From 6670711220a59f555778e04e10003f656ba96c24 Mon Sep 17 00:00:00 2001 From: Miraty Date: Tue, 30 May 2023 22:36:40 +0200 Subject: [PATCH] Generate Atom feeds (+ delete Parsedown) --- README.md | 34 +- mkht.php | 369 ++--- parsedown-extra/LICENSE.txt | 20 - parsedown-extra/ParsedownExtra.php | 686 ---------- parsedown-extra/README.md | 31 - parsedown/LICENSE.txt | 20 - parsedown/Parsedown.php | 1994 ---------------------------- parsedown/README.md | 103 -- 8 files changed, 235 insertions(+), 3022 deletions(-) delete mode 100755 parsedown-extra/LICENSE.txt delete mode 100755 parsedown-extra/ParsedownExtra.php delete mode 100755 parsedown-extra/README.md delete mode 100755 parsedown/LICENSE.txt delete mode 100755 parsedown/Parsedown.php delete mode 100755 parsedown/README.md diff --git a/README.md b/README.md index 62b4f04..c23abff 100755 --- a/README.md +++ b/README.md @@ -1,6 +1,8 @@ +# mkht.php + mkht.php is a PHP script for building Gemini, Markdown and HTML/CSS sites from source documents in Gemini, Markdown Extra, HTML, PHP, CSS and Less. -# Usage +## Usage Place your pages tree in `/src/*/*.(gmi|md)`. @@ -16,11 +18,15 @@ Optional files: `destination` is optionnal and can be: * `onion` if you want links ending with .onion when available -# Input +## Input -Pages in `/src`can use Gemini (if using `gmi` extension), Markdown, HTML and PHP. +Pages in `/src` can use Gemini (if using `gmi` extension), Markdown, HTML and PHP. -# Output +Files starting with a dot or not ending in `.gmi`, `.md` or `.html` are ignored. + +Files containing `draft` in their name are ignored for Atom feeds. + +## Output * `/*/*.gmi` (if using `.gmi` extension in /src) * `/*/*.md` @@ -28,24 +34,30 @@ Pages in `/src`can use Gemini (if using `gmi` extension), Markdown, HTML and PHP * `/*/*.gz` Note that format translation is only done in the following order: -Gemini > Markdown > HTML, which means that the last of these formats you will use will be the first that will be readable by hypertext browsers. (PHP is executed before.) +Gemini > Markdown > HTML, which means that the last of these formats you will use will be the first that will be readable by hypertext browsers. (PHP is always executed first.) -# External dependencies +## Data persistence + +IDs are attributed to titles according to their content, therefor modifying a title breaks links to page sections. + +### For atom feeds + +* Make sure modification timestamps of source files are preserved. For example, `cp --preserve=timestamps` must be used instead of just `cp` when backing up or migrating. +* Renaming/moving a page creates a new page and delete the older. + +## External dependencies * PHP * gzip -* find * pandoc -# Internal libraries used +## Internal libraries used | Name | Description | Repository | | --------------- | ---------------------------- | ----------------------------------------- | | less.php | Less compiler in PHP | https://github.com/wikimedia/less.php | -| parsedown | Markdown compiler in PHP | https://github.com/erusev/parsedown | -| parsedown-extra | Extension for Markdown Extra | https://github.com/erusev/parsedown-extra | -# License +## License [AGPLv3+](LICENSE) diff --git a/mkht.php b/mkht.php index acc7552..5705b15 100755 --- a/mkht.php +++ b/mkht.php @@ -1,40 +1,48 @@ #!/usr/bin/php CSS if ($config['css'] == true) { @@ -69,176 +77,223 @@ function clearnetOrOnion($clearnet_url, $onion_url) { return (DESTINATION === 'onion') ? $onion_url : $clearnet_url; } -exec('find ' . SITE . "/src -name '*.gmi' -o -name '*.md'", $pages); +$files = new RecursiveIteratorIterator(new RecursiveDirectoryIterator(SITE . '/src', RecursiveDirectoryIterator::SKIP_DOTS)); -foreach ($pages as $page) { +foreach($files as $file) { + $info = new SplFileInfo($file->getPathName()); + if ($info->getType() !== 'file' OR !in_array($info->getExtension(), ['gmi', 'md', 'html'], true) OR str_starts_with($info->getPathname(), '.')) + continue; + $files_dates[$info->getPathname()] = $info->getMTime(); +} - $pathParts = pathinfo(str_replace('/src', '', $page)); +asort($files_dates); - // Create parent directory if needed - if (!file_exists($pathParts['dirname'])) - mkdir($pathParts['dirname'], 0755, true); +ob_start(); +?> + + + <?= $config['title'] ?> + urn:publicid: +' . LF; +?> + + + + +' . file_get_contents($page)); - file_put_contents($pathParts['dirname'] . '/' . $pathParts['basename'], ob_get_contents()); - ob_end_clean(); +foreach ($files_dates as $src_page => $last_mod) { + $dest_page = str_replace('/src/', '/', $src_page); - // Convert Gemtext to Markdown - if ($pathParts['extension'] === 'gmi') { - $gmilines = explode(LF, file_get_contents($pathParts['dirname'] . '/' . $pathParts['basename'])); + $page_content = file_get_contents($src_page); - foreach ($gmilines as $key => $line) { - if (substr($line, 0, 2) === '=>') { - preg_match('/=> +(.[^ ]+)/', $line, $lnUrl); - preg_match('/=> +.[^ ]+ +(.+)/', $line, $lnTitle); + preg_match('/^# ?(?.*)$/Dm', $page_content, $matches); + $title = $matches['title'] ?? NULL; - $urlPathParts = pathinfo(parse_url($lnUrl[1], PHP_URL_PATH)); + $path_parts = pathinfo($dest_page); - // .gmi > .md for local links - if (!str_contains($lnUrl[1], ':') AND $urlPathParts['extension'] === 'gmi') // If it's a local link - $lnUrl[1] = $urlPathParts['dirname'] . '/' . $urlPathParts['filename'] . '.md'; + $base_filepath = $path_parts['dirname'] . '/' . $path_parts['filename']; - if (isset($lnTitle[1])) { - $gmilines[$key] = '[' . $lnTitle[1] . '](' . $lnUrl[1] . ')'; - } else { - $gmilines[$key] = '[' . $lnUrl[1] . '](' . $lnUrl[1] . ')'; + if (!file_exists($dest_page) OR (filemtime($src_page) > filemtime($dest_page)) OR $opt['force']) { + echo 'Compiling ' . $src_page . ' ' . date("Y-m-d H:i:s", $last_mod) . LF; + + // Create parent directory if needed + if (!file_exists($path_parts['dirname'])) + mkdir($path_parts['dirname'], 0755, true); + + // Execute PHP code + ob_start(); + eval('?>' . $page_content); + file_put_contents($base_filepath . '.gmi', ob_get_contents()); + ob_end_clean(); + + // Convert Gemtext to Markdown + if ($path_parts['extension'] === 'gmi') { + $gmilines = explode(LF, file_get_contents($base_filepath . '.gmi')); + + foreach ($gmilines as $key => $line) { + if (str_starts_with($line, '=>')) { + preg_match('/=> +(.[^ ]+)/', $line, $lnUrl); + preg_match('/=> +.[^ ]+ +(.+)/', $line, $lnTitle); + + $urlPathParts = pathinfo(parse_url($lnUrl[1], PHP_URL_PATH)); + + // .gmi > .md for local links + if (!str_contains($lnUrl[1], ':') AND $urlPathParts['extension'] === 'gmi') // If it's a local link + $lnUrl[1] = $urlPathParts['dirname'] . '/' . $urlPathParts['filename'] . '.md'; + + $gmilines[$key] = '[' . ($lnTitle[1] ?? $lnUrl[1]) . '](' . $lnUrl[1] . ')'; } } + $code = ''; + foreach ($gmilines as $line) + $code .= LF . $line; + file_put_contents($base_filepath . '.md', $code); } - $code = ''; - foreach ($gmilines as $line) { - $code = $code . LF . $line; - } - file_put_contents($pathParts['dirname'] . '/' . $pathParts['filename'] . '.md', $code); - } - // Compile Markdown to HTML - $markdown = file_get_contents($pathParts['dirname'] . '/' . $pathParts['filename'] . '.md'); - if (preg_match("/# (.*)\\n/", $markdown, $matches)) // If a main heading is found - $title = $matches[1]; // Then it will be the HTML page <title> - else - $title = NULL; - if ($use_pandoc) { - $process = proc_open('pandoc --fail-if-warnings -f markdown -t html', [ + // Compile Markdown to HTML + $markdown = file_get_contents($base_filepath . '.md'); + $process = proc_open('pandoc --fail-if-warnings -f markdown_phpextra-citations-native_divs-native_spans+abbreviations+hard_line_breaks+lists_without_preceding_blankline -t html --wrap none', [ 0 => ['pipe', 'r'], 1 => ['pipe', 'w'], ], $pipes); if (is_resource($process) !== true) - exit('Can\'t spawn pandoc.'); + exit('Can\'t spawn pandoc.' . PHP_EOL); fwrite($pipes[0], $markdown); fclose($pipes[0]); - $pageContent = fread($pipes[1], 1000); + $pageContent = stream_get_contents($pipes[1]); fclose($pipes[1]); if (proc_close($process) !