diff --git a/Parsedown.php b/Parsedown.php index ae0cbde..04c44ad 100644 --- a/Parsedown.php +++ b/Parsedown.php @@ -1,1994 +1,1404 @@ ['Header'], + '*' => ['Rule', 'List'], + '+' => ['List'], + '-' => ['SetextHeader', 'Table', 'Rule', 'List'], + '0' => ['List'], + '1' => ['List'], + '2' => ['List'], + '3' => ['List'], + '4' => ['List'], + '5' => ['List'], + '6' => ['List'], + '7' => ['List'], + '8' => ['List'], + '9' => ['List'], + ':' => ['Table'], + '<' => ['Comment', 'Markup'], + '=' => ['SetextHeader'], + '>' => ['Quote'], + '[' => ['Reference'], + '_' => ['Rule'], + '`' => ['FencedCode'], + '|' => ['Table'], + '~' => ['FencedCode'], + ]; + + /** + * @var string[] + */ + protected $unmarkedBlockTypes = [ + 'Code', + ]; + + /** + * @var string[][] + */ + protected $inlineTypes = [ + '"' => ['SpecialCharacter'], + '!' => ['Image'], + '&' => ['SpecialCharacter'], + '*' => ['Emphasis'], + ':' => ['Url'], + '<' => ['UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'], + '>' => ['SpecialCharacter'], + '[' => ['Link'], + '_' => ['Emphasis'], + '`' => ['Code'], + '~' => ['Strikethrough'], + '\\' => ['EscapeSequence'], + ]; + + protected $inlineMarkerList = '!"*_&[:<>`~\\'; + + protected $DefinitionData; + + protected $specialCharacters = [ + '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', + ]; + + protected $StrongRegex = [ + '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s', + '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us', + ]; + + protected $EmRegex = [ + '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', + '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', + ]; + + protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?'; + + protected $voidElements = [ + 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', + ]; + + protected $textLevelElements = [ + 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', + 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', + 'i', 'rp', 'del', 'code', 'strike', 'marquee', + 'q', 'rt', 'ins', 'font', 'strong', + 's', 'tt', 'kbd', 'mark', + 'u', 'xm', 'sub', 'nobr', + 'sup', 'ruby', + 'var', 'span', + 'wbr', 'time', + ]; + + /** + * @param string|null $name + * @return Parsedown + */ + public static function instance(?string $name = null): self + { + $name = $name ?? 'default'; + + if (isset(self::$instances[$name]) === true) { + return self::$instances[$name]; + } + + $instance = new static; + + self::$instances[$name] = $instance; + + return $instance; + } + + protected static function escape(string $text, bool $allowQuotes = false): string + { + return htmlspecialchars($text, $allowQuotes ? ENT_NOQUOTES : ENT_QUOTES, 'UTF-8'); + } + + protected static function striAtStart(string $string, string $needle): bool + { + if (strlen($needle) > strlen($string)) { + return false; + } + + return stripos($string, strtolower($needle)) === 0; + } + + public function text(string $text): string + { + // make sure no definitions are set + $this->DefinitionData = []; - # ~ + // standardize line breaks + $text = str_replace(["\r\n", "\r"], "\n", $text); - function text($text) - { - $Elements = $this->textElements($text); + // remove surrounding line breaks + $text = trim($text, "\n"); - # convert to markup - $markup = $this->elements($Elements); + // split text into lines + $lines = explode("\n", $text); - # trim line breaks - $markup = trim($markup, "\n"); + // iterate through lines to identify blocks + $markup = $this->lines($lines); - return $markup; - } + // trim line breaks + $markup = trim($markup, "\n"); - protected function textElements($text) - { - # make sure no definitions are set - $this->DefinitionData = array(); - - # standardize line breaks - $text = str_replace(array("\r\n", "\r"), "\n", $text); - - # remove surrounding line breaks - $text = trim($text, "\n"); - - # split text into lines - $lines = explode("\n", $text); - - # iterate through lines to identify blocks - return $this->linesElements($lines); - } - - # - # Setters - # - - function setBreaksEnabled($breaksEnabled) - { - $this->breaksEnabled = $breaksEnabled; - - return $this; - } - - protected $breaksEnabled; - - function setMarkupEscaped($markupEscaped) - { - $this->markupEscaped = $markupEscaped; - - return $this; - } - - protected $markupEscaped; - - function setUrlsLinked($urlsLinked) - { - $this->urlsLinked = $urlsLinked; - - return $this; - } - - protected $urlsLinked = true; - - function setSafeMode($safeMode) - { - $this->safeMode = (bool) $safeMode; - - return $this; - } - - protected $safeMode; - - function setStrictMode($strictMode) - { - $this->strictMode = (bool) $strictMode; - - return $this; - } - - protected $strictMode; - - protected $safeLinksWhitelist = array( - 'http://', - 'https://', - 'ftp://', - 'ftps://', - 'mailto:', - 'tel:', - 'data:image/png;base64,', - 'data:image/gif;base64,', - 'data:image/jpeg;base64,', - 'irc:', - 'ircs:', - 'git:', - 'ssh:', - 'news:', - 'steam:', - ); - - # - # Lines - # - - protected $BlockTypes = array( - '#' => array('Header'), - '*' => array('Rule', 'List'), - '+' => array('List'), - '-' => array('SetextHeader', 'Table', 'Rule', 'List'), - '0' => array('List'), - '1' => array('List'), - '2' => array('List'), - '3' => array('List'), - '4' => array('List'), - '5' => array('List'), - '6' => array('List'), - '7' => array('List'), - '8' => array('List'), - '9' => array('List'), - ':' => array('Table'), - '<' => array('Comment', 'Markup'), - '=' => array('SetextHeader'), - '>' => array('Quote'), - '[' => array('Reference'), - '_' => array('Rule'), - '`' => array('FencedCode'), - '|' => array('Table'), - '~' => array('FencedCode'), - ); - - # ~ - - protected $unmarkedBlockTypes = array( - 'Code', - ); - - # - # Blocks - # - - protected function lines(array $lines) - { - return $this->elements($this->linesElements($lines)); - } - - protected function linesElements(array $lines) - { - $Elements = array(); - $CurrentBlock = null; - - foreach ($lines as $line) - { - if (chop($line) === '') - { - if (isset($CurrentBlock)) - { - $CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted']) - ? $CurrentBlock['interrupted'] + 1 : 1 - ); - } - - continue; - } - - while (($beforeTab = strstr($line, "\t", true)) !== false) - { - $shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4; - - $line = $beforeTab - . str_repeat(' ', $shortage) - . substr($line, strlen($beforeTab) + 1) - ; - } - - $indent = strspn($line, ' '); - - $text = $indent > 0 ? substr($line, $indent) : $line; - - # ~ - - $Line = array('body' => $line, 'indent' => $indent, 'text' => $text); - - # ~ - - if (isset($CurrentBlock['continuable'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Continue'; - $Block = $this->$methodName($Line, $CurrentBlock); - - if (isset($Block)) - { - $CurrentBlock = $Block; - - continue; - } - else - { - if ($this->isBlockCompletable($CurrentBlock['type'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; - $CurrentBlock = $this->$methodName($CurrentBlock); - } - } - } - - # ~ - - $marker = $text[0]; - - # ~ - - $blockTypes = $this->unmarkedBlockTypes; - - if (isset($this->BlockTypes[$marker])) - { - foreach ($this->BlockTypes[$marker] as $blockType) - { - $blockTypes []= $blockType; - } - } - - # - # ~ - - foreach ($blockTypes as $blockType) - { - $Block = $this->{"block$blockType"}($Line, $CurrentBlock); - - if (isset($Block)) - { - $Block['type'] = $blockType; - - if ( ! isset($Block['identified'])) - { - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - $Block['identified'] = true; - } - - if ($this->isBlockContinuable($blockType)) - { - $Block['continuable'] = true; - } - - $CurrentBlock = $Block; - - continue 2; - } - } - - # ~ - - if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph') - { - $Block = $this->paragraphContinue($Line, $CurrentBlock); - } - - if (isset($Block)) - { - $CurrentBlock = $Block; - } - else - { - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - $CurrentBlock = $this->paragraph($Line); - - $CurrentBlock['identified'] = true; - } - } - - # ~ - - if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; - $CurrentBlock = $this->$methodName($CurrentBlock); - } - - # ~ - - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - # ~ - - return $Elements; - } - - protected function extractElement(array $Component) - { - if ( ! isset($Component['element'])) - { - if (isset($Component['markup'])) - { - $Component['element'] = array('rawHtml' => $Component['markup']); - } - elseif (isset($Component['hidden'])) - { - $Component['element'] = array(); - } - } - - return $Component['element']; - } - - protected function isBlockContinuable($Type) - { - return method_exists($this, 'block' . $Type . 