Søren Løvborg printTruncated 函数的另一个细微变化使其与 UTF-8(需要 mbstring)兼容,并使其返回字符串而不是打印一个。我认为它更有用。而且我的代码没有像 Bounce 变体那样使用缓冲,只是多了一个变量。
UPD:要使其与标记属性中的 utf-8 字符一起正常工作,您需要 mb_preg_match 函数,如下所示。
非常感谢 Søren Løvborg 提供的功能,它非常好。
/* Truncate HTML, close opened tags
*
* @param int, maxlength of the string
* @param string, html
* @return $html
*/
function htmlTruncate($maxLength, $html)
{
mb_internal_encoding("UTF-8");
$printedLength = 0;
$position = 0;
$tags = array();
$out = "";
while ($printedLength < $maxLength && mb_preg_match('{</?([a-z]+)[^>]*>|&#?[a-zA-Z0-9]+;}', $html, $match, PREG_OFFSET_CAPTURE, $position))
{
list($tag, $tagPosition) = $match[0];
// Print text leading up to the tag.
$str = mb_substr($html, $position, $tagPosition - $position);
if ($printedLength + mb_strlen($str) > $maxLength)
{
$out .= mb_substr($str, 0, $maxLength - $printedLength);
$printedLength = $maxLength;
break;
}
$out .= $str;
$printedLength += mb_strlen($str);
if ($tag[0] == '&')
{
// Handle the entity.
$out .= $tag;
$printedLength++;
}
else
{
// Handle the tag.
$tagName = $match[1][0];
if ($tag[1] == '/')
{
// This is a closing tag.
$openingTag = array_pop($tags);
assert($openingTag == $tagName); // check that tags are properly nested.
$out .= $tag;
}
else if ($tag[mb_strlen($tag) - 2] == '/')
{
// Self-closing tag.
$out .= $tag;
}
else
{
// Opening tag.
$out .= $tag;
$tags[] = $tagName;
}
}
// Continue after the tag.
$position = $tagPosition + mb_strlen($tag);
}
// Print any remaining text.
if ($printedLength < $maxLength && $position < mb_strlen($html))
$out .= mb_substr($html, $position, $maxLength - $printedLength);
// Close any open tags.
while (!empty($tags))
$out .= sprintf('</%s>', array_pop($tags));
return $out;
}
function mb_preg_match(
$ps_pattern,
$ps_subject,
&$pa_matches,
$pn_flags = 0,
$pn_offset = 0,
$ps_encoding = NULL
) {
// WARNING! - All this function does is to correct offsets, nothing else:
//(code is independent of PREG_PATTER_ORDER / PREG_SET_ORDER)
if (is_null($ps_encoding)) $ps_encoding = mb_internal_encoding();
$pn_offset = strlen(mb_substr($ps_subject, 0, $pn_offset, $ps_encoding));
$ret = preg_match($ps_pattern, $ps_subject, $pa_matches, $pn_flags, $pn_offset);
if ($ret && ($pn_flags & PREG_OFFSET_CAPTURE))
foreach($pa_matches as &$ha_match) {
$ha_match[1] = mb_strlen(substr($ps_subject, 0, $ha_match[1]), $ps_encoding);
}
return $ret;
}