== 0) - exit('pandoc failed.'); - } else { - require_once ROOT . '/parsedown/Parsedown.php'; - require_once ROOT . '/parsedown-extra/ParsedownExtra.php'; - $Parsedown = new ParsedownExtra; - $Parsedown = $Parsedown->setUrlsLinked(false); - $Parsedown = $Parsedown->setMarkupEscaped(false); - $Parsedown = $Parsedown->setBreaksEnabled(true); - $pageContent = $Parsedown->text($markdown); - } + exit('pandoc failed.' . PHP_EOL); - // .md > .html for local links - $pageContent = preg_replace('#<a href="(?!.*:)(.*)\.md">#', '<a href="$1.html">', $pageContent); + // .md > .html for local links + $pageContent = preg_replace('#<a href="(?!.*:)(.*)\.md">#', '<a href="$1.html">', $pageContent); - // Add header and footer to HTML - $urlPath = str_replace(SITE, '', $pathParts['dirname']); - $relativePathToRoot = ''; - for ($i = substr_count($urlPath, '/') ; $i > 0 ; $i--) - $relativePathToRoot .= '../'; + $relativePathToRoot = ''; + for ($i = substr_count(str_replace(SITE, '', $path_parts['dirname']), '/') ; $i > 0 ; $i--) + $relativePathToRoot .= '../'; - ob_start(); + ob_start(); -?> - <!DOCTYPE html> - <html lang="<?php + ?> + <!DOCTYPE html> + <html lang="<?php - preg_match('#\.([a-zA-Z-]{2,5})\.#', $pathParts['basename'], $lang); - if (isset($lang[1])) { - echo $lang[1]; - } else { - preg_match('#/([a-z]{2})(/|$)#', $pathParts['dirname'], $lang); - if (isset($lang[1])) - echo $lang[1]; + preg_match('#\.([a-zA-Z-]{2,5})\.#', $path_parts['basename'], $file_lang); + if (isset($file_lang[1])) { + $lang = $file_lang[1]; + } else { + preg_match('#/([a-z]{2})(/|$)#', $path_parts['dirname'], $dir_lang); + $lang = $dir_lang[1] ?? $config['default-lang']; + } + echo $lang ?? ''; + + ?>"> + <head> + <meta charset="utf-8"> + <?php + if (isset($title) AND isset($config['title'])) + echo '<title>' . $title . ' · ' . $config['title'] . ''; + else if (isset($title)) + echo '' . $title . ''; + else if (isset($config['title'])) + echo '' . $config['title'] . ''; + ?> + + + +' . LF; + + if ($config['announce-css']) + echo '' . LF; + + if (file_exists(SITE . '/head.inc.html')) + echo file_get_contents(SITE . '/head.inc.html'); + ?> + + + + +
+ + '; + else + echo $config['site-title']; + ?> + +
+ ' . $pageContent . ''; else - echo $config['defaultLang']; - } + echo '
' . $pageContent . '
'; + if (file_exists(SITE . '/end.inc.html')) + require SITE . '/end.inc.html'; + echo ''; - ?>"> - - - ' . $title . ' · ' . $config['siteTitle'] . ''; - else if (isset($title) AND !is_null($title)) - echo '' . $title . ''; - else if (isset($config['siteTitle'])) - echo '' . $config['siteTitle'] . ''; - ?> - -' . LF; + $pageContent = ob_get_clean(); - if (file_exists(SITE . '/head.inc.html')) - echo file_get_contents(SITE . '/head.inc.html'); -?> - - - - -
- -'; - else - echo $config['siteTitle']; -?> - -
-' . $pageContent . ''; - else - echo '
' . $pageContent . '
'; - if (file_exists(SITE . '/end.inc.html')) - require SITE . '/end.inc.html'; - echo ''; - - $pageContent = ob_get_clean(); - - if (extension_loaded('tidy')) { - $tidy = new tidy; - $tidy->parseString($pageContent, [ + if (extension_loaded('tidy')) { + $pageContent = tidy_repair_string($pageContent, [ 'indent' => true, - 'keep-tabs' => true, - 'wrap' => 0 - ] - ); - $tidy->cleanRepair(); - $pageContent = tidy_get_output($tidy); - } else { - echo 'tidy extension unavailable' . PHP_EOL; + 'indent-spaces' => 4, + 'output-xhtml' => true, + 'wrap' => 0, + ]); + $pageContent = str_replace(' ', ' ', $pageContent); + } + + file_put_contents($base_filepath . '.html', $pageContent); + + // Gzip compression + exec('gzip --keep --fast --force ' . $base_filepath . '.html'); } - file_put_contents($pathParts['dirname'] . '/' . $pathParts['filename'] . '.html', $pageContent); + $relative_addr = substr_replace($base_filepath . '.html', '', strpos($base_filepath, SITE), strlen(SITE)); - // Gzip compression - exec('gzip --keep --fast --force ' . $pathParts['dirname'] . '/' . $pathParts['filename'] . '.html'); -} + // As of RFC 3151: A URN Namespace for Public Identifiers + $public_id = 'urn:publicid:' . $config['id'] . str_replace('/', '%2F', $relative_addr); -ob_start(); + preg_match('#\(?.*)\#s', file_get_contents($base_filepath . '.html'), $match); + $atom_entry_content = $match['content']; + + // Make relative links absolute + $atom_entry_content = preg_replace_callback('# href=\"(?[^:"]+)\"#', function ($matches) { + global $config; + global $path_parts; + + return ' href="' . $config['base-url'][0] . substr($path_parts['dirname'], strlen(SITE)) . '/' . $matches['relative_url'] . '"'; + }, $atom_entry_content); + + if (!in_array('draft', explode('.', $path_parts['basename']), true)) { + ob_start(); +?> + + <?= $title ?> + + +' . LF; +?> + + +' . LF); if ($config['css'] == true) exec('gzip --keep --fast --force ' . SITE . '/css/' . CSS_FILENAME); diff --git a/parsedown-extra/LICENSE.txt b/parsedown-extra/LICENSE.txt deleted file mode 100755 index baca86f..0000000 --- a/parsedown-extra/LICENSE.txt +++ /dev/null @@ -1,20 +0,0 @@ -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/parsedown-extra/ParsedownExtra.php b/parsedown-extra/ParsedownExtra.php deleted file mode 100755 index 8cdb5d2..0000000 --- a/parsedown-extra/ParsedownExtra.php +++ /dev/null @@ -1,686 +0,0 @@ -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) - { - $Elements = $this->textElements($text); - - # convert to markup - $markup = $this->elements($Elements); - - # trim line breaks - $markup = trim($markup, "\n"); - - # 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 $Block['type'] !== 'Paragraph') - { - return; - } - - $Element = array( - 'name' => 'dl', - 'elements' => array(), - ); - - $terms = explode("\n", $Block['element']['handler']['argument']); - - foreach ($terms as $term) - { - $Element['elements'] []= array( - 'name' => 'dt', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $term, - 'destination' => 'elements' - ), - ); - } - - $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']['function'] = 'textElements'; - $Block['dd']['handler']['argument'] .= "\n\n"; - - $Block['dd']['handler']['destination'] = 'elements'; - - unset($Block['interrupted']); - } - - $text = substr($Line['body'], min($Line['indent'], 4)); - - $Block['dd']['handler']['argument'] .= "\n" . $text; - - return $Block; - } - } - - # - # Header - - protected function blockHeader($Line) - { - $Block = parent::blockHeader($Line); - - if ($Block !== null && preg_match('/[ #]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['handler']['argument'], $matches, PREG_OFFSET_CAPTURE)) - { - $attributeString = $matches[1][0]; - - $Block['element']['attributes'] = $this->parseAttributeData($attributeString); - - $Block['element']['handler']['argument'] = substr($Block['element']['handler']['argument'], 0, $matches[0][1]); - } - - return $Block; - } - - # - # Markup - - protected function blockMarkup($Line) - { - if ($this->markupEscaped or $this->safeMode) - { - return; - } - - if (preg_match('/^<(\w[\w-]*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches)) - { - $element = strtolower($matches[1]); - - if (in_array($element, $this->textLevelElements)) - { - return; - } - - $Block = array( - 'name' => $matches[1], - 'depth' => 0, - 'element' => array( - 'rawHtml' => $Line['text'], - 'autobreak' => true, - ), - ); - - $length = strlen($matches[0]); - $remainder = substr($Line['text'], $length); - - if (trim($remainder) === '') - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - $Block['closed'] = true; - $Block['void'] = true; - } - } - else - { - if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) - { - return; - } - if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder)) - { - $Block['closed'] = true; - } - } - - return $Block; - } - } - - protected function blockMarkupContinue($Line, array $Block) - { - if (isset($Block['closed'])) - { - 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'])) - { - $Block['element']['rawHtml'] .= "\n"; - unset($Block['interrupted']); - } - - $Block['element']['rawHtml'] .