/**
* @param Text $text
*
* @return array
*/
protected function parseAttributes(Text $text)
{
$patterns = ['id' => '/^#([a-zA-Z0-9_-]+)/', 'class' => '/^\\.([a-zA-Z0-9_-]+)/', 'attr' => '/^\\[([^\\]]+)\\]/', 'ident' => '/^(.)/'];
$tokens = ['id' => [], 'class' => [], 'attr' => [], 'ident' => []];
while (!$text->isEmpty()) {
foreach ($patterns as $name => $pattern) {
if ($text->match($pattern, $matches)) {
$tokens[$name][] = $matches[1];
$text->setString(substr($text->getString(), strlen($matches[0])));
break;
}
}
}
$attributes = array();
if (count($tokens['id'])) {
$attributes['id'] = array_pop($tokens['id']);
}
if (count($tokens['class'])) {
$attributes['class'] = implode(' ', $tokens['class']);
}
if (count($tokens['attr'])) {
foreach ($tokens['attr'] as $raw) {
$items = explode(' ', $raw);
foreach ($items as $item) {
if (strpos($item, '=') !== false) {
list($key, $value) = explode('=', $item);
$attributes[$key] = trim($value, '"');
} else {
$attributes[$item] = $item;
}
}
}
}
return $attributes;
}
/**
* {@inheritdoc}
*/
public function processListItems(Text $list, array $options = array(), $level = 0)
{
$list->replace('/\\n{2,}\\z/', "\n");
/** @noinspection PhpUnusedParameterInspection */
$list->replace('{
(\\n)? # leading line = $1
(^[ \\t]*) # leading whitespace = $2
(' . $this->getPattern() . ') [ \\t]+ # list marker = $3
(([ ]*(\\[([ ]|x)\\]) [ \\t]+)?(?s:.+?) # list item text = $4, checkbox = $5, checked = %6
(\\n{1,2}))
(?= \\n* (\\z | \\2 (' . $this->getPattern() . ') [ \\t]+))
}mx', function (Text $w, Text $leadingLine, Text $ls, Text $m, Text $item, Text $checkbox, Text $check) use($options, $level) {
if (!$checkbox->isEmpty()) {
$item->replace('/^\\[( |x)\\]/', function (Text $w, Text $check) {
$attr = array('type' => 'checkbox');
if ($check == 'x') {
$attr['checked'] = 'checked';
}
return $this->getRenderer()->renderTag('input', new Text(), Tag::TYPE_INLINE, array('attr' => $attr));
});
}
if ((string) $leadingLine || $item->match('/\\n{2,}/')) {
$this->getEmitter()->emit('outdent', array($item));
$this->getEmitter()->emit('block', array($item));
} else {
$this->getEmitter()->emit('outdent', array($item));
$this->processList($item, $options, ++$level);
$item->rtrim();
$this->getEmitter()->emit('inline', array($item));
}
return $this->getRenderer()->renderListItem($item) . "\n";
});
}
/**
* @param Text $text
* @param array $options
*/
public function processFencedCodeBlock(Text $text, array $options = [])
{
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{
(?:\\n\\n|\\A)
(?:
([`~]{3})[ ]* #1 fence ` or ~
([a-zA-Z0-9]*?)? #2 language [optional]
\\n+
(.*?)\\n #3 code block
\\1 # matched #1
)
}smx', function (Text $w, Text $fence, Text $lang, Text $code) use($options) {
$rendererOptions = [];
if (!$lang->isEmpty()) {
if ($options['pygments'] && class_exists('KzykHys\\Pygments\\Pygments')) {
$pygments = new Pygments();
