diff --git a/src/server/lib/parsedown/Parsedown.php b/src/server/lib/parsedown/Parsedown.php
index c8c92a3..ae0cbde 100644
--- a/src/server/lib/parsedown/Parsedown.php
+++ b/src/server/lib/parsedown/Parsedown.php
@@ -17,11 +17,24 @@ class Parsedown
{
# ~
- const version = '1.6.0';
+ const version = '1.8.0-beta-7';
# ~
function text($text)
+ {
+ $Elements = $this->textElements($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();
@@ -36,12 +49,7 @@ class Parsedown
$lines = explode("\n", $text);
# iterate through lines to identify blocks
- $markup = $this->lines($lines);
-
- # trim line breaks
- $markup = trim($markup, "\n");
-
- return $markup;
+ return $this->linesElements($lines);
}
#
@@ -75,6 +83,42 @@ class Parsedown
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
#
@@ -115,8 +159,14 @@ class Parsedown
# Blocks
#
- private function lines(array $lines)
+ protected function lines(array $lines)
{
+ return $this->elements($this->linesElements($lines));
+ }
+
+ protected function linesElements(array $lines)
+ {
+ $Elements = array();
$CurrentBlock = null;
foreach ($lines as $line)
@@ -125,35 +175,25 @@ class Parsedown
{
if (isset($CurrentBlock))
{
- $CurrentBlock['interrupted'] = true;
+ $CurrentBlock['interrupted'] = (isset($CurrentBlock['interrupted'])
+ ? $CurrentBlock['interrupted'] + 1 : 1
+ );
}
continue;
}
- if (strpos($line, "\t") !== false)
+ while (($beforeTab = strstr($line, "\t", true)) !== false)
{
- $parts = explode("\t", $line);
+ $shortage = 4 - mb_strlen($beforeTab, 'utf-8') % 4;
- $line = $parts[0];
-
- unset($parts[0]);
-
- foreach ($parts as $part)
- {
- $shortage = 4 - mb_strlen($line, 'utf-8') % 4;
-
- $line .= str_repeat(' ', $shortage);
- $line .= $part;
- }
+ $line = $beforeTab
+ . str_repeat(' ', $shortage)
+ . substr($line, strlen($beforeTab) + 1)
+ ;
}
- $indent = 0;
-
- while (isset($line[$indent]) and $line[$indent] === ' ')
- {
- $indent ++;
- }
+ $indent = strspn($line, ' ');
$text = $indent > 0 ? substr($line, $indent) : $line;
@@ -165,7 +205,8 @@ class Parsedown
if (isset($CurrentBlock['continuable']))
{
- $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock);
+ $methodName = 'block' . $CurrentBlock['type'] . 'Continue';
+ $Block = $this->$methodName($Line, $CurrentBlock);
if (isset($Block))
{
@@ -175,9 +216,10 @@ class Parsedown
}
else
{
- if (method_exists($this, 'block'.$CurrentBlock['type'].'Complete'))
+ if ($this->isBlockCompletable($CurrentBlock['type']))
{
- $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock);
+ $methodName = 'block' . $CurrentBlock['type'] . 'Complete';
+ $CurrentBlock = $this->$methodName($CurrentBlock);
}
}
}
@@ -203,7 +245,7 @@ class Parsedown
foreach ($blockTypes as $blockType)
{
- $Block = $this->{'block'.$blockType}($Line, $CurrentBlock);
+ $Block = $this->{"block$blockType"}($Line, $CurrentBlock);
if (isset($Block))
{
@@ -211,12 +253,15 @@ class Parsedown
if ( ! isset($Block['identified']))
{
- $Blocks []= $CurrentBlock;
+ if (isset($CurrentBlock))
+ {
+ $Elements[] = $this->extractElement($CurrentBlock);
+ }
$Block['identified'] = true;
}
- if (method_exists($this, 'block'.$blockType.'Continue'))
+ if ($this->isBlockContinuable($blockType))
{
$Block['continuable'] = true;
}
@@ -229,13 +274,21 @@ class Parsedown
