private static void VerifyUtf32Encoding(UTF32Encoding encoding, bool bigEndian, bool byteOrderMark, bool throwOnInvalidBytes)
{
if (byteOrderMark)
{
if (bigEndian)
{
Assert.Equal(new byte[] { 0, 0, 254, 255 }, encoding.GetPreamble());
}
else
{
Assert.Equal(new byte[] { 255, 254, 0, 0 }, encoding.GetPreamble());
}
}
else
{
Assert.Empty(encoding.GetPreamble());
}
if (throwOnInvalidBytes)
{
Assert.Equal(EncoderFallback.ExceptionFallback, encoding.EncoderFallback);
Assert.Equal(DecoderFallback.ExceptionFallback, encoding.DecoderFallback);
}
else
{
Assert.Equal(new EncoderReplacementFallback("\uFFFD"), encoding.EncoderFallback);
Assert.Equal(new DecoderReplacementFallback("\uFFFD"), encoding.DecoderFallback);
}
}
public static void VerifyUtf32Encoding(UTF32Encoding encoding, bool bigEndian, bool byteOrderMark, bool throwOnInvalidBytes)
{
if (byteOrderMark)
{
if (bigEndian)
{
Assert.Equal(new byte[] { 0, 0, 254, 255 }, encoding.GetPreamble());
}
else
{
Assert.Equal(new byte[] { 255, 254, 0, 0 }, encoding.GetPreamble());
}
}
else
{
Assert.Empty(encoding.GetPreamble());
}
if (throwOnInvalidBytes)
{
Assert.Equal(EncoderFallback.ExceptionFallback, encoding.EncoderFallback);
Assert.Equal(DecoderFallback.ExceptionFallback, encoding.DecoderFallback);
}
else
{
Assert.Equal(new EncoderReplacementFallback("\uFFFD"), encoding.EncoderFallback);
Assert.Equal(new DecoderReplacementFallback("\uFFFD"), encoding.DecoderFallback);
}
}
public static void Main()
{
var utf32 = new UTF32Encoding(!BitConverter.IsLittleEndian, true);
String s = "It was the best of times, it was the worst of times...";
// We need to dimension the array, since we'll populate it with 2 method calls.
Byte[] bytes = new Byte[utf32.GetByteCount(s) + utf32.GetPreamble().Length];
// Encode the string.
Array.Copy(utf32.GetPreamble(), bytes, utf32.GetPreamble().Length);
utf32.GetBytes(s, 0, s.Length, bytes, utf32.GetPreamble().Length);
// Decode the byte array.
String s2 = utf32.GetString(bytes, 0, bytes.Length);
Console.WriteLine(s2);
}
public static void Main()
{
// Create instances of UTF32Encoding, with the byte order mark and without.
UTF32Encoding u32LeNone = new UTF32Encoding();
UTF32Encoding u32BeNone = new UTF32Encoding(true, false);
UTF32Encoding u32LeBom = new UTF32Encoding(false, true);
UTF32Encoding u32BeBom = new UTF32Encoding(true, true);
// Display the preamble for each instance.
PrintHexBytes(u32LeNone.GetPreamble());
PrintHexBytes(u32BeNone.GetPreamble());
PrintHexBytes(u32LeBom.GetPreamble());
PrintHexBytes(u32BeBom.GetPreamble());
}
public static void Main()
{
// Create a UTF-32 encoding that supports a BOM.
var enc = new UTF32Encoding();
// A Unicode string with two characters outside an 8-bit code range.
String s = "This Unicode string has 2 characters " +
"outside the ASCII range: \n" +
"Pi (\u03A0), and Sigma (\u03A3).";
Console.WriteLine("Original string:");
Console.WriteLine(s);
Console.WriteLine();
// Encode the string.