= "\n".$Line['body']; - - return $Block; - } - - protected function blockMarkupComplete($Block) - { - if ( ! isset($Block['void'])) - { - $Block['element']['rawHtml'] = $this->processTag($Block['element']['rawHtml']); - } - - return $Block; - } - - # - # Setext - - protected function blockSetextHeader($Line, array $Block = null) - { - $Block = parent::blockSetextHeader($Line, $Block); - - if ($Block !== null && preg_match('/[ ]*{('.$this->regexAttribute.'+)}[ ]*$/', $Block['element']['handler']['argument'], $matches, PREG_OFFSET_CAPTURE)) - { - $attributeString = $matches[1][0]; - - $Block['element']['attributes'] = $this->parseAttributeData($attributeString); - - $Block['element']['handler']['argument'] = substr($Block['element']['handler']['argument'], 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), - 'element' => 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 = $Link !== null ? substr($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; - } - - # - # ~ - # - - private $currentAbreviation; - private $currentMeaning; - - protected function insertAbreviation(array $Element) - { - if (isset($Element['text'])) - { - $Element['elements'] = self::pregReplaceElements( - '/\b'.preg_quote($this->currentAbreviation, '/').'\b/', - array( - array( - 'name' => 'abbr', - 'attributes' => array( - 'title' => $this->currentMeaning, - ), - 'text' => $this->currentAbreviation, - ) - ), - $Element['text'] - ); - - unset($Element['text']); - } - - return $Element; - } - - protected function inlineText($text) - { - $Inline = parent::inlineText($text); - - if (isset($this->DefinitionData['Abbreviation'])) - { - foreach ($this->DefinitionData['Abbreviation'] as $abbreviation => $meaning) - { - $this->currentAbreviation = $abbreviation; - $this->currentMeaning = $meaning; - - $Inline['element'] = $this->elementApplyRecursiveDepthFirst( - array($this, 'insertAbreviation'), - $Inline['element'] - ); - } - } - - return $Inline; - } - - # - # 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' => array( - 'function' => 'lineElements', - 'argument' => $text, - 'destination' => 'elements' - ), - ); - - if (isset($Block['interrupted'])) - { - $Block['dd']['handler']['function'] = 'textElements'; - - unset($Block['interrupted']); - } - - $Block['element']['elements'] []= & $Block['dd']; - - return $Block; - } - - protected function buildFootnoteElement() - { - $Element = array( - 'name' => 'div', - 'attributes' => array('class' => 'footnotes'), - 'elements' => array( - array('name' => 'hr'), - array( - 'name' => 'ol', - 'elements' => array(), - ), - ), - ); - - uasort($this->DefinitionData['Footnote'], 'self::sortFootnotes'); - - foreach ($this->DefinitionData['Footnote'] as $definitionId => $DefinitionData) - { - if ( ! isset($DefinitionData['number'])) - { - continue; - } - - $text = $DefinitionData['text']; - - $textElements = parent::textElements($text); - - $numbers = range(1, $DefinitionData['count']); - - $backLinkElements = array(); - - foreach ($numbers as $number) - { - $backLinkElements[] = array('text' => ' '); - $backLinkElements[] = array( - 'name' => 'a', - 'attributes' => array( - 'href' => "#fnref$number:$definitionId", - 'rev' => 'footnote', - 'class' => 'footnote-backref', - ), - 'rawHtml' => '↩', - 'allowRawHtmlInSafeMode' => true, - 'autobreak' => false, - ); - } - - unset($backLinkElements[0]); - - $n = count($textElements) -1; - - if ($textElements[$n]['name'] === 'p') - { - $backLinkElements = array_merge( - array( - array( - 'rawHtml' => ' ', - 'allowRawHtmlInSafeMode' => true, - ), - ), - $backLinkElements - ); - - unset($textElements[$n]['name']); - - $textElements[$n] = array( - 'name' => 'p', - 'elements' => array_merge( - array($textElements[$n]), - $backLinkElements - ), - ); - } - else - { - $textElements[] = array( - 'name' => 'p', - 'elements' => $backLinkElements - ); - } - - $Element['elements'][1]['elements'] []= array( - 'name' => 'li', - 'attributes' => array('id' => 'fn:'.$definitionId), - 'elements' => array_merge( - $textElements - ), - ); - } - - 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\x1A'; - - $markup = $DOMDocument->saveHTML($DOMDocument->documentElement); - $markup = str_replace('placeholder\x1A', $elementText, $markup); - - return $markup; - } - - # ~ - - protected function sortFootnotes($A, $B) # callback - { - return $A['number'] - $B['number']; - } - - # - # Fields - # - - protected $regexAttribute = '(?:[#.][-\w]+[ ]*)'; -} diff --git a/parsedown-extra/README.md b/parsedown-extra/README.md deleted file mode 100755 index cee4b54..0000000 --- a/parsedown-extra/README.md +++ /dev/null @@ -1,31 +0,0 @@ -> You might also like [Caret](http://caret.io?ref=parsedown) - our Markdown editor for the Desktop. - -## Parsedown Extra - -[![Build Status](https://img.shields.io/travis/erusev/parsedown-extra/master.svg?style=flat-square)](https://travis-ci.org/erusev/parsedown-extra) - -An extension of [Parsedown](http://parsedown.org) that adds support for [Markdown Extra](https://michelf.ca/projects/php-markdown/extra/). - -[See Demo](http://parsedown.org/extra/) - -### Installation - -Include both `Parsedown.php` and `ParsedownExtra.php` or install [the composer package](https://packagist.org/packages/erusev/parsedown-extra). - -### Example - -``` php -$Extra = new ParsedownExtra(); - -echo $Extra->text('# Header {.sth}'); # prints:

Header

-``` - -### Questions - -**Who uses Parsedown Extra?** - -[October CMS](http://octobercms.com/), [Bolt CMS](http://bolt.cm/), [Kirby CMS](http://getkirby.com/), [Grav CMS](http://getgrav.org/), [Statamic CMS](http://www.statamic.com/) and [more](https://www.versioneye.com/php/erusev:parsedown-extra/references). - -**How can I help?** - -Use it, star it, share it and in case you feel generous, [donate some money](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=528P3NZQMP8N2). diff --git a/parsedown/LICENSE.txt b/parsedown/LICENSE.txt deleted file mode 100755 index 8e7c764..0000000 --- a/parsedown/LICENSE.txt +++ /dev/null @@ -1,20 +0,0 @@ -The MIT License (MIT) - -Copyright (c) 2013-2018 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. diff --git a/parsedown/Parsedown.php b/parsedown/Parsedown.php deleted file mode 100755 index ae0cbde..0000000 --- a/parsedown/Parsedown.php +++ /dev/null @@ -1,1994 +0,0 @@ -textElements($text); - - # convert to markup - $markup = $this->elements($Elements); - - # trim line breaks - $markup = trim($markup, "\n"); - - return $markup; - } - - protected function textElements($text) - { - # make sure no definitions are set - $this->DefinitionData = array(); - - # standardize line breaks - $text = str_replace(array("\r\n", "\r"), "\n", $text); - - # remove surrounding line breaks - $text = trim($text, "\n"); - - # split text into lines - $lines = explode("\n", $text); - - # iterate through lines to identify blocks - return $this->linesElements($lines); - } - - # - # Setters - # - - function setBreaksEnabled($breaksEnabled) - { - $this->breaksEnabled = $breaksEnabled; - - return $this; - } - - protected $breaksEnabled; - - function setMarkupEscaped($markupEscaped) - { - $this->markupEscaped = $markupEscaped; - - return $this; - } - - protected $markupEscaped; - - function setUrlsLinked($urlsLinked) - { - $this->urlsLinked = $urlsLinked; - - return $this; - } - - protected $urlsLinked = true; - - function setSafeMode($safeMode) - { - $this->safeMode = (bool) $safeMode; - - return $this; - } - - protected $safeMode; - - function setStrictMode($strictMode) - { - $this->strictMode = (bool) $strictMode; - - return $this; - } - - protected $strictMode; - - protected $safeLinksWhitelist = array( - 'http://', - 'https://', - 'ftp://', - 'ftps://', - 'mailto:', - 'tel:', - 'data:image/png;base64,', - 'data:image/gif;base64,', - 'data:image/jpeg;base64,', - 'irc:', - 'ircs:', - 'git:', - 'ssh:', - 'news:', - 'steam:', - ); - - # - # Lines - # - - protected $BlockTypes = array( - '#' => array('Header'), - '*' => array('Rule', 'List'), - '+' => array('List'), - '-' => array('SetextHeader', 'Table', 'Rule', 'List'), - '0' => array('List'), - '1' => array('List'), - '2' => array('List'), - '3' => array('List'), - '4' => array('List'), - '5' => array('List'), - '6' => array('List'), - '7' => array('List'), - '8' => array('List'), - '9' => array('List'), - ':' => array('Table'), - '<' => array('Comment', 'Markup'), - '=' => array('SetextHeader'), - '>' => array('Quote'), - '[' => array('Reference'), - '_' => array('Rule'), - '`' => array('FencedCode'), - '|' => array('Table'), - '~' => array('FencedCode'), - ); - - # ~ - - protected $unmarkedBlockTypes = array( - 'Code', - ); - - # - # Blocks - # - - protected function lines(array $lines) - { - return $this->elements($this->linesElements($lines)); - } - - protected function linesElements(array $lines) - { - $Elements = array(); - $CurrentBlock = null; - - foreach ($lines as $line) - { - if (chop($line) === '') - { - if (isset($CurrentBlock)) - { - $CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted']) - ? $CurrentBlock['interrupted'] + 1 : 1 - ); - } - - continue; - } - - while (($beforeTab = strstr($line, "\t", true)) !