# ~
- if (isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted']))
+ if (isset($CurrentBlock) and $CurrentBlock['type'] === 'Paragraph')
{
- $CurrentBlock['element']['text'] .= "\n".$text;
+ $Block = $this->paragraphContinue($Line, $CurrentBlock);
+ }
+
+ if (isset($Block))
+ {
+ $CurrentBlock = $Block;
}
else
{
- $Blocks []= $CurrentBlock;
+ if (isset($CurrentBlock))
+ {
+ $Elements[] = $this->extractElement($CurrentBlock);
+ }
$CurrentBlock = $this->paragraph($Line);
@@ -245,37 +298,49 @@ class Parsedown
# ~
- if (isset($CurrentBlock['continuable']) and method_exists($this, 'block'.$CurrentBlock['type'].'Complete'))
+ if (isset($CurrentBlock['continuable']) and $this->isBlockCompletable($CurrentBlock['type']))
{
- $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock);
+ $methodName = 'block' . $CurrentBlock['type'] . 'Complete';
+ $CurrentBlock = $this->$methodName($CurrentBlock);
}
# ~
- $Blocks []= $CurrentBlock;
-
- unset($Blocks[0]);
+ if (isset($CurrentBlock))
+ {
+ $Elements[] = $this->extractElement($CurrentBlock);
+ }
# ~
- $markup = '';
+ return $Elements;
+ }
- foreach ($Blocks as $Block)
+ protected function extractElement(array $Component)
+ {
+ if ( ! isset($Component['element']))
{
- if (isset($Block['hidden']))
+ if (isset($Component['markup']))
{
- continue;
+ $Component['element'] = array('rawHtml' => $Component['markup']);
+ }
+ elseif (isset($Component['hidden']))
+ {
+ $Component['element'] = array();
}
-
- $markup .= "\n";
- $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']);
}
- $markup .= "\n";
+ return $Component['element'];
+ }
- # ~
+ protected function isBlockContinuable($Type)
+ {
+ return method_exists($this, 'block' . $Type . 'Continue');
+ }
- return $markup;
+ protected function isBlockCompletable($Type)
+ {
+ return method_exists($this, 'block' . $Type . 'Complete');
}
#
@@ -283,7 +348,7 @@ class Parsedown
protected function blockCode($Line, $Block = null)
{
- if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted']))
+ if (isset($Block) and $Block['type'] === 'Paragraph' and ! isset($Block['interrupted']))
{
return;
}
@@ -295,8 +360,7 @@ class Parsedown
$Block = array(
'element' => array(
'name' => 'pre',
- 'handler' => 'element',
- 'text' => array(
+ 'element' => array(
'name' => 'code',
'text' => $text,
),
@@ -313,16 +377,16 @@ class Parsedown
{
if (isset($Block['interrupted']))
{
- $Block['element']['text']['text'] .= "\n";
+ $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']);
unset($Block['interrupted']);
}
- $Block['element']['text']['text'] .= "\n";
+ $Block['element']['element']['text'] .= "\n";
$text = substr($Line['body'], 4);
- $Block['element']['text']['text'] .= $text;
+ $Block['element']['element']['text'] .= $text;
return $Block;
}
@@ -330,12 +394,6 @@ class Parsedown
protected function blockCodeComplete($Block)
{
- $text = $Block['element']['text']['text'];
-
- $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8');
-
- $Block['element']['text']['text'] = $text;
-
return $Block;
}
@@ -344,18 +402,21 @@ class Parsedown
protected function blockComment($Line)
{
- if ($this->markupEscaped)
+ if ($this->markupEscaped or $this->safeMode)
{
return;
}
- if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!')
