128debb64b
Follows-up I361fde0de7f4406bce6ed075ed397effa5be3359. Per T253461, not mass-changing source code, but the use of the native error silencing operator (@) is especially useful in tests because: 1. It requires any/all statements to be explicitly marked. The suppressWarnings/restoreWarnings sections encourage developers to be "lazy" and thus encapsulate more than needed if there are multiple ones near each other, which would ignore potentially important warnings in a test case, which is generally exactly the time when it is really useful to get warnings etc. 2. It avoids leaking state, for example in LBFactoryTest the assertFalse call would throw a PHPUnit assertion error (not meant to be caught by the local catch), and thus won't reach AtEase::restoreWarnings. This then causes later code to end up in a mismatching state and creates a confusing error_reporting state. See .phpcs.xml, where the at operator is allowed for all test code. Change-Id: I68d1725d685e0a7586468bc9de6dc29ceea31b8a
84 lines
2.4 KiB
PHP
84 lines
2.4 KiB
PHP
<?php
|
|
|
|
/**
|
|
* @ingroup Testing
|
|
*/
|
|
class ParserTestResultNormalizer {
|
|
protected $doc, $xpath, $invalid;
|
|
|
|
public static function normalize( $text, $funcs ) {
|
|
$norm = new self( $text );
|
|
if ( $norm->invalid ) {
|
|
return $text;
|
|
}
|
|
foreach ( $funcs as $func ) {
|
|
$norm->$func();
|
|
}
|
|
return $norm->serialize();
|
|
}
|
|
|
|
protected function __construct( $text ) {
|
|
$this->doc = new DOMDocument( '1.0', 'utf-8' );
|
|
|
|
// Parsing a supposedly-XHTML document with an XML parser is not
|
|
// guaranteed to give accurate results. For example, it may introduce
|
|
// differences in the number of line breaks in <pre> tags.
|
|
if ( !@$this->doc->loadXML( '<html><body>' . $text . '</body></html>' ) ) {
|
|
$this->invalid = true;
|
|
}
|
|
|
|
$this->xpath = new DOMXPath( $this->doc );
|
|
$this->body = $this->xpath->query( '//body' )->item( 0 );
|
|
}
|
|
|
|
protected function removeTbody() {
|
|
foreach ( $this->xpath->query( '//tbody' ) as $tbody ) {
|
|
while ( $tbody->firstChild ) {
|
|
$child = $tbody->firstChild;
|
|
$tbody->removeChild( $child );
|
|
$tbody->parentNode->insertBefore( $child, $tbody );
|
|
}
|
|
$tbody->parentNode->removeChild( $tbody );
|
|
}
|
|
}
|
|
|
|
/**
|
|
* The point of this function is to produce a normalized DOM in which
|
|
* Tidy's output matches the output of RemexHtml. Tidy both trims
|
|
* and pretty-prints, so this requires fairly aggressive treatment.
|
|
*
|
|
* In particular, note that Tidy converts <pre>x</pre> to <pre>\nx\n</pre>,
|
|
* which theoretically affects display since the second line break is not
|
|
* ignored by compliant HTML parsers.
|
|
*
|
|
* This function also removes empty elements, as does Tidy.
|
|
*/
|
|
protected function trimWhitespace() {
|
|
foreach ( $this->xpath->query( '//text()' ) as $child ) {
|
|
if ( strtolower( $child->parentNode->nodeName ) === 'pre' ) {
|
|
// Just trim one line break from the start and end
|
|
if ( substr_compare( $child->data, "\n", 0 ) === 0 ) {
|
|
$child->data = substr( $child->data, 1 );
|
|
}
|
|
if ( substr_compare( $child->data, "\n", -1 ) === 0 ) {
|
|
$child->data = substr( $child->data, 0, -1 );
|
|
}
|
|
} else {
|
|
// Trim all whitespace
|
|
$child->data = trim( $child->data );
|
|
}
|
|
if ( $child->data === '' ) {
|
|
$child->parentNode->removeChild( $child );
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Serialize the XML DOM for comparison purposes. This does not generate HTML.
|
|
* @return string
|
|
*/
|
|
protected function serialize() {
|
|
return strtr( $this->doc->saveXML( $this->body ),
|
|
[ '<body>' => '', '</body>' => '' ] );
|
|
}
|
|
}
|