From edf2c88d12dc881153c2de8dd786e3688850d9fa Mon Sep 17 00:00:00 2001 From: Starbeamrainbowlabs Date: Sun, 4 Oct 2015 13:37:12 +0100 Subject: [PATCH] Add optional parsedown module --- build/index.php | 2136 ++++++++++++++++++++++++++++++++++ module_index.json | 9 + modules/parser-parsedown.php | 2135 +++++++++++++++++++++++++++++++++ 3 files changed, 4280 insertions(+) create mode 100644 modules/parser-parsedown.php diff --git a/build/index.php b/build/index.php index 8053384..35fae27 100644 --- a/build/index.php +++ b/build/index.php @@ -2017,6 +2017,2142 @@ class Slimdown { + +register_module([ + "name" => "Parsedown", + "version" => "0.1", + "author" => "Johnny Broadway, Emanuil Rusev & Starbeamrainbowlabs", + "description" => "An upgraded parser based on Emanuil Rusev's Parsedown Extra PHP library (https://github.com/erusev/parsedown-extra), which is licensed MIT. Also uses a modified Slimdown engine by Johnny Broadway in order to add support for internal links etc. Please be careful, as this module adds a _ton_ of weight to your installation.", + "id" => "parser-parsedown", + "optional" => true, + "code" => function() { + $parsedown_extra = new ParsedownExtra(); + add_parser("parsedown", function($source) use ($parsedown_extra) { + $source = Parsedown_Slimdown_Extensions::render($source); + + return $parsedown_extra->text($source); + }); + } +]); + +/** + * Slimdown - A very basic regex-based Markdown parser. Supports the + * following elements (and can be extended via Slimdown::add_rule()): + * + * - Headers + * - Links + * - Bold + * - Emphasis + * - Deletions + * - Quotes + * - Inline code + * - Blockquotes + * - Ordered/unordered lists + * - Horizontal rules + * + * Author: Johnny Broadway + * Website: https://gist.github.com/jbroadway/2836900 + * License: MIT + */ + +/** + * Modified by Starbeamrainbowlabs (starbeamrainbowlabs) + * + * Changed bold to use single asterisks + * Changed italics to use single underscores + * Added one to add the heading levels (no

tags allowed) + * Added wiki style internal link parsing + * Added wiki style internal link parsing with display text + * Added image support + */ +class Parsedown_Slimdown_Extensions { + public static $rules = array ( + '/\r\n/' => "\n", // new line normalisation + + '/!\[(.*)\]\(([^\s]+)\s(\d+.+)\s(left|right)\)/' => '\1', // images with size + '/!\[(.*)\]\(([^\s]+)\s(\d+.+)\)/' => '\1', // images with size + '/!\[(.*)\]\((.*)\)/' => '\1', // basic images + + '/\[\[([a-zA-Z0-9\_\- ]+)\|([a-zA-Z0-9\_\- ]+)\]\]/' => '\2', //internal links with display text + '/\[\[([a-zA-Z0-9\_\- ]+)\]\]/' => '\1', //internal links + ); + + /** + * Add a rule. + */ + public static function add_rule ($regex, $replacement) { + self::$rules[$regex] = $replacement; + } + /** + * Render some Markdown into HTML. + */ + public static function render ($text) { + foreach (self::$rules as $regex => $replacement) { + if (is_callable ( $replacement)) { + $text = preg_replace_callback ($regex, $replacement, $text); + } else { + $text = preg_replace ($regex, $replacement, $text); + } + } + return trim ($text); + } +} + + +# +# +# Parsedown +# http://parsedown.org +# +# (c) Emanuil Rusev +# http://erusev.com +# +# For the full license information, view the LICENSE file that was distributed +# with this source code. +# +# + +class Parsedown +{ + # ~ + + const version = '1.5.4'; + + # ~ + + function text($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 + $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; + + # + # 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 + # + + private 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 = $Block; + + continue; + } + else + { + if (method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $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; + + $Block['identified'] = true; + } + + if (method_exists($this, 'block'.$blockType.'Continue')) + { + $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 method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + } + + # ~ + + $Blocks []= $CurrentBlock; + + unset($Blocks[0]); + + # ~ + + $markup = ''; + + foreach ($Blocks as $Block) + { + if (isset($Block['hidden'])) + { + continue; + } + + $markup .= "\n"; + $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']); + } + + $markup .= "\n"; + + # ~ + + return $markup; + } + + # + # Code + + protected function blockCode($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']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $Block['element']['text']['text'] = $text; + + return $Block; + } + + # + # Comment + + protected function blockComment($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!') + { + $Block = array( + 'markup' => $Line['body'], + ); + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + } + + protected function blockCommentContinue($Line, array $Block) + { + if (isset($Block['closed'])) + { + return; + } + + $Block['markup'] .= "\n" . $Line['body']; + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + + # + # Fenced Code + + protected function blockFencedCode($Line) + { + if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([\w-]+)?