* As well as ' which is only defined starting in XHTML1.
* @private
*/
- static $htmlEntities = array(
+ private static $htmlEntities = array(
'Aacute' => 193,
'aacute' => 225,
'Acirc' => 194,
/**
* Character entity aliases accepted by MediaWiki
*/
- static $htmlEntityAliases = array(
+ private static $htmlEntityAliases = array(
'רלמ' => 'rlm',
'رلم' => 'rlm',
);
/**
* Lazy-initialised attributes regex, see getAttribsRegex()
+ * @private
*/
- static $attribsRegex;
+ private static $attribsRegex;
/**
* Regular expression to match HTML/XML attribute pairs within a tag.
* removes HTML comments
* @private
* @param $text String
- * @param $processCallback Callback to do any variable or parameter replacements in HTML attribute values
+ * @param $processCallback Callback to do any variable or parameter
+ * replacements in HTML attribute values
* @param array $args for the processing callback
* @param array $extratags for any extra tags to include
* @param array $removetags for any tags (default or extra) to exclude
* @return string
*/
- static function removeHTMLtags( $text, $processCallback = null, $args = array(), $extratags = array(), $removetags = array() ) {
+ static function removeHTMLtags( $text, $processCallback = null,
+ $args = array(), $extratags = array(), $removetags = array()
+ ) {
global $wgUseTidy, $wgAllowMicrodataAttributes, $wgAllowImageTag;
static $htmlpairsStatic, $htmlsingle, $htmlsingleonly, $htmlnest, $tabletags,
'kbd', 'samp', 'data', 'time', 'mark'
);
$htmlsingle = array(
- 'br', 'hr', 'li', 'dt', 'dd'
+ 'br', 'wbr', 'hr', 'li', 'dt', 'dd'
);
$htmlsingleonly = array( # Elements that cannot have close tags
- 'br', 'hr'
+ 'br', 'wbr', 'hr'
);
if ( $wgAllowMicrodataAttributes ) {
$htmlsingle[] = $htmlsingleonly[] = 'meta';
# $params: String between element name and >
# $brace: Ending '>' or '/>'
# $rest: Everything until the next element of $bits
- if ( preg_match( '!^(/?)(\\w+)([^>]*?)(/{0,1}>)([^<]*)$!', $x, $regs ) ) {
+ if ( preg_match( '!^(/?)([^\\s/>]+)([^>]*?)(/{0,1}>)([^<]*)$!', $x, $regs ) ) {
list( /* $qbar */, $slash, $t, $params, $brace, $rest ) = $regs;
} else {
$slash = $t = $params = $brace = $rest = null;
while ( substr( $text, $spaceStart + $spaceLen, 1 ) === ' ' ) {
$spaceLen++;
}
- if ( substr( $text, $spaceStart, 1 ) === "\n" and substr( $text, $spaceStart + $spaceLen, 1 ) === "\n" ) {
+ if ( substr( $text, $spaceStart, 1 ) === "\n"
+ && substr( $text, $spaceStart + $spaceLen, 1 ) === "\n" ) {
# Remove the comment, leading and trailing
# spaces, and leave only one newline.
$text = substr_replace( $text, "\n", $spaceStart, $spaceLen + 1 );
continue;
}
- //RDFa and microdata properties allow URLs, URIs and/or CURIs. check them for sanity
- if ( $attribute === 'rel' || $attribute === 'rev' ||
- $attribute === 'about' || $attribute === 'property' || $attribute === 'resource' || #RDFa
- $attribute === 'datatype' || $attribute === 'typeof' || #RDFa
- $attribute === 'itemid' || $attribute === 'itemprop' || $attribute === 'itemref' || #HTML5 microdata
- $attribute === 'itemscope' || $attribute === 'itemtype' ) { #HTML5 microdata
-
+ // RDFa and microdata properties allow URLs, URIs and/or CURIs.
+ // Check them for sanity.
+ if ( $attribute === 'rel' || $attribute === 'rev'
+ # RDFa
+ || $attribute === 'about' || $attribute === 'property'
+ || $attribute === 'resource' || $attribute === 'datatype'
+ || $attribute === 'typeof'
+ # HTML5 microdata
+ || $attribute === 'itemid' || $attribute === 'itemprop'
+ || $attribute === 'itemref' || $attribute === 'itemscope'
+ || $attribute === 'itemtype'
+ ) {
//Paranoia. Allow "simple" values but suppress javascript
if ( preg_match( self::EVIL_URI_PATTERN, $value ) ) {
continue;
if ( $attribute === 'href' || $attribute === 'src' ) {
if ( !preg_match( $hrefExp, $value ) ) {
continue; //drop any href or src attributes not using an allowed protocol.
