From e3552314b5e8ea6ecf615a16e55d0a8fc0ee24da Mon Sep 17 00:00:00 2001 From: Gifford Nowland Date: Wed, 4 Nov 2020 08:18:45 -0500 Subject: [PATCH] add slug support https://github.com/erusev/parsedown/pull/765 --- Parsedown.php | 1144 +++++++++++++++++++++++++++++++------------------ 1 file changed, 717 insertions(+), 427 deletions(-) diff --git a/Parsedown.php b/Parsedown.php index 1b9d6d5bc..12d94751f 100644 --- a/Parsedown.php +++ b/Parsedown.php @@ -17,11 +17,24 @@ class Parsedown { # ~ - const version = '1.7.4'; + const version = '1.8.0-beta-7'; # ~ function text($text) + { + $Elements = $this->textElements($text); + + # convert to markup + $markup = $this->elements($Elements); + + # trim line breaks + $markup = trim($markup, "\n"); + + return $markup; + } + + protected function textElements($text) { # make sure no definitions are set $this->DefinitionData = array(); @@ -36,12 +49,7 @@ function text($text) $lines = explode("\n", $text); # iterate through lines to identify blocks - $markup = $this->lines($lines); - - # trim line breaks - $markup = trim($markup, "\n"); - - return $markup; + return $this->linesElements($lines); } # @@ -84,12 +92,22 @@ function setSafeMode($safeMode) protected $safeMode; + function setStrictMode($strictMode) + { + $this->strictMode = (bool) $strictMode; + + return $this; + } + + protected $strictMode; + protected $safeLinksWhitelist = array( 'http://', 'https://', 'ftp://', 'ftps://', 'mailto:', + 'tel:', 'data:image/png;base64,', 'data:image/gif;base64,', 'data:image/jpeg;base64,', @@ -143,6 +161,12 @@ function setSafeMode($safeMode) protected function lines(array $lines) { + return $this->elements($this->linesElements($lines)); + } + + protected function linesElements(array $lines) + { + $Elements = array(); $CurrentBlock = null; foreach ($lines as $line) @@ -151,35 +175,25 @@ protected function lines(array $lines) { if (isset($CurrentBlock)) { - $CurrentBlock['interrupted'] = true; + $CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted']) + ? $CurrentBlock['interrupted'] + 1 : 1 + ); } continue; } - if (strpos($line, "\t") !== false) + while (($beforeTab = strstr($line, "\t", true)) !== false) { - $parts = explode("\t", $line); - - $line = $parts[0]; - - unset($parts[0]); + $shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4; - foreach ($parts as $part) - { - $shortage = 4 - mb_strlen($line, 'utf-8') % 4; - - $line .= str_repeat(' ', $shortage); - $line .= $part; - } + $line = $beforeTab + . str_repeat(' ', $shortage) + . substr($line, strlen($beforeTab) + 1) + ; } - $indent = 0; - - while (isset($line[$indent]) and $line[$indent] === ' ') - { - $indent ++; - } + $indent = strspn($line, ' '); $text = $indent > 0 ? substr($line, $indent) : $line; @@ -191,7 +205,8 @@ protected function lines(array $lines) if (isset($CurrentBlock['continuable'])) { - $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Continue'; + $Block = $this->$methodName($Line, $CurrentBlock); if (isset($Block)) { @@ -203,7 +218,8 @@ protected function lines(array $lines) { if ($this->isBlockCompletable($CurrentBlock['type'])) { - $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; + $CurrentBlock = $this->$methodName($CurrentBlock); } } } @@ -229,7 +245,7 @@ protected function lines(array $lines) foreach ($blockTypes as $blockType) { - $Block = $this->{'block'.$blockType}($Line, $CurrentBlock); + $Block = $this->{"block$blockType"}($Line, $CurrentBlock); if (isset($Block)) { @@ -237,7 +253,10 @@ protected function lines(array $lines) if ( ! isset($Block['identified'])) { - $Blocks []= $CurrentBlock; + if (isset($CurrentBlock)) + { + $Elements[] = $this->extractElement($CurrentBlock); + } $Block['identified'] = true; } @@ -255,13 +274,21 @@ protected function lines(array $lines) # ~ - if (isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted'])) + if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph') { - $CurrentBlock['element']['text'] .= "\n".