PHP intercepts HTML articles_PHP tutorial

PHP intercepts the html code and considers the closing problem of html tags

/* Generate summary
* @param (string) $body
* Text
* @param (int) $size
* Summary length
* @param (int) $format
* Input format id
*/
function blog_summary($body, $size, $format = NULL){
$_size = mb_strlen($body, "utf-8');
 
if($_size <= $size) return $body;
 
// There is a PHP filter in the input format
/*
if(!isset($format) && filter_is_php($format)){
Return $body;
}
*/
 
$strlen_var = strlen($body);
 
//Does not contain html tags
if(strpos($body, '<') === false){
Return mb_substr($body, 0, $size);
}
 
// Contains truncation flag, priority
if($e = strpos($body, '')){
Return mb_substr($body, 0, $e);
}
 
// html code tag
$html_tag = 0;
 
// Summary string
$summary_string = '';
 
/**
* The array is used to record the html tags
that appear within the summary range * The start and end are saved under the left and right key names respectively
* If the string is:

a

, assuming p is not closed
* The array is: array('left' => array('h3', 'p', 'b'), 'right' => 'b', 'h3');
* Only complete html tags, ​*/
$html_array = array('left' => array(), 'right' => array());
for($i = 0; $i < $strlen_var; ++$i) {
If(!$size){
Break;
}  
         
$current_var = substr($body, $i, 1);
         
If($current_var == '<'){
// html code starts
$html_tag = 1;
$html_array_str = '';
}else if($html_tag == 1){
// End of a piece of html code
If($current_var == '>'){
/**
* Remove leading and trailing spaces, such as
< img src="" / > etc. Leading and trailing spaces may appear
                     */
          $html_array_str = trim($html_array_str);
                                                                         /**
* Determine whether the last character is /, if so, the label is closed and
is not recorded                      */
If(substr($html_array_str, -1) != '/'){
                                                                      // Determine whether the first character is /, if so, place it in the right unit
              $f = substr($html_array_str, 0, 1);
If($f == '/'){
                           // Remove /                 $html_array['right'][] = str_replace('/', '', $html_array_str);
              }else if($f != '?'){
                       // Determine whether it is ?, if so, it is PHP code, skip
                                                                                   /**
* Determine whether there is a half-width space. If so, separate it with spaces. The first unit is the html tag
* Such as

                                                If(strpos($html_array_str, ' ') !== false){
                                     // Divide into 2 units, there may be multiple spaces, such as:

                  $html_array['left'][] = strtolower(current(explode(' ', $html_array_str, 2)));
              }else{
                /**
                     * * If there are no spaces, the entire string is an html tag, such as:

etc.
* Convert to lowercase letters
                               */ 
                  $html_array['left'][] = strtolower($html_array_str);
                                                                                                                                                                                                                                                  } 
                                                                         // String reset
          $html_array_str = '';
          $html_tag = 0;
}else{
/**
* Compose the characters between < > into a string
* Used to extract html tags
                     */
          $html_array_str .= $current_var;
}  
}else{
// Only non-html codes are counted
--$size;
}  
         
$ord_var_c = ord($body{$i});
         
switch (true) {
case (($ord_var_c & 0xE0) == 0xC0):
              // 2 bytes
          $summary_string .= substr($body, $i, 2);
         $i += 1;
Break;
case (($ord_var_c & 0xF0) == 0xE0):
                                                                                       // 3 bytes
          $summary_string .= substr($body, $i, 3);
         $i += 2;
Break;
case (($ord_var_c & 0xF8) == 0xF0):
              // 4 bytes
          $summary_string .= substr($body, $i, 4);
         $i += 3;
Break;
case (($ord_var_c & 0xFC) == 0xF8):
               // 5 bytes
          $summary_string .= substr($body, $i, 5);
         $i += 4;
Break;
case (($ord_var_c & 0xFE) == 0xFC):
              // 6 bytes
          $summary_string .= substr($body, $i, 6);
         $i += 5;
Break;
default:
              // 1 byte
         $summary_string .= $current_var;
}  
}

if($html_array['left']){
/**
* Compare the left and right html tags and complete them if they are insufficient
​​*/
         
/**
* Exchange the order of left, and the order of supplementation should be opposite to the order in which html appears
* * If the string to be completed is:

abcabc

abc
* * The supplementary order should be:

​​*/
$html_array['left'] = array_reverse($html_array['left']);
         
foreach($html_array['left'] as $index => $tag){
// Determine whether the tag appears in right
$key = array_search($tag, $html_array['right']);
If($key !== false){
// appears, delete the unit from right
         unset($html_array['right'][$key]);
}else{
                                                                                                                                                                                                                                                                    $summary_string .= '';
}  
}  
}
return $summary_string;
}

-->

http://www.bkjia.com/PHPjc/478039.htmlwww.bkjia.comtruehttp: //www.bkjia.com/PHPjc/478039.htmlTechArticlePHP intercepts the html code and considers the closing problem of html tags/* Generate summary* @param (string) $body * Text* @param (int) $size * Summary length* @param (int) $format * Input format...