1
0
mirror of https://github.com/erusev/parsedown.git synced 2023-08-10 21:13:06 +03:00

Compare commits

...

47 Commits
0.1.2 ... 0.4.7

Author SHA1 Message Date
a4fb0651d5 resolve #27 2013-11-13 01:07:39 +02:00
50a58eab16 Merge pull request #29 from hkdobrev/multi-line-emphasis
Allow multi-line emphasis. Fix #28.
2013-11-12 12:46:05 -08:00
1f347e17eb Allow multi-line emphasis. Fix #28. 2013-11-12 19:22:17 +02:00
df3db71698 add 5.2 to PHP versions to test against 2013-11-10 11:02:18 +02:00
a37f5ff31e improve tests 2013-11-10 10:44:52 +02:00
8e6f4cf7b8 leading spaces should not get trimmed 2013-11-09 22:23:56 +02:00
ee9a1e92c0 remove goto comment 2013-11-09 00:40:13 +02:00
689ef24cc5 strip trailing spaces 2013-11-08 23:40:00 +02:00
4403fe4d96 labels of reference links should be case insensitive 2013-11-08 21:59:26 +02:00
400c8f7d46 simplify regex for inline link in attempt to resolve #23 2013-11-08 00:24:40 +02:00
379cbf34b3 parse_block_elements doesn't have to use ltrim on lines with no indentation 2013-11-07 22:48:15 +02:00
b6c8cac512 optimize quick paragraph 2013-11-07 22:46:01 +02:00
0e9202689e escaping of "<" breaks span-level html 2013-11-05 21:40:33 +02:00
7249d02cff code blocks get unwanted empty lines 2013-11-05 10:21:48 +02:00
ecf86b073e error when last line consists of 1-3 spaces 2013-11-05 10:17:19 +02:00
b12973415f parse link references as blocks to improve performance 2013-11-05 00:57:16 +02:00
6d113f47fb rearrange block types to optimize performance 2013-11-04 09:28:50 +02:00
d4d3612710 escaping for special characters 2013-11-03 17:32:45 +02:00
2e314ad474 resolve #24 2013-11-02 21:42:55 +02:00
e475602e2f simplify parsing of code blocks 2013-11-02 02:18:13 +02:00
f43f54b877 remove redundant parse_inline_elements call 2013-10-23 00:50:32 +03:00
d733acc94e add .idea to .gitignore 2013-10-23 00:44:21 +03:00
6a0695deb9 correct spelling of $link_definition 2013-10-13 22:52:36 +03:00
5dd40e7adf add test for horizontal rule 2013-09-24 22:53:42 +03:00
b9808f23e0 setext underlines should not work on interrupted paragraphs 2013-09-24 22:36:24 +03:00
47b1789430 resolve #9 2013-09-24 02:32:58 +03:00
f8119fa3cb separate compiling from parsing 2013-09-24 01:19:17 +03:00
d306ee3db5 improve tests 2013-09-24 01:09:13 +03:00
e15241cb92 remove incomplete tests 2013-09-24 01:00:20 +03:00
7ab71ade06 optimize parsing of rule 2013-09-20 02:12:06 +03:00
64f82e1e2a inline links should get parsed before reference links 2013-09-20 01:12:40 +03:00
f40dbdfb65 variable names should express what they represent rather than why they represent it 2013-09-19 23:54:28 +03:00
033c2b78c1 match blockquote comment 2013-09-19 23:28:12 +03:00
34035316df NULL » null 2013-09-19 23:12:48 +03:00
f13214cfa7 single line blockquotes should also go through "parse_lines" 2013-09-18 19:53:44 +03:00
238b1029c0 remove "parse_blocks" method in favor of a more capable "parse_lines" 2013-09-18 00:27:35 +03:00
bc27850c41 improve emphasis test 2013-09-03 00:15:25 +03:00
3afeee3b19 parse * and _ emphasis types separately to optimize performance and improve readability 2013-09-03 00:14:04 +03:00
a94a45f955 reference_link test should reference md.png with a relative path 2013-09-02 22:12:43 +03:00
4af89c5087 reference links should be able to have their names on the next line 2013-08-31 22:27:38 +03:00
0352f01c7e leading \n characters should not be parsed as part of first block 2013-08-31 21:44:23 +03:00
40c2dcfac7 resolve #20 2013-08-31 20:28:23 +03:00
097ec5e8a5 test case should deal with \r characters 2013-08-31 20:11:48 +03:00
8ac52a2f30 resolve #17 2013-08-31 19:55:07 +03:00
4a6bb88239 improve the code that removes \r characters 2013-08-31 19:54:14 +03:00
609ad47c38 resolve #16 2013-07-26 00:08:52 +03:00
7d7e89f5c3 remove 5.2 from PHP versions to test against 2013-07-25 01:49:02 +03:00
80 changed files with 985 additions and 858 deletions