== false) - { - $shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4; - - $line = $beforeTab - . str_repeat(' ', $shortage) - . substr($line, strlen($beforeTab) + 1) - ; - } - - $indent = strspn($line, ' '); - - $text = $indent > 0 ? substr($line, $indent) : $line; - - # ~ - - $Line = array('body' => $line, 'indent' => $indent, 'text' => $text); - - # ~ - - if (isset($CurrentBlock['continuable'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Continue'; - $Block = $this->$methodName($Line, $CurrentBlock); - - if (isset($Block)) - { - $CurrentBlock = $Block; - - continue; - } - else - { - if ($this->isBlockCompletable($CurrentBlock['type'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; - $CurrentBlock = $this->$methodName($CurrentBlock); - } - } - } - - # ~ - - $marker = $text[0]; - - # ~ - - $blockTypes = $this->unmarkedBlockTypes; - - if (isset($this->BlockTypes[$marker])) - { - foreach ($this->BlockTypes[$marker] as $blockType) - { - $blockTypes []= $blockType; - } - } - - # - # ~ - - foreach ($blockTypes as $blockType) - { - $Block = $this->{"block$blockType"}($Line, $CurrentBlock); - - if (isset($Block)) - { - $Block['type'] = $blockType; - - if ( ! isset($Block['identified'])) - { - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - $Block['identified'] = true; - } - - if ($this->isBlockContinuable($blockType)) - { - $Block['continuable'] = true; - } - - $CurrentBlock = $Block; - - continue 2; - } - } - - # ~ - - if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph') - { - $Block = $this->paragraphContinue($Line, $CurrentBlock); - } - - if (isset($Block)) - { - $CurrentBlock = $Block; - } - else - { - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - $CurrentBlock = $this->paragraph($Line); - - $CurrentBlock['identified'] = true; - } - } - - # ~ - - if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type'])) - { - $methodName = 'block' . $CurrentBlock['type'] . 'Complete'; - $CurrentBlock = $this->$methodName($CurrentBlock); - } - - # ~ - - if (isset($CurrentBlock)) - { - $Elements[] = $this->extractElement($CurrentBlock); - } - - # ~ - - return $Elements; - } - - protected function extractElement(array $Component) - { - if ( ! isset($Component['element'])) - { - if (isset($Component['markup'])) - { - $Component['element'] = array('rawHtml' => $Component['markup']); - } - elseif (isset($Component['hidden'])) - { - $Component['element'] = array(); - } - } - - return $Component['element']; - } - - protected function isBlockContinuable($Type) - { - return method_exists($this, 'block' . $Type . 'Continue'); - } - - protected function isBlockCompletable($Type) - { - return method_exists($this, 'block' . $Type . 'Complete'); - } - - # - # Code - - protected function blockCode($Line, $Block = null) - { - if (isset($Block) and $Block['type'] === 'Paragraph' and ! isset($Block['interrupted'])) - { - return; - } - - if ($Line['indent'] >= 4) - { - $text = substr($Line['body'], 4); - - $Block = array( - 'element' => array( - 'name' => 'pre', - 'element' => array( - 'name' => 'code', - 'text' => $text, - ), - ), - ); - - return $Block; - } - } - - protected function blockCodeContinue($Line, $Block) - { - if ($Line['indent'] >= 4) - { - if (isset($Block['interrupted'])) - { - $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); - - unset($Block['interrupted']); - } - - $Block['element']['element']['text'] .= "\n"; - - $text = substr($Line['body'], 4); - - $Block['element']['element']['text'] .= $text; - - return $Block; - } - } - - protected function blockCodeComplete($Block) - { - return $Block; - } - - # - # Comment - - protected function blockComment($Line) - { - if ($this->markupEscaped or $this->safeMode) - { - return; - } - - if (strpos($Line['text'], '') !== false) - { - $Block['closed'] = true; - } - - return $Block; - } - } - - protected function blockCommentContinue($Line, array $Block) - { - if (isset($Block['closed'])) - { - return; - } - - $Block['element']['rawHtml'] .= "\n" . $Line['body']; - - if (strpos($Line['text'], '-->') !== false) - { - $Block['closed'] = true; - } - - return $Block; - } - - # - # Fenced Code - - protected function blockFencedCode($Line) - { - $marker = $Line['text'][0]; - - $openerLength = strspn($Line['text'], $marker); - - if ($openerLength < 3) - { - return; - } - - $infostring = trim(substr($Line['text'], $openerLength), "\t "); - - if (strpos($infostring, '`') !== false) - { - return; - } - - $Element = array( - 'name' => 'code', - 'text' => '', - ); - - if ($infostring !== '') - { - /** - * https://www.w3.org/TR/2011/WD-html5-20110525/elements.html#classes - * Every HTML element may have a class attribute specified. - * The attribute, if specified, must have a value that is a set - * of space-separated tokens representing the various classes - * that the element belongs to. - * [...] - * The space characters, for the purposes of this specification, - * are U+0020 SPACE, U+0009 CHARACTER TABULATION (tab), - * U+000A LINE FEED (LF), U+000C FORM FEED (FF), and - * U+000D CARRIAGE RETURN (CR). - */ - $language = substr($infostring, 0, strcspn($infostring, " \t\n\f\r")); - - $Element['attributes'] = array('class' => "language-$language"); - } - - $Block = array( - 'char' => $marker, - 'openerLength' => $openerLength, - 'element' => array( - 'name' => 'pre', - 'element' => $Element, - ), - ); - - return $Block; - } - - protected function blockFencedCodeContinue($Line, $Block) - { - if (isset($Block['complete'])) - { - return; - } - - if (isset($Block['interrupted'])) - { - $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']); - - unset($Block['interrupted']); - } - - if (($len = strspn($Line['text'], $Block['char'])) >= $Block['openerLength'] - and chop(substr($Line['text'], $len), ' ') === '' - ) { - $Block['element']['element']['text'] = substr($Block['element']['element']['text'], 1); - - $Block['complete'] = true; - - return $Block; - } - - $Block['element']['element']['text'] .= "\n" . $Line['body']; - - return $Block; - } - - protected function blockFencedCodeComplete($Block) - { - return $Block; - } - - # - # Header - - protected function blockHeader($Line) - { - $level = strspn($Line['text'], '#'); - - if ($level > 6) - { - return; - } - - $text = trim($Line['text'], '#'); - - if ($this->strictMode and isset($text[0]) and $text[0] !== ' ') - { - return; - } - - $text = trim($text, ' '); - - $Block = array( - 'element' => array( - 'name' => 'h' . $level, - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $text, - 'destination' => 'elements', - ) - ), - ); - - return $Block; - } - - # - # List - - protected function blockList($Line, array $CurrentBlock = null) - { - list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]'); - - if (preg_match('/^('.$pattern.'([ ]++|$))(.*+)/', $Line['text'], $matches)) - { - $contentIndent = strlen($matches[2]); - - if ($contentIndent >= 5) - { - $contentIndent -= 1; - $matches[1] = substr($matches[1], 0, -$contentIndent); - $matches[3] = str_repeat(' ', $contentIndent) . $matches[3]; - } - elseif ($contentIndent === 0) - { - $matches[1] .