utf_functions.h

utf8转换工具

/*
* Written by Boby Thomas Pazheparampil. (March 2007.)
* Platform independent code.  (I hope so)
* Tested with Windows 2000, XP, Cygwin and Linux Debian.
*/


#ifndef utf_functions_h__
#define utf_functions_h__


#include <iostream>
#include <string>
#include <math.h>



using namespace std;




/*************************************************************************
* @f Fnct			: convertHex2UTF
* @r Return			: single character UTF string.
* Description       : Convert stl hex charater string to corresponding
						UTF character string. Do not misunderstand this function
                  with a stream converter. This function converts only one 
                  character. 
                  For example 
                  "7f" return "7f"
                  "80" return "c280"
                  "fffd" return "efbfbd"

* @author			: Boby thomas
**************************************************************************/
string convertHex2UTF(string);

/*************************************************************************
* @f Fnct			: convertUTF2Hex
* @r Return			: Hex value corresponding to the UTF chracter.
						"error" on invalid character.
* Description       : Returns the hex value corresponding to a UTF character.
						Do not misunderstand this function with a stream converter.
                  This function convert only one UTF-8 character. 
                  For example 
                  "7f" return "7f"
                  "c280" return "80"
                  "efbfbd" return "fffd"

* @author			: Boby thomas
**************************************************************************/
string convertUTF2Hex(string);


/*************************************************************************
* @f Fnct			: findLengthUTF
* @r Return			: single character. Normaly first character of a UTF stream.
						-1 for invalid UTF entry.
* Description       : Returns the number of characters in the UTF string.
						Say for example 0xc2  will return 2 since one more byte 
						following this will constitute the UTF character.
* @author			: Boby thomas
**************************************************************************/
long findLengthUTF(string sUTFFirstByte);


/*************************************************************************
* @f Fnct			: generateUTFFileDetails
* @r Return			: true - file could be a UTF file. 
						(No invalid UTF character in the file)
* Description       : This function evaluate a file for validity. Returns false
						if there a single occurance of a nonpossible character.
						Writes a file utfdetails_<filename> with all the utf 
						character details.
* @author			: Boby thomas
**************************************************************************/
bool generateUTFFileDetails(string sFileName);

/*************************************************************************
* @f Fnct			: hex2binary
* @r Return			: Binary string.
* Description       : Convert stl string of hex values to a binary string.
* @author			: Boby thomas
**************************************************************************/

string hex2binary(string sAscii);

/*************************************************************************
* @f Fnct			: binary2hex
* @r Return			: Hexadecimal string.
* Description       : Convert stl binary string to of hex value string.
						Accept binary string of any length. 
* @author			: Boby thomas
**************************************************************************/
string binary2hex(string sBinary);

#endif //utf_functions_h__