$html = $pygments->highlight($code, $lang, 'html');
return "\n\n" . $html . "\n\n";
}
$rendererOptions = ['attr' => ['class' => 'prettyprint lang-' . $lang->lower()]];
}
$code->escapeHtml(ENT_NOQUOTES);
$this->markdown->emit('detab', array($code));
$code->replace('/\\A\\n+/', '');
$code->replace('/\\s+\\z/', '');
return "\n\n" . $this->getRenderer()->renderCodeBlock($code, $rendererOptions) . "\n\n";
});
}
/**
* @param Text $text
*/
public function processHorizontalRule(Text $text)
{
$marks = array('\\*', '-', '_');
foreach ($marks as $mark) {
$text->replace('/^[ ]{0,2}([ ]?' . $mark . '[ ]?){3,}[ \\t]*$/m', $this->getRenderer()->renderHorizontalRule() . "\n\n");
}
}
/**
* @param Text $text
*/
public function processMentions(Text $text)
{
// Turn @username into [@username](http://example.com/user/username)
$text->replace('/(?:^|[^a-zA-Z0-9.])@([A-Za-z0-9]+)/', function (Text $w, Text $username) {
return ' [@' . $username . '](' . $this->config->site->url . '/user/0/' . $username . ')';
});
}
/**
* @param Text $text
*/
public function processMentions(Text $text)
{
// Turn @username into [@username](http://example.com/user/username)
$text->replace('/(?:^|[^a-zA-Z0-9.])@([A-Za-z]+[A-Za-z0-9]+)/', function (Text $w, Text $username) {
return ' [@' . $username . '](http://forum.phalconphp.com/user/0/' . $username . ')';
});
}
/**
* Strike-through `~~word~~` to `<del>word</del>`
*
* @param Text $text
*/
public function processStrikeThrough(Text $text)
{
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{ (~~) (?=\\S) (.+?) (?<=\\S) \\1 }sx', function (Text $w, Text $a, Text $target) {
return $this->getRenderer()->renderTag('del', $target, Tag::TYPE_INLINE);
});
}
/**
* @param Text $text
*/
public function processMentions(Text $text)
{
/**
* Turn @username into [@username](http://example.com/user/username)
*/
$text->replace('/(?:^|[^a-zA-Z0-9.])@([A-Za-z]+[A-Za-z0-9]+)/', function (Text $w, Text $username) {
return sprintf('[@%s](https://github.com/%s)', $username, $username);
});
}
public function testTrim()
{
$text = new Text(' #Test## ');
$this->assertEquals('#Test##', $text->trim());
$this->assertEquals('Test', $text->trim('#'));
$text = new Text('Test## ');
$this->assertEquals('Test##', $text->rtrim());
$this->assertEquals('Test', $text->rtrim('#'));
}
/**
* @param Text $text
*/
public function processIssues(Text $text)
{
/**
* Turn the token to a github issue URL
*/
$text->replace('(\\[GI:(\\d+)\\])', function (Text $w, Text $issue) {
return sprintf($this->issueUrl, $issue, $issue);
});
}
/**
* Newlines
*
* The biggest difference that GFM introduces is in the handling of line breaks.
* With SM you can hard wrap paragraphs of text and they will be combined into a single paragraph.
* We find this to be the cause of a huge number of unintentional formatting errors.
* GFM treats newlines in paragraph-like content as real line breaks, which is probably what you intended.
