在wchar_t和网络字节之间进行转换

case WM_CREATE: {   

    //Convert String to NetworkByte
    wchar_t Data[] = L"This is a string";
    char* DataA = (char*)Data;
    unsigned short uData = htons((unsigned int)DataA);
    //Convert String to HostByte
    unsigned short hData = ntohs(uData);
    DataA = (char*)&hData;
    wchar_t* DataW = (wchar_t*)DataA;
    MessageBeep(0);

    break;
}

쳌쳌쳌쳌쳌곭쳌쳌쳌쳌쳌ē쳌쳌쳌쳌This is a string

UTF8和UTF16以完全不同的方式存储文本。将wchar_t*转化为char*是没有意义的，就像将float转化为char*一样。

使用WideCharToMultiByte将UTF16转换为UTF8发送到网络功能

当从网络函数接收到UTF8时，使用MultiByteToWideChar将其转换回UTF16，以便在Windows函数中使用。

的例子:

#include <iostream>
#include <string>
#include <windows.h>
std::string get_utf8(const std::wstring &wstr)
{
    if (wstr.empty()) return std::string();
    int sz = WideCharToMultiByte(CP_UTF8, 0, &wstr[0], -1, 0, 0, 0, 0);
    std::string res(sz, 0);
    WideCharToMultiByte(CP_UTF8, 0, &wstr[0], -1, &res[0], sz, 0, 0);
    return res;
}
std::wstring get_utf16(const std::string &str)
{
    if (str.empty()) return std::wstring();
    int sz = MultiByteToWideChar(CP_UTF8, 0, &str[0], -1, 0, 0);
    std::wstring res(sz, 0);
    MultiByteToWideChar(CP_UTF8, 0, &str[0], -1, &res[0], sz);
    return res;
}
int main()
{
    std::wstring greek = L"ελληνικά";
    std::string utf8 = get_utf8(greek);
    //use utf8.data() for network function...
    //convert utf8 back to utf16 so it can be displayed in Windows:
    std::wstring utf16 = get_utf16(utf8);
    MessageBoxW(0, utf16.c_str(), 0, 0);
    return 0;
}

---

编辑

另一个显示UTF16和UTF8区别的例子。这个示例查看UTF16和UTF8的字节值。

注意，对于拉丁字母，UTF8和ANSI字节是完全相同的。

对于拉丁字母，UTF8和UTF16也有相似之处，除了UTF16有一个额外的零。

对于希腊字母和中文字母有明显的差异。

//(Windows example)
void printbytes_char(const char* ANSI_or_UTF8)
{
    const char *bytes = ANSI_or_UTF8;
    int len = strlen(bytes);
    for (size_t i = 0; i < len; i++)
        printf("%02X ", 0xFF & bytes[i]);
    printf("n");
}
void printbytes_wchar_t(const wchar_t* UTF16)
{
    //Note, in Windows wchar_t length is 2 bytes
    const char *bytes = (const char*)UTF16;
    int len = wcslen(UTF16) * 2;
    for (size_t i = 0; i < len; i++)
        printf("%02X ", 0xFF & bytes[i]);
    printf("n");
}
int main()
{
    printbytes_char("ABC");
    printbytes_char(u8"ABC");
    printbytes_wchar_t(L"ABC");
    printbytes_char(u8"ελληνικά");
    printbytes_wchar_t(L"ελληνικά");
    printbytes_char(u8"汉字/漢字");
    printbytes_wchar_t(L"汉字/漢字");
    return 0;
}

输出:

"ABC":
41 42 43 //ANSI
41 42 43 //UTF8
41 00 42 00 43 00 //UTF16 (this is little endian, bytes are swapped)
"ελληνικά"
CE B5 CE BB CE BB CE B7 CE BD CE B9 CE BA CE AC //UTF8
B5 03 BB 03 BB 03 B7 03 BD 03 B9 03 BA 03 AC 03 //UTF16
"汉字/漢字"
E6 B1 89 E5 AD 97 2F E6 BC A2 E5 AD 97 //UTF8
49 6C 57 5B 2F 00 22 6F 57 5B //UTF16

    wchar_t Data[] = L"test";
    //Convert String to NetworkByte
    for (wchar_t &val : Data) {
        if (sizeof(val) == 4) {
            val = htonl(val);
        }
        else if (sizeof(val) == 2) {
            val = htons(val);
        }
        else {
            static_assert(sizeof(val) <= 4, "wchar_t is gretter that 32 bit");
        }
    }
    //Convert String to HostByte
    for (wchar_t &val : Data) {
        if (sizeof(val) == 4) {
            val = ntohl(val);
        }
        else if (sizeof(val) == 2) {
            val = ntohs(val);
        }
        else {
            static_assert(sizeof(val) <= 4, "wchar_t is gretter that 32 bit");
        }
    }