From 5fa575f8ac284e060a8893c83c03a82bc55f57c1 Mon Sep 17 00:00:00 2001
From: "Edward Z. Yang" <edwardzyang@thewritingpot.com>
Date: Thu, 15 May 2008 05:16:36 +0000
Subject: [PATCH] [2.1.4] [MFH] Encoder optimization and shut-up operator
 bugfix from r1680

git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/branches/php4@1718 48356398-32a2-884e-a903-53898d9a118a
---
 NEWS                             |  2 ++
 library/HTMLPurifier/Encoder.php | 16 +++++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/NEWS b/NEWS
index 7ba715d6..627afd1d 100644
--- a/NEWS
+++ b/NEWS
@@ -17,6 +17,7 @@ ERRATA
 2.1.4, unknown release date
 ! DefinitionCacheFactory now can register new implementations
 ! CSS properties are now case-insensitive
+! Encoder optimized with valid UTF-8 input
 - Colors missing # but in hex form will be corrected
 - CSS Number algorithm improved
 - Autoclose now operates iteratively, i.e. <span><span><div> now has
@@ -26,6 +27,7 @@ ERRATA
 - Fix bug with rgb(0, 1, 2) color syntax with spaces inside shorthand syntax
 - HTMLPurifier_HTMLDefinition->addAttribute can now be called multiple times
   on the same element without emitting errors.
+- Iconv uses set_error_handler instead of shut-up operator
 
 2.1.3, released 2007-11-05
 ! tests/multitest.php allows you to test multiple versions by running
diff --git a/library/HTMLPurifier/Encoder.php b/library/HTMLPurifier/Encoder.php
index e5adf83f..31ebb785 100644
--- a/library/HTMLPurifier/Encoder.php
+++ b/library/HTMLPurifier/Encoder.php
@@ -62,6 +62,11 @@ class HTMLPurifier_Encoder
         trigger_error('Cannot instantiate encoder, call methods statically', E_USER_ERROR);
     }
     
+    /**
+     * Error-handler that mutes errors, alternative to shut-up operator.
+     */
+    function muteErrorHandler() {}
+    
     /**
      * Cleans a UTF-8 string for well-formedness and SGML validity
      * 
@@ -106,9 +111,18 @@ 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);
         }