/// <summary>
/// Initializes the LDAP DN safe lists.
/// </summary>
private static void InitialiseDistinguishedNameSafeList()
{
DistinguishedNameSafeListSyncLock.EnterWriteLock();
try
{
if (distinguishedNameCharacterValues == null)
{
distinguishedNameCharacterValues = SafeList.Generate(255, SafeList.HashThenHexValueGenerator);
SafeList.PunchSafeList(ref distinguishedNameCharacterValues, DistinguishedNameSafeList());
// Now mark up the specially listed characters from http://www.ietf.org/rfc/rfc2253.txt
EscapeDistinguisedNameCharacter(',');
EscapeDistinguisedNameCharacter('+');
EscapeDistinguisedNameCharacter('"');
EscapeDistinguisedNameCharacter('\\');
EscapeDistinguisedNameCharacter('<');
EscapeDistinguisedNameCharacter('>');
EscapeDistinguisedNameCharacter(';');
}
}
finally
{
DistinguishedNameSafeListSyncLock.ExitWriteLock();
}
}
/// <summary>
/// Initializes the HTML safe list.
/// </summary>
private static void InitialiseSafeList()
{
syncLock.EnterWriteLock();
try
{
characterValues = SafeList.Generate(255, SafeList.PercentThenHexValueGenerator);
SafeList.PunchSafeList(ref characterValues, UrlParameterSafeList());
}
finally
{
syncLock.ExitWriteLock();
}
}
/// <summary>
/// Initializes the LDAP filter safe lists.
/// </summary>
private static void InitialiseFilterSafeList()
{
FilterSafeListSyncLock.EnterWriteLock();
try
{
if (filterCharacterValues == null)
{
filterCharacterValues = SafeList.Generate(255, SafeList.SlashThenHexValueGenerator);
SafeList.PunchSafeList(ref filterCharacterValues, FilterEncodingSafeList());
}
}
finally
{
FilterSafeListSyncLock.ExitWriteLock();
}
}
/// <summary>
/// Initializes the HTML safe list.
/// </summary>
private static void InitialiseSafeList()
{
syncLock.EnterWriteLock();
try
{
if (characterValues == null)
{
characterValues = SafeList.Generate(0xFF, SafeList.SlashThenSixDigitHexValueGenerator);
SafeList.PunchSafeList(ref characterValues, CssSafeList());
}
}
finally
{
syncLock.ExitWriteLock();
}
}
/// <summary>
/// Marks characters from the specified languages as safe.
/// </summary>
/// <param name="lowerCodeCharts">The combination of lower code charts to use.</param>
/// <param name="lowerMidCodeCharts">The combination of lower mid code charts to use.</param>
/// <param name="midCodeCharts">The combination of mid code charts to use.</param>
/// <param name="upperMidCodeCharts">The combination of upper mid code charts to use.</param>
/// <param name="upperCodeCharts">The combination of upper code charts to use.</param>
/// <remarks>The safe list affects all HTML and XML encoding functions.</remarks>
public static void MarkAsSafe(
LowerCodeCharts lowerCodeCharts,
LowerMidCodeCharts lowerMidCodeCharts,
MidCodeCharts midCodeCharts,
UpperMidCodeCharts upperMidCodeCharts,
UpperCodeCharts upperCodeCharts)
{
if (lowerCodeCharts == currentLowerCodeChartSettings &&
lowerMidCodeCharts == currentLowerMidCodeChartSettings &&
midCodeCharts == currentMidCodeChartSettings &&
upperMidCodeCharts == currentUpperMidCodeChartSettings &&
upperCodeCharts == currentUpperCodeChartSettings)
{
return;
}
SyncLock.EnterWriteLock();
try
{
if (characterValues == null)
{
characterValues = SafeList.Generate(65536, SafeList.HashThenValueGenerator);
}
SafeList.PunchUnicodeThrough(
ref characterValues,
lowerCodeCharts,
lowerMidCodeCharts,
midCodeCharts,
upperMidCodeCharts,
upperCodeCharts);
ApplyHtmlSpecificValues();
currentLowerCodeChartSettings = lowerCodeCharts;
currentLowerMidCodeChartSettings = lowerMidCodeCharts;
currentMidCodeChartSettings = midCodeCharts;
currentUpperMidCodeChartSettings = upperMidCodeCharts;
currentUpperCodeChartSettings = upperCodeCharts;
}
finally
{
SyncLock.ExitWriteLock();
}
}
/// <summary>
/// Initializes the HTML safe list.