= ' '; - } - - $markerWithoutWhitespace = strstr($matches[1], ' ', true); - - $Block = array( - 'indent' => $Line['indent'], - 'pattern' => $pattern, - 'data' => array( - 'type' => $name, - 'marker' => $matches[1], - 'markerType' => ($name === 'ul' ? $markerWithoutWhitespace : substr($markerWithoutWhitespace, -1)), - ), - 'element' => array( - 'name' => $name, - 'elements' => array(), - ), - ); - $Block['data']['markerTypeRegex'] = preg_quote($Block['data']['markerType'], '/'); - - if ($name === 'ol') - { - $listStart = ltrim(strstr($matches[1], $Block['data']['markerType'], true), '0') ?: '0'; - - if ($listStart !== '1') - { - if ( - isset($CurrentBlock) - and $CurrentBlock['type'] === 'Paragraph' - and ! isset($CurrentBlock['interrupted']) - ) { - return; - } - - $Block['element']['attributes'] = array('start' => $listStart); - } - } - - $Block['li'] = array( - 'name' => 'li', - 'handler' => array( - 'function' => 'li', - 'argument' => !empty($matches[3]) ? array($matches[3]) : array(), - 'destination' => 'elements' - ) - ); - - $Block['element']['elements'] []= & $Block['li']; - - return $Block; - } - } - - protected function blockListContinue($Line, array $Block) - { - if (isset($Block['interrupted']) and empty($Block['li']['handler']['argument'])) - { - return null; - } - - $requiredIndent = ($Block['indent'] + strlen($Block['data']['marker'])); - - if ($Line['indent'] < $requiredIndent - and ( - ( - $Block['data']['type'] === 'ol' - and preg_match('/^[0-9]++'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) - ) or ( - $Block['data']['type'] === 'ul' - and preg_match('/^'.$Block['data']['markerTypeRegex'].'(?:[ ]++(.*)|$)/', $Line['text'], $matches) - ) - ) - ) { - if (isset($Block['interrupted'])) - { - $Block['li']['handler']['argument'] []= ''; - - $Block['loose'] = true; - - unset($Block['interrupted']); - } - - unset($Block['li']); - - $text = isset($matches[1]) ? $matches[1] : ''; - - $Block['indent'] = $Line['indent']; - - $Block['li'] = array( - 'name' => 'li', - 'handler' => array( - 'function' => 'li', - 'argument' => array($text), - 'destination' => 'elements' - ) - ); - - $Block['element']['elements'] []= & $Block['li']; - - return $Block; - } - elseif ($Line['indent'] < $requiredIndent and $this->blockList($Line)) - { - return null; - } - - if ($Line['text'][0] === '[' and $this->blockReference($Line)) - { - return $Block; - } - - if ($Line['indent'] >= $requiredIndent) - { - if (isset($Block['interrupted'])) - { - $Block['li']['handler']['argument'] []= ''; - - $Block['loose'] = true; - - unset($Block['interrupted']); - } - - $text = substr($Line['body'], $requiredIndent); - - $Block['li']['handler']['argument'] []= $text; - - return $Block; - } - - if ( ! isset($Block['interrupted'])) - { - $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']); - - $Block['li']['handler']['argument'] []= $text; - - return $Block; - } - } - - protected function blockListComplete(array $Block) - { - if (isset($Block['loose'])) - { - foreach ($Block['element']['elements'] as &$li) - { - if (end($li['handler']['argument']) !== '') - { - $li['handler']['argument'] []= ''; - } - } - } - - return $Block; - } - - # - # Quote - - protected function blockQuote($Line) - { - if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) - { - $Block = array( - 'element' => array( - 'name' => 'blockquote', - 'handler' => array( - 'function' => 'linesElements', - 'argument' => (array) $matches[1], - 'destination' => 'elements', - ) - ), - ); - - return $Block; - } - } - - protected function blockQuoteContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches)) - { - $Block['element']['handler']['argument'] []= $matches[1]; - - return $Block; - } - - if ( ! isset($Block['interrupted'])) - { - $Block['element']['handler']['argument'] []= $Line['text']; - - return $Block; - } - } - - # - # Rule - - protected function blockRule($Line) - { - $marker = $Line['text'][0]; - - if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '') - { - $Block = array( - 'element' => array( - 'name' => 'hr', - ), - ); - - return $Block; - } - } - - # - # Setext - - protected function blockSetextHeader($Line, array $Block = null) - { - if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) - { - return; - } - - if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '') - { - $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; - - return $Block; - } - } - - # - # Markup - - protected function blockMarkup($Line) - { - if ($this->markupEscaped or $this->safeMode) - { - return; - } - - if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches)) - { - $element = strtolower($matches[1]); - - if (in_array($element, $this->textLevelElements)) - { - return; - } - - $Block = array( - 'name' => $matches[1], - 'element' => array( - 'rawHtml' => $Line['text'], - 'autobreak' => true, - ), - ); - - return $Block; - } - } - - protected function blockMarkupContinue($Line, array $Block) - { - if (isset($Block['closed']) or isset($Block['interrupted'])) - { - return; - } - - $Block['element']['rawHtml'] .= "\n" . $Line['body']; - - return $Block; - } - - # - # Reference - - protected function blockReference($Line) - { - if (strpos($Line['text'], ']') !== false - and preg_match('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches) - ) { - $id = strtolower($matches[1]); - - $Data = array( - 'url' => $matches[2], - 'title' => isset($matches[3]) ? $matches[3] : null, - ); - - $this->DefinitionData['Reference'][$id] = $Data; - - $Block = array( - 'element' => array(), - ); - - return $Block; - } - } - - # - # Table - - protected function blockTable($Line, array $Block = null) - { - if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted'])) - { - return; - } - - if ( - strpos($Block['element']['handler']['argument'], '|') === false - and strpos($Line['text'], '|') === false - and strpos($Line['text'], ':') === false - or strpos($Block['element']['handler']['argument'], "\n") !== false - ) { - return; - } - - if (chop($Line['text'], ' -:|') !== '') - { - return; - } - - $alignments = array(); - - $divider = $Line['text']; - - $divider = trim($divider); - $divider = trim($divider, '|'); - - $dividerCells = explode('|', $divider); - - foreach ($dividerCells as $dividerCell) - { - $dividerCell = trim($dividerCell); - - if ($dividerCell === '') - { - return; - } - - $alignment = null; - - if ($dividerCell[0] === ':') - { - $alignment = 'left'; - } - - if (substr($dividerCell, - 1) === ':') - { - $alignment = $alignment === 'left' ? 'center' : 'right'; - } - - $alignments []= $alignment; - } - - # ~ - - $HeaderElements = array(); - - $header = $Block['element']['handler']['argument']; - - $header = trim($header); - $header = trim($header, '|'); - - $headerCells = explode('|', $header); - - if (count($headerCells) !