[ ]*$/', $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']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $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'], '# '); + + $Block = array( + 'element' => array( + 'name' => 'h' . min(6, $level), + 'text' => $text, + 'handler' => 'line', + ), + ); + + return $Block; + } + } + + # + # List + + protected function blockList($Line) + { + list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]'); + + if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches)) + { + $Block = array( + 'indent' => $Line['indent'], + 'pattern' => $pattern, + 'element' => array( + 'name' => $name, + 'handler' => 'elements', + ), + ); + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $matches[2], + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + } + + protected function blockListContinue($Line, array $Block) + { + if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches)) + { + if (isset($Block['interrupted'])) + { + $Block['li']['text'] []= ''; + + unset($Block['interrupted']); + } + + unset($Block['li']); + + $text = isset($matches[1]) ? $matches[1] : ''; + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $text, + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + + if ($Line['text'][0] === '[' and $this->blockReference($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 $Block; + } + } + + # + # Quote + + protected function blockQuote($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 $Block) + { + if ($Line['text'][0] === '>' and 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 $Block; + } + } + + # + # Rule + + protected function blockRule($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($Line['text'], $Line['text'][0]) === '') + { + $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; + + return $Block; + } + } + + # + # Markup + + protected function blockMarkup($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (preg_match('/^<(\w*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)/', $Line['text'], $matches)) + { + $element = strtolower($matches[1]); + + if (in_array($element, $this->textLevelElements)) + { + return; + } + + $Block = array( + 'name' => $matches[1], + 'depth' => 0, + 'markup' => $Line['text'], + ); + + $length = strlen($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'])) + { + 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']; + + 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($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '') + { + $alignments = array(); + + $divider = $Line['text']; + + $divider = trim($divider); + $divider = trim($divider, '|'); + + $dividerCells = explode('|', $divider); + + foreach ($dividerCells as $dividerCell) + { + $dividerCell = trim($dividerCell); + + if ($dividerCell === '') + { + continue; + } + + $alignment = null; + + if ($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('|', $header); + + foreach ($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 ($Line['text'][0] === '|' or strpos($Line['text'], '|')) + { + $Elements = array(); + + $row = $Line['text']; + + $row = trim($row); + $row = trim($row, '|'); + + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + + foreach ($matches[0] 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('SpecialCharacter'), + '!' => array('Image'), + '&' => array('SpecialCharacter'), + '*' => array('Emphasis'), + ':' => array('Url'), + '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'), + '>' => array('SpecialCharacter'), + '[' => array('Link'), + '_' => array('Emphasis'), + '`' => array('Code'), + '~' => array('Strikethrough'), + '\\' => array('EscapeSequence'), + ); + + # ~ + + protected $inlineMarkerList = '!"*_&[:<>`~\\'; + + # + # ~ + # + + public function line($text) + { + $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) + { + $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; + } + + # the text that comes before the inline + $unmarkedText = substr($text, 0, $Inline['position']); + + # compile the unmarked text + $markup .= $this->unmarkedText($unmarkedText); + + # compile the inline + $markup .= isset($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 $markup; + } + + # + # ~ + # + + protected function inlineCode($Excerpt) + { + $marker = $Excerpt['text'][0]; + + if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(? strlen($matches[0]), + 'element' => array( + 'name' => 'code', + 'text' => $text, + ), + ); + } + } + + protected function inlineEmailTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/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( + 'markup' => $Excerpt['text'][1], + 'extent' => 2, + ); + } + } + + protected function inlineImage($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', + '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('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:[ ]+("[^"]*"|\'[^\']*\'))?[)]/', $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']; + } + + $Element['attributes']['href'] = str_replace(array('&', '<'), array('&', '<'), $Element['attributes']['href']); + + return array( + 'extent' => $extent, + 'element' => $Element, + ); + } + + protected function inlineMarkup($Excerpt) + { + if ($this->markupEscaped or strpos($Excerpt['text'], '>') === false) + { + return; + } + + if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*[ ]*>/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\//s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + } + + protected function inlineSpecialCharacter($Excerpt) + { + if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text'])) + { + return array( + 'markup' => '&', + 'extent' => 1, + ); + } + + $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot'); + + if (isset($SpecialCharacter[$Excerpt['text'][0]])) + { + return array( + 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';', + 'extent' => 1, + ); + } + } + + protected function inlineStrikethrough($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)) + { + $Inline = array( + 'extent' => strlen($matches[0][0]), + 'position' => $matches[0][1], + 'element' => array( + 'name' => 'a', + 'text' => $matches[0][0], + 'attributes' => array( + 'href' => $matches[0][0], + ), + ), + ); + + return $Inline; + } + } + + protected function inlineUrlTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches)) + { + $url = str_replace(array('&', '<'), array('&', '<'), $matches[1]); + + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => 'a', + 'text' => $url, + 'attributes' => array( + 'href' => $url, + ), + ), + ); + } + } + + # ~ + + protected function unmarkedText($text) + { + if ($this->breaksEnabled) + { + $text = preg_replace('/[ ]*\n/', "