*
* @param Text $text
*/
public function processHardBreak(Text $text)
{
$text->replace('/^[\\S\\<][^\\n]*\\n+(?!( |\\t)*<)/m', function (Text $w) {
if ($w->match('/\\n{2}/') || $w->match('/ \\n/')) {
return $w;
}
return $w->trim()->append(" \n");
});
}
/**
* @param Text $text
*
* @throws \Exception
*/
public function processPullRequest(Text $text)
{
if (true === empty($this->accountName) || true === empty($this->projectName)) {
throw new \Exception('Github account name or project are not set');
}
/**
* Turn the token to a github issue URL
*/
$text->replace('(\\[GPR:(\\d+)\\])', function (Text $w, Text $issue) {
return sprintf($this->issueUrl, $issue, $this->accountName, $this->projectName, $issue);
});
}
/**
* @param Text $text
*/
public function processItalic(Text $text)
{
if (!$text->contains('*') && !$text->contains('_')) {
return;
}
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{ ([^\\*_\\s]?) (\\*|_) (?=\\S) (.+?) (?<=\\S) \\2 ([^\\*_\\s]?) }sx', function (Text $w, Text $prevChar, Text $a, Text $target, Text $nextChar) {
if (!$prevChar->isEmpty() && !$nextChar->isEmpty() && $target->contains(' ')) {
$this->getEmitter()->emit('escape.special_chars', [$w->replaceString(['*', '_'], ['\\*', '\\_'])]);
return $w;
}
return $prevChar . $this->getRenderer()->renderItalicText($target) . $nextChar;
});
}
/**
* Turn standard URL into markdown URL
*
* @param Text $text
*/
public function processStandardUrl(Text $text)
{
$hashes = [];
// escape <code>
$text->replace('{<code>.*?</code>}m', function (Text $w) use(&$hashes) {
$md5 = md5($w);
$hashes[$md5] = $w;
return "{gfm-extraction-{$md5}}";
});
$text->replace('{(?<!]\\(|"|<|\\[)((?:https?|ftp)://[^\'"\\)>\\s]+)(?!>|\\"|\\])}', '<\\1>');
/** @noinspection PhpUnusedParameterInspection */
$text->replace('/\\{gfm-extraction-([0-9a-f]{32})\\}/m', function (Text $w, Text $md5) use(&$hashes) {
return $hashes[(string) $md5];
});
}
/**
* @param Text $text
*/
public function processAtxHeader(Text $text)
{
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{
^(\\#{1,6}) # $1 = string of #\'s
[ \\t]*
(.+?) # $2 = Header text
[ \\t]*
\\#* # optional closing #\'s (not counted)
\\n+
}mx', function (Text $whole, Text $marks, Text $content) {
$level = strlen($marks);
$this->markdown->emit('inline', array($content));
return $this->getRenderer()->renderHeader($content, array('level' => $level)) . "\n\n";
});
}
public function processTest(Text $text)
{
$hashes = [];
// escape <code>
$text->replace('{<code>.*?</code>}m', function (Text $w) use(&$hashes) {
$md5 = md5($w);
$hashes[$md5] = $w;
return "{gfm-extraction-{$md5}}";
});
$text->replace('#(?:(?<=[href|src]=\\"|\')(?:[a-z0-9]+:\\/\\/)?|(?:[a-z0-9]+:\\/\\/))([^\'">\\s]+_+[^\'">\\s]*)+#i', function (Text $w) {
$w->replaceString('_', '%5');
return $w;
});
/** @noinspection PhpUnusedParameterInspection */
$text->replace('/\\{gfm-extraction-([0-9a-f]{32})\\}/m', function (Text $w, Text $md5) use(&$hashes) {
return $hashes[(string) $md5];
});
}
/**
* @param Text $text
*/
public function buildParagraph(Text $text)
{
$parts = $text->replace('/\\A\\n+/', '')->replace('/\\n+\\z/', '')->split('/\\n{2,}/', PREG_SPLIT_NO_EMPTY);
$parts->apply(function (Text $part) {
if (!$this->markdown->getHashRegistry()->exists($part)) {
$this->markdown->emit('inline', array($part));
$part->replace('/^([ \\t]*)/', '');
$part->setString($this->getRenderer()->renderParagraph((string) $part));
}
return $part;