'Continue'); - } - - protected function isBlockCompletable($Type) - { - return method_exists($this, 'block' . $Type . 'Complete'); - } - - # - # Code - - protected function blockCode($Line, $Block = null) - { - if (isset($Block) and $Block['type'] === 'Paragraph' and ! isset($Block['interrupted'])) - { - return; - } - - if ($Line['indent'] >= 4) - { - $text = substr($Line['body'], 4); - - $Block = array( - 'element' => array( - 'name' => 'pre', - 'element' => array( - 'name' => 'code', - 'text' => $text, - ), - ), - ); - - return $Block; - } - } - - protected function blockCodeContinue($Line, $Block) - { - if ($Line['indent'] >= 4) - { - if (isset($Block['interrupted'])) - { - $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); - - unset($Block['interrupted']); - } - - $Block['element']['element']['text'] .= "\n"; - - $text = substr($Line['body'], 4); - - $Block['element']['element']['text'] .= $text; - - return $Block; - } - } - - protected function blockCodeComplete($Block) - { - return $Block; - } - - # - # Comment - - protected function blockComment($Line) - { - if ($this->markupEscaped or $this->safeMode) - { - return; - } - - if (strpos($Line['text'], '') !== false) - { - $Block['closed'] = true; - } - - return $Block; - } - } - - protected function blockCommentContinue($Line, array $Block) - { - if (isset($Block['closed'])) - { - return; - } - - $Block['element']['rawHtml'] .= "\n" . $Line['body']; - - if (strpos($Line['text'], '-->') !== false) - { - $Block['closed'] = true; - } - - return $Block; - } - - # - # Fenced Code - - protected function blockFencedCode($Line) - { - $marker = $Line['text'][0]; - - $openerLength = strspn($Line['text'], $marker); - - if ($openerLength < 3) - { - return; - } - - $infostring = trim(substr($Line['text'], $openerLength), "\t "); - - if (strpos($infostring, '`') !== false) - { - return; - } - - $Element = array( - 'name' => 'code', - 'text' => '', - ); - - if ($infostring !== '') - { - /** - * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes - * Every HTML element may have a class attribute specified. - * The attribute, if specified, must have a value that is a set - * of space-separated tokens representing the various classes - * that the element belongs to. - * [...] - * The space characters, for the purposes of this specification, - * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), - * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and - * U+000D CARRIAGE RETURN (CR). - */ - $language = substr($infostring, 0, strcspn($infostring, " \t\n\f\r")); - - $Element['attributes'] = array('class' => "language-$language"); - } - - $Block = array( - 'char' => $marker, - 'openerLength' => $openerLength, - 'element' => array( - 'name' => 'pre', - 'element' => $Element, - ), - ); - - return $Block; - } - - protected function blockFencedCodeContinue($Line, $Block) - { - if (isset($Block['complete'])) - { - return; - } - - if (isset($Block['interrupted'])) - { - $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); - - unset($Block['interrupted']); - } - - if (($len = strspn($Line['text'], $Block['char'])) >= $Block['openerLength'] - and chop(substr($Line['text'], $len), ' ') === '' - ) { - $Block['element']['element']['text'] = substr($Block['element']['element']['text'], 1); - - $Block['complete'] = true; - - return $Block; - } - - $Block['element']['element']['text'] .= "\n" . $Line['body']; - - return $Block; - } - - protected function blockFencedCodeComplete($Block) - { - return $Block; - } - - # - # Header - - protected function blockHeader($Line) - { - $level = strspn($Line['text'], '#'); - - if ($level > 6) - { - return; - } - - $text = trim($Line['text'], '#'); - - if ($this->strictMode and isset($text[0]) and $text[0] !== ' ') - { - return; - } - - $text = trim($text, ' '); - - $Block = array( - 'element' => array( - 'name' => 'h' . $level, - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $text, - 'destination' => 'elements', - ) - ), - ); - - return $Block; - } - - # - # List - - protected function blockList($Line, array $CurrentBlock = null) - { - list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]'); - - if (preg_match('/^('.$pattern.'([ ]++|$))(.*+)/', $Line['text'], $matches)) - { - $contentIndent = strlen($matches[2]); - - if ($contentIndent >= 5) - { - $contentIndent -= 1; - $matches[1] = substr($matches[1], 0, -$contentIndent); - $matches[3] = str_repeat(' ', $contentIndent) . $matches[3]; - } - elseif ($contentIndent === 0) - { - $matches[1] .= ' '; - } - - $markerWithoutWhitespace = strstr($matches[1], ' ', true); - - $Block = array( - 'indent' => $Line['indent'], - 'pattern' => $pattern, - 'data' => array( - 'type' => $name, - 'marker' => $matches[1], - 'markerType' => ($name === 'ul' ? $markerWithoutWhitespace : substr($markerWithoutWhitespace, -1)), - ), - 'element' => array( - 'name' => $name, - 'elements' => array(), - ), - ); - $Block['data']['markerTypeRegex'] = preg_quote($Block['data']['markerType'], '/'); - - if ($name === 'ol') - { - $listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0'; - - if ($listStart !== '1') - { - if ( - isset($CurrentBlock) - and $CurrentBlock['type'] === 'Paragraph' - and ! isset($CurrentBlock['interrupted']) - ) { - return; - } - - $Block['element']['attributes'] = array('start' => $listStart); - } - } - - $Block['li'] = array( - 'name' => 'li', - 'handler' => array( - 'function' => 'li', - 'argument' => !empty($matches[3]) ? array($matches[3]) : array(), - 'destination' => 'elements' - ) - ); - - $Block['element']['elements'] []= & $Block['li']; - - return $Block; - } - } - - protected function blockListContinue($Line, array $Block) - { - if (isset($Block['interrupted']) and empty($Block['li']['handler']['argument'])) - { - return null; - } - - $requiredIndent = ($Block['indent'] + strlen($Block['data']['marker'])); - - if ($Line['indent'] < $requiredIndent - and ( - ( - $Block['data']['type'] === 'ol' - and preg_match('/^[0-9]++'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) - ) or ( - $Block['data']['type'] === 'ul' - and preg_match('/^'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) - ) - ) - ) { - if (isset($Block['interrupted'])) - { - $Block['li']['handler']['argument'] []= ''; - - $Block['loose'] = true; - - unset($Block['interrupted']); - } - - unset($Block['li']); - - $text = isset($matches[1]) ? $matches[1] : ''; - - $Block['indent'] = $Line['indent']; - - $Block['li'] = array( - 'name' => 'li', - 'handler' => array( - 'function' => 'li', - 'argument' => array($text), - 'destination' => 'elements' - ) - ); - - $Block['element']['elements'] []= & $Block['li']; - - return $Block; - } - elseif ($Line['indent'] < $requiredIndent and $this->blockList($Line)) - { - return null; - } - - if ($Line['text'][0] === '[' and $this->blockReference($Line)) - { - return $Block; - } - - if ($Line['indent'] >= $requiredIndent) - { - if (isset($Block['interrupted'])) - { - $Block['li']['handler']['argument'] []= ''; - - $Block['loose'] = true; - - unset($Block['interrupted']); - } - - $text = substr($Line['body'], $requiredIndent); - - $Block['li']['handler']['argument'] []= $text; - - return $Block; - } - - if ( ! isset($Block['interrupted'])) - { - $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']); - - $Block['li']['handler']['argument'] []= $text; - - return $Block; - } - } - - protected function blockListComplete(array $Block) - { - if (isset($Block['loose'])) - { - foreach ($Block['element']['elements'] as &$li) - { - if (end($li['handler']['argument']) !