'width', 'height' => 'height', 'align' => 'alignement', ); /** * Construct tokenizer * * Create token array with regular repression matching the respective * token. * * @return void */ public function __construct() { $this->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(?Ph[1-6].' . self::WHITESPACE_CHARS . '*))S' ), array( 'class' => 'ezcDocumentWikiParagraphIndentationToken', 'match' => '(\\A\\n(?Pbq.)' . self::WHITESPACE_CHARS . '*)S' ), array( 'class' => 'ezcDocumentWikiQuoteToken', 'match' => '(\\A\\n(?P\\{quote\\}))S' ), array( 'class' => 'ezcDocumentWikiPageBreakToken', 'match' => '(\\A(?P\\n' . self::WHITESPACE_CHARS . '*(?P-{4})' . self::WHITESPACE_CHARS . '*)\\n)S' ), array( 'class' => 'ezcDocumentWikiBulletListItemToken', 'match' => '(\\A\\n(?P[#*-]*[*-])' . self::WHITESPACE_CHARS . '+)S' ), array( 'class' => 'ezcDocumentWikiEnumeratedListItemToken', 'match' => '(\\A\\n(?P[#*-]*#)' . self::WHITESPACE_CHARS . '+)S' ), array( 'class' => 'ezcDocumentWikiTableRowToken', 'match' => '(\\A(?P\\n)(?P\\|))S' ), array( 'class' => 'ezcDocumentWikiPluginToken', 'match' => '(\\A\\n(?P\\{([a-zA-Z]+)[^}]*\\}(?:.*?\\n\\{\\2\\})?))Ss' ), // 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(?P\\\\))[^\\\\])S' ), // Inline markup array( 'class' => 'ezcDocumentWikiBoldToken', 'match' => '(\\A(?P\\*))S' ), array( 'class' => 'ezcDocumentWikiItalicToken', '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' => 'ezcDocumentWikiStrikeToken', 'match' => '(\\A(?P-))S' ), array( 'class' => 'ezcDocumentWikiInlineQuoteToken', 'match' => '(\\A(?P\\?\\?))S' ), array( 'class' => 'ezcDocumentWikiMonospaceToken', 'match' => '(\\A(?P\\{\\{|\\}\\}))S' ), array( 'class' => 'ezcDocumentWikiLineBreakToken', 'match' => '(\\A(?P\\\\\\\\))S' ), array( 'class' => 'ezcDocumentWikiConfluenceLinkStartToken', 'match' => '(\\A(?P\\[))S' ), array( 'class' => 'ezcDocumentWikiLinkEndToken', 'match' => '(\\A(?P\\]))S' ), array( 'class' => 'ezcDocumentWikiTableHeaderToken', 'match' => '(\\A(?P\\|\\|))S' ), array( 'class' => 'ezcDocumentWikiSeparatorToken', 'match' => '(\\A(?P\\|))S' ), array( 'class' => 'ezcDocumentWikiExternalLinkToken', 'match' => '(\\A(?P(?P[a-z]+://\\S+?|mailto:\\S+?))[,.?!:;"\']?(?:' . self::WHITESPACE_CHARS . '|\\n|\\||]|$))S' ), array( 'class' => 'ezcDocumentWikiImageStartToken', 'match' => '(\\A(?P(?P!))\S)S' ), array( 'class' => 'ezcDocumentWikiImageEndToken', 'match' => '(\\A(?P!))S' ), // 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 $plugin ) { // Match title, property string and plugin contents // {code:title=Bar.java|borderStyle=solid} ... {code} if ( preg_match( '(^{(?P[a-zA-Z]+)(?::(?P[^}]+))?}(?:(?P.*){\\1})?$)s', $plugin->content, $match ) ) { $plugin->type = $match['type']; if ( isset( $match['text'] ) ) { $plugin->text = $match['text']; } // Parse plugin parameters if ( isset( $match['params'] ) ) { $rawParams = explode( '|', $match['params'] ); $parameters = array(); foreach ( $rawParams as $content ) { if ( preg_match( '(^(?P[a-zA-Z]+)=(?P.*)$)', $content, $match ) ) { $parameters[$match['name']] = $match['value']; } else { $parameters[] = $content; } } $plugin->parameters = $parameters; } } } /** * Parse confluence image descriptors * * Parse confluence image descriptors which are completely different from * other wiki languages, so that they cannot be handled by the default * parser. * * @param ezcDocumentWikiImageStartToken $token * @param mixed $descriptor * @return void */ protected function parseImageDescriptor( ezcDocumentWikiImageStartToken $token, $descriptor ) { if ( !preg_match_all( '((?P[a-zA-Z]+)(?:=(?P[^,]+))?)', $descriptor, $matches ) ) { return; } // Set known properties on image start node, if available. foreach ( $matches['name'] as $nr => $name ) { $name = strtolower( $name ); if ( isset( $this->imageAttributeMapping[$name] ) ) { $property = $this->imageAttributeMapping[$name]; $token->$property = $matches['value'][$nr]; } } } /** * 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 ) { $lastImageStartToken = null; $lastImageSeparator = null; foreach ( $tokens as $nr => $token ) { switch ( true ) { // Extract the title / indentation level from the tokens // length. case $token instanceof ezcDocumentWikiTitleToken: $token->level = (int) $token->content[1]; break; case $token instanceof ezcDocumentWikiParagraphIndentationToken: $token->level = 1; break; case $token instanceof ezcDocumentWikiBulletListItemToken: case $token instanceof ezcDocumentWikiEnumeratedListItemToken: $token->indentation = strlen( $token->content ); break; case $token instanceof ezcDocumentWikiPluginToken: $this->parsePluginContents( $token ); break; case $token instanceof ezcDocumentWikiImageStartToken: // Store reference to last image start token $lastImageStartToken = $token; break; case $token instanceof ezcDocumentWikiSeparatorToken: if ( $lastImageStartToken !== null ) { $lastImageSeparator = $token; } break; case $token instanceof ezcDocumentWikiImageEndToken: if ( $lastImageSeparator === null ) { // No relating start token and/or separator - we do not // need to care. continue; } // Aggregate all texts until the separator $imageTokens = array(); $i = $nr - 1; while ( ( $i > 0 ) && ( $tokens[$i] !== $lastImageSeparator ) ) { $imageTokens[] = $tokens[$i]->content; unset( $tokens[$i--] ); } unset( $tokens[$i] ); // Extract and combine image descritor string, and remove // relating tokens, so that are not used elsewhere. $descriptior = implode( '', array_reverse( $imageTokens ) ); $this->parseImageDescriptor( $lastImageStartToken, $descriptior ); // Reset image token parsing environment $lastImageStartToken = null; $lastImageSeparator = null; break; case $token instanceof ezcDocumentWikiPluginToken: $this->parsePluginContents( $token ); break; } } return array_values( $tokens ); } } ?>