});
$parts->apply(function (Text $part) {
if ($this->markdown->getHashRegistry()->exists($part)) {
$part->setString(trim($this->markdown->getHashRegistry()->get($part)));
}
return $part;
});
$text->setString($parts->join("\n\n"));
}
/**
* @param Text $text
*/
public function processCodeSpan(Text $text)
{
if (!$text->contains('`')) {
return;
}
$chars = ['\\\\', '`', '\\*', '_', '{', '}', '\\[', '\\]', '\\(', '\\)', '>', '#', '\\+', '\\-', '\\.', '!'];
$chars = implode('|', $chars);
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{
(`+) # $1 = Opening run of `
(.+?) # $2 = The code block
(?<!`)
\\1 # Matching closer
(?!`)
}x', function (Text $w, Text $b, Text $code) use($chars) {
$code->trim()->escapeHtml(ENT_NOQUOTES);
$code->replace(sprintf('/(?<!\\\\)(%s)/', $chars), '\\\\${1}');
return $this->getRenderer()->renderCodeSpan($code);
});
}
/**
* {@inheritdoc}
*/
public function renderList($content, array $options = array())
{
if (!$content instanceof Text) {
$content = new Text($content);
}
$options = $this->createResolver()->setRequired(array('type'))->setAllowedValues(array('type' => array('ul', 'ol')))->setDefaults(array('type' => 'ul'))->resolve($options);
$tag = new Tag($options['type']);
$tag->setText($content->prepend("\n"));
$tag->setAttributes($options['attr']);
return $tag->render();
}
/**
* @param Text $text
*/
public function processBlockQuote(Text $text)
{
$text->replace('{
(?:
(?:
^[ \\t]*>[ \\t]? # > at the start of a line
.+\\n # rest of the first line
(?:.+\\n)* # subsequent consecutive lines
\\n* # blanks
)+
)
}mx', function (Text $bq) {
$bq->replace('/^[ \\t]*>[ \\t]?/m', '');
$bq->replace('/^[ \\t]+$/m', '');
$this->markdown->emit('block', [$bq]);
$bq->replace('|\\s*<pre>.+?</pre>|s', function (Text $pre) {
return $pre->replace('/^ /m', '');
});
return $this->getRenderer()->renderBlockQuote($bq) . "\n\n";
});
}
/**
* @param Text $text
*/
public function processHeader(Text $text)
{
$text->replace('{
^h([1-6]) #1 Level
(|=|>)\\. #2 Align marker
[ \\t]*
(.+)
[ \\t]*\\n+
}mx', function (Text $w, Text $level, Text $mark, Text $header) {
$attributes = [];
switch ((string) $mark) {
case '>':
$attributes['align'] = 'right';
break;
case '=':
$attributes['align'] = 'center';
break;
}
return $this->getRenderer()->renderHeader($header, ['level' => (int) $level->getString(), 'attr' => $attributes]) . "\n\n";
});
}
/**
* @param Text $text
*/
public function processFencedCodeBlock(Text $text)
{
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{
(?:\\n\\n|\\A)
(?:
([`~]{3})[ ]* #1 fence ` or ~
([a-zA-Z0-9]*?)? #2 language [optional]
\\n+
(.*?)\\n #3 code block
\\1 # matched #1
)
}smx', function (Text $w, Text $fence, Text $lang, Text $code) {
$options = array();
if (!$lang->isEmpty()) {
$options = array('attr' => array('class' => 'prettyprint lang-' . $lang->lower()));
}
$code->escapeHtml(ENT_NOQUOTES);
$this->markdown->emit('detab', array($code));
$code->replace('/\\A\\n+/', '');
$code->replace('/\\s+\\z/', '');
return "\n\n" . $this->getRenderer()->renderCodeBlock($code, $options) . "\n\n";
});
}
/**
* @param Text $text
*/
public function processWikiDefinitionList(Text $text)
{
$text->replace('{
(^
;[ \\t]*.+\\n
(:[ \\t]*.+\\n){1,}
){1,}
\\n+
}mx', function (Text $w) {
$w->replace('/^;[ \\t]*(.+)\\n((:[ \\t]*.+\\n){1,})/m', function (Text $w, Text $item, Text $content) {
$dt = Tag::create('dt')->setText($item);
