怎么判断char数组里是不是汉字？

是的，负数是为汉字，二个字节一个
整个汉字的ASCII码是有一定范围的，楼主去搜搜

gb2312 两个字节都是负的
如果是gbk，第一个字节还是负的，第二字节就不一定了

“我是想数组里有汉字有字母有数字，怎么分别提取出来？汉字有什么判断方法？”
以宽字符形式存存储
然后一个个取出来，左移七位看是不是0，使得话，不是汉字，否则是汉字
wchar_t arr[10] = L"中国woaini";
int i;i=0;
while(arr[i])
{
    if(arr[i]>>7)
        printf("YES\n");
    else
        printf("NO\n");
    i++;
}
另外，不知哪位高人可以指教下，如何打印宽字符？比如一个个汉字打印？搞了半天愣是没弄出来

参考一下下面的函数：
void GetCEFont( CString Text )   //可以把CString看成是char[]
{
int len=Text.GetLength();
TCHAR chTmp; for(int i = 0 ; i < len;)
{
chTmp = Text.GetAt(i); //去一个字节
if ( chTmp < 0 )   //为汉字
{
i++;
i++;

}else{            //为英文

             i++;
}
}
}

isleadbyte()当测试字符是多字节 “字符” 的首字节是返回非零值可以用这个方法判读是不是汉字

1 LZ如果只想知道如何存储字母,汉字,数字,可以直接存储为多字节可以存储在wchar_t数组中,不管字母,数字还是汉字都是两个字节表示.所以不会出现什么问题.判断起来也比较容易.
2 如果本着研究学习的角度,必须存储在char数组中........
两字节内码：区号+0xA0   ,   位号+0xa0
  如：第一个汉字“啊”的内码为     0xb0,0xa1

  GBK范围：
  1st   byte         2nd   byte
  0x81~0xfe       0x40~0x7e   and   0x80~0xfe

  BIG5范围：
  1st   byte         2nd   byte
  0x81~0xfe       0x40~0x7e   and   0xa1~0xfe

