public static void Main()
{
Char[] chars;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding utf7 = new UTF7Encoding();
int charCount = utf7.GetCharCount(bytes, 2, 8);
chars = new Char[charCount];
int charsDecodedCount = utf7.GetChars(bytes, 2, 8, chars, 0);
Console.WriteLine(
"{0} characters used to decode bytes.", charsDecodedCount
);
Console.Write("Decoded chars: ");
foreach (Char c in chars)
{
Console.Write("[{0}]", c);
}
Console.WriteLine();
}
public void RFC1642_Example4()
{
string UniCodeString = "\u0049\u0074\u0065\u006D\u0020\u0033\u0020\u0069\u0073\u0020\u00A3\u0031\u002E";
char[] expected = UniCodeString.ToCharArray();
byte[] UTF7Bytes = new byte[] { 0x49, 0x74, 0x65, 0x6D, 0x20, 0x33, 0x20, 0x69, 0x73, 0x20, 0x2B, 0x41, 0x4B, 0x4D, 0x2D, 0x31, 0x2E };
UTF7Encoding UTF7enc = new UTF7Encoding();
char[] actual = UTF7enc.GetChars(UTF7Bytes);
// "Item 3 is +AKM-1." is decoded as "Item 3 is <POUND SIGN>1."
Assert.AreEqual(expected [0], actual [0], "UTF #1");
Assert.AreEqual(expected [1], actual [1], "UTF #2");
Assert.AreEqual(expected [2], actual [2], "UTF #3");
Assert.AreEqual(expected [3], actual [3], "UTF #4");
Assert.AreEqual(expected [4], actual [4], "UTF #5");
Assert.AreEqual(expected [5], actual [5], "UTF #6");
Assert.AreEqual(expected [6], actual [6], "UTF #7");
Assert.AreEqual(expected [7], actual [7], "UTF #8");
Assert.AreEqual(expected [8], actual [8], "UTF #9");
Assert.AreEqual(expected [9], actual [9], "UTF #10");
Assert.AreEqual(expected [10], actual [10], "UTF #11");
Assert.AreEqual(expected [11], actual [11], "UTF #12");
Assert.AreEqual(expected [12], actual [12], "UTF #13");
Assert.AreEqual(UniCodeString, UTF7enc.GetString(UTF7Bytes), "GetString");
}
public void RFC1642_Example2()
{
string UniCodeString = "\u0048\u0069\u0020\u004D\u006F\u004D\u0020\u263A\u0021";
char[] expected = UniCodeString.ToCharArray();
byte[] UTF7Bytes = new byte[] { 0x48, 0x69, 0x20, 0x4D, 0x6F, 0x4D, 0x20, 0x2B, 0x4A, 0x6A, 0x6F, 0x41, 0x49, 0x51, 0x2D };
UTF7Encoding UTF7enc = new UTF7Encoding();
char[] actual = UTF7enc.GetChars(UTF7Bytes);
// "Hi Mom +Jjo-!" is decoded as "Hi Mom <WHITE SMILING FACE>!"
Assert.AreEqual(expected [0], actual [0], "UTF #1");
Assert.AreEqual(expected [1], actual [1], "UTF #2");
Assert.AreEqual(expected [2], actual [2], "UTF #3");
Assert.AreEqual(expected [3], actual [3], "UTF #4");
Assert.AreEqual(expected [4], actual [4], "UTF #5");
Assert.AreEqual(expected [5], actual [5], "UTF #6");
Assert.AreEqual(expected [6], actual [6], "UTF #7");
Assert.AreEqual(expected [7], actual [7], "UTF #8");
Assert.AreEqual(expected [8], actual [8], "UTF #9");
Assert.AreEqual(UniCodeString, UTF7enc.GetString(UTF7Bytes), "GetString");
}
public static void Main()
{
// A few optional characters.
string chars = "!@#$";
// The default Encoding does not allow optional characters.
// Alternate byte values are used.
