Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merge request for CommonMark compliance improvements #334

Open
wants to merge 10 commits into
base: master
Choose a base branch
from
Open

Merge request for CommonMark compliance improvements #334

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
ffddc55
Allow tabs to be left unprocessed
anthonywilliams Jul 14, 2015
c1a60bf
Fix for more commonmark tabs tests
anthonywilliams Jul 14, 2015
3c4ed6f
Fix for more commonmark tabs tests
anthonywilliams Jul 14, 2015
77d93d5
4 Space indent stops HR generation as per commonmark spec
anthonywilliams Jul 14, 2015
33575b9
Commonmark HTML block element processing
anthonywilliams Jul 14, 2015
53b8876
Commonmark allows arbitrary HTML tags to start a markup block provide…
anthonywilliams Jul 14, 2015
a9f3218
CommonMark literal blocks can contain blank lines
anthonywilliams Jul 14, 2015
3c1db88
Merged changes from https://github.com/erusev/parsedown.git
anthonywilliams Oct 14, 2015
3ffd295
Fixed language designation for code blocks
anthonywilliams Oct 14, 2015
5e08edc
Merge remote-tracking branch 'upstream/master'
anthonywilliams Jan 7, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
144 changes: 115 additions & 29 deletions Parsedown.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,23 @@ function setUrlsLinked($urlsLinked)

protected $urlsLinked = true;

function setTabsExpanded($tabsExpanded)
{
$this->tabsExpanded = $tabsExpanded;

return $this;
}

protected $tabsExpanded = true;

function setCommonMarkHtmlBlocks($commonMarkHtmlBlocks)
{
$this->commonMarkHtmlBlocks = $commonMarkHtmlBlocks;

return $this;
}

protected $commonMarkHtmlBlocks = false;
#
# Lines
#
Expand Down Expand Up @@ -131,7 +148,7 @@ protected function lines(array $lines)
continue;
}

if (strpos($line, "\t") !== false)
if ($this->tabsExpanded && (strpos($line, "\t") !== false))
{
$parts = explode("\t", $line);

Expand All @@ -149,17 +166,23 @@ protected function lines(array $lines)
}

$indent = 0;
$effective_indent=0;

while (isset($line[$indent]) and $line[$indent] === ' ')
while (isset($line[$indent]) and ($line[$indent] === ' ' or $line[$indent] === "\t"))
{
$effective_indent++;
if($line[$indent]==="\t")
{
$effective_indent+=4-$effective_indent%4;
}
$indent ++;
}

$text = $indent > 0 ? substr($line, $indent) : $line;

# ~

$Line = array('body' => $line, 'indent' => $indent, 'text' => $text);
$Line = array('body' => $line, 'indent' => $effective_indent, 'text' => $text);

# ~

Expand Down Expand Up @@ -294,6 +317,17 @@ protected function isBlockCompletable($Type)
#
# Code

protected function stripIndent($text){
for ($pos=0;$pos<4;++$pos){
if ($text[$pos]==="\t"){
return substr($text,$pos+1);
}
if($text[$pos]!==' ')
return substr($text,$pos);
}
return substr($text,4);
}

protected function blockCode($Line, $Block = null)
{
if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted']))
Expand All @@ -303,7 +337,7 @@ protected function blockCode($Line, $Block = null)

if ($Line['indent'] >= 4)
{
$text = substr($Line['body'], 4);
$text = $this->stripIndent($Line['body']);

$Block = array(
'element' => array(
Expand Down Expand Up @@ -333,7 +367,7 @@ protected function blockCodeContinue($Line, $Block)

$Block['element']['text']['text'] .= "\n";

$text = substr($Line['body'], 4);
$text = $this->stripIndent($Line['body']);

$Block['element']['text']['text'] .= $text;

Expand Down Expand Up @@ -399,16 +433,16 @@ protected function blockCommentContinue($Line, array $Block)

protected function blockFencedCode($Line)
{
if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([\w-]+)?[ ]*$/', $Line['text'], $matches))
if (preg_match('/^(['.$Line['text'][0].']{3,})\s*([\w-]+)?\s*$/', $Line['text'], $matches))
{
$Element = array(
'name' => 'code',
'text' => '',
);

if (isset($matches[1]))
if (isset($matches[2]))
{
$class = 'language-'.$matches[1];
$class = 'language-'.$matches[2];

$Element['attributes'] = array(
'class' => $class,
Expand Down Expand Up @@ -442,7 +476,7 @@ protected function blockFencedCodeContinue($Line, $Block)
unset($Block['interrupted']);
}

if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text']))
if (preg_match('/^'.$Block['char'].'{3,}\s*$/', $Line['text']))
{
$Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1);

