1
0
mirror of https://github.com/phpbb/phpbb.git synced 2025-06-06 22:45:02 +02:00

Merge branch 'ticket/bantu/9933' into develop-olympus

* ticket/bantu/9933:
  [ticket/9933] Remove empty word check.
  [ticket/9933] Add $use_unicode parameter to get_censor_preg_expression().
  [ticket/9933] Adjust word censor regex for non-unicode mode.
This commit is contained in:
Igor Wiedler 2011-01-16 20:25:06 +01:00
commit e9c584af6a
2 changed files with 27 additions and 17 deletions

View File

@ -3433,29 +3433,25 @@ function get_preg_expression($mode)
* Depends on whether installed PHP version supports unicode properties
*
* @param string $word word template to be replaced
* @param bool $use_unicode whether or not to take advantage of PCRE supporting unicode
*
* @return string $preg_expr regex to use with word censor
*/
function get_censor_preg_expression($word)
function get_censor_preg_expression($word, $use_unicode = true)
{
static $unicode = null;
if (empty($word))
{
return '';
}
static $unicode_support = null;
// Check whether PHP version supports unicode properties
if (is_null($unicode))
if (is_null($unicode_support))
{
$unicode = ((version_compare(PHP_VERSION, '5.1.0', '>=') || (version_compare(PHP_VERSION, '5.0.0-dev', '<=') && version_compare(PHP_VERSION, '4.4.0', '>='))) && @preg_match('/\p{L}/u', 'a') !== false) ? true : false;
$unicode_support = ((version_compare(PHP_VERSION, '5.1.0', '>=') || (version_compare(PHP_VERSION, '5.0.0-dev', '<=') && version_compare(PHP_VERSION, '4.4.0', '>='))) && @preg_match('/\p{L}/u', 'a') !== false) ? true : false;
}
if ($unicode)
{
// Unescape the asterisk to simplify further conversions
$word = str_replace('\*', '*', preg_quote($word, '#'));
if ($use_unicode && $unicode_support)
{
// Replace asterisk(s) inside the pattern, at the start and at the end of it with regexes
$word = preg_replace(array('#(?<=[\p{Nd}\p{L}_])\*+(?=[\p{Nd}\p{L}_])#iu', '#^\*+#', '#\*+$#'), array('([\x20]*?|[\p{Nd}\p{L}_-]*?)', '[\p{Nd}\p{L}_-]*?', '[\p{Nd}\p{L}_-]*?'), $word);
@ -3464,7 +3460,11 @@ function get_censor_preg_expression($word)
}
else
{
$preg_expr = '#(?<!\S)(' . str_replace('\*', '\S*?', preg_quote($word, '#')) . ')(?!\S)#iu';
// Replace the asterisk inside the pattern, at the start and at the end of it with regexes
$word = preg_replace(array('#(?<=\S)\*+(?=\S)#iu', '#^\*+#', '#\*+$#'), array('(\x20*?\S*?)', '\S*?', '\S*?'), $word);
// Generate the final substitution
$preg_expr = '#(?<!\S)(' . $word . ')(?!\S)#iu';
}
return $preg_expr;

View File

@ -31,9 +31,19 @@ class phpbb_regex_censor_test extends phpbb_test_case
/**
* @dataProvider censor_test_data
*/
public function test_censor($pattern, $subject)
public function test_censor_unicode($pattern, $subject)
{
$regex = get_censor_preg_expression($pattern);
$regex = get_censor_preg_expression($pattern, true);
$this->assertRegExp($regex, $subject);
}
/**
* @dataProvider censor_test_data
*/
public function test_censor_no_unicode($pattern, $subject)
{
$regex = get_censor_preg_expression($pattern, false);
$this->assertRegExp($regex, $subject);
}