== '') - { - $li['handler']['argument'] []= ''; - } - } - } - - return $Block; - } - - # - # Quote - - protected function blockQuote($Line) - { - if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) - { - $Block = array( - 'element' => array( - 'name' => 'blockquote', - 'handler' => array( - 'function' => 'linesElements', - 'argument' => (array) $matches[1], - 'destination' => 'elements', - ) - ), - ); - - return $Block; - } - } - - protected function blockQuoteContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) - { - $Block['element']['handler']['argument'] []= $matches[1]; - - return $Block; - } - - if ( ! isset($Block['interrupted'])) - { - $Block['element']['handler']['argument'] []= $Line['text']; - - return $Block; - } - } - - # - # Rule - - protected function blockRule($Line) - { - $marker = $Line['text'][0]; - - if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '') - { - $Block = array( - 'element' => array( - 'name' => 'hr', - ), - ); - - return $Block; - } - } - - # - # Setext - - protected function blockSetextHeader($Line, array $Block = null) - { - if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) - { - return; - } - - if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '') - { - $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; - - return $Block; - } - } - - # - # Markup - - protected function blockMarkup($Line) - { - if ($this->markupEscaped or $this->safeMode) - { - return; - } - - if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches)) - { - $element = strtolower($matches[1]); - - if (in_array($element, $this->textLevelElements)) - { - return; - } - - $Block = array( - 'name' => $matches[1], - 'element' => array( - 'rawHtml' => $Line['text'], - 'autobreak' => true, - ), - ); - - return $Block; - } - } - - protected function blockMarkupContinue($Line, array $Block) - { - if (isset($Block['closed']) or isset($Block['interrupted'])) - { - return; - } - - $Block['element']['rawHtml'] .= "\n" . $Line['body']; - - return $Block; - } - - # - # Reference - - protected function blockReference($Line) - { - if (strpos($Line['text'], ']') !== false - and preg_match('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches) - ) { - $id = strtolower($matches[1]); - - $Data = array( - 'url' => $matches[2], - 'title' => isset($matches[3]) ? $matches[3] : null, - ); - - $this->DefinitionData['Reference'][$id] = $Data; - - $Block = array( - 'element' => array(), - ); - - return $Block; - } - } - - # - # Table - - protected function blockTable($Line, array $Block = null) - { - if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) - { - return; - } - - if ( - strpos($Block['element']['handler']['argument'], '|') === false - and strpos($Line['text'], '|') === false - and strpos($Line['text'], ':') === false - or strpos($Block['element']['handler']['argument'], "\n") !== false - ) { - return; - } - - if (chop($Line['text'], ' -:|') !== '') - { - return; - } - - $alignments = array(); - - $divider = $Line['text']; - - $divider = trim($divider); - $divider = trim($divider, '|'); - - $dividerCells = explode('|', $divider); - - foreach ($dividerCells as $dividerCell) - { - $dividerCell = trim($dividerCell); - - if ($dividerCell === '') - { - return; - } - - $alignment = null; - - if ($dividerCell[0] === ':') - { - $alignment = 'left'; - } - - if (substr($dividerCell, - 1) === ':') - { - $alignment = $alignment === 'left' ? 'center' : 'right'; - } - - $alignments []= $alignment; - } - - # ~ + return $markup; + } - $HeaderElements = array(); - - $header = $Block['element']['handler']['argument']; - - $header = trim($header); - $header = trim($header, '|'); - - $headerCells = explode('|', $header); - - if (count($headerCells) !== count($alignments)) - { - return; - } - - foreach ($headerCells as $index => $headerCell) - { - $headerCell = trim($headerCell); - - $HeaderElement = array( - 'name' => 'th', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $headerCell, - 'destination' => 'elements', - ) - ); - - if (isset($alignments[$index])) - { - $alignment = $alignments[$index]; - - $HeaderElement['attributes'] = array( - 'style' => "text-align: $alignment;", - ); - } - - $HeaderElements []= $HeaderElement; - } - - # ~ - - $Block = array( - 'alignments' => $alignments, - 'identified' => true, - 'element' => array( - 'name' => 'table', - 'elements' => array(), - ), - ); - - $Block['element']['elements'] []= array( - 'name' => 'thead', - ); - - $Block['element']['elements'] []= array( - 'name' => 'tbody', - 'elements' => array(), - ); - - $Block['element']['elements'][0]['elements'] []= array( - 'name' => 'tr', - 'elements' => $HeaderElements, - ); - - return $Block; - } - - protected function blockTableContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|')) - { - $Elements = array(); - - $row = $Line['text']; - - $row = trim($row); - $row = trim($row, '|'); - - preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches); - - $cells = array_slice($matches[0], 0, count($Block['alignments'])); - - foreach ($cells as $index => $cell) - { - $cell = trim($cell); - - $Element = array( - 'name' => 'td', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $cell, - 'destination' => 'elements', - ) - ); - - if (isset($Block['alignments'][$index])) - { - $Element['attributes'] = array( - 'style' => 'text-align: ' . $Block['alignments'][$index] . ';', - ); - } - - $Elements []= $Element; - } - - $Element = array( - 'name' => 'tr', - 'elements' => $Elements, - ); - - $Block['element']['elements'][1]['elements'] []= $Element; - - return $Block; - } - } - - # - # ~ - # - - protected function paragraph($Line) - { - return array( - 'type' => 'Paragraph', - 'element' => array( - 'name' => 'p', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $Line['text'], - 'destination' => 'elements', - ), - ), - ); - } - - protected function paragraphContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - $Block['element']['handler']['argument'] .= "\n".$Line['text']; - - return $Block; - } - - # - # Inline Elements - # - - protected $InlineTypes = array( - '!' => array('Image'), - '&' => array('SpecialCharacter'), - '*' => array('Emphasis'), - ':' => array('Url'), - '<' => array('UrlTag', 'EmailTag', 'Markup'), - '[' => array('Link'), - '_' => array('Emphasis'), - '`' => array('Code'), - '~' => array('Strikethrough'), - '\\' => array('EscapeSequence'), - ); + public function setBreaksEnabled(bool $breaksEnabled): self + { + $this->breaksEnabled = $breaksEnabled; - # ~ + return $this; + } - protected $inlineMarkerList = '!*_&[:<`~\\'; + public function setMarkupEscaped(bool $markupEscaped): self + { + $this->markupEscaped = $markupEscaped; - # - # ~ - # + return $this; + } - public function line($text, $nonNestables = array()) - { - return $this->elements($this->lineElements($text, $nonNestables)); - } + public function setUrlsLinked(bool $urlsLinked): self + { + $this->urlsLinked = $urlsLinked; - protected function lineElements($text, $nonNestables = array()) - { - # standardize line breaks - $text = str_replace(array("\r\n", "\r"), "\n", $text); + return $this; + } - $Elements = array(); - - $nonNestables = (empty($nonNestables) - ? array() - : array_combine($nonNestables, $nonNestables) - ); - - # $excerpt is based on the first occurrence of a marker - - while ($excerpt = strpbrk($text, $this->inlineMarkerList)) - { - $marker = $excerpt[0]; - - $markerPosition = strlen($text) - strlen($excerpt); - - $Excerpt = array('text' => $excerpt, 'context' => $text); - - foreach ($this->InlineTypes[$marker] as $inlineType) - { - # check to see if the current inline type is nestable in the current context - - if (isset($nonNestables[$inlineType])) - { - continue; - } - - $Inline = $this->{"inline$inlineType"}($Excerpt); + public function setSafeMode(bool $safeMode): self + { + $this->safeMode = $safeMode; - if ( ! isset($Inline)) - { - continue; - } - - # makes sure that the inline belongs to "our" marker - - if (isset($Inline['position']) and $Inline['position'] > $markerPosition) - { - continue; - } - - # sets a default inline position - - if ( ! isset($Inline['position'])) - { - $Inline['position'] = $markerPosition; - } - - # cause the new element to 'inherit' our non nestables + return $this; + } + public function line(string $text, array $nonNestables = []): string + { + $markup = ''; - $Inline['element']['nonNestables'] = isset($Inline['element']['nonNestables']) - ? array_merge($Inline['element']['nonNestables'], $nonNestables) - : $nonNestables - ; + # $excerpt is