• gbk与utf-8转换


    linux:

     1 #include <iconv.h>
     2 
     3 int code_convert(char *from_charset,char *to_charset,char *inbuf,int inlen,char *outbuf,int outlen)
     4 {
     5         iconv_t cd;
     6         int rc;
     7         char **pin = &inbuf;
     8         char **pout = &outbuf;
     9 
    10         cd = iconv_open(to_charset,from_charset);
    11         if (cd==0)
    12                 return -1;
    13         memset(outbuf,0,outlen);
    14         if (iconv(cd,pin,&inlen,pout,&outlen) == -1)
    15                 return -1;
    16         iconv_close(cd);
    17         return 0;
    18 }
    19 
    20 int u2g(char *inbuf,int inlen,char *outbuf,int outlen)
    21 {
    22         return code_convert("utf-8","gb2312",inbuf,inlen,outbuf,outlen);
    23 }
    24 
    25 int g2u(char *inbuf,size_t inlen,char *outbuf,size_t outlen)
    26 {
    27         return code_convert("gb2312","utf-8",inbuf,inlen,outbuf,outlen);
    28 }

    解释:

    其中
    
    iconv函数族的头文件是iconv.h,使用前需包含之。
    #include <iconv.h>
    iconv函数族有三个函数,原型如下:
    (1) iconv_t iconv_open(const char *tocode, const char *fromcode);
    此函数说明将要进行哪两种编码的转换,tocode是目标编码,fromcode是原编码,该函数返回一个转换句柄,供以下两个函数使用。
    (2) size_t iconv(iconv_t cd,char **inbuf,size_t *inbytesleft,char **outbuf,size_t *outbytesleft);
    此函数从inbuf中读取字符,转换后输出到outbuf中,inbytesleft用以记录还未转换的字符数,outbytesleft用以记录输出缓冲的剩余空间。
    
    (3) int iconv_close(iconv_t cd);
    此函数用于关闭转换句柄,释放资源。

    Windows:

     1     #include <iostream>  
     2     #include <string>  
     3     #include <fstream>  
     4     #include <windows.h>   
     5       
     6     using namespace std;  
     7       
     8     string GBKToUTF8(const std::string& strGBK)  
     9     {  
    10         string strOutUTF8 = "";  
    11         WCHAR * str1;  
    12         int n = MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, NULL, 0);  
    13         str1 = new WCHAR[n];  
    14         MultiByteToWideChar(CP_ACP, 0, strGBK.c_str(), -1, str1, n);  
    15         n = WideCharToMultiByte(CP_UTF8, 0, str1, -1, NULL, 0, NULL, NULL);  
    16         char * str2 = new char[n];  
    17         WideCharToMultiByte(CP_UTF8, 0, str1, -1, str2, n, NULL, NULL);  
    18         strOutUTF8 = str2;  
    19         delete[]str1;  
    20         str1 = NULL;  
    21         delete[]str2;  
    22         str2 = NULL;  
    23         return strOutUTF8;  
    24     }  
    25       
    26     string UTF8ToGBK(const std::string& strUTF8)  
    27     {  
    28         int len = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);  
    29         unsigned short * wszGBK = new unsigned short[len + 1];  
    30         memset(wszGBK, 0, len * 2 + 2);  
    31         MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUTF8.c_str(), -1, wszGBK, len);  
    32       
    33         len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);  
    34         char *szGBK = new char[len + 1];  
    35         memset(szGBK, 0, len + 1);  
    36         WideCharToMultiByte(CP_ACP,0, wszGBK, -1, szGBK, len, NULL, NULL);  
    37         //strUTF8 = szGBK;  
    38         std::string strTemp(szGBK);  
    39         delete[]szGBK;  
    40         delete[]wszGBK;  
    41         return strTemp;  
    42     }  
    43       
    44     int _tmain(int argc, _TCHAR* argv[])  
    45     {  
    46         string test("我们中国是个强大的名族,强大的动力来自每个人的支持");  
    47         fstream output("test.txt",ios_base::out | ios_base::app);  
    48         output << GBKToUTF8(test);  
    49         //system("iconv -f GBK -t utf-8");  
    50         return 0;  
    51     }  
  • 相关阅读:
    TCP/IP面试要点浅析
    Mysql优化策略
    Mysql集群方案简介
    Mysql主从复制
    UML序列图总结(Loop、Opt、Par和Alt)
    Java之注解
    mac:查看端口号被占用情况
    C#监控U盘插拔
    QMap
    js统计对象的层数
  • 原文地址:https://www.cnblogs.com/jiu0821/p/6257246.html
Copyright © 2020-2023  润新知