很全的筆記：Linux下字符編碼轉換

一、利用iconv函數族進行編碼轉換
iconv函數族的頭文件是iconv.h,使用前需包含之。
#include <iconv.h>
iconv函數族有三個函數,原型如下:
(1) iconv_t iconv_open(const char *tocode, const char *fromcode);
此函數說明將要進行哪兩種編碼的轉換,tocode是目標編碼,fromcode是原編碼,該函數返回一個轉換句柄,供以下兩個函數使用。
(2) size_t iconv(iconv_t cd,char **inbuf,size_t *inbytesleft,char **outbuf,size_t *outbytesleft);
此函數從inbuf中讀取字符,轉換後輸出到outbuf中,inbytesleft用以記錄還未轉換的字符數,outbytesleft用以記錄輸出緩沖的剩余空間，cd是iconv_open返回的句柄。 (3) int iconv_close(iconv_t cd);
此函數用於關閉轉換句柄,釋放資源。
例子1: 用C語言實現的轉換示例程序

/* f.c : 代碼轉換示例C程序 */
#include <iconv.h>
#define OUTLEN 255
main()
{
char *in_utf8 = "姝ｅ?ㄥ??瑁?";
char *in_gb2312 = "正在安裝";
char out[OUTLEN];

//unicode碼轉為gb2312碼
rc = u2g(in_utf8,strlen(in_utf8),out,OUTLEN);
printf("unicode-->gb2312 out=%sn",out);
//gb2312碼轉為unicode碼
rc = g2u(in_gb2312,strlen(in_gb2312),out,OUTLEN);
printf("gb2312-->unicode out=%sn",out);
}
//代碼轉換:從一種編碼轉為另一種編碼
int code_convert(char *from_charset,char *to_charset,char *inbuf,int inlen,char *outbuf,int outlen)
{
iconv_t cd;
int rc;
char **pin = &inbuf;
char **pout = &outbuf;

cd = iconv_open(to_charset,from_charset);
if (cd==0) return -1;
memset(outbuf,0,outlen);
if (iconv(cd,pin,&inlen,pout,&outlen)==-1) return -1;
iconv_close(cd);
return 0;
}
//UNICODE碼轉為GB2312碼
int u2g(char *inbuf,int inlen,char *outbuf,int outlen)
{
return code_convert("utf-8","gb2312",inbuf,inlen,outbuf,outlen);
}
//GB2312碼轉為UNICODE碼
int g2u(char *inbuf,size_t inlen,char *outbuf,size_t outlen)
{
return code_convert("gb2312","utf-8",inbuf,inlen,outbuf,outlen);
}

例子2: 用C++語言實現的轉換示例程序

/* f.cpp : 代碼轉換示例C++程序 */
#include <iconv.h>
#include <iostream>

#define OUTLEN 255

using namespace std;

// 代碼轉換操作類
class CodeConverter {
private:
iconv_t cd;
public:
// 構造
CodeConverter(const char *from_charset,const char *to_charset) {
cd = iconv_open(to_charset,from_charset);
}

// 析構
~CodeConverter() {
iconv_close(cd);
}

// 轉換輸出
int convert(char *inbuf,int inlen,char *outbuf,int outlen) {
char **pin = &inbuf;
char **pout = &outbuf;

memset(outbuf,0,outlen);
return iconv(cd,pin,(size_t *)&inlen,pout,(size_t *)&outlen);
}
};

int main(int argc, char **argv)
{
char *in_utf8 = "姝ｅ?ㄥ??瑁?";
char *in_gb2312 = "正在安裝";
char out[OUTLEN];

// utf-8-->gb2312
CodeConverter cc = CodeConverter("utf-8","gb2312");
cc.convert(in_utf8,strlen(in_utf8),out,OUTLEN);
cout << "utf-8-->gb2312 in=" << in_utf8 << ",out=" << out << endl;

// gb2312-->utf-8
CodeConverter cc2 = CodeConverter("gb2312","utf-8");
cc2.convert(in_gb2312,strlen(in_gb2312),out,OUTLEN);
cout << "gb2312-->utf-8 in=" << in_gb2312 << ",out=" << out << endl;
}