下面的代码实现了一个用于C++中转码的类strCoding。里面有UTF8、UNICODE、GB2312编码的互相转换。
.H文件:
#pragma once #include <iostream> #include <string> #include <windows.h> using namespace std; class strCoding { public: strCoding(void); ~strCoding(void); void UTF_8ToGB2312(string &pOut, char *pText, int pLen);//utf_8转为gb2312 void GB2312ToUTF_8(string& pOut,char *pText, int pLen); //gb2312 转utf_8 string UrlGB2312(char * str); //urlgb2312编码 string UrlUTF8(char * str); //urlutf8 编码 string UrlUTF8Decode(string str); //urlutf8解码 string UrlGB2312Decode(string str); //urlgb2312解码 private: void Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer); void UTF_8ToUnicode(WCHAR* pOut,char *pText); void UnicodeToUTF_8(char* pOut,WCHAR* pText); void UnicodeToGB2312(char* pOut,WCHAR uData); char CharToInt(char ch); char StrToBin(char *str); };
.cpp
#include "StdAfx.h" #include ".urlcodeing.h" //这是个类strCoding (strCoding.cpp文件) strCoding::strCoding(void) { } strCoding::~strCoding(void) { } void strCoding::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer) { ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1); return; } void strCoding::UTF_8ToUnicode(WCHAR* pOut,char *pText) { char* uchar = (char *)pOut; uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F); uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F); return; } void strCoding::UnicodeToUTF_8(char* pOut,WCHAR* pText) { // 注意 WCHAR高低字的顺序,低字节在前,高字节在后 char* pchar = (char *)pText; pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4)); pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6); pOut[2] = (0x80 | (pchar[0] & 0x3F)); return; } void strCoding::UnicodeToGB2312(char* pOut,WCHAR uData) { WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL); return; } //做为解Url使用 char strCoding:: CharToInt(char ch){ if(ch>='0' && ch<='9')return (char)(ch-'0'); if(ch>='a' && ch<='f')return (char)(ch-'a'+10); if(ch>='A' && ch<='F')return (char)(ch-'A'+10); return -1; } char strCoding::StrToBin(char *str){ char tempWord[2]; char chn; tempWord[0] = CharToInt(str[0]); //make the B to 11 -- 00001011 tempWord[1] = CharToInt(str[1]); //make the 0 to 0 -- 00000000 chn = (tempWord[0] << 4) | tempWord[1]; //to change the BO to 10110000 return chn; } //UTF_8 转gb2312 void strCoding::UTF_8ToGB2312(string &pOut, char *pText, int pLen) { char buf[4]; char* rst = new char[pLen + (pLen >> 2) + 2]; memset(buf,0,4); memset(rst,0,pLen + (pLen >> 2) + 2); int i =0; int j = 0; while(i < pLen) { if(*(pText + i) >= 0) { rst[j++] = pText[i++]; } else { WCHAR Wtemp; UTF_8ToUnicode(&Wtemp,pText + i); UnicodeToGB2312(buf,Wtemp); unsigned short int tmp = 0; tmp = rst[j] = buf[0]; tmp = rst[j+1] = buf[1]; tmp = rst[j+2] = buf[2]; //newBuf[j] = Ctemp[0]; //newBuf[j + 1] = Ctemp[1]; i += 3; j += 2; } } rst[j]='