C++ 汉字UTF-8字符串处理类库

// mString.h: interface for the mString class. // ////////////////////////////////////////////////////////////////////// #if !defined(AFX_MSTRING_H__F225839C_CEFD_4B3E_9501_CA06A4591700__INCLUDED_) #define AFX_MSTRING_H__F225839C_CEFD_4B3E_9501_CA06A4591700__INCLUDED_ #if _MSC_VER > 1000 #pragma once #endif // _MSC_VER > 1000 ////定义 //// CHAR signed char ,作为WINDOWS,ANSI,MBCS字符集使用 ////UCHAR unsigned char,作为UTF-8字符集使用 ////WCHAR ( wide ) unsigned char ,作为UNICODE UCS-2字符集 ////ULONG unsigned long, ,作为UNICODE UCS-4字符集,Quad Char = QCHAR,Octad Char typedef char CHAR; ////__int8, asc,oem,mbcs,dbcs typedef unsigned char UCHAR; ////unsigned __int8, utf-8, typedef wchar_t WCHAR; ////unsigned __int16, ucs-2,unsigned short,wide char typedef unsigned long QCHAR; ////unsigned __int32, ucs-4,quad char typedef unsigned __int64 OCHAR; ////unsigned __int64, ucs-8,octad char typedef long double QFLOAT; ////float4,非标准扩展long float #define FIND_ERROR -1 namespace UCS { class utf8_ucs2_t; class utf8_ucs4_t; #ifdef UCS_4 typedef utf8_ucs4_t utf8_t; #else ////use for define UCS-2 or _UNICODE typedef utf8_ucs2_t utf8_t; #endif class utfCount ////UTF字符数量统计表 { long Byte[7]; ////Byte[0] = Error.其它分别代表UTF中1-6字节字符统计数 public: utfCount( void ); //// utfCount( const QCHAR *pString ); ////ucs-4 utfCount( const WCHAR *pString ); ////ucs-2 utfCount( const UCHAR *pString ); ////utf-8 //////////////////////////////////////////////// long Count( const QCHAR *pString ); ////统计UTF字节数量,DWORD,ucs-4 long Count( const WCHAR *pString ); ////统计UTF字节数量,WCHAR,ucs-2 long Count( const UCHAR *pString ); ////统计UTF字节数量,UCHAR,utf-8 bool Legal(const UCHAR *pString); ////错误检测 //////////////////////////////////////////////// long GetSortSize( int Index ) const; ////分类读取数量，Index = 单词字节数，0=出错数量 long GetByteSize( void ) const; ////读取字节数 long GetCharSize( void ) const; ////读取字符数 private: void Reset( void ); }; class utf8_ucs2_t {////UTF8字符 与 UNICODE字符之间字符转换基类 public: bool Status; public: //////////////////////////////////////////////////////////// int UtfToUcs( WCHAR &Word, const UCHAR *putf ); ////UTF-8到Ucs-2转换 int UcsToUtf( UCHAR *pUtf,WCHAR Word ); ////Ucs-2到UTF-8转换 //////////////////////////////////////////////////////////// int Skip( const UCHAR * pString ) const; ////UTF移动指针 utf8_ucs2_t(void); virtual ~utf8_ucs2_t(); private: bool Weave( WCHAR &UniChar,UCHAR tmpByte ); ////ucs-2字符拼装 UCHAR Split( WCHAR &UniChar ); ////ucs-2字符拆分 }; class utf8_ucs4_t {////UTF8字符 与 UNICODE字符之间字符转换基类 public: bool Status; public: int UcsToUtf( UCHAR *pUtf,ULONG Ucs4 ); ////ucs-4到utf int UtfToUcs( QCHAR &Ucs4,const UCHAR *putf ); ////utf-8到ucs-4 //////////////////////////////////////////////////////////// int Skip(const UCHAR * pUtfString ) const; ////UTF移动指针 utf8_ucs4_t(void); virtual ~utf8_ucs4_t(); private: int PickLead( BYTE &Head ); ////首字符吸取,返回单词总长 UCHAR MakeLead( BYTE Ucs,int nCount ); ////首字节合成 int Weave( QCHAR &Ucs4,const UCHAR *pUtf ); ////ucs-4字符拼装 void Split( UCHAR *pUtf,int Count,QCHAR Ucs4 ); ////ucs-4字符拆分 }; class utfString : protected Memory { ////仅用于UCS-2 与 UTF-8之间的转换(UNICODE)，不再支持ASC字符，即CHAR类字符 ULONG ByteCount; ////字节数量,不是空间大小!! public: utfString Copy( ULONG nIndex,ULONG nCount ); ////部分复制对象 utfString Cut( ULONG nIndex,ULONG nCount ); ////部分剪切对象 long Paste( ULONG nIndex, const UCHAR *pString ); ////定位粘贴字串 long Delete( ULONG nIndex,ULONG nCount ); ////定位删除字串 //////////////////////////////////////////////////////// long Replace( const