based on the first occurrence of a marker - # the text that comes before the inline - $unmarkedText = substr($text, 0, $Inline['position']); + while ($excerpt = strpbrk($text, $this->inlineMarkerList)) { + $marker = $excerpt[0]; + $markerPosition = strpos($text, $marker); + $Excerpt = ['text' => $excerpt, 'context' => $text]; + + foreach ($this->inlineTypes[$marker] as $inlineType) { + # check to see if the current inline type is nestable in the current context + + if (!empty($nonNestables) && in_array($inlineType, $nonNestables, true)) { + continue; + } + + $inline = $this->{'inline' . $inlineType}($Excerpt); + + if (!isset($inline)) { + continue; + } + + # makes sure that the inline belongs to "our" marker + + if (isset($inline['position']) && $inline['position'] > $markerPosition) { + continue; + } + + # sets a default inline position + + if (!isset($inline['position'])) { + $inline['position'] = $markerPosition; + } + + # cause the new element to 'inherit' our non nestables + + foreach ($nonNestables as $non_nestable) { + $inline['element']['nonNestables'][] = $non_nestable; + } + + # the text that comes before the inline + $unmarkedText = substr($text, 0, $inline['position']); + + # compile the unmarked text + $markup .= $this->unmarkedText($unmarkedText); + + # compile the inline + $markup .= $inline['markup'] ?? $this->element($inline['element']); + + # remove the examined text + $text = substr($text, $inline['position'] + $inline['extent']); + + continue 2; + } + + # the marker does not belong to an inline + + $unmarkedText = substr($text, 0, $markerPosition + 1); + $markup .= $this->unmarkedText($unmarkedText); + $text = substr($text, $markerPosition + 1); + } + + $markup .= $this->unmarkedText($text); + + return $markup; + } + + /** + * Alias for ->text(). + * + * @param string $haystack + * @return string + */ + public function parse(string $haystack): string + { + return $this->text($haystack); + } + + protected function lines(array $lines): string + { + $currentBlock = null; + + foreach ($lines as $line) { + if (rtrim($line) === '') { + if (isset($currentBlock)) { + $currentBlock['interrupted'] = true; + } + + continue; + } + + if (strpos($line, "\t") !== false) { + $parts = explode("\t", $line); + $line = $parts[0]; + unset($parts[0]); + + foreach ($parts as $part) { + $shortage = 4 - mb_strlen($line, 'utf-8') % 4; + $line .= str_repeat(' ', $shortage); + $line .= $part; + } + } + + $indent = 0; + + while (isset($line[$indent]) && $line[$indent] === ' ') { + $indent++; + } + + $text = $indent > 0 ? substr($line, $indent) : $line; + $Line = ['body' => $line, 'indent' => $indent, 'text' => $text]; + + if (isset($currentBlock['continuable'])) { + $block = $this->{'block' . $currentBlock['type'] . 'Continue'}($Line, $currentBlock); + + if (isset($block)) { + $currentBlock = $block; + + continue; + } + + if ($this->isBlockCompletable($currentBlock['type'])) { + $currentBlock = $this->{'block' . $currentBlock['type'] . 'Complete'}($currentBlock); + } + } + + # ~ + + $marker = $text[0]; + $blockTypes = $this->unmarkedBlockTypes; + + if (isset($this->blockTypes[$marker])) { + foreach ($this->blockTypes[$marker] as $blockType) { + $blockTypes[] = $blockType; + } + } + + # ~ + + foreach ($blockTypes as $blockType) { + $block = $this->{'block' . $blockType}($Line, $currentBlock); + + if (isset($block)) { + $block['type'] = $blockType; + + if (!isset($block['identified'])) { + $blocks[] = $currentBlock; + $block['identified'] = true; + } + + if ($this->isBlockContinuable($blockType)) { + $block['continuable'] = true; + } + + $currentBlock = $block; + + continue 2; + } + } + + # ~ + + if (isset($currentBlock) && !isset($currentBlock['type']) && !isset($currentBlock['interrupted'])) { + $currentBlock['element']['text'] .= "\n" . $text; + } else { + $blocks[] = $currentBlock; + $currentBlock = $this->paragraph($Line); + $currentBlock['identified'] = true; + } + } + + if (isset($currentBlock['continuable']) && $this->isBlockCompletable($currentBlock['type'])) { + $currentBlock = $this->{'block' . $currentBlock['type'] . 'Complete'}($currentBlock); + } + + $blocks[] = $currentBlock; + + unset($blocks[0]); + + $markup = ''; + + foreach ($blocks as $block) { + if (isset($block['hidden'])) { + continue; + } + + $markup .= "\n"; + $markup .= $block['markup'] ?? $this->element($block['element']); + } + + $markup .= "\n"; + + return $markup; + } + + protected function isBlockContinuable($type): bool + { + return method_exists($this, 'block' . $type . 'Continue'); + } + + protected function isBlockCompletable(string $type): bool + { + return method_exists($this, 'block' . $type . 'Complete'); + } + + protected function blockCode(array $Line, ?array $block = null): ?array + { + if (isset($block) && !isset($block['type']) && !isset($block['interrupted'])) { + return null; + } + + if ($Line['indent'] >= 4) { + return [ + 'element' => [ + 'name' => 'pre', + 'handler' => 'element', + 'text' => [ + 'name' => 'code', + 'text' => substr($Line['body'], 4), + ], + ], + ]; + } + + return null; + } + + protected function blockCodeContinue(array $line, array $block): ?array + { + if ($line['indent'] >= 4) { + if (isset($block['interrupted'])) { + $block['element']['text']['text'] .= "\n"; + unset($block['interrupted']); + } + + $block['element']['text']['text'] .= "\n"; + $text = substr($line['body'], 4); + $block['element']['text']['text'] .= $text; + + return $block; + } + + return null; + } + + protected function blockCodeComplete(array $block): array + { + $text = $block['element']['text']['text']; + $block['element']['text']['text'] = $text; + + return $block; + } + + protected function blockComment(array $line): ?array + { + if ($this->markupEscaped || $this->safeMode) { + return null; + } + + if (isset($line['text'][3]) && $line['text'][3] === '-' && $line['text'][2] === '-' && $line['text'][1] === '!') { + $block = [ + 'markup' => $line['body'], + ]; + + if (preg_match('/-->$/', $line['text'])) { + $block['closed'] = true; + } + + return $block; + } + + return null; + } + + protected function blockCommentContinue(array $line, array $block): ?array + { + if (isset($block['closed'])) { + return null; + } + + $block['markup'] .= "\n" . $line['body']; + + if (preg_match('/-->$/', $line['text'])) { + $block['closed'] = true; + } + + return $block; + } + + protected function blockFencedCode(array $Line): ?array + { + if (preg_match('/^[' . $Line['text'][0] . ']{3,}[ ]*([^`]+)?[ ]*$/', $Line['text'], $matches)) { + $element = [ + 'name' => 'code', + 'text' => '', + ]; + + if (isset($matches[1])) { + /** + * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes + * Every HTML element may have a class attribute specified. + * The attribute, if specified, must have a value that is a set + * of space-separated tokens representing the various classes + * that the element belongs to. + * [...] + * The space characters, for the purposes of this specification, + * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), + * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and + * U+000D CARRIAGE RETURN (CR). + */ + $language = substr($matches[1], 0, strcspn($matches[1], " \t\n\f\r")); + $class = 'language-' . $language; + $element['attributes'] = [ + 'class' => $class, + ]; + } + + return [ + 'char' => $Line['text'][0], + 'element' => [ + 'name' => 'pre', + 'handler' => 'element', + 'text' => $element, + ], + ]; + } + + return null; + } + + protected function blockFencedCodeContinue(array $line, array $block): ?array + { + if (isset($block['complete'])) { + return null; + } + + if (isset($block['interrupted'])) { + $block['element']['text']['text'] .= "\n"; + + unset($block['interrupted']); + } + + if (preg_match('/^' . $block['char'] . '{3,}[ ]*$/', $line['text'])) { + $block['element']['text']['text'] = substr($block['element']['text']['text'], 1); + $block['complete'] = true; + + return $block; + } + + $block['element']['text']['text'] .