1
.gitignore vendored
View File

@ -1,2 +1,3 @@
.DS_Store
.idea
nbproject

View File

@ -5,3 +5,7 @@ php:
- 5.4
- 5.3
- 5.2
matrix:
allow_failures:
- php: 5.2

View File

@ -50,7 +50,8 @@ class Parsedown
$text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text);
# Removes \r characters.
$text = str_replace("\r", '', $text);
$text = str_replace("\r\n", "\n", $text);
$text = str_replace("\r", "\n", $text);
# Replaces tabs with spaces.
$text = str_replace("\t", ' ', $text);
@ -74,21 +75,14 @@ class Parsedown
}
}
# Extracts link references.
if (preg_match_all('/^[ ]{0,3}\[(.+)\][ ]?:[ ]*\n?[ ]*(.+)$/m', $text, $matches, PREG_SET_ORDER))
{
foreach ($matches as $matches)
{
$this->reference_map[$matches[1]] = $matches[2];
$text = str_replace($matches[0], '', $text);
}
}
# ~
$text = $this->parse_blocks($text);
$text = preg_replace('/\n\s*\n/', "\n\n", $text);
$text = trim($text, "\n");
$lines = explode("\n", $text);
$text = $this->parse_block_elements($lines);
# Decodes escape sequences (leaves out backslashes).
@ -106,379 +100,431 @@ class Parsedown
# Private Methods
#
private function parse_blocks($text)
private function parse_block_elements(array $lines, $context = '')
{
# Divides text into blocks.
$blocks = preg_split('/\n\s*\n/', $text, -1, PREG_SPLIT_NO_EMPTY);
$elements = array();
# Makes sure compound blocks get rendered.
$blocks []= NULL;
$element = array(
'type' => '',
);
$markup = '';
# Parses blocks.
foreach ($blocks as $block)
foreach ($lines as $line)
{
if (isset($block) and $block[0] >= 'A')
{
$quick_block = $block;
# Block-Level HTML
unset($block);
if ($element['type'] === 'block' and ! isset($element['closed']))
{
if (preg_match('{<'.$element['subtype'].'>$}', $line)) # <open>
{
$element['depth']++;
}
# List
if (isset($block) and preg_match('/^([ ]{0,3})(\d+[.]|[*+-])[ ]/', $block, $matches)) # list item
if (preg_match('{</'.$element['subtype'].'>$}', $line)) # </close>
{
if (isset($list)) # subsequent
{
$list .= "\n\n".$block;
}
else # first
{
$list = $block;
$list_indentation = strlen($matches[1]);
list($list_type, $list_marker_pattern) = ($matches[2] === '-' or $matches[2] === '+' or $matches[2] === '*')
? array('ul', '[*+-]')
: array('ol', '\d+[.]');
$element['depth'] > 0
? $element['depth']--
: $element['closed'] = true;
}
unset($block);
$element['text'] .= "\n".$line;
continue;
}
elseif (isset($block) and isset($list) and $block[0] === ' ') # list item block
{
$list .= "\n\n".$block;
unset($block);
# Empty
if ($line === '')
{
$element['interrupted'] = true;
continue;
}
elseif (isset($list))
{
$markup .= '<'.$list_type.'>'."\n";
# Of the same type and indentation.
$list_items = preg_split('/^([ ]{'.$list_indentation.'})'.$list_marker_pattern.'[ ]/m', $list, -1, PREG_SPLIT_NO_EMPTY);
# Lazy Blockquote
foreach ($list_items as $list_item)
if ($element['type'] === 'blockquote' and ! isset($element['interrupted']))
{
$markup .= '<li>';
$line = preg_replace('/^[ ]*>[ ]?/', '', $line);
if (strpos($list_item, "\n\n")) # sparse
{
$list_item = trim($list_item, "\n");
$element['lines'] []= $line;
if (strpos($list_item, "\n\n"))
continue;
}
# Lazy List Item
if ($element['type'] === 'li')
{
$list_item = preg_replace('/^[ ]{0,4}/m', '', $list_item);
$list_item = $this->parse_blocks($list_item);
if (preg_match('/^([ ]{0,3})(\d+[.]|[*+-])[ ](.*)/', $line, $matches))
{
if ($element['indentation'] !== $matches[1])
{
$element['lines'] []= $line;
}
else
{
$list_item = $this->parse_lines($list_item);
unset($element['last']);
$elements []= $element;
$element = array(
'type' => 'li',
'indentation' => $matches[1],
'last' => true,
'lines' => array(
preg_replace('/^[ ]{0,4}/', '', $matches[3]),
),
);
}
$markup .= "\n".$list_item;
continue;
}
else # dense
if (isset($element['interrupted']))
{
$list_item = trim($list_item, "\n");
if ($line[0] === ' ')
{
$element['lines'] []= '';
$list_item = strpos($list_item, "\n")
? $this->parse_lines($list_item)
: $this->parse_inline_elements($list_item);
$line = preg_replace('/^[ ]{0,4}/', '', $line);;
$markup .= $list_item;
$element['lines'] []= $line;
continue;
}
}
else
{
$line = preg_replace('/^[ ]{0,4}/', '', $line);;
$element['lines'] []= $line;
continue;
}
}
$markup .= '</li>'."\n";
}
# Quick Paragraph
$markup .= '</'.$list_type.'>'."\n";
unset($list);
if ($line[0] >= 'a' or $line[0] >= 'A' and $line[0] <= 'Z')
{
goto paragraph;
}
# Code Block
if (isset($block) and strlen($block) > 4 and $block[0] === ' ' and $block[1] === ' ' and $block[2] === ' ' and $block[3] === ' ')
if ($line[0] === ' ' and preg_match('/^[ ]{4}(.*)/', $line, $matches))
{
if (isset($code_block))
if (trim($line) === '')
{
$code_block .= "\n\n".$block;
continue;
}
if ($element['type'] === 'code')
{
if (isset($element['interrupted']))
{
$element['text'] .= "\n";
unset ($element['interrupted']);
}
$element['text'] .= "\n".$matches[1];
}
else
{
$code_block = $block;
$elements []= $element;
$element = array(
'type' => 'code',
'text' => $matches[1],
);
}
unset($block);
continue;
}
elseif (isset($code_block))
# Setext Header (---)
if ($line[0] === '-' and $element['type'] === 'p' and ! isset($element['interrupted']) and preg_match('/^[-]+[ ]*$/', $line))
{
$code_block_text = preg_replace('/^[ ]{4}/m', '', $code_block);
$code_block_text = htmlentities($code_block_text, ENT_NOQUOTES);
$element['type'] = 'h.';
$element['level'] = 2;
# Decodes encoded escape sequences if present.
strpos($code_block_text, "\x1A\\") !== FALSE and $code_block_text = strtr($code_block_text, $this->escape_sequence_map);
$markup .= '<pre><code>'.$code_block_text.'</code></pre>'."\n";
unset($code_block);
continue;
}