Byte[] encodedBytes = enc.GetBytes(s);
Console.WriteLine("The encoded string has {0} bytes.\n",
encodedBytes.Length);
// Write the bytes to a file with a BOM.
var fs = new FileStream(@".\UTF32Encoding.txt", FileMode.Create);
Byte[] bom = enc.GetPreamble();
fs.Write(bom, 0, bom.Length);
fs.Write(encodedBytes, 0, encodedBytes.Length);
Console.WriteLine("Wrote {0} bytes to the file.\n", fs.Length);
fs.Close();
// Open the file using StreamReader.
var sr = new StreamReader(@".\UTF32Encoding.txt");
String newString = sr.ReadToEnd();
sr.Close();
Console.WriteLine("String read using StreamReader:");
Console.WriteLine(newString);
Console.WriteLine();
// Open the file as a binary file and decode the bytes back to a string.
fs = new FileStream(@".\Utf32Encoding.txt", FileMode.Open);
Byte[] bytes = new Byte[fs.Length];
fs.Read(bytes, 0, (int)fs.Length);
fs.Close();
String decodedString = enc.GetString(encodedBytes);
Console.WriteLine("Decoded bytes from binary file:");
Console.WriteLine(decodedString);
}
static EncodingUtility()
{
Encoding utf32BE = new UTF32Encoding(true, true, true);
Encoding utf32LE = new UTF32Encoding(false, true, true);
Encoding utf16BE = new UnicodeEncoding(true, true, true);
Encoding utf16LE = new UnicodeEncoding(false, true, true);
Encoding utf8BOM = new UTF8Encoding(true, true);
encodingLookup = new KeyValuePair <byte[], Encoding>[]
{
new KeyValuePair <byte[], Encoding>(utf32BE.GetPreamble(), utf32BE),
new KeyValuePair <byte[], Encoding>(utf32LE.GetPreamble(), utf32LE),
new KeyValuePair <byte[], Encoding>(utf16BE.GetPreamble(), utf16BE),
new KeyValuePair <byte[], Encoding>(utf16LE.GetPreamble(), utf16LE),
new KeyValuePair <byte[], Encoding>(utf8BOM.GetPreamble(), utf8BOM),
};
}
public void OpensReaderWithAutoDetectEncoding()
{
string expected = "test";
Encoding utf32 = new UTF32Encoding(false, true);
byte[] resourceData = GetBytes(expected, utf32);
resourceData = (byte[])ArrayUtils.Concat(utf32.GetPreamble(), resourceData);
EncodedResource r = new EncodedResource(new InputStreamResource(new MemoryStream(resourceData), "description"), Encoding.UTF8, true);
StreamReader reader = (StreamReader)r.OpenReader();
Assert.AreEqual(Encoding.UTF8.EncodingName, reader.CurrentEncoding.EncodingName);
string actual = reader.ReadToEnd();
Assert.AreEqual("\uFEFF" + expected, actual);
// interestingly the line below is *not* true!
// Assert.AreEqual(utf32.GetString(resourceData), actual);
Assert.AreEqual(utf32, reader.CurrentEncoding);
}
static EncodingUtility()
{
TextAsset.EncodingUtility.targetEncoding = Encoding.GetEncoding(Encoding.UTF8.CodePage, new EncoderReplacementFallback("�"), new DecoderReplacementFallback("�"));
Encoding encoding = new UTF32Encoding(true, true, true);
Encoding encoding2 = new UTF32Encoding(false, true, true);
Encoding encoding3 = new UnicodeEncoding(true, true, true);
Encoding encoding4 = new UnicodeEncoding(false, true, true);
Encoding encoding5 = new UTF8Encoding(true, true);
TextAsset.EncodingUtility.encodingLookup = new KeyValuePair <byte[], Encoding>[]
{
new KeyValuePair <byte[], Encoding>(encoding.GetPreamble(), encoding),
new KeyValuePair <byte[], Encoding>(encoding2.GetPreamble(), encoding2),
new KeyValuePair <byte[], Encoding>(encoding3.GetPreamble(), encoding3),
new KeyValuePair <byte[], Encoding>(encoding4.GetPreamble(), encoding4),
new KeyValuePair <byte[], Encoding>(encoding5.GetPreamble(), encoding5)
};
}