$text; + $Block = $this->paragraphContinue($Line, $CurrentBlock); + } + + if (isset($Block)) + { + $CurrentBlock = $Block; } else { - $Blocks []= $CurrentBlock; + if (isset($CurrentBlock)) + { + $Elements[] = $this->extractElement($CurrentBlock); + } $CurrentBlock = $this->paragraph($Line); @@ -273,45 +300,47 @@ protected function lines(array $lines) if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type'])) { - $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; + $CurrentBlock = $this->$methodName($CurrentBlock); } # ~ - $Blocks []= $CurrentBlock; - - unset($Blocks[0]); + if (isset($CurrentBlock)) + { + $Elements[] = $this->extractElement($CurrentBlock); + } # ~ - $markup = ''; + return $Elements; + } - foreach ($Blocks as $Block) + protected function extractElement(array $Component) + { + if ( ! isset($Component['element'])) { - if (isset($Block['hidden'])) + if (isset($Component['markup'])) { - continue; + $Component['element'] = array('rawHtml' => $Component['markup']); + } + elseif (isset($Component['hidden'])) + { + $Component['element'] = array(); } - - $markup .= "\n"; - $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']); } - $markup .= "\n"; - - # ~ - - return $markup; + return $Component['element']; } protected function isBlockContinuable($Type) { - return method_exists($this, 'block'.$Type.'Continue'); + return method_exists($this, 'block' . $Type . 'Continue'); } protected function isBlockCompletable($Type) { - return method_exists($this, 'block'.$Type.'Complete'); + return method_exists($this, 'block' . $Type . 'Complete'); } # @@ -319,7 +348,7 @@ protected function isBlockCompletable($Type) protected function blockCode($Line, $Block = null) { - if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted'])) + if (isset($Block) and $Block['type'] === 'Paragraph' and ! isset($Block['interrupted'])) { return; } @@ -331,8 +360,7 @@ protected function blockCode($Line, $Block = null) $Block = array( 'element' => array( 'name' => 'pre', - 'handler' => 'element', - 'text' => array( + 'element' => array( 'name' => 'code', 'text' => $text, ), @@ -349,16 +377,16 @@ protected function blockCodeContinue($Line, $Block) { if (isset($Block['interrupted'])) { - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); unset($Block['interrupted']); } - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= "\n"; $text = substr($Line['body'], 4); - $Block['element']['text']['text'] .= $text; + $Block['element']['element']['text'] .= $text; return $Block; } @@ -366,10 +394,6 @@ protected function blockCodeContinue($Line, $Block) protected function blockCodeComplete($Block) { - $text = $Block['element']['text']['text']; - - $Block['element']['text']['text'] = $text; - return $Block; } @@ -383,13 +407,16 @@ protected function blockComment($Line) return; } - if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!') + if (strpos($Line['text'], '$/', $Line['text'])) + if (strpos($Line['text'], '-->') !== false) { $Block['closed'] = true; } @@ -405,9 +432,9 @@ protected function blockCommentContinue($Line, array $Block) return; } - $Block['markup'] .= "\n" . $Line['body']; + $Block['element']['rawHtml'] .= "\n" . $Line['body']; - if (preg_match('/-->$/', $Line['text'])) + if (strpos($Line['text'], '-->') !== false) { $Block['closed'] = true; } @@ -420,47 +447,56 @@ protected function blockCommentContinue($Line, array $Block) protected function blockFencedCode($Line) { - if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([^`]+)?[ ]*$/', $Line['text'], $matches)) + $marker = $Line['text'][0]; + + $openerLength = strspn($Line['text'], $marker); + + if ($openerLength < 3) { - $Element = array( - 'name' => 'code', - 'text' => '', - ); + return; + } - if (isset($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'] = array( - 'class' => $class, - ); - } + $infostring = trim(substr($Line['text'], $openerLength), "\t "); - $Block = array( - 'char' => $Line['text'][0], - 'element' => array( - 'name' => 'pre', - 'handler' => 'element', - 'text' => $Element, - ), - ); + if (strpos($infostring, '`') !== false) + { + return; + } - return $Block; + $Element = array( + 'name' => 'code', + 'text' => '', + ); + + if ($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, $Block) @@ -472,31 +508,28 @@ protected function blockFencedCodeContinue($Line, $Block) if (isset($Block['interrupted'])) { - $Block['element']['text']['text'] .= "\n"; + $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); unset($Block['interrupted']); } - if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text'])) - { - $Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1); + 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; } - $Block['element']['text']['text'] .= "\n".$Line['body']; + $Block['element']['element']['text'] .