# Atx Heading
# Atx Header (#)
if (isset($block) and $block[0] === '#' and preg_match('/^(#{1,6})[ ]*(.+?)[ ]*#*$/', $block, $matches))
if ($line[0] === '#' and preg_match('/^(#{1,6})[ ]*(.+?)[ ]*#*$/', $line, $matches))
{
$elements []= $element;
$level = strlen($matches[1]);
$heading = $this->parse_inline_elements($matches[2]);
$markup .= '<h'.$level.'>'.$heading.'</h'.$level.'>'."\n";
$element = array(
'type' => 'h.',
'text' => $matches[2],
'level' => $level,
);
continue;
}
# Quote Block
# Setext Header (===)
if (isset($block) and preg_match('/^[ ]{0,3}>/', $block))
if ($line[0] === '=' and $element['type'] === 'p' and ! isset($element['interrupted']) and preg_match('/^[=]+[ ]*$/', $line))
{
$block = preg_replace('/^[ ]{0,3}>[ ]?/m', '', $block);
$block = $this->parse_blocks($block);
$markup .= '<blockquote>'."\n".$block.'</blockquote>'."\n";
continue;
}
# Horizontal Line
if (isset($block) and preg_match('/^[ ]{0,3}([-*_])([ ]{0,2}\1){2,}$/', $block))
{
$markup .= '<hr />'."\n";
$element['type'] = 'h.';
$element['level'] = 1;
continue;
}
# ~
if (isset($quick_block))
{
$block = $quick_block;
$pure_line = $line[0] !== ' ' ? $line : ltrim($line);
unset ($quick_block);
if ($pure_line === '')
{
continue;
}
#
# Paragraph
# Link Reference
if (isset($block))
if ($pure_line[0] === '[' and preg_match('/^\[(.+?)\]:[ ]*([^ ]+)/', $pure_line, $matches))
{
if (strpos($block, "\n"))
$label = strtolower($matches[1]);
$url = trim($matches[2], '<>');
$this->reference_map[$label] = $url;
continue;
}
# Blockquote
if ($pure_line[0] === '>' and preg_match('/^>[ ]?(.*)/', $pure_line, $matches))
{
$markup .= $this->parse_lines($block);
if ($element['type'] === 'blockquote')
{
if (isset($element['interrupted']))
{
$element['lines'] []= '';
unset($element['interrupted']);
}
$element['lines'] []= $matches[1];
}
else
{
$element_text = $this->parse_inline_elements($block);
$element = '<p>'.$element_text.'</p>'."\n";
$elements []= $element;
$markup .= $element;
}
}
$element = array(
'type' => 'blockquote',
'lines' => array(
$matches[1],
),
);
}
return $markup;
continue;
}
private function parse_lines($text)
# HTML
if ($pure_line[0] === '<')
{
$text = trim($text, "\n");
# Block-Level HTML <self-closing/>
$lines = explode("\n", $text);
if (preg_match('{^<.+?/>$}', $pure_line))
{
$elements []= $element;
$lines []= NULL;
$element = array(
'type' => '',
'text' => $pure_line,
);
continue;
}
# Block-Level HTML <open>
if (preg_match('{^<(\w+)(?:[ ].*?)?>}', $pure_line, $matches))
{
$elements []= $element;
$element = array(
'type' => 'block',
'subtype' => strtolower($matches[1]),
'text' => $pure_line,
'depth' => 0,
);
preg_match('{</'.$matches[1].'>\s*$}', $pure_line) and $element['closed'] = true;
continue;
}
}
# Horizontal Rule
if (preg_match('/^([-*_])([ ]{0,2}\1){2,}[ ]*$/', $pure_line))
{
$elements []= $element;
$element = array(
'type' => 'hr',
);
continue;
}
# List Item
if (preg_match('/^([ ]*)(\d+[.]|[*+-])[ ](.*)/', $line, $matches))
{
$elements []= $element;
$element = array(
'type' => 'li',
'ordered' => isset($matches[2][1]),
'indentation' => $matches[1],
'last' => true,
'lines' => array(
preg_replace('/^[ ]{0,4}/', '', $matches[3]),
),
);
continue;
}
# ~
paragraph:
if ($element['type'] === 'p')
{
if (isset($element['interrupted']))
{
$elements []= $element;
$element['text'] = $line;
unset($element['interrupted']);
}
else
{
$element['text'] .= "\n".$line;
}
}
else
{
$elements []= $element;
$element = array(
'type' => 'p',
'text' => $line,
);
}
}
$elements []= $element;
array_shift($elements);
#
# ~
#
$markup = '';
foreach ($lines as $line)
foreach ($elements as $index => $element)
{
if (isset($line) and $line === '')
switch ($element['type'])
{
unset($line);
}
case 'li':
# Paragraph
if (isset($line) and $line[0] >= 'A')
if (isset($element['ordered'])) # first
{
$quick_line = $line;
unset($line);
}
# List
if (isset($line) and preg_match('/^([ ]*)(\d+[.]|[*+-])[ ](.*)/', $line, $matches)) # list item
{
$list_item_indentation = strlen($matches[1]);
$list_item_type = ($matches[2] === '-' or $matches[2] === '+' or $matches[2] === '*')
? 'ul'
: 'ol';
if (isset($list)) # subsequent
{
if ($list_item_indentation === $list_indentation and $list_item_type === $list_type)
{
# Adds last list item to the list.
$list []= $list_item;
# Creates a separate list item.
$list_item = $matches[3];
}
else
{
# Adds line to the current list item.
$list_item .= "\n".$line;
}
}
else # first
{
$list = array();
$list_indentation = $list_item_indentation;
$list_type = $list_item_type;
$list_item = $matches[3];
}
unset($line);
}
else
{
if (isset($list))
{
$list []= $list_item;
$list_type = $element['ordered'] ? 'ol' : 'ul';
$markup .= '<'.$list_type.'>'."\n";
foreach ($list as $list_item)
{
$list_item_text = strpos($list_item, "\n")
? $this->parse_lines($list_item)
: $this->parse_inline_elements($list_item);
$markup .= '<li>'.$list_item_text.'</li>'."\n";
}
$markup .= '</'.$list_type.'>'."\n";
unset($list);
}
if (isset($element['interrupted']) and ! isset($element['last']))
{
$element['lines'] []= '';
}
# Quote Block
$text = $this->parse_block_elements($element['lines'], 'li');
if (isset($line) and preg_match('/^[ ]*>[ ]?(.*)/', $line, $matches))
$markup .= '<li>'.$text.'</li>'."\n";
isset($element['last']) and $markup .= '</'.$list_type.'>'."\n";
break;
case 'p':
$text = $this->parse_inline_elements($element['text']);
$text = preg_replace('/[ ]{2}\n/', '<br />'."\n", $text);
if ($context === 'li' and $index === 0)
{
if (isset($quote))
if (isset($element['interrupted']))
{
$quote .= "\n".$matches[1];
$markup .= "\n".'<p>'.$text.'</p>'."\n";
}
else
{
$quote = $matches[1];
}
unset($line);
}
else
{
if (isset($quote))
{
$quote = $this->parse_blocks($quote);
