C++字符编码相关

一、wcstombs

使用函数 wcstombs() 前，先 setlocale()，如果系统没有zh_CN.utf8时，setlocale(LC_ALL, "zh_CN.utf8") 会失败，wcstombs() 转码也会失败。

char* locname = setlocale(LC_ALL, "zh_CN.utf8");
char utf8_confname[MAX_CN_LEN] = { 0 };
//int utflen = wcstombs(NULL, info.conf_name.c_str(), 0);//计算转换后的长度
wstring sss = L"中文test";
int ret = wcstombs(utf8_confname, sss.c_str(), MAX_CN_LEN);

locale -a 查看当前系统支持的字符编码方式

当没有 zh_CN.utf8 时，需要安装 apt-get install -y language-pack-zh-hans

打印字符串的16进制编码：

wstring sss = L"中文test";
int ret = wcstombs(utf8_confname, sss.c_str(), MAX_CN_LEN);


for (int i = 0; i < (int)sss.length(); ++i)
{
    printf("L-中文test:0x%x", sss[i]);
}

for (int i = 0; i < (int)sizeof(utf8_confname); ++i)
{
    printf("utf8_confname[中文test]: 0x%x", utf8_confname[i]);
}

for (int i = 0; i < (int)info.conf_name.length(); ++i)
{
    printf("info.conf_name:0x%x", info.conf_name[i]);
}

L-中文test:0x4e2d
L-中文test:0x6587
L-中文test:0x74
L-中文test:0x65
L-中文test:0x73
L-中文test:0x74

utf8_confname[中文test]: 0xffffffe4
utf8_confname[中文test]: 0xffffffb8
utf8_confname[中文test]: 0xffffffad
utf8_confname[中文test]: 0xffffffe6
utf8_confname[中文test]: 0xffffff96
utf8_confname[中文test]: 0xffffff87

二、按UTF8编码规则转换

inline std::wstring UTF8ToUnicode(std::string const& utf8)

{

    std::wstring res = L"";

    if (utf8.empty())

    {

        return res;

    }



    for (size_t i = 0; i < utf8.size();)
    {

        auto c = (unsigned char)utf8[i];

        wchar_t wide_char = 0;

        if ((c & 0x80) == 0)

        {

            wide_char = c;

            ++i;

        }

        else if ((c & 0xE0) == 0xC0)  ///< 110x-xxxx 10xx-xxxx
        {

            if (i + 2 > utf8.size())

                break;

            wide_char = (wchar_t(c) & 0x3F) << 6;

            wide_char |= (wchar_t(utf8[i + 1]) & 0x3F);

            i += 2;

        }
        else if ((c & 0xF0) == 0xE0)  ///< 1110-xxxx 10xx-xxxx 10xx-xxxx

        {

            if (i + 3 > utf8.size())

                break;

            wide_char = (wchar_t(c) & 0x1F) << 12;

            wide_char |= (wchar_t(utf8[i + 1]) & 0x3F) << 6;

            wide_char |= (wchar_t(utf8[i + 2]) & 0x3F);

            i += 3;

        }
        else if ((c & 0xF8) == 0xF0)  ///< 1111-0xxx 10xx-xxxx 10xx-xxxx 10xx-xxxx
        {

            if (i + 4 > utf8.size())

                break;

            wide_char = (wchar_t(c) & 0x0F) << 18;

            wide_char |= (wchar_t(utf8[i + 1]) & 0x3F) << 12;

            wide_char |= (wchar_t(utf8[i + 2]) & 0x3F) << 6;

            wide_char |= (wchar_t(utf8[i + 3]) & 0x3F);

            i += 4;

        }
        else///< 1111-10xx 10xx-xxxx 10xx-xxxx 10xx-xxxx 10xx-xxxx
        {

            if (i + 4 > utf8.size())

                break;

            wide_char = (wchar_t(c) & 0x07) << 24;

            wide_char |= (wchar_t(utf8[i + 1]) & 0x3F) << 18;

            wide_char |= (wchar_t(utf8[i + 2]) & 0x3F) << 12;

            wide_char |= (wchar_t(utf8[i + 3]) & 0x3F) << 6;

            wide_char |= (wchar_t(utf8[i + 4]) & 0x3F);

            i += 4;

        }

        res.push_back(wide_char);

    }

    return res;

}

三、其他

mysql++库设置中文到数据库会乱码，转utf-8码后设置也是乱码，结论mysql++库不支持中文设置

查看汉字的编码链接：查看字符编码（UTF-8） (mytju.com)