From 5abbbca5332a4e5f9b8e5fb24a45611df9b874e2 Mon Sep 17 00:00:00 2001 From: Fabio Bas Date: Wed, 12 Feb 2014 15:39:31 +0100 Subject: Dropped Markdown for Parsedown --- framework/3rdParty/Parsedown/LICENSE.txt | 20 + framework/3rdParty/Parsedown/Parsedown.php | 1135 ++++++++++++++++++++++++++++ 2 files changed, 1155 insertions(+) create mode 100644 framework/3rdParty/Parsedown/LICENSE.txt create mode 100755 framework/3rdParty/Parsedown/Parsedown.php (limited to 'framework/3rdParty/Parsedown') diff --git a/framework/3rdParty/Parsedown/LICENSE.txt b/framework/3rdParty/Parsedown/LICENSE.txt new file mode 100644 index 00000000..baca86f5 --- /dev/null +++ b/framework/3rdParty/Parsedown/LICENSE.txt @@ -0,0 +1,20 @@ +The MIT License (MIT) + +Copyright (c) 2013 Emanuil Rusev, erusev.com + +Permission is hereby granted, free of charge, to any person obtaining a copy of +this software and associated documentation files (the "Software"), to deal in +the Software without restriction, including without limitation the rights to +use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of +the Software, and to permit persons to whom the Software is furnished to do so, +subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS +FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR +COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER +IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN +CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. \ No newline at end of file diff --git a/framework/3rdParty/Parsedown/Parsedown.php b/framework/3rdParty/Parsedown/Parsedown.php new file mode 100755 index 00000000..ebc80974 --- /dev/null +++ b/framework/3rdParty/Parsedown/Parsedown.php @@ -0,0 +1,1135 @@ +breaks_enabled = $breaks_enabled; + + return $this; + } + + private $breaks_enabled = false; + + # + # Synopsis + # + + # Markdown is intended to be easy-to-read by humans - those of us who read + # line by line, left to right, top to bottom. In order to take advantage of + # this, Parsedown tries to read in a similar way. It breaks texts into + # lines, it iterates through them and it looks at how they start and relate + # to each other. + + # + # Methods + # + + function parse($text) + { + # standardize line breaks + $text = str_replace("\r\n", "\n", $text); + $text = str_replace("\r", "\n", $text); + + # replace tabs with spaces + $text = str_replace("\t", ' ', $text); + + # remove surrounding line breaks + $text = trim($text, "\n"); + + # split text into lines + $lines = explode("\n", $text); + + # convert lines into html + $text = $this->parse_block_elements($lines); + + # remove trailing line breaks + $text = chop($text, "\n"); + + return $text; + } + + # + # Private + + private function parse_block_elements(array $lines, $context = '') + { + $blocks = array(); + + $block = array( + 'type' => '', + ); + + foreach ($lines as $line) + { + # context + + switch ($block['type']) + { + case 'fenced': + + if ( ! isset($block['closed'])) + { + if (preg_match('/^[ ]*'.$block['fence'][0].'{3,}[ ]*$/', $line)) + { + $block['closed'] = true; + } + else + { + if ($block['text'] !== '') + { + $block['text'] .= "\n"; + } + + $block['text'] .= $line; + } + + continue 2; + } + + break; + + case 'markup': + + if ( ! isset($block['closed'])) + { + if (strpos($line, $block['start']) !== false) # opening tag + { + $block['depth']++; + } + + if (strpos($line, $block['end']) !== false) # closing tag + { + if ($block['depth'] > 0) + { + $block['depth']--; + } + else + { + $block['closed'] = true; + } + } + + $block['text'] .= "\n".