/**
+----------------------------------------------------------
* 字符串截取,支持中文和其他编码
+----------------------------------------------------------
* @static
* @access public
+----------------------------------------------------------
* @param string $str 需要转换的字符串
* @param string $start 开始位置
* @param string $length 截取长度
* @param string $charset 编码格式
* @param string $suffix 截断显示字符
+----------------------------------------------------------
* @return string
+----------------------------------------------------------
*/
function msubstr($str, $start=0, $length, $charset="utf-8", $suffix=true) {
if(function_exists("mb_substr"))
$slice = mb_substr($str, $start, $length, $charset);
elseif(function_exists('iconv_substr')) {
$slice = iconv_substr($str,$start,$length,$charset);
if(false === $slice) {
$slice = '';
}
}else{
$re['utf-8'] = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xff][\x80-\xbf]{3}/";
$re['gb2312'] = "/[\x01-\x7f]|[\xb0-\xf7][\xa0-\xfe]/";
$re['gbk'] = "/[\x01-\x7f]|[\x81-\xfe][\x40-\xfe]/";
$re['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
preg_match_all($re[$charset], $str, $match);
$slice = join("",array_slice($match[0], $start, $length));
}
return $suffix ? $slice.'...' : $slice;
}
/**
+----------------------------------------------------------
* 检查字符串是否是UTF8编码
+----------------------------------------------------------
* @param string $string 字符串
+----------------------------------------------------------
* @return Boolean
+----------------------------------------------------------
*/
function is_utf8($string) {
return preg_match('%^(?:
[\x09\x0A\x0D\x20-\x7E] # ASCII
| [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte
| \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte
| \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates
| \xF0[\x90-\xBF][\x80-\xBF]{2} # planes 1-3
| [\xF1-\xF3][\x80-\xBF]{3} # planes 4-15
| \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16
)*$%xs', $string);
}
function remove_xss($val) {
// remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
// this prevents some character re-spacing such as <java\0script>
// note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
$val = preg_replace('/([\x00-\x08,\x0b-\x0c,\x0e-\x19])/', '', $val);
// straight replacements, the user should never need these since they're normal characters
// this prevents like <IMG SRC=@avascript:alert('XSS')>
$search = 'abcdefghijklmnopqrstuvwxyz';
$search .= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
$search .= '1234567890!@#$%^&*()';
$search .= '~`";:?+/={}[]-_|\'\\';
for ($i = 0; $i < strlen($search); $i++) {
// ;? matches the ;, which is optional
// 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
// @ @ search for the hex values
$val = preg_replace('/(&#[xX]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val); // with a ;
// @ @ 0{0,7} matches '0' zero to seven times
$val = preg_replace('/(�{0,8}'.ord($search[$i]).';?)/', $search[$i], $val); // with a ;
}
// now the only remaining whitespace attacks are \t, \n, and \r
$ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base');
$ra2 = array('onabort', 'onactivate', 'onafterprint', 'onafterupdate', 'onbeforeactivate', 'onbeforecopy', 'onbeforecut', 'onbeforedeactivate', 'onbeforeeditfocus', 'onbeforepaste', 'onbeforeprint', 'onbeforeunload', 'onbeforeupdate', 'onblur', 'onbounce', 'oncellchange', 'onchange', 'onclick', 'oncontextmenu', 'oncontrolselect', 'oncopy', 'oncut', 'ondataavailable', 'ondatasetchanged', 'ondatasetcomplete', 'ondblclick', 'ondeactivate', 'ondrag', 'ondragend', 'ondragenter', 'ondragleave', 'ondragover', 'ondragstart', 'ondrop', 'onerror', 'onerrorupdate', 'onfilterchange', 'onfinish', 'onfocus', 'onfocusin', 'onfocusout', 'onhelp', 'onkeydown', 'onkeypress', 'onkeyup', 'onlayoutcomplete', 'onload', 'onlosecapture', 'onmousedown', 'onmouseenter', 'onmouseleave', 'onmousemove', 'onmouseout', 'onmouseover', 'onmouseup', 'onmousewheel', 'onmove', 'onmoveend', 'onmovestart', 'onpaste', 'onpropertychange', 'onreadystatechange', 'onreset', 'onresize', 'onresizeend', 'onresizestart', 'onrowenter', 'onrowexit', 'onrowsdelete', 'onrowsinserted', 'onscroll', 'onselect', 'onselectionchange', 'onselectstart', 'onstart', 'onstop', 'onsubmit', 'onunload');
$ra = array_merge($ra1, $ra2);
$found = true; // keep replacing as long as the previous round replaced something
while ($found == true) {
$val_before = $val;
for ($i = 0; $i < sizeof($ra); $i++) {
$pattern = '/';
for ($j = 0; $j < strlen($ra[$i]); $j++) {
if ($j > 0) {
$pattern .= '(';
$pattern .= '(&#[xX]0{0,8}([9ab]);)';
$pattern .= '|';
$pattern .= '|(�{0,8}([9|10|13]);)';
$pattern .= ')*';
}
$pattern .= $ra[$i][$j];
}
$pattern .= '/i';
$replacement = substr($ra[$i], 0, 2).'<x>'.substr($ra[$i], 2); // add in <> to nerf the tag
$val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
if ($val_before == $val) {
// no replacements were made, so exit the loop
$found = false;
}
}
}
return $val;
}
转载于:https://my.oschina.net/yoke/blog/75286