当第一个字符范围为：(ch>=0x81 && ch<=0XFE)
第二个字符范围为：(ch>=0X40 && ch<=0XFE && ch!=0X7F)
表示中文。封装了一个类你可以参考一下：
头文件：#pragma oncestruct WIDECHAR
{
union
{
unsigned char szChar[4];
char szText[4];
}; WIDECHAR();
__forceinline BOOL IsNULL() const;
__forceinline BOOL IsWide() const;
__forceinline void Confirm();
    operator UINT() const;
};class CEditorText : public CString
{
public:
CEditorText(void);
virtual ~CEditorText(void);
public:
CEditorText & operator=(LPCTSTR szText);public:
BOOL GetChar(int index, WIDECHAR & ch) const; BOOL MoveNextChar(int & index) const;
BOOL MovePrevChar(int & index) const; BOOL MoveNextWord(int & index) const;
BOOL MovePrevWord(int & index) const; void WordBegin(int & index) const;
void WordEnd(int & index) const;
};#define CHARCLASS1(ch) ((ch>='0' && ch<='9') || (ch>='A' && ch<='Z') || (ch>='a' && ch<='z') || ch=='_' || ch=='$' || ch=='#')
#define CHARCLASS2(ch) (ch==' ' || ch=='\t' || ch=='\r' || ch=='\n')
#define CHARCLASS3(ch) (ch>=1  && ch<=6)
#define CHARCLASS4(ch) ((ch>=7  && ch<=31) || ch=='@')
#define CHARCLASS5(ch) (!CHARCLASS1(ch) && !CHARCLASS2(ch) && !CHARCLASS3(ch) && !CHARCLASS4(ch))#define ISSPLITCHAR(ch) (ch==' ' || ch=='\t' || ch=='\r' || ch=='\n')
#define ISEMPTYCHAR(ch) ((ch>=0&&ch<=32)||ch==127)#define ISWIDECHARFIRST(ch) (ch>=0x81 && ch<=0XFE)
#define ISWIDECHARNEXT(ch)  (ch>=0X40 && ch<=0XFE && ch!=0X7F)#define CONFIRMWIDECHAR(ch) \
if (ISWIDECHARFIRST(ch.szChar[0])) \
{ \
if (!ISWIDECHARNEXT(ch.szChar[1])) \
{ \
ch.szChar[0] ='?';  \
ch.szChar[1] =  0;  \
} \
} else  \
{ \
ch.szChar[1] = 0; \
if (ch.szChar[0]==0X80 || ch.szChar[0]==0X7F || ch.szChar[0]==0XFF) \
ch.szChar[0]='?'; \
} \
实现文件：
BOOL IsCharSameClass(char ch1, char ch2)
{
if (CHARCLASS1(ch1) && CHARCLASS1(ch2))
return TRUE;
else if (CHARCLASS2(ch1) && CHARCLASS2(ch2))
return TRUE;
else if (CHARCLASS3(ch1) && CHARCLASS3(ch2))
return TRUE;
else if (CHARCLASS4(ch1) && CHARCLASS4(ch2))
return TRUE;
else if (CHARCLASS5(ch1) && CHARCLASS5(ch2))
return TRUE; return FALSE;
}BOOL IsCharSameWord(unsigned char ch1,unsigned char ch2)
{
if ((ch1>='0' && ch1<='9')
&& (ch1>='0' && ch2<='9'))
return TRUE;
if (((ch1>='A' && ch1<='Z') || (ch1>='a' && ch1<='z'))
&&((ch2>='A' && ch2<='Z') || (ch2>='a' && ch2<='z')))
return TRUE;
return FALSE;
}
WIDECHAR::WIDECHAR()
{
szChar[0]= 0;
szChar[1]= 0;
szChar[2]= 0;
szChar[3]= 0;
}BOOL WIDECHAR::IsNULL() const
{
return (szChar[0]==0);
}BOOL WIDECHAR::IsWide() const
{
return (szChar[1]);
}void WIDECHAR::Confirm()
{
CONFIRMWIDECHAR((*this));
}WIDECHAR::operator UINT() const
{
    union {
        UINT nChar;
        unsigned char szChar[4];
    } a;    if (szChar[1]==0)
        a.nChar = szChar[0];
    else
    {
        a.nChar = 0;
        a.szChar[1] = szChar[0];
        a.szChar[0] = szChar[1];
    }    return a.nChar;
}CEditorText::CEditorText(void)
{
}CEditorText::~CEditorText(void)
{
}BOOL CEditorText::GetChar(int index, WIDECHAR & ch) const
{
if (index>=GetLength() || index<0) return FALSE; ch.szChar[0] = (*this)[index];
ch.szChar[1] = 0; if (index<GetLength()-1)
ch.szChar[1] = (*this)[index+1]; ch.Confirm(); return TRUE;
}BOOL CEditorText::MoveNextChar(int & index) const
{
if (index>=GetLength() || index<0) return FALSE;
WIDECHAR ch; ch.szChar[0] = (*this)[index];
ch.szChar[1] = 0; if (index<GetLength()-1)
ch.szChar[1] = (*this)[index+1]; CONFIRMWIDECHAR(ch); index++;
if (ch.IsWide()) index++; return TRUE;
}BOOL CEditorText::MovePrevChar(int & index) const
{
if (index>GetLength() || index<=0)
return FALSE; if (index==1)
{
index = 0;
return TRUE;
} unsigned char * pStart=(unsigned char *)((LPCTSTR)(*this));
unsigned char * ptr=pStart+index-1; if (!ISWIDECHARNEXT(*ptr))
{
index--; return TRUE;
} ptr--;
while (ISWIDECHARFIRST(*ptr) && ISWIDECHARNEXT(*ptr))
{
if (ptr==pStart) break;
ptr --;
} if (ISWIDECHARFIRST(*ptr))
{
if ((index+pStart-ptr)%2==0)
{
index-=2;
return TRUE;
} index--;
return TRUE;
} if ((index+pStart-ptr)%2==0)
{
index--;
return TRUE;
} index-=2;
return TRUE;
}BOOL CEditorText::MoveNextWord(int & index) const
{
if (index>=GetLength() || index<0) return FALSE; WIDECHAR ch;
LPCTSTR szText = (*this);
int textLen = GetLength(); ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1])
{
index+=2;
return TRUE;
} unsigned char chBase = ch.szChar[0]; index++; while (index<textLen)
{
ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) break;
if (!IsCharSameWord(ch.szChar[0],chBase))
break;
index++;
} return TRUE;
}
BOOL CEditorText::MovePrevWord(int & index) const
{
if (index>GetLength() || index<=0) return FALSE; WIDECHAR ch;
LPCTSTR szText = (*this); MovePrevChar(index); ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) return TRUE; unsigned char chBase = ch.szChar[0];
int temp = index; while (MovePrevChar(temp))
{
ch.szChar[0] = szText[temp];
ch.szChar[1] = szText[temp+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) break; if (!IsCharSameWord(ch.szChar[0],chBase))
break; index = temp;
} return TRUE;
}void CEditorText::WordBegin(int & index) const
{
if (index>GetLength() || index<=0) return; WIDECHAR ch;
LPCTSTR szText = (*this); ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) return; unsigned char chBase = ch.szChar[0];
int temp = index; while (MovePrevChar(temp))
{
ch.szChar[0] = szText[temp];
ch.szChar[1] = szText[temp+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) break; if (!IsCharSameWord(ch.szChar[0],chBase))
break; index = temp;
}
}void CEditorText::WordEnd(int & index) const
{
if (index>=GetLength() || index<0) return; WIDECHAR ch;
LPCTSTR szText = (*this);
int textLen = GetLength(); ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1])
{
index+=2;
return;
} unsigned char chBase = ch.szChar[0]; index++; while (index<textLen)
{
ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1];
CONFIRMWIDECHAR(ch); if (ch.szChar[1]) break;
if (!IsCharSameWord(ch.szChar[0],chBase))
break;
index++;
}
}CEditorText & CEditorText::operator=(LPCTSTR szText)
{
int len = (int)strlen(szText);
CString strText; WIDECHAR ch;
int index = 0; strText = "";
while (index<len)
{
ch.szChar[0] = szText[index];
ch.szChar[1] = szText[index+1]; CONFIRMWIDECHAR(ch); if (ch.szChar[0]!='\r')
strText += ch.szText; index++;if (ch.szChar[1]) index++;
} CString::operator =(strText); return (*this);
}

调试易

怎么判断char数组里是不是汉字？

解决方案 »