public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c;
do
{
c = Read(reader);
} while (IsWhitespace(c));
if (c == '>')
{
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (c == -1)
{
ReportParseError();
Token.ForceQuirks = true;
tokenizer.EmitToken(Token);
return DataState.Instance;
// Reconsume the EOF character (?)
}
ReportParseError();
return BogusDocTypeState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
switch (c)
{
case '-':
return CommentStartDashState.Instance;
case 0:
ReportParseError();
Token.Comment += '\uFFFD';
CommentState.Instance.Token = Token;
return CommentState.Instance;
case '>':
ReportParseError();
tokenizer.EmitToken(Token);
return DataState.Instance;
case -1:
ReportParseError();
tokenizer.EmitToken(Token);
return DataState.Instance;
// Reconsume the EOF character (?)
default:
Token.Comment += (char)c;
CommentState.Instance.Token = Token;
return CommentState.Instance;
}
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c;
do
{
c = Read(reader);
} while (IsWhitespace(c));
if (c == '>')
{
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (c == -1)
{
// Parse error. Switch to the data state. Set the DOCTYPE token's force-quirks flag to on. Emit that DOCTYPE token. Reconsume the EOF character.
ReportParseError();
Token.ForceQuirks = true;
tokenizer.EmitToken(Token);
return DataState.Instance;
}
char[] buffer = new char[6];
buffer[0] = (char)c;
ReadBlock(reader, buffer, 1, 5);
string bufferStr = new string(buffer);
// If the six characters starting from the current input character are an ASCII case-insensitive match for the
// word "PUBLIC", then consume those characters and switch to the after DOCTYPE public keyword state.
if (bufferStr.Equals("public", StringComparison.OrdinalIgnoreCase))
{
AfterDocTypePublicKeywordState.Instance.Token = Token;
return AfterDocTypePublicKeywordState.Instance;
}
// Otherwise, if the six characters starting from the current input character are an ASCII case-insensitive match
// for the word "SYSTEM", then consume those characters and switch to the after DOCTYPE system keyword state.
if (bufferStr.Equals("system", StringComparison.OrdinalIgnoreCase))
{
return AfterDocTypeSystemKeywordState.Instance;
}
// Otherwise, this is a parse error. Set the DOCTYPE token's force-quirks flag to on. Switch to the bogus DOCTYPE
// state.
reader.BaseStream.Seek(-6, SeekOrigin.Current);
ReportParseError();
Token.ForceQuirks = true;
BogusCommentState.Instance.Comment.Append(bufferStr);
return BogusCommentState.Instance;
}
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)
{
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);
if (IsWhitespace(c))
{
BeforeAttributeNameState.Instance.Token = Token.ContainingTag;
return BeforeAttributeNameState.Instance;
}
if (c == '/')
{
SelfClosingStartTagState.Instance.Token = Token.ContainingTag;
return SelfClosingStartTagState.Instance;
}
if (c == '>')
{
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (c == -1)
{
ReportParseError();
return DataState.Instance;
//reconsume...
}
ReportParseError();
BeforeAttributeNameState.Instance.Token = Token.ContainingTag;
BeforeDocTypeNameState.Instance.LastConsumedCharacters.Enqueue((char)c);
return BeforeAttributeNameState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c = Read(reader);
if (IsWhitespace(c))
{
BeforeDocTypePublicIdentifierState.Instance.Token = Token;
return BeforeDocTypePublicIdentifierState.Instance;
}
if (c == '"')
{
ReportParseError();
Token.PublicIdentifier = string.Empty;
DocTypePublicIdentifierQuotedState.InstanceDoubleQuoted.Token = Token;
return DocTypePublicIdentifierQuotedState.InstanceDoubleQuoted;
}
if (c == '\'')
{
ReportParseError();
Token.PublicIdentifier = string.Empty;
DocTypePublicIdentifierQuotedState.InstanceSingleQuoted.Token = Token;
return DocTypePublicIdentifierQuotedState.InstanceSingleQuoted;
}
if (c == '>')
{
ReportParseError();
Token.ForceQuirks = true;
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (c == -1)
{
ReportParseError();
Token.ForceQuirks = true;
tokenizer.EmitToken(Token);
return DataState.Instance;
// Reconsume the EOF character. (?)
}
ReportParseError();
Token.ForceQuirks = true;
BogusDocTypeState.Instance.Token = Token;
return BogusDocTypeState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
for (;;)
{
int c = Read(reader);
if (IsWhitespace(c))
{
AfterDocTypeNameState.Instance.Token = Token;
return AfterDocTypeNameState.Instance;
}
if (c == '>')
{
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (base.IsUppercaseAsciiLetter(c))
{
// Append the lowercase version of the current input character (add 0x0020 to the character's code point) to the current tag token's tag name.
Token.Name += Char.ToLower((char)c);
continue;
}
if (c == 0)
{
// Parse error. Append a U+FFFD REPLACEMENT CHARACTER character to the current tag token's tag name.
