[3.1.0] Encoder optimization, as suggested by Diego

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@1680 48356398-32a2-884e-a903-53898d9a118a

NEWS

@@ -12,7 +12,9 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 3.1.0, unknown release date
 - InterchangeBuilder now alphabetizes its lists
 - Validation error in configdoc output fixed
+- Iconv errors muted even with custom error handlers
 . Out-of-date documentation revised
+. UTF-8 encoding check optimization as suggested by Diego
 
 3.1.0rc1, released 2008-04-22
 # Autoload support added. Internal require_once's removed in favor of an

TODO

@@ -29,11 +29,14 @@ NICE FEATURES
 
 BUGS
  - Style attribute height/width limiting for images
- - Easy way to blacklist elements and attributes
- - Investigate iconv error emitting
- - Investigate UTF-8 optimization <http://htmlpurifier.org/phorum/read.php?3,1496>
  - Figure out what to do about target="" and name="", since they show up so often
 
+EXTERNAL
+ - Improve Phorum install documentation
+ - Mia
+ - Aliro
+ - Comparison: http://code.iamcal.com/php/lib_filter/
+
 FUTURE VERSIONS
 ---------------
 

library/HTMLPurifier/Encoder.php

@@ -14,6 +14,11 @@ class HTMLPurifier_Encoder
         trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
     }
     
+    /**
+     * Error-handler that mutes errors, alternative to shut-up operator.
+     */
+    private static function muteErrorHandler() {}
+    
     /**
      * Cleans a UTF-8 string for well-formedness and SGML validity
      * 
@@ -57,9 +62,18 @@ class HTMLPurifier_Encoder
         static $iconv = null;
         if ($iconv === null) $iconv = function_exists('iconv');
         
+        // UTF-8 validity is checked since PHP 4.3.5
+        // This is an optimization: if the string is already valid UTF-8, no
+        // need to do iconv/php stuff. 99% of the time, this will be the case.
+        if (preg_match('/^.{1}/us', $str)) {
+            return strtr($str, $non_sgml_chars);
+        }
+        
         if ($iconv && !$force_php) {
             // do the shortcut way
-            $str = @iconv('UTF-8', 'UTF-8//IGNORE', $str);
+            set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
+            $str = iconv('UTF-8', 'UTF-8//IGNORE', $str);
+            restore_error_handler();
             return strtr($str, $non_sgml_chars);
         }