4 files changed, 86 insertions, 18 deletions
diff --git a/phpBB/includes/acp/acp_words.php b/phpBB/includes/acp/acp_words.php
index 35095d8b71..450a2fad4c 100644
--- a/phpBB/includes/acp/acp_words.php
+++ b/phpBB/includes/acp/acp_words.php
@@ -95,6 +95,9 @@ class acp_words
 					trigger_error($user->lang['ENTER_WORD'] . adm_back_link($this->u_action), E_USER_WARNING);
 				}
 
+				// Replace multiple consecutive asterisks with single one as those are not needed
+				$word = preg_replace('#\*{2,}#', '*', $word);
+
 				$sql_ary = array(
 					'word'			=> $word,
 					'replacement'	=> $replacement
diff --git a/phpBB/includes/cache.php b/phpBB/includes/cache.php
index 1986f021c6..49b690f1a4 100644
--- a/phpBB/includes/cache.php
+++ b/phpBB/includes/cache.php
@@ -82,26 +82,9 @@ class cache extends acm
 			$result = $db->sql_query($sql);
 
 			$censors = array();
-			$unicode = pcre_utf8_support();
-
 			while ($row = $db->sql_fetchrow($result))
 			{
-				if ($unicode)
-				{
-					// Unescape the asterisk to simplify further conversions
-					$row['word'] = str_replace('\*', '*', preg_quote($row['word'], '#'));
-					
-					// Replace the asterisk inside the pattern, at the start and at the end of it with regexes
-					$row['word'] = preg_replace(array('#(?<=[\p{Nd}\p{L}_])\*(?=[\p{Nd}\p{L}_])#iu', '#^\*#', '#\*$#'), array('([\x20]*?|[\p{Nd}\p{L}_-]*?)', '[\p{Nd}\p{L}_-]*?', '[\p{Nd}\p{L}_-]*?'), $row['word']);
-
-					// Generate the final substitution
-					$censors['match'][] = '#(?<![\p{Nd}\p{L}_-])(' . $row['word'] . ')(?![\p{Nd}\p{L}_-])#iu';
-				}
-				else
-				{
-					$censors['match'][] = '#(?<!\S)(' . str_replace('\*', '\S*?', preg_quote($row['word'], '#')) . ')(?!\S)#iu';
-				}
-
+				$censors['match'][] = get_censor_preg_expression($row['word']);
 				$censors['replace'][] = $row['replacement'];
 			}
 			$db->sql_freeresult($result);
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 $preg_expr;
+}
+
+/**
 * Returns the first block of the specified IPv6 address and as many additional
 * ones as specified in the length paramater.
 * If length is zero, then an empty string is returned.
diff --git a/tests/regex/censor.php b/tests/regex/censor.php
new file mode 100644
index 0000000000..ae2d86e07e
--- /dev/null
+++ b/tests/regex/censor.php
@@ -0,0 +1,40 @@
+<?php
+/**
+*
+* @package testing
+* @copyright (c) 2010 phpBB Group
+* @license http://opensource.org/licenses/gpl-license.php GNU Public License
+*
+*/
+
+require_once __DIR__ . '/../../phpBB/includes/functions.php';
+
+class phpbb_regex_censor_test extends phpbb_test_case
+{
+	public function censor_test_data()
+	{
+		return array(
+			array('bad*word', 'bad word'),
+			array('bad***word', 'bad word'),
+			array('bad**word', 'bad word'),
+			array('*bad*word*', 'bad word'),
+			array('b*d', 'bad'),
+			array('*bad*', 'bad'),
+			array('*b*d*', 'bad'),
+			array('*b*d*', 'b d'),
+			array('b*d*word', 'bad word'),
+			array('**b**d**word**', 'bad word'),
+			array('**b**d**word**', 'the bad word catched'),
+		);
+	}
+
+	/**
+	* @dataProvider censor_test_data
+	*/
+	public function test_censor($pattern, $subject)
+	{
+		$regex = get_censor_preg_expression($pattern);
+
+		$this->assertRegExp($regex, $subject);
+	}
+}
+\ No newline at end of file