fork(1) download 
  1. <?php
  2.  
  3. 		function FixUTF8($args) {
  4. 			$output = $args['input'];
  5.  
  6. 			$output = convertNamedHTMLEntitiesToNumeric(['input'=>$output]);
  7.  
  8. 			preg_match_all('/(&#[0-9]+;)/', $output, $matches, PREG_OFFSET_CAPTURE);
  9. 			$full_matches = $matches[0];
  10.  
  11. 			$found = [];
  12. 			$search = [];
  13. 			$replace = [];
  14.  
  15. 			for($i = 0; $i < count($full_matches); $i++) {
  16. 				$match = $full_matches[$i];
  17. 				$word = $match[0];
  18. 				if(!$found[$word]) {
  19. 					$found[$word] = TRUE;
  20. 					$search[] = $word;
  21. 					$replacement = str_replace(['&#', ';'], ['HTML Entity #', ''], $word);
  22. 					$replace[] = $replacement;
  23. 				}
  24. 			}
  25.  
  26. 			$new_output = str_replace($search, $replace, $output);
  27.  
  28. 			return $new_output;
  29. 		}
  30.  
  31. 		function convertNamedHTMLEntitiesToNumeric($args) {
  32. 			$input = $args['input'];
  33. 			return preg_replace_callback("/(&[a-zA-Z][a-zA-Z0-9]*;)/",function($m){
  34. 				$c = html_entity_decode($m[0],ENT_HTML5,"UTF-8");
  35. 				# return htmlentities($c,ENT_XML1,"UTF-8"); -- see update below
  36.  
  37. 				$convmap = array(0x80, 0xffff, 0, 0xffff);
  38. 				return mb_encode_numericentity($c, $convmap, 'UTF-8');
  39. 			}, $input);
  40. 		}
  41.  
  42. print(FixUTF8(['input'=>"Oggi &egrave; un bel&nbsp;giorno"]));
Success #stdin #stdout #stderr 0.02s 26660KB
comments (?)
stdin 
Standard input is empty
stdout 
Oggi HTML Entity #232 un belHTML Entity #160giorno
stderr 
PHP Notice:  Undefined index: &#232; in /home/TEPVwT/prog.php on line 18
PHP Notice:  Undefined index: &#160; in /home/TEPVwT/prog.php on line 18
https://ideone.com/PPAo1g
language:
PHP (php 7.3.5)
created:
3 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!