字符转换

一 C++ 中 string与wstring互转

方法一：

string WideToMutilByte(const wstring& _src)
{
int nBufSize = WideCharToMultiByte(GetACP(), 0, _src.c_str(),-1, NULL, 0, 0, FALSE);

char *szBuf = new char[nBufSize];

WideCharToMultiByte(GetACP(), 0, _src.c_str(),-1, szBuf, nBufSize, 0, FALSE);

string strRet(szBuf);

delete []szBuf;
szBuf = NULL;

return strRet;
}

wstring MutilByteToWide(const string& _src)
{
//计算字符串 string 转成 wchar_t 之后占用的内存字节数
int nBufSize = MultiByteToWideChar(GetACP(),0,_src.c_str(),-1,NULL,0);

//为 wsbuf 分配内存 BufSize 个字节
wchar_t *wsBuf = new wchar_t[nBufSize];

//转化为 unicode 的 WideString
MultiByteToWideChar(GetACP(),0,_src.c_str(),-1,wsBuf,nBufSize);

wstring wstrRet(wsBuf);

delete []wsBuf;
wsBuf = NULL;

return wstrRet;
}

转载：csdn

这篇文章里，我将给出几种C++ std::string和std::wstring相互转换的转换方法。
第一种方法：调用WideCharToMultiByte()和MultiByteToWideChar()，代码如下（关于详细的解释，可以参考《windows核心编程》）：

#include <string>
#include <windows.h>
using namespace std;
//Converting a WChar string to a Ansi string
std::string WChar2Ansi(LPCWSTR pwszSrc)
{
int nLen = WideCharToMultiByte(CP_ACP, 0, pwszSrc, -1, NULL, 0, NULL, NULL);
if (nLen<= 0) return std::string("");
char* pszDst = new char[nLen];
if (NULL == pszDst) return std::string("");
WideCharToMultiByte(CP_ACP, 0, pwszSrc, -1, pszDst, nLen, NULL, NULL);
pszDst[nLen -1] = 0;
std::string strTemp(pszDst);
delete [] pszDst;
return strTemp;
}

string ws2s(wstring& inputws)
{
return WChar2Ansi(inputws.c_str());
}

//Converting a Ansi string to WChar string

std::wstring Ansi2WChar(LPCSTR pszSrc, int nLen)
{
int nSize = MultiByteToWideChar(CP_ACP, 0, (LPCSTR)pszSrc, nLen, 0, 0);
if(nSize <= 0) return NULL;
WCHAR *pwszDst = new WCHAR[nSize+1];
if( NULL == pwszDst) return NULL;
MultiByteToWideChar(CP_ACP, 0,(LPCSTR)pszSrc, nLen, pwszDst, nSize);
pwszDst[nSize] = 0;
if( pwszDst[0] == 0xFEFF) // skip Oxfeff
for(int i = 0; i < nSize; i ++)
pwszDst[i] = pwszDst[i+1];
wstring wcharString(pwszDst);
delete pwszDst;
return wcharString;
}

std::wstring s2ws(const string& s)
{
return Ansi2WChar(s.c_str(),s.size());
}

第二种方法：采用ATL封装_bstr_t的过渡：（注，_bstr_是Microsoft Specific的，所以下面代码可以在VS2005通过，无移植性）；

#include <string>
#include <comutil.h>
using namespace std;
#pragma comment(lib, "comsuppw.lib")
string ws2s(const wstring& ws);
wstring s2ws(const string& s);
string ws2s(const wstring& ws)
{
_bstr_t t = ws.c_str();
char* pchar = (char*)t;
string result = pchar;
return result;
}

wstring s2ws(const string& s)
{
_bstr_t t = s.c_str();
wchar_t* pwchar = (wchar_t*)t;
wstring result = pwchar;
return result;
}