Expand Down Expand Up @@ -507,7 +541,7 @@ protected function blockList($Line)
{
list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]');

if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches))
if (preg_match('/^('.$pattern.'\s+)(.*)/', $Line['text'], $matches))
{
$Block = array(
'indent' => $Line['indent'],
Expand All @@ -534,7 +568,7 @@ protected function blockList($Line)

protected function blockListContinue($Line, array $Block)
{
if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches))
if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:\s+(.*)|$)/', $Line['text'], $matches))
{
if (isset($Block['interrupted']))
{
Expand Down Expand Up @@ -567,7 +601,7 @@ protected function blockListContinue($Line, array $Block)

if ( ! isset($Block['interrupted']))
{
$text = preg_replace('/^[ ]{0,4}/', '', $Line['body']);
$text = $this->stripIndent($Line['body']);

$Block['li']['text'] []= $text;

Expand All @@ -578,7 +612,7 @@ protected function blockListContinue($Line, array $Block)
{
$Block['li']['text'] []= '';

$text = preg_replace('/^[ ]{0,4}/', '', $Line['body']);
$text = $this->stripIndent($Line['body']);

$Block['li']['text'] []= $text;

Expand All @@ -593,7 +627,7 @@ protected function blockListContinue($Line, array $Block)

protected function blockQuote($Line)
{
if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
if (preg_match('/^>\s?(.*)/', $Line['text'], $matches))
{
$Block = array(
'element' => array(
Expand All @@ -609,7 +643,7 @@ protected function blockQuote($Line)

protected function blockQuoteContinue($Line, array $Block)
{
if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
if ($Line['text'][0] === '>' and preg_match('/^>\s?(.*)/', $Line['text'], $matches))
{
if (isset($Block['interrupted']))
{
Expand All @@ -636,7 +670,8 @@ protected function blockQuoteContinue($Line, array $Block)

protected function blockRule($Line)
{
if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text']))
if (($Line['indent']<4) and
preg_match('/^(['.$Line['text'][0].'])(\s*\1){2,}\s*$/', $Line['text']))
{
$Block = array(
'element' => array(
Expand Down Expand Up @@ -676,7 +711,29 @@ protected function blockMarkup($Line)
return;
}

if (preg_match('/^<(\w*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches))
if($this->commonMarkHtmlBlocks){
if (preg_match('/^<\/?(\w+)((\s|>).*)?$/', $Line['text'], $matches)){
if(in_array(strtolower($matches[1]),$this->commonMarkHtmlElements) or
in_array(strtolower($matches[1]),$this->commonMarkLiteralHtmlElements))
{
$Block = array(
'name' => $matches[1],
'markup' => $Line['text'],
);
return $Block;
}
}
if (preg_match('/^<\/?(\w+)(\s[^>]*)?>$/', $Line['text'], $matches)){
$Block = array(
'name' => $matches[1],
'markup' => $Line['text'],
);
return $Block;
}
return;
}

if (preg_match('/^<(\w*)(?:\s*'.$this->regexHtmlAttribute.')*\s*(\/)?>/', $Line['text'], $matches))
{
$element = strtolower($matches[1]);

Expand Down Expand Up @@ -711,7 +768,7 @@ protected function blockMarkup($Line)
return;
}

if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder))
if (preg_match('/<\/'.$matches[1].'>\s*$/i', $remainder))
{
$Block['closed'] = true;
}
Expand All @@ -728,12 +785,26 @@ protected function blockMarkupContinue($Line, array $Block)
return;
}

if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open
if($this->commonMarkHtmlBlocks)
{
if(isset($Block['interrupted']))
{
unset($Block['interrupted']);
$Block['markup'] .= "\n";
if(!in_array(strtolower($Block['name']),$this->commonMarkLiteralHtmlElements)){
return;
}
}
$Block['markup'] .= "\n".$Line['text'];
return $Block;
}

if (preg_match('/^<'.$Block['name'].'(?:\s*'.$this->regexHtmlAttribute.')*\s*>/i', $Line['text'])) # open
{
$Block['depth'] ++;
}

if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close
if (preg_match('/(.*?)<\/'.$Block['name'].'>\s*$/i', $Line['text'], $matches)) # close
{
if ($Block['depth'] > 0)
{
Expand All @@ -748,7 +819,6 @@ protected function blockMarkupContinue($Line, array $Block)
if (isset($Block['interrupted']))
{
$Block['markup'] .= "\n";

unset($Block['interrupted']);
}

Expand All @@ -762,7 +832,7 @@ protected function blockMarkupContinue($Line, array $Block)

protected function blockReference($Line)
{
if (preg_match('/^\[(.+?)\]:[ ]*<?(\S+?)>?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches))
if (preg_match('/^\[(.+?)\]:\s*<?(\S+?)>?(?:\s+["\'(](.+)["\')])?\s*$/', $Line['text'], $matches))
{
$id = strtolower($matches[1]);

