public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
for (;;)
{
int c = Read(reader);
switch (c)
{
case '&':
CharacterReferenceInDataState.Instance.Process(tokenizer, reader, null);
break;
case '<':
return TagOpenState.Instance;
case '\0':
ReportParseError();
tokenizer.EmitChar('\0');
break;
case -1:
tokenizer.EmitToken(new EndOfFileToken());
return null;
default:
tokenizer.EmitChar((char)c);
return this; // Required to allow switching the state.
}
}
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
switch (c)
{
case '&':
return CharacterReferenceInRCDATAState.Instance;
case '<':
return RCDATALessThanSignState.Instance;
case 0:
ReportParseError();
tokenizer.EmitChar('\uFFFD');
return this;
case -1:
tokenizer.EmitToken(new EndOfFileToken());
return this;
default:
tokenizer.EmitChar((char)c);
return this;
}
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
if (base.IsUppercaseAsciiLetter(c))
{
EndTagToken token = new EndTagToken(){ TagName = Char.ToLower((char)c).ToString() };
//Create a new end tag token, and set its tag name to the lowercase version of the current input
//character (add 0x0020 to the character's code point).
//Append the current input character to the temporary buffer. (http://www.w3.org/TR/html5/syntax.html#temporary-buffer)
//Finally, switch to the RCDATA end tag name state. (Don't emit the token yet;
//further details will be filled in before it is emitted.)
tokenizer.TemporaryBuffer.Add((char)c);
RCDATAEndTagNameState.Instance.Token = token;
return RCDATAEndTagNameState.Instance;
}
if (base.IsLowercaseAsciiLetter(c))
{
EndTagToken token = new EndTagToken(){ TagName = ((char)c).ToString() };
//Create a new end tag token, and set its tag name to the current input character.
//Append the current input character to the temporary buffer. (http://www.w3.org/TR/html5/syntax.html#temporary-buffer)
//Finally, switch to the RCDATA end tag name state. (Don't emit the token yet;
//further details will be filled in before it is emitted.)
tokenizer.TemporaryBuffer.Add((char)c);
RCDATAEndTagNameState.Instance.Token = token;
return RCDATAEndTagNameState.Instance;
}
tokenizer.EmitChar('<');
tokenizer.EmitChar('/');
LastConsumedCharacters.Enqueue((char)c);
return RCDATAState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
if (IsWhitespace(c))
{
if (tokenizer.IsAppropriateEndTagToken(Token))
{
return BeforeAttributeNameState.Instance;
}
}
else if (c == '/')
{
if (tokenizer.IsAppropriateEndTagToken(Token))
{
return SelfClosingStartTagState.Instance;
}
}
else if (c == '>')
{
if (tokenizer.IsAppropriateEndTagToken(Token))
{
tokenizer.EmitToken(Token); // TODO - is this the right token to emit?
return DataState.Instance;
}
}
else if (IsUppercaseAsciiLetter(c))
{
Token.TagName += Char.ToLower((char)c);
tokenizer.TemporaryBuffer.Add((char)c);
return this;
}
else if (IsLowercaseAsciiLetter(c))
{
Token.TagName += (char)c;
tokenizer.TemporaryBuffer.Add((char)c);
return this;
}
tokenizer.EmitChar('<');
tokenizer.EmitChar('/');
foreach (char bc in tokenizer.TemporaryBuffer)
{
tokenizer.EmitChar(bc);
}
RCDATAState.Instance.LastConsumedCharacters.Enqueue((char)c);
return RCDATAState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, System.IO.StreamReader reader)
{
for (;;){
int c = Read(reader);
switch(c)
{
case 0:
ReportParseError();
tokenizer.EmitChar('\uFFFD');
break;
case -1:
tokenizer.EmitToken(new EndOfFileToken());
break;
default:
tokenizer.EmitChar((char)c);
return this;
}
}
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
if (c == '/')
{
tokenizer.TemporaryBuffer.Clear();
return RCDATAEndTagOpenState.Instance;
}
tokenizer.EmitChar('<');
LastConsumedCharacters.Enqueue((char)c);
return RCDATAState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
char c = (char)Read(reader);
if (c == '!')
{
return MarkupDeclarationOpenState.Instance;
}
if (c == '/')
{
return EndTagOpenState.Instance;
}
if (base.IsUppercaseAsciiLetter(c))
{
StartTagToken token = new StartTagToken();
token.TagName = Char.ToLower(c).ToString();
TagNameState.Instance.Token = token;
return TagNameState.Instance;
}
if (base.IsLowercaseAsciiLetter(c))
{
StartTagToken token = new StartTagToken();
token.TagName = ((char)c).ToString();
TagNameState.Instance.Token = token;
return TagNameState.Instance;
}
if (c == '?')
{
ReportParseError();
return BogusCommentState.Instance;
}
ReportParseError();
tokenizer.EmitChar(c);
DataState.Instance.LastConsumedCharacters.Enqueue(c);
return DataState.Instance;
}
public BaseState Process(HtmlTokenizer tokenizer, StreamReader reader, char? additionalAllowedCharacter)
{
// Switch to the data state.
// Attempt to consume a character reference, with no additional allowed character.
// (http://www.w3.org/TR/html5/syntax.html#tokenizing-character-references)
// (http://www.w3.org/TR/html5/syntax.html#additional-allowed-character)
//
// If nothing is returned, emit a U+0026 AMPERSAND character (&) token.
// Otherwise, emit the character tokens that were returned.
int c = Peek(reader);
if (c == 9 || c == 0x0A || c == 0x0C || c == ' ' || c == '<' || c == -1 ||
additionalAllowedCharacter.HasValue && c == additionalAllowedCharacter.Value)
{
} else if (c == '#')
{
Read(reader);
int nc = Peek(reader);
uint? val = null;
if (nc == 'X' || nc == 'x')
{
Read(reader);
val = ConsumeHexDigits(reader);
// http://www.w3.org/TR/html5/infrastructure.html#ascii-hex-digits
} else
{
val = ConsumeDigits(reader);
}
if (val.HasValue)
{
char parsedChar = GetCharFromNumericValue(val.Value);
tokenizer.EmitChar(parsedChar);
} else
{
tokenizer.EmitChar('&');
}
} else
{
// Consume the maximum number of characters possible, with the consumed characters matching one of the identifiers in the first column of the named character references table (in a case-sensitive manner).
// If no match can be made, then no characters are consumed, and nothing is returned. In this case, if the characters after the U+0026 AMPERSAND character (&) consist of a sequence of one or more alphanumeric ASCII characters followed by a U+003B SEMICOLON character (;), then this is a parse error.
// If the character reference is being consumed as part of an attribute, and the last character matched is not a ";" (U+003B) character, and the next character is either a "=" (U+003D) character or an alphanumeric ASCII character, then, for historical reasons, all the characters that were matched after the U+0026 AMPERSAND character (&) must be unconsumed, and nothing is returned. However, if this next character is in fact a "=" (U+003D) character, then this is a parse error, because some legacy user agents will misinterpret the markup in those cases.
// Otherwise, a character reference is parsed. If the last character matched is not a ";" (U+003B) character, there is a parse error.
// Return one or two character tokens for the character(s) corresponding to the character reference name (as given by the second column of the named character references table).
//
// Code Example:
// If the markup contains (not in an attribute) the string "I'm ¬it; I tell you", the character reference is
// parsed as "not", as in, "I'm ¬it; I tell you" (and this is a parse error). But if the markup was
// "I'm ∉ I tell you", the character reference would be parsed as "notin;", resulting in "I'm ∉ I tell you"
// (and no parse error).
}
return DataState.Instance;
}