public void ForbidUndefinedCharacters_RemovesUndefinedChars()
{
// Arrange
// We only allow odd-numbered characters in this test so that
// we can validate that we properly merged the two bitmaps together
// rather than simply overwriting the target.
var bitmap = AllowedCharsBitmap.CreateNew();
for (int i = 1; i <= Char.MaxValue; i += 2)
{
bitmap.AllowCharacter((char)i);
}
// Act
bitmap.ForbidUndefinedCharacters();
// Assert
for (int i = 0; i <= Char.MaxValue; i++)
{
if (i % 2 == 0)
{
Assert.False(bitmap.IsCharacterAllowed((char)i)); // these chars were never allowed in the original description
}
else
{
Assert.Equal(UnicodeHelpers.IsCharacterDefined((char)i), bitmap.IsCharacterAllowed((char)i));
}
}
}
public void IsCharacterDefined()
{
// Arrange
bool[] definedChars = ReadListOfDefinedCharacters();
List <string> errors = new List <string>();
// Act & assert
for (int i = 0; i <= Char.MaxValue; i++)
{
bool expected = definedChars[i];
bool actual = UnicodeHelpers.IsCharacterDefined((char)i);
if (expected != actual)
{
errors.Add($"Character U+{i:X4}: expected = {expected}, actual = {actual}");
}
}
if (errors.Count > 0)
{
Assert.True(false, String.Join(Environment.NewLine, errors));
}
}
public void UrlEncode_AllRangesAllowed_StillEncodesForbiddenChars()
{
// Arrange
UrlEncoder encoder = new UrlEncoder(UnicodeRanges.All);
// Act & assert - BMP chars
for (int i = 0; i <= 0xFFFF; i++)
{
string input = new String((char)i, 1);
string expected;
if (IsSurrogateCodePoint(i))
{
expected = "%EF%BF%BD"; // unpaired surrogate -> Unicode replacement char
}
else
{
bool mustEncode = true;
// RFC 3987, Sec. 2.2 gives the list of allowed chars
// (We allow 'ipchar' except for "'", "&", "+", "%", and "="
if (('a' <= i && i <= 'z') || ('A' <= i && i <= 'Z') || ('0' <= i && i <= '9'))
{
mustEncode = false; // ALPHA / DIGIT
}
else if ((0x00A0 <= i && i <= 0xD7FF) | (0xF900 <= i && i <= 0xFDCF) | (0xFDF0 <= i && i <= 0xFFEF))
{
mustEncode = !UnicodeHelpers.IsCharacterDefined((char)i); // 'ucschar'
}
else
{
switch (i)
{
// iunreserved
case '-':
case '.':
case '_':
case '~':
// isegment-nz-nc
case '@':
// sub-delims
case '!':
case '$':
case '(':
case ')':
case '*':
case ',':
case ';':
mustEncode = false;
break;
}
}
if (mustEncode)
{
expected = GetKnownGoodPercentEncodedValue(i);
}
else
{
expected = input; // no encoding
}
}
string retVal = encoder.UrlEncode(input);
Assert.Equal(expected, retVal);
}
// Act & assert - astral chars
for (int i = 0x10000; i <= 0x10FFFF; i++)
{
string input = Char.ConvertFromUtf32(i);
string expected = GetKnownGoodPercentEncodedValue(i);
string retVal = encoder.UrlEncode(input);
Assert.Equal(expected, retVal);
}
}
public void JavaScriptStringEncode_AllRangesAllowed_StillEncodesForbiddenChars_Extended()
{
// Arrange
JavaScriptStringEncoder encoder = new JavaScriptStringEncoder(UnicodeRanges.All);
// Act & assert - BMP chars
for (int i = 0; i <= 0xFFFF; i++)
{
string input = new String((char)i, 1);
string expected;
if (IsSurrogateCodePoint(i))
{
expected = "\uFFFD"; // unpaired surrogate -> Unicode replacement char
}
else
{
if (input == "\b")
{
expected = @"\b";
}
else if (input == "\t")
{
expected = @"\t";
}
else if (input == "\n")
{
expected = @"\n";
}
else if (input == "\f")
{
expected = @"\f";
}
else if (input == "\r")
{
expected = @"\r";
}
else if (input == "\\")
{
expected = @"\\";
}
else if (input == "/")
{
expected = @"\/";
}
else
{
bool mustEncode = false;
switch (i)
{
case '<':
case '>':
case '&':
case '\"':
case '\'':
case '+':
mustEncode = true;
break;
}
if (i <= 0x001F || (0x007F <= i && i <= 0x9F))
{
mustEncode = true; // control char
}
else if (!UnicodeHelpers.IsCharacterDefined((char)i))
{
mustEncode = true; // undefined (or otherwise disallowed) char
}
if (mustEncode)
{
expected = String.Format(CultureInfo.InvariantCulture, @"\u{0:X4}", i);
}
else
{
expected = input; // no encoding
}
}
}
string retVal = encoder.JavaScriptStringEncode(input);
Assert.Equal(expected, retVal);
}
// Act & assert - astral chars
for (int i = 0x10000; i <= 0x10FFFF; i++)
{
string input = Char.ConvertFromUtf32(i);
string expected = String.Format(CultureInfo.InvariantCulture, @"\u{0:X4}\u{1:X4}", (uint)input[0], (uint)input[1]);
string retVal = encoder.JavaScriptStringEncode(input);
Assert.Equal(expected, retVal);
}
}
public void HtmlEncode_AllRangesAllowed_StillEncodesForbiddenChars_Extended()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder(UnicodeRanges.All);
// Act & assert - BMP chars
for (int i = 0; i <= 0xFFFF; i++)
{
string input = new String((char)i, 1);
string expected;
if (IsSurrogateCodePoint(i))
{
expected = "\uFFFD"; // unpaired surrogate -> Unicode replacement char
}
else
{
if (input == "<")
{
expected = "<";
}
else if (input == ">")
{
expected = ">";
}
else if (input == "&")
{
expected = "&";
}
else if (input == "\"")
{
expected = """;
}
else
{
bool mustEncode = false;
if (i == '\'' || i == '+')
{
mustEncode = true; // apostrophe, plus
}
else if (i <= 0x001F || (0x007F <= i && i <= 0x9F))
{
mustEncode = true; // control char
}
else if (!UnicodeHelpers.IsCharacterDefined((char)i))
{
mustEncode = true; // undefined (or otherwise disallowed) char
}
if (mustEncode)
{
expected = String.Format(CultureInfo.InvariantCulture, "&#x{0:X};", i);
}
else
{
expected = input; // no encoding
}
}
}
string retVal = encoder.HtmlEncode(input);
Assert.Equal(expected, retVal);
}
// Act & assert - astral chars
for (int i = 0x10000; i <= 0x10FFFF; i++)
{
string input = Char.ConvertFromUtf32(i);
string expected = String.Format(CultureInfo.InvariantCulture, "&#x{0:X};", i);
string retVal = encoder.HtmlEncode(input);
Assert.Equal(expected, retVal);
}
}