// in data state, gather characters until a character reference or tag is found
public override void Read(Tokeniser t, CharacterReader r)
{
switch (r.Current())
{
case '&':
t.AdvanceTransition(CharacterReferenceInData);
break;
case '<':
t.AdvanceTransition(TagOpen);
break;
case _nullChar:
t.Error(this); // NOT replacement character (oddly?)
t.Emit(r.Consume());
break;
case _eof:
t.Emit(new Token.EOF());
break;
default:
string data = r.ConsumeToAny('&', '<', _nullChar);
t.Emit(data);
break;
}
}
/// handles data in title, textarea etc
public override void Read(Tokeniser t, CharacterReader r)
{
switch (r.Current())
{
case '&':
t.AdvanceTransition(CharacterReferenceInRcData);
break;
case '<':
t.AdvanceTransition(RcDataLessThanSign);
break;
case _nullChar:
t.Error(this);
r.Advance();
t.Emit(_replacementChar);
break;
case _eof:
t.Emit(new Token.EOF());
break;
default:
string data = r.ConsumeToAny('&', '<', _nullChar);
t.Emit(data);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.Matches('/'))
{
t.Emit('/');
t.CreateTempBuffer();
t.AdvanceTransition(ScriptDataDoubleEscapeEnd);
}
else
{
t.Transition(ScriptDataDoubleEscaped);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Current();
switch (c)
{
case '-':
t.Emit(c);
t.AdvanceTransition(ScriptDataDoubleEscapedDash);
break;
case '<':
t.Emit(c);
t.AdvanceTransition(ScriptDataDoubleEscapedLessthanSign);
break;
case _nullChar:
t.Error(this);
r.Advance();
t.Emit(_replacementChar);
break;
case _eof:
t.EofError(this);
t.Transition(Data);
break;
default:
string data = r.ConsumeToAny('-', '<', _nullChar);
t.Emit(data);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.MatchesLetter())
{
t.CreateTagPending(false);
t.TagPending.AppendTagName(char.ToLowerInvariant(r.Current()));
t.DataBuffer.Append(r.Current());
t.AdvanceTransition(ScriptDataEscapedEndTagName);
}
else
{
t.Emit("</");
t.Transition(ScriptDataEscaped);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.MatchesLetter())
{
t.CreateTempBuffer();
t.DataBuffer.Append(char.ToLowerInvariant(r.Current()));
t.Emit("<" + r.Current());
t.AdvanceTransition(ScriptDataDoubleEscapeStart);
}
else if (r.Matches('/'))
{
t.CreateTempBuffer();
t.AdvanceTransition(ScriptDataEscapedEndTagOpen);
}
else
{
t.Emit('<');
t.Transition(ScriptDataEscaped);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.IsEmpty())
{
t.EofError(this);
t.Transition(Data);
return;
}
switch (r.Current())
{
case '-':
t.Emit('-');
t.AdvanceTransition(ScriptDataEscapedDash);
break;
case '<':
t.AdvanceTransition(ScriptDataEscapedLessThanSign);
break;
case _nullChar:
t.Error(this);
r.Advance();
t.Emit(_replacementChar);
break;
default:
string data = r.ConsumeToAny('-', '<', _nullChar);
t.Emit(data);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.Matches('-'))
{
t.Emit('-');
t.AdvanceTransition(ScriptDataEscapedDashDash);
}
else
{
t.Transition(ScriptData);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.Matches('/'))
{
t.CreateTempBuffer();
t.AdvanceTransition(RawTextEndTagOpen);
}
else
{
t.Emit('<');
t.Transition(RawText);
}
}
// from < in rcdata
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.Matches('/'))
{
t.CreateTempBuffer();
t.AdvanceTransition(RcDataEndTagOpen);
}
else if (r.MatchesLetter() && !r.ContainsIgnoreCase("</" + t.AppropriateEndTagName()))
{
// diverge from spec: got a start tag, but there's no appropriate end tag (</title>), so rather than
// consuming to EOF; break out here
t.TagPending = new Token.EndTag(t.AppropriateEndTagName());
t.EmitTagPending();
r.Unconsume(); // undo "<"
t.Transition(Data);
}
else
{
t.Emit("<");
t.Transition(RcData);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.IsEmpty())
{
t.EofError(this);
t.Emit("</");
t.Transition(Data);
}
else if (r.MatchesLetter())
{
t.CreateTagPending(false);
t.Transition(TagName);
}
else if (r.Matches('>'))
{
t.Error(this);
t.AdvanceTransition(Data);
}
else
{
t.Error(this);
t.AdvanceTransition(BogusComment);
}
}
// from < in data
public override void Read(Tokeniser t, CharacterReader r)
{
switch (r.Current())
{
case '!':
t.AdvanceTransition(MarkupDeclarationOpen);
break;
case '/':
t.AdvanceTransition(EndTagOpen);
break;
case '?':
t.AdvanceTransition(BogusComment);
break;
default:
if (r.MatchesLetter())
{
t.CreateTagPending(true);
t.Transition(TagName);
}
else
{
t.Error(this);
t.Emit('<'); // char that got us here
t.Transition(Data);
}
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.IsEmpty())
{
t.EofError(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
return;
}
if (r.MatchesAny('\t', '\n', '\r', '\f', ' '))
{
r.Advance(); // ignore whitespace
}
else if (r.Matches('>'))
{
t.EmitDoctypePending();
t.AdvanceTransition(Data);
}
else if (r.MatchConsumeIgnoreCase("PUBLIC"))
{
t.Transition(AfterDoctypePublicKeyword);
}
else if (r.MatchConsumeIgnoreCase("SYSTEM"))
{
t.Transition(AfterDoctypeSystemKeyword);
}
else
{
t.Error(this);
t.DoctypePending.ForceQuirks = true;
t.AdvanceTransition(BogusDoctype);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Current();
switch (c)
{
case '-':
t.AdvanceTransition(CommentEndDash);
break;
case _nullChar:
t.Error(this);
r.Advance();
t.CommentPending.Data.Append(_replacementChar);
break;
case _eof:
t.EofError(this);
t.EmitCommentPending();
t.Transition(Data);
break;
default:
t.CommentPending.Data.Append(r.ConsumeToAny('-', _nullChar));
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.MatchConsume("--"))
{
t.CreateCommentPending();
t.Transition(CommentStart);
}
else if (r.MatchConsumeIgnoreCase("DOCTYPE"))
{
t.Transition(Doctype);
}
else if (r.MatchConsume("[CDATA["))
{
// todo: should actually check current namepspace, and only non-html allows cdata. until namespace
// is implemented properly, keep handling as cdata
//} else if (!t.currentNodeInHtmlNS() && r.matchConsume("[CDATA[")) {
t.Transition(CDataSection);
}
else
{
t.Error(this);
t.AdvanceTransition(BogusComment); // advance so this character gets in bogus comment data's rewind
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
// todo: handle bogus comment starting from eof. when does that trigger?
// rewind to capture character that lead us here
r.Unconsume();
Token.Comment comment = new Token.Comment();
comment.Data.Append(r.ConsumeTo('>'));
// todo: replace nullChar with replaceChar
t.Emit(comment);
t.AdvanceTransition(Data);
}