C# 判斷字符編碼的六種方法

方法一
http://blog.csdn.net/qiujiahao/archive/2007/08/09/1733169.aspx
unicode 字符串中,中文的範圍是在4E00..9FFF:CJK Unified Ideographshtml

經過對字符的unicode編碼進行判斷來肯定字符是否爲中文。編碼


 protected bool   IsChineseLetter(string input,int index)
    {.net

        int code = 0;
        int chfrom = Convert.ToInt32("4e00", 16);    //範圍(0x4e000x9fff)轉換成intchfromchend
        int chend = Convert.ToInt32("9fff", 16);
        if (input != "")
        {
             code = Char.ConvertToUtf32(input, index);    //得到字符串input中指定索引index處字符unicode編碼
            
           if (code >= chfrom && code <= chend)     
            {
                 return true;     //code在中文範圍內返回true

             }
            else
            {
                  return false ;    //code不在中文範圍內返回false
             }
         }code

          return false;
 }

方法二:
http://hi.baidu.com/yhfd/blog/item/3222e1fca22cfb80b901a027.html
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:htm

        /// <summary>
        /// 
判斷句子中是否含有中文     寧夏大學 張冬 zd4004.blog.163.com
        /// </summary>
        /// <param >
字符串</param> 
        public bool WordsIScn(string words)
        {
            string TmmP;
blog

            for (int i = 0; i < words.Length; i++)
            {
                TmmP = words.Substring(i, 1);
索引

                byte[] sarr = System.Text.Encoding.GetEncoding("gb2312").GetBytes(TmmP);unicode

                if (sarr.Length == 2)
                {
                    return true;
                }
            }
            return false;
        }
字符串



方法四:
for (int i=0; i<s.length; i++)
{
Regex rx = new Regex("^[/u4e00-/u9fa5]$");
if (rx.IsMatch(s[i]))
// 

else
// 

}
正解!
/u4e00-/u9fa5 
漢字的範圍。
^[/u4e00-/u9fa5]$ 
漢字的範圍的正則

方法五
unicodeencoding unicodeencoding = new unicodeencoding(); 
byte [] unicodebytearray = unicodeencoding.getbytes( inputstring ); 
for( int i = 0; i < unicodebytearray.length; i++ ) 

i++; 
//
若是是中文字符那麼高位不爲
if ( unicodebytearray[i] != 0 ) 


……   

方法六
    /// <summary>
        /// 
給定一個字符串,判斷其是否只包含有漢字
        /// </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;
        }
get

        /// <summary>
        /// 
判斷一個word是否爲GB2312編碼的漢字
        /// </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)    //
判斷是不是GB2312
                {
                    return true;
                }
                else
                {
                    return false;
                }
            }
        }

        /// <summary>
        /// 
判斷一個word是否爲GBK編碼的漢字
        /// </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)     //
判斷是不是GBK編碼
                {
                    return true;
                }
                else
                {
                    return false;
                }
            }
        }

        /// <summary>
        /// 
判斷一個word是否爲Big5編碼的漢字
        /// </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)) )     //
判斷是不是Big5編碼                {                    return true;                }                else                {                    return false;                }            }        }

相關文章
相關標籤/搜索