Linux C ++ Character Set conversion, UTF-8, gb2312

During encoding and conversion on Linux, you can use both the iconv function family programming and the iconv command, but the latter is for files, converts a specified file from one encoding to another.
I. Use the iconv function family for encoding and conversion
When iconv function family headers are encoded and converted in Linux, they can be implemented using both the iconv function family programming and the iconv command, except that the latter is for files, converts a specified file from one encoding to another.

I. Use the iconv function family for encoding and conversion
The header file of the iconv function family is iconv. H, which must be included before use.
# Include <iconv. h>
The iconv function family has three functions. The prototype is as follows:
(1) iconv_t iconv_open (const char * tocode, const char * fromcode );
This function indicates which two types of encoding are to be converted. tocode is the target encoding and fromcode is the original encoding. This function returns a conversion handle for the following two functions.
(2) size_t iconv (iconv_t CD, char ** inbuf, size_t * inbytesleft, char ** outbuf, size_t * outbytesleft );

This function reads characters from inbuf and outputs the converted characters to outbuf. inbytesleft records the number of characters that have not been converted, and outbytesleft records the remaining space of the output buffer. (3) int iconv_close (iconv_t CD );

This function is used to close the conversion handle and release resources.
Example 1: A conversion example program implemented in C Language

/* F. C: Code Conversion example C program */
# Include <iconv. h>
# Deprecision outlen 255
Main ()
{
Char * in_utf8 = "e? Why ?? Why? ";
Char * in_gb2312 = "installing ";
Char out [outlen];

// Convert Unicode code to gb2312 code
Rc = u2g (in_utf8, strlen (in_utf8), Out, outlen );
Printf ("Unicode --> gb2312 out = % Sn", out );
// Convert the gb2312 code to the Unicode code
Rc = g2u (in_gb2312, strlen (in_gb2312), Out, outlen );
Printf ("gb2312 --> Unicode out = % Sn", out );
}
// Code Conversion: Convert from one encoding to another
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;
}
// Convert Unicode code to gb2312 code
Int u2g (char * inbuf, int inlen, char * outbuf, int outlen)
{
Return code_convert ("UTF-8", "gb2312", inbuf, inlen, outbuf, outlen );
}
// Convert the gb2312 code to the Unicode code
Int g2u (char * inbuf, size_t inlen, char * outbuf, size_t outlen)
{
Return code_convert ("gb2312", "UTF-8", inbuf, inlen, outbuf, outlen );
}

Example 2: A conversion example program in C ++

/* F. cpp: Code Conversion example c ++ Program */
# Include <iconv. h>
# Include <iostream>

# Deprecision outlen 255

Using namespace STD;

// Code conversion operation class
Class codeconverter {
PRIVATE:
Iconv_t CD;
Public:
// Construct
Codeconverter (const char * from_charset, const char * to_charset ){
Cd = iconv_open (to_charset, from_charset );
}

// Structure
~ Codeconverter (){
Iconv_close (CD );
}

// Conversion output
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 = "e? Why ?? Why? ";
Char * in_gb2312 = "installing ";
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;
} Linux C Character Set conversion, UTF-8, gb2312 recently helped a friend to write a system interface of small Dongdong, two different system character set, a use of UTF-8, a use of gb2312, had to convert character set. The conversion function record is as follows:

# Include <iconv. h>
# Include <stdio. h>
# Include <stdlib. h>
# Include <string. h>
# Deprecision outlen 255
Main ()
{
Char * in_utf8 = "utf8 string ";
Char * in_gb2312 = "\ xbe \ XB2 \ Xcc \ xac \ xc4 \ xa3 \ xca \ xbd ";

Char out [outlen];
Int REC;

// Convert Unicode code to gb2312 code
Rec = u2g (in_utf8, strlen (in_utf8), Out, outlen );
Printf ("Unicode --> gb2312 out = % s \ n", out );

// Convert the gb2312 code to the Unicode code
Rec = g2u (in_gb2312, strlen (in_gb2312), Out, outlen );
Printf ("gb2312 --> Unicode out = % s \ n", out );
}
// Code Conversion: Convert from one encoding to another
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;
}
// Convert Unicode code to gb2312 code
Int u2g (char * inbuf, int inlen, char * outbuf, int outlen)
{
Return code_convert ("UTF-8", "gb2312", inbuf, inlen, outbuf, outlen );
}
// Convert the gb2312 code to the Unicode code
Int g2u (char * inbuf, size_t inlen, char * outbuf, size_t outlen)
{
Return code_convert ("gb2312", "UTF-8", inbuf, inlen, outbuf, outlen );