/// </summary>
private static void InitialiseSafeList()
{
SyncLock.EnterWriteLock();
try
{
if (characterValues == null)
{
characterValues = SafeList.Generate(0xFFFF, SafeList.HashThenValueGenerator);
SafeList.PunchUnicodeThrough(
ref characterValues,
LowerCodeCharts.Default,
LowerMidCodeCharts.None,
MidCodeCharts.None,
UpperMidCodeCharts.None,
UpperCodeCharts.None);
ApplyHtmlSpecificValues();
}
}
finally
{
SyncLock.ExitWriteLock();
}
}
/// <summary>
/// Encodes input strings for use in HTML.
/// </summary>
/// <param name="input">String to be encoded</param>
/// <param name="useNamedEntities">Value indicating if the HTML 4.0 named entities should be used.</param>
/// <param name="encoderTweak">A <see cref="MethodSpecificEncoder"/> function, if needed.</param>
/// <returns>
/// Encoded string for use in HTML.
/// </returns>
/// <exception cref="InvalidUnicodeValueException">Thrown if a character with an invalid Unicode value is encountered within the input string.</exception>
/// <exception cref="InvalidSurrogatePairException">Thrown if a high surrogate code point is encoded without a following low surrogate code point, or a
/// low surrogate code point is encounter without having been preceded by a high surrogate code point.</exception>
private static string HtmlEncode(string input, bool useNamedEntities, MethodSpecificEncoder encoderTweak)
{
if (string.IsNullOrEmpty(input))
{
return(input);
}
if (characterValues == null)
{
InitialiseSafeList();
}
if (useNamedEntities && namedEntities == null)
{
InitialiseNamedEntityList();
}
// Setup a new character array for output.
char[] inputAsArray = input.ToCharArray();
int outputLength = 0;
int inputLength = inputAsArray.Length;
char[] encodedInput = new char[inputLength * 10]; // Worse case scenario - the longest entity name, thetasym is 10 characters, including the & and ;.
SyncLock.EnterReadLock();
try
{
for (int i = 0; i < inputLength; i++)
{
char currentCharacter = inputAsArray[i];
int currentCodePoint = inputAsArray[i];
char[] tweekedValue;
// Check for invalid values
if (currentCodePoint == 0xFFFE ||
currentCodePoint == 0xFFFF)
{
throw new InvalidUnicodeValueException(currentCodePoint);
}
else if (currentCharacter.IsHighSurrogate())
{
if (i + 1 == inputLength)
{
throw new InvalidSurrogatePairException(currentCharacter, '\0');
}
// Now peak ahead and check if the following character is a low surrogate.
char nextCharacter = inputAsArray[i + 1];
char nextCodePoint = inputAsArray[i + 1];
if (!nextCharacter.IsLowSurrogate())
{
throw new InvalidSurrogatePairException(currentCharacter, nextCharacter);
}
// Look-ahead was good, so skip.
