diff options
| author | Igor Wiedler <igor@wiedler.ch> | 2011-01-16 20:25:06 +0100 |
|---|---|---|
| committer | Igor Wiedler <igor@wiedler.ch> | 2011-01-16 20:25:06 +0100 |
| commit | e9c584af6aee4d8cec81ad1f96066860ea878644 (patch) | |
| tree | 4f9b4ab59849c55c788d6d57c6aa11a898508d51 | |
| parent | 1359cf654714107f752d14a358d76ee310a9ff57 (diff) | |
| parent | 2b37a4fe56f86430733fd5757f6c8a4907f51a3f (diff) | |
| download | forums-e9c584af6aee4d8cec81ad1f96066860ea878644.tar forums-e9c584af6aee4d8cec81ad1f96066860ea878644.tar.gz forums-e9c584af6aee4d8cec81ad1f96066860ea878644.tar.bz2 forums-e9c584af6aee4d8cec81ad1f96066860ea878644.tar.xz forums-e9c584af6aee4d8cec81ad1f96066860ea878644.zip | |
Merge branch 'ticket/bantu/9933' into develop-olympus
* ticket/bantu/9933:
[ticket/9933] Remove empty word check.
[ticket/9933] Add $use_unicode parameter to get_censor_preg_expression().
[ticket/9933] Adjust word censor regex for non-unicode mode.
| -rw-r--r-- | phpBB/includes/functions.php | 30 | ||||
| -rw-r--r-- | tests/regex/censor_test.php | 14 |
2 files changed, 27 insertions, 17 deletions
diff --git a/phpBB/includes/functions.php b/phpBB/includes/functions.php index 69be1627cf..8697a0a472 100644 --- a/phpBB/includes/functions.php +++ b/phpBB/includes/functions.php @@ -3432,30 +3432,26 @@ function get_preg_expression($mode) * Generate regexp for naughty words censoring * Depends on whether installed PHP version supports unicode properties * -* @param string $word word template to be replaced +* @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, '#')); + // 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 $preg_expr; diff --git a/tests/regex/censor_test.php b/tests/regex/censor_test.php index ae2d86e07e..93c761c8d0 100644 --- a/tests/regex/censor_test.php +++ b/tests/regex/censor_test.php @@ -31,9 +31,19 @@ class phpbb_regex_censor_test extends phpbb_test_case /** * @dataProvider censor_test_data */ - public function test_censor($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); } |