\n", $text); + } + else + { + $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
\n", $text); + $text = str_replace(" \n", "\n", $text); + } + + return $text; + } + + # + # Handlers + # + + protected function element(array $Element) + { + $markup = '<'.$Element['name']; + + if (isset($Element['attributes'])) + { + foreach ($Element['attributes'] as $name => $value) + { + if ($value === null) + { + continue; + } + + $markup .= ' '.$name.'="'.$value.'"'; + } + } + + if (isset($Element['text'])) + { + $markup .= '>'; + + if (isset($Element['handler'])) + { + $markup .= $this->{$Element['handler']}($Element['text']); + } + else + { + $markup .= $Element['text']; + } + + $markup .= ''; + } + else + { + $markup .= ' />'; + } + + return $markup; + } + + protected function elements(array $Elements) + { + $markup = ''; + + foreach ($Elements as $Element) + { + $markup .= "\n" . $this->element($Element); + } + + $markup .= "\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 $markup; + } + + # + # Deprecated Methods + # + + function parse($text) + { + $markup = $this->text($text); + + return $markup; + } + + # + # Static Methods + # + + static function instance($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', 'sub', 'mark', + 'u', 'xm', 'sup', 'nobr', + 'var', 'ruby', + 'wbr', 'span', + 'time', + ); +} + +# +# +# Parsedown Extra +# https://github.com/erusev/parsedown-extra +# +# (c) Emanuil Rusev +# http://erusev.com +# +# For the full license information, view the LICENSE file that was distributed +# with this source code. +# +# + +class ParsedownExtra extends Parsedown +{ + # ~ + + const version = '0.7.0'; + + # ~ + + function __construct() + { + if (parent::version < '1.5.0') + { + throw new Exception('ParsedownExtra requires a later version of Parsedown'); + } + + $this->BlockTypes[':'] []= 'DefinitionList'; + $this->BlockTypes['*'] []= 'Abbreviation'; + + # identify footnote definitions before reference definitions + array_unshift($this->BlockTypes['['], 'Footnote'); + + # identify footnote markers before before links + array_unshift($this->InlineTypes['['], 'FootnoteMarker'); + } + + # + # ~ + + function text($text) + { + $markup = parent::text($text); + + # merge consecutive dl elements + + $markup = preg_replace('/<\/dl>\s+
\s+/', '', $markup); + + # add footnotes + + if (isset($this->DefinitionData['Footnote'])) + { + $Element = $this->buildFootnoteElement(); + + $markup .= "\n" . $this->element($Element); + } + + return $markup; + } + + # + # Blocks + # + + # + # Abbreviation + + protected function blockAbbreviation($Line) + { + if (preg_match('/^\*\[(.+?)\]:[ ]*(.+?)[ ]*$/', $Line['text'], $matches)) + { + $this->DefinitionData['Abbreviation'][$matches[1]] = $matches[2]; + + $Block = array( + 'hidden' => true, + ); + + return $Block; + } + } + + # + # Footnote + + protected function blockFootnote($Line) + { + if (preg_match('/^\[\^(.+?)\]:[ ]?(.*)$/', $Line['text'], $matches)) + { + $Block = array( + 'label' => $matches[1], + 'text' => $matches[2], + 'hidden' => true, + ); + + return $Block; + } + } + + protected function blockFootnoteContinue($Line, $Block) + { + if ($Line['text'][0] === '[' and preg_match('/^\[\^(.+?)\]:/', $Line['text'])) + { + return; + } + + if (isset($Block['interrupted'])) + { + if ($Line['indent'] >= 4) + { + $Block['text'] .= "\n\n" . $Line['text']; + + return $Block; + } + } + else + { + $Block['text'] .= "\n" . $Line['text']; + + return $Block; + } + } + + protected function blockFootnoteComplete($Block) + { + $this->DefinitionData['Footnote'][$Block['label']] = array( + 'text' => $Block['text'], + 'count' => null, + 'number' => null, + ); + + return $Block; + } + + # + # Definition List + + protected function blockDefinitionList($Line, $Block) + { + if ( ! isset($Block) or isset($Block['type'])) + { + return; + } + + $Element = array( + 'name' => 'dl', + 'handler' => 'elements', + 'text' => array(), + ); + + $terms = explode("\n", $Block['element']['text']); + + foreach ($terms as $term) + { + $Element['text'] []= array( + 'name' => 'dt', + 'handler' => 'line', + 'text' => $term, + ); + } + + $Block['element'] = $Element; + + $Block = $this->addDdElement($Line, $Block); + + return $Block; + } + + protected function blockDefinitionListContinue($Line, array $Block) + { + if ($Line['text'][0] === ':') + { + $Block = $this->addDdElement($Line, $Block); + + return $Block; + } + else + { + if (isset($Block['interrupted']) and $Line['indent'] === 0) + { + return; + } + + if (isset($Block['interrupted'])) + { + $Block['dd']['handler'] = 'text'; + $Block['dd']['text'] .= "\n\n"; + + unset($Block['interrupted']); + } + + $text = substr($Line['body'], min($Line['indent'], 4)); + + $Block['dd']['text'] .= "\n" . $text; + + return $Block; + } + } + + # + # Header + + protected function blockHeader($Line) + { + $Block = parent::blockHeader($Line); + + if (preg_match('/[ #]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['text'], $matches, PREG_OFFSET_CAPTURE)) + { + $attributeString = $matches[1][0]; + + $Block['element']['attributes'] = $this->parseAttributeData($attributeString); + + $Block['element']['text'] = substr($Block['element']['text'], 0, $matches[0][1]); + } + + return $Block; + } + + # + # Markup + + protected function blockMarkupComplete($Block) + { + if ( ! isset($Block['void'])) + { + $Block['markup'] = $this->processTag($Block['markup']); + } + + return $Block; + } + + # + # Setext + + protected function blockSetextHeader($Line, array $Block = null) + { + $Block = parent::blockSetextHeader($Line, $Block); + + if (preg_match('/[ ]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['text'], $matches, PREG_OFFSET_CAPTURE)) + { + $attributeString = $matches[1][0]; + + $Block['element']['attributes'] = $this->parseAttributeData($attributeString); + + $Block['element']['text'] = substr($Block['element']['text'], 0, $matches[0][1]); + } + + return $Block; + } + + # + # Inline Elements + # + + # + # Footnote Marker + + protected function inlineFootnoteMarker($Excerpt) + { + if (preg_match('/^\[\^(.