= "\n" . $Line['body']; return $Block; } protected function blockFencedCodeComplete($Block) { - $text = $Block['element']['text']['text']; - - $Block['element']['text']['text'] = $text; - return $Block; } @@ -505,71 +538,111 @@ protected function blockFencedCodeComplete($Block) protected function blockHeader($Line) { - if (isset($Line['text'][1])) + $level = strspn($Line['text'], '#'); + + if ($level > 6) { - $level = 1; + return; + } - while (isset($Line['text'][$level]) and $Line['text'][$level] === '#') - { - $level ++; - } + $text = trim($Line['text'], '#'); - if ($level > 6) - { - return; - } + if ($this->strictMode and isset($text[0]) and $text[0] !== ' ') + { + return; + } - $text = trim($Line['text'], '# '); + $text = trim($text, ' '); + $link = preg_replace('/[^\p{L}\p{N}\p{M}-]+/u', '', mb_strtolower(mb_ereg_replace(' ','-',$text))); + $attr = array(); + if (!empty($link)) { + $attr = array( + 'id' => $link, + ); + } - $Block = array( - 'element' => array( - 'name' => 'h' . min(6, $level), - 'text' => $text, - 'handler' => 'line', + $Block = array( + 'element' => array( + 'name' => 'h' . $level, + 'attributes' => $attr, + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $text, + 'destination' => 'elements', ), - ); + ), + ); - return $Block; - } + return $Block; } # # List - protected function blockList($Line) + protected function blockList($Line, array $CurrentBlock = null) { - list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]'); + list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]'); - if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches)) + if (preg_match('/^('.$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, - 'handler' => 'elements', + 'elements' => array(), ), ); + $Block['data']['markerTypeRegex'] = preg_quote($Block['data']['markerType'], '/'); - if($name === 'ol') + if ($name === 'ol') { - $listStart = stristr($matches[0], '.', true); + $listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0'; - if($listStart !== '1') + 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' => 'li', - 'text' => array( - $matches[2], - ), + 'handler' => array( + 'function' => 'li', + 'argument' => !empty($matches[3]) ? array($matches[3]) : array(), + 'destination' => 'elements' + ) ); - $Block['element']['text'] []= & $Block['li']; + $Block['element']['elements'] []= & $Block['li']; return $Block; } @@ -577,11 +650,27 @@ protected function blockList($Line) protected function blockListContinue($Line, array $Block) { - if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches)) + if (isset($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']['text'] []= ''; + $Block['li']['handler']['argument'] []= ''; $Block['loose'] = true; @@ -592,42 +681,54 @@ protected function blockListContinue($Line, array $Block) $text = isset($matches[1]) ? $matches[1] : ''; + $Block['indent'] = $Line['indent']; + $Block['li'] = array( 'name' => 'li', - 'handler' => 'li', - 'text' => array( - $text, - ), + 'handler' => array( + 'function' => 'li', + 'argument' => array($text), + 'destination' => 'elements' + ) ); - $Block['element']['text'] []= & $Block['li']; + $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 $Block; } - if ( ! isset($Block['interrupted'])) + if ($Line['indent'] >= $requiredIndent) { - $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); + if (isset($Block['interrupted'])) + { + $Block['li']['handler']['argument'] []= ''; - $Block['li']['text'] []= $text; + $Block['loose'] = true; + + unset($Block['interrupted']); + } + + $text = substr($Line['body'], $requiredIndent); + + $Block['li']['handler']['argument'] []= $text; return $Block; } - if ($Line['indent'] > 0) + if ( ! isset($Block['interrupted'])) { - $Block['li']['text'] []= ''; + $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']); - $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); - - $Block['li']['text'] []= $text; - - unset($Block['interrupted']); + $Block['li']['handler']['argument'] []= $text; return $Block; } @@ -637,11 +738,11 @@ protected function blockListComplete(array $Block) { if (isset($Block['loose'])) { - foreach ($Block['element']['text'] as &$li) + foreach ($Block['element']['elements'] as &$li) { - if (end($li['text']) !== '') + if (end($li['handler']['argument']) !