$line; + + continue 2; + } + + break; + } + + # ~ + + $indentation = 0; + + while(isset($line[$indentation]) and $line[$indentation] === ' ') + { + $indentation++; + } + + $outdented_line = $indentation > 0 ? ltrim($line) : $line; + + # blank + + if ($outdented_line === '') + { + $block['interrupted'] = true; + + continue; + } + + # context + + switch ($block['type']) + { + case 'quote': + + if ( ! isset($block['interrupted'])) + { + $line = preg_replace('/^[ ]*>[ ]?/', '', $line); + + $block['lines'] []= $line; + + continue 2; + } + + break; + + case 'li': + + if ($block['indentation'] === $indentation and preg_match('/^'.$block['marker'].'[ ]+(.*)/', $outdented_line, $matches)) + { + unset($block['last']); + + $blocks []= $block; + + $block['last'] = true; + $block['lines'] = array($matches[1]); + + unset($block['first']); + unset($block['interrupted']); + + continue 2; + } + + if ( ! isset($block['interrupted'])) + { + $line = preg_replace('/^[ ]{0,'.$block['baseline'].'}/', '', $line); + + $block['lines'] []= $line; + + continue 2; + } + elseif ($line[0] === ' ') + { + $block['lines'] []= ''; + + $line = preg_replace('/^[ ]{0,'.$block['baseline'].'}/', '', $line); + + $block['lines'] []= $line; + + unset($block['interrupted']); + + continue 2; + } + + break; + } + + # indentation sensitive types + + switch ($line[0]) + { + case ' ': + + # code + + if ($indentation >= 4) + { + $code_line = substr($line, 4); + + if ($block['type'] === 'code') + { + if (isset($block['interrupted'])) + { + $block['text'] .= "\n"; + + unset($block['interrupted']); + } + + $block['text'] .= "\n".$code_line; + } + else + { + $blocks []= $block; + + $block = array( + 'type' => 'code', + 'text' => $code_line, + ); + } + + continue 2; + } + + break; + + case '#': + + # atx heading (#) + + if (isset($line[1])) + { + $blocks []= $block; + + $level = 1; + + while (isset($line[$level]) and $line[$level] === '#') + { + $level++; + } + + $block = array( + 'type' => 'heading', + 'text' => trim($line, '# '), + 'level' => $level, + ); + + continue 2; + } + + break; + + case '-': + case '=': + + # setext heading (===) + + if ($block['type'] === 'paragraph' and isset($block['interrupted']) === false) + { + $chopped_line = chop($line); + + $i = 1; + + while (isset($chopped_line[$i])) + { + if ($chopped_line[$i] !== $line[0]) + { + break 2; + } + + $i++; + } + + $block['type'] = 'heading'; + + $block['level'] = $line[0] === '-' ? 2 : 1; + + continue 2; + } + + break; + } + + # indentation insensitive types + + switch ($outdented_line[0]) + { + case '<': + + $position = strpos($outdented_line, '>'); + + if ($position > 1) + { + $substring = substr($outdented_line, 1, $position - 1); + + $substring = chop($substring); + + if (substr($substring, -1) === '/') + { + $is_self_closing = true; + + $substring = substr($substring, 0, -1); + } + + $position = strpos($substring, ' '); + + if ($position) + { + $name = substr($substring, 0, $position); + } + else + { + $name = $substring; + } + + if ( ! ctype_alpha($name)) + { + break; + } + + if (in_array($name, self::$text_level_elements)) + { + break; + } + + $blocks []= $block; + + if (isset($is_self_closing)) + { + $block = array( + 'type' => 'self-closing tag', + 'text' => $outdented_line, + ); + + unset($is_self_closing); + + continue 2; + } + + $block = array( + 'type' => 'markup', + 'text' => $outdented_line, + 'start' => '<'.$name.'>', + 'end' => '', + 'depth' => 0, + ); + + if (strpos($outdented_line, $block['end'])) + { + $block['closed'] = true; + } + + continue 2; + } + + break; + + case '>': + + # quote + + if (preg_match('/^>[ ]?(.