$markup .= '<blockquote>'."\n".$quote.'</blockquote>'."\n";
unset($quote);
}
}
# Atx Heading
if (isset($atx_heading))
{
$markup .= '<h'.$atx_heading_level.'>'.$atx_heading.'</h'.$atx_heading_level.'>'."\n";
unset($atx_heading);
}
if (isset($line) and $line[0] === '#' and preg_match('/^(#{1,6})[ ]*(.+?)[ ]*#*$/', $line, $matches))
{
$atx_heading_level = strlen($matches[1]);
$atx_heading = $this->parse_inline_elements($matches[2]);
unset($line);
}
# Setext Heading
if (isset($line) and isset($paragraph))
{
$setext_characters = array('=', '-');
foreach ($setext_characters as $index => $setext_character)
{
if ($line[0] === $setext_character and preg_match('/^['.$setext_character.']+[ ]*$/', $line))
{
$setext_heading_level = $index + 1;
$setext_heading_text = $this->parse_inline_elements($paragraph);
$markup .= '<h'.$setext_heading_level.'>'.$setext_heading_text.'</h'.$setext_heading_level.'>'."\n";
unset($paragraph, $line);
continue 2;
}
}
}
# Paragraph
if (isset($quick_line))
{
$line = $quick_line;
unset($quick_line);
}
if (isset($line))
{
substr($line, -2) === ' '
and $line = substr($line, 0, -2)
and $line .= '<br/>';
if (isset($paragraph))
{
$paragraph .= "\n".$line;
}
else
{
$paragraph = $line;
$markup .= $text;
}
}
else
{
if (isset($paragraph))
{
$element_text = $this->parse_inline_elements($paragraph);
$markup .= '<p>'.$element_text.'</p>'."\n";
unset($paragraph);
$markup .= '<p>'.$text.'</p>'."\n";
}
break;
case 'code':
$text = htmlentities($element['text'], ENT_NOQUOTES);
strpos($text, "\x1A\\") !== FALSE and $text = strtr($text, $this->escape_sequence_map);
$markup .= '<pre><code>'.$text.'</code></pre>'."\n";
break;
case 'blockquote':
$text = $this->parse_block_elements($element['lines']);
$markup .= '<blockquote>'."\n".$text.'</blockquote>'."\n";
break;
case 'h.':
$text = $this->parse_inline_elements($element['text']);
$markup .= '<h'.$element['level'].'>'.$text.'</h'.$element['level'].'>'."\n";
break;
case 'hr':
$markup .= '<hr />'."\n";
break;
default:
$markup .= $element['text']."\n";
}
}
@ -522,15 +568,56 @@ class Parsedown
}
}
# Reference(d) Link / Image
# Inline Link / Image
if ($this->reference_map and strpos($text, '[') !== FALSE and preg_match_all('/(!?)\[(.+?)\][ ]?\[(.+?)\]/', $text, $matches, PREG_SET_ORDER))
if (strpos($text, '](') !== FALSE and preg_match_all('/(!?)(\[((?:[^\[\]]|(?2))*)\])\((.*?)\)/', $text, $matches, PREG_SET_ORDER)) # inline
{
foreach ($matches as $matches)
{
if (array_key_exists($matches[3], $this->reference_map))
$url = $matches[4];
strpos($url, '&') !== FALSE and $url = preg_replace('/&(?!#?\w+;)/', '&amp;', $url);
if ($matches[1]) # image
{
$url = $this->reference_map[$matches[3]];
$element = '<img alt="'.$matches[3].'" src="'.$url.'">';
}
else
{
$element_text = $this->parse_inline_elements($matches[3]);
$element = '<a href="'.$url.'">'.$element_text.'</a>';
}
# ~
$code = "\x1A".'$'.$index;
$text = str_replace($matches[0], $code, $text);
$map[$code] = $element;
$index ++;
}
}
# Reference(d) Link / Image
if ($this->reference_map and strpos($text, '[') !== FALSE and preg_match_all('/(!?)\[(.+?)\](?:\n?[ ]?\[(.*?)\])?/ms', $text, $matches, PREG_SET_ORDER))
{
foreach ($matches as $matches)
{
$link_definition = isset($matches[3]) && $matches[3]
? $matches[3]
: $matches[2]; # implicit
$link_definition = strtolower($link_definition);
if (isset($this->reference_map[$link_definition]))
{
$url = $this->reference_map[$link_definition];
strpos($url, '&') !== FALSE and $url = preg_replace('/&(?!#?\w+;)/', '&amp;', $url);
if ($matches[1]) # image
{
@ -556,44 +643,19 @@ class Parsedown
}
}
# Inline Link / Image
if (strpos($text, '](') !== FALSE and preg_match_all('/(!?)(\[((?:[^][]+|(?2))*)\])\((.*?)\)/', $text, $matches, PREG_SET_ORDER)) # inline
{
foreach ($matches as $matches)
{
if ($matches[1]) # image
{
$element = '<img alt="'.$matches[3].'" src="'.$matches[4].'">';
}
else
{
$element_text = $this->parse_inline_elements($matches[3]);
$element = '<a href="'.$matches[4].'">'.$element_text.'</a>';
}
$element_text = $this->parse_inline_elements($matches[1]);
# ~
$code = "\x1A".'$'.$index;
$text = str_replace($matches[0], $code, $text);
$map[$code] = $element;
$index ++;
}
}
# Automatic Links
if (strpos($text, '<') !== FALSE and preg_match_all('/<((https?|ftp|dict):[^\^\s]+?)>/i', $text, $matches, PREG_SET_ORDER))
{
foreach ($matches as $matches)
{
$url = $matches[1];
strpos($url, '&') !== FALSE and $url = preg_replace('/&(?!#?\w+;)/', '&amp;', $url);
$element = '<a href=":href">:text</a>';
$element = str_replace(':text', $matches[1], $element);
$element = str_replace(':href', $matches[1], $element);
$element = str_replace(':text', $url, $element);
$element = str_replace(':href', $url, $element);
# ~
@ -607,10 +669,23 @@ class Parsedown
}
}
if (strpos($text, '*') !== FALSE or strpos($text, '_') !== FALSE)
# ~
strpos($text, '&') !== FALSE and $text = preg_replace('/&(?!#?\w+;)/', '&amp;', $text);
strpos($text, '<') !== FALSE and $text = preg_replace('/<(?!\/?\w.*?>)/', '&lt;', $text);
# ~
if (strpos($text, '_') !== FALSE)
{
$text = preg_replace('/(\*\*|__)(.+?[*_]*)(?<=\S)\1/', '<strong>$2</strong>', $text);
$text = preg_replace('/(\*|_)(.+?)(?<=\S)\1/', '<em>$2</em>', $text);
$text = preg_replace('/__(?=\S)(.+?)(?<=\S)__(?!_)/s', '<strong>$1</strong>', $text);
$text = preg_replace('/_(?=\S)(.+?)(?<=\S)_/s', '<em>$1</em>', $text);
}
if (strpos($text, '*') !== FALSE)
{
$text = preg_replace('/\*\*(?=\S)(.+?)(?<=\S)\*\*(?!\*)/s', '<strong>$1</strong>', $text);
$text = preg_replace('/\*(?=\S)(.+?)(?<=\S)\*/s', '<em>$1</em>', $text);
}
$text = strtr($text, $map);
@ -618,4 +693,3 @@ class Parsedown
return $text;
}
}

