iconv 文件编码转换

查了下iconv命令用法如下：

iconv [选项...] [文件...]

有如下选项可用:

输入/输出格式规范：
-f, --from-code=名称 原始文本编码
-t, --to-code=名称 输出编码

信息：
-l, --list 列举所有已知的字符集

输出控制：
-c 从输出中忽略无效的字符
-o, --output=FILE 输出文件
-s, --silent 关闭警告
--verbose 打印进度信息

iconv -f utf-8 -t gb2312 /server_test/reports/software_.txt > /server_test/reports/software_asserts.txt

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。

例子1: 用C语言实现的转换示例程序

/* f.c : 代码转换示例C程序 */
#include <iconv.h>
#define OUTLEN 255
main()
{
char *in_utf8 = "姝ｅ?ㄥ??瑁?";
char *in_gb2312 = "正在安装";
char out[OUTLEN];

//unicode码转为gb2312码
rc = u2g(in_utf8,strlen(in_utf8),out,OUTLEN);
printf("unicode-->gb2312 out=%sn",out);
//gb2312码转为unicode码
rc = g2u(in_gb2312,strlen(in_gb2312),out,OUTLEN);
printf("gb2312-->unicode out=%sn",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 = &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);
}

例子2: 用C++语言实现的转换示例程序

/* f.cpp : 代码转换示例C++程序 */
#include <iconv.h>
#include <iostream>

#define OUTLEN 255

using namespace std;

// 代码转换操作类
class CodeConverter {
private:
iconv_t cd;
public:
// 构造
CodeConverter(const char *from_charset,const char *to_charset) {
cd = iconv_open(to_charset,from_charset);
}

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

// 转换输出
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 = "正在安装";
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;
}

例子3.iconv实现通用语言编码转换(c++)
   可以实现对任意的两个iconv支持的语言编码做互相转换，比如GB2312, GBK, GB18030, UTF-8, UTF-16, BIG5等.
下面这段程序，非常的稳定，测试了超过10万行的数十种编码的文本的转换都没有出问题。 

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <iconv.h>

#ifndef ICONV_CONST
# define ICONV_CONST const
#endif

/*!
 对字符串进行语言编码转换
 param from  原始编码，比如"GB2312",的按照iconv支持的写
 param to      转换的目的编码
 param save  转换后的数据保存到这个指针里，需要在外部分配内存
 param savelen 存储转换后数据的内存大小
 param src      原始需要转换的字符串
 param srclen    原始字符串长度
 */
int
convert(const char *from, const char *to, char* save, int savelen, char *src, int srclen)
{
    iconv_t cd;
    char   *inbuf = src;
    char *outbuf = save;
    size_t outbufsize = savelen;
    int status = 0;
    size_t  savesize = 0;
    size_t inbufsize = srclen;
    const char* inptr = inbuf;
    size_t      insize = inbufsize;
    char* outptr = outbuf;
    size_t outsize = outbufsize;
    
    cd = iconv_open(to, from);
    iconv(cd,NULL,NULL,NULL,NULL);
    if (inbufsize == 0) {
        status = -1;
        goto done;
    }
    while (insize > 0) {
        size_t res = iconv(cd,(ICONV_CONST char**)&inptr,&insize,&outptr,&outsize);
        if (outptr != outbuf) {
            int saved_errno = errno;
            int outsize = outptr - outbuf;
            strncpy(save+savesize, outbuf, outsize);
            errno = saved_errno;
        }
        if (res == (size_t)(-1)) {
            if (errno == EILSEQ) {
                int one = 1;
                iconvctl(cd,ICONV_SET_DISCARD_ILSEQ,&one);
                status = -3;
            } else if (errno == EINVAL) {
                if (inbufsize == 0) {
                    status = -4;
                    goto done;
                } else {
                    break;
                }
            } else if (errno == E2BIG) {
                status = -5;
                goto done;
            } else {
                status = -6;
                goto done;
            }
        }
    }
    status = strlen(save);
done:
    iconv_close(cd);
    return status;

