字符编码转换实现(基于conv)

本文介绍了如何在C++中使用libiconv库进行字符编码转换,如GBK到UTF-8和UTF-8到GBK的转换,通过`iconv_open`、`iconv`和`iconv_close`函数实现编码间的转换功能。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

#include <string>
#include <set>
#include <windows.h>

namespace ConvertUtil_ICONV {

    // 参考:https://baike.baidu.com/item/libiconv/10026740?fr=ge_ala

    /*
    libiconv库 [1] 为需要做转换的应用提供了一个iconv的函数,以实现一个字符编码到另一个字符编码的转换。
    包括的编码有:
    欧洲语系
    ASCII,
    ISO-8859-{1,2,3,4,5,7,9,10,13,14,15,16},
    KOI8-R, KOI8-U, KOI8-RU,
    CP{1250,1251,1252,1253,1254,1257},
    CP{850,866},
    Mac{Roman,CentralEurope,Iceland,Croatian,Romania},
    Mac{Cyrillic,Ukraine,Greek,Turkish},
    Macintosh
    犹太语系
    ISO-8859-{6,8}, CP{1255,1256}, CP862, Mac{Hebrew,Arabic}
    日文
    EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP, ISO-2022-JP-2, ISO-2022-JP-1
    中文
    EUC-CN, HZ, GBK, GB18030, EUC-TW, BIG5, CP950, BIG5-HKSCS, ISO-2022-CN, ISO-2022-CN-EXT
    朝鲜文
    EUC-KR, CP949, ISO-2022-KR, JOHAB
    亚美尼亚语
    ARMSCII-8
    格鲁尼亚语
    Georgian-Academy, Georgian-PS
    塔吉克语
    KOI8-T
    泰国语
    TIS-620, CP874, MacThai
    老挝语
    MuleLao-1, CP1133
    越南语
    VISCII, TCVN, CP1258
    特殊平台
    HP-ROMAN8, NEXTSTEP
    全部Unicode
    UTF-8, UTF-7
    UCS-2, UCS-2BE, UCS-2LE, UCS-4, UCS-4BE, UCS-4LE
    UTF-16, UTF-16BE, UTF-16LE, UTF-32, UTF-32BE, UTF-32LE
    C99, JAVA
    */

    // 常用code列表
    std::set<std::string> k_set_code = 
    { 
        "GP2312", 
        "GBK", 
        "BIG5", 
        "UTF-8", 
        "EUC-KR", 
        "SHIFT_JIS",
        "ISO8859-1",
        // 1~16...
        "ISO8859-16"
    };

    const char* k_iconv_file_name = "libiconv2.dll";

    typedef void* iconv_t;
    typedef iconv_t (*iconv_open)(const char* tocode, const char* fromcode);
    typedef size_t (*iconv)(iconv_t cd, const char* * inbuf, size_t *inbytesleft, char* * outbuf, size_t *outbytesleft);
    typedef int (*iconv_close)(iconv_t cd);

    HMODULE file_handle_ = nullptr;
    iconv_open iconv_open_ = nullptr;
    iconv iconv_ = nullptr;
    iconv_close iconv_close_ = nullptr;

    void* GetProcAddress(const char* fun_name)
    {
        void* fun = nullptr;

        fun = ::GetProcAddress(file_handle_, fun_name);
        
        if (nullptr == fun)
        {
            return nullptr;
        }

        return fun;
    }

    bool Init()
    {
        if (nullptr != file_handle_)
        {
            return true;
        }

        file_handle_ = ::LoadLibraryA(k_iconv_file_name);
        if (nullptr == file_handle_)
        {
            return false;
        }

        iconv_open_ = (iconv_open)GetProcAddress("libiconv_open");
        iconv_ = (iconv)GetProcAddress("libiconv");
        iconv_close_ = (iconv_close)GetProcAddress("libiconv_close");

        return (nullptr != iconv_open_) && (nullptr != iconv_) && (nullptr != iconv_close_);
    }

    void UnInit()
    {
        BOOL ret = ::FreeLibrary(file_handle_);
        // log...
    }

    bool Convert(std::string& out_string, const std::string& in_string, const std::string& out_code, const std::string& in_code)
    {
        bool ret = false;

        do 
        {
            ret = Init();
            if (!ret)
            {
                break;
            }

            iconv_t conv = iconv_open_(out_code.c_str(), in_code.c_str());
            if (iconv_t(-1) == conv)
            {
                ret = false;
                break;
            }

            const char* p_in = in_string.c_str();
            size_t in_size = in_string.size() + 1;
            size_t out_size = in_string.size() * 4;
            char* p_out = new char[out_size];
            memset(p_out, 0, out_size);
            char* p_out_src = p_out;
            size_t out_size_left = out_size;

            if (size_t(-1) == iconv_(conv, &p_in, &in_size, &p_out, &out_size_left))
            {
                delete[] p_out_src;
                p_out_src = nullptr;
                iconv_close_(conv);
                conv = nullptr;

                ret = false;
                break;
            }

            ret = true;
            out_string.assign(p_out_src, out_size - out_size_left);

            delete[] p_out_src;
            p_out_src = nullptr;
            iconv_close_(conv);
            conv = nullptr;
        } while (false);

        return ret;
    }

    bool GBKToUTF8(std::string& utf8, const std::string& gbk)
    {
        return Convert(utf8, gbk, "utf-8", "GB2312");
    }

    bool UTF8ToGBK(std::string& gbk, const std::string& utf8)
    {
        return Convert(gbk, utf8, "gbk" , "utf-8");
    }
}

int main()
{
    std::string ansi = "中国";    //  GB2312
    std::string utf8;
    ConvertUtil_ICONV::GBKToUTF8(utf8, ansi);
    ConvertUtil_ICONV::UTF8ToGBK(ansi, utf8);
    return 1;
}

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值