View File

@ -34,6 +34,8 @@ class Test extends PHPUnit_Framework_TestCase
continue;
$expected_markup = file_get_contents(__DIR__ . '/' . self::provider_dir . $basename . '.html');
$expected_markup = str_replace("\r\n", "\n", $expected_markup);
$expected_markup = str_replace("\r", "\n", $expected_markup);
$provider [] = array($markdown, $expected_markup);
}

View File

@ -4,11 +4,3 @@
<h4>This is an h4</h4>
<h5>This is an h5</h5>
<h6>This is an h6</h6>
<h1>This is a closed h1</h1>
<h2>This is a closed h2</h2>
<h3>This is a closed h3</h3>
<h4>This is a closed h4</h4>
<h5>This is a closed h5</h5>
<h6>This is a closed h6</h6>
<h1>This is an irregularly closed h1</h1>
<h4>This is an irregularly closed h4</h4>

View File

@ -9,19 +9,3 @@
##### This is an h5
###### This is an h6
# This is a closed h1 #
## This is a closed h2 ##
### This is a closed h3 ###
#### This is a closed h4 ####
##### This is a closed h5 #####
###### This is a closed h6 ######
# This is an irregularly closed h1 ###
#### This is an irregularly closed h4 ##

View File

@ -0,0 +1,6 @@
<h1>h1</h1>
<h2>h2</h2>
<h3>h3</h3>
<h4>h4</h4>
<h5>h5</h5>
<h6>h6</h6>

View File

@ -0,0 +1,11 @@
# h1 #
## h2 ##
### h3 ###
#### h4 ####
##### h5 #####
###### h6 ######

View File

@ -1,25 +1,9 @@
<p>Here's a regular blockquote:</p>
<p>Here's a blockquote:</p>
<blockquote>
<p>This is a blockquote.</p>
<p>blockquote</p>
</blockquote>
<p>Here's one with no space after the ">":</p>
<p>Here's one on multiple lines:</p>
<blockquote>
<p>This is a blockquote.</p>
</blockquote>
<p>Here's one with multiple paragraphs:</p>
<blockquote>
<p>This is line one.</p>
<p>This is line two.</p>
</blockquote>
<p>Here's one with multiple types of blocks:</p>
<blockquote>
<p>This is a quoted paragraph.</p>
<ul>
<li>This is a list item of a quoted list.</li>
<li>This is another list item.</li>
</ul>
<blockquote>
<p>This is a nested quote block.</p>
</blockquote>
<p>This is another paragraph.</p>
<p>line 1
line 2</p>
</blockquote>

View File

@ -1,24 +1,8 @@
Here's a regular blockquote:
Here's a blockquote:
> This is a blockquote.
> blockquote
Here's one with no space after the ">":
Here's one on multiple lines:
>This is a blockquote.
Here's one with multiple paragraphs:
> This is line one.
>
> This is line two.
Here's one with multiple types of blocks:
> This is a quoted paragraph.
>
> - This is a list item of a quoted list.
> - This is another list item.
>
> > This is a nested quote block.
>
> This is another paragraph.
> line 1
> line 2

View File

@ -0,0 +1,16 @@
<p>Here's one with multiple paragraphs:</p>
<blockquote>
<p>This is line one.</p>
<p>This is line two.</p>
</blockquote>
<p>Here's one with multiple types of blocks:</p>
<blockquote>
<p>This is a quoted paragraph.</p>
<ul>
<li>This is a list item of a quoted list.</li>
<li>This is another list item.</li>
</ul>
<blockquote>
<p>This is a nested quote block.</p>
</blockquote>
</blockquote>

View File

@ -0,0 +1,14 @@
Here's one with multiple paragraphs:
> This is line one.
>
> This is line two.
Here's one with multiple types of blocks:
> This is a quoted paragraph.
>
> - This is a list item of a quoted list.
> - This is another list item.
>
> > This is a nested quote block.

