Created
July 28, 2012 17:00
-
-
Save koenpunt/3194002 to your computer and use it in GitHub Desktop.
PHP port of gfm at https://gist.github.com/118964
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
function gfm($text){ | |
# Extract pre blocks | |
$extractions = array(); | |
$text = preg_replace_callback('/<pre>.*?<\/pre>/s', function($matches) use (&$extractions){ | |
$match = $matches[0]; | |
$md5 = md5($match); | |
$extractions[$md5] = $match; | |
return "{gfm-extraction-${md5}}"; | |
}, $text); | |
# prevent foo_bar_baz from ending up with an italic word in the middle | |
$text = preg_replace_callback('/(^(?! {4}|\t)\w+_\w+_\w[\w_]*)/s', function($matches){ | |
$x = $matches[0]; | |
$x_parts = str_split($x); | |
sort($x_parts); | |
if( substr(implode('', $x_parts), 0, 2) == '__' ){ | |
return str_replace('_', '\_', $x); | |
} | |
}, $text); | |
# in very clear cases, let newlines become <br /> tags | |
$text = preg_replace_callback('/^[\w\<][^\n]*\n+/m', function($matches){ | |
$x = $matches[0]; | |
if( !preg_match('/\n{2}/', $x) ){ | |
$x = trim($x); | |
$x .= " \n"; | |
} | |
return $x; | |
}, $text); | |
# Insert pre block extractions | |
$text = preg_replace_callback('/\{gfm-extraction-([0-9a-f]{32})\}/', function($matches) use (&$extractions){ | |
$match = $matches[1]; | |
return "\n\n" . $extractions[$match]; | |
}, $text); | |
return $text; | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
require 'gfm.php'; | |
class GFMTest extends PHPUnit_Framework_TestCase{ | |
public function testShouldNotTouchSingleUnderscoresInsideWords(){ | |
$this->assertEquals("foo_bar", gfm("foo_bar")); | |
} | |
public function testShouldNotTouchUnderscoresInCodeBlocks(){ | |
$this->assertEquals(" foo_bar_baz", gfm(" foo_bar_baz")); | |
} | |
public function testShouldNotTouchUnderscoresInPreBlocks(){ | |
$this->assertEquals("\n\n<pre>\nfoo_bar_baz\n</pre>", gfm("<pre>\nfoo_bar_baz\n</pre>")); | |
} | |
public function testShouldNotTreatPreBlocksWithPreTextDifferently(){ | |
$a = "\n\n<pre>\nthis is `a\\_test` and this\\_too\n</pre>"; | |
$b = "hmm<pre>\nthis is `a\\_test` and this\\_too\n</pre>"; | |
$this->assertEquals( substr(gfm($a), 2), substr(gfm($b), 3) ); | |
} | |
public function testShouldEscapeTwoOrMoreUnderscoresInsideWords(){ | |
$this->assertEquals( "foo\\_bar\\_baz", gfm("foo_bar_baz") ); | |
} | |
public function testShouldTurnNewlinesIntoBrTagsInSimpleCases(){ | |
$this->assertEquals( "foo \nbar", gfm("foo\nbar") ); | |
} | |
public function testShouldConvertNewlinesInAllGroups(){ | |
$this->assertEquals( "apple \npear \norange\n\nruby \npython \nerlang", | |
gfm("apple\npear\norange\n\nruby\npython\nerlang") ); | |
} | |
public function testShouldConvertNewlinesInEvenLongGroups(){ | |
$this->assertEquals( "apple \npear \norange \nbanana\n\nruby \npython \nerlang", | |
gfm("apple\npear\norange\nbanana\n\nruby\npython\nerlang") ); | |
} | |
public function testShouldNotConvertNewlinesInLists(){ | |
$this->assertEquals( "# foo\n# bar", gfm("# foo\n# bar") ); | |
$this->assertEquals( "* foo\n* bar", gfm("* foo\n* bar") ); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Nice work, man! Does it have a license or something? Or I can just use it?