== '') { - $li['text'] []= ''; + $li['handler']['argument'] []= ''; } } } @@ -654,13 +755,16 @@ protected function blockListComplete(array $Block) protected function blockQuote($Line) { - if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) { $Block = array( 'element' => array( 'name' => 'blockquote', - 'handler' => 'lines', - 'text' => (array) $matches[1], + 'handler' => array( + 'function' => 'linesElements', + 'argument' => (array) $matches[1], + 'destination' => 'elements', + ) ), ); @@ -670,23 +774,21 @@ protected function blockQuote($Line) protected function blockQuoteContinue($Line, array $Block) { - if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + if (isset($Block['interrupted'])) { - if (isset($Block['interrupted'])) - { - $Block['element']['text'] []= ''; - - unset($Block['interrupted']); - } + return; + } - $Block['element']['text'] []= $matches[1]; + if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) + { + $Block['element']['handler']['argument'] []= $matches[1]; return $Block; } if ( ! isset($Block['interrupted'])) { - $Block['element']['text'] []= $Line['text']; + $Block['element']['handler']['argument'] []= $Line['text']; return $Block; } @@ -697,11 +799,13 @@ protected function blockQuoteContinue($Line, array $Block) protected function blockRule($Line) { - if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text'])) + $marker = $Line['text'][0]; + + if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '') { $Block = array( 'element' => array( - 'name' => 'hr' + 'name' => 'hr', ), ); @@ -714,12 +818,12 @@ protected function blockRule($Line) protected function blockSetextHeader($Line, array $Block = null) { - if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) { return; } - if (chop($Line['text'], $Line['text'][0]) === '') + if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '') { $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; @@ -737,7 +841,7 @@ protected function blockMarkup($Line) return; } - if (preg_match('/^<(\w[\w-]*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches)) + if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches)) { $element = strtolower($matches[1]); @@ -748,72 +852,24 @@ protected function blockMarkup($Line) $Block = array( 'name' => $matches[1], - 'depth' => 0, - 'markup' => $Line['text'], + 'element' => array( + 'rawHtml' => $Line['text'], + 'autobreak' => true, + ), ); - $length = strlen($matches[0]); - - $remainder = substr($Line['text'], $length); - - if (trim($remainder) === '') - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - $Block['closed'] = true; - - $Block['void'] = true; - } - } - else - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - return; - } - - if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder)) - { - $Block['closed'] = true; - } - } - return $Block; } } protected function blockMarkupContinue($Line, array $Block) { - if (isset($Block['closed'])) + if (isset($Block['closed']) or isset($Block['interrupted'])) { return; } - if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open - { - $Block['depth'] ++; - } - - if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close - { - if ($Block['depth'] > 0) - { - $Block['depth'] --; - } - else - { - $Block['closed'] = true; - } - } - - if (isset($Block['interrupted'])) - { - $Block['markup'] .= "\n"; - - unset($Block['interrupted']); - } - - $Block['markup'] .= "\n".$Line['body']; + $Block['element']['rawHtml'] .= "\n" . $Line['body']; return $Block; } @@ -823,24 +879,20 @@ protected function blockMarkupContinue($Line, array $Block) protected function blockReference($Line) { - if (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches)) - { + if (strpos($Line['text'], ']') !== false + and preg_match('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches) + ) { $id = strtolower($matches[1]); $Data = array( 'url' => $matches[2], - 'title' => null, + 'title' => isset($matches[3]) ? $matches[3] : null, ); - if (isset($matches[3])) - { - $Data['title'] = $matches[3]; - } - $this->DefinitionData['Reference'][$id] = $Data; $Block = array( - 'hidden' => true, + 'element' => array(), ); return $Block; @@ -852,109 +904,125 @@ protected function blockReference($Line) protected function blockTable($Line, array $Block = null) { - if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) { return; } - if (strpos($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '') + 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'], ' -:|') !