}

iconv的支持的编码有

ANSI_X3.4-1968 ANSI_X3.4-1986 ASCII CP367 IBM367 ISO-IR-6 ISO646-US ISO_646.IRV:1991 US US-ASCII CSASCII
UTF-8
ISO-10646-UCS-2 UCS-2 CSUNICODE
UCS-2BE UNICODE-1-1 UNICODEBIG CSUNICODE11
UCS-2LE UNICODELITTLE
ISO-10646-UCS-4 UCS-4 CSUCS4
UCS-4BE
UCS-4LE
UTF-16
UTF-16BE
UTF-16LE
UTF-32
UTF-32BE
UTF-32LE
UNICODE-1-1-UTF-7 UTF-7 CSUNICODE11UTF7
UCS-2-INTERNAL
UCS-2-SWAPPED
UCS-4-INTERNAL
UCS-4-SWAPPED
C99
JAVA
CP819 IBM819 ISO-8859-1 ISO-IR-100 ISO8859-1 ISO_8859-1 ISO_8859-1:1987 L1 LATIN1 CSISOLATIN1
ISO-8859-2 ISO-IR-101 ISO8859-2 ISO_8859-2 ISO_8859-2:1987 L2 LATIN2 CSISOLATIN2
ISO-8859-3 ISO-IR-109 ISO8859-3 ISO_8859-3 ISO_8859-3:1988 L3 LATIN3 CSISOLATIN3
ISO-8859-4 ISO-IR-110 ISO8859-4 ISO_8859-4 ISO_8859-4:1988 L4 LATIN4 CSISOLATIN4
CYRILLIC ISO-8859-5 ISO-IR-144 ISO8859-5 ISO_8859-5 ISO_8859-5:1988 CSISOLATINCYRILLIC
ARABIC ASMO-708 ECMA-114 ISO-8859-6 ISO-IR-127 ISO8859-6 ISO_8859-6 ISO_8859-6:1987 CSISOLATINARABIC
ECMA-118 ELOT_928 GREEK GREEK8 ISO-8859-7 ISO-IR-126 ISO8859-7 ISO_8859-7 ISO_8859-7:1987 CSISOLATINGREEK
HEBREW ISO-8859-8 ISO-IR-138 ISO8859-8 ISO_8859-8 ISO_8859-8:1988 CSISOLATINHEBREW
ISO-8859-9 ISO-IR-148 ISO8859-9 ISO_8859-9 ISO_8859-9:1989 L5 LATIN5 CSISOLATIN5
ISO-8859-10 ISO-IR-157 ISO8859-10 ISO_8859-10 ISO_8859-10:1992 L6 LATIN6 CSISOLATIN6
ISO-8859-13 ISO-IR-179 ISO8859-13 ISO_8859-13 L7 LATIN7
ISO-8859-14 ISO-CELTIC ISO-IR-199 ISO8859-14 ISO_8859-14 ISO_8859-14:1998 L8 LATIN8
ISO-8859-15 ISO-IR-203 ISO8859-15 ISO_8859-15 ISO_8859-15:1998 LATIN-9
ISO-8859-16 ISO-IR-226 ISO8859-16 ISO_8859-16 ISO_8859-16:2001 L10 LATIN10
KOI8-R CSKOI8R
KOI8-U
KOI8-RU
CP1250 MS-EE WINDOWS-1250
CP1251 MS-CYRL WINDOWS-1251
CP1252 MS-ANSI WINDOWS-1252
CP1253 MS-GREEK WINDOWS-1253
CP1254 MS-TURK WINDOWS-1254
CP1255 MS-HEBR WINDOWS-1255
CP1256 MS-ARAB WINDOWS-1256
CP1257 WINBALTRIM WINDOWS-1257
CP1258 WINDOWS-1258
850 CP850 IBM850 CSPC850MULTILINGUAL
862 CP862 IBM862 CSPC862LATINHEBREW
866 CP866 IBM866 CSIBM866
MAC MACINTOSH MACROMAN CSMACINTOSH
MACCENTRALEUROPE
MACICELAND
MACCROATIAN
MACROMANIA
MACCYRILLIC
MACUKRAINE
MACGREEK
MACTURKISH
MACHEBREW
MACARABIC
MACTHAI
HP-ROMAN8 R8 ROMAN8 CSHPROMAN8
NEXTSTEP
ARMSCII-8
GEORGIAN-ACADEMY
GEORGIAN-PS
KOI8-T
MULELAO-1
CP1133 IBM-CP1133
ISO-IR-166 TIS-620 TIS620 TIS620-0 TIS620.2529-1 TIS620.2533-0 TIS620.2533-1
CP874 WINDOWS-874
VISCII VISCII1.1-1 CSVISCII
TCVN TCVN-5712 TCVN5712-1 TCVN5712-1:1993
ISO-IR-14 ISO646-JP JIS_C6220-1969-RO JP CSISO14JISC6220RO
JISX0201-1976 JIS_X0201 X0201 CSHALFWIDTHKATAKANA
ISO-IR-87 JIS0208 JIS_C6226-1983 JIS_X0208 JIS_X0208-1983 JIS_X0208-1990 X0208 CSISO87JISX0208
ISO-IR-159 JIS_X0212 JIS_X0212-1990 JIS_X0212.1990-0 X0212 CSISO159JISX02121990
CN GB_1988-80 ISO-IR-57 ISO646-CN CSISO57GB1988
CHINESE GB_2312-80 ISO-IR-58 CSISO58GB231280
CN-GB-ISOIR165 ISO-IR-165
ISO-IR-149 KOREAN KSC_5601 KS_C_5601-1987 KS_C_5601-1989 CSKSC56011987
EUC-JP EUCJP EXTENDED_UNIX_CODE_PACKED_FORMAT_FOR_JAPANESE CSEUCPKDFMTJAPANESE
MS_KANJI SHIFT-JIS SHIFT_JIS SJIS CSSHIFTJIS
CP932
ISO-2022-JP CSISO2022JP
ISO-2022-JP-1
ISO-2022-JP-2 CSISO2022JP2
CN-GB EUC-CN EUCCN GB2312 CSGB2312
CP936 GBK MS936 WINDOWS-936
GB18030
ISO-2022-CN CSISO2022CN
ISO-2022-CN-EXT
HZ HZ-GB-2312
EUC-TW EUCTW CSEUCTW
BIG-5 BIG-FIVE BIG5 BIGFIVE CN-BIG5 CSBIG5
CP950
BIG5-HKSCS BIG5HKSCS
EUC-KR EUCKR CSEUCKR
CP949 UHC
CP1361 JOHAB
ISO-2022-KR CSISO2022KR
437 CP437 IBM437 CSPC8CODEPAGE437
CP737
CP775 IBM775 CSPC775BALTIC
852 CP852 IBM852 CSPCP852
CP853
855 CP855 IBM855 CSIBM855
857 CP857 IBM857 CSIBM857
CP858
860 CP860 IBM860 CSIBM860
861 CP-IS CP861 IBM861 CSIBM861
863 CP863 IBM863 CSIBM863
CP864 IBM864 CSIBM864
865 CP865 IBM865 CSIBM865
869 CP-GR CP869 IBM869 CSIBM869
CP1125