* 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);
}