== '') { - $alignments = array(); + return; + } - $divider = $Line['text']; + $alignments = array(); - $divider = trim($divider); - $divider = trim($divider, '|'); + $divider = $Line['text']; - $dividerCells = explode('|', $divider); + $divider = trim($divider); + $divider = trim($divider, '|'); - foreach ($dividerCells as $dividerCell) - { - $dividerCell = trim($dividerCell); + $dividerCells = explode('|', $divider); - if ($dividerCell === '') - { - continue; - } + foreach ($dividerCells as $dividerCell) + { + $dividerCell = trim($dividerCell); - $alignment = null; + if ($dividerCell === '') + { + return; + } - if ($dividerCell[0] === ':') - { - $alignment = 'left'; - } + $alignment = null; - if (substr($dividerCell, - 1) === ':') - { - $alignment = $alignment === 'left' ? 'center' : 'right'; - } + if ($dividerCell[0] === ':') + { + $alignment = 'left'; + } - $alignments []= $alignment; + if (substr($dividerCell, - 1) === ':') + { + $alignment = $alignment === 'left' ? 'center' : 'right'; } - # ~ + $alignments []= $alignment; + } - $HeaderElements = array(); + # ~ - $header = $Block['element']['text']; + $HeaderElements = array(); - $header = trim($header); - $header = trim($header, '|'); + $header = $Block['element']['handler']['argument']; - $headerCells = explode('|', $header); + $header = trim($header); + $header = trim($header, '|'); - foreach ($headerCells as $index => $headerCell) - { - $headerCell = trim($headerCell); + $headerCells = explode('|', $header); - $HeaderElement = array( - 'name' => 'th', - 'text' => $headerCell, - 'handler' => 'line', - ); + if (count($headerCells) !== count($alignments)) + { + return; + } - if (isset($alignments[$index])) - { - $alignment = $alignments[$index]; + foreach ($headerCells as $index => $headerCell) + { + $headerCell = trim($headerCell); - $HeaderElement['attributes'] = array( - 'style' => 'text-align: '.$alignment.';', - ); - } + $HeaderElement = array( + 'name' => 'th', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $headerCell, + 'destination' => 'elements', + ) + ); + + if (isset($alignments[$index])) + { + $alignment = $alignments[$index]; - $HeaderElements []= $HeaderElement; + $HeaderElement['attributes'] = array( + 'style' => "text-align: $alignment;", + ); } - # ~ + $HeaderElements []= $HeaderElement; + } - $Block = array( - 'alignments' => $alignments, - 'identified' => true, - 'element' => array( - 'name' => 'table', - 'handler' => 'elements', - ), - ); + # ~ - $Block['element']['text'] []= array( - 'name' => 'thead', - 'handler' => 'elements', - ); + $Block = array( + 'alignments' => $alignments, + 'identified' => true, + 'element' => array( + 'name' => 'table', + 'elements' => array(), + ), + ); - $Block['element']['text'] []= array( - 'name' => 'tbody', - 'handler' => 'elements', - 'text' => array(), - ); + $Block['element']['elements'] []= array( + 'name' => 'thead', + ); - $Block['element']['text'][0]['text'] []= array( - 'name' => 'tr', - 'handler' => 'elements', - 'text' => $HeaderElements, - ); + $Block['element']['elements'] []= array( + 'name' => 'tbody', + 'elements' => array(), + ); - return $Block; - } + $Block['element']['elements'][0]['elements'] []= array( + 'name' => 'tr', + 'elements' => $HeaderElements, + ); + + return $Block; } protected function blockTableContinue($Line, array $Block) @@ -964,7 +1032,7 @@ protected function blockTableContinue($Line, array $Block) return; } - if ($Line['text'][0] === '|' or strpos($Line['text'], '|')) + if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|')) { $Elements = array(); @@ -973,22 +1041,27 @@ protected function blockTableContinue($Line, array $Block) $row = trim($row); $row = trim($row, '|'); - preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches); - foreach ($matches[0] as $index => $cell) + $cells = array_slice($matches[0], 0, count($Block['alignments'])); + + foreach ($cells as $index => $cell) { $cell = trim($cell); $Element = array( 'name' => 'td', - 'handler' => 'line', - 'text' => $cell, + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $cell, + 'destination' => 'elements', + ) ); if (isset($Block['alignments'][$index])) { $Element['attributes'] = array( - 'style' => 'text-align: '.