+?)\]/', $Excerpt['text'], $matches)) + { + $name = $matches[1]; + + if ( ! isset($this->DefinitionData['Footnote'][$name])) + { + return; + } + + $this->DefinitionData['Footnote'][$name]['count'] ++; + + if ( ! isset($this->DefinitionData['Footnote'][$name]['number'])) + { + $this->DefinitionData['Footnote'][$name]['number'] = ++ $this->footnoteCount; # » & + } + + $Element = array( + 'name' => 'sup', + 'attributes' => array('id' => 'fnref'.$this->DefinitionData['Footnote'][$name]['count'].':'.$name), + 'handler' => 'element', + 'text' => array( + 'name' => 'a', + 'attributes' => array('href' => '#fn:'.$name, 'class' => 'footnote-ref'), + 'text' => $this->DefinitionData['Footnote'][$name]['number'], + ), + ); + + return array( + 'extent' => strlen($matches[0]), + 'element' => $Element, + ); + } + } + + private $footnoteCount = 0; + + # + # Link + + protected function inlineLink($Excerpt) + { + $Link = parent::inlineLink($Excerpt); + + $remainder = substr($Excerpt['text'], $Link['extent']); + + if (preg_match('/^[ ]*{('.$this->regexAttribute.'+)}/', $remainder, $matches)) + { + $Link['element']['attributes'] += $this->parseAttributeData($matches[1]); + + $Link['extent'] += strlen($matches[0]); + } + + return $Link; + } + + # + # ~ + # + + protected function unmarkedText($text) + { + $text = parent::unmarkedText($text); + + if (isset($this->DefinitionData['Abbreviation'])) + { + foreach ($this->DefinitionData['Abbreviation'] as $abbreviation => $meaning) + { + $pattern = '/\b'.preg_quote($abbreviation, '/').'\b/'; + + $text = preg_replace($pattern, ''.$abbreviation.'', $text); + } + } + + return $text; + } + + # + # Util Methods + # + + protected function addDdElement(array $Line, array $Block) + { + $text = substr($Line['text'], 1); + $text = trim($text); + + unset($Block['dd']); + + $Block['dd'] = array( + 'name' => 'dd', + 'handler' => 'line', + 'text' => $text, + ); + + if (isset($Block['interrupted'])) + { + $Block['dd']['handler'] = 'text'; + + unset($Block['interrupted']); + } + + $Block['element']['text'] []= & $Block['dd']; + + return $Block; + } + + protected function buildFootnoteElement() + { + $Element = array( + 'name' => 'div', + 'attributes' => array('class' => 'footnotes'), + 'handler' => 'elements', + 'text' => array( + array( + 'name' => 'hr', + ), + array( + 'name' => 'ol', + 'handler' => 'elements', + 'text' => array(), + ), + ), + ); + + uasort($this->DefinitionData['Footnote'], 'self::sortFootnotes'); + + foreach ($this->DefinitionData['Footnote'] as $definitionId => $DefinitionData) + { + if ( ! isset($DefinitionData['number'])) + { + continue; + } + + $text = $DefinitionData['text']; + + $text = parent::text($text); + + $numbers = range(1, $DefinitionData['count']); + + $backLinksMarkup = ''; + + foreach ($numbers as $number) + { + $backLinksMarkup .= ' ↩'; + } + + $backLinksMarkup = substr($backLinksMarkup, 1); + + if (substr($text, - 4) === '

') + { + $backLinksMarkup = ' '.$backLinksMarkup; + + $text = substr_replace($text, $backLinksMarkup.'

', - 4); + } + else + { + $text .= "\n".'

'.$backLinksMarkup.'

'; + } + + $Element['text'][1]['text'] []= array( + 'name' => 'li', + 'attributes' => array('id' => 'fn:'.$definitionId), + 'text' => "\n".$text."\n", + ); + } + + return $Element; + } + + # ~ + + protected function parseAttributeData($attributeString) + { + $Data = array(); + + $attributes = preg_split('/[ ]+/', $attributeString, - 1, PREG_SPLIT_NO_EMPTY); + + foreach ($attributes as $attribute) + { + if ($attribute[0] === '#') + { + $Data['id'] = substr($attribute, 1); + } + else # "." + { + $classes []= substr($attribute, 1); + } + } + + if (isset($classes)) + { + $Data['class'] = implode(' ', $classes); + } + + return $Data; + } + + # ~ + + protected function processTag($elementMarkup) # recursive + { + # http://stackoverflow.com/q/1148928/200145 + libxml_use_internal_errors(true); + + $DOMDocument = new DOMDocument; + + # http://stackoverflow.com/q/11309194/200145 + $elementMarkup = mb_convert_encoding($elementMarkup, 'HTML-ENTITIES', 'UTF-8'); + + # http://stackoverflow.com/q/4879946/200145 + $DOMDocument->loadHTML($elementMarkup); + $DOMDocument->removeChild($DOMDocument->doctype); + $DOMDocument->replaceChild($DOMDocument->firstChild->firstChild->firstChild, $DOMDocument->firstChild); + + $elementText = ''; + + if ($DOMDocument->documentElement->getAttribute('markdown') === '1') + { + foreach ($DOMDocument->documentElement->childNodes as $Node) + { + $elementText .= $DOMDocument->saveHTML($Node); + } + + $DOMDocument->documentElement->removeAttribute('markdown'); + + $elementText = "\n".$this->text($elementText)."\n"; + } + else + { + foreach ($DOMDocument->documentElement->childNodes as $Node) + { + $nodeMarkup = $DOMDocument->saveHTML($Node); + + if ($Node instanceof DOMElement and ! in_array($Node->nodeName, $this->textLevelElements)) + { + $elementText .= $this->processTag($nodeMarkup); + } + else + { + $elementText .