= "\n" . $line['body']; + + return $block; + } + + protected function blockFencedCodeComplete(array $block): array + { + $text = $block['element']['text']['text']; + $block['element']['text']['text'] = $text; + + return $block; + } + + protected function blockHeader(array $line): ?array + { + if (isset($line['text'][1])) { + $level = 1; + + while (isset($line['text'][$level]) && $line['text'][$level] === '#') { + $level++; + } + + if ($level > 6) { + return null; + } + + $Block = [ + 'element' => [ + 'name' => 'h' . min(6, $level), + 'text' => trim($line['text'], '# '), + 'handler' => 'line', + ], + ]; + + return $Block; + } + + return null; + } + + protected function blockList(array $Line): ?array + { + [$name, $pattern] = $Line['text'][0] <= '-' ? ['ul', '[*+-]'] : ['ol', '[0-9]+[.]']; + + if (preg_match('/^(' . $pattern . '[ ]+)(.*)/', $Line['text'], $matches)) { + $block = [ + 'indent' => $Line['indent'], + 'pattern' => $pattern, + 'element' => [ + 'name' => $name, + 'handler' => 'elements', + ], + ]; + + if ($name === 'ol' && ($listStart = strstr($matches[0], '.', true)) !== '1') { + $block['element']['attributes'] = ['start' => $listStart]; + } + + $block['li'] = [ + 'name' => 'li', + 'handler' => 'li', + 'text' => [ + $matches[2], + ], + ]; + + $block['element']['text'] [] = &$block['li']; + + return $block; + } + + return null; + } + + protected function blockListContinue(array $line, array $block): ?array + { + if ($block['indent'] === $line['indent'] && preg_match('/^' . $block['pattern'] . '(?:[ ]+(.*)|$)/', $line['text'], $matches)) { + if (isset($block['interrupted'])) { + $block['li']['text'] [] = ''; + $block['loose'] = true; + + unset($block['interrupted']); + } + + unset($block['li']); + $text = $matches[1] ?? ''; + + $block['li'] = [ + 'name' => 'li', + 'handler' => 'li', + 'text' => [ + $text, + ], + ]; + + $block['element']['text'] [] = &$block['li']; + + return $block; + } + + if ($line['text'][0] === '[' && $this->blockReference($line)) { + return $block; + } + + if (!isset($block['interrupted'])) { + $text = preg_replace('/^[ ]{0,4}/', '', $line['body']); + $block['li']['text'] [] = $text; + + return $block; + } + + if ($line['indent'] > 0) { + $block['li']['text'] [] = ''; + $text = preg_replace('/^[ ]{0,4}/', '', $line['body']); + $block['li']['text'] [] = $text; + unset($block['interrupted']); + + return $block; + } + + return null; + } + + protected function blockListComplete(array $block): array + { + if (isset($block['loose'])) { + foreach ($block['element']['text'] as &$li) { + if (end($li['text']) !== '') { + $li['text'] [] = ''; + } + } + } + + return $block; + } + + protected function blockQuote(array $line): ?array + { + if (preg_match('/^>[ ]?(.*)/', $line['text'], $matches)) { + return [ + 'element' => [ + 'name' => 'blockquote', + 'handler' => 'lines', + 'text' => (array) $matches[1], + ], + ]; + } + + return null; + } + + protected function blockQuoteContinue($line, array $block): ?array + { + if ($line['text'][0] === '>' && preg_match('/^>[ ]?(.*)/', $line['text'], $matches)) { + if (isset($block['interrupted'])) { + $block['element']['text'] [] = ''; + unset($block['interrupted']); + } + + $block['element']['text'] [] = $matches[1]; + + return $block; + } + + if (!isset($block['interrupted'])) { + $block['element']['text'] [] = $line['text']; + + return $block; + } + + return null; + } + + protected function blockRule(array $line): ?array + { + if (preg_match('/^([' . $line['text'][0] . '])([ ]*\1){2,}[ ]*$/', $line['text'])) { + return [ + 'element' => [ + 'name' => 'hr', + ], + ]; + } + + return null; + } + + protected function blockSetextHeader(array $line, array $block = null): ?array + { + if (!isset($block) || isset($block['type']) || isset($block['interrupted'])) { + return null; + } + + if (rtrim($line['text'], $line['text'][0]) === '') { + $block['element']['name'] = $line['text'][0] === '=' ? 'h1' : 'h2'; + + return $block; + } + + return null; + } + + protected function blockMarkup(array $line): ?array + { + if ($this->markupEscaped || $this->safeMode) { + return null; + } + + if (preg_match('/^<(\w[\w-]*)(?:[ ]*' . $this->regexHtmlAttribute . ')*[ ]*(\/)?>/', $line['text'], $matches)) { + $element = strtolower($matches[1]); + + if (in_array($element, $this->textLevelElements, true)) { + return null; + } + + $block = [ + 'name' => $matches[1], + 'depth' => 0, + 'markup' => $line['text'], + ]; + + $length = strlen($matches[0]); + $remainder = substr($line['text'], $length); + + if (trim($remainder) === '') { + if (isset($matches[2]) || in_array($matches[1], $this->voidElements, true)) { + $block['closed'] = true; + + $block['void'] = true; + } + } else { + if (isset($matches[2]) || in_array($matches[1], $this->voidElements, true)) { + return null; + } + + if (preg_match('/<\/' . $matches[1] . '>[ ]*$/i', $remainder)) { + $block['closed'] = true; + } + } + + return $block; + } + + return null; + } + + protected function blockMarkupContinue(array $line, array $block): ?array + { + if (isset($block['closed'])) { + return null; + } + + if (preg_match('/^<' . $block['name'] . '(?:[ ]*' . $this->regexHtmlAttribute . ')*[ ]*>/i', $line['text'])) { + $block['depth']++; // Open + } + + if (preg_match('/(.*?)<\/' . $block['name'] . '>[ ]*$/i', $line['text'], $matches)) { + if ($block['depth'] > 0) { // Close + $block['depth']--; + } else { + $block['closed'] = true; + } + } + + if (isset($block['interrupted'])) { + $block['markup'] .= "\n"; + unset($block['interrupted']); + } + + $block['markup'] .= "\n" . $line['body']; + + return $block; + } + + protected function blockReference(array $line): ?array + { + if (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $line['text'], $matches)) { + $data = [ + 'url' => $matches[2], + 'title' => null, + ]; + + if (isset($matches[3])) { + $data['title'] = $matches[3]; + } + + $this->DefinitionData['Reference'][strtolower($matches[1])] = $data; + + return [ + 'hidden' => true, + ]; + } + + return null; + } + + protected function blockTable(array $line, ?array $block = null): ?array + { + if (!isset($block) || isset($block['type']) || isset($block['interrupted'])) { + return null; + } + + if (rtrim($line['text'], ' -:|') === '' && strpos($block['element']['text'], '|') !== false) { + $alignments = []; + + foreach (explode('|', trim(trim($line['text']), '|')) as $dividerCell) { + $dividerCell = trim($dividerCell); + + if ($dividerCell === '') { + continue; + } + + $alignment = null; + + if (strpos($dividerCell, ':') === 0) { + $alignment = 'left'; + } + + if (substr($dividerCell, -1) === ':') { + $alignment = $alignment === 'left' ? 'center' : 'right'; + } + + $alignments[] = $alignment; + } + + $headerElements = []; + $header = trim(trim($block['element']['text']), '|'); + $headerCells = explode('|', $header); + + foreach ($headerCells as $index => $headerCell) { + $headerCell = trim($headerCell); + + $HeaderElement = [ + 'name' => 'th', + 'text' => $headerCell, + 'handler' => 'line', + ]; + + if (isset($alignments[$index])) { + $alignment = $alignments[$index]; + + $HeaderElement['attributes'] = [ + 'style' => 'text-align: ' . $alignment . ';', + ]; + } + + $headerElements[] = $HeaderElement; + } + + $block = [ + 'alignments' => $alignments, + 'identified' => true, + 'element' => [ + 'name' => 'table', + 'handler' => 'elements', + ], + ]; + + $block['element']['text'] [] = [ + 'name' => 'thead', + 'handler' => 'elements', + ]; + + $block['element']['text'] [] = [ + 'name' => 'tbody', + 'handler' => 'elements', + 'text' => [], + ]; + + $block['element']['text'][0]['text'] [] = [ + 'name' => 'tr', + 'handler' => 'elements', + 'text' => $headerElements, + ]; + + return $block; + } + + return null; + } + + protected function blockTableContinue(array $line, array $block): ?array + { + if (isset($block['interrupted'])) { + return null; + } + + if ($line['text'][0] === '|' || strpos($line['text'], '|')) { + $elements = []; + $row = trim(trim($line['text']), '|'); + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + + foreach ($matches[0] as $index => $cell) { + $cell = trim($cell); + + $element = [ + 'name' => 'td', + 'handler' => 'line', + 'text' => $cell, + ]; + + if (isset($block['alignments'][$index])) { + $element['attributes'] = [ + 'style' => 'text-align: ' . $block['alignments'][$index] . ';', + ]; + } + + $elements[] = $element; + } + + $element = [ + 'name' => 'tr', + 'handler' => 'elements', + 'text' => $elements, + ]; + + $block['element']['text'][1]['text'] [] = $element; + + return $block; + } + + return null; + } + + protected function paragraph(array $line): array + { + return [ + 'element' => [ + 'name' => 'p', + 'text' => $line['text'], + 'handler' => 'line', + ], + ]; + } + + protected function inlineCode(array $excerpt): ?array + { + $marker = $excerpt['text'][0]; + + if (preg_match('/^(' . $marker . '+)[ ]*(.