Généralités
|
byte[] bytes = Encoding.Default.GetBytes("é"); // bytes[0] → 233 (10)
bytes[0].ToString("X"); // E9 (16)
string utf8String = Encoding.UTF8.GetString(bytes); // é
string s1 = Char.ConvertFromUtf32(bytes[0]); // é
string s2 = Char.ConvertFromUtf32(0xE9); // é
|
 |
Les string en mémoire sont encodé en UTF-16. |
| Encoding.Default |
the operating system's current ANSI code page
|
| Encoding.UTF8 |
UTF-8 avec BOM
|
| Encoding.Unicode |
UTF-16 format using the little endian byte order
|
| Encoding.BigEndianUnicode |
UTF-16 format using the big endian byte order
|
| Encoding.UTF32 |
UTF-32 format using the little endian byte order
|
Changer la base d'un chiffre
UTF-8 sans BOM
|
|
Encoding utf8WithBom = new UTF8Encoding();
Encoding utf8WithoutBom = new UTF8Encoding(false);
using (TextWriter tw = new StreamWriter(filePath, false, utf8WithoutBom))
{
tw.WriteLine("text");
}
|
|
StreamWriter pour écrire dans un flux (file, buffer, memory)
StringWriter pour écrire dans un String |
StringWriter en UTF-8
|
|
public class Utf8StringWriter : StringWriter
{
public override Encoding Encoding
{
// UTF8Encoding(false) instead of Encoding.UTF8 to get utf-8 without BOM
get { return new UTF8Encoding(false); }
}
}
using (var sw = new Utf8StringWriter())
{
var serializer = new XmlSerializer(monObjet.GetType());
serializer.Serialize(sw, monObjet, null);
string output = sw.ToString();
}
|
|
Par défaut, StringWriter utilise UTF-16. |
Écrire dans un fichier
|
|
File.WriteAllText(filePath, "text"); // UTF-8 sans BOM
File.WriteAllText(filePath, "text", Encoding.UTF8); // UTF-8 avec BOM
|
|
|
var unicodeText = "éà";
var normalizedString = unicodeText.Normalize(NormalizationForm.FormD);
var stringBuilder = new StringBuilder();
foreach (var c in normalizedString)
{
var unicodeCategory = CharUnicodeInfo.GetUnicodeCategory(c);
if (unicodeCategory != UnicodeCategory.NonSpacingMark)
{
stringBuilder.Append(c);
}
}
var v = stringBuilder.ToString().Normalize(NormalizationForm.FormC);
|
NormalizationForm
