C#判断中文字符 收藏
方法一: 在unicode 字符串中,中文的范围是在4E00..9FFF:CJK Unified Ideographs。 通过对字符的unicode编码进行判断来确定字符是否为中文。 程序代码
view plaincopy to clipboardprint?
<PRE class=csharp name="code">protected bool IsChineseLetter(string input,int index)
{
int code = 0;
int chfrom = Convert.ToInt32("4e00", 16); //范围(0x4e00~0x9fff)转换成int(chfrom~chend)
int chend = Convert.ToInt32("9fff", 16);
if (input != "")
{
code = Char.ConvertToUtf32(input, index); //获得字符串input中指定索引index处字符unicode编码
if (code >= chfrom && code <= chend)
{
return true; //当code在中文范围内返回true
}
else
{
return false ; //当code不在中文范围内返回false
}
}
return false;
}</PRE>
view plaincopy to clipboardprint?protected bool IsChineseLetter(string input,int index) { int code = 0; int chfrom = Convert.ToInt32("4e00", 16); //范围(0x4e00~0x9fff)转换成int(chfrom~chend) int chend = Convert.ToInt32("9fff", 16); if (input != "") { code = Char.ConvertToUtf32(input, index); //获得字符串input中指定索引index处字符unicode编码 if (code >= chfrom && code <= chend) { return true; //当code在中文范围内返回true } else { return false ; //当code不在中文范围内返回false } } return false; } protected bool IsChineseLetter(string input,int index)
{
int code = 0;
int chfrom = Convert.ToInt32("4e00", 16); //范围(0x4e00~0x9fff)转换成int(chfrom~chend)
int chend = Convert.ToInt32("9fff", 16);
if (input != "")
{
code = Char.ConvertToUtf32(input, index); //获得字符串input中指定索引index处字符unicode编码
if (code >= chfrom && code <= chend)
{
return true; //当code在中文范围内返回true
}
else
{
return false ; //当code不在中文范围内返回false
}
}
return false;
}
方法二: 程序代码
view plaincopy to clipboardprint?
public bool IsChina(string CString)
{
bool BoolValue = false;
for (int i = 0; i < CString.Length; i++)
{
if (Convert.ToInt32(Convert.ToChar(CString.Substring(i, 1))) < Convert.ToInt32(Convert.ToChar(128)))
{
BoolValue = false;
}
else
{
return BoolValue = true;
}
}
return BoolValue;
}
public bool IsChina(string CString)
{
bool BoolValue = false;
for (int i = 0; i < CString.Length; i++)
{
if (Convert.ToInt32(Convert.ToChar(CString.Substring(i, 1))) < Convert.ToInt32(Convert.ToChar(128)))
{
BoolValue = false;
}
else
{
return BoolValue = true;
}
}
return BoolValue;
}
方法三: 程序代码
view plaincopy to clipboardprint?
/// <summary>
/// 判断句子中是否含有中文
/// </summary>
/// <param >字符串</param>
public bool WordsIScn(string words)
{
string TmmP;
for (int i = 0; i < words.Length; i++)
{
TmmP = words.Substring(i, 1);
byte[] sarr = System.Text.Encoding.GetEncoding("gb2312").GetBytes(TmmP);
if (sarr.Length == 2)
{
return true;
}
}
return false;
}
/// <summary>
/// 判断句子中是否含有中文
/// </summary>
/// <param >字符串</param>
public bool WordsIScn(string words)
{
string TmmP;
for (int i = 0; i < words.Length; i++)
{
TmmP = words.Substring(i, 1);
byte[] sarr = System.Text.Encoding.GetEncoding("gb2312").GetBytes(TmmP);
if (sarr.Length == 2)
{
return true;
}
}
return false;
}view plaincopy to clipboardprint?
<STRONG>方法四:</STRONG> 程序代码
方法四: 程序代码view plaincopy to clipboardprint?