UTF7Encoding utf7 = new UTF7Encoding();
Byte[] bytes1 = utf7.GetBytes(chars);
Console.WriteLine("Default UTF7 Encoding:");
ShowArray(bytes1);
// Convert back to characters.
Console.WriteLine("Characters:");
ShowArray(utf7.GetChars(bytes1));
// Now, allow optional characters.
// Optional characters are encoded with their normal code points.
UTF7Encoding utf7AllowOptionals = new UTF7Encoding(true);
Byte[] bytes2 = utf7AllowOptionals.GetBytes(chars);
Console.WriteLine("UTF7 Encoding with optional characters allowed:");
ShowArray(bytes2);
// Convert back to characters.
Console.WriteLine("Characters:");
ShowArray(utf7AllowOptionals.GetChars(bytes2));
}
public void PosTest2()
{
Char[] chars;
Byte[] bytes = new Byte[] { };
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 0, 0);
chars = new Char[] { };
int charsDecodedCount = UTF7.GetChars(bytes, 0, 0, chars, 0);
Assert.Equal(0, charsDecodedCount);
}
public void NegTest1()
{
Char[] chars;
Byte[] bytes = null;
UTF7Encoding UTF7 = new UTF7Encoding();
chars = new Char[] { };
Assert.Throws<ArgumentNullException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, 0, 0, chars, 0);
});
}
public void NegTest1()
{
Char[] chars;
Byte[] bytes = null;
UTF7Encoding UTF7 = new UTF7Encoding();
chars = new Char[] { };
Assert.Throws <ArgumentNullException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, 0, 0, chars, 0);
});
}
public void PosTest2()
{
Char[] chars;
Byte[] bytes = new Byte[] { };
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 0, 0);
chars = new Char[] { };
int charsDecodedCount = UTF7.GetChars(bytes, 0, 0, chars, 0);
Assert.Equal(0, charsDecodedCount);
}
public void PosTest1()
{
Char[] chars;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 2, 8);
chars = new Char[charCount];
int charsDecodedCount = UTF7.GetChars(bytes, 2, 8, chars, 0);
}
public void PosTest1()
{
Char[] chars;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 2, 8);
chars = new Char[charCount];
int charsDecodedCount = UTF7.GetChars(bytes, 2, 8, chars, 0);
}
public void NegTest2()
{
Char[] chars = null;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
Assert.Throws<ArgumentNullException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, 2, 8, chars, 0);
});
}
public void NegTest2()
{
Char[] chars = null;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
Assert.Throws <ArgumentNullException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, 2, 8, chars, 0);
});
}
public void TestCompare256WithUtf7()
{
Encoding utf7 = new UTF7Encoding(allowOptionals: true);
Encoding penc = new PythonSurrogateEscapeEncoding(utf7);
// The following Python output is produced with python 3.4 but is not correct: it is missing the '+' character
string python_chars = "\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !\"#$%&'()*,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\udc80\udc81\udc82\udc83\udc84\udc85\udc86\udc87\udc88\udc89\udc8a\udc8b\udc8c\udc8d\udc8e\udc8f\udc90\udc91\udc92\udc93\udc94\udc95\udc96\udc97\udc98\udc99\udc9a\udc9b\udc9c\udc9d\udc9e\udc9f\udca0\udca1\udca2\udca3\udca4\udca5\udca6\udca7\udca8\udca9\udcaa\udcab\udcac\udcad\udcae\udcaf\udcb0\udcb1\udcb2\udcb3\udcb4\udcb5\udcb6\udcb7\udcb8\udcb9\udcba\udcbb\udcbc\udcbd\udcbe\udcbf\udcc0\udcc1\udcc2\udcc3\udcc4\udcc5\udcc6\udcc7\udcc8\udcc9\udcca\udccb\udccc\udccd\udcce\udccf\udcd0\udcd1\udcd2\udcd3\udcd4\udcd5\udcd6\udcd7\udcd8\udcd9\udcda\udcdb\udcdc\udcdd\udcde\udcdf\udce0\udce1\udce2\udce3\udce4\udce5\udce6\udce7\udce8\udce9\udcea\udceb\udcec\udced\udcee\udcef\udcf0\udcf1\udcf2\udcf3\udcf4\udcf5\udcf6\udcf7\udcf8\udcf9\udcfa\udcfb\udcfc\udcfd\udcfe\udcff";
// Our implementation will refuse (correctly) to decode because the ',' after '+' is not valid thus requires escaping,
// but escaping of chars under 128 is not allowed.