+ if (strpos($Line['text'], '$/', $Line['text']))
+ if (strpos($Line['text'], '-->') !== false)
{
$Block['closed'] = true;
}
@@ -371,9 +432,9 @@ class Parsedown
return;
}
- $Block['markup'] .= "\n" . $Line['body'];
+ $Block['element']['rawHtml'] .= "\n" . $Line['body'];
- if (preg_match('/-->$/', $Line['text']))
+ if (strpos($Line['text'], '-->') !== false)
{
$Block['closed'] = true;
}
@@ -386,33 +447,56 @@ class Parsedown
protected function blockFencedCode($Line)
{
- if (preg_match('/^['.$Line['text'][0].']{3,}[ ]*([\w-]+)?[ ]*$/', $Line['text'], $matches))
+ $marker = $Line['text'][0];
+
+ $openerLength = strspn($Line['text'], $marker);
+
+ if ($openerLength < 3)
{
- $Element = array(
- 'name' => 'code',
- 'text' => '',
- );
-
- if (isset($matches[1]))
- {
- $class = 'language-'.$matches[1];
-
- $Element['attributes'] = array(
- 'class' => $class,
- );
- }
-
- $Block = array(
- 'char' => $Line['text'][0],
- 'element' => array(
- 'name' => 'pre',
- 'handler' => 'element',
- 'text' => $Element,
- ),
- );
-
- return $Block;
+ 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, $Block)
@@ -424,33 +508,28 @@ class Parsedown
if (isset($Block['interrupted']))
{
- $Block['element']['text']['text'] .= "\n";
+ $Block['element']['element']['text'] .= str_repeat("\n", $Block['interrupted']);
unset($Block['interrupted']);
}
- if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text']))
- {
- $Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1);
+ 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;
}
- $Block['element']['text']['text'] .= "\n".$Line['body'];;
+ $Block['element']['element']['text'] .= "\n" . $Line['body'];
return $Block;
}
protected function blockFencedCodeComplete($Block)
{
- $text = $Block['element']['text']['text'];
-
- $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8');
-
- $Block['element']['text']['text'] = $text;
-
return $Block;
}
@@ -459,61 +538,103 @@ class Parsedown
protected function blockHeader($Line)
{
- if (isset($Line['text'][1]))
+ $level = strspn($Line['text'], '#');
+
+ if ($level > 6)
{
- $level = 1;
-
- while (isset($Line['text'][$level]) and $Line['text'][$level] === '#')
- {
- $level ++;
- }
-
- if ($level > 6)
- {
- return;
- }
-
- $text = trim($Line['text'], '# ');
-
- $Block = array(
- 'element' => array(
- 'name' => 'h' . min(6, $level),
- 'text' => $text,
- 'handler' => 'line',
- ),
- );
-
- return $Block;
+ 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)
+ protected function blockList($Line, array $CurrentBlock = null)
{
- list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]');
+ list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]{1,9}+[.\)]');
- if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches))
+ if (preg_match('/^('.$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,
- 'handler' => 'elements',
+ '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' => 'li',
- 'text' => array(
- $matches[2],
- ),
+ 'handler' => array(
+ 'function' => 'li',
+ 'argument' => !empty($matches[3]) ? array($matches[3]) : array(),
+ 'destination' => 'elements'
+ )
);
- $Block['element']['text'] []= & $Block['li'];
+ $Block['element']['elements'] []= & $Block['li'];
return $Block;
}
@@ -521,11 +642,29 @@ class Parsedown
protected function blockListContinue($Line, array $Block)
{
- if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches))
+ if (isset($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']['text'] []= '';
+ $Block['li']['handler']['argument'] []= '';
+
+ $Block['loose'] = true;
unset($Block['interrupted']);
}
@@ -534,45 +673,73 @@ class Parsedown
$text = isset($matches[1]) ? $matches[1] : '';
+ $Block['indent'] = $Line['indent'];
+
$Block['li'] = array(
'name' => 'li',
- 'handler' => 'li',
- 'text' => array(
- $text,
- ),
+ 'handler' => array(
+ 'function' => 'li',
+ 'argument' => array($text),
+ 'destination' => 'elements'
+ )
);
- $Block['element']['text'] []= & $Block['li'];