*)/', $outdented_line, $matches)) + { + $blocks []= $block; + + $block = array( + 'type' => 'quote', + 'lines' => array( + $matches[1], + ), + ); + + continue 2; + } + + break; + + case '[': + + # reference + + $position = strpos($outdented_line, ']:'); + + if ($position) + { + $reference = array(); + + $label = substr($outdented_line, 1, $position - 1); + $label = strtolower($label); + + $substring = substr($outdented_line, $position + 2); + $substring = trim($substring); + + if ($substring === '') + { + break; + } + + if ($substring[0] === '<') + { + $position = strpos($substring, '>'); + + if ($position === false) + { + break; + } + + $reference['»'] = substr($substring, 1, $position - 1); + + $substring = substr($substring, $position + 1); + } + else + { + $position = strpos($substring, ' '); + + if ($position === false) + { + $reference['»'] = $substring; + + $substring = false; + } + else + { + $reference['»'] = substr($substring, 0, $position); + + $substring = substr($substring, $position + 1); + } + } + + if ($substring !== false) + { + if ($substring[0] !== '"' and $substring[0] !== "'" and $substring[0] !== '(') + { + break; + } + + $last_char = substr($substring, -1); + + if ($last_char !== '"' and $last_char !== "'" and $last_char !== ')') + { + break; + } + + $reference['#'] = substr($substring, 1, -1); + } + + $this->reference_map[$label] = $reference; + + continue 2; + } + + break; + + case '`': + case '~': + + # fenced code block + + if (preg_match('/^([`]{3,}|[~]{3,})[ ]*(\S+)?[ ]*$/', $outdented_line, $matches)) + { + $blocks []= $block; + + $block = array( + 'type' => 'fenced', + 'text' => '', + 'fence' => $matches[1], + ); + + if (isset($matches[2])) + { + $block['language'] = $matches[2]; + } + + continue 2; + } + + break; + + case '*': + case '+': + case '-': + case '_': + + # hr + + if (preg_match('/^([-*_])([ ]{0,2}\1){2,}[ ]*$/', $outdented_line)) + { + $blocks []= $block; + + $block = array( + 'type' => 'rule', + ); + + continue 2; + } + + # li + + if (preg_match('/^([*+-][ ]+)(.*)/', $outdented_line, $matches)) + { + $blocks []= $block; + + $baseline = $indentation + strlen($matches[1]); + + $block = array( + 'type' => 'li', + 'indentation' => $indentation, + 'baseline' => $baseline, + 'marker' => '[*+-]', + 'first' => true, + 'last' => true, + 'lines' => array(), + ); + + $block['lines'] []= preg_replace('/^[ ]{0,4}/', '', $matches[2]); + + continue 2; + } + } + + # li + + if ($outdented_line[0] <= '9' and preg_match('/^(\d+[.][ ]+)(.*)/', $outdented_line, $matches)) + { + $blocks []= $block; + + $baseline = $indentation + strlen($matches[1]); + + $block = array( + 'type' => 'li', + 'indentation' => $indentation, + 'baseline' => $baseline, + 'marker' => '\d+[.]', + 'first' => true, + 'last' => true, + 'ordered' => true, + 'lines' => array(), + ); + + $block['lines'] []= preg_replace('/^[ ]{0,4}/', '', $matches[2]); + + continue; + } + + # paragraph + + if ($block['type'] === 'paragraph') + { + if (isset($block['interrupted'])) + { + $blocks []= $block; + + $block['text'] = $line; + + unset($block['interrupted']); + } + else + { + if ($this->breaks_enabled) + { + $block['text'] .= ' '; + } + + $block['text'] .= "\n".$line; + } + } + else + { + $blocks []= $block; + + $block = array( + 'type' => 'paragraph', + 'text' => $line, + ); + } + } + + $blocks []= $block; + + unset($blocks[0]); + + # $blocks » HTML + + $markup = ''; + + foreach ($blocks as $block) + { + switch ($block['type']) + { + case 'paragraph': + + $text = $this->parse_span_elements($block['text']); + + if ($context === 'li' and $markup === '') + { + if (isset($block['interrupted'])) + { + $markup .= "\n".'

'.$text.'

'."\n"; + } + else + { + $markup .= $text; + + if (isset($blocks[2])) + { + $markup .= "\n"; + } + } + } + else + { + $markup .= '

'.$text.'

'."\n"; + } + + break; + + case 'quote': + + $text = $this->parse_block_elements($block['lines']); + + $markup .= '
'."\n".$text.'
'."\n"; + + break; + + case 'code': + + $text = htmlspecialchars($block['text'], ENT_NOQUOTES, 'UTF-8'); + + $markup .= '
'.$text.'
