/**
* 去掉字符串中的html标签
* 使用方法:
* <code>
* $input = '<a href="http://test/test.php" title="example">hello</a>';
* $output = Typecho_Common::stripTags($input, <a href="">);
* echo $output;
* //display: '<a href="http://test/test.php">hello</a>'
* </code>
*
* @access public
* @param string $string 需要处理的字符串
* @param string $allowableTags 需要忽略的html标签
* @return string
*/
public static function stripTags($html, $allowableTags = NULL)
{
if (!empty($allowableTags) && preg_match_all("/\\<([a-z]+)([^>]*)\\>/is", $allowableTags, $tags)) {
self::$_allowableTags = '|' . implode('|', $tags[1]) . '|';
if (in_array('code', $tags[1])) {
$html = self::lockHTML($html);
}
$normalizeTags = '<' . implode('><', $tags[1]) . '>';
$html = strip_tags($html, $normalizeTags);
$attributes = array_map('trim', $tags[2]);
$allowableAttributes = array();
foreach ($attributes as $key => $val) {
$allowableAttributes[$tags[1][$key]] = array_keys(self::__parseAtttrs($val));
}
self::$_allowableAttributes = $allowableAttributes;
$len = strlen($html);
$tag = '';
$attrs = '';
$pos = -1;
$quote = '';
$start = 0;
for ($i = 0; $i < $len; $i++) {
if ('<' == $html[$i] && -1 == $pos) {
$start = $i;
$pos = 0;
} else {
if (0 == $pos && '/' == $html[$i] && empty($tag)) {
$pos = -1;
} else {
if (0 == $pos && ctype_alpha($html[$i])) {
$tag .= $html[$i];
} else {
if (0 == $pos && ctype_space($html[$i])) {
$pos = 1;
} else {
if (1 == $pos && (!empty($quote) || '>' != $html[$i])) {
if (empty($quote) && ('"' == $html[$i] || "'" == $html[$i])) {
$quote = $html[$i];
} else {
if (!empty($quote) && $quote == $html[$i]) {
$quote = '';
}
}
$attrs .= $html[$i];
} else {
if (-1 != $pos && empty($quote) && '>' == $html[$i]) {
$out = self::__tagFilter($tag, $attrs);
$outLen = strlen($out);
$nextStart = $start + $outLen;
$tag = '';
$attrs = '';
$html = substr_replace($html, $out, $start, $i - $start + 1);
$len = strlen($html);
$i = $nextStart - 1;
$pos = -1;
}
}
}
}
}
}
}
$html = preg_replace_callback("/<\\/([_0-9a-z-]+)>/is", array('Typecho_Common', '__closeTagFilter'), $html);
$html = self::releaseHTML($html);
} else {
$html = strip_tags($html);
}
//去掉注释
return preg_replace("/<\\!\\-\\-[^>]*\\-\\->/s", '', $html);
}
