KernelLand/Kernel/utf16.c

   1 /*
   2  * Acess2 Kernel
   3  * - By John Hodge (thePowersGang)
   4  *
   5  * utf16.c
   6  * - UTF-16 Translation/Manipulation
   7  */
   8 #define DEBUG   0
   9 #include <acess.h>
  10 #include <utf16.h>
  11 #include <ctype.h>
  12
  13 int ReadUTF16(const Uint16 *Str16, Uint32 *Codepoint)
  14 {
  15         if( 0xD800 < *Str16 && *Str16 <= 0xDFFF )
  16         {
  17                 // UTF-16 surrogate pair
  18                 // > 0xDC00 is the second word
  19                 if( Str16[0] > 0xDC00 ) {
  20                         *Codepoint = 0;
  21                         return 1;
  22                 }
  23                 if( Str16[1] < 0xD800 || Str16[1] >= 0xDC00 ) {
  24                         *Codepoint = 0;
  25                         return 2;
  26                 }
  27                 // 2^16 + 20-bit
  28                 *Codepoint = 0x10000 + (((Str16[0] & 0x3FF) << 10) | (Str16[1] & 0x3FF));
  29                 return 2;
  30         }
  31         else {
  32                 *Codepoint = *Str16;
  33                 return 1;
  34         }
  35 }
  36
  37 size_t UTF16_ConvertToUTF8(size_t DestLen, char *Dest, size_t SrcLen, const Uint16 *Source)
  38 {
  39          int    len = 0;
  40         for( ; *Source && SrcLen --; Source ++ )
  41         {
  42                 // TODO: Decode/Reencode
  43                 if( Dest && len < DestLen )
  44                         Dest[len] = *Source;
  45                 len += 1;
  46         }
  47         if( Dest && len < DestLen )
  48                 Dest[len] = 0;
  49         return len;
  50 }
  51
  52 int UTF16_CompareWithUTF8Ex(size_t Str16Len, const Uint16 *Str16, const char *Str8, int bCaseInsensitive)
  53 {
  54          int    pos16 = 0, pos8 = 0;
  55         const Uint8     *str8 = (const Uint8 *)Str8;
  56
  57         while( pos16 < Str16Len && Str16[pos16] && str8[pos8] )
  58         {
  59                 Uint32  cp8, cp16;
  60                 pos16 += ReadUTF16(Str16+pos16, &cp16);
  61                 pos8 += ReadUTF8(str8 + pos8, &cp8);
  62                 if( bCaseInsensitive ) {
  63                         cp16 = toupper(cp16);
  64                         cp8 = toupper(cp8);
  65                 }
  66
  67                 LOG("cp16 = %x, cp8 = %x", cp16, cp8);
  68                 if(cp16 == cp8) continue ;
  69
  70                 if(cp16 < cp8)
  71                         return -1;
  72                 else
  73                         return 1;
  74         }
  75         if( pos16 == Str16Len )
  76                 return 0;
  77         if( Str16[pos16] && str8[pos8] )
  78                 return 0;
  79         if( Str16[pos16] )
  80                 return 1;
  81         else
  82                 return -1;
  83 }
  84
  85 int UTF16_CompareWithUTF8(size_t Str16Len, const Uint16 *Str16, const char *Str8)
  86 {
  87         return UTF16_CompareWithUTF8Ex(Str16Len, Str16, Str8, 0);
  88 }
  89
  90 int UTF16_CompareWithUTF8CI(size_t Str16Len, const Uint16 *Str16, const char *Str8)
  91 {
  92         return UTF16_CompareWithUTF8Ex(Str16Len, Str16, Str8, 1);
  93 }
  94