$Block['alignments'][$index].';', + 'style' => 'text-align: ' . $Block['alignments'][$index] . ';', ); } @@ -997,11 +1070,10 @@ protected function blockTableContinue($Line, array $Block) $Element = array( 'name' => 'tr', - 'handler' => 'elements', - 'text' => $Elements, + 'elements' => $Elements, ); - $Block['element']['text'][1]['text'] []= $Element; + $Block['element']['elements'][1]['elements'] []= $Element; return $Block; } @@ -1013,13 +1085,27 @@ protected function blockTableContinue($Line, array $Block) protected function paragraph($Line) { - $Block = array( + return array( + 'type' => 'Paragraph', 'element' => array( 'name' => 'p', - 'text' => $Line['text'], - 'handler' => 'line', + '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 $Block; } @@ -1029,13 +1115,11 @@ protected function paragraph($Line) # protected $InlineTypes = array( - '"' => array('SpecialCharacter'), '!' => array('Image'), '&' => array('SpecialCharacter'), '*' => array('Emphasis'), ':' => array('Url'), - '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'), - '>' => array('SpecialCharacter'), + '<' => array('UrlTag', 'EmailTag', 'Markup'), '[' => array('Link'), '_' => array('Emphasis'), '`' => array('Code'), @@ -1045,15 +1129,28 @@ protected function paragraph($Line) # ~ - protected $inlineMarkerList = '!"*_&[:<>`~\\'; + protected $inlineMarkerList = '!*_&[:<`~\\'; # # ~ # - public function line($text, $nonNestables=array()) + public function line($text, $nonNestables = array()) { - $markup = ''; + return $this->elements($this->lineElements($text, $nonNestables)); + } + + protected function lineElements($text, $nonNestables = array()) + { + # standardize line breaks + $text = str_replace(array("\r\n", "\r"), "\n", $text); + + $Elements = array(); + + $nonNestables = (empty($nonNestables) + ? array() + : array_combine($nonNestables, $nonNestables) + ); # $excerpt is based on the first occurrence of a marker @@ -1061,7 +1158,7 @@ public function line($text, $nonNestables=array()) { $marker = $excerpt[0]; - $markerPosition = strpos($text, $marker); + $markerPosition = strlen($text) - strlen($excerpt); $Excerpt = array('text' => $excerpt, 'context' => $text); @@ -1069,12 +1166,12 @@ public function line($text, $nonNestables=array()) { # check to see if the current inline type is nestable in the current context - if ( ! empty($nonNestables) and in_array($inlineType, $nonNestables)) + if (isset($nonNestables[$inlineType])) { continue; } - $Inline = $this->{'inline'.$inlineType}($Excerpt); + $Inline = $this->{"inline$inlineType"}($Excerpt); if ( ! isset($Inline)) { @@ -1097,19 +1194,21 @@ public function line($text, $nonNestables=array()) # cause the new element to 'inherit' our non nestables - foreach ($nonNestables as $non_nestable) - { - $Inline['element']['nonNestables'][] = $non_nestable; - } + + $Inline['element']['nonNestables'] = isset($Inline['element']['nonNestables']) + ? array_merge($Inline['element']['nonNestables'], $nonNestables) + : $nonNestables + ; # the text that comes before the inline $unmarkedText = substr($text, 0, $Inline['position']); # compile the unmarked text - $markup .= $this->unmarkedText($unmarkedText); + $InlineText = $this->inlineText($unmarkedText); + $Elements[] = $InlineText['element']; # compile the inline - $markup .= isset($Inline['markup']) ? $Inline['markup'] : $this->element($Inline['element']); + $Elements[] = $this->extractElement($Inline); # remove the examined text $text = substr($text, $Inline['position'] + $Inline['extent']); @@ -1121,28 +1220,57 @@ public function line($text, $nonNestables=array()) $unmarkedText = substr($text, 0, $markerPosition + 1); - $markup .= $this->unmarkedText($unmarkedText); + $InlineText = $this->inlineText($unmarkedText); + $Elements[] = $InlineText['element']; $text = substr($text, $markerPosition + 1); } - $markup .= $this->unmarkedText($text); + $InlineText = $this->inlineText($text); + $Elements[] = $InlineText['element']; - return $markup; + foreach ($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($matches[0]), @@ -1156,13 +1284,19 @@ protected function inlineCode($Excerpt) protected function inlineEmailTag($Excerpt) { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $Excerpt['text'], $matches)) - { + $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; + $url = "mailto:$url"; } return array( @@ -1204,8 +1338,11 @@ protected function inlineEmphasis($Excerpt) 'extent' => strlen($matches[0]), 'element' => array( 'name' => $emphasis, - 'handler' => 'line', - 'text' => $matches[1], + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $matches[1], + 'destination' => 'elements', + ) ), ); } @@ -1215,7 +1352,7 @@ protected function inlineEscapeSequence($Excerpt) if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters)) { return array( - 'markup' => $Excerpt['text'][1], + 'element' => array('rawHtml' => $Excerpt['text'][1]), 'extent' => 2, ); } @@ -1243,8 +1380,9 @@ protected function inlineImage($Excerpt) 'name' => 'img', 'attributes' => array( 'src' => $Link['element']['attributes']['href'], - 