ReportParseError();
Token.Name += "\uFFFD";
continue;
}
if (c == -1)
{
// Parse error. Switch to the data state. Reconsume the EOF character.
ReportParseError();
Token.ForceQuirks = true;
tokenizer.EmitToken(Token);
return DataState.Instance;
}
// Append the current input character to the current tag token's tag name.
Token.Name += (char)c;
}
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c;
do
{
c = Read(reader);
} while (IsWhitespace(c));
if (c == '"')
{
AttributeValueQuotedState.InstanceDoubleQuoted.Token = Token;
return AttributeValueQuotedState.InstanceDoubleQuoted;
}
if (c == '&')
{
AttributeValueUnquotedState.Instance.Token = Token;
AttributeValueUnquotedState.Instance.LastConsumedCharacters.Enqueue((char)c);
return AttributeValueUnquotedState.Instance;
}
if (c == '\'')
{
AttributeValueQuotedState.InstanceSingleQuoted.Token = Token;
return AttributeValueQuotedState.InstanceSingleQuoted;
}
if (c == 0)
{
ReportParseError();
Token.AttributeValue += "\uFFFD";
AttributeValueUnquotedState.Instance.Token = Token;
return AttributeValueUnquotedState.Instance;
}
if (c == '>')
{
ReportParseError();
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (c == -1)
{
ReportParseError();
return DataState.Instance; //reconsume... ?
}
if (c == '<' || c == '=' || c == '`')
{
ReportParseError();
}
Token.AttributeValue += (char)c;
AttributeValueUnquotedState.Instance.Token = Token;
return AttributeValueUnquotedState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
int c;
do
{
c = Read(reader);
} while (IsWhitespace(c));
DocTypeToken token = new DocTypeToken();
DocTypeNameState.Instance.Token = token;
if (base.IsUppercaseAsciiLetter(c))
{
token.Name = Char.ToLower((char)c).ToString();
return DocTypeNameState.Instance;
}
if (c == 0)
{
ReportParseError();
token.Name = "\uFFFD";
return DocTypeNameState.Instance;
}
if (c == '>')
{
ReportParseError();
token.ForceQuirks = true;
tokenizer.EmitToken(token);
return DataState.Instance;
}
if (c == -1)
{
ReportParseError();
token.ForceQuirks = true;
tokenizer.EmitToken(token);
return DataState.Instance;
// Parse error. Switch to the data state. Reconsume the EOF character.
}
token.Name = ((char)c).ToString();
return DocTypeNameState.Instance;
}
public override BaseState Process(HtmlTokenizer tokenizer, StreamReader reader)
{
for (;;)
{
int c = Read(reader);
switch (c)
{
case '>':
tokenizer.EmitToken(Token);
return DataState.Instance;
case 0:
ReportParseError();
Token.Comment += "--\uFFFD";
CommentState.Instance.Token = Token;
return CommentState.Instance;
case '!':
ReportParseError();
CommentEndBangState.Instance.Token = Token;
return CommentEndBangState.Instance;
case '-':
ReportParseError();
Token.Comment += "-";
break;
case -1:
ReportParseError();
tokenizer.EmitToken(Token);
return DataState.Instance;
//Reconsume the EOF character (?)
default:
ReportParseError();
Token.Comment += "--" + (char)c;
CommentState.Instance.Token = Token;
return CommentState.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)
{
AttributeToken attrToken = null;
int c;
do
{
c = Read(reader);
} while (IsWhitespace(c));
if (c == '/')
{
return SelfClosingStartTagState.Instance;
}
if (c == '>')
{
tokenizer.EmitToken(Token);
return DataState.Instance;
}
if (base.IsUppercaseAsciiLetter(c))
{
attrToken = new AttributeToken() {
AttributeName = Char.ToLower((char)c).ToString(),
AttributeValue = string.Empty,
ContainingTag = Token
};
Token.Attributes.Add(attrToken);
AttributeNameState.Instance.Token = attrToken;
return AttributeNameState.Instance;
}
if (c == 0)
{
ReportParseError();
attrToken = new AttributeToken() {
AttributeName = "\uFFFD",
AttributeValue = string.Empty,
ContainingTag = Token
};
Token.Attributes.Add(attrToken);
AttributeNameState.Instance.Token = attrToken;
return AttributeNameState.Instance;
}
if (c == -1)
{
ReportParseError();
return DataState.Instance;
// Reconsume the EOF character (?)
}
if (c == '"' || c == '\'' || c == '<' || c == '=')
{
ReportParseError();
}
attrToken = new AttributeToken() {
AttributeName = ((char)c).ToString(),
AttributeValue = string.Empty,
ContainingTag = Token
};
Token.Attributes.Add(attrToken);
AttributeNameState.Instance.Token = attrToken;
return AttributeNameState.Instance;
}