View File

@ -0,0 +1,11 @@
<p>Here's a lazy blockquote:</p>
<blockquote>
<p>line
line</p>
</blockquote>
<p>Here's one with multiple lines:</p>
<blockquote>
<p>line
line
line</p>
</blockquote>

View File

@ -0,0 +1,10 @@
Here's a lazy blockquote:
> line
line
Here's one with multiple lines:
> line
line
line

View File

@ -0,0 +1,12 @@
<p>Here's a blockquote with no space after the ">":</p>
<blockquote>
<p>blockquote</p>
</blockquote>
<p>Here's a blockquote with leading space:</p>
<blockquote>
<p>blockquote</p>
</blockquote>
<p>Here's a blockquote on the next line:</p>
<blockquote>
<p>blockquote</p>
</blockquote>

View File

@ -0,0 +1,10 @@
Here's a blockquote with no space after the ">":
>blockquote
Here's a blockquote with leading space:
> blockquote
Here's a blockquote on the next line:
> blockquote

View File

@ -1,9 +1,5 @@
<p>Here's a regular code block:</p>
<p>Here's a code block:</p>
<pre><code>&lt;?php
echo 'Hello World!';
?&gt;</code></pre>
<p>Here's one that holds a list:</p>
<pre><code>- list item
- another list item</code></pre>
$message = 'Hello World!';
echo $message;</code></pre>

View File

@ -1,13 +1,6 @@
Here's a regular code block:
Here's a code block:
<?php
echo 'Hello World!';
?>
Here's one that holds a list:
- list item
- another list item
$message = 'Hello World!';
echo $message;

View File

View File

View File

View File

@ -1,8 +1,11 @@
<p>Here's <em>an emphasis</em>.</p>
<p>A short emphasis <em>a</em> <em>b</em> .</p>
<p>A short one <em>a</em> <em>b</em> .</p>
<p>Here's <strong>a strong one</strong>. </p>
<p>Here's <em>an emphasis that uses underscores</em>. </p>
<p>Here's <strong>a strong emphasis that uses underscores</strong>.</p>
<p>This is _ not an emphasis _ neither is * that * .</p>
<p>Empty emphasis ** is not __ an emphasis.</p>
<p>Three asterisks are an emphasized asterisk <em>*</em> .</p>
<p>Here's <em>one that uses underscores</em>. </p>
<p>Here's <strong>a strong one that uses underscores</strong>.</p>
<p>This is not _ one _ neither is * this * neither is _ this_ neither is _this _.</p>
<p>An empty emphasis ** is not __ an emphasis.</p>
<p>A <em>multi-line
emphasis</em></p>
<p>A <strong>multi-line
strong emphasis</strong></p>

View File

@ -1,15 +1,19 @@
Here's *an emphasis*.
A short emphasis _a_ *b* .
A short one _a_ *b* .
Here's **a strong one**.
Here's _an emphasis that uses underscores_.
Here's _one that uses underscores_.
Here's __a strong emphasis that uses underscores__.
Here's __a strong one that uses underscores__.
This is _ not an emphasis _ neither is * that * .
This is not _ one _ neither is * this * neither is _ this_ neither is _this _.
Empty emphasis ** is not __ an emphasis.
An empty emphasis ** is not __ an emphasis.
Three asterisks are an emphasized asterisk *** .
A *multi-line
emphasis*
A **multi-line
strong emphasis**

View File

@ -0,0 +1,5 @@
<p><strong><em>em strong</em></strong></p>
<p><strong><em>one</em> at the start</strong></p>
<p><strong>one at the <em>end</em></strong></p>
<p><strong>one <em>in the</em> middle</strong></p>
<p><strong>one with <em>asterisks</em></strong></p>

View File

@ -0,0 +1,9 @@
___em strong___
___one_ at the start__
__one at the _end___
__one _in the_ middle__
**one with *asterisks***

View File

@ -1,6 +1,2 @@
<p>Here's an <em>emphasis</em> and here's an escaped *emphasis*. Here are also an escaped `code span`, escaped [inline link](http://example.com).</p>
<p>Here's <code>an escaped \*emphasis\* inside of a code span</code>.</p>
<p>Here's one inside of a code block:</p>
<pre><code>An escaped \*emphasis\*.</code></pre>
<p>Finally, an escaped reference:</p>
<p>[1]: http://example.com</p>
<p>Here's an <em>emphasis</em> and here's an escaped *emphasis*. Here are also an escaped `code span`, an escaped [inline link](http://example.com) and an escaped <code>\*emphasis\*</code> inside of a code span.</p>
<pre><code>An escaped \*emphasis\* inside of a code block.</code></pre>

View File

@ -1,11 +1,3 @@
Here's an *emphasis* and here's an escaped \*emphasis\*. Here are also an escaped \`code span\`, escaped \[inline link](http://example.com).
Here's an *emphasis* and here's an escaped \*emphasis\*. Here are also an escaped \`code span\`, an escaped \[inline link](http://example.com) and an escaped `\*emphasis\*` inside of a code span.
Here's `an escaped \*emphasis\* inside of a code span`.
Here's one inside of a code block:
An escaped \*emphasis\*.
Finally, an escaped reference:
\[1]: http://example.com
An escaped \*emphasis\* inside of a code block.

View File

@ -0,0 +1,10 @@
<p>Dashes:</p>
<hr />
<hr />
<hr />
<p>Asterisks:</p>
<hr />
<p>Underscores:</p>
<hr />
<p>On the next line:</p>
<hr />

View File

@ -0,0 +1,18 @@
Dashes:
---
- - -
- - -
Asterisks:
***
Underscores:
___
On the next line:
___

15
tests/data/html.html Normal file
View File

@ -0,0 +1,15 @@
<p>A self-closing tag:</p>
<hr/>
<p>One with attributes:</p>
<hr style="background: #eaa" />
<p>A bare element:</p>
<div>content</div>
<p>One with attributes:</p>
<a href="http://example.com">link</a>
<p>Nested elements:</p>
<div>
parent
<div>
child
</div>
</div>