'alt' => $Link['element']['text'], + 'alt' => $Link['element']['handler']['argument'], ), + 'autobreak' => true, ), ); @@ -1259,9 +1397,12 @@ protected function inlineLink($Excerpt) { $Element = array( 'name' => 'a', - 'handler' => 'line', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => null, + 'destination' => 'elements', + ), 'nonNestables' => array('Url', 'Link'), - 'text' => null, 'attributes' => array( 'href' => null, 'title' => null, @@ -1274,7 +1415,7 @@ protected function inlineLink($Excerpt) if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches)) { - $Element['text'] = $matches[1]; + $Element['handler']['argument'] = $matches[1]; $extent += strlen($matches[0]); @@ -1285,7 +1426,7 @@ protected function inlineLink($Excerpt) return; } - if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*"|\'[^\']*\'))?\s*[)]/', $remainder, $matches)) + if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*+"|\'[^\']*+\'))?\s*+[)]/', $remainder, $matches)) { $Element['attributes']['href'] = $matches[1]; @@ -1300,14 +1441,14 @@ protected function inlineLink($Excerpt) { if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) { - $definition = strlen($matches[1]) ? $matches[1] : $Element['text']; + $definition = strlen($matches[1]) ? $matches[1] : $Element['handler']['argument']; $definition = strtolower($definition); $extent += strlen($matches[0]); } else { - $definition = strtolower($Element['text']); + $definition = strtolower($Element['handler']['argument']); } if ( ! isset($this->DefinitionData['Reference'][$definition])) @@ -1334,26 +1475,26 @@ protected function inlineMarkup($Excerpt) return; } - if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*[ ]*>/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*+[ ]*+>/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } - if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } - if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches)) + if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches)) { return array( - 'markup' => $matches[0], + 'element' => array('rawHtml' => $matches[0]), 'extent' => strlen($matches[0]), ); } @@ -1361,23 +1502,16 @@ protected function inlineMarkup($Excerpt) protected function inlineSpecialCharacter($Excerpt) { - if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text'])) - { + if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false + and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches) + ) { return array( - 'markup' => '&', - 'extent' => 1, + 'element' => array('rawHtml' => '&' . $matches[1] . ';'), + 'extent' => strlen($matches[0]), ); } - $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot'); - - if (isset($SpecialCharacter[$Excerpt['text'][0]])) - { - return array( - 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';', - 'extent' => 1, - ); - } + return; } protected function inlineStrikethrough($Excerpt) @@ -1393,8 +1527,11 @@ protected function inlineStrikethrough($Excerpt) 'extent' => strlen($matches[0]), 'element' => array( 'name' => 'del', - 'text' => $matches[1], - 'handler' => 'line', + 'handler' => array( + 'function' => 'lineElements', + 'argument' => $matches[1], + 'destination' => 'elements', + ) ), ); } @@ -1407,8 +1544,9 @@ protected function inlineUrl($Excerpt) return; } - if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE)) - { + if (strpos($Excerpt['context'], 'http') !== false + and preg_match('/\bhttps?+:[\/]{2}[^\s<]+\b\/*+/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE) + ) { $url = $matches[0][0]; $Inline = array( @@ -1429,7 +1567,7 @@ protected function inlineUrl($Excerpt) protected function inlineUrlTag($Excerpt) { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches)) + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches)) { $url = $matches[1]; @@ -1450,22 +1588,111 @@ protected function inlineUrlTag($Excerpt) protected function unmarkedText($text) { - if ($this->breaksEnabled) + $Inline = $this->inlineText($text); + return $this->element($Inline['element']); + } + + # + # Handlers + # + + protected function handle(array $Element) + { + if (isset($Element['handler'])) { - $text = preg_replace('/[ ]*\n/', "
\n", $text); + if (!isset($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']); } - else + + 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'])) { - $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