+ $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('/^[ ]{0,4}/', '', $Line['body']);
+ $text = preg_replace('/^[ ]{0,'.$requiredIndent.'}+/', '', $Line['body']);
- $Block['li']['text'] []= $text;
+ $Block['li']['handler']['argument'] []= $text;
return $Block;
}
+ }
- if ($Line['indent'] > 0)
+ protected function blockListComplete(array $Block)
+ {
+ if (isset($Block['loose']))
{
- $Block['li']['text'] []= '';
-
- $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']);
-
- $Block['li']['text'] []= $text;
-
- unset($Block['interrupted']);
-
- return $Block;
+ foreach ($Block['element']['elements'] as &$li)
+ {
+ if (end($li['handler']['argument']) !== '')
+ {
+ $li['handler']['argument'] []= '';
+ }
+ }
}
+
+ return $Block;
}
#
@@ -580,13 +747,16 @@ class Parsedown
protected function blockQuote($Line)
{
- if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
+ if (preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches))
{
$Block = array(
'element' => array(
'name' => 'blockquote',
- 'handler' => 'lines',
- 'text' => (array) $matches[1],
+ 'handler' => array(
+ 'function' => 'linesElements',
+ 'argument' => (array) $matches[1],
+ 'destination' => 'elements',
+ )
),
);
@@ -596,23 +766,21 @@ class Parsedown
protected function blockQuoteContinue($Line, array $Block)
{
- if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches))
+ if (isset($Block['interrupted']))
{
- if (isset($Block['interrupted']))
- {
- $Block['element']['text'] []= '';
+ return;
+ }
- unset($Block['interrupted']);
- }
-
- $Block['element']['text'] []= $matches[1];
+ if ($Line['text'][0] === '>' and preg_match('/^>[ ]?+(.*+)/', $Line['text'], $matches))
+ {
+ $Block['element']['handler']['argument'] []= $matches[1];
return $Block;
}
if ( ! isset($Block['interrupted']))
{
- $Block['element']['text'] []= $Line['text'];
+ $Block['element']['handler']['argument'] []= $Line['text'];
return $Block;
}
@@ -623,11 +791,13 @@ class Parsedown
protected function blockRule($Line)
{
- if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text']))
+ $marker = $Line['text'][0];
+
+ if (substr_count($Line['text'], $marker) >= 3 and chop($Line['text'], " $marker") === '')
{
$Block = array(
'element' => array(
- 'name' => 'hr'
+ 'name' => 'hr',
),
);
@@ -640,12 +810,12 @@ class Parsedown
protected function blockSetextHeader($Line, array $Block = null)
{
- if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted']))
+ if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted']))
{
return;
}
- if (chop($Line['text'], $Line['text'][0]) === '')
+ if ($Line['indent'] < 4 and chop(chop($Line['text'], ' '), $Line['text'][0]) === '')
{
$Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2';
@@ -658,12 +828,12 @@ class Parsedown
protected function blockMarkup($Line)
{
- if ($this->markupEscaped)
+ if ($this->markupEscaped or $this->safeMode)
{
return;
}
- if (preg_match('/^<(\w*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches))
+ if (preg_match('/^<[\/]?+(\w*)(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+(\/)?>/', $Line['text'], $matches))
{
$element = strtolower($matches[1]);
@@ -674,72 +844,24 @@ class Parsedown
$Block = array(
'name' => $matches[1],
- 'depth' => 0,
- 'markup' => $Line['text'],
+ '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']))
+ if (isset($Block['closed']) or isset($Block['interrupted']))
{
return;
}
- if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open
- {
- $Block['depth'] ++;
- }
-
- if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close
- {
- if ($Block['depth'] > 0)
- {
- $Block['depth'] --;
- }
- else
- {
- $Block['closed'] = true;
- }
- }
-
- if (isset($Block['interrupted']))
- {
- $Block['markup'] .= "\n";
-
- unset($Block['interrupted']);
- }
-
- $Block['markup'] .= "\n".$Line['body'];
+ $Block['element']['rawHtml'] .= "\n" . $Line['body'];
return $Block;
}
@@ -749,24 +871,20 @@ class Parsedown
protected function blockReference($Line)
{
- if (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches))
- {