+?)[ ]*(? strlen($matches[0]), + 'element' => [ + 'name' => 'code', + 'text' => (string) preg_replace("/[ ]*\n/", ' ', $matches[2]), + ], + ]; + } + + return null; + } + + protected function inlineEmailTag(array $excerpt): ?array + { + if (strpos($excerpt['text'], '>') !== false && preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $excerpt['text'], $matches)) { + return [ + 'extent' => strlen($matches[0]), + 'element' => [ + 'name' => 'a', + 'text' => $matches[1], + 'attributes' => [ + 'href' => !isset($matches[2]) ? 'mailto:' . $matches[1] : $matches[1], + ], + ], + ]; + } + + return null; + } + + protected function inlineEmphasis(array $excerpt): ?array + { + if (!isset($excerpt['text'][1])) { + return null; + } + + $marker = $excerpt['text'][0]; + + if ($excerpt['text'][1] === $marker && preg_match($this->StrongRegex[$marker], $excerpt['text'], $matches)) { + $emphasis = 'strong'; + } elseif (preg_match($this->EmRegex[$marker], $excerpt['text'], $matches)) { + $emphasis = 'em'; + } else { + return null; + } + + return [ + 'extent' => strlen($matches[0]), + 'element' => [ + 'name' => $emphasis, + 'handler' => 'line', + 'text' => $matches[1], + ], + ]; + } + + protected function inlineEscapeSequence(array $excerpt): ?array + { + if (isset($excerpt['text'][1]) && in_array($excerpt['text'][1], $this->specialCharacters, true)) { + return [ + 'markup' => $excerpt['text'][1], + 'extent' => 2, + ]; + } + + return null; + } + + protected function inlineImage(array $excerpt): ?array + { + if (!isset($excerpt['text'][1]) || $excerpt['text'][1] !== '[') { + return null; + } + + $excerpt['text'] = substr($excerpt['text'], 1); + $Link = $this->inlineLink($excerpt); + + if ($Link === null) { + return null; + } + + $inline = [ + 'extent' => $Link['extent'] + 1, + 'element' => [ + 'name' => 'img', + 'attributes' => [ + 'src' => $Link['element']['attributes']['href'], + 'alt' => $Link['element']['text'], + ], + ], + ]; + + $inline['element']['attributes'] += $Link['element']['attributes']; + unset($inline['element']['attributes']['href']); + + return $inline; + } + + protected function inlineLink(array $excerpt): ?array + { + $element = [ + 'name' => 'a', + 'handler' => 'line', + 'nonNestables' => ['Url', 'Link'], + 'text' => null, + 'attributes' => [ + 'href' => null, + 'title' => null, + ], + ]; + + $extent = 0; + $remainder = $excerpt['text']; + + if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches)) { + $element['text'] = $matches[1]; + $extent += strlen($matches[0]); + $remainder = substr($remainder, $extent); + } else { + return null; + } + + if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*"|\'[^\']*\'))?\s*[)]/', $remainder, $matches)) { + $element['attributes']['href'] = $matches[1]; + $extent += strlen($matches[0]); + + if (isset($matches[2])) { + $element['attributes']['title'] = substr($matches[2], 1, -1); + } + } else { + if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) { + $definition = ($matches[1] ?? '') !== '' ? $matches[1] : $element['text']; + $definition = strtolower($definition); + $extent += strlen($matches[0]); + } else { + $definition = strtolower($element['text']); + } + + if (!isset($this->DefinitionData['Reference'][$definition])) { + return null; + } + + $element['attributes']['href'] = $this->DefinitionData['Reference'][$definition]['url']; + $element['attributes']['title'] = $this->DefinitionData['Reference'][$definition]['title']; + } + + return [ + 'extent' => $extent, + 'element' => $element, + ]; + } + + protected function inlineMarkup(array $excerpt): ?array + { + if ($this->markupEscaped || $this->safeMode || strpos($excerpt['text'], '>') === false) { + return null; + } + + if ($excerpt['text'][1] === '/' && preg_match('/^<\/\w[\w-]*[ ]*>/', $excerpt['text'], $matches)) { + return [ + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ]; + } + + if ($excerpt['text'][1] === '!' && preg_match('/^/', $excerpt['text'], $matches)) { + return [ + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ]; + } + + if ($excerpt['text'][1] !== ' ' && preg_match('/^<\w[\w-]*(?:[ ]*' . $this->regexHtmlAttribute . ')*[ ]*\/?>/s', $excerpt['text'], $matches)) { + return [ + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ]; + } + + return null; + } + + protected function inlineSpecialCharacter(array $excerpt): ?array + { + static $specialCharacter = ['>' => 'gt', '<' => 'lt', '"' => 'quot']; + + if ($excerpt['text'][0] === '&' && !preg_match('/^&#?\w+;/', $excerpt['text'])) { + return [ + 'markup' => '&', + 'extent' => 1, + ]; + } + + if (isset($specialCharacter[$excerpt['text'][0]])) { + return [ + 'markup' => '&' . $specialCharacter[$excerpt['text'][0]] . ';', + 'extent' => 1, + ]; + } + + return null; + } + + protected function inlineStrikethrough(array $excerpt): ?array + { + if (!isset($excerpt['text'][1])) { + return null; + } + + if ($excerpt['text'][1] === '~' && preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $excerpt['text'], $matches)) { + return [ + 'extent' => strlen($matches[0]), + 'element' => [ + 'name' => 'del', + 'text' => $matches[1], + 'handler' => 'line', + ], + ]; + } + + return null; + } + + protected function inlineUrl(array $excerpt): ?array + { + if ($this->urlsLinked !== true || !isset($excerpt['text'][2]) || $excerpt['text'][2] !== '/') { + return null; + } + + if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $excerpt['context'], $matches, PREG_OFFSET_CAPTURE)) { + return [ + 'extent' => strlen($matches[0][0]), + 'position' => $matches[0][1], + 'element' => [ + 'name' => 'a', + 'text' => $matches[0][0], + 'attributes' => [ + 'href' => $matches[0][0], + ], + ], + ]; + } + + return null; + } + + protected function inlineUrlTag(array $excerpt): array + { + if (strpos($excerpt['text'], '>') !== false && preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $excerpt['text'], $matches)) { + return [ + 'extent' => strlen($matches[0]), + 'element' => [ + 'name' => 'a', + 'text' => $matches[1], + 'attributes' => [ + 'href' => $matches[1], + ], + ], + ]; + } + + return null; + } + + protected function unmarkedText(string $haystack): string + { + if ($this->breaksEnabled) { + $haystack = (string) preg_replace('/[ ]*\n/', "
\n", $haystack); + } else { + $haystack = (string) preg_replace('/(?:[ ]{2,}|[ ]*\\\\)\n/', "
\n", $haystack); + $haystack = str_replace(" \n", "\n", $haystack); + } + + return $haystack; + } + + protected function element(array $element): string + { + if ($this->safeMode) { + $element = $this->sanitiseElement($element); + } + + $markup = '<' . $element['name']; + + if (isset($element['attributes'])) { + foreach ($element['attributes'] as $name => $value) { + if ($value === null) { + continue; + } + + $markup .= ' ' . $name . '="' . self::escape($value) . '"'; + } + } + + if (isset($element['text'])) { + $markup .= '>'; + + if (!isset($element['nonNestables'])) { + $element['nonNestables'] = []; + } + + if (isset($element['handler'])) { + $markup .= $this->{$element['handler']}($element['text'], $element['nonNestables']); + } else { + $markup .= self::escape($element['text'], true); + } + + $markup .= ''; + } else { + $markup .= ' />'; + } + + return $markup; + } + + protected function elements(array $Elements): string + { + $markup = ''; + + foreach ($Elements as $Element) { + $markup .= "\n" . $this->element($Element); + } + + return $markup . "\n"; + } + + protected function li(array $lines): string + { + $markup = $this->lines($lines); + + if (!\in_array('', $lines, true) && strpos($trimmedMarkup = trim($markup), '

') === 0) { + $markup = substr_replace(substr($trimmedMarkup, 3), '', strpos($markup, '

