0313128b10
In cases where we're operating on text data (and not binary data),
use e.g. "\u{00A0}" to refer directly to the Unicode character
'NO-BREAK SPACE' instead of "\xc2\xa0" to specify the bytes C2h A0h
(which correspond to the UTF-8 encoding of that character). This
makes it easier to look up those mysterious sequences, as not all
are as recognizable as the no-break space.
This is not enforced by PHP, but I think we should write those in
uppercase and zero-padded to at least four characters, like the
Unicode standard does.
Note that not all "\xNN" escapes can be automatically replaced:
* We can't use Unicode escapes for binary data that is not UTF-8
(e.g. in code converting from legacy encodings or testing the
handling of invalid UTF-8 byte sequences).
* '\xNN' escapes in regular expressions in single-quoted strings
are actually handled by PCRE and have to be dealt with carefully
(those regexps should probably be changed to use the /u modifier).
* "\xNN" referring to ASCII characters ("\x7F" and lower) should
probably be left as-is.
The replacements in this commit were done semi-manually by piping
the existing "\xNN" escapes through the following terrible Ruby
script I devised:
chars = eval('"' + ARGV[0] + '"').force_encoding('utf-8')
puts chars.split('').map{|char|
'\\u{' + char.ord.to_s(16).upcase.rjust(4, '0') + '}'
}.join('')
Change-Id: Idc3dee3a7fb5ebfaef395754d8859b18f1f8769a
70 lines
1.7 KiB
PHP
70 lines
1.7 KiB
PHP
<?php
|
|
|
|
namespace MediaWiki\Tidy;
|
|
|
|
use RemexHtml\HTMLData;
|
|
use RemexHtml\Serializer\HtmlFormatter;
|
|
use RemexHtml\Serializer\SerializerNode;
|
|
|
|
/**
|
|
* @internal
|
|
*/
|
|
class RemexCompatFormatter extends HtmlFormatter {
|
|
private static $markedEmptyElements = [
|
|
'li' => true,
|
|
'p' => true,
|
|
'tr' => true,
|
|
];
|
|
|
|
public function __construct( $options = [] ) {
|
|
parent::__construct( $options );
|
|
$this->attributeEscapes["\u{00A0}"] = ' ';
|
|
unset( $this->attributeEscapes["&"] );
|
|
$this->textEscapes["\u{00A0}"] = ' ';
|
|
unset( $this->textEscapes["&"] );
|
|
}
|
|
|
|
public function startDocument( $fragmentNamespace, $fragmentName ) {
|
|
return '';
|
|
}
|
|
|
|
public function element( SerializerNode $parent, SerializerNode $node, $contents ) {
|
|
$data = $node->snData;
|
|
if ( $data && $data->isPWrapper ) {
|
|
if ( $data->nonblankNodeCount ) {
|
|
return "<p>$contents</p>";
|
|
} else {
|
|
return $contents;
|
|
}
|
|
}
|
|
|
|
$name = $node->name;
|
|
$attrs = $node->attrs;
|
|
if ( isset( self::$markedEmptyElements[$name] ) && $attrs->count() === 0 ) {
|
|
if ( strspn( $contents, "\t\n\f\r " ) === strlen( $contents ) ) {
|
|
return "<{$name} class=\"mw-empty-elt\">$contents</{$name}>";
|
|
}
|
|
}
|
|
|
|
$s = "<$name";
|
|
foreach ( $attrs->getValues() as $attrName => $attrValue ) {
|
|
$encValue = strtr( $attrValue, $this->attributeEscapes );
|
|
$s .= " $attrName=\"$encValue\"";
|
|
}
|
|
if ( $node->namespace === HTMLData::NS_HTML && isset( $this->voidElements[$name] ) ) {
|
|
$s .= ' />';
|
|
return $s;
|
|
}
|
|
|
|
$s .= '>';
|
|
if ( $node->namespace === HTMLData::NS_HTML
|
|
&& isset( $contents[0] ) && $contents[0] === "\n"
|
|
&& isset( $this->prefixLfElements[$name] )
|
|
) {
|
|
$s .= "\n$contents</$name>";
|
|
} else {
|
|
$s .= "$contents</$name>";
|
|
}
|
|
return $s;
|
|
}
|
|
}
|