linux下C语言utf-8编码与gb2312转换代码---libiconv

朱雀 2021-09-14 06:44 504阅读 0赞

linux下C语言utf-8编码与gb2312转换代码

2010-04-02 14:09

<table style="table-layout:fixed; font-family:Arial; width:780px"> 
 <tbody> 
 <tr> 
 <td style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; line-height:18px"> 
 <div style="font-family:Georgia; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:14px; line-height:20px; color:rgb(51,51,51); padding:29px 3px 3px 33px; overflow:hidden; position:relative!important"> 
 
 
 <table style="table-layout:auto!important; border-collapse:collapse"> 
 <tbody> 
 <tr> 
 <td style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important"> int code_convert(char *from_charset, char *to_charset, char *inbuf, int inlen, char *outbuf, int outlen) { iconv_t cd; int rc; char **pin = &amp;inbuf; char **pout = &amp;outbuf; cd = iconv_open(to_charset, from_charset); if (cd == 0)&nbsp; return 1; memset(outbuf, 0, outlen); if (iconv(cd, pin, &amp;inlen, pout, &amp;outlen) == -1)&nbsp; return 1; iconv_close(cd); return 0; } </td> 
 </tr> 
 </tbody> 
 </table> 
 
 我也发一个自己写的程序，一直在用的 
 
 
 <table style="table-layout:auto!important; border-collapse:collapse"> 
 <tbody> 
 <tr> 
 <td style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important"> <code style="line-height:normal">/****************************************************** EncodingConv.c 使用iconv进行字符编码转换 SUNLAN 2006/08/17 ******************************************************/ #include &lt;stdio.h&gt; #include &lt;stdlib.h&gt; #include &lt;iconv.h&gt; #include &lt;errno.h&gt; #include "SDKpub.h" #ifndef ERRFILE #define ERRFILE "errlog" #endif char * EncodingConv(&nbsp; const char * in, char *encFrom, char *encTo ) { char *buff, *sin, *sout; int lenin, lenout; iconv_t ct; if( (ct=iconv_open(encTo, encFrom)) == (iconv_t)-1 ) { SDKerrlog( ERRFILE, "%s|%d| iconv_open error! %s", __FILE__, __LINE__, strerror(errno) ); return( NULL ); } iconv( ct, NULL, NULL, NULL, NULL ); sin = (char *)in; lenin&nbsp; = strlen(in) + 1; if( (buff=malloc( lenin*2 ))==NULL ) { SDKerrlog( ERRFILE, "%s|%d| malloc error! %s", __FILE__, __LINE__, strerror(errno) ); iconv_close( ct ); return( NULL ); } sout&nbsp;&nbsp; = buff; lenout = lenin*2; if( iconv( ct, &amp;sin, (size_t *)&amp;lenin, &amp;sout, (size_t *)&amp;lenout) == -1 ) { SDKerrlog( ERRFILE, "%s|%d| iconv() error! errno=%d %s", __FILE__, __LINE__, errno, strerror(errno) ); free( buff ); iconv_close( ct ); return NULL; } iconv_close( ct ); sout=strdup(buff); free( buff ); return( sout ); } </code> </td> 
 </tr> 
 </tbody> 
 </table> over 
 
 
 <h1 style="line-height:normal; word-wrap:break-word">linux C C++ 字符集转换,UTF-8,GB2312</h1> 
 
 http://jazka.blog.51cto.com/809003/231917 
 
 
 <div style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:12px; line-height:normal">
 在LINUX上进行编码转换时,既可以利用iconv函数族编程实现,也可以利用iconv命令来实现,只不过后者是针对文件的,即将指定文件从一种编码转换为另一种编码。&nbsp; 
 一、利用iconv函数族进行编码转换&nbsp; 
 iconv函数族的头文 
 </div> 
 <div style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:12px; line-height:normal">
 在LINUX上进行编码转换时,既可以利用iconv函数族编程实现,也可以利用iconv命令来实现,只不过后者是针对文件的,即将指定文件从一种编码转换为另一种编码。&nbsp; 
 一、利用iconv函数族进行编码转换&nbsp; 
 iconv函数族的头文件是iconv.h,使用前需包含之。&nbsp; 
 #include &lt;iconv.h&gt;&nbsp; 
 iconv函数族有三个函数,原型如下:&nbsp; 
 (1) iconv_t iconv_open(const char *tocode, const char *fromcode);&nbsp; 
 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。&nbsp; 
 (2) size_t iconv(iconv_t cd,char **inbuf,size_t *inbytesleft,char **outbuf,size_t *outbytesleft);&nbsp; 
 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);&nbsp; 
 此函数用于关闭转换句柄,释放资源。&nbsp; 
 例子1: 用C语言实现的转换示例程序&nbsp; 
 