= $nodeMarkup; + } + } + } + + # because we don't want for markup to get encoded + $DOMDocument->documentElement->nodeValue = 'placeholder'; + + $markup = $DOMDocument->saveHTML($DOMDocument->documentElement); + $markup = str_replace('placeholder', $elementText, $markup); + + return $markup; + } + + # ~ + + protected function sortFootnotes($A, $B) # callback + { + return $A['number'] - $B['number']; + } + + # + # Fields + # + + protected $regexAttribute = '(?:[#.][-\w]+[ ]*)'; +} + + + // %next_module% // diff --git a/module_index.json b/module_index.json index b61b63a..31af2bc 100644 --- a/module_index.json +++ b/module_index.json @@ -151,5 +151,14 @@ "id": "parser-default", "lastupdate": 1443945169, "optional": false + }, + { + "name": "Parsedown", + "version": "0.1", + "author": "Johnny Broadway, Emanuil Rusev & Starbeamrainbowlabs", + "description": "An upgraded parser based on Emanuil Rusev's Parsedown Extra PHP library (https:\/\/github.com\/erusev\/parsedown-extra), which is licensed MIT. Also uses a modified Slimdown engine by Johnny Broadway in order to add support for internal links etc. Please be careful, as this module adds a _ton_ of weight to your installation.", + "id": "parser-parsedown", + "lastupdate": 1443961922, + "optional": true } ] \ No newline at end of file diff --git a/modules/parser-parsedown.php b/modules/parser-parsedown.php new file mode 100644 index 0000000..63e45a8 --- /dev/null +++ b/modules/parser-parsedown.php @@ -0,0 +1,2135 @@ + "Parsedown", + "version" => "0.1", + "author" => "Johnny Broadway, Emanuil Rusev & Starbeamrainbowlabs", + "description" => "An upgraded parser based on Emanuil Rusev's Parsedown Extra PHP library (https://github.com/erusev/parsedown-extra), which is licensed MIT. Also uses a modified Slimdown engine by Johnny Broadway in order to add support for internal links etc. Please be careful, as this module adds a _ton_ of weight to your installation.", + "id" => "parser-parsedown", + "optional" => true, + "code" => function() { + $parsedown_extra = new ParsedownExtra(); + add_parser("parsedown", function($source) use ($parsedown_extra) { + $source = Parsedown_Slimdown_Extensions::render($source); + + return $parsedown_extra->text($source); + }); + } +]); + +/** + * Slimdown - A very basic regex-based Markdown parser. Supports the + * following elements (and can be extended via Slimdown::add_rule()): + * + * - Headers + * - Links + * - Bold + * - Emphasis + * - Deletions + * - Quotes + * - Inline code + * - Blockquotes + * - Ordered/unordered lists + * - Horizontal rules + * + * Author: Johnny Broadway + * Website: https://gist.github.com/jbroadway/2836900 + * License: MIT + */ + +/** + * Modified by Starbeamrainbowlabs (starbeamrainbowlabs) + * + * Changed bold to use single asterisks + * Changed italics to use single underscores + * Added one to add the heading levels (no

tags allowed) + * Added wiki style internal link parsing + * Added wiki style internal link parsing with display text + * Added image support + */ +class Parsedown_Slimdown_Extensions { + public static $rules = array ( + '/\r\n/' => "\n", // new line normalisation + + '/!\[(.*)\]\(([^\s]+)\s(\d+.+)\s(left|right)\)/' => '\1', // images with size + '/!\[(.*)\]\(([^\s]+)\s(\d+.+)\)/' => '\1', // images with size + '/!\[(.*)\]\((.*)\)/' => '\1', // basic images + + '/\[\[([a-zA-Z0-9\_\- ]+)\|([a-zA-Z0-9\_\- ]+)\]\]/' => '\2', //internal links with display text + '/\[\[([a-zA-Z0-9\_\- ]+)\]\]/' => '\1', //internal links + ); + + /** + * Add a rule. + */ + public static function add_rule ($regex, $replacement) { + self::$rules[$regex] = $replacement; + } + /** + * Render some Markdown into HTML. + */ + public static function render ($text) { + foreach (self::$rules as $regex => $replacement) { + if (is_callable ( $replacement)) { + $text = preg_replace_callback ($regex, $replacement, $text); + } else { + $text = preg_replace ($regex, $replacement, $text); + } + } + return trim ($text); + } +} + + +# +# +# Parsedown +# http://parsedown.org +# +# (c) Emanuil Rusev +# http://erusev.com +# +# For the full license information, view the LICENSE file that was distributed +# with this source code. +# +# + +class Parsedown +{ + # ~ + + const version = '1.5.4'; + + # ~ + + function text($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 + $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; + + # + # 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 + # + + private 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 = $Block; + + continue; + } + else + { + if (method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $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; + + $Block['identified'] = true; + } + + if (method_exists($this, 'block'.$blockType.'Continue')) + { + $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 method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + } + + # ~ + + $Blocks []= $CurrentBlock; + + unset($Blocks[0]); + + # ~ + + $markup = ''; + + foreach ($Blocks as $Block) + { + if (isset($Block['hidden'])) + { + continue; + } + + $markup .= "\n"; + $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']); + } + + $markup .= "\n"; + + # ~ + + return $markup; + } + + # + # Code + + protected function blockCode($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']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $Block['element']['text']['text'] = $text; + + return $Block; + } + + # + # Comment + + protected function blockComment($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!') + { + $Block = array( + 'markup' => $Line['body'], + ); + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + } + + protected function blockCommentContinue($Line, array $Block) + { + if (isset($Block['closed'])) + { + return; + } + + $Block['markup'] .= "\n" . $Line['body']; + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + + # + # Fenced Code + + protected function blockFencedCode($Line) + { + if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([\w-]+)?