# Constants needed for external link processing
# Everything except bracket, space, or control characters
# \p{Zs} is unicode 'separator, space' category. It covers the space 0x20
- # as well as U+3000 is IDEOGRAPHIC SPACE for bug 19052
+ # as well as U+3000 is IDEOGRAPHIC SPACE for T21052
const EXT_LINK_URL_CLASS = '[^][<>"\\x00-\\x20\\x7F\p{Zs}]';
# Simplified expression to match an IPv4 or IPv6 address, or
# at least one character of a host name (embeds EXT_LINK_URL_CLASS)
/**
* @var string Deprecated accessor for the strip marker prefix.
* @deprecated since 1.26; use Parser::MARKER_PREFIX instead.
- **/
+ */
public $mUniqPrefix = Parser::MARKER_PREFIX;
/**
# Preprocessor_Hash is much faster than Preprocessor_DOM under HipHop
$this->mPreprocessorClass = 'Preprocessor_Hash';
} elseif ( extension_loaded( 'domxml' ) ) {
- # PECL extension that conflicts with the core DOM extension (bug 13770)
+ # PECL extension that conflicts with the core DOM extension (T15770)
wfDebug( "Warning: you have the obsolete domxml extension for PHP. Please remove it!\n" );
$this->mPreprocessorClass = 'Preprocessor_Hash';
} elseif ( extension_loaded( 'dom' ) ) {
public function __clone() {
$this->mInParse = false;
- // Bug 56226: When you create a reference "to" an object field, that
+ // T58226: When you create a reference "to" an object field, that
// makes the object field itself be a reference too (until the other
// reference goes out of scope). When cloning, any field that's a
// reference is copied as a reference in the new object. Both of these
$this->mStripState = new StripState;
- # Clear these on every parse, bug 4549
+ # Clear these on every parse, T6549
$this->mTplRedirCache = $this->mTplDomCache = [];
$this->mShowToc = true;
}
/**
- * Process the wikitext for the "?preload=" feature. (bug 5210)
+ * Process the wikitext for the "?preload=" feature. (T7210)
*
* "<noinclude>", "<includeonly>" etc. are parsed as for template
* transclusion, comments, templates, arguments, tags hooks and parser
# A cell could contain both parameters and data
$cell_data = explode( '|', $cell, 2 );
- # Bug 553: Note that a '|' inside an invalid link should not
+ # T2553: Note that a '|' inside an invalid link should not
# be mistaken as delimiting cell parameters
- if ( strpos( $cell_data[0], '[[' ) !== false ) {
+ # Bug T153140: Neither should language converter markup.
+ if ( preg_match( '/\[\[|-\{/', $cell_data[0] ) === 1 ) {
$cell = "{$previous}<{$last_tag}>{$cell}";
} elseif ( count( $cell_data ) == 1 ) {
$cell = "{$previous}<{$last_tag}>{$cell_data[0]}";
# Clean up special characters, only run once, next-to-last before doBlockLevels
$fixtags = [
- # french spaces, last one Guillemet-left
+ # French spaces, last one Guillemet-left
# only if there is something before the space
'/(.) (?=\\?|:|;|!|%|\\302\\273)/' => '\\1 ',
# french spaces, Guillemet-right
'/(\\302\\253) /' => '\\1 ',
- '/ (!\s*important)/' => ' \\1', # Beware of CSS magic word !important, bug #11874.
+ '/ (!\s*important)/' => ' \\1', # Beware of CSS magic word !important, T13874.