第三种方法：使用CRT库的mbstowcs()函数和wcstombs()函数，平台无关，需设定locale。

#include <string>
#include <locale.h>
using namespace std;
string ws2s(const wstring& ws)
{
string curLocale = setlocale(LC_ALL, NULL); // curLocale = "C";
setlocale(LC_ALL, "chs");
const wchar_t* _Source = ws.c_str();
size_t _Dsize = 2 * ws.size() + 1;
char *_Dest = new char[_Dsize];
memset(_Dest,0,_Dsize);
wcstombs(_Dest,_Source,_Dsize);
string result = _Dest;
delete []_Dest;
setlocale(LC_ALL, curLocale.c_str());
return result;
}

wstring s2ws(const string& s)
{
setlocale(LC_ALL, "chs");
const char* _Source = s.c_str();
size_t _Dsize = s.size() + 1;
wchar_t *_Dest = new wchar_t[_Dsize];
wmemset(_Dest, 0, _Dsize);
mbstowcs(_Dest,_Source,_Dsize);
wstring result = _Dest;
delete []_Dest;
setlocale(LC_ALL, "C");
return result;
}

二 utf8.utf16.utf32的相互转化

可以参考Unicode.org 上有ConvertUTF.c和ConvertUTF.h （下载地址：http://www.unicode.org/Public/PROGRAMS/CVTUTF/）

实现文件ConvertUTF.c：（.h省）
/**//*
* Copyright 2001-2004 Unicode, Inc.
*
* Disclaimer
*
* This source code is provided as is by Unicode, Inc. No claims are
* made as to fitness for any particular purpose. No warranties of any
* kind are expressed or implied. The recipient agrees to determine
* applicability of information provided. If this file has been
* purchased on magnetic or optical media from Unicode, Inc., the
* sole remedy for any claim will be exchange of defective media
* within 90 days of receipt.
*
* Limitations on Rights to Redistribute This Code
*
* Unicode, Inc. hereby grants the right to freely use the information
* supplied in this file in the creation of products supporting the
* Unicode Standard, and to make copies of this file in any form
* for internal or external distribution as long as this notice
* remains attached.
*/

/**//* ---------------------------------------------------------------------

Conversions between UTF32, UTF-16, and UTF-8. Source code file.
Author: Mark E. Davis, 1994.
Rev History: Rick McGowan, fixes & updates May 2001.
Sept 2001: fixed const & error conditions per
mods suggested by S. Parent & A. Lillich.
June 2002: Tim Dodd added detection and handling of incomplete
source sequences, enhanced error detection, added casts
to eliminate compiler warnings.
July 2003: slight mods to back out aggressive FFFE detection.
Jan 2004: updated switches in from-UTF8 conversions.
Oct 2004: updated to use UNI_MAX_LEGAL_UTF32 in UTF-32 conversions.

See the header file "ConvertUTF.h" for complete documentation.

------------------------------------------------------------------------ */

#include "ConvertUTF.h"
#ifdef CVTUTF_DEBUG
#include <stdio.h>
#endif

static const int halfShift = 10; /**//* used for shifting by 10 bits */

static const UTF32 halfBase = 0x0010000UL;
static const UTF32 halfMask = 0x3FFUL;

#define UNI_SUR_HIGH_START (UTF32)0xD800
#define UNI_SUR_HIGH_END (UTF32)0xDBFF
#define UNI_SUR_LOW_START (UTF32)0xDC00
#define UNI_SUR_LOW_END (UTF32)0xDFFF
#define false 0
#define true 1

/**//* --------------------------------------------------------------------- */

ConversionResult ConvertUTF32toUTF16 (
const UTF32** sourceStart, const UTF32* sourceEnd,
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF32* source = *sourceStart;
UTF16* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch;
if (target >= targetEnd) {
result = targetExhausted; break;
}
ch = *source++;
if (ch <= UNI_MAX_BMP) { /**//* Target is a character <= 0xFFFF */
/**//* UTF-16 surrogate values are illegal in UTF-32; 0xffff or 0xfffe are both reserved values */
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
if (flags == strictConversion) {
--source; /**//* return to the illegal value itself */
result = sourceIllegal;
break;
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
*target++ = (UTF16)ch; /**//* normal case */
}
} else if (ch > UNI_MAX_LEGAL_UTF32) {
if (flags == strictConversion) {
result = sourceIllegal;
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
/**//* target is a character in range 0xFFFF - 0x10FFFF. */
if (target + 1 >= targetEnd) {
--source; /**//* Back up source pointer! */
result = targetExhausted; break;
}
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[6] = { 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[7] = { 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);
}