'."\n"; + + break; + + case 'fenced': + + $text = htmlspecialchars($block['text'], ENT_NOQUOTES, 'UTF-8'); + + $markup .= '
'."\n"; + + break; + + case 'heading': + + $text = $this->parse_span_elements($block['text']); + + $markup .= ''.$text.''."\n"; + + break; + + case 'rule': + + $markup .= '
'."\n"; + + break; + + case 'li': + + if (isset($block['first'])) + { + $type = isset($block['ordered']) ? 'ol' : 'ul'; + + $markup .= '<'.$type.'>'."\n"; + } + + if (isset($block['interrupted']) and ! isset($block['last'])) + { + $block['lines'] []= ''; + } + + $text = $this->parse_block_elements($block['lines'], 'li'); + + $markup .= '
  • '.$text.'
    • '."\n"; + + if (isset($block['last'])) + { + $type = isset($block['ordered']) ? 'ol' : 'ul'; + + $markup .= ''."\n"; + } + + break; + + case 'markup': + + $markup .= $block['text']."\n"; + + break; + + default: + + $markup .= $block['text']."\n"; + } + } + + return $markup; + } + + private function parse_span_elements($text, $markers = array(" \n", '![', '&', '*', '<', '[', '\\', '_', '`', 'http', '~~')) + { + if (isset($text[1]) === false or $markers === array()) + { + return $text; + } + + # ~ + + $markup = ''; + + while ($markers) + { + $closest_marker = null; + $closest_marker_index = 0; + $closest_marker_position = null; + + foreach ($markers as $index => $marker) + { + $marker_position = strpos($text, $marker); + + if ($marker_position === false) + { + unset($markers[$index]); + + continue; + } + + if ($closest_marker === null or $marker_position < $closest_marker_position) + { + $closest_marker = $marker; + $closest_marker_index = $index; + $closest_marker_position = $marker_position; + } + } + + # ~ + + if ($closest_marker === null or isset($text[$closest_marker_position + 1]) === false) + { + $markup .= $text; + + break; + } + else + { + $markup .= substr($text, 0, $closest_marker_position); + } + + $text = substr($text, $closest_marker_position); + + # ~ + + unset($markers[$closest_marker_index]); + + # ~ + + switch ($closest_marker) + { + case " \n": + + $markup .= '
    '."\n"; + + $offset = 3; + + break; + + case '![': + case '[': + + if (strpos($text, ']') and preg_match('/\[((?:[^][]|(?R))*)\]/', $text, $matches)) + { + $element = array( + '!' => $text[0] === '!', + 'a' => $matches[1], + ); + + $offset = strlen($matches[0]); + + if ($element['!']) + { + $offset++; + } + + $remaining_text = substr($text, $offset); + + if ($remaining_text[0] === '(' and preg_match('/\([ ]*(.*?)(?:[ ]+[\'"](.+?)[\'"])?[ ]*\)/', $remaining_text, $matches)) + { + $element['»'] = $matches[1]; + + if (isset($matches[2])) + { + $element['#'] = $matches[2]; + } + + $offset += strlen($matches[0]); + } + elseif ($this->reference_map) + { + $reference = $element['a']; + + if (preg_match('/^\s*\[(.*?)\]/', $remaining_text, $matches)) + { + $reference = $matches[1] ? $matches[1] : $element['a']; + + $offset += strlen($matches[0]); + } + + $reference = strtolower($reference); + + if (isset($this->reference_map[$reference])) + { + $element['»'] = $this->reference_map[$reference]['»']; + + if (isset($this->reference_map[$reference]['#'])) + { + $element['#'] = $this->reference_map[$reference]['#']; + } + } + else + { + unset($element); + } + } + else + { + unset($element); + } + } + + if (isset($element)) + { + $element['»'] = str_replace('&', '&', $element['»']); + $element['»'] = str_replace('<', '<', $element['»']); + + if ($element['!']) + { + $markup .= ''.$element['a'].'parse_span_elements($element['a'], $markers); + + $markup .= ''; + } + + unset($element); + } + else + { + $markup .= $closest_marker; + + $offset = $closest_marker === '![' ? 