[ ]*$/', $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']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $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'], '# '); + + $Block = array( + 'element' => array( + 'name' => 'h' . min(6, $level), + 'text' => $text, + 'handler' => 'line', + ), + ); + + return $Block; + } + } + + # + # List + + protected function blockList($Line) + { + list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]'); + + if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches)) + { + $Block = array( + 'indent' => $Line['indent'], + 'pattern' => $pattern, + 'element' => array( + 'name' => $name, + 'handler' => 'elements', + ), + ); + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $matches[2], + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + } + + protected function blockListContinue($Line, array $Block) + { + if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches)) + { + if (isset($Block['interrupted'])) + { + $Block['li']['text'] []= ''; + + unset($Block['interrupted']); + } + + unset($Block['li']); + + $text = isset($matches[1]) ? $matches[1] : ''; + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $text, + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + + if ($Line['text'][0] === '[' and $this->blockReference($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 $Block; + } + } + + # + # Quote + + protected function blockQuote($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 $Block) + { + if ($Line['text'][0] === '>' and 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 $Block; + } + } + + # + # Rule + + protected function blockRule($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($Line['text'], $Line['text'][0]) === '') + { + $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; + + return $Block; + } + } + + # + # Markup + + protected function blockMarkup($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (preg_match('/^<(\w*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches)) + { + $element = strtolower($matches[1]); + + if (in_array($element, $this->textLevelElements)) + { + return; + } + + $Block = array( + 'name' => $matches[1], + 'depth' => 0, + 'markup' => $Line['text'], + ); + + $length = strlen($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'])) + { + 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']; + + 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($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '') + { + $alignments = array(); + + $divider = $Line['text']; + + $divider = trim($divider); + $divider = trim($divider, '|'); + + $dividerCells = explode('|', $divider); + + foreach ($dividerCells as $dividerCell) + { + $dividerCell = trim($dividerCell); + + if ($dividerCell === '') + { + continue; + } + + $alignment = null; + + if ($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('|', $header); + + foreach ($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 ($Line['text'][0] === '|' or strpos($Line['text'], '|')) + { + $Elements = array(); + + $row = $Line['text']; + + $row = trim($row); + $row = trim($row, '|'); + + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + + foreach ($matches[0] 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('SpecialCharacter'), + '!' => array('Image'), + '&' => array('SpecialCharacter'), + '*' => array('Emphasis'), + ':' => array('Url'), + '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'), + '>' => array('SpecialCharacter'), + '[' => array('Link'), + '_' => array('Emphasis'), + '`' => array('Code'), + '~' => array('Strikethrough'), + '\\' => array('EscapeSequence'), + ); + + # ~ + + protected $inlineMarkerList = '!"*_&[:<>`~\\'; + + # + # ~ + # + + public function line($text) + { + $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) + { + $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; + } + + # the text that comes before the inline + $unmarkedText = substr($text, 0, $Inline['position']); + + # compile the unmarked text + $markup .= $this->unmarkedText($unmarkedText); + + # compile the inline + $markup .= isset($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 $markup; + } + + # + # ~ + # + + protected function inlineCode($Excerpt) + { + $marker = $Excerpt['text'][0]; + + if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(? strlen($matches[0]), + 'element' => array( + 'name' => 'code', + 'text' => $text, + ), + ); + } + } + + protected function inlineEmailTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/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( + 'markup' => $Excerpt['text'][1], + 'extent' => 2, + ); + } + } + + protected function inlineImage($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', + '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('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:[ ]+("[^"]*"|\'[^\']*\'))?[)]/', $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']; + } + + $Element['attributes']['href'] = str_replace(array('&', '<'), array('&', '<'), $Element['attributes']['href']); + + return array( + 'extent' => $extent, + 'element' => $Element, + ); + } + + protected function inlineMarkup($Excerpt) + { + if ($this->markupEscaped or strpos($Excerpt['text'], '>') === false) + { + return; + } + + if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*[ ]*>/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + } + + protected function inlineSpecialCharacter($Excerpt) + { + if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text'])) + { + return array( + 'markup' => '&', + 'extent' => 1, + ); + } + + $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot'); + + if (isset($SpecialCharacter[$Excerpt['text'][0]])) + { + return array( + 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';', + 'extent' => 1, + ); + } + } + + protected function inlineStrikethrough($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)) + { + $Inline = array( + 'extent' => strlen($matches[0][0]), + 'position' => $matches[0][1], + 'element' => array( + 'name' => 'a', + 'text' => $matches[0][0], + 'attributes' => array( + 'href' => $matches[0][0], + ), + ), + ); + + return $Inline; + } + } + + protected function inlineUrlTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches)) + { + $url = str_replace(array('&', '<'), array('&', '<'), $matches[1]); + + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => 'a', + 'text' => $url, + 'attributes' => array( + 'href' => $url, + ), + ), + ); + } + } + + # ~ + + protected function unmarkedText($text) + { + if ($this->breaksEnabled) + { + $text = preg_replace('/[ ]*\n/', "
