[ticket/9933] Move word censor regex into separate function in functions.php

PHPBB3-9933
This commit is contained in:
rxu 2011-01-05 21:13:33 +07:00 committed by Andreas Fischer
parent 9a25e4ad89
commit 951b7b22e0
2 changed files with 43 additions and 18 deletions

View file

@ -82,26 +82,9 @@ class cache extends acm
$result = $db->sql_query($sql);
$censors = array();
$unicode = ((version_compare(PHP_VERSION, '5.1.0', '>=') || (version_compare(PHP_VERSION, '5.0.0-dev', '<=') && version_compare(PHP_VERSION, '4.4.0', '>='))) && @preg_match('/\p{L}/u', 'a') !== false) ? true : false;
while ($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);

View file

@ -3428,6 +3428,48 @@ function get_preg_expression($mode)
return '';
}
/**
* 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))
{
$unicode = ((version_compare(PHP_VERSION, '5.1.0', '>=') || (version_compare(PHP_VERSION, '5.0.0-dev', '<=') && version_compare(PHP_VERSION, '4.4.0', '>='))) && @preg_match('/\p{L}/u', 'a') !== false) ? true : false;
}
if ($unicode)
{
// Unescape the asterisk to simplify further conversions
$word = str_replace('\*', '*', preg_quote($word, '#'));
// 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.