我没有使用过这种方法，但是Michael Kaplan在他的博客文章(有一个令人困惑的标题)中描述了一种方法，谈论剥离变音符:剥离是一项有趣的工作(又名剥离) 论无意义的意义，即一切 Mn字符是非空格的，但是 有些更非间距比 其他人)

static string RemoveDiacritics(string text) 
{
    var normalizedString = text.Normalize(NormalizationForm.FormD);
    var stringBuilder = new StringBuilder(capacity: normalizedString.Length);

    for (int i = 0; i < normalizedString.Length; i++)
    {
        char c = normalizedString[i];
        var unicodeCategory = CharUnicodeInfo.GetUnicodeCategory(c);
        if (unicodeCategory != UnicodeCategory.NonSpacingMark)
        {
            stringBuilder.Append(c);
        }
    }

    return stringBuilder
        .ToString()
        .Normalize(NormalizationForm.FormC);
}

请注意，这是他之前帖子的后续:剥离变音符....

该方法使用String。Normalize将输入字符串分割为组成符号(基本上是将“基本”字符与变音符符分开)，然后扫描结果并仅保留基本字符。这只是有点复杂，但实际上你看到的是一个复杂的问题。

当然，如果你限制自己使用法语，你可能会使用@David Dibben推荐的如何在c++ std::string中删除重音和波浪号的简单基于表的方法。

这是VB版本(工作与希腊):

导入系统。文本

导入系统。全球化

Public Function RemoveDiacritics(ByVal s As String)
    Dim normalizedString As String
    Dim stringBuilder As New StringBuilder
    normalizedString = s.Normalize(NormalizationForm.FormD)
    Dim i As Integer
    Dim c As Char
    For i = 0 To normalizedString.Length - 1
        c = normalizedString(i)
        If CharUnicodeInfo.GetUnicodeCategory(c) <> UnicodeCategory.NonSpacingMark Then
            stringBuilder.Append(c)
        End If
    Next
    Return stringBuilder.ToString()
End Function

我需要一些东西，转换所有主要的unicode字符和投票的答案留下了一些，所以我已经创建了一个CodeIgniter的convert_accented_characters($str)的版本为c#，很容易自定义:

using System;
using System.Text;
using System.Collections.Generic;

public static class Strings
{
    static Dictionary<string, string> foreign_characters = new Dictionary<string, string>
    {
        { "äæǽ", "ae" },
        { "öœ", "oe" },
        { "ü", "ue" },
        { "Ä", "Ae" },
        { "Ü", "Ue" },
        { "Ö", "Oe" },
        { "ÀÁÂÃÄÅǺĀĂĄǍΑΆẢẠẦẪẨẬẰẮẴẲẶА", "A" },
        { "àáâãåǻāăąǎªαάảạầấẫẩậằắẵẳặа", "a" },
        { "Б", "B" },
        { "б", "b" },
        { "ÇĆĈĊČ", "C" },
        { "çćĉċč", "c" },
        { "Д", "D" },
        { "д", "d" },
        { "ÐĎĐΔ", "Dj" },
        { "ðďđδ", "dj" },
        { "ÈÉÊËĒĔĖĘĚΕΈẼẺẸỀẾỄỂỆЕЭ", "E" },
        { "èéêëēĕėęěέεẽẻẹềếễểệеэ", "e" },
        { "Ф", "F" },
        { "ф", "f" },
        { "ĜĞĠĢΓГҐ", "G" },
        { "ĝğġģγгґ", "g" },
        { "ĤĦ", "H" },
        { "ĥħ", "h" },
        { "ÌÍÎÏĨĪĬǏĮİΗΉΊΙΪỈỊИЫ", "I" },
        { "ìíîïĩīĭǐįıηήίιϊỉịиыї", "i" },
        { "Ĵ", "J" },
        { "ĵ", "j" },
        { "ĶΚК", "K" },
        { "ķκк", "k" },
        { "ĹĻĽĿŁΛЛ", "L" },
        { "ĺļľŀłλл", "l" },
        { "М", "M" },
        { "м", "m" },
        { "ÑŃŅŇΝН", "N" },
        { "ñńņňʼnνн", "n" },
        { "ÒÓÔÕŌŎǑŐƠØǾΟΌΩΏỎỌỒỐỖỔỘỜỚỠỞỢО", "O" },
        { "òóôõōŏǒőơøǿºοόωώỏọồốỗổộờớỡởợо", "o" },
        { "П", "P" },
        { "п", "p" },
        { "ŔŖŘΡР", "R" },
        { "ŕŗřρр", "r" },
        { "ŚŜŞȘŠΣС", "S" },
        { "śŝşșšſσςс", "s" },
        { "ȚŢŤŦτТ", "T" },
        { "țţťŧт", "t" },
        { "ÙÚÛŨŪŬŮŰŲƯǓǕǗǙǛŨỦỤỪỨỮỬỰУ", "U" },
        { "ùúûũūŭůűųưǔǖǘǚǜυύϋủụừứữửựу", "u" },
        { "ÝŸŶΥΎΫỲỸỶỴЙ", "Y" },
        { "ýÿŷỳỹỷỵй", "y" },
        { "В", "V" },
        { "в", "v" },
        { "Ŵ", "W" },
        { "ŵ", "w" },
        { "ŹŻŽΖЗ", "Z" },
        { "źżžζз", "z" },
        { "ÆǼ", "AE" },
        { "ß", "ss" },
        { "IJ", "IJ" },
        { "ij", "ij" },
        { "Œ", "OE" },
        { "ƒ", "f" },
        { "ξ", "ks" },
        { "π", "p" },
        { "β", "v" },
        { "μ", "m" },
        { "ψ", "ps" },
        { "Ё", "Yo" },
        { "ё", "yo" },
        { "Є", "Ye" },
        { "є", "ye" },
        { "Ї", "Yi" },
        { "Ж", "Zh" },
        { "ж", "zh" },
        { "Х", "Kh" },
        { "х", "kh" },
        { "Ц", "Ts" },
        { "ц", "ts" },
        { "Ч", "Ch" },
        { "ч", "ch" },
        { "Ш", "Sh" },
        { "ш", "sh" },
        { "Щ", "Shch" },
        { "щ", "shch" },
        { "ЪъЬь", "" },
        { "Ю", "Yu" },
        { "ю", "yu" },
        { "Я", "Ya" },
        { "я", "ya" },
    };