+ if (strpos($Line['text'], ']') !== false
+ and preg_match('/^\[(.+?)\]:[ ]*+?(?:[ ]+["\'(](.+)["\')])?[ ]*+$/', $Line['text'], $matches)
+ ) {
$id = strtolower($matches[1]);
$Data = array(
'url' => $matches[2],
- 'title' => null,
+ 'title' => isset($matches[3]) ? $matches[3] : null,
);
- if (isset($matches[3]))
- {
- $Data['title'] = $matches[3];
- }
-
$this->DefinitionData['Reference'][$id] = $Data;
$Block = array(
- 'hidden' => true,
+ 'element' => array(),
);
return $Block;
@@ -778,109 +896,125 @@ class Parsedown
protected function blockTable($Line, array $Block = null)
{
- if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted']))
+ if ( ! isset($Block) or $Block['type'] !== 'Paragraph' or isset($Block['interrupted']))
{
return;
}
- if (strpos($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '')
- {
- $alignments = array();
-
- $divider = $Line['text'];
-
- $divider = trim($divider);
- $divider = trim($divider, '|');
-
- $dividerCells = explode('|', $divider);
-
- foreach ($dividerCells as $dividerCell)
- {
- $dividerCell = trim($dividerCell);
-
- if ($dividerCell === '')
- {
- continue;
- }
-
- $alignment = null;
-
- if ($dividerCell[0] === ':')
- {
- $alignment = 'left';
- }
-
- if (substr($dividerCell, - 1) === ':')
- {
- $alignment = $alignment === 'left' ? 'center' : 'right';
- }
-
- $alignments []= $alignment;
- }
-
- # ~
-
- $HeaderElements = array();
-
- $header = $Block['element']['text'];
-
- $header = trim($header);
- $header = trim($header, '|');
-
- $headerCells = explode('|', $header);
-
- foreach ($headerCells as $index => $headerCell)
- {
- $headerCell = trim($headerCell);
-
- $HeaderElement = array(
- 'name' => 'th',
- 'text' => $headerCell,
- 'handler' => 'line',
- );
-
- if (isset($alignments[$index]))
- {
- $alignment = $alignments[$index];
-
- $HeaderElement['attributes'] = array(
- 'style' => 'text-align: '.$alignment.';',
- );
- }
-
- $HeaderElements []= $HeaderElement;
- }
-
- # ~
-
- $Block = array(
- 'alignments' => $alignments,
- 'identified' => true,
- 'element' => array(
- 'name' => 'table',
- 'handler' => 'elements',
- ),
- );
-
- $Block['element']['text'] []= array(
- 'name' => 'thead',
- 'handler' => 'elements',
- );
-
- $Block['element']['text'] []= array(
- 'name' => 'tbody',
- 'handler' => 'elements',
- 'text' => array(),
- );
-
- $Block['element']['text'][0]['text'] []= array(
- 'name' => 'tr',
- 'handler' => 'elements',
- 'text' => $HeaderElements,
- );
-
- return $Block;
+ if (
+ strpos($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 $Block)
@@ -890,7 +1024,7 @@ class Parsedown
return;
}
- if ($Line['text'][0] === '|' or strpos($Line['text'], '|'))
+ if (count($Block['alignments']) === 1 or $Line['text'][0] === '|' or strpos($Line['text'], '|'))
{
$Elements = array();
@@ -899,22 +1033,27 @@ class Parsedown
$row = trim($row);
$row = trim($row, '|');
- preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches);
+ preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]++`|`)++/', $row, $matches);
- foreach ($matches[0] as $index => $cell)
+ $cells = array_slice($matches[0], 0, count($Block['alignments']));
+
+ foreach ($cells as $index => $cell)
{
$cell = trim($cell);
$Element = array(
'name' => 'td',
- 'handler' => 'line',
- 'text' => $cell,
+ 'handler' => array(
+ 'function' => 'lineElements',
+ 'argument' => $cell,
+ 'destination' => 'elements',
+ )
);
if (isset($Block['alignments'][$index]))
{
$Element['attributes'] = array(
- 'style' => 'text-align: '.$Block['alignments'][$index].';',
+ 'style' => 'text-align: ' . $Block['alignments'][$index] . ';',
);
}
@@ -923,11 +1062,10 @@ class Parsedown
$Element = array(
'name' => 'tr',
- 'handler' => 'elements',
- 'text' => $Elements,
+ 'elements' => $Elements,
);
- $Block['element']['text'][1]['text'] []= $Element;
+ $Block['element']['elements'][1]['elements'] []= $Element;
return $Block;
}
@@ -939,13 +1077,27 @@ class Parsedown
protected function paragraph($Line)
{
- $Block = array(
+ return array(
