public void Ctor_WithUnicodeRanges()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder(UnicodeRanges.Latin1Supplement, UnicodeRanges.MiscellaneousSymbols);
// Act & assert
Assert.Equal("a", encoder.HtmlEncode("a"));
Assert.Equal("\u00E9", encoder.HtmlEncode("\u00E9" /* LATIN SMALL LETTER E WITH ACUTE */));
Assert.Equal("\u2601", encoder.HtmlEncode("\u2601" /* CLOUD */));
}
public void Ctor_WithNoParameters_DefaultsToBasicLatin()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder();
// Act & assert
Assert.Equal("a", encoder.HtmlEncode("a"));
Assert.Equal("é", encoder.HtmlEncode("\u00E9" /* LATIN SMALL LETTER E WITH ACUTE */));
Assert.Equal("☁", encoder.HtmlEncode("\u2601" /* CLOUD */));
}
public void HtmlEncode_NullInput_Throws()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder();
Assert.Throws <ArgumentNullException>(() => { encoder.HtmlEncode(null); });
}
public void HtmlEncode_EmptyStringInput_ReturnsEmptyString()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder();
// Act & assert
Assert.Equal("", encoder.HtmlEncode(""));
}
public void HtmlEncode_InputDoesNotRequireEncoding_ReturnsOriginalStringInstance()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder();
string input = "Hello, there!";
// Act & assert
Assert.Same(input, encoder.HtmlEncode(input));
}
public void HtmlEncode_AllRangesAllowed_StillEncodesForbiddenChars_Simple(string input, string expected)
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder(UnicodeRanges.All);
// Act
string retVal = encoder.HtmlEncode(input);
// Assert
Assert.Equal(expected, retVal);
}
public void HtmlEncode_StringSubstring()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder();
var output = new StringWriter();
// Act
encoder.HtmlEncode("Hello+world!", 3, 5, output);
// Assert
Assert.Equal("lo+wo", output.ToString());
}
public void HtmlEncode_BadSurrogates_ReturnsUnicodeReplacementChar()
{
// Arrange
HtmlEncoder encoder = new HtmlEncoder(UnicodeRanges.All); // allow all codepoints
// "a<unpaired leading>b<unpaired trailing>c<trailing before leading>d<unpaired trailing><valid>e<high at end of string>"
const string input = "a\uD800b\uDFFFc\uDFFF\uD800d\uDFFF\uD800\uDFFFe\uD800";
const string expected = "a\uFFFDb\uFFFDc\uFFFD\uFFFDd\uFFFD𐏿e\uFFFD";
// Act
string retVal = encoder.HtmlEncode(input);
// Assert
Assert.Equal(expected, retVal);
}
public void Default_EquivalentToBasicLatin()
{
// Arrange
HtmlEncoder controlEncoder = new HtmlEncoder(UnicodeRanges.BasicLatin);
HtmlEncoder testEncoder = HtmlEncoder.Default;
// Act & assert
for (int i = 0; i <= char.MaxValue; i++)
{
if (!IsSurrogateCodePoint(i))
{
string input = new string((char)i, 1);
Assert.Equal(controlEncoder.HtmlEncode(input), testEncoder.HtmlEncode(input));
}
}
}
public void Ctor_WithTextEncoderSettings()
{
// Arrange
var filter = new TextEncoderSettings();
filter.AllowCharacters('a', 'b');
filter.AllowCharacters('\0', '&', '\uFFFF', 'd');
HtmlEncoder encoder = new HtmlEncoder(filter);
// Act & assert
Assert.Equal("a", encoder.HtmlEncode("a"));
Assert.Equal("b", encoder.HtmlEncode("b"));
Assert.Equal("c", encoder.HtmlEncode("c"));
Assert.Equal("d", encoder.HtmlEncode("d"));
Assert.Equal("�", encoder.HtmlEncode("\0")); // we still always encode control chars
Assert.Equal("&", encoder.HtmlEncode("&")); // we still always encode HTML-special chars
Assert.Equal("", encoder.HtmlEncode("\uFFFF")); // we still always encode non-chars and other forbidden chars
}
public void JavaScriptStringEncode_DoesNotOutputHtmlSensitiveCharacters()
{
// Per the design document, we provide additional defense-in-depth
// by never emitting HTML-sensitive characters unescaped.
// Arrange
JavaScriptStringEncoder javaScriptStringEncoder = new JavaScriptStringEncoder(UnicodeRanges.All);
HtmlEncoder htmlEncoder = new HtmlEncoder(UnicodeRanges.All);
// Act & assert
for (int i = 0; i <= 0x10FFFF; i++)
{
if (IsSurrogateCodePoint(i))
{
continue; // surrogates don't matter here
}
string javaScriptStringEncoded = javaScriptStringEncoder.JavaScriptStringEncode(char.ConvertFromUtf32(i));
string thenHtmlEncoded = htmlEncoder.HtmlEncode(javaScriptStringEncoded);
Assert.Equal(javaScriptStringEncoded, thenHtmlEncoded); // should have contained no HTML-sensitive characters
}
}
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);
}
}