Assert.Throws <DecoderFallbackException>(() => penc.GetChars(bytes));
// Let's try again without the '+'
bytes = bytes.Where(i => i != (byte)'+').ToArray();
char[] chars = penc.GetChars(bytes);
Assert.AreEqual(python_chars, chars);
// Now the encoding part
byte[] encoded_bytes = penc.GetBytes(chars);
byte[] expected_bytes = "+AAAAAQACAAMABAAFAAYABwAI-\t\n+AAsADA-\r+AA4ADwAQABEAEgATABQAFQAWABcAGAAZABoAGwAcAB0AHgAf- !\"#$%&'()*,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[+AFw-]^_`abcdefghijklmnopqrstuvwxyz{|}+AH4Af9yA3IHcgtyD3ITchdyG3IfciNyJ3Irci9yM3I3cjtyP3JDckdyS3JPclNyV3Jbcl9yY3Jncmtyb3Jzcndye3J/coNyh3KLco9yk3KXcptyn3Kjcqdyq3KvcrNyt3K7cr9yw3LHcstyz3LTctdy23LfcuNy53Lrcu9y83L3cvty/3MDcwdzC3MPcxNzF3Mbcx9zI3MncytzL3MzczdzO3M/c0NzR3NLc09zU3NXc1tzX3Njc2dza3Nvc3Nzd3N7c39zg3OHc4tzj3OTc5dzm3Ofc6Nzp3Orc69zs3O3c7tzv3PDc8dzy3PPc9Nz13Pbc99z43Pnc+tz73Pzc/dz+3P8-"
.Select(c => (byte)c).ToArray();
Assert.AreEqual(expected_bytes, encoded_bytes);
// Encoding the given chars with CPython produces the following byte string
byte[] python_bytes = "+AAAAAQACAAMABAAFAAYABwAI\t\n+AAsADA\r+AA4ADwAQABEAEgATABQAFQAWABcAGAAZABoAGwAcAB0AHgAf !\"#$%&'()*,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[+AFw]^_`abcdefghijklmnopqrstuvwxyz{|}+AH4Af9yA3IHcgtyD3ITchdyG3IfciNyJ3Irci9yM3I3cjtyP3JDckdyS3JPclNyV3Jbcl9yY3Jncmtyb3Jzcndye3J/coNyh3KLco9yk3KXcptyn3Kjcqdyq3KvcrNyt3K7cr9yw3LHcstyz3LTctdy23LfcuNy53Lrcu9y83L3cvty/3MDcwdzC3MPcxNzF3Mbcx9zI3MncytzL3MzczdzO3M/c0NzR3NLc09zU3NXc1tzX3Njc2dza3Nvc3Nzd3N7c39zg3OHc4tzj3OTc5dzm3Ofc6Nzp3Orc69zs3O3c7tzv3PDc8dzy3PPc9Nz13Pbc99z43Pnc+tz73Pzc/dz+3P8-"
.Select(c => (byte)c).ToArray();
// The sequences expected_bytes and python_bytes are NOT equal: .NET ends encoded blocks (starting with '+') with '-'
// Terminating encoded blocks with '-' is optional if not ambiguous.
// CPython doesn't terminate blocks with '-' if not mandatory, resulting in a more compact encoding.
