我试图转换一些字符串,在法国加拿大,基本上,我想能够拿出法国重音标记在字母,同时保持字母。(例如,将é转换为e,那么crème brûlée就会变成creme brulee)
实现这一目标的最佳方法是什么?
我试图转换一些字符串,在法国加拿大,基本上,我想能够拿出法国重音标记在字母,同时保持字母。(例如,将é转换为e,那么crème brûlée就会变成creme brulee)
实现这一目标的最佳方法是什么?
当前回答
我真的很喜欢azrafe7提供的简洁实用的代码。 所以,我稍微改变了一下,把它转换成一个扩展方法:
public static class StringExtensions
{
public static string RemoveDiacritics(this string text)
{
const string SINGLEBYTE_LATIN_ASCII_ENCODING = "ISO-8859-8";
if (string.IsNullOrEmpty(text))
{
return string.Empty;
}
return Encoding.ASCII.GetString(
Encoding.GetEncoding(SINGLEBYTE_LATIN_ASCII_ENCODING).GetBytes(text));
}
}
其他回答
有趣的是,这样的问题可以得到这么多答案,但没有一个符合我的要求:)周围有这么多语言,一个完全语言不可知的解决方案是不可能的,因为其他人已经提到FormC或FormD正在给出问题。
由于最初的问题与法语有关,最简单的答案确实是
public static string ConvertWesternEuropeanToASCII(this string str)
{
return Encoding.ASCII.GetString(Encoding.GetEncoding(1251).GetBytes(str));
}
1251应该被输入语言的编码代码所取代。
但是,这只能用一个字符替换一个字符。由于我也使用德语作为输入,所以我进行了手动转换
public static string LatinizeGermanCharacters(this string str)
{
StringBuilder sb = new StringBuilder(str.Length);
foreach (char c in str)
{
switch (c)
{
case 'ä':
sb.Append("ae");
break;
case 'ö':
sb.Append("oe");
break;
case 'ü':
sb.Append("ue");
break;
case 'Ä':
sb.Append("Ae");
break;
case 'Ö':
sb.Append("Oe");
break;
case 'Ü':
sb.Append("Ue");
break;
case 'ß':
sb.Append("ss");
break;
default:
sb.Append(c);
break;
}
}
return sb.ToString();
}
它可能不能提供最好的性能,但至少它非常易于阅读和扩展。 Regex是一个不去,比任何字符/字符串的东西慢得多。
我还有一个非常简单的方法来删除空间:
public static string RemoveSpace(this string str)
{
return str.Replace(" ", string.Empty);
}
最终,我使用以上3个扩展的组合:
public static string LatinizeAndConvertToASCII(this string str, bool keepSpace = false)
{
str = str.LatinizeGermanCharacters().ConvertWesternEuropeanToASCII();
return keepSpace ? str : str.RemoveSpace();
}
并对其进行了一个小单元测试(不详尽),以成功通过。
[TestMethod()]
public void LatinizeAndConvertToASCIITest()
{
string europeanStr = "Bonjour ça va? C'est l'été! Ich möchte ä Ä á à â ê é è ë Ë É ï Ï î í ì ó ò ô ö Ö Ü ü ù ú û Û ý Ý ç Ç ñ Ñ";
string expected = "Bonjourcava?C'estl'ete!IchmoechteaeAeaaaeeeeEEiIiiiooooeOeUeueuuuUyYcCnN";
string actual = europeanStr.LatinizeAndConvertToASCII();
Assert.AreEqual(expected, actual);
}
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
在这里弹出这个库,如果您还没有考虑过的话。看起来有一个完整的单元测试。
https://github.com/thomasgalliker/Diacritics.NET
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
}
没有足够的声誉,显然我不能评论亚历山大的优秀链接。Lucene似乎是唯一的解决方案在合理的通用情况下工作。
对于那些想要一个简单的复制粘贴解决方案的人,这里是利用Lucene中的代码:
字符串试验台= " AAAACEIIOOØUUÞaaaaaaæceeeeiiiið人参公鸡øUUāăčĐęğıŁłńŌōřŞşšźžșțệủ”;
Console.WriteLine (Lucene.latinizeLucene(实验);
AAAACEIIOOOUUTHaaaaaaaeceeeeiiiidnoooouuaacDegiLlnOorSsszzsteu
//////////
public static class Lucene
{
// source: https://raw.githubusercontent.com/apache/lucenenet/master/src/Lucene.Net.Analysis.Common/Analysis/Miscellaneous/ASCIIFoldingFilter.cs
// idea: https://stackoverflow.com/questions/249087/how-do-i-remove-diacritics-accents-from-a-string-in-net (scroll down, search for lucene by Alexander)
public static string latinizeLucene(string arg)
{
char[] argChar = arg.ToCharArray();
// latinizeLuceneImpl can expand one char up to four chars - e.g. Þ to TH, or æ to ae, or in fact ⑽ to (10)
char[] resultChar = new String(' ', arg.Length * 4).ToCharArray();
int outputPos = Lucene.latinizeLuceneImpl(argChar, 0, ref resultChar, 0, arg.Length);
string ret = new string(resultChar);
ret = ret.Substring(0, outputPos);
return ret;
}
/// <summary>
