telsale-management/代码/cpp/telsale_aux_kit/source/StringCodeConverter.cpp

//#include "stdafx.h"
#include "StringCodeConverter.h"
#include <locale.h>
#include <stdlib.h>
//#include <stdio.h>
#include <string>
#include <cstring>
 
using namespace std;

size_t StringCodeConverter::mbslen( const char *pcszSource )
{
	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" );

    int mbl = 0;
    size_t cnt = 0;

    for (cnt = 0; *pcszSource; ++cnt)
	{
		mbl = mblen( pcszSource, MB_CUR_MAX );
		pcszSource += mbl;
	}

	setlocale( LC_ALL, strCurLocale.c_str() );

	return cnt;
}

wstring StringCodeConverter::mbs2unicode( const string &cstrSource )
{
	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	const char *pcszSource = cstrSource.c_str();

	size_t iCount = cstrSource.size() + 1;
	wchar_t *pwszBuffer = new wchar_t[ iCount ];

	wmemset( pwszBuffer, 0, iCount );
	size_t iConvertedCount = mbstowcs( pwszBuffer, pcszSource, iCount );

	if ( iConvertedCount == -1 )
	{
		delete [] pwszBuffer; 
		throw string( "mbs2unicode参数有非中英文字符" );
	}

	wstring wstrDest( pwszBuffer );
	delete [] pwszBuffer;

	setlocale( LC_ALL, strCurLocale.c_str() );

	return wstrDest;
}

void StringCodeConverter::mbs2unicode(const string &strSource, wstring &wstrDest)
{
	const char *pcszSource = strSource.c_str();
	string strCurLocale( setlocale(LC_ALL, NULL) );//先保存当前的locale设置
	
	setlocale( LC_ALL, "chs" );//设置为中文

	size_t iCharCount = strSource.size() + 1;//unicode字符串所需要的字符数
	wchar_t *pwszBuffer = new wchar_t[ iCharCount ];

	wmemset( pwszBuffer, 0, iCharCount );
	mbstowcs( pwszBuffer, pcszSource, iCharCount );

	setlocale( LC_ALL, strCurLocale.c_str() );//改回原来的locale设置

	wstrDest = pwszBuffer;
	delete [] pwszBuffer;
}

void StringCodeConverter::mbs2unicode( const char *pcszSource, wchar_t *pwszDest ) throw (string)
{
	if ( pcszSource == NULL || pwszDest == NULL )
	{
		throw string( "参数指针为NULL" );
	}

	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	size_t iCharCount = mbslen( pcszSource ) + 1;

	if ( iCharCount == -1 )
	{
		throw string( "源字符串的编码有非中英文字符" );
	}

	wmemset( pwszDest, 0, iCharCount );
	size_t iConvertedCount = mbstowcs( pwszDest, pcszSource, iCharCount );

	if ( iConvertedCount == -1 )
	{
		throw string( "源字符串的编码有非中英文字符" );
	}

	*( pwszDest + iConvertedCount ) = NULL;

	setlocale( LC_ALL, strCurLocale.c_str() );
}

void StringCodeConverter::mbs2utf8( const string &cstrSource, char *pszDest )
{
	const char *pcszSource = cstrSource.c_str();

	string strCurLocale( setlocale( LC_ALL, NULL ) );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	while ( *pcszSource != NULL )
	{
		if ( *pcszSource > 0 )
		{
			//英文字符,可以直接复制
			*pszDest = *pcszSource;
			
			pcszSource++;
			pszDest++;
		}
		else
		{
			//非ascii英文字符,先转换成unicode，再转换utf8
			int iLen = 0;
			wchar_t wUnicode = 0;
			char *pcUnicode = (char *)&wUnicode;

			//转换成unicode，返回mb字符的长度
			iLen = mbtowc( &wUnicode, pcszSource, MB_CUR_MAX );

			pszDest[0] = (0xE0 | ((pcUnicode[1] & 0xF0) >> 4));
			pszDest[1] = (0x80 | ((pcUnicode[1] & 0x0F) << 2)) + ((pcUnicode[0] & 0xC0) >> 6);
			pszDest[2] = (0x80 | (pcUnicode[0] & 0x3F));

			pszDest += 3;
			pcszSource += iLen;
		}
	}

	setlocale( LC_ALL, strCurLocale.c_str() );

	*pszDest = NULL;
}

string StringCodeConverter::unicode2mbs( const wstring &wstrSource )
{
	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	const wchar_t *pcwszSource = wstrSource.c_str();

	size_t iCount = wstrSource.size() * 2 + 1;
	char *pszBuffer = new char[ iCount ];
	memset( pszBuffer, 0, iCount );

	size_t iConvertedCount = wcstombs( pszBuffer, pcwszSource, iCount );

	if ( iConvertedCount == -1 )
	{
		throw string( "unicode2mbs源字符串的编码有非中英文字符" );
	}

	setlocale( LC_ALL, strCurLocale.c_str() );

	string strDest( pszBuffer );
	delete [] pszBuffer;

	return strDest;
}

void StringCodeConverter::unicode2mbs( const wstring &wstrSource, string &strDest )
{
	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chs" );

	size_t iCount = wstrSource.size() + 1;
	char *pszBuffer = new char[ iCount ];
	const wchar_t *pcwszSource = wstrSource.c_str();

	memset( pszBuffer, 0, iCount );
	size_t iConvertedCount = wcstombs( pszBuffer, pcwszSource , iCount );

	if ( iConvertedCount == -1 )
	{
		delete [] pszBuffer;
		throw string( "unicode2mbs转换失败，字符串中有非中英文字符！" );
	}

	strDest = pszBuffer;
	delete [] pszBuffer;

	setlocale( LC_ALL, strCurLocale.c_str() );
}

void StringCodeConverter::unicode2mbs( const wchar_t *pcwszSource, char *pszDest )
{
	if ( pcwszSource == NULL || pszDest == NULL )
	{
		throw string( "unicode2mbs函数，参数值为NULL" );
	}

