ch -= halfBase;
*target++ = （UTF16）（（ch 》 halfShift） + UNI_SUR_HIGH_START）；
*target++ = （UTF16）（（ch & halfMask） + UNI_SUR_LOW_START）；
}
}
*sourceStart = source;
*targetStart = target;
return result;
}
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF16toUTF32 （
const UTF16** sourceStart, const UTF16* sourceEnd,
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags） {
ConversionResult result = conversionOK;
const UTF16* source = *sourceStart;
UTF32* target = *targetStart;
UTF32 ch, ch2;
while （source < sourceEnd） {
const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
ch = *source++;
/* If we have a surrogate pair, convert to UTF32 first. */
if （ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END） {
/* If the 16 bits following the high surrogate are in the source buffer */
if （source < sourceEnd） {
ch2 = *source;
/* If it's a low surrogate, convert to UTF32. */
if （ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END） {
ch = （（ch - UNI_SUR_HIGH_START） 《 halfShift）
+ （ch2 - UNI_SUR_LOW_START） + halfBase;
++source;
} else if （flags == strictConversion） { /* it's an unpaired high surrogate */
--source; /* return to the illegal value itself */
result = sourceIllegal;
break;
}
} else { /* We don't have the 16 bits following the high surrogate. */
--source; /* return to the high surrogate */
result = sourceExhausted;
break;
}
} else if （flags == strictConversion） {
/* UTF-16 surrogate values are illegal in UTF-32 */
if （ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END） {
--source; /* return to the illegal value itself */
result = sourceIllegal;
break;
}
}
if （target >= targetEnd） {
source = oldSource; /* Back up source pointer! */
result = targetExhausted; break;
}
*target++ = ch;
}
*sourceStart = source;
*targetStart = target;
#ifdef CVTUTF_DEBUG
if （result == sourceIllegal） {
fprintf（stderr, "ConvertUTF16toUTF32 illegal seq 0x%04x,%04x\n", ch, ch2）；
fflush（stderr）；
}
#endif
return result;
}
/* --------------------------------------------------------------------- */
/*
* Index into the table below with the first byte of a UTF-8 sequence to
* get the number of trailing bytes that are supposed to follow it.
* Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
* left as-is for anyone who may want to do such conversion, which was
* allowed in earlier algorithms.
*/
static const char trailingBytesForUTF8[256] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};
/*
* Magic values subtracted from a buffer value during UTF8 conversion.
* This table contains as many values as there might be trailing bytes
* in a UTF-8 sequence.
*/
static const UTF32 offsetsFromUTF8 = { 0x00000000UL, 0x00003080UL, 0x000E2080UL,
0x03C82080UL, 0xFA082080UL, 0x82082080UL };
/*
* Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
* into the first byte, depending on how many bytes follow. There are
* as many entries in this table as there are UTF-8 sequence types.
* （I.e., one byte sequence, two byte etc.）。 Remember that sequencs
* for *legal* UTF-8 will be 4 or fewer bytes total.
*/
static const UTF8 firstByteMark = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
/* --------------------------------------------------------------------- */
/* The interface converts a whole buffer to avoid function-call overhead.
* Constants have been gathered. Loops & conditionals have been removed as
* much as possible for efficiency, in favor of drop-through switches.
* （See "Note A" at the bottom of the file for equivalent code.）
* If your compiler supports it, the "isLegalUTF8" call can be turned
* into an inline function.