\n", $text); + } + else + { + $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
\n", $text); + $text = str_replace(" \n", "\n", $text); + } + + return $text; + } + + # + # Handlers + # + + protected function element(array $Element) + { + $markup = '<'.$Element['name']; + + if (isset($Element['attributes'])) + { + foreach ($Element['attributes'] as $name => $value) + { + if ($value === null) + { + continue; + } + + $markup .= ' '.$name.'="'.$value.'"'; + } + } + + if (isset($Element['text'])) + { + $markup .= '>'; + + if (isset($Element['handler'])) + { + $markup .= $this->{$Element['handler']}($Element['text']); + } + else + { + $markup .= $Element['text']; + } + + $markup .= ''; + } + else + { + $markup .= ' />'; + } + + return $markup; + } + + protected function elements(array $Elements) + { + $markup = ''; + + foreach ($Elements as $Element) + { + $markup .= "\n" . $this->element($Element); + } + + $markup .= "\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 $markup; + } + + # + # Deprecated Methods + # + + function parse($text) + { + $markup = $this->text($text); + + return $markup; + } + + # + # Static Methods + # + + static function instance($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', 'sub', 'mark', + 'u', 'xm', 'sup', 'nobr', + 'var', 'ruby', + 'wbr', 'span', + 'time', + ); +} + +# +# +# Parsedown Extra +# https://github.com/erusev/parsedown-extra +# +# (c) Emanuil Rusev +# http://erusev.com +# +# For the full license information, view the LICENSE file that was distributed +# with this source code. +# +# + +class ParsedownExtra extends Parsedown +{ + # ~ + + const version = '0.7.0'; + + # ~ + + function __construct() + { + if (parent::version < '1.5.0') + { + throw new Exception('ParsedownExtra requires a later version of Parsedown'); + } + + $this->BlockTypes[':'] []= 'DefinitionList'; + $this->BlockTypes['*'] []= 'Abbreviation'; + + # identify footnote definitions before reference definitions + array_unshift($this->BlockTypes['['], 'Footnote'); + + # identify footnote markers before before links + array_unshift($this->InlineTypes['['], 'FootnoteMarker'); + } + + # + # ~ + + function text($text) + { + $markup = parent::text($text); + + # merge consecutive dl elements + + $markup = preg_replace('/<\/dl>\s+
\s+/', '', $markup); + + # add footnotes + + if (isset($this->DefinitionData['Footnote'])) + { + $Element = $this->buildFootnoteElement(); + + $markup .= "\n" . $this->element($Element); + } + + return $markup; + } + + # + # Blocks + # + + # + # Abbreviation + + protected function blockAbbreviation($Line) + { + if (preg_match('/^\*\[(.+?)\]:[ ]*(.+?)[ ]*$/', $Line['text'], $matches)) + { + $this->DefinitionData['Abbreviation'][$matches[1]] = $matches[2]; + + $Block = array( + 'hidden' => true, + ); + + return $Block; + } + } + + # + # Footnote + + protected function blockFootnote($Line) + { + if (preg_match('/^\[\^(.+?)\]:[ ]?(.*)$/', $Line['text'], $matches)) + { + $Block = array( + 'label' => $matches[1], + 'text' => $matches[2], + 'hidden' => true, + ); + + return $Block; + } + } + + protected function blockFootnoteContinue($Line, $Block) + { + if ($Line['text'][0] === '[' and preg_match('/^\[\^(.+?)\]:/', $Line['text'])) + { + return; + } + + if (isset($Block['interrupted'])) + { + if ($Line['indent'] >= 4) + { + $Block['text'] .= "\n\n" . $Line['text']; + + return $Block; + } + } + else + { + $Block['text'] .= "\n" . $Line['text']; + + return $Block; + } + } + + protected function blockFootnoteComplete($Block) + { + $this->DefinitionData['Footnote'][$Block['label']] = array( + 'text' => $Block['text'], + 'count' => null, + 'number' => null, + ); + + return $Block; + } + + # + # Definition List + + protected function blockDefinitionList($Line, $Block) + { + if ( ! isset($Block) or isset($Block['type'])) + { + return; + } + + $Element = array( + 'name' => 'dl', + 'handler' => 'elements', + 'text' => array(), + ); + + $terms = explode("\n", $Block['element']['text']); + + foreach ($terms as $term) + { + $Element['text'] []= array( + 'name' => 'dt', + 'handler' => 'line', + 'text' => $term, + ); + } + + $Block['element'] = $Element; + + $Block = $this->addDdElement($Line, $Block); + + return $Block; + } + + protected function blockDefinitionListContinue($Line, array $Block) + { + if ($Line['text'][0] === ':') + { + $Block = $this->addDdElement($Line, $Block); + + return $Block; + } + else + { + if (isset($Block['interrupted']) and $Line['indent'] === 0) + { + return; + } + + if (isset($Block['interrupted'])) + { + $Block['dd']['handler'] = 'text'; + $Block['dd']['text'] .= "\n\n"; + + unset($Block['interrupted']); + } + + $text = substr($Line['body'], min($Line['indent'], 4)); + + $Block['dd']['text'] .= "\n" . $text; + + return $Block; + } + } + + # + # Header + + protected function blockHeader($Line) + { + $Block = parent::blockHeader($Line); + + if (preg_match('/[ #]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['text'], $matches, PREG_OFFSET_CAPTURE)) + { + $attributeString = $matches[1][0]; + + $Block['element']['attributes'] = $this->parseAttributeData($attributeString); + + $Block['element']['text'] = substr($Block['element']['text'], 0, $matches[0][1]); + } + + return $Block; + } + + # + # Markup + + protected function blockMarkupComplete($Block) + { + if ( ! isset($Block['void'])) + { + $Block['markup'] = $this->processTag($Block['markup']); + } + + return $Block; + } + + # + # Setext + + protected function blockSetextHeader($Line, array $Block = null) + { + $Block = parent::blockSetextHeader($Line, $Block); + + if (preg_match('/[ ]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['text'], $matches, PREG_OFFSET_CAPTURE)) + { + $attributeString = $matches[1][0]; + + $Block['element']['attributes'] = $this->parseAttributeData($attributeString); + + $Block['element']['text'] = substr($Block['element']['text'], 0, $matches[0][1]); + } + + return $Block; + } + + # + # Inline Elements + # + + # + # Footnote Marker + + protected function inlineFootnoteMarker($Excerpt) + { + if (preg_match('/^\[\^(.