== count($alignments)) - { - return; - } - - foreach ($headerCells as $index => $headerCell) - { - $headerCell = trim($headerCell); - - $HeaderElement = array( - 'name' => 'th', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $headerCell, - 'destination' => 'elements', - ) - ); - - if (isset($alignments[$index])) - { - $alignment = $alignments[$index]; - - $HeaderElement['attributes'] = array( - 'style' => "text-align: $alignment;", - ); - } - - $HeaderElements []= $HeaderElement; - } - - # ~ - - $Block = array( - 'alignments' => $alignments, - 'identified' => true, - 'element' => array( - 'name' => 'table', - 'elements' => array(), - ), - ); - - $Block['element']['elements'] []= array( - 'name' => 'thead', - ); - - $Block['element']['elements'] []= array( - 'name' => 'tbody', - 'elements' => array(), - ); - - $Block['element']['elements'][0]['elements'] []= array( - 'name' => 'tr', - 'elements' => $HeaderElements, - ); - - return $Block; - } - - protected function blockTableContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|')) - { - $Elements = array(); - - $row = $Line['text']; - - $row = trim($row); - $row = trim($row, '|'); - - preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches); - - $cells = array_slice($matches[0], 0, count($Block['alignments'])); - - foreach ($cells as $index => $cell) - { - $cell = trim($cell); - - $Element = array( - 'name' => 'td', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $cell, - 'destination' => 'elements', - ) - ); - - if (isset($Block['alignments'][$index])) - { - $Element['attributes'] = array( - 'style' => 'text-align: ' . $Block['alignments'][$index] . ';', - ); - } - - $Elements []= $Element; - } - - $Element = array( - 'name' => 'tr', - 'elements' => $Elements, - ); - - $Block['element']['elements'][1]['elements'] []= $Element; - - return $Block; - } - } - - # - # ~ - # - - protected function paragraph($Line) - { - return array( - 'type' => 'Paragraph', - 'element' => array( - 'name' => 'p', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $Line['text'], - 'destination' => 'elements', - ), - ), - ); - } - - protected function paragraphContinue($Line, array $Block) - { - if (isset($Block['interrupted'])) - { - return; - } - - $Block['element']['handler']['argument'] .= "\n".$Line['text']; - - return $Block; - } - - # - # Inline Elements - # - - protected $InlineTypes = array( - '!' => array('Image'), - '&' => array('SpecialCharacter'), - '*' => array('Emphasis'), - ':' => array('Url'), - '<' => array('UrlTag', 'EmailTag', 'Markup'), - '[' => array('Link'), - '_' => array('Emphasis'), - '`' => array('Code'), - '~' => array('Strikethrough'), - '\\' => array('EscapeSequence'), - ); - - # ~ - - protected $inlineMarkerList = '!*_&[:<`~\\'; - - # - # ~ - # - - public function line($text, $nonNestables = array()) - { - return $this->elements($this->lineElements($text, $nonNestables)); - } - - protected function lineElements($text, $nonNestables = array()) - { - # standardize line breaks - $text = str_replace(array("\r\n", "\r"), "\n", $text); - - $Elements = array(); - - $nonNestables = (empty($nonNestables) - ? array() - : array_combine($nonNestables, $nonNestables) - ); - - # $excerpt is based on the first occurrence of a marker - - while ($excerpt = strpbrk($text, $this->inlineMarkerList)) - { - $marker = $excerpt[0]; - - $markerPosition = strlen($text) - strlen($excerpt); - - $Excerpt = array('text' => $excerpt, 'context' => $text); - - foreach ($this->InlineTypes[$marker] as $inlineType) - { - # check to see if the current inline type is nestable in the current context - - if (isset($nonNestables[$inlineType])) - { - continue; - } - - $Inline = $this->{"inline$inlineType"}($Excerpt); - - if ( ! isset($Inline)) - { - continue; - } - - # makes sure that the inline belongs to "our" marker - - if (isset($Inline['position']) and $Inline['position'] > $markerPosition) - { - continue; - } - - # sets a default inline position - - if ( ! isset($Inline['position'])) - { - $Inline['position'] = $markerPosition; - } - - # cause the new element to 'inherit' our non nestables - - - $Inline['element']['nonNestables'] = isset($Inline['element']['nonNestables']) - ? array_merge($Inline['element']['nonNestables'], $nonNestables) - : $nonNestables - ; - - # the text that comes before the inline - $unmarkedText = substr($text, 0, $Inline['position']); - - # compile the unmarked text - $InlineText = $this->inlineText($unmarkedText); - $Elements[] = $InlineText['element']; - - # compile the inline - $Elements[] = $this->extractElement($Inline); - - # remove the examined text - $text = substr($text, $Inline['position'] + $Inline['extent']); - - continue 2; - } - - # the marker does not belong to an inline - - $unmarkedText = substr($text, 0, $markerPosition + 1); - - $InlineText = $this->inlineText($unmarkedText); - $Elements[] = $InlineText['element']; - - $text = substr($text, $markerPosition + 1); - } - - $InlineText = $this->inlineText($text); - $Elements[] = $InlineText['element']; - - foreach ($Elements as &$Element) - { - if ( ! isset($Element['autobreak'])) - { - $Element['autobreak'] = false; - } - } - - return $Elements; - } - - # - # ~ - # - - protected function inlineText($text) - { - $Inline = array( - 'extent' => strlen($text), - 'element' => array(), - ); - - $Inline['element']['elements'] = self::pregReplaceElements( - $this->breaksEnabled ? '/[ ]*+\n/' : '/(?:[ ]*+\\\\|[ ]{2,}+)\n/', - array( - array('name' => 'br'), - array('text' => "\n"), - ), - $text - ); - - return $Inline; - } - - protected function inlineCode($Excerpt) - { - $marker = $Excerpt['text'][0]; - - if (preg_match('/^(['.$marker.']++)[ ]*+(.+?)[ ]*+(? strlen($matches[0]), - 'element' => array( - 'name' => 'code', - 'text' => $text, - ), - ); - } - } - - protected function inlineEmailTag($Excerpt) - { - $hostnameLabel = '[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?'; - - $commonMarkEmail = '[a-zA-Z0-9.!#$%&\'*+\/=?^_`{|}~-]++@' - . $hostnameLabel . '(?:\.' . $hostnameLabel . ')*'; - - if (strpos($Excerpt['text'], '>') !== false - and preg_match("/^<((mailto:)?$commonMarkEmail)>/i", $Excerpt['text'], $matches) - ){ - $url = $matches[1]; - - if ( ! isset($matches[2])) - { - $url = "mailto:$url"; - } - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'a', - 'text' => $matches[1], - 'attributes' => array( - 'href' => $url, - ), - ), - ); - } - } - - protected function inlineEmphasis($Excerpt) - { - if ( ! isset($Excerpt['text'][1])) - { - return; - } - - $marker = $Excerpt['text'][0]; - - if ($Excerpt['text'][1] === $marker and preg_match($this->StrongRegex[$marker], $Excerpt['text'], $matches)) - { - $emphasis = 'strong'; - } - elseif (preg_match($this->EmRegex[$marker], $Excerpt['text'], $matches)) - { - $emphasis = 'em'; - } - else - { - return; - } - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => $emphasis, - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $matches[1], - 'destination' => 'elements', - ) - ), - ); - } - - protected function inlineEscapeSequence($Excerpt) - { - if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters)) - { - return array( - 'element' => array('rawHtml' => $Excerpt['text'][1]), - 'extent' => 2, - ); - } - } - - protected function inlineImage($Excerpt) - { - if ( ! isset($Excerpt['text'][1]) or $Excerpt['text'][1] !== '[') - { - return; - } - - $Excerpt['text']= substr($Excerpt['text'], 1); - - $Link = $this->inlineLink($Excerpt); - - if ($Link === null) - { - return; - } - - $Inline = array( - 'extent' => $Link['extent'] + 1, - 'element' => array( - 'name' => 'img', - 'attributes' => array( - 'src' => $Link['element']['attributes']['href'], - 'alt' => $Link['element']['handler']['argument'], - ), - 'autobreak' => true, - ), - ); - - $Inline['element']['attributes'] += $Link['element']['attributes']; - - unset($Inline['element']['attributes']['href']); - - return $Inline; - } - - protected function inlineLink($Excerpt) - { - $Element = array( - 'name' => 'a', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => null, - 'destination' => 'elements', - ), - 'nonNestables' => array('Url', 'Link'), - 'attributes' => array( - 'href' => null, - 'title' => null, - ), - ); - - $extent = 0; - - $remainder = $Excerpt['text']; - - if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches)) - { - $Element['handler']['argument'] = $matches[1]; - - $extent += strlen($matches[0]); - - $remainder = substr($remainder, $extent); - } - else - { - return; - } - - if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*+"|\'[^\']*+\'))?