/// Converts characters above ASCII to their ASCII equivalents. For example,
/// accents are removed from accented characters.
/// <para/>
/// @lucene.internal
/// </summary>
/// <param name="input"> The characters to fold </param>
/// <param name="inputPos"> Index of the first character to fold </param>
/// <param name="output"> The result of the folding. Should be of size >= <c>length * 4</c>. </param>
/// <param name="outputPos"> Index of output where to put the result of the folding </param>
/// <param name="length"> The number of characters to fold </param>
/// <returns> length of output </returns>
private static int latinizeLuceneImpl(char[] input, int inputPos, ref char[] output, int outputPos, int length)
{
int end = inputPos + length;
for (int pos = inputPos; pos < end; ++pos)
{
char c = input[pos];
// Quick test: if it's not in range then just keep current character
if (c < '\u0080')
{
output[outputPos++] = c;
}
else
{
switch (c)
{
case '\u00C0': // À [LATIN CAPITAL LETTER A WITH GRAVE]
case '\u00C1': // Á [LATIN CAPITAL LETTER A WITH ACUTE]
case '\u00C2': // Â [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
case '\u00C3': // Ã [LATIN CAPITAL LETTER A WITH TILDE]
case '\u00C4': // Ä [LATIN CAPITAL LETTER A WITH DIAERESIS]
case '\u00C5': // Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
case '\u0100': // Ā [LATIN CAPITAL LETTER A WITH MACRON]
case '\u0102': // Ă [LATIN CAPITAL LETTER A WITH BREVE]
case '\u0104': // Ą [LATIN CAPITAL LETTER A WITH OGONEK]
case '\u018F': // Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
case '\u01CD': // Ǎ [LATIN CAPITAL LETTER A WITH CARON]
case '\u01DE': // Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
case '\u01E0': // Ǡ [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
case '\u01FA': // Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
case '\u0200': // Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
case '\u0202': // Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
case '\u0226': // Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE]
case '\u023A': // Ⱥ [LATIN CAPITAL LETTER A WITH STROKE]
case '\u1D00': // ᴀ [LATIN LETTER SMALL CAPITAL A]
case '\u1E00': // Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW]
case '\u1EA0': // Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW]
case '\u1EA2': // Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
case '\u1EA4': // Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
case '\u1EA6': // Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
case '\u1EA8': // Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
case '\u1EAA': // Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
case '\u1EAC': // Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
case '\u1EAE': // Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
case '\u1EB0': // Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
case '\u1EB2': // Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
case '\u1EB4': // Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
case '\u1EB6': // Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
case '\u24B6': // Ⓐ [CIRCLED LATIN CAPITAL LETTER A]
case '\uFF21': // A [FULLWIDTH LATIN CAPITAL LETTER A]
output[outputPos++] = 'A';
break;
case '\u00E0': // à [LATIN SMALL LETTER A WITH GRAVE]
case '\u00E1': // á [LATIN SMALL LETTER A WITH ACUTE]
case '\u00E2': // â [LATIN SMALL LETTER A WITH CIRCUMFLEX]
