diff options
author | Andreas Fischer <bantu@phpbb.com> | 2011-01-07 15:58:10 +0100 |
---|---|---|
committer | Andreas Fischer <bantu@phpbb.com> | 2011-01-07 15:58:10 +0100 |
commit | 1c95101284d1545443bf6070d2f9dbc2880165f6 (patch) | |
tree | fe969e58749941a6754ecc882223a7c3b921e026 /phpBB/includes/functions.php | |
parent | 08f6a12325ab02696e0093ff7ddfb005dd7d2321 (diff) | |
parent | a469e804930e66c244da27deb4dc94b5e280659f (diff) | |
download | forums-1c95101284d1545443bf6070d2f9dbc2880165f6.tar forums-1c95101284d1545443bf6070d2f9dbc2880165f6.tar.gz forums-1c95101284d1545443bf6070d2f9dbc2880165f6.tar.bz2 forums-1c95101284d1545443bf6070d2f9dbc2880165f6.tar.xz forums-1c95101284d1545443bf6070d2f9dbc2880165f6.zip |
Merge branch 'develop-olympus' into develop
* develop-olympus:
[ticket/9933] Create unit test for word censor regular expression.
[ticket/9933] Move word censor regex into separate function in functions.php
[ticket/9933] Wrong handling consecutive multiple asterisks in word censor
Conflicts:
phpBB/includes/cache.php
Diffstat (limited to 'phpBB/includes/functions.php')
-rw-r--r-- | phpBB/includes/functions.php | 42 |
1 files changed, 42 insertions, 0 deletions
diff --git a/phpBB/includes/functions.php b/phpBB/includes/functions.php index 41dad77141..c55931a2fb 100644 --- a/phpBB/includes/functions.php +++ b/phpBB/includes/functions.php @@ -3250,6 +3250,48 @@ 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 +* +* @return string $preg_expr regex to use with word censor +*/ +function get_censor_preg_expression($word) +{ + static $unicode = null; + + if (empty($word)) + { + return ''; + } + + // Check whether PHP version supports unicode properties + if (is_null($unicode)) + { + $unicode = pcre_utf8_support(); + } + + if ($unicode) + { + // Unescape the asterisk to simplify further conversions + $word = str_replace('\*', '*', preg_quote($word, '#')); + + // 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); + + // Generate the final substitution + $preg_expr = '#(?<![\p{Nd}\p{L}_-])(' . $word . ')(?![\p{Nd}\p{L}_-])#iu'; + } + else + { + $preg_expr = '#(?<!\S)(' . str_replace('\*', '\S*?', preg_quote($word, '#')) . ')(?!\S)#iu'; + } + + return $preg_expr; +} + +/** * Returns the first block of the specified IPv6 address and as many additional * ones as specified in the length paramater. * If length is zero, then an empty string is returned. |