C++ 字符集转换 codecvt utf-8 gb2312 url

最新推荐文章于 2023-06-09 14:17:00 发布

C++程序员Carea

最新推荐文章于 2023-06-09 14:17:00 发布

阅读量6.5k

点赞数 2

分类专栏： C++

本文链接：https://blog.csdn.net/calmreason/article/details/17278157

版权

C++ 专栏收录该内容

98 篇文章 15 订阅

订阅专栏

现在的做法：

http://www.cppblog.com/mythma/archive/2012/09/11/wstring_convert_utf8.html

扔掉MultiByteToWideChar 吧，使用std::wstring_convert和 std::codecvt_utf8 来处理UTF8与WChar之间的互转。
VC和Clang都支持哦~

#include <iostream>
#include <string>
#include <locale>
#include <codecvt>
#include <fstream>

int main(int argc, char *argv[])
{
std::wstring str = L"123,我是谁？我爱钓鱼岛！";

std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;

std::string narrowStr = conv.to_bytes(str);
{
std::ofstream ofs ("c:\\test.txt");
ofs << narrowStr;
}

std::wstring wideStr = conv.from_bytes(narrowStr);
{
std::locale::global(std::locale("Chinese-simplified"));
std::wofstream ofs (L"c:\\testW.txt");
ofs << wideStr;
}
｝

之前的做法：

vs默认是GB2312编码，你看到的程序源代码是，输出结果是，内部存储是，

1 如果你想改变内部存储可以用下面的这些函数

2 如果你想改变源代码的存储方式你可以用文本编辑工具修改之后重新编译

3 如果你想修改输出编码，你还没发让她输出UTF-8的目前

4 但是这并不影响你的程序跨平台的处理，因为你总是将任何字符类型的编码字符串保存在单字节的string中，如果你知道需要处理固定双字节的字符，你可以使用wstring

strCoding.h

//这是个类strCoding (strCoding.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);

};

strCoding.cpp

//这是个类strCoding (strCoding.cpp文件)
//#include "StdAfx.h"

#include ".\strcoding.h"



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]='\0';
	pOut = rst; 
	delete []rst;
}

//GB2312 转为 UTF-8
void strCoding::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
	char buf[4];
	memset(buf,0,4);

	pOut.clear();

	int i = 0;
	while(i < pLen)
	{
		//如果是英文直接复制就可以
		if( pText[i] >= 0)
		{
			char asciistr[2]={0};
			asciistr[0] = (pText[i++]);
			pOut.append(asciistr);
		}
		else
		{
			WCHAR pbuffer;
			Gb2312ToUnicode(&pbuffer,pText+i);

			UnicodeToUTF_8(buf,&pbuffer);

			pOut.append(buf);

			i += 2;
		}
	}

	return;
}
//把str编码为网页中的 GB2312 url encode ,英文不变，汉字双字节  如%3D%AE%88
string strCoding::UrlGB2312(char * str)
{
	string dd;
	size_t len = strlen(str);
	for (size_t i=0;i<len;i++)
	{
		if(isalnum((BYTE)str[i]))
		{
			char tempbuff[2];
			sprintf(tempbuff,"%c",str[i]);
			dd.append(tempbuff);
		}
		else if (isspace((BYTE)str[i]))
		{
			dd.append("+");
		}
		else
		{
			char tempbuff[4];
			sprintf(tempbuff,"%%%X%X",((BYTE*)str)[i] >>4,((BYTE*)str)[i] %16);
			dd.append(tempbuff);
		}

	}
	return dd;
}

//把str编码为网页中的 UTF-8 url encode ,英文不变，汉字三字节  如%3D%AE%88

string strCoding::UrlUTF8(char * str)
{
	string tt;
	string dd;
	GB2312ToUTF_8(tt,str,(int)strlen(str));

	size_t len=tt.length();
	for (size_t i=0;i<len;i++)
	{
		if(isalnum((BYTE)tt.at(i)))
		{
			char tempbuff[2]={0};
			sprintf(tempbuff,"%c",(BYTE)tt.at(i));
			dd.append(tempbuff);
		}
		else if (isspace((BYTE)tt.at(i)))
		{
			dd.append("+");
		}
		else
		{
			char tempbuff[4];
			sprintf(tempbuff,"%%%X%X",((BYTE)tt.at(i)) >>4,((BYTE)tt.at(i)) %16);
			dd.append(tempbuff);
		}

	}
	return dd;
}
//把url GB2312解码
string strCoding::UrlGB2312Decode(string str)
{
	string output="";
	char tmp[2];
	int i=0,idx=0,ndx,len=str.length();

	while(i<len){
		if(str[i]=='%'){
			tmp[0]=str[i+1];
			tmp[1]=str[i+2];
			output += StrToBin(tmp);
			i=i+3;
		}
		else if(str[i]=='+'){
			output+=' ';
			i++;
		}
		else{
			output+=str[i];
			i++;
		}
	}

	return output;
}
//把url utf8解码
string strCoding::UrlUTF8Decode(string str)
{
	string output="";

	string temp =UrlGB2312Decode(str);//

	UTF_8ToGB2312(output,(char *)temp.data(),strlen(temp.data()));

	return output;

}

main.cpp

//test
//#include "stdafx.h"
#include "strCoding.h"

using namespace std;


int main()
{ 

	strCoding cfm;
	string keyword="大家好,欢迎你";
	string Temp="";
	string Output="";

	//把关键字做url的utf8编码
	Temp= cfm.UrlUTF8((char *)keyword.data());
	cout<<Temp<<endl;

	//把url的utf8编码的结果解码
	Temp =cfm.UrlUTF8Decode(Temp);
	cout<<Temp<<endl;

	//把关键字做url的gb2312编码
	Temp =cfm.UrlGB2312((char *)keyword.data());
	cout<<Temp<<endl;

	//把url的gb2312编码的结果解码
	Temp =cfm.UrlGB2312Decode(Temp);
	cout<<Temp<<endl;


	//把关键字GB2312转UTF_8

	cfm.GB2312ToUTF_8(Output,(char *)keyword.data(),strlen(keyword.data()));
	cout<<Output<<endl;

	//把GB2312转UTF_8转为中文
	cfm.UTF_8ToGB2312(Temp,(char *)Output.data(),strlen(Output.data()));
	cout<<Temp<<endl;


	//system("pasue");
	getchar();

	return 0;
	//
}

C++程序员Carea

关注

2
点赞
踩
8

收藏

觉得还不错? 一键收藏
打赏
0
评论
C++ 字符集转换 codecvt utf-8 gb2312 url

现在的做法：http://www.cppblog.com/mythma/archive/2012/09/11/wstring_convert_utf8.html扔掉MultiByteToWideChar 吧，使用std::wstring_convert和 std::codecvt_utf8 来处理UTF8与WChar之间的互转。VC和Clang都支持哦~#include
复制链接

扫一扫