 /* f.c : 代码转换示例C程序 */&nbsp; 
 #include &lt;iconv.h&gt;&nbsp; 
 #define OUTLEN 255&nbsp; 
 main()&nbsp; 
 {&nbsp; 
 char *in_utf8 = "姝ｅ?ㄥ??瑁?";&nbsp; 
 char *in_gb2312 = "正在安装";&nbsp; 
 char out[OUTLEN];&nbsp; 
 
 //unicode码转为gb2312码&nbsp; 
 rc = u2g(in_utf8,strlen(in_utf8),out,OUTLEN);&nbsp; 
 printf("unicode--&gt;gb2312 out=%sn",out);&nbsp; 
 //gb2312码转为unicode码&nbsp; 
 rc = g2u(in_gb2312,strlen(in_gb2312),out,OUTLEN);&nbsp; 
 printf("gb2312--&gt;unicode out=%sn",out);&nbsp; 
 }&nbsp; 
 //代码转换:从一种编码转为另一种编码&nbsp; 
 int code_convert(char *from_charset,char *to_charset,char *inbuf,int inlen,char *outbuf,int outlen)&nbsp; 
 {&nbsp; 
 iconv_t cd;&nbsp; 
 int rc;&nbsp; 
 char **pin = &amp;inbuf;&nbsp; 
 char **pout = &amp;outbuf;&nbsp; 
 
 cd = iconv_open(to_charset,from_charset);&nbsp; 
 if (cd==0) return -1;&nbsp; 
 memset(outbuf,0,outlen);&nbsp; 
 if (iconv(cd,pin,&amp;inlen,pout,&amp;outlen)==-1) return -1;&nbsp; 
 iconv_close(cd);&nbsp; 
 return 0;&nbsp; 
 }&nbsp; 
 //UNICODE码转为GB2312码&nbsp; 
 int u2g(char *inbuf,int inlen,char *outbuf,int outlen)&nbsp; 
 {&nbsp; 
 return code_convert("utf-8","gb2312",inbuf,inlen,outbuf,outlen);&nbsp; 
 }&nbsp; 
 //GB2312码转为UNICODE码&nbsp; 
 int g2u(char *inbuf,size_t inlen,char *outbuf,size_t outlen)&nbsp; 
 {&nbsp; 
 return code_convert("gb2312","utf-8",inbuf,inlen,outbuf,outlen);&nbsp; 
 }&nbsp; 
 
 例子2: 用C++语言实现的转换示例程序&nbsp; 
 
 /* f.cpp : 代码转换示例C++程序 */&nbsp; 
 #include &lt;iconv.h&gt;&nbsp; 
 #include &lt;iostream&gt;&nbsp; 
 
 #define OUTLEN 255&nbsp; 
 
 using namespace std;&nbsp; 
 
 // 代码转换操作类&nbsp; 
 class CodeConverter {&nbsp; 
 private:&nbsp; 
 iconv_t cd;&nbsp; 
 public:&nbsp; 
 // 构造&nbsp; 
 CodeConverter(const char *from_charset,const char *to_charset) {&nbsp; 
 cd = iconv_open(to_charset,from_charset);&nbsp; 
 }&nbsp; 
 
 // 析构&nbsp; 
 ~CodeConverter() {&nbsp; 
 iconv_close(cd);&nbsp; 
 }&nbsp; 
 