+ 'type' => 'Paragraph',
'element' => array(
'name' => 'p',
- 'text' => $Line['text'],
- 'handler' => 'line',
+ '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;
}
@@ -955,13 +1107,11 @@ class Parsedown
#
protected $InlineTypes = array(
- '"' => array('SpecialCharacter'),
'!' => array('Image'),
'&' => array('SpecialCharacter'),
'*' => array('Emphasis'),
':' => array('Url'),
- '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'),
- '>' => array('SpecialCharacter'),
+ '<' => array('UrlTag', 'EmailTag', 'Markup'),
'[' => array('Link'),
'_' => array('Emphasis'),
'`' => array('Code'),
@@ -971,15 +1121,28 @@ class Parsedown
# ~
- protected $inlineMarkerList = '!"*_&[:<>`~\\';
+ protected $inlineMarkerList = '!*_&[:<`~\\';
#
# ~
#
- public function line($text)
+ public function line($text, $nonNestables = array())
{
- $markup = '';
+ 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
@@ -987,13 +1150,20 @@ class Parsedown
{
$marker = $excerpt[0];
- $markerPosition = strpos($text, $marker);
+ $markerPosition = strlen($text) - strlen($excerpt);
$Excerpt = array('text' => $excerpt, 'context' => $text);
foreach ($this->InlineTypes[$marker] as $inlineType)
{
- $Inline = $this->{'inline'.$inlineType}($Excerpt);
+ # check to see if the current inline type is nestable in the current context
+
+ if (isset($nonNestables[$inlineType]))
+ {
+ continue;
+ }
+
+ $Inline = $this->{"inline$inlineType"}($Excerpt);
if ( ! isset($Inline))
{
@@ -1014,14 +1184,23 @@ class Parsedown
$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
- $markup .= $this->unmarkedText($unmarkedText);
+ $InlineText = $this->inlineText($unmarkedText);
+ $Elements[] = $InlineText['element'];
# compile the inline
- $markup .= isset($Inline['markup']) ? $Inline['markup'] : $this->element($Inline['element']);
+ $Elements[] = $this->extractElement($Inline);
# remove the examined text
$text = substr($text, $Inline['position'] + $Inline['extent']);
@@ -1033,29 +1212,57 @@ class Parsedown
$unmarkedText = substr($text, 0, $markerPosition + 1);
- $markup .= $this->unmarkedText($unmarkedText);
+ $InlineText = $this->inlineText($unmarkedText);
+ $Elements[] = $InlineText['element'];
$text = substr($text, $markerPosition + 1);
}
- $markup .= $this->unmarkedText($text);
+ $InlineText = $this->inlineText($text);
+ $Elements[] = $InlineText['element'];
- return $markup;
+ foreach ($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($matches[0]),
@@ -1069,13 +1276,19 @@ class Parsedown
protected function inlineEmailTag($Excerpt)
{
- if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $Excerpt['text'], $matches))
- {
+ $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;
+ $url = "mailto:$url";
}
return array(
@@ -1117,8 +1330,11 @@ class Parsedown
'extent' => strlen($matches[0]),
'element' => array(
'name' => $emphasis,
- 'handler' => 'line',
- 'text' => $matches[1],
+ 'handler' => array(
+ 'function' => 'lineElements',
+ 'argument' => $matches[1],
+ 'destination' => 'elements',
+ )
),
);
}
@@ -1128,7 +1344,7 @@ class Parsedown
if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters))
{
return array(
- 'markup' => $Excerpt['text'][1],
+ 'element' => array('rawHtml' => $Excerpt['text'][1]),
'extent' => 2,
);
}
@@ -1156,8 +1372,9 @@ class Parsedown
'name' => 'img',
'attributes' => array(
'src' => $Link['element']['attributes']['href'],
- 'alt' => $Link['element']['text'],
+ 'alt' => $Link['element']['handler']['argument'],
),
+ 'autobreak' => true,
),
);
@@ -1172,8 +1389,12 @@ class Parsedown
{
$Element = array(
'name' => 'a',
- 'handler' => 'line',
- 'text' => null,
+ 'handler' => array(
+ 'function' => 'lineElements',
+ 'argument' => null,
+ 'destination' => 'elements',
+ ),
+ 'nonNestables' => array('Url', 'Link'),
'attributes' => array(
'href' => null,
'title' => null,
@@ -1184,9 +1405,9 @@ class Parsedown
$remainder = $Excerpt['text'];
- if (preg_match('/\[((?:[^][]|(?R))*)\]/', $remainder, $matches))
