下面将解码一个代码点并返回将字符串增加多少(“咀嚼”多少)。请注意,xs_utf16 是一个无符号短整数。更多信息:http ://sree.kotay.com/2006/12/unicode-is-pain-in.html
enum
{
xs_UTF_Max = 0x0010FFFFUL,
xs_UTF_Replace = 0x0000FFFDUL,
xs_UTF16_HalfBase = 0x00010000UL,
xs_UTF16_HighStart = 0x0000D800UL,
xs_UTF16_HighEnd = 0x0000DBFFUL,
xs_UTF16_LowStart = 0x0000DC00UL,
xs_UTF16_LowEnd = 0x0000DFFFUL,
xs_UTF16_MaxUCS2 = 0x0000FFFFUL,
xs_UTF16_HalfMask = 0x000003FFUL,
xs_UTF16_HalfShift = 10
};
int32 xs_UTF16Decode (uint32 &code, const xs_utf16* str, int32 len, bool strict)
{
if (str==0||len==0) {code=0; return 0;}
uint32 c1 = str[0];
//note: many implementations test from HighStart to HighEnd,
// this may be a partial code point, and is incorrect(?)
// trivial checking should exclude the WHOLE surrogate range
if (c1<xs_UTF16_HighStart || c1>xs_UTF16_LowEnd) return 1;
//really an error if we're starting in the low range
//surrogate pair
if (len<=1 || str[1]==0) {code=xs_UTF_Replace; return strict ? 0 : 1;} //error
uint32 c2 = str[1];
code = ((c1-xs_UTF16_HighStart)<<xs_UTF16_HalfShift) + (c2-xs_UTF16_LowStart) + xs_UTF16_HalfBase;
if (strict==false) return 2;
//check for errors
if (c1>=xs_UTF16_LowStart && c1<=xs_UTF16_LowEnd) {code=xs_UTF_Replace; return 0;} //error
if (c2<xs_UTF16_LowStart || c2>xs_UTF16_LowEnd) {code=xs_UTF_Replace; return 0;} //error
if (code>xs_UTF_Max) {code=xs_UTF_Replace; return 0;} //error
//success
return 2;
}