/**//* --------------------------------------------------------------------- */

ConversionResult ConvertUTF8toUTF16 (
const UTF8** sourceStart, const UTF8* sourceEnd,
UTF16** targetStart, UTF16* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF8* source = *sourceStart;
UTF16* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch = 0;
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
if (source + extraBytesToRead >= sourceEnd) {
result = sourceExhausted; break;
}
/**//* Do this check whether lenient or strict */
if (! isLegalUTF8(source, extraBytesToRead+1)) {
result = sourceIllegal;
break;
}
/**//*
* The cases all fall through. See "Note A" below.
*/
switch (extraBytesToRead) {
case 5: ch += *source++; ch <<= 6; /**//* remember, illegal UTF-8 */
case 4: ch += *source++; ch <<= 6; /**//* remember, illegal UTF-8 */
case 3: ch += *source++; ch <<= 6;
case 2: ch += *source++; ch <<= 6;
case 1: ch += *source++; ch <<= 6;
case 0: ch += *source++;
}
ch -= offsetsFromUTF8[extraBytesToRead];

if (target >= targetEnd) {
source -= (extraBytesToRead+1); /**//* Back up source pointer! */
result = targetExhausted; break;
}
if (ch <= UNI_MAX_BMP) { /**//* Target is a character <= 0xFFFF */
/**//* UTF-16 surrogate values are illegal in UTF-32 */
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
if (flags == strictConversion) {
source -= (extraBytesToRead+1); /**//* return to the illegal value itself */
result = sourceIllegal;
break;
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
*target++ = (UTF16)ch; /**//* normal case */
}
} else if (ch > UNI_MAX_UTF16) {
if (flags == strictConversion) {
result = sourceIllegal;
source -= (extraBytesToRead+1); /**//* return to the start */
break; /**//* Bail out; shouldn't continue */
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
/**//* target is a character in range 0xFFFF - 0x10FFFF. */
if (target + 1 >= targetEnd) {
source -= (extraBytesToRead+1); /**//* Back up source pointer! */
result = targetExhausted; break;
}
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 ConvertUTF32toUTF8 (
const UTF32** sourceStart, const UTF32* sourceEnd,
UTF8** targetStart, UTF8* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF32* source = *sourceStart;
UTF8* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch;
unsigned short bytesToWrite = 0;
const UTF32 byteMask = 0xBF;
const UTF32 byteMark = 0x80;
ch = *source++;
if (flags == strictConversion ) {
/**//* UTF-16 surrogate values are illegal in UTF-32 */
if (ch >= UNI_SUR_HIGH_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. Turn any
* illegally large UTF32 things (> Plane 17) into replacement chars.
*/
if (ch < (UTF32)0x80) { bytesToWrite = 1;
} else if (ch < (UTF32)0x800) { bytesToWrite = 2;
} else if (ch < (UTF32)0x10000) { bytesToWrite = 3;
} else if (ch <= UNI_MAX_LEGAL_UTF32) { bytesToWrite = 4;
} else { bytesToWrite = 3;
ch = UNI_REPLACEMENT_CHAR;
result = sourceIllegal;
}
target += bytesToWrite;
if (target > targetEnd) {
--source; /**//* 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;
}