'), 4); + } + + return $markup; + } + + protected function sanitiseElement(array $element): array + { + static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/'; + static $safeUrlNameToAtt = [ + 'a' => 'href', + 'img' => 'src', + ]; + + if (isset($safeUrlNameToAtt[$element['name']])) { + $element = $this->filterUnsafeUrlInAttribute($element, $safeUrlNameToAtt[$element['name']]); + } + + if (!empty($element['attributes'])) { + foreach ($element['attributes'] as $att => $val) { + if (!preg_match($goodAttribute, $att)) { // filter out badly parsed attribute + unset($element['attributes'][$att]); + } elseif (self::striAtStart($att, 'on')) { // dump onevent attribute + unset($element['attributes'][$att]); + } + } + } + + return $element; + } + + protected function filterUnsafeUrlInAttribute(array $element, $attribute): array + { + foreach ($this->safeLinksWhitelist as $scheme) { + if (self::striAtStart($element['attributes'][$attribute], $scheme)) { + return $element; + } + } + + $element['attributes'][$attribute] = str_replace(':', '%3A', $element['attributes'][$attribute]); + + return $element; + } - # compile the unmarked text - $InlineText = $this->inlineText($unmarkedText); - $Elements[] = $InlineText['element']; - - # compile the inline - $Elements[] = $this->extractElement($Inline); - - # remove the examined text - $text = substr($text, $Inline['position'] + $Inline['extent']); - - continue 2; - } - - # the marker does not belong to an inline - - $unmarkedText = substr($text, 0, $markerPosition + 1); - - $InlineText = $this->inlineText($unmarkedText); - $Elements[] = $InlineText['element']; - - $text = substr($text, $markerPosition + 1); - } - - $InlineText = $this->inlineText($text); - $Elements[] = $InlineText['element']; - - foreach ($Elements as &$Element) - { - if ( ! isset($Element['autobreak'])) - { - $Element['autobreak'] = false; - } - } - - return $Elements; - } - - # - # ~ - # - - protected function inlineText($text) - { - $Inline = array( - 'extent' => strlen($text), - 'element' => array(), - ); - - $Inline['element']['elements'] = self::pregReplaceElements( - $this->breaksEnabled ? '/[ ]*+\n/' : '/(?:[ ]*+\\\\|[ ]{2,}+)\n/', - array( - array('name' => 'br'), - array('text' => "\n"), - ), - $text - ); - - return $Inline; - } - - protected function inlineCode($Excerpt) - { - $marker = $Excerpt['text'][0]; - - if (preg_match('/^(['.$marker.']++)[ ]*+(.+?)[ ]*+(? strlen($matches[0]), - 'element' => array( - 'name' => 'code', - 'text' => $text, - ), - ); - } - } - - protected function inlineEmailTag($Excerpt) - { - $hostnameLabel = '[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?'; - - $commonMarkEmail = '[a-zA-Z0-9.!#$%&\'*+\/=?^_`{|}~-]++@' - . $hostnameLabel . '(?:\.' . $hostnameLabel . ')*'; - - if (strpos($Excerpt['text'], '>') !== false - and preg_match("/^<((mailto:)?$commonMarkEmail)>/i", $Excerpt['text'], $matches) - ){ - $url = $matches[1]; - - if ( ! isset($matches[2])) - { - $url = "mailto:$url"; - } - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'a', - 'text' => $matches[1], - 'attributes' => array( - 'href' => $url, - ), - ), - ); - } - } - - protected function inlineEmphasis($Excerpt) - { - if ( ! isset($Excerpt['text'][1])) - { - return; - } - - $marker = $Excerpt['text'][0]; - - if ($Excerpt['text'][1] === $marker and preg_match($this->StrongRegex[$marker], $Excerpt['text'], $matches)) - { - $emphasis = 'strong'; - } - elseif (preg_match($this->EmRegex[$marker], $Excerpt['text'], $matches)) - { - $emphasis = 'em'; - } - else - { - return; - } - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => $emphasis, - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $matches[1], - 'destination' => 'elements', - ) - ), - ); - } - - protected function inlineEscapeSequence($Excerpt) - { - if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters)) - { - return array( - 'element' => array('rawHtml' => $Excerpt['text'][1]), - 'extent' => 2, - ); - } - } - - protected function inlineImage($Excerpt) - { - if ( ! isset($Excerpt['text'][1]) or $Excerpt['text'][1] !== '[') - { - return; - } - - $Excerpt['text']= substr($Excerpt['text'], 1); - - $Link = $this->inlineLink($Excerpt); - - if ($Link === null) - { - return; - } - - $Inline = array( - 'extent' => $Link['extent'] + 1, - 'element' => array( - 'name' => 'img', - 'attributes' => array( - 'src' => $Link['element']['attributes']['href'], - 'alt' => $Link['element']['handler']['argument'], - ), - 'autobreak' => true, - ), - ); - - $Inline['element']['attributes'] += $Link['element']['attributes']; - - unset($Inline['element']['attributes']['href']); - - return $Inline; - } - - protected function inlineLink($Excerpt) - { - $Element = array( - 'name' => 'a', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => null, - 'destination' => 'elements', - ), - 'nonNestables' => array('Url', 'Link'), - 'attributes' => array( - 'href' => null, - 'title' => null, - ), - ); - - $extent = 0; - - $remainder = $Excerpt['text']; - - if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches)) - { - $Element['handler']['argument'] = $matches[1]; - - $extent += strlen($matches[0]); - - $remainder = substr($remainder, $extent); - } - else - { - return; - } - - if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*+"|\'[^\']*+\'))?\s*+[)]/', $remainder, $matches)) - { - $Element['attributes']['href'] = $matches[1]; - - if (isset($matches[2])) - { - $Element['attributes']['title'] = substr($matches[2], 1, - 1); - } - - $extent += strlen($matches[0]); - } - else - { - if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) - { - $definition = strlen($matches[1]) ? $matches[1] : $Element['handler']['argument']; - $definition = strtolower($definition); - - $extent += strlen($matches[0]); - } - else - { - $definition = strtolower($Element['handler']['argument']); - } - - if ( ! isset($this->DefinitionData['Reference'][$definition])) - { - return; - } - - $Definition = $this->DefinitionData['Reference'][$definition]; - - $Element['attributes']['href'] = $Definition['url']; - $Element['attributes']['title'] = $Definition['title']; - } - - return array( - 'extent' => $extent, - 'element' => $Element, - ); - } - - protected function inlineMarkup($Excerpt) - { - if ($this->markupEscaped or $this->safeMode or strpos($Excerpt['text'], '>') === false) - { - return; - } - - if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*+[ ]*+>/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - - if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - - if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - } - - protected function inlineSpecialCharacter($Excerpt) - { - if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false - and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches) - ) { - return array( - 'element' => array('rawHtml' => '&' . $matches[1] . ';'), - 'extent' => strlen($matches[0]), - ); - } - - return; - } - - protected function inlineStrikethrough($Excerpt) - { - if ( ! isset($Excerpt['text'][1])) - { - return; - } - - if ($Excerpt['text'][1] === '~' and preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $Excerpt['text'], $matches)) - { - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'del', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $matches[1], - 'destination' => 'elements', - ) - ), - ); - } - } - - protected function inlineUrl($Excerpt) - { - if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/') - { - return; - } - - if (strpos($Excerpt['context'], 'http') !== false - and preg_match('/\bhttps?