+ if (preg_match('/\[((?:[^][]++|(?R))*+)\]/', $remainder, $matches))
{
- $Element['text'] = $matches[1];
+ $Element['handler']['argument'] = $matches[1];
$extent += strlen($matches[0]);
@@ -1197,7 +1418,7 @@ class Parsedown
return;
}
- if (preg_match('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:[ ]+("[^"]*"|\'[^\']*\'))?[)]/', $remainder, $matches))
+ if (preg_match('/^[(]\s*+((?:[^ ()]++|[(][^ )]+[)])++)(?:[ ]+("[^"]*+"|\'[^\']*+\'))?\s*+[)]/', $remainder, $matches))
{
$Element['attributes']['href'] = $matches[1];
@@ -1212,14 +1433,14 @@ class Parsedown
{
if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches))
{
- $definition = strlen($matches[1]) ? $matches[1] : $Element['text'];
+ $definition = strlen($matches[1]) ? $matches[1] : $Element['handler']['argument'];
$definition = strtolower($definition);
$extent += strlen($matches[0]);
}
else
{
- $definition = strtolower($Element['text']);
+ $definition = strtolower($Element['handler']['argument']);
}
if ( ! isset($this->DefinitionData['Reference'][$definition]))
@@ -1233,8 +1454,6 @@ class Parsedown
$Element['attributes']['title'] = $Definition['title'];
}
- $Element['attributes']['href'] = str_replace(array('&', '<'), array('&', '<'), $Element['attributes']['href']);
-
return array(
'extent' => $extent,
'element' => $Element,
@@ -1243,31 +1462,31 @@ class Parsedown
protected function inlineMarkup($Excerpt)
{
- if ($this->markupEscaped or strpos($Excerpt['text'], '>') === false)
+ if ($this->markupEscaped or $this->safeMode or strpos($Excerpt['text'], '>') === false)
{
return;
}
- if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*[ ]*>/s', $Excerpt['text'], $matches))
+ if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w[\w-]*+[ ]*+>/s', $Excerpt['text'], $matches))
{
return array(
- 'markup' => $matches[0],
+ 'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
- if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches))
+ if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches))
{
return array(
- 'markup' => $matches[0],
+ 'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
- if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches))
+ if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w[\w-]*+(?:[ ]*+'.$this->regexHtmlAttribute.')*+[ ]*+\/?>/s', $Excerpt['text'], $matches))
{
return array(
- 'markup' => $matches[0],
+ 'element' => array('rawHtml' => $matches[0]),
'extent' => strlen($matches[0]),
);
}
@@ -1275,23 +1494,16 @@ class Parsedown
protected function inlineSpecialCharacter($Excerpt)
{
- if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text']))
- {
+ if (substr($Excerpt['text'], 1, 1) !== ' ' and strpos($Excerpt['text'], ';') !== false
+ and preg_match('/^&(#?+[0-9a-zA-Z]++);/', $Excerpt['text'], $matches)
+ ) {
return array(
- 'markup' => '&',
- 'extent' => 1,
+ 'element' => array('rawHtml' => '&' . $matches[1] . ';'),
+ 'extent' => strlen($matches[0]),
);
}
- $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot');
-
- if (isset($SpecialCharacter[$Excerpt['text'][0]]))
- {
- return array(
- 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';',
- 'extent' => 1,
- );
- }
+ return;
}
protected function inlineStrikethrough($Excerpt)
@@ -1307,8 +1519,11 @@ class Parsedown
'extent' => strlen($matches[0]),
'element' => array(
'name' => 'del',
- 'text' => $matches[1],
- 'handler' => 'line',
+ 'handler' => array(
+ 'function' => 'lineElements',
+ 'argument' => $matches[1],
+ 'destination' => 'elements',
+ )
),
);
}
@@ -1321,16 +1536,19 @@ class Parsedown
return;
}
- if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE))
- {
+ if (strpos($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' => $matches[0][0],
+ 'text' => $url,
'attributes' => array(
- 'href' => $matches[0][0],
+ 'href' => $url,
),
),
);
@@ -1341,9 +1559,9 @@ class Parsedown
protected function inlineUrlTag($Excerpt)
{
- if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches))
+ if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w++:\/{2}[^ >]++)>/i', $Excerpt['text'], $matches))
