C++读取和处理UTF-8格式文件的方法_C/C++_编程开发_程序员俱乐部

class="c++">
// UtfFile.h: interface for the UtfFile class.
//
//////////////////////////////////////////////////////////////////////

#if !defined(AFX_UTFFILE_H__8ED10D8A_D1A3_412F_A600_124F521CE4F1__INCLUDED_)
#define AFX_UTFFILE_H__8ED10D8A_D1A3_412F_A600_124F521CE4F1__INCLUDED_

#if _MSC_VER > 1000
#pragma once
#endif // _MSC_VER > 1000

#include <windows.h> 
#include <stdio.h>
#include <locale.h>
#include <IOSTREAM>
#include <FSTREAM>
using namespace std;

class UtfFile 
{
public:
 static char * UnicodeToGB2312(WCHAR uData, char buffer[2]);  // Unicode 转换成 GB2312
 static WCHAR * UTF_8ToUnicode(char *pText, WCHAR &unicode);  // 把UTF-8 转化成 Unicode
 static char * TranslateUTF8ToGB(char *str, size_t len);   // 把UTF-8字符串转化成ANSI（GB2312）编码形式
 char * GetString(char *str, int maxLen = 1024);  // 读取一个字符串，以换行符为结束标示
 char * GetLine(char *str, int maxLen);    // 读取一行字符
 void close();          // 关闭文件流
 int open(const char *sFileName);     // 用于打开一个文件
 UtfFile(const char *sour);
 virtual ~UtfFile();
 
private:
 ifstream inf;
};

#endif // !defined(AFX_UTFFILE_H__8ED10D8A_D1A3_412F_A600_124F521CE4F1__INCLUDED_)

 

/*-----------------------------------------------以下为.cpp文件内容------------------------------------------*/

// UtfFile.cpp: implementation of the UtfFile class.
//
//////////////////////////////////////////////////////////////////////

#include "UtfFile.h"

//////////////////////////////////////////////////////////////////////
// Construction/Destruction
//////////////////////////////////////////////////////////////////////

UtfFile::UtfFile(const char *sour)
:inf(sour)
{
 if( !inf.is_open() )
 {
  char str[1024];
  sprintf(str, "错误的文件路径，文件无法打开：%s", sour);
  throw runtime_error(str);
 }
}

UtfFile::~UtfFile()
{

}

void UtfFile::close()
{
 inf.close();
}


char * UtfFile::GetLine(char *str, int maxLen)
{
 if ( inf.eof() )
 {
  str[0] = '\0';
 }
 else
 {
  inf.getline(str, maxLen);
  TranslateUTF8ToGB(str, maxLen);
 }
 return str;
}


char * UtfFile::GetString(char *str, int maxLen)
{
 if ( inf.eof() )
 {
  str[0] = '\0';
 }
 else
 {
  inf >> str;
  TranslateUTF8ToGB(str, maxLen);
 }
 return str;
}

 

char * UtfFile::UnicodeToGB2312(WCHAR uData, char buffer[2])
{
 WideCharToMultiByte(CP_ACP,NULL, &uData, 1,buffer,sizeof(WCHAR),NULL,NULL);
 return buffer;
}

WCHAR * UtfFile::UTF_8ToUnicode(char *pText, WCHAR &unicode)
{ 
/*    http://blog.csdn.net/liuzhiyuan1982/article/details/3911150
UTF-8是一种多字节编码的字符集，表示一个Unicode字符时，它可以是1个至多个字节，在表示上有规律：
1字节：0xxxxxxx
2字节：110xxxxx 10xxxxxx
3字节：1110xxxx 10xxxxxx 10xxxxxx
4字节：11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
*/
 char *uchar = (char *)&unicode; 
 uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
 uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);
 return &unicode;
}

char * UtfFile::TranslateUTF8ToGB(char *str, size_t len)
{
 char * newCharBuffer = new char[len];
 int index =0;
 int nCBIndex = 0;
 WCHAR wTemp = 0;
 char cTemp[2] = " ";
 while(index < len)
 {
  if ( str[index] == 0 )
   break;
  else if(str[index] > 0)  // 如果是GB2312的字符
  {
   newCharBuffer[nCBIndex] = str[index];    //直接复制
   index += 1;    //源字符串偏移量1
   nCBIndex += 1;   //目标字符串偏移量1
  }
  else      //如果是UTF-8的字符
  {
   UTF_8ToUnicode(str + index, wTemp);   //先把UTF-8转成Unicode
   UnicodeToGB2312(wTemp, &newCharBuffer[nCBIndex]); //再把Unicode 转成 GB2312
   index += 3;    //源字符串偏移量3
   nCBIndex += 2;   //目标字符串偏移量2  因为一个中文UTF-8占3个字节，GB2312占两个字节
  }
 }
 newCharBuffer[nCBIndex] = '\0'; //结束符
 strcpy( str, newCharBuffer );
 delete newCharBuffer;  //避免内存泄漏，这是对源代码的稍许修改
 newCharBuffer = NULL;
 return str;  
}

int UtfFile::open(const char *sFileName)
{
 inf.open(sFileName);
 return inf.is_open();
}