Methods of C to Judge Character Coding Summarize Six Methods of of

  • 2021-10-16 02:27:11
  • OfStack

This paper summarizes the method of judging character coding by C # with examples. Share it for your reference, as follows:

Method 1

In the unicode string, the Chinese range is in 4E00... 9FFF: CJK Unified Ideographs.
It is determined whether the character is Chinese or not by judging the unicode code of the character.


protected bool  IsChineseLetter(string input,int index)
{
    int code = 0;
    int chfrom = Convert.ToInt32("4e00", 16);  // Scope ( 0x4e00 ~ 0x9fff ) Convert to int ( chfrom ~ chend ) 
    int chend = Convert.ToInt32("9fff", 16);
    if (input != "")
    {
       code = Char.ConvertToUtf32(input, index);  // Get a string input The index specified in the index Place character unicode Code 
      if (code >= chfrom && code <= chend)
      {
         return true;   // When code Returns in Chinese range true
       }
      else
      {
         return false ;  // When code Returns outside the Chinese range false
       }
     }
     return false;
}

Method 2:


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;
}

Method 3:


/// <summary>
///  Judge whether the sentence contains Chinese     Ningxia University   Zhang Dong  zd4004.blog.163.com
/// </summary>
/// <param > String </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;
}

Method 4:


for (int i=0; i<s.length; i++)
{
Regex rx = new Regex("^[/u4e00-/u9fa5]$");
if (rx.IsMatch(s[i]))
//  Yes 
else
//  No 
}

Positive solution!

/u4e00-/u9fa5.
^ [/u4e00-/u9fa5] $Range regularity of Chinese characters

Method 5


unicodeencoding unicodeencoding = new unicodeencoding();
byte [] unicodebytearray = unicodeencoding.getbytes( inputstring );
for( int i = 0; i < unicodebytearray.length; i++ )
{
i++;
// If it is a Chinese character, the high order is not 0
if ( unicodebytearray[i] != 0 )
{
}
 ... 

Method 6


/// <summary>
///  Given 1 The character string is used to judge whether it only contains Chinese characters 
/// </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>
///  Judge 1 A word Whether it is GB2312 Coded Chinese characters 
/// </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)  // Determine whether it is GB2312
    {
      return true;
    }
    else
    {
      return false;
    }
  }
}
/// <summary>
///  Judge 1 A word Whether it is GBK Coded Chinese characters 
/// </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)   // Determine whether it is GBK Code 
    {
      return true;
    }
    else
    {
      return false;
    }
  }
}
/// <summary>
///  Judge 1 A word Whether it is Big5 Coded Chinese characters 
/// </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)) )   // Determine whether it is Big5 Code 
    {
      return true;
    }
    else
    {
      return false;
    }
  }
}

For more readers interested in C # related content, please check the topics on this site: "Summary of XML File Operation Skills in C #", "C # Common Control Usage Tutorial", "WinForm Control Usage Summary", "C # Data Structure and Algorithm Tutorial", "C # Object-Oriented Programming Introduction Tutorial" and "C # Programming Thread Use Skills Summary"

I hope this article is helpful to everyone's C # programming.


Related articles: