I made some awesome progress on the UtfString system, it stores in native utf16

encoding to make things easier (little endian in our case).  It can currently
read utf8 and utf16be, but not BOM.  It will give you full unicode code points
instead of the raw utf16 values, which is pretty slick.

1 files changed, 18 insertions, 2 deletions

diff --git a/src/utfstring.h b/src/utfstring.h
index 6f85e93..79ef62e 100644
--- a/src/utfstring.h
+++ b/src/utfstring.h
@@ -9,9 +9,12 @@
 #define BU_UTF_STRING_H
 
 #include <stdint.h>
+#include "bu/array.h"
 
 namespace Bu
 {
+        class String;
+
         /**
          * UtfChar isn't actually a character, unicode specifies "code points" not
          * characters.  The main reason for this is that not all code points define
@@ -40,10 +43,23 @@ namespace Bu
                 UtfString( const Bu::String &sInput, Encoding eEnc=Utf8 );
                 virtual ~UtfString();
 
-                static void debugUtf8( const Bu::String &sUtf8 );
+                void append( UtfChar ch );
+
+                void set( const Bu::String &sInput, Encoding eEnc=Utf8 );
+                void setUtf8( const Bu::String &sInput );
+                void setUtf16( const Bu::String &sInput );
+//              void setUtf16be( const Bu::String &sInput );
+//              void setUtf16le( const Bu::String &sInput );
+
+                void debug();
+
+                UtfChar get( int iIndex );
+
+        private:
+                void append16( uint16_t i ) { aData.append( i ); }
 
         private:
-                uint16_t *pData;
+                Bu::Array<uint16_t> aData;
                 int iRawLen;
                 int iCharLen;
         };