<PRE class=csharp name="code">for (int i=0; i<s.length; i++)
{
Regex rx = new Regex("^[\u4e00-\u9fa5]___FCKpd___4quot;);
if (rx.IsMatch(s[i]))
// 是
else
// 否
}</PRE>
view plaincopy to clipboardprint?for (int i=0; i<s.length; i++) { Regex rx = new Regex("^[\u4e00-\u9fa5]___FCKpd___4quot;); if (rx.IsMatch(s[i])) // 是 else // 否 } for (int i=0; i<s.length; i++)
{
Regex rx = new Regex("^[\u4e00-\u9fa5]___FCKpd___4quot;);
if (rx.IsMatch(s[i]))
// 是
else
// 否
}
\u4e00-\u9fa5 汉字的范围。 ^[\u4e00-\u9fa5]$ 汉字的范围的正则
同理可以判断日文: \u0x3040-\u0x309F 是平假名, \u0x30A0-\u0x30FF 是片假名
方法五: 程序代码
view plaincopy to clipboardprint?
unicodeencoding unicodeencoding = new unicodeencoding();
byte [] unicodebytearray = unicodeencoding.getbytes( inputstring );
for( int i = 0; i < unicodebytearray.length; i++ )
{
i++;
//如果是中文字符那么高位不为0
if ( unicodebytearray[i] != 0 )
{
}
……
unicodeencoding unicodeencoding = new unicodeencoding();
byte [] unicodebytearray = unicodeencoding.getbytes( inputstring );
for( int i = 0; i < unicodebytearray.length; i++ )
{
i++;
//如果是中文字符那么高位不为0
if ( unicodebytearray[i] != 0 )
{
}
…… 方法六: 程序代码
view plaincopy to clipboardprint?
/// <summary>
/// 给定一个字符串,判断其是否只包含有汉字
/// </summary>
/// <param name="testStr"></param>
/// <returns></returns>
public bool IsOnlyContainsChinese(string testStr)
{
char[] words = testStr.ToCharArray();
foreach (char word in words)
{
if ( IsGBCode(word.ToString()) || IsGBKCode(word.ToString()) ) // it is a GB2312 or GBK chinese word
{
continue;
}
else
{
return false;
}
}
return true;
}
/// <summary>
/// 判断一个word是否为GB2312编码的汉字
/// </summary>
/// <param name="word"></param>
/// <returns></returns>
private bool IsGBCode(string word)
{
byte[] bytes = Encoding.GetEncoding("GB2312").GetBytes(word);
if (bytes.Length <= 1) // if there is only one byte, it is ASCII code or other code
{
return false;
}
else
{
byte byte1 = bytes[0];
byte byte2 = bytes[1];
if (byte1 >= 176 && byte1 <= 247 && byte2 >= 160 && byte2 <= 254) //判断是否是GB2312
{
return true;
}
else
{
return false;
}
}
}
/// <summary>
/// 判断一个word是否为GBK编码的汉字
/// </summary>
/// <param name="word"></param>
/// <returns></returns>
private bool IsGBKCode(string word)
{
byte[] bytes = Encoding.GetEncoding("GBK").GetBytes(word.ToString());
if (bytes.Length <= 1) // if there is only one byte, it is ASCII code
{
return false;
}
else
{
byte byte1 = bytes[0];
byte byte2 = bytes[1];
if ( byte1 >= 129 && byte1 <= 254 && byte2 >= 64 && byte2 <= 254) //判断是否是GBK编码
{
return true;
}
else
{
return false;
}
}
}
/// <summary>
/// 判断一个word是否为Big5编码的汉字
/// </summary>
/// <param name="word"></param>
/// <returns></returns>
private bool IsBig5Code(string word)
{
byte[] bytes = Encoding.GetEncoding("Big5").GetBytes(word.ToString());
if (bytes.Length <= 1) // if there is only one byte, it is ASCII code
{
return false;
}
else
{
byte byte1 = bytes[0];
byte byte2 = bytes[1];
if ( (byte1 >= 129 && byte1 <= 254) && ((byte2 >= 64 && byte2 <= 126) || (byte2 >= 161 && byte2 <= 254)) ) //判断是否是Big5编码
{
return true;
}
else
{
return false;
}
}
}
本文来自CSDN博客,转载请标明出处:http://blog.csdn.net/yur505/archive/2008/06/17/2557211.aspx