2 : 1; + } + + break; + + case '&': + + if (preg_match('/^&#?\w+;/', $text, $matches)) + { + $markup .= $matches[0]; + + $offset = strlen($matches[0]); + } + else + { + $markup .= '&'; + + $offset = 1; + } + + break; + + case '*': + case '_': + + if ($text[1] === $closest_marker and preg_match(self::$strong_regex[$closest_marker], $text, $matches)) + { + $markers[] = $closest_marker; + $matches[1] = $this->parse_span_elements($matches[1], $markers); + + $markup .= ''.$matches[1].''; + } + elseif (preg_match(self::$em_regex[$closest_marker], $text, $matches)) + { + $markers[] = $closest_marker; + $matches[1] = $this->parse_span_elements($matches[1], $markers); + + $markup .= ''.$matches[1].''; + } + + if (isset($matches) and $matches) + { + $offset = strlen($matches[0]); + } + else + { + $markup .= $closest_marker; + + $offset = 1; + } + + break; + + case '<': + + if (strpos($text, '>') !== false) + { + if ($text[1] === 'h' and preg_match('/^<(https?:[\/]{2}[^\s]+?)>/i', $text, $matches)) + { + $element_url = $matches[1]; + $element_url = str_replace('&', '&', $element_url); + $element_url = str_replace('<', '<', $element_url); + + $markup .= ''.$element_url.''; + + $offset = strlen($matches[0]); + } + elseif (strpos($text, '@') > 1 and preg_match('/<(\S+?@\S+?)>/', $text, $matches)) + { + $markup .= ''.$matches[1].''; + + $offset = strlen($matches[0]); + } + elseif (preg_match('/^<\/?\w.*?>/', $text, $matches)) + { + $markup .= $matches[0]; + + $offset = strlen($matches[0]); + } + else + { + $markup .= '<'; + + $offset = 1; + } + } + else + { + $markup .= '<'; + + $offset = 1; + } + + break; + + case '\\': + + if (in_array($text[1], self::$special_characters)) + { + $markup .= $text[1]; + + $offset = 2; + } + else + { + $markup .= '\\'; + + $offset = 1; + } + + break; + + case '`': + + if (preg_match('/^(`+)[ ]*(.+?)[ ]*(?'.$element_text.''; + + $offset = strlen($matches[0]); + } + else + { + $markup .= '`'; + + $offset = 1; + } + + break; + + case 'http': + + if (preg_match('/^https?:[\/]{2}[^\s]+\b\/*/ui', $text, $matches)) + { + $element_url = $matches[0]; + $element_url = str_replace('&', '&', $element_url); + $element_url = str_replace('<', '<', $element_url); + + $markup .= ''.$element_url.''; + + $offset = strlen($matches[0]); + } + else + { + $markup .= 'http'; + + $offset = 4; + } + + break; + + case '~~': + + if (preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $text, $matches)) + { + $matches[1] = $this->parse_span_elements($matches[1], $markers); + + $markup .= ''.$matches[1].''; + + $offset = strlen($matches[0]); + } + else + { + $markup .= '~~'; + + $offset = 2; + } + + break; + } + + if (isset($offset)) + { + $text = substr($text, $offset); + } + + $markers[$closest_marker_index] = $closest_marker; + } + + return $markup; + } + + # + # Fields + # + + private $reference_map = array(); + + # + # Read-only + + private static $strong_regex = array( + '*' => '/^[*]{2}((?:[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s', + '_' => '/^__((?:[^_]|_[^_]*_)+?)__(?!_)/us', + ); + + private static $em_regex = array( + '*' => '/^[*]((?:[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', + '_' => '/^_((?:[^_]|__[^_]*__)+?)_(?!_)\b/us', + ); + + private static $special_characters = array( + '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', + ); + + private static $text_level_elements = array( + 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', + 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', + 'i', 'rp', 'sub', 'code', 'strike', 'marquee', + 'q', 'rt', 'sup', 'font', 'strong', + 's', 'tt', 'var', 'mark', + 'u', 'xm', 'wbr', 'nobr', + 'ruby', + 'span', + 'time', + ); +} -- cgit v1.2.3