/** * Helper function for parse() that transforms half-parsed HTML into fully * parsed HTML. * * @param string $text * @param bool $isMain * @param bool $linestart * @return string */ private function internalParseHalfParsed($text, $isMain = true, $linestart = true) { $text = $this->mStripState->unstripGeneral($text); if ($isMain) { Hooks::run('ParserAfterUnstrip', array(&$this, &$text)); } # Clean up special characters, only run once, next-to-last before doBlockLevels $fixtags = array('/(.) (?=\\?|:|;|!|%|\\302\\273)/' => '\\1 ', '/(\\302\\253) /' => '\\1 ', '/ (!\\s*important)/' => ' \\1'); $text = preg_replace(array_keys($fixtags), array_values($fixtags), $text); $text = $this->doBlockLevels($text, $linestart); $this->replaceLinkHolders($text); /** * The input doesn't get language converted if * a) It's disabled * b) Content isn't converted * c) It's a conversion table * d) it is an interface message (which is in the user language) */ if (!($this->mOptions->getDisableContentConversion() || isset($this->mDoubleUnderscores['nocontentconvert']))) { if (!$this->mOptions->getInterfaceMessage()) { # The position of the convert() call should not be changed. it # assumes that the links are all replaced and the only thing left # is the <nowiki> mark. $text = $this->getConverterLanguage()->convert($text); } } $text = $this->mStripState->unstripNoWiki($text); if ($isMain) { Hooks::run('ParserBeforeTidy', array(&$this, &$text)); } $text = $this->replaceTransparentTags($text); $text = $this->mStripState->unstripGeneral($text); $text = Sanitizer::normalizeCharReferences($text); if (MWTidy::isEnabled() && $this->mOptions->getTidy()) { $text = MWTidy::tidy($text); } else { # attempt to sanitize at least some nesting problems # (bug #2702 and quite a few others) $tidyregs = array('/(<([bi])>)(<([bi])>)?([^<]*)(<\\/?a[^<]*>)([^<]*)(<\\/\\4>)?(<\\/\\2>)/' => '\\1\\3\\5\\8\\9\\6\\1\\3\\7\\8\\9', '/(<a[^>]+>)([^<]*)(<a[^>]+>[^<]*)<\\/a>(.*)<\\/a>/' => '\\1\\2</a>\\3</a>\\1\\4</a>', '/(<([aib]) [^>]+>)([^<]*)(<div([^>]*)>)(.*)(<\\/div>)([^<]*)(<\\/\\2>)/' => '\\1\\3<div\\5>\\6</div>\\8\\9', '/<([bi])><\\/\\1>/' => ''); $text = preg_replace(array_keys($tidyregs), array_values($tidyregs), $text); } if ($isMain) { Hooks::run('ParserAfterTidy', array(&$this, &$text)); } return $text; }