{
- $url = str_replace(array('&', '<'), array('&', '<'), $matches[1]);
+ $url = $matches[1];
return array(
'extent' => strlen($matches[0]),
@@ -1362,56 +1580,189 @@ class Parsedown
protected function unmarkedText($text)
{
- if ($this->breaksEnabled)
- {
- $text = preg_replace('/[ ]*\n/', "
\n", $text);
- }
- else
- {
- $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
\n", $text);
- $text = str_replace(" \n", "\n", $text);
- }
-
- return $text;
+ $Inline = $this->inlineText($text);
+ return $this->element($Inline['element']);
}
#
# Handlers
#
- protected function element(array $Element)
+ protected function handle(array $Element)
{
- $markup = '<'.$Element['name'];
-
- if (isset($Element['attributes']))
+ if (isset($Element['handler']))
{
- foreach ($Element['attributes'] as $name => $value)
+ if (!isset($Element['nonNestables']))
{
- if ($value === null)
- {
- continue;
- }
-
- $markup .= ' '.$name.'="'.$value.'"';
+ $Element['nonNestables'] = array();
}
- }
- if (isset($Element['text']))
- {
- $markup .= '>';
-
- if (isset($Element['handler']))
+ if (is_string($Element['handler']))
{
- $markup .= $this->{$Element['handler']}($Element['text']);
+ $function = $Element['handler'];
+ $argument = $Element['text'];
+ unset($Element['text']);
+ $destination = 'rawHtml';
}
else
{
- $markup .= $Element['text'];
+ $function = $Element['handler']['function'];
+ $argument = $Element['handler']['argument'];
+ $destination = $Element['handler']['destination'];
}
- $markup .= '';
+ $Element[$destination] = $this->{$function}($argument, $Element['nonNestables']);
+
+ if ($destination === 'handler')
+ {
+ $Element = $this->handle($Element);
+ }
+
+ unset($Element['handler']);
}
- else
+
+ 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 .= ' />';
}
@@ -1423,12 +1774,26 @@ class Parsedown
{
$markup = '';
+ $autoBreak = true;
+
foreach ($Elements as $Element)
{
- $markup .= "\n" . $this->element($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 .= "\n";
+ $markup .= $autoBreak ? "\n" : '';
return $markup;
}
@@ -1437,21 +1802,49 @@ class Parsedown
protected function li($lines)
{
- $markup = $this->lines($lines);
+ $Elements = $this->linesElements($lines);
- $trimmedMarkup = trim($markup);
-
- if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '')
- {
- $markup = $trimmedMarkup;
- $markup = substr($markup, 3);
-
- $position = strpos($markup, "
");
-
- $markup = substr_replace($markup, '', $position, 4);
+ if ( ! in_array('', $lines)
+ and isset($Elements[0]) and isset($Elements[0]['name'])
+ and $Elements[0]['name'] === 'p'
+ ) {
+ unset($Elements[0]['name']);
}
- return $markup;
+ 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;
}
#
@@ -1465,10 +1858,83 @@ class Parsedown
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]))
@@ -1495,12 +1961,12 @@ class Parsedown
# Read-Only
protected $specialCharacters = array(
- '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|',
+ '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', '~'
);
protected $StrongRegex = array(
- '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s',
- '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us',
+ '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*+[*])+?)[*]{2}(?![*])/s',
+ '_' => '/^__((?:\\\\_|[^_]|_[^_]*+_)+?)__(?!_)/us',
);
protected $EmRegex = array(
@@ -1508,7 +1974,7 @@ class Parsedown
'_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us',
);
- protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?';
+ 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',
@@ -1519,10 +1985,10 @@ class Parsedown
'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing',
'i', 'rp', 'del', 'code', 'strike', 'marquee',
'q', 'rt', 'ins', 'font', 'strong',
- 's', 'tt', 'sub', 'mark',
- 'u', 'xm', 'sup', 'nobr',
- 'var', 'ruby',
- 'wbr', 'span',
- 'time',
+ 's', 'tt', 'kbd', 'mark',
+ 'u', 'xm', 'sub', 'nobr',
+ 'sup', 'ruby',
+ 'var', 'span',
+ 'wbr', 'time',
);
}