+?)\]/', $Excerpt['text'], $matches)) + { + $name = $matches[1]; + + if ( ! isset($this->DefinitionData['Footnote'][$name])) + { + return; + } + + $this->DefinitionData['Footnote'][$name]['count'] ++; + + if ( ! isset($this->DefinitionData['Footnote'][$name]['number'])) + { + $this->DefinitionData['Footnote'][$name]['number'] = ++ $this->footnoteCount; # » & + } + + $Element = array( + 'name' => 'sup', + 'attributes' => array('id' => 'fnref'.$this->DefinitionData['Footnote'][$name]['count'].':'.$name), + 'handler' => 'element', + 'text' => array( + 'name' => 'a', + 'attributes' => array('href' => '#fn:'.$name, 'class' => 'footnote-ref'), + 'text' => $this->DefinitionData['Footnote'][$name]['number'], + ), + ); + + return array( + 'extent' => strlen($matches[0]), + 'element' => $Element, + ); + } + } + + private $footnoteCount = 0; + + # + # Link + + protected function inlineLink($Excerpt) + { + $Link = parent::inlineLink($Excerpt); + + $remainder = substr($Excerpt['text'], $Link['extent']); + + if (preg_match('/^[ ]*{('.$this->regexAttribute.'+)}/', $remainder, $matches)) + { + $Link['element']['attributes'] += $this->parseAttributeData($matches[1]); + + $Link['extent'] += strlen($matches[0]); + } + + return $Link; + } + + # + # ~ + # + + protected function unmarkedText($text) + { + $text = parent::unmarkedText($text); + + if (isset($this->DefinitionData['Abbreviation'])) + { + foreach ($this->DefinitionData['Abbreviation'] as $abbreviation => $meaning) + { + $pattern = '/\b'.preg_quote($abbreviation, '/').'\b/'; + + $text = preg_replace($pattern, ''.$abbreviation.'', $text); + } + } + + return $text; + } + + # + # Util Methods + # + + protected function addDdElement(array $Line, array $Block) + { + $text = substr($Line['text'], 1); + $text = trim($text); + + unset($Block['dd']); + + $Block['dd'] = array( + 'name' => 'dd', + 'handler' => 'line', + 'text' => $text, + ); + + if (isset($Block['interrupted'])) + { + $Block['dd']['handler'] = 'text'; + + unset($Block['interrupted']); + } + + $Block['element']['text'] []= & $Block['dd']; + + return $Block; + } + + protected function buildFootnoteElement() + { + $Element = array( + 'name' => 'div', + 'attributes' => array('class' => 'footnotes'), + 'handler' => 'elements', + 'text' => array( + array( + 'name' => 'hr', + ), + array( + 'name' => 'ol', + 'handler' => 'elements', + 'text' => array(), + ), + ), + ); + + uasort($this->DefinitionData['Footnote'], 'self::sortFootnotes'); + + foreach ($this->DefinitionData['Footnote'] as $definitionId => $DefinitionData) + { + if ( ! isset($DefinitionData['number'])) + { + continue; + } + + $text = $DefinitionData['text']; + + $text = parent::text($text); + + $numbers = range(1, $DefinitionData['count']); + + $backLinksMarkup = ''; + + foreach ($numbers as $number) + { + $backLinksMarkup .= ' ↩'; + } + + $backLinksMarkup = substr($backLinksMarkup, 1); + + if (substr($text, - 4) === '

') + { + $backLinksMarkup = ' '.$backLinksMarkup; + + $text = substr_replace($text, $backLinksMarkup.'

', - 4); + } + else + { + $text .= "\n".'

'.$backLinksMarkup.'

'; + } + + $Element['text'][1]['text'] []= array( + 'name' => 'li', + 'attributes' => array('id' => 'fn:'.$definitionId), + 'text' => "\n".$text."\n", + ); + } + + return $Element; + } + + # ~ + + protected function parseAttributeData($attributeString) + { + $Data = array(); + + $attributes = preg_split('/[ ]+/', $attributeString, - 1, PREG_SPLIT_NO_EMPTY); + + foreach ($attributes as $attribute) + { + if ($attribute[0] === '#') + { + $Data['id'] = substr($attribute, 1); + } + else # "." + { + $classes []= substr($attribute, 1); + } + } + + if (isset($classes)) + { + $Data['class'] = implode(' ', $classes); + } + + return $Data; + } + + # ~ + + protected function processTag($elementMarkup) # recursive + { + # http://stackoverflow.com/q/1148928/200145 + libxml_use_internal_errors(true); + + $DOMDocument = new DOMDocument; + + # http://stackoverflow.com/q/11309194/200145 + $elementMarkup = mb_convert_encoding($elementMarkup, 'HTML-ENTITIES', 'UTF-8'); + + # http://stackoverflow.com/q/4879946/200145 + $DOMDocument->loadHTML($elementMarkup); + $DOMDocument->removeChild($DOMDocument->doctype); + $DOMDocument->replaceChild($DOMDocument->firstChild->firstChild->firstChild, $DOMDocument->firstChild); + + $elementText = ''; + + if ($DOMDocument->documentElement->getAttribute('markdown') === '1') + { + foreach ($DOMDocument->documentElement->childNodes as $Node) + { + $elementText .= $DOMDocument->saveHTML($Node); + } + + $DOMDocument->documentElement->removeAttribute('markdown'); + + $elementText = "\n".$this->text($elementText)."\n"; + } + else + { + foreach ($DOMDocument->documentElement->childNodes as $Node) + { + $nodeMarkup = $DOMDocument->saveHTML($Node); + + if ($Node instanceof DOMElement and ! in_array($Node->nodeName, $this->textLevelElements)) + { + $elementText .= $this->processTag($nodeMarkup); + } + else + { + $elementText .= $nodeMarkup; + } + } + } + + # because we don't want for markup to get encoded + $DOMDocument->documentElement->nodeValue = 'placeholder'; + + $markup = $DOMDocument->saveHTML($DOMDocument->documentElement); + $markup = str_replace('placeholder', $elementText, $markup); + + return $markup; + } + + # ~ + + protected function sortFootnotes($A, $B) # callback + { + return $A['number'] - $B['number']; + } + + # + # Fields + # + + protected $regexAttribute = '(?:[#.][-\w]+[ ]*)'; +} + +?>