24
tests/data/html.md Normal file
View File

@ -0,0 +1,24 @@
A self-closing tag:
<hr/>
One with attributes:
<hr style="background: #eaa" />
A bare element:
<div>content</div>
One with attributes:
<a href="http://example.com">link</a>
Nested elements:
<div>
parent
<div>
child
</div>
</div>

View File

@ -1,2 +1,2 @@
<p>Here's a <a href="http://parsedown.org">link</a>.</p>
<p>Here's an image link: <a href="http://daringfireball.net/projects/markdown/"><img alt="MD Logo" src="http://parsedown.org/md.png"></a>.</p>
<p>Here's a <a href="http://example.com">link</a>.</p>
<p>Here's one that is based on an image: <a href="http://daringfireball.net/projects/markdown/"><img alt="MD Logo" src="http://parsedown.org/md.png"></a>.</p>

View File

@ -1,3 +1,3 @@
Here's a [link](http://parsedown.org).
Here's a [link](http://example.com).
Here's an image link: [![MD Logo](http://parsedown.org/md.png)](http://daringfireball.net/projects/markdown/).
Here's one that is based on an image: [![MD Logo](http://parsedown.org/md.png)](http://daringfireball.net/projects/markdown/).

View File

@ -0,0 +1,2 @@
<p>line<br />
line</p>

2
tests/data/line_break.md Normal file
View File

@ -0,0 +1,2 @@
line
line

5
tests/data/list.html Normal file
View File

@ -0,0 +1,5 @@
<p>Here's a list:</p>
<ul>
<li>li</li>
<li>li</li>
</ul>

4
tests/data/list.md Normal file
View File

@ -0,0 +1,4 @@
Here's a list:
- li
- li

View File

@ -7,4 +7,3 @@ Here's a compound list:
- This is another list item.
> This is a quote block that belongs to it.

View File

@ -0,0 +1,4 @@
<ul>
<li>li
more text</li>
</ul>

View File

@ -0,0 +1,2 @@
- li
more text

View File

@ -2,7 +2,6 @@
<ol>
<li>one</li>
<li>two</li>
<li>three</li>
</ol>
<p>Here's one with repeating numbers:</p>
<ol>
@ -12,5 +11,4 @@
<p>Here's one with large numbers:</p>
<ol>
<li>one</li>
<li>two</li>
</ol>

View File

@ -2,7 +2,6 @@ Here's a regular ordered list:
1. one
2. two
3. three
Here's one with repeating numbers:
@ -12,5 +11,3 @@ Here's one with repeating numbers:
Here's one with large numbers:
123. one
123. two

View File

@ -0,0 +1,16 @@
<p>Here's a sparse list:</p>
<ul>
<li>
<p>list item</p>
</li>
<li>another list item</li>
</ul>
<p>Here's one with an indented list item:</p>
<ul>
<li>
<p>li</p>
<ul>
<li>li</li>
</ul>
</li>
</ul>

View File

@ -0,0 +1,11 @@
Here's a sparse list:
- list item
- another list item
Here's one with an indented list item:
- li
- li

View File

@ -0,0 +1,11 @@
<p>Here's an unordered list:</p>
<ul>
<li>li</li>
<li>li</li>
</ul>
<p>Here's one with mixed markers:</p>
<ul>
<li>li</li>
<li>li</li>
<li>li</li>
</ul>

View File

@ -0,0 +1,10 @@
Here's an unordered list:
- li
- li
Here's one with mixed markers:
- li
+ li
* li

View File

@ -0,0 +1,5 @@
<p>Here's one with white space around items:</p>
<ul>
<li>li </li>
<li>li </li>
</ul>

View File

@ -0,0 +1,4 @@
Here's one with white space around items:
- li
- li

View File

@ -1,5 +0,0 @@
<p>Here's a list that's "inside" a paragraph:</p>
<ul>
<li>list item</li>
<li>another list item</li>
</ul>

View File

@ -1,4 +0,0 @@
Here's a list that's "inside" a paragraph:
- list item
- another list item

View File

@ -1,20 +0,0 @@
<p>Here's a regular quote block:</p>
<blockquote>
<p>Some quoted text.
Here goes some more.</p>
</blockquote>
<p>Here's one with space before lines:</p>
<blockquote>
<p>Some quoted text.
Here goes some more.</p>
</blockquote>
<p>Here's one with no space after >:</p>
<blockquote>
<p>Some quoted text.
Here goes some more.</p>
</blockquote>
<p>Here's one with no > on the second line:</p>
<blockquote>
<p>Some quoted text.
Here goes some more.</p>
</blockquote>

View File

@ -1,19 +0,0 @@
Here's a regular quote block:
> Some quoted text.
> Here goes some more.
Here's one with space before lines:
> Some quoted text.
> Here goes some more.
Here's one with no space after >:
>Some quoted text.
>Here goes some more.
Here's one with no > on the second line:
> Some quoted text.
Here goes some more.

View File

@ -1,8 +1,7 @@
<p>Here's a <a href="http://parsedown.org">reference link</a>.</p>
<p>Here's <a href="http://parsedown.org">one</a> with an alternative syntax.</p>
<p>Here's <a href="http://parsedown.org">one</a> on the next line.</p>
<p>Here's <a href="http://parsedown.org">one</a> on 2 lines.</p>
<p>Here's <a href="http://parsedown.org/tests/">one</a> with a different URL.</p>
<p>Here's <a href="http://parsedown.org">one</a> with a semantic name.</p>
<p>Here's a <a href="http://example.com">reference link</a>.</p>
<p>Here's <a href="http://example.com">one</a> with a semantic name.</p>
<p>Here's <a href="http://example.com">one</a> with an upper case label definition.</p>
<p>Here's <a href="http://example.com">one</a> with definition name on the next line.</p>
<p>Here's [one][404] with no definition.</p>
<p>Here's an image: <img alt="Markdown Logo" src="https://raw.github.com/dcurtis/markdown-mark/master/png/32x20-solid.png"></p>
<p>Here's a <a href="http://example.com">multiline
one</a> defined on 2 lines.</p>

View File

@ -1,29 +1,19 @@
Here's a [reference link][1].
[1]: http://parsedown.org
[1]: http://example.com
Here's [one] [2] with an alternative syntax.
Here's [one][website] with a semantic name.
[2] :http://parsedown.org
[website]: http://example.com
Here's [one][3] on the next line.
[3]: http://parsedown.org
Here's [one][case] with an upper case label definition.
Here's [one][4] on 2 lines.
[CASE]: http://example.com
[4]:
http://parsedown.org
Here's [one][5] with a different URL.
[5]: http://parsedown.org/tests/
Here's [one][the website] with a semantic name.
[the website]: http://parsedown.org
Here's [one]
[website] with definition name on the next line.
Here's [one][404] with no definition.
Here's an image: ![Markdown Logo][image]
[image]: https://raw.github.com/dcurtis/markdown-mark/master/png/32x20-solid.png
Here's a [multiline
one][website] defined on 2 lines.

