origRelPath
*/
protected static function overwriteHtmlFile( string $relPath, DOMDocument $doc, string $origRelPath ) : void {
// Do not use $doc->saveHtml(), it outputs an awful soup of HTML entities for documents with
// non-ASCII characters
$html = file_get_contents( __DIR__ . '/../' . $origRelPath );
// Replace the body tag only in full Parsoid docs
if ( strpos( $html, '<body' ) !== false ) {
$innerHtml = DOMCompat::getInnerHTML( $doc->getElementsByTagName( 'body' )->item( 0 )->firstChild );
$html = preg_replace(
'`(<body[^>]*>)(.*)(</body>)`s',
// Quote \ and $ in the replacement text
'$1' . strtr( $innerHtml, [ '\\' => '\\\\', '$' => '\\$' ] ) . '$3',
$html
);
} else {
$html = DOMCompat::getInnerHTML( $doc->getElementsByTagName( 'body' )->item( 0 ) );
}
file_put_contents( __DIR__ . '/../' . $relPath, $html );
}
/**
* Create a comment parser
*
* @param DOMElement $rootNode
* @param array $data
* @return CommentParser
*/
public static function createParser( DOMElement $rootNode, array $data ) : CommentParser {
$services = MediaWikiServices::getInstance();
return new CommentParser(
$rootNode,
$services->getContentLanguage(),
$services->getMainConfig(),
$data
);
}
}