i++;
// Calculate the combined code point
long combinedCodePoint =
0x10000 + ((currentCodePoint - 0xD800) * 0x400) + (nextCodePoint - 0xDC00);
char[] encodedCharacter = SafeList.HashThenValueGenerator(combinedCodePoint);
encodedInput[outputLength++] = '&';
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
encodedInput[outputLength++] = ';';
}
else if (currentCharacter.IsLowSurrogate())
{
throw new InvalidSurrogatePairException('\0', currentCharacter);
}
else if (encoderTweak != null && encoderTweak(currentCharacter, out tweekedValue))
{
for (int j = 0; j < tweekedValue.Length; j++)
{
encodedInput[outputLength++] = tweekedValue[j];
}
}
else if (useNamedEntities && namedEntities[currentCodePoint] != null)
{
char[] encodedCharacter = namedEntities[currentCodePoint];
encodedInput[outputLength++] = '&';
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
encodedInput[outputLength++] = ';';
}
else if (characterValues[currentCodePoint] != null)
{
// character needs to be encoded
char[] encodedCharacter = characterValues[currentCodePoint];
encodedInput[outputLength++] = '&';
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
encodedInput[outputLength++] = ';';
}
else
{
// character does not need encoding
encodedInput[outputLength++] = currentCharacter;
}
}
}
finally
{
SyncLock.ExitReadLock();
}
return(new string(encodedInput, 0, outputLength));
}
/// <summary>
/// Encodes according to the CSS encoding rules.
/// </summary>
/// <param name="input">The string to encode.</param>
/// <returns>The encoded string.</returns>
/// <exception cref="InvalidUnicodeValueException">Thrown if a character with an invalid Unicode value is encountered within the input string.</exception>
/// <exception cref="InvalidSurrogatePairException">Thrown if a high surrogate code point is encoded without a following low surrogate code point, or a
/// low surrogate code point is encounter without having been preceded by a high surrogate code point.</exception>
internal static string Encode(string input)
{
if (string.IsNullOrEmpty(input))
{
return(input);
}
if (characterValues == null)
{
InitialiseSafeList();
}
// Setup a new character array for output.
char[] inputAsArray = input.ToCharArray();
int outputLength = 0;
int inputLength = inputAsArray.Length;
char[] encodedInput = new char[inputLength * 7]; // Worse case scenario - CSS encoding wants \XXXXXX for encoded characters.
syncLock.EnterReadLock();
try
{
for (int i = 0; i < inputLength; i++)
{
char currentCharacter = inputAsArray[i];
int currentCodePoint = inputAsArray[i];
// Check for invalid values
if (currentCodePoint == 0xFFFE ||
currentCodePoint == 0xFFFF)
{
throw new InvalidUnicodeValueException(currentCodePoint);
}
else if (currentCharacter.IsHighSurrogate())
{
if (i + 1 == inputLength)
{
throw new InvalidSurrogatePairException(currentCharacter, '\0');
}
// Now peak ahead and check if the following character is a low surrogate.
char nextCharacter = inputAsArray[i + 1];
char nextCodePoint = inputAsArray[i + 1];
if (!nextCharacter.IsLowSurrogate())
{
throw new InvalidSurrogatePairException(currentCharacter, nextCharacter);
}
// Look-ahead was good, so skip.
i++;
// Calculate the combined code point
long combinedCodePoint =
0x10000 + ((currentCodePoint - 0xD800) * 0x400) + (nextCodePoint - 0xDC00);
char[] encodedCharacter = SafeList.SlashThenSixDigitHexValueGenerator(combinedCodePoint);
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
}
else if (currentCharacter.IsLowSurrogate())
{
throw new InvalidSurrogatePairException('\0', currentCharacter);
}
else if (currentCodePoint > characterValues.Length - 1)
{
char[] encodedCharacter = SafeList.SlashThenSixDigitHexValueGenerator(currentCodePoint);
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
}
else if (characterValues[currentCodePoint] != null)
{
// character needs to be encoded
char[] encodedCharacter = characterValues[currentCodePoint];
for (int j = 0; j < encodedCharacter.Length; j++)
{
encodedInput[outputLength++] = encodedCharacter[j];
}
}
else
{
// character does not need encoding
encodedInput[outputLength++] = currentCharacter;
}
}
}
finally
{
syncLock.ExitReadLock();
}
return(new string(encodedInput, 0, outputLength));
}