Expand Down Expand Up @@ -1064,11 +1134,11 @@ protected function inlineCode($Excerpt)
{
$marker = $Excerpt['text'][0];

if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(?<!'.$marker.')\1(?!'.$marker.')/s', $Excerpt['text'], $matches))
if (preg_match('/^('.$marker.'+)\s*(.+?)\s*(?<!'.$marker.')\1(?!'.$marker.')/s', $Excerpt['text'], $matches))
{
$text = $matches[2];
$text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8');
$text = preg_replace("/[ ]*\n/", ' ', $text);
$text = preg_replace("/\s*\n/", ' ', $text);

return array(
'extent' => strlen($matches[0]),
Expand Down Expand Up @@ -1210,7 +1280,7 @@ protected function inlineLink($Excerpt)
return;
}

if (preg_match('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:[ ]+("[^"]*"|\'[^\']*\'))?[)]/', $remainder, $matches))
if (preg_match('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:\s+("[^"]*"|\'[^\']*\'))?[)]/', $remainder, $matches))
{
$Element['attributes']['href'] = $matches[1];

Expand Down Expand Up @@ -1261,7 +1331,7 @@ protected function inlineMarkup($Excerpt)
return;
}

if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*[ ]*>/s', $Excerpt['text'], $matches))
if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*\s*>/s', $Excerpt['text'], $matches))
{
return array(
'markup' => $matches[0],
Expand All @@ -1277,7 +1347,7 @@ protected function inlineMarkup($Excerpt)
);
}

if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches))
if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:\s*'.$this->regexHtmlAttribute.')*\s*\/?>/s', $Excerpt['text'], $matches))
{
return array(
'markup' => $matches[0],
Expand Down Expand Up @@ -1377,11 +1447,11 @@ protected function unmarkedText($text)
{
if ($this->breaksEnabled)
{
$text = preg_replace('/[ ]*\n/', "<br />\n", $text);
$text = preg_replace('/\s*\n/', "<br />\n", $text);
}
else
{
$text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "<br />\n", $text);
$text = preg_replace('/(?:\s\s+|\s*\\\\)\n/', "<br />\n", $text);
$text = str_replace(" \n", "\n", $text);
}

Expand Down Expand Up @@ -1527,6 +1597,22 @@ static function instance($name = 'default')
'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source',
);

protected $commonMarkHtmlElements = array(
'address','article', 'aside', 'base', 'basefont', 'blockquote', 'body',
'caption', 'center', 'col', 'colgroup', 'dd', 'details', 'dialog',
'dir', 'div', 'dl', 'dt', 'fieldset', 'figcaption', 'figure',
'footer', 'form', 'frame', 'frameset', 'h1', 'head', 'header', 'hr',
'html', 'legend', 'li', 'link', 'main', 'menu', 'menuitem', 'meta',
'nav', 'noframes', 'ol', 'optgroup', 'option', 'p', 'param', 'pre',
'section', 'source', 'title', 'summary', 'table', 'tbody', 'td',
'tfoot', 'th', 'thead', 'title', 'tr', 'track', 'ul'
);

protected $commonMarkLiteralHtmlElements = array(
'script','pre','style'
);


protected $textLevelElements = array(
'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont',
'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing',
Expand Down
3 changes: 3 additions & 0 deletions test/CommonMarkTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ function test_($section, $markdown, $expectedHtml)
{
$Parsedown = new Parsedown();
$Parsedown->setUrlsLinked(false);
$Parsedown->setTabsExpanded(false);
$Parsedown->setCommonMarkHtmlBlocks(true);

$actualHtml = $Parsedown->text($markdown);
$actualHtml = $this->normalizeMarkup($actualHtml);
Expand All @@ -48,6 +50,7 @@ function($matches) use ( & $tests, & $currentSection, & $testCount) {
$markdown = preg_replace('/→/', "\t", $markdown);
$expectedHtml = $matches[2];
$expectedHtml = $this->normalizeMarkup($expectedHtml);
$expectedHtml = preg_replace('/→/', "\t", $expectedHtml);
$tests []= array(
$currentSection, # section
$markdown, # markdown
Expand Down