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 $markup = $this->lines($lines); # trim line breaks $markup = trim($markup, "\n"); return $markup; } # # Setters # function setBreaksEnabled($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; protected $safeLinksWhitelist = array( 'http://', 'https://', 'ftp://', 'ftps://', 'mailto:', '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) { $CurrentBlock = null; foreach ($lines as $line) { if (chop($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]) and $line[$indent] === ' ') { $indent ++; } $text = $indent > 0 ? substr($line, $indent) : $line; # ~ $Line = array('body' => $line, 'indent' => $indent, 'text' => $text); # ~ if (isset($CurrentBlock['continuable'])) { $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock); if (isset($Block)) { $CurrentBlock = $Block; continue; } else { if ($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) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted'])) { $CurrentBlock['element']['text'] .= "\n".$text; } else { $Blocks []= $CurrentBlock; $CurrentBlock = $this->paragraph($Line); $CurrentBlock['identified'] = true; } } # ~ if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($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 .= $this->element($Block['element']); } $markup .= "\n"; # ~ return $markup; } protected function isBlockContinuable($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 ! isset($Block['type']) and ! isset($Block['interrupted'])) { return; } if ($Line['indent'] >= 4) { $text = substr($Line['body'], 4); $Block = array( 'element' => array( 'name' => 'pre', 'handler' => 'element', 'text' => array( 'name' => 'code', 'text' => $text, ), ), ); return $Block; } } protected function blockCodeContinue($Line, $Block) { if ($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 $Block; } } protected function blockCodeComplete($Block) { $text = $Block['element']['text']['text']; $Block['element']['text']['text'] = $text; 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) { if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([^`]+)?[ ]*$/', $Line['text'], $matches)) { $Element = array( 'name' => 'code', 'text' => '', ); if (isset($matches[1])) { $class = 'language-'.$matches[1]; $Element['attributes'] = array( 'class' => $class, ); } $Block = array( 'char' => $Line['text'][0], 'element' => array( 'name' => 'pre', 'handler' => 'element', 'text' => $Element, ), ); return $Block; } } protected function blockFencedCodeContinue($Line, $Block) { if (isset($Block['complete'])) { return; } 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 $Block; } protected function blockFencedCodeComplete($Block) { $text = $Block['element']['text']['text']; $Block['element']['text']['text'] = $text; return $Block; } # # Header protected function blockHeader($Line) { if (isset($Line['text'][1])) { $level = 1; while (isset($Line['text'][$level]) and $Line['text'][$level] === '#') { $level ++; } if ($level > 6) { return; } $text = trim($Line['text'], '#'); $text = trim($text, ' '); $Block = array( 'element' => array( 'name' => 'h' . min(6, $level), 'text' => $text, 'handler' => 'line', ), ); 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] .= ' '; } $Block = array( 'indent' => $Line['indent'], 'pattern' => $pattern, 'data' => array( 'type' => $name, 'marker' => $matches[1], 'markerType' => ($name === 'ul' ? strstr($matches[1], ' ', true) : substr(strstr($matches[1], ' ', true), -1)), ), 'element' => array( 'name' => $name, 'handler' => 'elements', ), ); if ($name === 'ol') { $listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0'; if ($listStart !== '1') { if ( isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted']) ) { return; } $Block['element']['attributes'] = array('start' => $listStart); } } $Block['li'] = array( 'name' => 'li', 'handler' => 'li', 'text' => !empty($matches[3]) ? array($matches[3]) : array(), ); $Block['element']['text'] []= & $Block['li']; return $Block; } } protected function blockListContinue($Line, array $Block) { if (isset($Block['interrupted']) and empty($Block['li']['text'])) { return null; } $requiredIndent = ($Block['indent'] + strlen($Block['data']['marker'])); if ($Line['indent'] < $requiredIndent and ( ( $Block['data']['type'] === 'ol' and preg_match('/^[0-9]+'.preg_quote($Block['data']['markerType']).'(?:[ ]+(.*)|$)/', $Line['text'], $matches) ) or ( $Block['data']['type'] === 'ul' and preg_match('/^'.preg_quote($Block['data']['markerType']).'(?:[ ]+(.*)|$)/', $Line['text'], $matches) ) ) ) { if (isset($Block['interrupted'])) { $Block['li']['text'] []= ''; $Block['loose'] = true; unset($Block['interrupted']); } unset($Block['li']); $text = isset($matches[1]) ? $matches[1] : ''; $Block['indent'] = $Line['indent']; $Block['li'] = array( 'name' => 'li', 'handler' => 'li', 'text' => array( $text, ), ); $Block['element']['text'] []= & $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'])) { $Block['li']['text'] []= ''; unset($Block['interrupted']); } $text = substr($Line['body'], $requiredIndent); $Block['li']['text'] []= $text; return $Block; } if ( ! isset($Block['interrupted'])) { $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}/', '', $Line['body']); $Block['li']['text'] []= $text; return $Block; } } protected function blockListComplete(array $Block) { if (isset($Block['loose'])) { foreach ($Block['element']['text'] as &$li) { if (end($li['text']) !