// However, they both decode to the same text, although, again, CPython's version cannot be decoded using surrogateescape
char[] dotnet_decoded = penc.GetChars(encoded_bytes);
char[] python_decoded = utf7.GetChars(python_bytes);
Assert.AreEqual(chars, python_decoded);
Assert.AreEqual(chars, dotnet_decoded);
dotnet_decoded = utf7.GetChars(encoded_bytes);
Assert.AreEqual(chars, dotnet_decoded);
}
public void NegTest3()
{
Char[] chars;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 2, 8);
chars = new Char[charCount];
Assert.Throws<ArgumentOutOfRangeException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, -2, 8, chars, 0);
});
}
public void NegTest4()
{
Char[] chars;
Byte[] bytes = new Byte[] {
85, 84, 70, 55, 32, 69, 110,
99, 111, 100, 105, 110, 103, 32,
69, 120, 97, 109, 112, 108, 101
};
UTF7Encoding UTF7 = new UTF7Encoding();
int charCount = UTF7.GetCharCount(bytes, 2, 8);
chars = new Char[charCount];
Assert.Throws <ArgumentOutOfRangeException>(() =>
{
int charsDecodedCount = UTF7.GetChars(bytes, 2, -8, chars, 0);
});
}
public void RFC1642_Example1()
{
string UniCodeString = "\u0041\u2262\u0391\u002E";
char[] expected = UniCodeString.ToCharArray();
byte[] UTF7Bytes = new byte [] { 0x41, 0x2B, 0x49, 0x6D, 0x49, 0x44, 0x6B, 0x51, 0x2D, 0x2E };
UTF7Encoding UTF7enc = new UTF7Encoding();
char[] actual = UTF7enc.GetChars(UTF7Bytes);
// "A+ImIDkQ-." is decoded as "A<NOT IDENTICAL TO><ALPHA>." see RFC 1642
Assert.AreEqual(expected [0], actual [0], "UTF #1");
Assert.AreEqual(expected [1], actual [1], "UTF #2");
Assert.AreEqual(expected [2], actual [2], "UTF #3");
Assert.AreEqual(expected [3], actual [3], "UTF #4");
Assert.AreEqual(UniCodeString, UTF7enc.GetString(UTF7Bytes), "GetString");
}
public void RFC1642_Example3()
{
string UniCodeString = "\u65E5\u672C\u8A9E";
char[] expected = UniCodeString.ToCharArray();
byte[] UTF7Bytes = new byte[] { 0x2B, 0x5A, 0x65, 0x56, 0x6E, 0x4C, 0x49, 0x71, 0x65, 0x2D };
UTF7Encoding UTF7enc = new UTF7Encoding();
char[] actual = UTF7enc.GetChars(UTF7Bytes);
// "+ZeVnLIqe-" is decoded as Japanese "nihongo"
Assert.AreEqual(expected [0], actual [0], "UTF #1");
Assert.AreEqual(expected [1], actual [1], "UTF #2");
Assert.AreEqual(expected [2], actual [2], "UTF #3");
Assert.AreEqual(UniCodeString, UTF7enc.GetString(UTF7Bytes), "GetString");
}
/// <summary>
/// Gets the cell address.
/// </summary>
/// <param name="rowIndex">Index of the row.</param>
/// <param name="columnIndex">Index of the column.</param>
/// <returns>Cell address string.</returns>
private String GetCellAddress(Int32 rowIndex, Int32 columnIndex)
{
Byte[] bytes;
Int32 columnDiv, columnReminder;
String cellAdress;
columnDiv = (columnIndex - 1) / 26;
columnReminder = ((columnIndex - 1) % 26) + 1;
if (columnDiv > 0)
{
bytes = new Byte[2];
bytes[0] = (Byte)(64 + columnDiv);
bytes[1] = (Byte)(64 + columnReminder);
}
else
{
bytes = new Byte[1];
bytes[0] = (Byte)(64 + columnReminder);
}
cellAdress = new String(_utf7Encoding.GetChars(bytes)) + rowIndex;
return(cellAdress);
}