/**//* --------------------------------------------------------------------- */

ConversionResult ConvertUTF8toUTF32 (
const UTF8** sourceStart, const UTF8* sourceEnd,
UTF32** targetStart, UTF32* targetEnd, ConversionFlags flags) {
ConversionResult result = conversionOK;
const UTF8* source = *sourceStart;
UTF32* target = *targetStart;
while (source < sourceEnd) {
UTF32 ch = 0;
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
if (source + extraBytesToRead >= sourceEnd) {
result = sourceExhausted; break;
}
/**//* Do this check whether lenient or strict */
if (! isLegalUTF8(source, extraBytesToRead+1)) {
result = sourceIllegal;
break;
}
/**//*
* The cases all fall through. See "Note A" below.
*/
switch (extraBytesToRead) {
case 5: ch += *source++; ch <<= 6;
case 4: ch += *source++; ch <<= 6;
case 3: ch += *source++; ch <<= 6;
case 2: ch += *source++; ch <<= 6;
case 1: ch += *source++; ch <<= 6;
case 0: ch += *source++;
}
ch -= offsetsFromUTF8[extraBytesToRead];

if (target >= targetEnd) {
source -= (extraBytesToRead+1); /**//* Back up the source pointer! */
result = targetExhausted; break;
}
if (ch <= UNI_MAX_LEGAL_UTF32) {
/**//*
* UTF-16 surrogate values are illegal in UTF-32, and anything
* over Plane 17 (> 0x10FFFF) is illegal.
*/
if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
if (flags == strictConversion) {
source -= (extraBytesToRead+1); /**//* return to the illegal value itself */
result = sourceIllegal;
break;
} else {
*target++ = UNI_REPLACEMENT_CHAR;
}
} else {
*target++ = ch;
}
} else { /**//* i.e., ch > UNI_MAX_LEGAL_UTF32 */
result = sourceIllegal;
*target++ = UNI_REPLACEMENT_CHAR;
}
}
*sourceStart = source;
*targetStart = target;
return result;
}

/**//* ---------------------------------------------------------------------

Note A.
The fall-through switches in UTF-8 reading code save a
temp variable, some decrements & conditionals. The switches
are equivalent to the following loop:
{
int tmpBytesToRead = extraBytesToRead+1;
do {
ch += *source++;
--tmpBytesToRead;
if (tmpBytesToRead) ch <<= 6;
} while (tmpBytesToRead > 0);
}
In UTF-8 writing code, the switches on "bytesToWrite" are
similarly unrolled loops.

--------------------------------------------------------------------- */

三 C++ 的字符串与C#的转化

1）将system::String 转化为C++的string：
// convert_system_string.cpp
// compile with: /clr
#include <string>
#include <iostream>
using namespace std;
using namespace System;

void MarshalString ( String ^ s, string& os ) {
using namespace Runtime::InteropServices;
const char* chars =
(const char*)(Marshal::StringToHGlobalAnsi(s)).ToPointer();
os = chars;
Marshal::FreeHGlobal(IntPtr((void*)chars));
}

void MarshalString ( String ^ s, wstring& os ) {
using namespace Runtime::InteropServices;
const wchar_t* chars =
(const wchar_t*)(Marshal::StringToHGlobalUni(s)).ToPointer();
os = chars;
Marshal::FreeHGlobal(IntPtr((void*)chars));
}

int main() {
string a = "test";
wstring b = L"test2";
String ^ c = gcnew String("abcd");

cout << a << endl;
MarshalString(c, a);
c = "efgh";
MarshalString(c, b);
cout << a << endl;
wcout << b << endl;
}

2）将System::String转化为char*或w_char*
// convert_string_to_wchar.cpp
// compile with: /clr
#include < stdio.h >
#include < stdlib.h >
#include < vcclr.h >

using namespace System;

int main() {
String ^str = "Hello";

// Pin memory so GC can't move it while native function is called
pin_ptr<const wchar_t> wch = PtrToStringChars(str);
printf_s("%S\n", wch);

// Conversion to char* :
// Can just convert wchar_t* to char* using one of the
// conversion functions such as:
// WideCharToMultiByte()
// wcstombs_s()
// etc
size_t convertedChars = 0;
size_t sizeInBytes = ((str->Length + 1) * 2);
errno_t err = 0;
char *ch = (char *)malloc(sizeInBytes);

err = wcstombs_s(&convertedChars,
ch, sizeInBytes,
wch, sizeInBytes);
if (err != 0)
printf_s("wcstombs_s failed!\n");

printf_s("%s\n", ch);
}