fork download 
  1. <?php
  2.  
  3. // your code goes here
  4. $text = '<strong>&amp;foo < FOO<em class="bar">bar</em></strong>';
  5.  
  6.     $document = <<<EOD
  7. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://w...content-available-to-author-only...3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  8. <html xmlns="http://w...content-available-to-author-only...3.org/1999/xhtml">
  9. <head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head>
  10. <body>!html</body>
  11. </html>
  12. EOD;
  13.     // PHP's \DOMDocument serialization adds straw whitespace in case the markup
  14.     // of the wrapping document contains newlines, so ensure to remove all
  15.     // newlines before injecting the actual HTML body to process.
  16.     $document = strtr($document, array("\n" => '', '!html' => $text));
  17.  
  18.     $dom = new \DOMDocument();
  19.     // Ignore warnings during HTML soup loading.
  20.     @$dom->loadHTML($document);
  21.  
  22.     $body_node = $dom->getElementsByTagName('body')->item(0);
  23.     $html = '';
  24.  
  25.     foreach ($body_node->getElementsByTagName('script') as $node) {
  26.       static::escapeCdataElement($node);
  27.     }
  28.     foreach ($body_node->getElementsByTagName('style') as $node) {
  29.       static::escapeCdataElement($node, '/*', '*/');
  30.     }
  31.     foreach ($body_node->childNodes as $node) {
  32.       $html .= $dom->saveXML($node);
  33.     }
  34.  
  35.     $text = $html;
  36.  
  37. preg_match_all('/<[^>]++>|[^<>\s]++/', $text, $tokens);
  38.  
  39. print_r($tokens);
  40.  
  41. $counter = 0;
  42. $maxlength = 5;
  43. $newtext = array();
  44. foreach ($tokens[0] as $token) {
  45. 	if (mb_substr($token, 0, 1, 'utf-8') === '<') {
  46. 		$newtext[] = $token;
  47. 		continue;
  48. 	}
  49. 	$counter += strlen(html_entity_decode($token));
  50. 	if ($counter > $maxlength) {
  51. 		break;
  52. 	}
  53. 	$newtext[] = $token;
  54. }
  55. $newtext = implode('', $newtext);
  56. print_r($tokens);
  57. print_r($newtext);
Success #stdin #stdout 0.01s 20568KB
comments (?)
stdin 
Standard input is empty
stdout 
Array
(
    [0] => Array
        (
            [0] => <strong>
            [1] => &amp;foo
            [2] => bar
            [3] => </strong>
        )

)
Array
(
    [0] => Array
        (
            [0] => <strong>
            [1] => &amp;foo
            [2] => bar
            [3] => </strong>
        )

)
<strong>&amp;foo
https://ideone.com/u0cd9c
language:
PHP (php 7.3.5)
created:
11 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!