== '') { $li['text'] []= ''; } } } return $Block; } # # Quote protected function blockQuote($Line) { if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) { $Block = array( 'element' => array( 'name' => 'blockquote', 'handler' => 'lines', 'text' => (array) $matches[1], ), ); 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']['text'] []= $matches[1]; return $Block; } if ( ! isset($Block['interrupted'])) { $Block['element']['text'] []= $Line['text']; return $Block; } } # # Rule protected function blockRule($Line) { if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text'])) { $Block = array( 'element' => array( 'name' => 'hr' ), ); return $Block; } } # # Setext protected function blockSetextHeader($Line, array $Block = null) { if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) { return; } if ( chop(chop($Line['text'], ' '), $Line['text'][0]) === '' and $Line['indent'] < 4 ) { $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']), ); 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 (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches)) { $id = strtolower($matches[1]); $Data = array( 'url' => $matches[2], 'title' => null, ); if (isset($matches[3])) { $Data['title'] = $matches[3]; } $this->DefinitionData['Reference'][$id] = $Data; $Block = array( 'hidden' => true, ); return $Block; } } # # Table protected function blockTable($Line, array $Block = null) { if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) { return; } if ( strpos($Block['element']['text'], '|') === false and strpos($Line['text'], '|') === false and strpos($Line['text'], ':') === false ) { return; } if (chop($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; } # ~ $HeaderElements = array(); $header = $Block['element']['text']; $header = trim($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', 'text' => $headerCell, 'handler' => 'line', ); if (isset($alignments[$index])) { $alignment = $alignments[$index]; $HeaderElement['attributes'] = array( 'style' => 'text-align: '.$alignment.';', ); } $HeaderElements []= $HeaderElement; } # ~ $Block = array( 'alignments' => $alignments, 'identified' => true, 'element' => array( 'name' => 'table', 'handler' => 'elements', ), ); $Block['element']['text'] []= array( 'name' => 'thead', 'handler' => 'elements', ); $Block['element']['text'] []= array( 'name' => 'tbody', 'handler' => 'elements', 'text' => array(), ); $Block['element']['text'][0]['text'] []= array( 'name' => 'tr', 'handler' => 'elements', 'text' => $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' => 'line', 'text' => $cell, ); if (isset($Block['alignments'][$index])) { $Element['attributes'] = array( 'style' => 'text-align: '.$Block['alignments'][$index].';', ); } $Elements []= $Element; } $Element = array( 'name' => 'tr', 'handler' => 'elements', 'text' => $Elements, ); $Block['element']['text'][1]['text'] []= $Element; return $Block; } } # # ~ # protected function paragraph($Line) { $Block = array( 'element' => array( 'name' => 'p', 'text' => $Line['text'], 'handler' => 'line', ), ); 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'), ); # ~ protected $inlineMarkerList = '!*_&[:<`~\\'; # # ~ # public function line($text, $nonNestables=array()) { $markup = ''; # $excerpt is based on the first occurrence of a marker while ($excerpt = strpbrk($text, $this->inlineMarkerList)) { $marker = $excerpt[0]; $markerPosition = strpos($text, $marker); $Excerpt = array('text' => $excerpt, 'context' => $text); foreach ($this->InlineTypes[$marker] as $inlineType) { # check to see if the current inline type is nestable in the current context if ( ! empty($nonNestables) and in_array($inlineType, $nonNestables)) { continue; } $Inline = $this->{'inline'.$inlineType}($Excerpt); if ( ! isset($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'] = $markerPosition; } # cause the new element to 'inherit' our non nestables foreach ($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 .= $this->element($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 $markup; } # # ~ # protected function inlineText($text) { $Inline = array( 'extent' => strlen($text), 'element' => array( 'handler' => 'elements', ), ); if ($this->breaksEnabled) { $Inline['element']['text'] = self::pregReplaceElements( '/[ ]*\n/', array( array('name' => 'br'), array('text' => "\n"), ), $text ); } else { $Inline['element']['text'] = self::pregReplaceElements( '/(?:[ ][ ]+|[ ]*\\\\)\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' => 'line', 'text' => $matches[1], ), ); } protected function inlineEscapeSequence($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']['text'], ), ), ); $Inline['element']['attributes'] += $Link['element']['attributes']; unset($Inline['element']['attributes']['href']); return $Inline; } protected function inlineLink($Excerpt) { $Element = array( 'name' => 'a', 'handler' => 'line', 'nonNestables' => array('Url', 'Link'), 'text' => null, 'attributes' => array( '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; } 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['text']; $definition = strtolower($definition); $extent += strlen($matches[0]); } else { $definition = strtolower($Element['text']); } 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 (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', 'text' => $matches[1], 'handler' => 'line', ), ); } } protected function inlineUrl($Excerpt) { if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/') { return; } if (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 element(array $Element) { if ($this->safeMode) { $Element = $this->sanitiseElement($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 || $allowRawHtmlInSafeMode; } if (isset($text)) { $markup .= $hasName ? '>' : ''; if (!isset($Element['nonNestables'])) { $Element['nonNestables'] = array(); } if (isset($Element['handler'])) { $markup .= $this->{$Element['handler']}($text, $Element['nonNestables']); } elseif (!$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) { // (autobreak === false) covers both sides of an element $autoBreak = !$autoBreak ? $autoBreak : isset($Element['name']); $markup .= ($autoBreak ? "\n" : '') . $this->element($Element); $autoBreak = isset($Element['name']); } $markup .= $autoBreak ? "\n" : ''; return $markup; } # ~ protected function li($lines) { $markup = $this->lines($lines); $trimmedMarkup = trim($markup); if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '

') { $markup = $trimmedMarkup; $markup = substr($markup, 3); $position = strpos($markup, "

"); $markup = substr_replace($markup, '', $position, 4); } return $markup; } # # 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', ); }