];
$text = preg_replace( array_keys( $fixtags ), array_values( $fixtags ), $text );
}
} else {
# attempt to sanitize at least some nesting problems
- # (bug #2702 and quite a few others)
+ # (T4702 and quite a few others)
$tidyregs = [
# ''Something [http://www.cool.com cool''] -->
# <i>Something</i><a href="http://www.cool.com"..><i>cool></i></a>
'/(<([bi])>)(<([bi])>)?([^<]*)(<\/?a[^<]*>)([^<]*)(<\/\\4>)?(<\/\\2>)/' =>
'\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9',
# fix up an anchor inside another anchor, only
- # at least for a single single nested link (bug 3695)
+ # at least for a single single nested link (T5695)
'/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\/a>(.*)<\/a>/' =>
'\\1\\2</a>\\3</a>\\1\\4</a>',
# fix div inside inline elements- doBlockLevels won't wrap a line which
$thislen = strlen( $arr[$i] );
// If there are ever four apostrophes, assume the first is supposed to
// be text, and the remaining three constitute mark-up for bold text.
- // (bug 13227: ''''foo'''' turns into ' ''' foo ' ''')
+ // (T15227: ''''foo'''' turns into ' ''' foo ' ''')
if ( $thislen == 4 ) {
$arr[$i - 1] .= "'";
$arr[$i] = "'''";
} elseif ( $thislen > 5 ) {
// If there are more than 5 apostrophes in a row, assume they're all
// text except for the last 5.
- // (bug 13227: ''''''foo'''''' turns into ' ''''' foo ' ''''')
+ // (T15227: ''''''foo'''''' turns into ' ''''' foo ' ''''')
$arr[$i - 1] .= str_repeat( "'", $thislen - 5 );
$arr[$i] = "'''''";
$thislen = 5;
# If we get a ] at the beginning of $m[3] that means we have a link that's something like:
# [[Image:Foo.jpg|[http://example.com desc]]] <- having three ] in a row fucks up,
# the real problem is with the $e1 regex
- # See bug 1300.
+ # See T1500.
# Still some problems for cases where the ] is meant to be outside punctuation,
- # and no image is in sight. See bug 2095.
+ # and no image is in sight. See T4095.
if ( $text !== ''
&& substr( $m[3], 0, 1 ) === ']'
&& strpos( $text, '[' ) !== false
if ( $wasblank ) {
$text = $link;
} else {
- # Bug 4598 madness. Handle the quotes only if they come from the alternate part
+ # T6598 madness. Handle the quotes only if they come from the alternate part
# [[Lista d''e paise d''o munno]] -> <a href="...">Lista d''e paise d''o munno</a>
# [[Criticism of Harry Potter|Criticism of ''Harry Potter'']]
# -> <a href="Criticism of Harry Potter">Criticism of <i>Harry Potter</i></a>
in_array( $iw, $wgExtraInterlanguageLinkPrefixes )
)
) {
- # Bug 24502: filter duplicates
+ # T26502: filter duplicates
if ( !isset( $this->mLangLinkLanguages[$iw] ) ) {
$this->mLangLinkLanguages[$iw] = true;
$this->mOutput->addLanguageLink( $nt->getFullText() );
continue;
}
} elseif ( $ns == NS_CATEGORY ) {
- $s = rtrim( $s . "\n" ); # bug 87
+ $s = rtrim( $s . "\n" ); # T2087
if ( $wasblank ) {
$sortkey = $this->getDefaultSort();
$this->mOutput->addCategory( $nt->getDBkey(), $sortkey );
/**
- * Strip the whitespace Category links produce, see bug 87
+ * Strip the whitespace Category links produce, see T2087
*/
$s .= trim( $prefix . $trail, "\n" ) == '' ? '' : $prefix . $trail;
$subjPage = $this->mTitle->getSubjectPage();
$value = wfEscapeWikiText( $subjPage->getPrefixedURL() );
break;
- case 'pageid': // requested in bug 23427
+ case 'pageid': // requested in T25427
$pageid = $this->getTitle()->getArticleID();
if ( $pageid == 0 ) {
# 0 means the page doesn't exist in the database,
$value = $pageLang->formatNum( MWTimestamp::getInstance( $ts )->format( 'H' ), true );
break;
case 'currentweek':
- # @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
+ # @bug T6594 PHP5 has it zero padded, PHP4 does not, cast to
# int to remove the padding
$value = $pageLang->formatNum( (int)MWTimestamp::getInstance( $ts )->format( 'W' ) );
break;
$value = $pageLang->formatNum( MWTimestamp::getLocalInstance( $ts )->format( 'H' ), true );
break;
case 'localweek':
- # @bug 4594 PHP5 has it zero padded, PHP4 does not, cast to
+ # @bug T6594 PHP5 has it zero padded, PHP4 does not, cast to
# int to remove the padding
$value = $pageLang->formatNum( (int)MWTimestamp::getLocalInstance( $ts )->format( 'W' ) );
break;
* included. Default is to assume a direct page view.