 // 转换输出&nbsp; 
 int convert(char *inbuf,int inlen,char *outbuf,int outlen) {&nbsp; 
 char **pin = &amp;inbuf;&nbsp; 
 char **pout = &amp;outbuf;&nbsp; 
 
 memset(outbuf,0,outlen);&nbsp; 
 return iconv(cd,pin,(size_t *)&amp;inlen,pout,(size_t *)&amp;outlen);&nbsp; 
 }&nbsp; 
 };&nbsp; 
 
 int main(int argc, char **argv)&nbsp; 
 {&nbsp; 
 char *in_utf8 = "姝ｅ?ㄥ??瑁?";&nbsp; 
 char *in_gb2312 = "正在安装";&nbsp; 
 char out[OUTLEN];&nbsp; 
 
 // utf-8--&gt;gb2312&nbsp; 
 CodeConverter cc = CodeConverter("utf-8","gb2312");&nbsp; 
 cc.convert(in_utf8,strlen(in_utf8),out,OUTLEN);&nbsp; 
 cout &lt;&lt; "utf-8--&gt;gb2312 in=" &lt;&lt; in_utf8 &lt;&lt; ",out=" &lt;&lt; out &lt;&lt; endl;&nbsp; 
 
 // gb2312--&gt;utf-8&nbsp; 
 CodeConverter cc2 = CodeConverter("gb2312","utf-8");&nbsp; 
 cc2.convert(in_gb2312,strlen(in_gb2312),out,OUTLEN);&nbsp; 
 cout &lt;&lt; "gb2312--&gt;utf-8 in=" &lt;&lt; in_gb2312 &lt;&lt; ",out=" &lt;&lt; out &lt;&lt; endl;&nbsp; 
 } 
 </div> 
 <div style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:12px; line-height:normal">
 &nbsp; 
 </div> 
 <div style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:12px; line-height:normal">
 linux C 字符集转换,UTF-8,GB2312 
 </div> 
 <div style="font-family:Arial; word-wrap:break-word; word-break:break-all; visibility:visible!important; zoom:1!important; font-size:12px; line-height:normal">
 最近帮朋友写个系统接口的小东东，2个系统字符集不同，一个采用UTF-8,一个采用GB2312，不得已需要转换字符集。转换函数记录如下： 
 </div> #include &lt;iconv.h&gt; 
 #include &lt;stdio.h&gt; 
 #include &lt;stdlib.h&gt; 
 #include &lt;string.h&gt; 
 #define OUTLEN 255 
 main() 
 { 
 char *in_utf8 = "utf8字符串"; 
 char *in_gb2312 = "\xbe\xb2\xcc\xac\xc4\xa3\xca\xbd"; 
 
 char out[OUTLEN]; 
 int rec ; 
 
 //unicode码转为gb2312码 
 rec = u2g(in_utf8,strlen(in_utf8),out,OUTLEN); 
 printf("unicode--&gt;gb2312 out=%s\n",out); 
 
 //gb2312码转为unicode码 
 rec = g2u(in_gb2312,strlen(in_gb2312),out,OUTLEN); 
 printf("gb2312--&gt;unicode out=%s \n",out); 
 } 
 //代码转换:从一种编码转为另一种编码 
 int code_convert(char *from_charset,char *to_charset,char *inbuf,int inlen,char *outbuf,int outlen) 
 { 
 iconv_t cd; 
 int rc; 
 char **pin = &amp;inbuf; 
 char **pout = &amp;outbuf; 
 
 cd = iconv_open(to_charset,from_charset); 
 if (cd==0) return -1; 
 memset(outbuf,0,outlen); 
 if (iconv(cd,pin,&amp;inlen,pout,&amp;outlen)==-1) return -1; 
 iconv_close(cd); 
 return 0; 
 } 
 //UNICODE码转为GB2312码 
 int u2g(char *inbuf,int inlen,char *outbuf,int outlen) 
 { 
 return code_convert("utf-8","gb2312",inbuf,inlen,outbuf,outlen); 
 } 
 //GB2312码转为UNICODE码 
 int g2u(char *inbuf,size_t inlen,char *outbuf,size_t outlen) 
 { 
 return code_convert("gb2312","utf-8",inbuf,inlen,outbuf,outlen); 
 </div> </td> 
 </tr> 
 </tbody> 
</table>