Changeset 18936 for S60/trunk/WebCore

Timestamp:

01/18/07 08:03:51 (2 years ago)

Author:

yongjzha

Message:

2007-01-18 sareen <shyam.sareen@yahoo.com>

Reviewed by Yongjun.
DESC: Wrong rendering of danish national characters for UTF8 coded web pages.(TSW ID: TMCN-6UQNXY)

Additional fix.

http://bugs.webkit.org/show_bug.cgi?id=12217

WARNING: NO TEST CASES ADDED OR CHANGED

• kwq/KWQTextCodec.cpp: (validateUtf8):

Location:

S60/trunk/WebCore

Files:

• ChangeLog (modified) (1 diff)
• kwq/KWQTextCodec.cpp (modified) (3 diffs)

S60/trunk/WebCore/ChangeLog

@@ +1 @@
+2007-01-18  sareen  <shyam.sareen@yahoo.com>
+
+        Reviewed by Yongjun.
+        DESC:  Wrong rendering of danish national characters for UTF8 coded web pages.(TSW ID: TMCN-6UQNXY)
+               Additional fix.
+        http://bugs.webkit.org/show_bug.cgi?id=12217
+
+        WARNING: NO TEST CASES ADDED OR CHANGED
+
+        * kwq/KWQTextCodec.cpp:
+        (validateUtf8):
+
 2007-01-17  w3liu  <wei.liu@nokia.com>
 

S60/trunk/WebCore/kwq/KWQTextCodec.cpp

@@ -106 +106 @@
     int seqRem=0;
     bool isUtf8 = true;
+    bool wrongUtf8 = false;
     validMultiByteChars = 0;
     while (c<e)
@@ -117 +118 @@
                 seqRem--;
             else {
-                isUtf8 = false;
-                break;
+                //Some times, there is wrong UTF-8 encoding in the characters.
+                //For example ( 0xd8 0x73). Then allow atleat one byte wrong encoding.
+                //This has been found in the real site. Also, this means here that is a 
+                //ASCII character.  ASCII can be handled in the UTF-8 also. 
+                wrongUtf8 = true;
             }
             if (seqRem==0)
@@ -139 +143 @@
             break;
         }
+        if ( wrongUtf8 ){
+             if( seqRem == 1 ){
+                 seqRem--; 
+                 wrongUtf8 = false;
+             }
+             else {
+                 isUtf8 = false;
+                 break; 
+             }
+         } //end if ( wrongUtf8 )
         c++;
-    }
+    } //end while
     return isUtf8;
 }