View File

@ -0,0 +1 @@
<p>Here's an image: <img alt="Markdown Logo" src="/md.png"></p>

View File

@ -0,0 +1,3 @@
Here's an image: ![Markdown Logo][image]
[image]: /md.png

View File

@ -0,0 +1,2 @@
<p>Here's an <a href="http://example.com">implicit</a> reference link.</p>
<p>Here's an <a href="http://example.com">implicit</a> one with an empty link definition.</p>

View File

@ -0,0 +1,5 @@
Here's an [implicit] reference link.
[implicit]: http://example.com
Here's an [implicit][] one with an empty link definition.

View File

@ -0,0 +1 @@
<p>Here's a <a href="http://example.com">reference link</a> with a definition on the next line.</p>

View File

@ -0,0 +1,2 @@
Here's a [reference link][2] with a definition on the next line.
[2]: http://example.com

View File

@ -1,17 +0,0 @@
<p>Here's a regular list:</p>
<ul>
<li>list item</li>
<li>another list item</li>
<li>3rd list item</li>
</ul>
<p>Here's one with white space around items:</p>
<ul>
<li>list item </li>
<li>another list item </li>
</ul>
<p>Here's one with too much space before items:</p>
<pre><code>- list item
- another list item</code></pre>
<p>Here's one with no space after markers:</p>
<p>-list item
-another list item</p>

View File

@ -1,20 +0,0 @@
Here's a regular list:
- list item
- another list item
- 3rd list item
Here's one with white space around items:
- list item
- another list item
Here's one with too much space before items:
- list item
- another list item
Here's one with no space after markers:
-list item
-another list item

View File

@ -0,0 +1,5 @@
<h1>h1</h1>
<h2>h2</h2>
<h2>single character</h2>
<p>not a header</p>
<hr />

View File

@ -0,0 +1,12 @@
h1
==
h2
--
single character
-
not a header
------------

View File

@ -1,6 +0,0 @@
<h1>Heading 1</h1>
<h2>Heading 2</h2>
<h2>Block Heading</h2>
<p>This is the rest of the block.</p>
<h1>Single "="</h1>
<h2>Single "-"</h2>

View File

@ -1,16 +0,0 @@
Heading 1
=========
Heading 2
---------
Block Heading
-------------
This is the rest of the block.
Single "="
=
Single "-"
-

View File

@ -0,0 +1 @@
<p>Here's an <b>important</b> <a href=''>link</a>.</p>

View File

@ -0,0 +1 @@
Here's an <b>important</b> <a href=''>link</a>.

View File

@ -1,14 +0,0 @@
<p>Here's a list where items are separated by empty lines:</p>
<ul>
<li>
<p>list item</p>
</li>
<li>another list item</li>
</ul>
<p>Here's an ordered one:</p>
<ol>
<li>
<p>item one</p>
</li>
<li>item two</li>
</ol>

View File

@ -1,11 +0,0 @@
Here's a list where items are separated by empty lines:
- list item
- another list item
Here's an ordered one:
1. item one
2. item two

View File

@ -0,0 +1,7 @@
<p>AT&amp;T has an ampersand in their name.</p>
<p>AT&amp;T is another way to write it.</p>
<p>This &amp; that.</p>
<p>4 &lt; 5 and 6 > 5.</p>
<p>Here's an autolink <a href="http://example.com/autolink?a=1&amp;b=2">http://example.com/autolink?a=1&amp;b=2</a></p>
<p>Here's an inline <a href="/script?a=1&amp;b=2">link</a>.</p>
<p>Here's a reference <a href="http://example.com/?a=1&amp;b=2">link</a> with an ampersand in the URL.</p>

View File

@ -0,0 +1,15 @@
AT&T has an ampersand in their name.
AT&amp;T is another way to write it.
This & that.
4 < 5 and 6 > 5.
Here's an autolink <http://example.com/autolink?a=1&b=2>
Here's an inline [link](/script?a=1&b=2).
Here's a reference [link] [1] with an ampersand in the URL.
[1]: http://example.com/?a=1&b=2

View File

@ -1,20 +0,0 @@
<p>Here's a regular unordered list:</p>
<ul>
<li>list item</li>
<li>another list item</li>
<li>3rd list item</li>
</ul>
<p>Here's one with a variety of markers:</p>
<ul>
<li>hyphen</li>
<li>plus</li>
<li>asterisk</li>
</ul>
<p>Here's one with white space around items:</p>
<ul>
<li>list item </li>
<li>another list item </li>
</ul>
<p>Here's one with no space after markers:</p>
<p>-list item
-another list item</p>

View File

@ -1,21 +0,0 @@
Here's a regular unordered list:
- list item
- another list item
- 3rd list item
Here's one with a variety of markers:
- hyphen
+ plus
* asterisk
Here's one with white space around items:
- list item
- another list item
Here's one with no space after markers:
-list item
-another list item

View File

@ -0,0 +1 @@
<pre><code>This text starts with a line that consists of 4 spaces and it ends with one. This is a code block to make sure that leading spaces don't get trimmed.</code></pre>

5
tests/data/whitespace.md Normal file
View File

@ -0,0 +1,5 @@
This text starts with a line that consists of 4 spaces and it ends with one. This is a code block to make sure that leading spaces don't get trimmed.