SCADATrainSys/CCGDServer/Global/coding_conv.h

#ifndef _coding_conv_ns_h__
#define _coding_conv_ns_h__



#include <stdio.h>
#include <stdlib.h>
#include <string>
#include <string.h>
#if defined(_MSC_VER) || defined(WIN64) || defined(WIN32)
#include <windows.h>
#else
#include <boost/locale.hpp>
#endif
namespace coding_conv_ns 
{


static int preNUm(unsigned char byted) {
    unsigned char mask = 0x80;
    int num = 0;
    for (int i = 0; i < 8; i++) {
        if ((byted & mask) == mask) {
            mask = mask >> 1;
            num++;
        } else {
            break;
        }
    }
    return num;
}


static bool isUtf8(unsigned char* data, int len) {
    int num = 0;
    int i = 0;
    while (i < len) {
        if ((data[i] & 0x80) == 0x00) {
            // 0XXX_XXXX
            i++;
            continue;
        }
        else if ((num = preNUm(data[i])) > 2) {
        // 110X_XXXX 10XX_XXXX
        // 1110_XXXX 10XX_XXXX 10XX_XXXX
        // 1111_0XXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
        // 1111_10XX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
        // 1111_110X 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX 10XX_XXXX
        // preNUm() 返回首个字节8个bits中首??0bit前面1bit的个数，该数量也是该字符所使用的字节数        
        i++;
        for(int j = 0; j < num - 1; j++) {
            //判断后面num - 1 个字节是不是都是10开
            if ((data[i] & 0xc0) != 0x80) {
                    return false;
                }
                i++;
        }
    } else {
        //其他情况说明不是utf-8
        return false;
    }
    } 
    return true;
}

static bool isGBK(unsigned char* data, int len)  {
    int i  = 0;
    while (i < len)  {
        if (data[i] <= 0x7f) {
            //编码小于等于127,只有一个字节的编码，兼容ASCII
            i++;
            continue;
        } else {
            //大于127的使用双字节编码
            if  (data[i] >= 0x81 &&
                data[i] <= 0xfe &&
                data[i + 1] >= 0x40 &&
                data[i + 1] <= 0xfe &&
                data[i + 1] != 0xf7) {
                i += 2;
                continue;
            } else {
                return false;
            }
        }
    }
    return true;
}
typedef enum  {
    GBK,
    UTF8,
    UNKOWN
} CODING;
//需要说明的是，isGBK()是通过双字节是否落在gbk的编码范围内实现的，
//而utf-8编码格式的每个字节都是落在gbk的编码范围内??
//所以只有先调用isUtf8()先判断不是utf-8编码，再调用isGBK()才有意义
static CODING GetCoding(const char* data, int len) {
    CODING coding;
    if (isUtf8((unsigned char*)(data), len) == true) {
        coding = UTF8;
    } else if (isGBK((unsigned char*)(data), len) == true) {
        coding = GBK;
    } else {
        coding = UNKOWN;
    }
    return coding;
}
#if defined(_MSC_VER) || defined(WIN64) || defined(WIN32)
static std::string utf8_to_gbk_str(const char* src)
{
    auto code = GetCoding(src, strlen(src));
    if (code != UTF8)
    {
        return src;
    }
    std::string gbkstr;
    wchar_t* pUnicodeBuff = NULL;
    int rlen = 0;
    rlen = MultiByteToWideChar(CP_UTF8, 0, src, -1, NULL, NULL);
    pUnicodeBuff = new wchar_t[rlen + 1];  //为Unicode字符串空间
    rlen = MultiByteToWideChar(CP_UTF8, 0, src, -1, pUnicodeBuff, rlen);
    rlen = WideCharToMultiByte(936, 0, pUnicodeBuff, -1, NULL, NULL, NULL, NULL); //936 为windows gb2312代码页码
    char* dstgbk = new char[rlen + 1];
    WideCharToMultiByte(936, 0, pUnicodeBuff, -1, dstgbk, rlen, NULL, NULL);
    delete[] pUnicodeBuff;
    gbkstr = dstgbk;
    delete[]dstgbk;
    return gbkstr;
}

static std::string gbk_to_utf8_str(const char* src)
{
    auto code = GetCoding(src, strlen(src));
    if (code == UTF8)
    {
        return src;
    }
    int rlen = MultiByteToWideChar(936, 0, src, -1, NULL, NULL);
    wchar_t* pUnicodeBuff = new wchar_t[rlen + 1];  //为Unicode字符串空间
    rlen = MultiByteToWideChar(936, 0, src, -1, pUnicodeBuff, rlen);
    rlen = WideCharToMultiByte(CP_UTF8, 0, pUnicodeBuff, -1, NULL, NULL, NULL, NULL);
    char* dstutf8 = new char[rlen + 1];
    WideCharToMultiByte(CP_UTF8, 0, pUnicodeBuff, -1, dstutf8, rlen, NULL, NULL);
    delete[] pUnicodeBuff;
    std::string str = dstutf8;
    delete[]dstutf8;
    return str;
}
#else
static std::string utf8_to_gbk_str(const char* src)
{
    auto code = GetCoding(src, strlen(src));
    if (code == UTF8)
    {
        std::string strGBK = boost::locale::conv::from_utf(src, "GBK");
        return strGBK;
    }
    return src;
}
static std::string gbk_to_utf8_str(const char* src)
{
    auto code =GetCoding(src, strlen(src));
    if (code == UTF8)
    {
        return src;
    }
    std::string strUTF8 = boost::locale::conv::to_utf<char>(src, "GBK");
    return strUTF8;

}
#endif // WIN32 || WIN64

//在linux 下如果是 gbk则转换为utf8
//在windows 下如果是 utf8则转换为gbk
static std::string check_str_to_default(const char* str)
{
#if defined(_MSC_VER) || defined(WIN64) || defined(WIN32)
    if (GetCoding(str, strlen(str) == UTF8))
    {
        return utf8_to_gbk_str(str);
    }
#else
    auto code = GetCoding(str, strlen(str));
    if (code != UTF8)
    {
        return gbk_to_utf8_str(str);
    }
#endif
    return str;
}

}

#endif // _coding_conv_ns_h__