case '\u00E3': // ã [LATIN SMALL LETTER A WITH TILDE]
case '\u00E4': // ä [LATIN SMALL LETTER A WITH DIAERESIS]
case '\u00E5': // å [LATIN SMALL LETTER A WITH RING ABOVE]
case '\u0101': // ā [LATIN SMALL LETTER A WITH MACRON]
case '\u0103': // ă [LATIN SMALL LETTER A WITH BREVE]
case '\u0105': // ą [LATIN SMALL LETTER A WITH OGONEK]
case '\u01CE': // ǎ [LATIN SMALL LETTER A WITH CARON]
case '\u01DF': // ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
case '\u01E1': // ǡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
case '\u01FB': // ǻ [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
case '\u0201': // ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
case '\u0203': // ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE]
case '\u0227': // ȧ [LATIN SMALL LETTER A WITH DOT ABOVE]
case '\u0250': // ɐ [LATIN SMALL LETTER TURNED A]
case '\u0259': // ə [LATIN SMALL LETTER SCHWA]
case '\u025A': // ɚ [LATIN SMALL LETTER SCHWA WITH HOOK]
case '\u1D8F': // ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
case '\u1D95': // ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
case '\u1E01': // ạ [LATIN SMALL LETTER A WITH RING BELOW]
case '\u1E9A': // ả [LATIN SMALL LETTER A WITH RIGHT HALF RING]
case '\u1EA1': // ạ [LATIN SMALL LETTER A WITH DOT BELOW]
case '\u1EA3': // ả [LATIN SMALL LETTER A WITH HOOK ABOVE]
case '\u1EA5': // ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
case '\u1EA7': // ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
case '\u1EA9': // ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
case '\u1EAB': // ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
case '\u1EAD': // ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
case '\u1EAF': // ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
case '\u1EB1': // ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
case '\u1EB3': // ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
case '\u1EB5': // ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE]
case '\u1EB7': // ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
case '\u2090': // ₐ [LATIN SUBSCRIPT SMALL LETTER A]
case '\u2094': // ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA]
case '\u24D0': // ⓐ [CIRCLED LATIN SMALL LETTER A]
case '\u2C65': // ⱥ [LATIN SMALL LETTER A WITH STROKE]
case '\u2C6F': // Ɐ [LATIN CAPITAL LETTER TURNED A]
case '\uFF41': // a [FULLWIDTH LATIN SMALL LETTER A]
output[outputPos++] = 'a';
break;
case '\uA732': // Ꜳ [LATIN CAPITAL LETTER AA]
output[outputPos++] = 'A';
output[outputPos++] = 'A';
break;
case '\u00C6': // Æ [LATIN CAPITAL LETTER AE]
case '\u01E2': // Ǣ [LATIN CAPITAL LETTER AE WITH MACRON]
case '\u01FC': // Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE]
case '\u1D01': // ᴁ [LATIN LETTER SMALL CAPITAL AE]
output[outputPos++] = 'A';
output[outputPos++] = 'E';
break;
case '\uA734': // Ꜵ [LATIN CAPITAL LETTER AO]
output[outputPos++] = 'A';
output[outputPos++] = 'O';
break;
case '\uA736': // Ꜷ [LATIN CAPITAL LETTER AU]
output[outputPos++] = 'A';
output[outputPos++] = 'U';
break;
// etc. etc. etc.
// see link above for complete source code
//
// unfortunately, postings are limited, as in
// "Body is limited to 30000 characters; you entered 136098."
[...]
case '\u2053': // ⁓ [SWUNG DASH]
case '\uFF5E': // ~ [FULLWIDTH TILDE]
output[outputPos++] = '~';
break;
default:
output[outputPos++] = c;
break;
}
}
}
return outputPos;
}
}