html包括文本内容,截断包含HTML的文本，忽略标签

我已经按照您的建议编写了一个将HTML截断的函数，但是没有打印出来，而是将其保存在字符串变量中。也处理HTML实体。

/**

*  function to truncate and then clean up end of the HTML,

*  truncates by counting characters outside of HTML tags

*

*  @author alex lockwood, alex dot lockwood at websightdesign

*

*  @param string $str the string to truncate

*  @param int $len the number of characters

*  @param string $end the end string for truncation

*  @return string $truncated_html

*

*  **/

public static function truncateHTML($str, $len, $end = '…'){

//find all tags

$tagPattern = '/(]*)>?|&[\w#]+;/i';  //match html tags and entities

preg_match_all($tagPattern, $str, $matches, PREG_OFFSET_CAPTURE | PREG_SET_ORDER );

//WSDDebug::dump($matches); exit;

$i =0;

//loop through each found tag that is within the $len, add those characters to the len,

//also track open and closed tags

// $matches[$i][0] = the whole tag string  --the only applicable field for html enitities

// IF its not matching an &htmlentity; the following apply

// $matches[$i][1] = the start of the tag either '

// $matches[$i][2] = the tag name

// $matches[$i][3] = the end of the tag

//$matces[$i][$j][0] = the string

//$matces[$i][$j][1] = the str offest

while($matches[$i][0][1] < $len && !empty($matches[$i])){

$len = $len + strlen($matches[$i][0][0]);

if(substr($matches[$i][0][0],0,1) == '&' )

$len = $len-1;

//if $matches[$i][2] is undefined then its an html entity, want to ignore those for tag counting

//ignore empty/singleton tags for tag counting

if(!empty($matches[$i][2][0]) && !in_array($matches[$i][2][0],array('br','img','hr', 'input', 'param', 'link'))){

//double check

if(substr($matches[$i][3][0],-1) !='/' && substr($matches[$i][1][0],-1) !='/')

$openTags[] = $matches[$i][2][0];

elseif(end($openTags) == $matches[$i][2][0]){

array_pop($openTags);

}else{

$warnings[] = "html has some tags mismatched in it:  $str";

}

}

$i++;

}

$closeTags = '';

if (!empty($openTags)){

$openTags = array_reverse($openTags);

foreach ($openTags as $t){

$closeTagString .="".$t . ">";

}

}

if(strlen($str)>$len){

// Finds the last space from the string new length

$lastWord = strpos($str, ' ', $len);

if ($lastWord) {

//truncate with new len last word

$str = substr($str, 0, $lastWord);

//finds last character

$last_character = (substr($str, -1, 1));

//add the end text

$truncated_html = ($last_character == '.' ? $str : ($last_character == ',' ? substr($str, 0, -1) : $str) . $end);

}

//restore any open tags

$truncated_html .= $closeTagString;

}else

$truncated_html = $str;

return $truncated_html;

}