    public static char RemoveDiacritics(this char c){
        foreach(KeyValuePair<string, string> entry in foreign_characters)
        {
            if(entry.Key.IndexOf (c) != -1)
            {
                return entry.Value[0];
            }
        }
        return c;
    }

    public static string RemoveDiacritics(this string s) 
    {
        //StringBuilder sb = new StringBuilder ();
        string text = "";


        foreach (char c in s)
        {
            int len = text.Length;

            foreach(KeyValuePair<string, string> entry in foreign_characters)
            {
                if(entry.Key.IndexOf (c) != -1)
                {
                    text += entry.Value;
                    break;
                }
            }

            if (len == text.Length) {
                text += c;  
            }
        }
        return text;
    }
}

使用

// for strings
"crème brûlée".RemoveDiacritics (); // creme brulee

// for chars
"Ã"[0].RemoveDiacritics (); // A

如果有人感兴趣，我正在寻找类似的东西，最后写了如下:

public static string NormalizeStringForUrl(string name)
{
    String normalizedString = name.Normalize(NormalizationForm.FormD);
    StringBuilder stringBuilder = new StringBuilder();

    foreach (char c in normalizedString)
    {
        switch (CharUnicodeInfo.GetUnicodeCategory(c))
        {
            case UnicodeCategory.LowercaseLetter:
            case UnicodeCategory.UppercaseLetter:
            case UnicodeCategory.DecimalDigitNumber:
                stringBuilder.Append(c);
                break;
            case UnicodeCategory.SpaceSeparator:
            case UnicodeCategory.ConnectorPunctuation:
            case UnicodeCategory.DashPunctuation:
                stringBuilder.Append('_');
                break;
        }
    }
    string result = stringBuilder.ToString();
    return String.Join("_", result.Split(new char[] { '_' }
        , StringSplitOptions.RemoveEmptyEntries)); // remove duplicate underscores
}

与接受的答案相同，但更快，使用Span而不是StringBuilder。 需要。net Core 3.1或更新的。net。

static string RemoveDiacritics(string text) 
{
    ReadOnlySpan<char> normalizedString = text.Normalize(NormalizationForm.FormD);
    int i = 0;
    Span<char> span = text.Length < 1000
        ? stackalloc char[text.Length]
        : new char[text.Length];

    foreach (char c in normalizedString)
    {
        if (CharUnicodeInfo.GetUnicodeCategory(c) != UnicodeCategory.NonSpacingMark)
            span[i++] = c;
    }

    return new string(span).Normalize(NormalizationForm.FormC);
}

此外，这是可扩展的额外字符替换，如抛光Ł。

span[i++] = c switch
{
    'Ł' => 'L',
    'ł' => 'l',
    _ => c
};

一个小提示:堆栈分配stackalloc比堆分配new要快得多，它为垃圾收集器减少了工作。1000是一个阈值，以避免在堆栈上分配大结构，这可能会导致StackOverflowException。虽然1000是一个相当安全的值，但在大多数情况下10000甚至100000也可以(100k在堆栈上分配最多200kB，而默认堆栈大小为1mb)。然而10万对我来说有点危险。

你可以从MMLib中使用字符串扩展。扩展nuget包:

using MMLib.RapidPrototyping.Generators;
public void ExtensionsExample()
{
  string target = "aácčeéií";
  Assert.AreEqual("aacceeii", target.RemoveDiacritics());
} 

Nuget页面:https://www.nuget.org/packages/MMLib.Extensions/ Codeplex项目网站https://mmlib.codeplex.com/