*
* The generated DOM tree must depend only on the input text and the flags.
- * The DOM tree must be the same in OT_HTML and OT_WIKI mode, to avoid a regression of bug 4899.
+ * The DOM tree must be the same in OT_HTML and OT_WIKI mode, to avoid a regression of T6899.
*
* Any flag added to the $flags parameter here, or any other parameter liable to cause a
* change in the DOM tree for a given text, must be passed through the section identifier
&& !$piece['lineStart']
&& preg_match( '/^(?:{\\||:|;|#|\*)/', $text )
) {
- # Bug 529: if the template begins with a table or block-level
+ # T2529: if the template begins with a table or block-level
# element, it should be treated as beginning a new line.
# This behavior is somewhat controversial.
$text = "\n" . $text;
if ( is_string( $text ) && !$this->incrementIncludeSize( 'post-expand', strlen( $text ) ) ) {
# Error, oversize inclusion
if ( $titleText !== false ) {
- # Make a working, properly escaped link if possible (bug 23588)
+ # Make a working, properly escaped link if possible (T25588)
$text = "[[:$titleText]]";
} else {
# This will probably not be a working link, but at least it may
) {
$this->addTrackingCategory( 'hidden-category-category' );
}
- # (bug 8068) Allow control over whether robots index a page.
- # @todo FIXME: Bug 14899: __INDEX__ always overrides __NOINDEX__ here! This
- # is not desirable, the last one on the page should win.
+ # (T10068) Allow control over whether robots index a page.
+ # __INDEX__ always overrides __NOINDEX__, see T16899
if ( isset( $this->mDoubleUnderscores['noindex'] ) && $this->mTitle->canUseNoindex() ) {
$this->mOutput->setIndexPolicy( 'noindex' );
$this->addTrackingCategory( 'noindex-category' );
# Strip out HTML (first regex removes any tag not allowed)
# Allowed tags are:
- # * <sup> and <sub> (bug 8393)
- # * <i> (bug 26375)
+ # * <sup> and <sub> (T10393)
+ # * <i> (T28375)
# * <b> (r105284)
- # * <bdi> (bug 72884)
- # * <span dir="rtl"> and <span dir="ltr"> (bug 35167)
+ # * <bdi> (T74884)
+ # * <span dir="rtl"> and <span dir="ltr"> (T37167)
# * <s> and <strike> (T35715)
# We strip any parameter from accepted tags (second regex), except dir="rtl|ltr" from <span>,
# to allow setting directionality in toc items.
'noninitial' );
}
- # HTML names must be case-insensitively unique (bug 10721).
+ # HTML names must be case-insensitively unique (T12721).
# This does not apply to Unicode characters per
# https://www.w3.org/TR/html5/infrastructure.html#case-sensitivity-and-string-comparison
# @todo FIXME: We may be changing them depending on the current locale.
# the database, we use $wgContLang here in order to give
# everyone the same signature and use the default one rather
# than the one selected in each user's preferences.
- # (see also bug 12815)
+ # (see also T14815)
$ts = $this->mOptions->getTimestamp();
$timestamp = MWTimestamp::getLocalInstance( $ts );
$ts = $timestamp->format( 'YmdHis' );
$descQuery = false;
Hooks::run( 'BeforeParserFetchFileAndTitle',
[ $this, $title, &$options, &$descQuery ] );
- # Don't register it now, as ImageGallery does that later.
+ # Don't register it now, as TraditionalImageGallery does that later.
$file = $this->fetchFileNoRegister( $title, $options );
$handler = $file ? $file->getHandler() : false;
// FIXME: Doing recursiveTagParse at this stage, and the trim before
// splitting on '|' is a bit odd, and different from makeImage.
$matches[3] = $this->recursiveTagParse( trim( $matches[3] ) );
- $parameterMatches = StringUtils::explode( '|', $matches[3] );
+ // Protect LanguageConverter markup
+ $parameterMatches = StringUtils::delimiterExplode(
+ '-{', '}-', '|', $matches[3], true /* nested */
+ );
foreach ( $parameterMatches as $parameterMatch ) {
list( $magicName, $match ) = $mwArray->matchVariableStartToEnd( $parameterMatch );
$addr = self::EXT_LINK_ADDR;
$prots = $this->mUrlProtocols;
// check to see if link matches an absolute url, if not then it must be a wiki link.
+ if ( preg_match( '/^-{R|(.*)}-$/', $linkValue ) ) {
+ // Result of LanguageConverter::markNoConversion
+ // invoked on an external link.
+ $linkValue = substr( $linkValue, 4, -2 );
+ }
if ( preg_match( "/^($prots)$addr$chars*$/u", $linkValue ) ) {
$link = $linkValue;
} else {
# * bottom
# * text-bottom
- $parts = StringUtils::explode( "|", $options );
+ # Protect LanguageConverter markup when splitting into parts
+ $parts = StringUtils::delimiterExplode(
+ '-{', '}-', '|', $options, true /* allow nesting */
+ );
# Give extensions a chance to select the file revision for us
$options = [];
$validated = true;
}
}
- # else no validation -- bug 13436
+ # else no validation -- T15436
} else {
if ( $type === 'handler' ) {
# Validate handler parameter
case 'framed':
case 'thumbnail':
// use first appearing option, discard others.
- $validated = ! $seenformat;
+ $validated = !$seenformat;
$seenformat = true;
break;
default:
* External callers should use the getSection and replaceSection methods.
*
* @param string $text Page wikitext
- * @param string|number $sectionId A section identifier string of the form:
+ * @param string|int $sectionId A section identifier string of the form:
* "<flag1> - <flag2> - ... - <section number>"
*
* Currently the only recognised flag is "T", which means the target section number
* was derived during a template inclusion parse, in other words this is a template
* section edit link. If no flags are given, it was an ordinary section edit link.
* This flag is required to avoid a section numbering mismatch when a section is
- * enclosed by "<includeonly>" (bug 6563).
+ * enclosed by "<includeonly>" (T8563).
*
* The section number 0 pulls the text before the first heading; other numbers will
* pull the given section along with its lower-level subsections. If the section is
* If a section contains subsections, these are also returned.
*
* @param string $text Text to look in
- * @param string|number $sectionId Section identifier as a number or string
+ * @param string|int $sectionId Section identifier as a number or string
* (e.g. 0, 1 or 'T-1').
* @param string $defaultText Default to return if section is not found
*
* section does not exist, $oldtext is returned unchanged.
*
* @param string $oldText Former text of the article
- * @param string|number $sectionId Section identifier as a number or string
+ * @param string|int $sectionId Section identifier as a number or string
* (e.g. 0, 1 or 'T-1').
* @param string $newText Replacing text
*
return $parsedWidthParam;
}
$m = [];
- # (bug 13500) In both cases (width/height and width only),
+ # (T15500) In both cases (width/height and width only),
# permit trailing "px" for backward compatibility.
if ( preg_match( '/^([0-9]*)x([0-9]*)\s*(?:px)?\s*$/', $value, $m ) ) {
$width = intval( $m[1] );