	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	size_t iCount = wcslen( pcwszSource )*2 + 1;
	memset( pszDest, 0, iCount );

	size_t iConvertedCount = wcstombs( pszDest, pcwszSource, iCount );

	if ( iConvertedCount == -1 )
	{
		throw string( "unicode2mbs转换失败，字符串中有非中英文字符！" );
	}

	setlocale( LC_ALL, strCurLocale.c_str() );
}

void StringCodeConverter::unicode2utf8( const wstring &cwstrSource, char *pszDest )
{
	if ( pszDest == NULL )
	{
		throw string( "参数为NULL" );
	}

	const wchar_t *pcwszSource = cwstrSource.c_str();

	while ( *pcwszSource != NULL )
	{
		unsigned short int iUnicode = *pcwszSource;

		if ( iUnicode < 128 )
		{
			//小于128是英文字符，不需要转换
			*pszDest = (char)iUnicode;
			pszDest++;
			pcwszSource++;
		}
		else
		{
			//大于128是mbs字符，需要转换
			const char *pcszUnicode = (const char *)pcwszSource;

			pszDest[0] = (0xE0 | ((pcszUnicode[1] & 0xF0) >> 4 ));
			pszDest[1] = (0x80 | ((pcszUnicode[1] & 0x0F) << 2)) + ((pcszUnicode[0] & 0xC0) >> 6);
			pszDest[2] = (0x80 | (pcszUnicode[0] & 0x3F));

			pszDest = pszDest + 3;
			pcwszSource++;
		}
	}

	*pszDest = NULL;//末尾的NULL字符
}

string StringCodeConverter::utf8tombs( const char *pcszSource )
{
	if ( pcszSource == NULL )
	{
		throw string( "参数为NULL" );
	}

	string strCurLocale( setlocale( LC_ALL, NULL ) );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	char *pszDest = new char[ strlen( pcszSource ) ];
	char *pszBuffer = pszDest;

	while ( *pcszSource != 0 )
	{
		if ( *pcszSource > 0 )
		{
			//是ASCII字符
			*pszDest = *pcszSource;

			pszDest++;
			pcszSource++;
		}
		else
		{
			wchar_t wUnicode = 0;
			char *pcUnicode = (char *)&wUnicode;

			pcUnicode[1] = ((pcszSource[0] & 0x0F) << 4) + ((pcszSource[1] >> 2) & 0x0F);
			pcUnicode[0] = ((pcszSource[1] & 0x03) << 6) + (pcszSource[2] & 0x3F);

			wchar_t wMcb;
			char *pcMbs = (char *)&wMcb;
			int iLen = 0;

			iLen = wctomb( pcMbs, wUnicode );

			if ( iLen == 1 )
			{
				*pszDest = *pcMbs;
			}
			else
			{
				pszDest[0] = pcMbs[0];
				pszDest[1] = pcMbs[1];
			}

			pszDest += iLen;
			pcszSource += 3;
		}
	}

	*pszDest = NULL;
	
	setlocale( LC_ALL, strCurLocale.c_str() );
	strCurLocale = pszBuffer; //废物利用

	return strCurLocale;
}

wstring StringCodeConverter::utf8tounicode( const char *pcszSource )
{
	if ( pcszSource == NULL )
	{
		throw string( "参数为NULL" );
	}

	string strCurLocale = setlocale( LC_ALL, NULL );
	setlocale( LC_ALL, "chinese-simplified" ); //改成中文环境,如果接受的参数不是中文字符串，得注意结果

	wchar_t *pwszBuffer = new wchar_t[ strlen( pcszSource ) ];
	wchar_t *pwszDest = pwszBuffer;

	while ( *pcszSource != NULL )
	{
		if ( *pcszSource > 0 )
		{
			//是ASCII字符
			wchar_t wUnicode;

			mbtowc( &wUnicode, pcszSource, 1 );

			*pwszDest = wUnicode;

			pwszDest++;
			pcszSource++;
		}
		else
		{
			//中文字符，3个字节
			wchar_t wUnicode;
			char *pcUnicode = (char *)&wUnicode;

			pcUnicode[1] = ((pcszSource[0] & 0x0F) << 4) + ((pcszSource[1] >> 2) & 0x0F);
			pcUnicode[0] = ((pcszSource[1] & 0x03) << 6) + (pcszSource[2] & 0x3F);

			*pwszDest = wUnicode;

			pwszDest++;
			pcszSource += 3;
		}
	}

	setlocale( LC_ALL, strCurLocale.c_str() );

	*pwszDest = NULL;//末尾空字符
	wstring wstrDest( pwszBuffer );

	return wstrDest;
}