aboutsummaryrefslogtreecommitdiff
path: root/src/utfstring.h
diff options
context:
space:
mode:
Diffstat (limited to 'src/utfstring.h')
-rw-r--r--src/utfstring.h20
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 @@
9#define BU_UTF_STRING_H 9#define BU_UTF_STRING_H
10 10
11#include <stdint.h> 11#include <stdint.h>
12#include "bu/array.h"
12 13
13namespace Bu 14namespace Bu
14{ 15{
16 class String;
17
15 /** 18 /**
16 * UtfChar isn't actually a character, unicode specifies "code points" not 19 * UtfChar isn't actually a character, unicode specifies "code points" not
17 * characters. The main reason for this is that not all code points define 20 * characters. The main reason for this is that not all code points define
@@ -40,10 +43,23 @@ namespace Bu
40 UtfString( const Bu::String &sInput, Encoding eEnc=Utf8 ); 43 UtfString( const Bu::String &sInput, Encoding eEnc=Utf8 );
41 virtual ~UtfString(); 44 virtual ~UtfString();
42 45
43 static void debugUtf8( const Bu::String &sUtf8 ); 46 void append( UtfChar ch );
47
48 void set( const Bu::String &sInput, Encoding eEnc=Utf8 );
49 void setUtf8( const Bu::String &sInput );
50 void setUtf16( const Bu::String &sInput );
51// void setUtf16be( const Bu::String &sInput );
52// void setUtf16le( const Bu::String &sInput );
53
54 void debug();
55
56 UtfChar get( int iIndex );
57
58 private:
59 void append16( uint16_t i ) { aData.append( i ); }
44 60
45 private: 61 private:
46 uint16_t *pData; 62 Bu::Array<uint16_t> aData;
47 int iRawLen; 63 int iRawLen;
48 int iCharLen; 64 int iCharLen;
49 }; 65 };