$lines = $content->trim()->ltrim(':')->split('/\\n?^:[ \\t]*/m', PREG_SPLIT_NO_EMPTY);
if (count($lines) > 1) {
$dd = Tag::create('dd')->setText(Tag::create('p')->setText(trim($lines->join($this->getRenderer()->renderLineBreak() . "\n"))));
} else {
$dd = Tag::create('dd')->setText($content->trim());
}
return $dt->render() . "\n" . $dd->render() . "\n";
});
$tag = Tag::create('dl')->setText("\n" . $w->trim() . "\n");
return $tag->render();
});
}
/**
* @param Text $text
*/
public function unhashHtmlBlocks(Text $text)
{
foreach ($this->markdown->getHashRegistry() as $hash => $html) {
$text->replaceString($hash, trim($html));
}
}
/**
* @param Text $text
*/
public function unescapeSpecialChars(Text $text)
{
foreach ($this->hashes as $char => $hash) {
$text->replaceString($hash, $char);
}
}
/**
* Make links out of things like `<http://example.com/>`
*
* @param Text $text
*/
public function processAutoLink(Text $text)
{
if (!$text->contains('<')) {
return;
}
$text->replace('{<((?:https?|ftp):[^\'">\\s]+)>}', function (Text $w, Text $url) {
$this->markdown->emit('escape.special_chars', [$url->replace('/(?<!\\\\)_/', '\\\\_')]);
return $this->getRenderer()->renderLink($url, ['href' => $url->getString()]);
});
/** @noinspection PhpUnusedParameterInspection */
$text->replace('{
<
(?:mailto:)?
(
[-.\\w]+
\\@
[-a-z0-9]+(\\.[-a-z0-9]+)*\\.[a-z]+
)
>
}ix', function (Text $w, Text $address) {
$address = "mailto:" . $address;
$encode = array(function ($char) {
return '&#' . ord($char) . ';';
}, function ($char) {
return '&#x' . dechex(ord($char)) . ';';
}, function ($char) {
return $char;
});
$chars = new Collection(str_split($address));
$chars->apply(function ($char) use($encode) {
if ($char == '@') {
return $encode[rand(0, 1)]($char);
} elseif ($char != ':') {
$rand = rand(0, 100);
$key = $rand > 90 ? 2 : ($rand < 45 ? 0 : 1);
return $encode[$key]($char);
}
return $char;
});
$address = $chars->join();
$text = $chars->slice(7)->join();
return $this->getRenderer()->renderLink($text, ['href' => $address]);
});
}
public function processNewLines(Text $text)
{
$text->replace('/\\n/', '<br>');
return $text;
}
/**
* @param Text $text
*/
protected function unescapePipes(Text $text)
{
$text->replaceString($this->hash, '|');
}
/**
* @param Text $text
*/
public function processComment(Text $text)
{
$text->replace('/^###\\.[ \\t]*(.+?)\\n{2,}/m', "\n\n");
}
/**
* Process the contents of a single ordered or unordered list, splitting it into individual list items.
*
* @param Text $list
* @param array $options
* @param int $level
*/
public function processListItems(Text $list, array $options = array(), $level = 0)
{
$list->replace('/\\n{2,}\\z/', "\n");
/** @noinspection PhpUnusedParameterInspection */
$list->replace('{
(\\n)? # leading line = $1
(^[ \\t]*) # leading whitespace = $2
(' . $this->getPattern() . ') [ \\t]+ # list marker = $3
((?s:.+?) # list item text = $4
(\\n{1,2}))
(?= \\n* (\\z | \\2 (' . $this->getPattern() . ') [ \\t]+))
}mx', function (Text $w, Text $leadingLine, Text $ls, Text $m, Text $item) use($options, $level) {
if ((string) $leadingLine || $item->match('/\\n{2,}/')) {
$this->markdown->emit('outdent', array($item));
$this->markdown->emit('block', array($item));
} else {
$this->markdown->emit('outdent', array($item));
$this->processList($item, $options, ++$level);
$item->rtrim();
$this->markdown->emit('inline', array($item));
}
return $this->getRenderer()->renderListItem($item) . "\n";
});
}
