tokens = array( // Match tokens which require to be at the start of a line before // matching the actual newlines, because they are the indicator for // line starts. array( 'class' => 'ezcDocumentWikiTitleToken', 'match' => '(\\A\\n(?P=+)' . self::WHITESPACE_CHARS . '+)S' ), array( 'class' => 'ezcDocumentWikiTitleToken', 'match' => '(\\A(?P' . self::WHITESPACE_CHARS . '+(?P=+))\\n)S' ), array( 'class' => 'ezcDocumentWikiBulletListItemToken', 'match' => '(\\A\\n' . self::WHITESPACE_CHARS . '*(?P[*-]+)' . self::WHITESPACE_CHARS . '+)S' ), array( 'class' => 'ezcDocumentWikiEnumeratedListItemToken', 'match' => '(\\A\\n' . self::WHITESPACE_CHARS . '*(?P#+)' . self::WHITESPACE_CHARS . '+)S' ), array( 'class' => 'ezcDocumentWikiPageBreakToken', 'match' => '(\\A(?P\n' . self::WHITESPACE_CHARS . '*(?P-{4})' . self::WHITESPACE_CHARS . '*)\\n)S' ), array( 'class' => 'ezcDocumentWikiLiteralBlockToken', 'match' => '(\\A(?P\\n\\{\\{\\{\\n(?P.+)\\n\\}\\}\\})\\n)SUs' ), array( 'class' => 'ezcDocumentWikiTableRowToken', 'match' => '(\\A(?P\\n)(?P\\|))S' ), array( 'class' => 'ezcDocumentWikiParagraphIndentationToken', 'match' => '(\\A\\n(?P(?:>|:)+)' . self::WHITESPACE_CHARS . '*)S' ), // Whitespaces array( 'class' => 'ezcDocumentWikiNewLineToken', 'match' => '(\\A' . self::WHITESPACE_CHARS . '*(?P\\r\\n|\\r|\\n))S' ), array( 'class' => 'ezcDocumentWikiWhitespaceToken', 'match' => '(\\A(?P' . self::WHITESPACE_CHARS . '+))S' ), array( 'class' => 'ezcDocumentWikiEndOfFileToken', 'match' => '(\\A(?P\\x0c))S' ), // Escape character array( 'class' => 'ezcDocumentWikiEscapeCharacterToken', 'match' => '(\\A(?P~))S' ), // Inline markup array( 'class' => 'ezcDocumentWikiBoldToken', 'match' => '(\\A(?P\\*\\*))S' ), array( 'class' => 'ezcDocumentWikiItalicToken', 'match' => '(\\A(?P//))S' ), array( 'class' => 'ezcDocumentWikiMonospaceToken', 'match' => '(\\A(?P##))S' ), array( 'class' => 'ezcDocumentWikiSuperscriptToken', 'match' => '(\\A(?P\\^\\^))S' ), array( 'class' => 'ezcDocumentWikiSubscriptToken', 'match' => '(\\A(?P,,))S' ), array( 'class' => 'ezcDocumentWikiUnderlineToken', 'match' => '(\\A(?P__))S' ), array( 'class' => 'ezcDocumentWikiInlineLiteralToken', 'match' => '(\\A\\{\\{\\{(?P.+?\\}*)\\}\\}\\})Ss' ), array( 'class' => 'ezcDocumentWikiLineBreakToken', 'match' => '(\\A(?P\\\\\\\\))S' ), array( 'class' => 'ezcDocumentWikiImageStartToken', 'match' => '(\\A(?P\\{\\{))S' ), array( 'class' => 'ezcDocumentWikiImageEndToken', 'match' => '(\\A(?P\\}\\}))S' ), array( 'class' => 'ezcDocumentWikiLinkStartToken', 'match' => '(\\A(?P\\[\\[))S' ), array( 'class' => 'ezcDocumentWikiLinkEndToken', 'match' => '(\\A(?P\\]\\]))S' ), array( 'class' => 'ezcDocumentWikiTableHeaderToken', 'match' => '(\\A(?P\\|=))S' ), array( 'class' => 'ezcDocumentWikiSeparatorToken', 'match' => '(\\A(?P\\||' . self::WHITESPACE_CHARS . '*->' . self::WHITESPACE_CHARS . '*))S' ), array( 'class' => 'ezcDocumentWikiInterWikiLinkToken', 'match' => '(\\A(?P([A-Za-z]+):(?:[A-Z][a-z0-9_-]+){2,}))S' ), array( 'class' => 'ezcDocumentWikiInternalLinkToken', 'match' => '(\\A(?P(?:[A-Z][a-z]+){2,}))S' ), array( 'class' => 'ezcDocumentWikiExternalLinkToken', 'match' => '(\\A(?P(?P[a-z]+://\S+?))[,.?!:;"\']?(?:' . self::WHITESPACE_CHARS . '|\\n|\\||]]|\\||$))S' ), // Handle plugins array( 'class' => 'ezcDocumentWikiPluginToken', 'match' => '(\\A<<(?P.*?)>>)Ss' ), // Match text except array( 'class' => 'ezcDocumentWikiTextLineToken', 'match' => '(\\A(?P[^' . self::TEXT_END_CHARS . ']+))S' ), // Match all special characters, which are not valid textual chars, // but do not have been matched by any other expression. array( 'class' => 'ezcDocumentWikiSpecialCharsToken', 'match' => '(\\A(?P([' . self::SPECIAL_CHARS . '])\\2*))S' ), ); } /** * Parse plugin contents * * Plugins are totally different in each wiki component and its contents * should not be passed through the normal wiki parser. So we fetch its * contents completely and let each tokinzer extract names and parameters * from the complete token itself. * * @param ezcDocumentWikiPluginToken $plugin * @return void */ protected function parsePluginContents( ezcDocumentWikiPluginToken $plugin ) { // Match name of plugin if ( preg_match( '(^[a-z]+)i', $plugin->content, $match ) ) { $plugin->type = $match[0]; } // Match plugin parameters $parameters = array(); if ( preg_match_all( '(\s+(?P[a-zA-Z_-]+)=([\'"])(?P.*?)(?!\\\\)\\2)s', $plugin->content, $match ) ) { foreach ( $match['key'] as $nr => $key ) { $parameters[$key] = $match['value'][$nr]; } } $plugin->parameters = $parameters; } /** * Filter tokens * * Method to filter tokens, after the input string ahs been tokenized. The * filter should extract additional information from tokens, which are not * generally available yet, like the depth of a title depending on the * title markup. * * @param array $tokens * @return array */ protected function filterTokens( array $tokens ) { foreach ( $tokens as $token ) { switch ( true ) { // Extract the title / indentation level from the tokens // length. case $token instanceof ezcDocumentWikiTitleToken: case $token instanceof ezcDocumentWikiParagraphIndentationToken: $token->level = strlen( trim( $token->content ) ); break; case $token instanceof ezcDocumentWikiBulletListItemToken: case $token instanceof ezcDocumentWikiEnumeratedListItemToken: $token->indentation = strlen( $token->content ); break; case $token instanceof ezcDocumentWikiPluginToken: $this->parsePluginContents( $token ); break; } } return $tokens; } } ?>