+:[\/]{2}[^\s<]+\b\/*+/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE) - ) { - $url = $matches[0][0]; - - $Inline = array( - 'extent' => strlen($matches[0][0]), - 'position' => $matches[0][1], - 'element' => array( - 'name' => 'a', - 'text' => $url, - 'attributes' => array( - 'href' => $url, - ), - ), - ); - - return $Inline; - } - } - - protected function inlineUrlTag($Excerpt) - { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches)) - { - $url = $matches[1]; - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'a', - 'text' => $url, - 'attributes' => array( - 'href' => $url, - ), - ), - ); - } - } - - # ~ - - protected function unmarkedText($text) - { - $Inline = $this->inlineText($text); - return $this->element($Inline['element']); - } - - # - # Handlers - # - - protected function handle(array $Element) - { - if (isset($Element['handler'])) - { - if (!isset($Element['nonNestables'])) - { - $Element['nonNestables'] = array(); - } - - if (is_string($Element['handler'])) - { - $function = $Element['handler']; - $argument = $Element['text']; - unset($Element['text']); - $destination = 'rawHtml'; - } - else - { - $function = $Element['handler']['function']; - $argument = $Element['handler']['argument']; - $destination = $Element['handler']['destination']; - } - - $Element[$destination] = $this->{$function}($argument, $Element['nonNestables']); - - if ($destination === 'handler') - { - $Element = $this->handle($Element); - } - - unset($Element['handler']); - } - - return $Element; - } - - protected function handleElementRecursive(array $Element) - { - return $this->elementApplyRecursive(array($this, 'handle'), $Element); - } - - protected function handleElementsRecursive(array $Elements) - { - return $this->elementsApplyRecursive(array($this, 'handle'), $Elements); - } - - protected function elementApplyRecursive($closure, array $Element) - { - $Element = call_user_func($closure, $Element); - - if (isset($Element['elements'])) - { - $Element['elements'] = $this->elementsApplyRecursive($closure, $Element['elements']); - } - elseif (isset($Element['element'])) - { - $Element['element'] = $this->elementApplyRecursive($closure, $Element['element']); - } - - return $Element; - } - - protected function elementApplyRecursiveDepthFirst($closure, array $Element) - { - if (isset($Element['elements'])) - { - $Element['elements'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['elements']); - } - elseif (isset($Element['element'])) - { - $Element['element'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['element']); - } - - $Element = call_user_func($closure, $Element); - - return $Element; - } - - protected function elementsApplyRecursive($closure, array $Elements) - { - foreach ($Elements as &$Element) - { - $Element = $this->elementApplyRecursive($closure, $Element); - } - - return $Elements; - } - - protected function elementsApplyRecursiveDepthFirst($closure, array $Elements) - { - foreach ($Elements as &$Element) - { - $Element = $this->elementApplyRecursiveDepthFirst($closure, $Element); - } - - return $Elements; - } - - protected function element(array $Element) - { - if ($this->safeMode) - { - $Element = $this->sanitiseElement($Element); - } - - # identity map if element has no handler - $Element = $this->handle($Element); - - $hasName = isset($Element['name']); - - $markup = ''; - - if ($hasName) - { - $markup .= '<' . $Element['name']; - - if (isset($Element['attributes'])) - { - foreach ($Element['attributes'] as $name => $value) - { - if ($value === null) - { - continue; - } - - $markup .= " $name=\"".self::escape($value).'"'; - } - } - } - - $permitRawHtml = false; - - if (isset($Element['text'])) - { - $text = $Element['text']; - } - // very strongly consider an alternative if you're writing an - // extension - elseif (isset($Element['rawHtml'])) - { - $text = $Element['rawHtml']; - - $allowRawHtmlInSafeMode = isset($Element['allowRawHtmlInSafeMode']) && $Element['allowRawHtmlInSafeMode']; - $permitRawHtml = !$this->safeMode || $allowRawHtmlInSafeMode; - } - - $hasContent = isset($text) || isset($Element['element']) || isset($Element['elements']); - - if ($hasContent) - { - $markup .= $hasName ? '>' : ''; - - if (isset($Element['elements'])) - { - $markup .= $this->elements($Element['elements']); - } - elseif (isset($Element['element'])) - { - $markup .= $this->element($Element['element']); - } - else - { - if (!$permitRawHtml) - { - $markup .= self::escape($text, true); - } - else - { - $markup .= $text; - } - } - - $markup .= $hasName ? '' : ''; - } - elseif ($hasName) - { - $markup .= ' />'; - } - - return $markup; - } - - protected function elements(array $Elements) - { - $markup = ''; - - $autoBreak = true; - - foreach ($Elements as $Element) - { - if (empty($Element)) - { - continue; - } - - $autoBreakNext = (isset($Element['autobreak']) - ? $Element['autobreak'] : isset($Element['name']) - ); - // (autobreak === false) covers both sides of an element - $autoBreak = !$autoBreak ? $autoBreak : $autoBreakNext; - - $markup .= ($autoBreak ? "\n" : '') . $this->element($Element); - $autoBreak = $autoBreakNext; - } - - $markup .= $autoBreak ? "\n" : ''; - - return $markup; - } - - # ~ - - protected function li($lines) - { - $Elements = $this->linesElements($lines); - - if ( ! in_array('', $lines) - and isset($Elements[0]) and isset($Elements[0]['name']) - and $Elements[0]['name'] === 'p' - ) { - unset($Elements[0]['name']); - } - - return $Elements; - } - - # - # AST Convenience - # - - /** - * Replace occurrences $regexp with $Elements in $text. Return an array of - * elements representing the replacement. - */ - protected static function pregReplaceElements($regexp, $Elements, $text) - { - $newElements = array(); - - while (preg_match($regexp, $text, $matches, PREG_OFFSET_CAPTURE)) - { - $offset = $matches[0][1]; - $before = substr($text, 0, $offset); - $after = substr($text, $offset + strlen($matches[0][0])); - - $newElements[] = array('text' => $before); - - foreach ($Elements as $Element) - { - $newElements[] = $Element; - } - - $text = $after; - } - - $newElements[] = array('text' => $text); - - return $newElements; - } - - # - # Deprecated Methods - # - - function parse($text) - { - $markup = $this->text($text); - - return $markup; - } - - protected function sanitiseElement(array $Element) - { - static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/'; - static $safeUrlNameToAtt = array( - 'a' => 'href', - 'img' => 'src', - ); - - if ( ! isset($Element['name'])) - { - unset($Element['attributes']); - return $Element; - } - - if (isset($safeUrlNameToAtt[$Element['name']])) - { - $Element = $this->filterUnsafeUrlInAttribute($Element, $safeUrlNameToAtt[$Element['name']]); - } - - if ( ! empty($Element['attributes'])) - { - foreach ($Element['attributes'] as $att => $val) - { - # filter out badly parsed attribute - if ( ! preg_match($goodAttribute, $att)) - { - unset($Element['attributes'][$att]); - } - # dump onevent attribute - elseif (self::striAtStart($att, 'on')) - { - unset($Element['attributes'][$att]); - } - } - } - - return $Element; - } - - protected function filterUnsafeUrlInAttribute(array $Element, $attribute) - { - foreach ($this->safeLinksWhitelist as $scheme) - { - if (self::striAtStart($Element['attributes'][$attribute], $scheme)) - { - return $Element; - } - } - - $Element['attributes'][$attribute] = str_replace(':', '%3A', $Element['attributes'][$attribute]); - - return $Element; - } - - # - # Static Methods - # - - protected static function escape($text, $allowQuotes = false) - { - return htmlspecialchars($text, $allowQuotes ? ENT_NOQUOTES : ENT_QUOTES, 'UTF-8'); - } - - protected static function striAtStart($string, $needle) - { - $len = strlen($needle); - - if ($len > strlen($string)) - { - return false; - } - else - { - return strtolower(substr($string, 0, $len)) === strtolower($needle); - } - } - - static function instance($name = 'default') - { - if (isset(self::$instances[$name])) - { - return self::$instances[$name]; - } - - $instance = new static(); - - self::$instances[$name] = $instance; - - return $instance; - } - - private static $instances = array(); - - # - # Fields - # - - protected $DefinitionData; - - # - # Read-Only - - protected $specialCharacters = array( - '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~' - ); - - protected $StrongRegex = array( - '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s', - '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us', - ); - - protected $EmRegex = array( - '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', - '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', - ); - - protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*+(?:\s*+=\s*+(?:[^"\'=<>`\s]+|"[^"]*+"|\'[^\']*+\'))?+'; - - protected $voidElements = array( - 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', - ); - - protected $textLevelElements = array( - 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', - 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', - 'i', 'rp', 'del', 'code', 'strike', 'marquee', - 'q', 'rt', 'ins', 'font', 'strong', - 's', 'tt', 'kbd', 'mark', - 'u', 'xm', 'sub', 'nobr', - 'sup', 'ruby', - 'var', 'span', - 'wbr', 'time', - ); }