Clear Vietnamese Sign C#

StringUtil.cs

public class StringUtil
{
 private static readonly string[] VietnameseSigns = new string[]
 {
  "aAeEoOuUiIdDyY",
  "áàạảãâấầậẩẫăắằặẳẵ",
  "ÁÀẠẢÃÂẤẦẬẨẪĂẮẰẶẲẴ",
  "éèẹẻẽêếềệểễ",
  "ÉÈẸẺẼÊẾỀỆỂỄ",
  "óòọỏõôốồộổỗơớờợởỡ",
  "ÓÒỌỎÕÔỐỒỘỔỖƠỚỜỢỞỠ",
  "úùụủũưứừựửữ",
  "ÚÙỤỦŨƯỨỪỰỬỮ",
  "íìịỉĩ",
  "ÍÌỊỈĨ",
  "đ",
  "Đ",
  "ýỳỵỷỹ",
  "ÝỲỴỶỸ"
 };
  
 public static string RemoveSign4VietnameseString(string str)
 {
  
  //Tiến hành thay thế , lọc bỏ dấu cho chuỗi
  for (int i = 1; i < VietnameseSigns.Length; i++)
  {
   for (int j = 0; j < VietnameseSigns[i].Length; j++)
    str = str.Replace(VietnameseSigns[i][j], VietnameseSigns[0][i - 1]);
  }
  return str;
 }
}

Xóa dấu tiếng việt dùng regex

public static partial class StringUtils
{
    public static string RemoveSign4VietnameseString(string s)
    {
        Regex regex = IsCombiningDiacriticalMarksRegex();
        string temp = s.Normalize(NormalizationForm.FormD);
        return regex.Replace(temp, string.Empty).Replace('\u0111', 'd').Replace('\u0110', 'D');
    }

    [GeneratedRegex("\\p{IsCombiningDiacriticalMarks}+")]
    private static partial Regex IsCombiningDiacriticalMarksRegex();
}

2024-04-22 Trung Nam