\s*+[)]/', $remainder, $matches)) - { - $Element['attributes']['href'] = $matches[1]; - - if (isset($matches[2])) - { - $Element['attributes']['title'] = substr($matches[2], 1, - 1); - } - - $extent += strlen($matches[0]); - } - else - { - if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) - { - $definition = strlen($matches[1]) ? $matches[1] : $Element['handler']['argument']; - $definition = strtolower($definition); - - $extent += strlen($matches[0]); - } - else - { - $definition = strtolower($Element['handler']['argument']); - } - - if ( ! isset($this->DefinitionData['Reference'][$definition])) - { - return; - } - - $Definition = $this->DefinitionData['Reference'][$definition]; - - $Element['attributes']['href'] = $Definition['url']; - $Element['attributes']['title'] = $Definition['title']; - } - - return array( - 'extent' => $extent, - 'element' => $Element, - ); - } - - protected function inlineMarkup($Excerpt) - { - if ($this->markupEscaped or $this->safeMode or strpos($Excerpt['text'], '>') === false) - { - return; - } - - if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*+[ ]*+>/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - - if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - - if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches)) - { - return array( - 'element' => array('rawHtml' => $matches[0]), - 'extent' => strlen($matches[0]), - ); - } - } - - protected function inlineSpecialCharacter($Excerpt) - { - if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false - and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches) - ) { - return array( - 'element' => array('rawHtml' => '&' . $matches[1] . ';'), - 'extent' => strlen($matches[0]), - ); - } - - return; - } - - protected function inlineStrikethrough($Excerpt) - { - if ( ! isset($Excerpt['text'][1])) - { - return; - } - - if ($Excerpt['text'][1] === '~' and preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $Excerpt['text'], $matches)) - { - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'del', - 'handler' => array( - 'function' => 'lineElements', - 'argument' => $matches[1], - 'destination' => 'elements', - ) - ), - ); - } - } - - protected function inlineUrl($Excerpt) - { - if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/') - { - return; - } - - if (strpos($Excerpt['context'], 'http') !== false - and preg_match('/\bhttps?+:[\/]{2}[^\s<]+\b\/*+/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE) - ) { - $url = $matches[0][0]; - - $Inline = array( - 'extent' => strlen($matches[0][0]), - 'position' => $matches[0][1], - 'element' => array( - 'name' => 'a', - 'text' => $url, - 'attributes' => array( - 'href' => $url, - ), - ), - ); - - return $Inline; - } - } - - protected function inlineUrlTag($Excerpt) - { - if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches)) - { - $url = $matches[1]; - - return array( - 'extent' => strlen($matches[0]), - 'element' => array( - 'name' => 'a', - 'text' => $url, - 'attributes' => array( - 'href' => $url, - ), - ), - ); - } - } - - # ~ - - protected function unmarkedText($text) - { - $Inline = $this->inlineText($text); - return $this->element($Inline['element']); - } - - # - # Handlers - # - - protected function handle(array $Element) - { - if (isset($Element['handler'])) - { - if (!isset($Element['nonNestables'])) - { - $Element['nonNestables'] = array(); - } - - if (is_string($Element['handler'])) - { - $function = $Element['handler']; - $argument = $Element['text']; - unset($Element['text']); - $destination = 'rawHtml'; - } - else - { - $function = $Element['handler']['function']; - $argument = $Element['handler']['argument']; - $destination = $Element['handler']['destination']; - } - - $Element[$destination] = $this->{$function}($argument, $Element['nonNestables']); - - if ($destination === 'handler') - { - $Element = $this->handle($Element); - } - - unset($Element['handler']); - } - - return $Element; - } - - protected function handleElementRecursive(array $Element) - { - return $this->elementApplyRecursive(array($this, 'handle'), $Element); - } - - protected function handleElementsRecursive(array $Elements) - { - return $this->elementsApplyRecursive(array($this, 'handle'), $Elements); - } - - protected function elementApplyRecursive($closure, array $Element) - { - $Element = call_user_func($closure, $Element); - - if (isset($Element['elements'])) - { - $Element['elements'] = $this->elementsApplyRecursive($closure, $Element['elements']); - } - elseif (isset($Element['element'])) - { - $Element['element'] = $this->elementApplyRecursive($closure, $Element['element']); - } - - return $Element; - } - - protected function elementApplyRecursiveDepthFirst($closure, array $Element) - { - if (isset($Element['elements'])) - { - $Element['elements'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['elements']); - } - elseif (isset($Element['element'])) - { - $Element['element'] = $this->elementsApplyRecursiveDepthFirst($closure, $Element['element']); - } - - $Element = call_user_func($closure, $Element); - - return $Element; - } - - protected function elementsApplyRecursive($closure, array $Elements) - { - foreach ($Elements as &$Element) - { - $Element = $this->elementApplyRecursive($closure, $Element); - } - - return $Elements; - } - - protected function elementsApplyRecursiveDepthFirst($closure, array $Elements) - { - foreach ($Elements as &$Element) - { - $Element = $this->elementApplyRecursiveDepthFirst($closure, $Element); - } - - return $Elements; - } - - protected function element(array $Element) - { - if ($this->safeMode) - { - $Element = $this->sanitiseElement($Element); - } - - # identity map if element has no handler - $Element = $this->handle($Element); - - $hasName = isset($Element['name']); - - $markup = ''; - - if ($hasName) - { - $markup .= '<' . $Element['name']; - - if (isset($Element['attributes'])) - { - foreach ($Element['attributes'] as $name => $value) - { - if ($value === null) - { - continue; - } - - $markup .= " $name=\"".self::escape($value).'"'; - } - } - } - - $permitRawHtml = false; - - if (isset($Element['text'])) - { - $text = $Element['text']; - } - // very strongly consider an alternative if you're writing an - // extension - elseif (isset($Element['rawHtml'])) - { - $text = $Element['rawHtml']; - - $allowRawHtmlInSafeMode = isset($Element['allowRawHtmlInSafeMode']) && $Element['allowRawHtmlInSafeMode']; - $permitRawHtml = !$this->safeMode || $allowRawHtmlInSafeMode; - } - - $hasContent = isset($text) || isset($Element['element']) || isset($Element['elements']); - - if ($hasContent) - { - $markup .= $hasName ? '>' : ''; - - if (isset($Element['elements'])) - { - $markup .= $this->elements($Element['elements']); - } - elseif (isset($Element['element'])) - { - $markup .= $this->element($Element['element']); - } - else - { - if (!$permitRawHtml) - { - $markup .= self::escape($text, true); - } - else - { - $markup .= $text; - } - } - - $markup .= $hasName ? '' : ''; - } - elseif ($hasName) - { - $markup .= ' />'; - } - - return $markup; - } - - protected function elements(array $Elements) - { - $markup = ''; - - $autoBreak = true; - - foreach ($Elements as $Element) - { - if (empty($Element)) - { - continue; - } - - $autoBreakNext = (isset($Element['autobreak']) - ? $Element['autobreak'] : isset($Element['name']) - ); - // (autobreak === false) covers both sides of an element - $autoBreak = !$autoBreak ? $autoBreak : $autoBreakNext; - - $markup .= ($autoBreak ? "\n" : '') . $this->element($Element); - $autoBreak = $autoBreakNext; - } - - $markup .= $autoBreak ? "\n" : ''; - - return $markup; - } - - # ~ - - protected function li($lines) - { - $Elements = $this->linesElements($lines); - - if ( ! in_array('', $lines) - and isset($Elements[0]) and isset($Elements[0]['name']) - and $Elements[0]['name'] === 'p' - ) { - unset($Elements[0]['name']); - } - - return $Elements; - } - - # - # AST Convenience - # - - /** - * Replace occurrences $regexp with $Elements in $text. Return an array of - * elements representing the replacement. - */ - protected static function pregReplaceElements($regexp, $Elements, $text) - { - $newElements = array(); - - while (preg_match($regexp, $text, $matches, PREG_OFFSET_CAPTURE)) - { - $offset = $matches[0][1]; - $before = substr($text, 0, $offset); - $after = substr($text, $offset + strlen($matches[0][0])); - - $newElements[] = array('text' => $before); - - foreach ($Elements as $Element) - { - $newElements[] = $Element; - } - - $text = $after; - } - - $newElements[] = array('text' => $text); - - return $newElements; - } - - # - # Deprecated Methods - # - - function parse($text) - { - $markup = $this->text($text); - - return $markup; - } - - protected function sanitiseElement(array $Element) - { - static $goodAttribute = '/^[a-zA-Z0-9][a-zA-Z0-9-_]*+$/'; - static $safeUrlNameToAtt = array( - 'a' => 'href', - 'img' => 'src', - ); - - if ( ! isset($Element['name'])) - { - unset($Element['attributes']); - return $Element; - } - - if (isset($safeUrlNameToAtt[$Element['name']])) - { - $Element = $this->filterUnsafeUrlInAttribute($Element, $safeUrlNameToAtt[$Element['name']]); - } - - if ( ! empty($Element['attributes'])) - { - foreach ($Element['attributes'] as $att => $val) - { - # filter out badly parsed attribute - if ( ! preg_match($goodAttribute, $att)) - { - unset($Element['attributes'][$att]); - } - # dump onevent attribute - elseif (self::striAtStart($att, 'on')) - { - unset($Element['attributes'][$att]); - } - } - } - - return $Element; - } - - protected function filterUnsafeUrlInAttribute(array $Element, $attribute) - { - foreach ($this->safeLinksWhitelist as $scheme) - { - if (self::striAtStart($Element['attributes'][$attribute], $scheme)) - { - return $Element; - } - } - - $Element['attributes'][$attribute] = str_replace(':', '%3A', $Element['attributes'][$attribute]); - - return $Element; - } - - # - # Static Methods - # - - protected static function escape($text, $allowQuotes = false) - { - return htmlspecialchars($text, $allowQuotes ? ENT_NOQUOTES : ENT_QUOTES, 'UTF-8'); - } - - protected static function striAtStart($string, $needle) - { - $len = strlen($needle); - - if ($len > strlen($string)) - { - return false; - } - else - { - return strtolower(substr($string, 0, $len)) === strtolower($needle); - } - } - - static function instance($name = 'default') - { - if (isset(self::$instances[$name])) - { - return self::$instances[$name]; - } - - $instance = new static(); - - self::$instances[$name] = $instance; - - return $instance; - } - - private static $instances = array(); - - # - # Fields - # - - protected $DefinitionData; - - # - # Read-Only - - protected $specialCharacters = array( - '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~' - ); - - protected $StrongRegex = array( - '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s', - '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us', - ); - - protected $EmRegex = array( - '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', - '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', - ); - - protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*+(?:\s*+=\s*+(?:[^"\'=<>`\s]+|"[^"]*+"|\'[^\']*+\'))?+'; - - protected $voidElements = array( - 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', - ); - - protected $textLevelElements = array( - 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', - 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', - 'i', 'rp', 'del', 'code', 'strike', 'marquee', - 'q', 'rt', 'ins', 'font', 'strong', - 's', 'tt', 'kbd', 'mark', - 'u', 'xm', 'sub', 'nobr', - 'sup', 'ruby', - 'var', 'span', - 'wbr', 'time', - ); -} diff --git a/parsedown/README.md b/parsedown/README.md deleted file mode 100755 index a4b8c63..0000000 --- a/parsedown/README.md +++ /dev/null @@ -1,103 +0,0 @@ - - -

Parsedown

- -

Parsedown

- -[![Build Status](https://travis-ci.org/erusev/parsedown.svg)](https://travis-ci.org/erusev/parsedown) -[![Total Downloads](https://poser.pugx.org/erusev/parsedown/d/total.svg)](https://packagist.org/packages/erusev/parsedown) -[![Version](https://poser.pugx.org/erusev/parsedown/v/stable.svg)](https://packagist.org/packages/erusev/parsedown) -[![License](https://poser.pugx.org/erusev/parsedown/license.svg)](https://packagist.org/packages/erusev/parsedown) - -Better Markdown Parser in PHP - Demo. - -## Features - -* One File -* No Dependencies -* [Super Fast](http://parsedown.org/speed) -* Extensible -* [GitHub flavored](https://github.github.com/gfm) -* [Tested](http://parsedown.org/tests/) in 5.3 to 7.3 -* [Markdown Extra extension](https://github.com/erusev/parsedown-extra) - -## Installation - -Install the [composer package]: - - composer require erusev/parsedown - -Or download the [latest release] and include `Parsedown.php` - -[composer package]: https://packagist.org/packages/erusev/parsedown "The Parsedown package on packagist.org" -[latest release]: https://github.com/erusev/parsedown/releases/latest "The latest release of Parsedown" - -## Example - -```php -$Parsedown = new Parsedown(); - -echo $Parsedown->text('Hello _Parsedown_!'); # prints:

Hello Parsedown!

-``` - -You can also parse inline markdown only: - -```php -echo $Parsedown->line('Hello _Parsedown_!'); # prints: Hello Parsedown! -``` - -More examples in [the wiki](https://github.com/erusev/parsedown/wiki/) and in [this video tutorial](http://youtu.be/wYZBY8DEikI). - -## Security - -Parsedown is capable of escaping user-input within the HTML that it generates. Additionally Parsedown will apply sanitisation to additional scripting vectors (such as scripting link destinations) that are introduced by the markdown syntax itself. - -To tell Parsedown that it is processing untrusted user-input, use the following: - -```php -$Parsedown->setSafeMode(true); -``` - -If instead, you wish to allow HTML within untrusted user-input, but still want output to be free from XSS it is recommended that you make use of a HTML sanitiser that allows HTML tags to be whitelisted, like [HTML Purifier](http://htmlpurifier.org/). - -In both cases you should strongly consider employing defence-in-depth measures, like [deploying a Content-Security-Policy](https://scotthelme.co.uk/content-security-policy-an-introduction/) (a browser security feature) so that your page is likely to be safe even if an attacker finds a vulnerability in one of the first lines of defence above. - -#### Security of Parsedown Extensions - -Safe mode does not necessarily yield safe results when using extensions to Parsedown. Extensions should be evaluated on their own to determine their specific safety against XSS. - -## Escaping HTML - -> **WARNING:** This method isn't safe from XSS! - -If you wish to escape HTML **in trusted input**, you can use the following: - -```php -$Parsedown->setMarkupEscaped(true); -``` - -Beware that this still allows users to insert unsafe scripting vectors, such as links like `[xss](javascript:alert%281%29)`. - -## Questions - -**How does Parsedown work?** - -It tries to read Markdown like a human. First, it looks at the lines. It’s interested in how the lines start. This helps it recognise blocks. It knows, for example, that if a line starts with a `-` then perhaps it belongs to a list. Once it recognises the blocks, it continues to the content. As it reads, it watches out for special characters. This helps it recognise inline elements (or inlines). - -We call this approach "line based". We believe that Parsedown is the first Markdown parser to use it. Since the release of Parsedown, other developers have used the same approach to develop other Markdown parsers in PHP and in other languages. - -**Is it compliant with CommonMark?** - -It passes most of the CommonMark tests. Most of the tests that don't pass deal with cases that are quite uncommon. Still, as CommonMark matures, compliance should improve. - -**Who uses it?** - -[Laravel Framework](https://laravel.com/), [Bolt CMS](http://bolt.cm/), [Grav CMS](http://getgrav.org/), [Herbie CMS](http://www.getherbie.org/), [Kirby CMS](http://getkirby.com/), [October CMS](http://octobercms.com/), [Pico CMS](http://picocms.org), [Statamic CMS](http://www.statamic.com/), [phpDocumentor](http://www.phpdoc.org/), [RaspberryPi.org](http://www.raspberrypi.org/), [Symfony Demo](https://github.com/symfony/demo) and [more](https://packagist.org/packages/erusev/parsedown/dependents). - -**How can I help?** - -Use it, star it, share it and if you feel generous, [donate](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=528P3NZQMP8N2). - -**What else should I know?** - -I also make [Nota](https://nota.md/) — a writing app designed for Markdown files :)