\n", $text); - $text = str_replace(" \n", "\n", $text); + $Element['element'] = $this->elementApplyRecursive($closure, $Element['element']); } - return $text; + return $Element; } - # - # Handlers - # + protected function elementApplyRecursiveDepthFirst($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) { @@ -1474,18 +1701,28 @@ protected function element(array $Element) $Element = $this->sanitiseElement($Element); } - $markup = '<'.$Element['name']; + # identity map if element has no handler + $Element = $this->handle($Element); + + $hasName = isset($Element['name']); - if (isset($Element['attributes'])) + $markup = ''; + + if ($hasName) { - foreach ($Element['attributes'] as $name => $value) + $markup .= '<' . $Element['name']; + + if (isset($Element['attributes'])) { - if ($value === null) + foreach ($Element['attributes'] as $name => $value) { - continue; - } + if ($value === null) + { + continue; + } - $markup .= ' '.$name.'="'.self::escape($value).'"'; + $markup .= " $name=\"".self::escape($value).'"'; + } } } @@ -1500,35 +1737,40 @@ protected function element(array $Element) elseif (isset($Element['rawHtml'])) { $text = $Element['rawHtml']; + $allowRawHtmlInSafeMode = isset($Element['allowRawHtmlInSafeMode']) && $Element['allowRawHtmlInSafeMode']; $permitRawHtml = !$this->safeMode || $allowRawHtmlInSafeMode; } - if (isset($text)) - { - $markup .= '>'; + $hasContent = isset($text) || isset($Element['element']) || isset($Element['elements']); - if (!isset($Element['nonNestables'])) - { - $Element['nonNestables'] = array(); - } + if ($hasContent) + { + $markup .= $hasName ? '>' : ''; - if (isset($Element['handler'])) + if (isset($Element['elements'])) { - $markup .= $this->{$Element['handler']}($text, $Element['nonNestables']); + $markup .= $this->elements($Element['elements']); } - elseif (!$permitRawHtml) + elseif (isset($Element['element'])) { - $markup .= self::escape($text, true); + $markup .= $this->element($Element['element']); } else { - $markup .= $text; + if (!$permitRawHtml) + { + $markup .= self::escape($text, true); + } + else + { + $markup .= $text; + } } - $markup .= ''; + $markup .= $hasName ? '' : ''; } - else + elseif ($hasName) { $markup .= ' />'; } @@ -1540,12 +1782,26 @@ protected function elements(array $Elements) { $markup = ''; + $autoBreak = true; + foreach ($Elements as $Element) { - $markup .= "\n" . $this->element($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 .= "\n"; + $markup .= $autoBreak ? "\n" : ''; return $markup; } @@ -1554,21 +1810,49 @@ protected function elements(array $Elements) protected function li($lines) { - $markup = $this->lines($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']); + } - $trimmedMarkup = trim($markup); + return $Elements; + } - if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '

') + # + # 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)) { - $markup = $trimmedMarkup; - $markup = substr($markup, 3); + $offset = $matches[0][1]; + $before = substr($text, 0, $offset); + $after = substr($text, $offset + strlen($matches[0][0])); + + $newElements[] = array('text' => $before); - $position = strpos($markup, "

"); + foreach ($Elements as $Element) + { + $newElements[] = $Element; + } - $markup = substr_replace($markup, '', $position, 4); + $text = $after; } - return $markup; + $newElements[] = array('text' => $text); + + return $newElements; } # @@ -1590,6 +1874,12 @@ protected function sanitiseElement(array $Element) 'img' => 'src', ); + if ( ! isset($Element['name'])) + { + unset($Element['attributes']); + return $Element; + } + if (isset($safeUrlNameToAtt[$Element['name']])) { $Element = $this->filterUnsafeUrlInAttribute($Element, $safeUrlNameToAtt[$Element['name']]); @@ -1679,12 +1969,12 @@ static function instance($name = 'default') # Read-Only protected $specialCharacters = array( - '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', + '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~' ); protected $StrongRegex = array( - '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s', - '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us', + '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s', + '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us', ); protected $EmRegex = array( @@ -1692,7 +1982,7 @@ static function instance($name = 'default') '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', ); - protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?'; + 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',