UCHAR *pOld,const UCHAR *pNew ); ////对象字串体会，返回替换数量 long Filter( const UCHAR *pString ); ////字串过滤删除，返回过滤数量 ULONG FindRight( ULONG nIndex, const UCHAR *pString ) const; ////右侧定位搜索 ULONG FindLeft( ULONG nIndex,const UCHAR *pString ) const; ////左侧定位搜索 //////////////////////////////////////////////////////// // int Trim( UCHAR *pString ); int TrimLeft( void ); ////左侧空格过滤 int TrimRight( void ); ////右侧空格过滤 //////////////////////////////////////////////////////// UCHAR & operator [](ULONG nIndex); ////不能变更数据长度 const UCHAR * operator *(void) const; ////不能变更数据长度 //////////////////////////////////////////////////////// utfString operator +(const WCHAR *pString); ////class + Unicode utfString operator +(const UCHAR *pString); ////class + utf-8 utfString operator +(const utfString &Object); ////class + class //////////////////////////////////////////////////////// utfString & operator +=(const WCHAR *pString); utfString & operator +=(const UCHAR *pString); utfString & operator +=(const utfString &Object); //////////////////////////////////////////////////////// utfString & operator =(const WCHAR *pString); utfString & operator =(const UCHAR *pString); utfString & operator =(const utfString &Object); //////////////////////////////////////////////////////// UCHAR * SetSize( ULONG tmpSize ); ////设置空间大小，单位字节 long GetSize( void ) const; ////计算空间大小，单位字节 long GetCount( void ) const; ////计算字符数量，字符总数 //////////////////////////////////////////////////////// void Empty( void ); /////清空 bool Legal( void ) const; ////UTF完整性检查 int Correct( const UCHAR *pString ) const; ////修正指针位置 long Skip( const UCHAR *pString ,long nCount ) const; ////字符移动±nCount有效字符，返回字节数量 //////////////////////////////////////////////////////// utfString( const UCHAR *pString ); ////UTF,UTF-8,unsigned char,BYTE utfString( const WCHAR *pString ); ////UCS,UNICODE,unsigned short,WORD utfString( const utfString &Object ); utfString( ULONG tmpSize ); utfString( void ); virtual ~utfString(); private: UCHAR * GetAddress( void ) const; ////外部函数用 * 操作,const utfString Extract( ULONG nIndex,ULONG nCount,bool Mode ); ////抽取,Mode = false 保留源，=true删除源 int Append(const WCHAR *pString); ////ucs,UNICODE int Append(const UCHAR *pString); ////mbs,utf8 }; class ascString : protected Memory { ULONG StrSize; /////内部字节大小 public: //////////////////////////////////////////////////////// int TrimLeft( void ); ////左侧空格过滤 int TrimRight( void ); ////右侧空格过滤 //////////////////////////////////////////////////////// //////////////////////////////////////////////////////// // int Remove( WCHAR Word ); ////用Filter代替(Erase) long Filter( CHAR Word ); long Filter( const CHAR *pString ); int Replace( const CHAR *pOld,const CHAR *pNew ); ULONG Find( ULONG nIndex, CHAR Word ) const; ULONG FindRight( ULONG nIndex, const CHAR *pString ) const; ////nIndex 为正向序号 ULONG FindLeft( ULONG nIndex, const CHAR *pString ) const; ////nIndex 为正向序号 //////////////////////////////////////////////////////// int Delete( ULONG nIndex,ULONG nCount ); int Paste( ULONG nIndex,const CHAR *pSource ); ascString Cut( ULONG nIndex, ULONG nCount ); ascString Copy( ULONG nIndex,ULONG nCount ); //////////////////////////////////////////////// const char * operator *(void) const; ////数组操作,UNCODE i*2 char & operator [](ULONG Index); ////数组操作,Uncode i*2 //////////////////////////////////////////////// ascString operator +(const CHAR *pString); ////ASC ascString operator +(const WCHAR *pString); ////UCS ascString