- //NOTE: this also drops all relative URLs
+ // NOTE: this also drops all relative URLs
}
}
);
if ( $wgAllowRdfaAttributes ) {
- #RDFa attributes as specified in section 9 of http://www.w3.org/TR/2008/REC-rdfa-syntax-20081014
+ # RDFa attributes as specified in section 9 of
+ # http://www.w3.org/TR/2008/REC-rdfa-syntax-20081014
$common = array_merge( $common, array(
'about', 'property', 'resource', 'datatype', 'typeof',
) );
}
if ( $wgAllowMicrodataAttributes ) {
- # add HTML5 microdata tags as specified by http://www.whatwg.org/html/microdata.html#the-microdata-model
+ # add HTML5 microdata tags as specified by
+ # http://www.whatwg.org/html/microdata.html#the-microdata-model
$common = array_merge( $common, array(
'itemid', 'itemprop', 'itemref', 'itemscope', 'itemtype'
) );
# 9.3.2
'br' => array( 'id', 'class', 'title', 'style', 'clear' ),
+ # http://www.whatwg.org/html/text-level-semantics.html#the-wbr-element
+ 'wbr' => array( 'id', 'class', 'title', 'style' ),
+
# 9.3.4
'pre' => array_merge( $common, array( 'width' ) ),
'td' => array_merge( $common, $tablecell, $tablealign ),
'th' => array_merge( $common, $tablecell, $tablealign ),
- # 12.2 # NOTE: <a> is not allowed directly, but the attrib whitelist is used from the Parser object
+ # 12.2
+ # NOTE: <a> is not allowed directly, but the attrib
+ # whitelist is used from the Parser object
'a' => array_merge( $common, array( 'href', 'rel', 'rev' ) ), # rel/rev esp. for RDFa
# 13.2
!! end
!! test
- <wbr> isn't (yet) valid wikitext (bug 52468)
+ <wbr> is valid wikitext (bug 52468)
!! input
<wbr>
!! result
- <p><wbr>
+ <p><wbr />
</p>
!! end
+# <strike> is HTML4, <s> is HTML4/5.
+!! test
+<s> or <strike> for strikethrough
+!! input
+<strike>strike</strike>
+
+<s>s</s>
+!! result
+<p><strike>strike</strike>
+</p><p><s>s</s>
+</p>
+!! end
+
+!! test
+Non-word characters don't terminate tag names (bug 17663, 40670, 52022)
+!! input
+<b→> doesn't work! </b>
+
+<bä> doesn't work! </b>
+
+<boo> works fine </b>
+
+<s.foo>foo</s>
+
+<s.foo>s.foo</s.foo>
+
+<sub-ID#1>
+!! result
+<p><b→> doesn't work! </b>
+</p><p><bä> doesn't work! </b>
+</p><p><boo> works fine </b>
+</p><p><s.foo>foo</s>
+</p><p><s.foo>s.foo</s.foo>
+</p><p><sub-ID#1>
+</p>
+!! end
+
###
### Special characters
###
!! end
-# Expected output in the following test is not really expected (there should be
-# <pre> in the output) -- it's only testing for well-formedness.
!! test
Bug 6200: Preformatted in <blockquote>
!! input
</blockquote>
!! result
<blockquote>
- Blah
+<pre>Blah
+</pre>
+</blockquote>
+
+!! end
+
+!! test
+Bug 51086: Double newlines in blockquotes should be turned into paragraphs
+!! input
+<blockquote>
+Foo
+
+Bar
+</blockquote>
+!! result
+<blockquote>
+<p>Foo
+</p><p>Bar
+</p>
+</blockquote>
+
+!! end
+
+!! test
+Bug 15491: <ins>/<del> in blockquote
+!! input
+<blockquote>
+Foo <del>bar</del> <ins>baz</ins> quux
+</blockquote>
+!! result
+<blockquote>
+<p>Foo <del>bar</del> <ins>baz</ins> quux
+</p>
+</blockquote>
+
+!! end
+
+# Note that the p-wrapping is newline sensitive, which could be
+# considered a bug: tidy will wrap only the 'Foo' in the example
+# below in a <p> tag. (see comment 23-25 of bug #6200)
+!! test
+Bug 15491: <ins>/<del> in blockquote (2)
+!! input
+<blockquote>Foo <del>bar</del> <ins>baz</ins> quux
+</blockquote>
+!! result
+<blockquote>Foo <del>bar</del> <ins>baz</ins> quux
</blockquote>
!! end
</pre>
</center>
<blockquote>
- foo
+<pre>foo
+</pre>
</blockquote>
<table><tr><td>
<pre>foo
!! end
###
-### Parser hooks (see maintenance/parserTestsParserHook.php for the <tag> extension)
+### Parser hooks (see tests/parser/parserTestsParserHook.php for the <tag> extension)
###
!! test
Parser hook: empty input
!! end
###
-### (see maintenance/parserTestsStaticParserHook.php for the <statictag> extension)
+### (see tests/parser/parserTestsParserHook.php for the <statictag> extension)
###
!! test
</p>
!! end
-# Expected output in the following test is not necessarily expected (there
-# should probably be <p> tags inside the <blockquote> in the output) -- it's
-# only testing for well-formedness.
!! test
Bug 6200: blockquotes and paragraph formatting
!! input
baz
!! result
<blockquote>
-foo
+<p>foo
+</p>
</blockquote>
<p>bar
</p>
# Bug 6200: <blockquote> should behave like <div> with respect to line breaks
!! test
Bug 6200: paragraphs inside blockquotes (no extra line breaks)
-!! options
-disabled
!! input
<blockquote>Line one
!! test
Bug 6200: paragraphs inside blockquotes (extra line break on open)
-!! options
-disabled
!! input
<blockquote>
Line one
!! test
Bug 6200: paragraphs inside blockquotes (extra line break on close)
-!! options
-disabled
!! input
<blockquote>Line one
!! test
Bug 6200: paragraphs inside blockquotes (extra line break on open and close)
-!! options
-disabled
!! input
<blockquote>
Line one
!! end
-# This fails in the PHP parser (see bug 40670,
-# https://bugzilla.wikimedia.org/show_bug.cgi?id=40670), so disabled for it.
+# This was a bug in the PHP parser (see bug 17663 and its dups,
+# https://bugzilla.wikimedia.org/show_bug.cgi?id=17663)
!! test
Tag names followed by punctuation should not be recognized as tags
-!! options
-parsoid
!! input
<s.ome> text
!! result
dépôts / lhc / web / wiklou.git / commitdiff