*/
/* --------------------------------------------------------------------- */
ConversionResult ConvertUTF16toUTF8 （
const UTF16** sourceStart, const UTF16* sourceEnd,
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags） {
ConversionResult result = conversionOK;
const UTF16* source = *sourceStart;
UTF8* target = *targetStart;
while （source < sourceEnd） {
UTF32 ch;
unsigned short bytesToWrite = 0;
const UTF32 byteMask = 0xBF;
const UTF32 byteMark = 0x80;
const UTF16* oldSource = source; /* In case we have to back up because of target overflow. */
ch = *source++;
/* If we have a surrogate pair, convert to UTF32 first. */
if （ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END） {
/* If the 16 bits following the high surrogate are in the source buffer */
if （source < sourceEnd） {
UTF32 ch2 = *source;
/* If it's a low surrogate, convert to UTF32. */
if （ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END） {
ch = （（ch - UNI_SUR_HIGH_START） 《 halfShift）
+ （ch2 - UNI_SUR_LOW_START） + halfBase;
++source;
} else if （flags == strictConversion） { /* it's an unpaired high surrogate */
--source; /* return to the illegal value itself */
result = sourceIllegal;
break;
}
} else { /* We don't have the 16 bits following the high surrogate. */
--source; /* return to the high surrogate */
result = sourceExhausted;
break;
}
} else if （flags == strictConversion） {
/* UTF-16 surrogate values are illegal in UTF-32 */
if （ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END） {
--source; /* return to the illegal value itself */
result = sourceIllegal;
break;
}
}
/* Figure out how many bytes the result will require */
if （ch < （UTF32）0x80） { bytesToWrite = 1;
} else if （ch < （UTF32）0x800） { bytesToWrite = 2;
} else if （ch < （UTF32）0x10000） { bytesToWrite = 3;
} else if （ch < （UTF32）0x110000） { bytesToWrite = 4;
} else { bytesToWrite = 3;
ch = UNI_REPLACEMENT_CHAR;
}
target += bytesToWrite;
if （target > targetEnd） {
source = oldSource; /* Back up source pointer! */
target -= bytesToWrite; result = targetExhausted; break;
}
switch （bytesToWrite） { /* note: everything falls through. */
case 4: *--target = （UTF8）（（ch | byteMark） & byteMask）； ch 》= 6;
case 3: *--target = （UTF8）（（ch | byteMark） & byteMask）； ch 》= 6;
case 2: *--target = （UTF8）（（ch | byteMark） & byteMask）； ch 》= 6;
case 1: *--target = （UTF8）（ch | firstByteMark[bytesToWrite]）；
}
target += bytesToWrite;
}
*sourceStart = source;
*targetStart = target;
return result;
}
/* --------------------------------------------------------------------- */
/*
* Utility routine to tell whether a sequence of bytes is legal UTF-8.
* This must be called with the length pre-determined by the first byte.
* If not calling this from ConvertUTF8to*, then the length can be set by:
* length = trailingBytesForUTF8[*source]+1;
* and the sequence is illegal right away if there aren't that many bytes
* available.
* If presented with a length > 4, this returns false. The Unicode
* definition of UTF-8 goes up to 4-byte sequences.
*/
static Boolean isLegalUTF8（const UTF8 *source, int length） {
UTF8 a;
const UTF8 *srcptr = source+length;
switch （length） {
default: return false;
/* Everything else falls through when "true" */
case 4: if （（a = （*--srcptr）） < 0x80 || a > 0xBF） return false;
case 3: if （（a = （*--srcptr）） < 0x80 || a > 0xBF） return false;
case 2: if （（a = （*--srcptr）） > 0xBF） return false;
switch （*source） {
/* no fall-through in this inner switch */
case 0xE0: if （a < 0xA0） return false; break;
case 0xED: if （a > 0x9F） return false; break;
case 0xF0: if （a < 0x90） return false; break;
case 0xF4: if （a > 0x8F） return false; break;
default: if （a < 0x80） return false;
}
case 1: if （*source >= 0x80 && *source < 0xC2） return false;
}
if （*source > 0xF4） return false;
return true;
}
/* --------------------------------------------------------------------- */
/*
* Exported function to return whether a UTF-8 sequence is legal or not.
* This is not used here; it's just exported.
*/
Boolean isLegalUTF8Sequence（const UTF8 *source, const UTF8 *sourceEnd） {
int length = trailingBytesForUTF8[*source]+1;
if （source+length > sourceEnd） {
return false;
}
return isLegalUTF8（source, length）；
}
/* --------------------------------------------------------------------- */