// from & in data
public override void Read(Tokeniser t, CharacterReader r)
{
char? c = t.ConsumeCharacterReference(null, false);
if (c == null)
{
t.Emit('&');
}
else
{
t.Emit(c.Value);
}
t.Transition(Data);
}
protected ParseErrorList _errors; // null when not tracking errors
protected virtual void InitialiseParse(string input, string baseUri, ParseErrorList errors)
{
if (input == null)
{
throw new ArgumentNullException("String input must not be null");
}
if (baseUri == null)
{
throw new ArgumentNullException("BaseURI must not be null");
}
_doc = new Document(baseUri);
_reader = new CharacterReader(input);
_errors = errors;
_tokeniser = new Tokeniser(_reader, errors);
_stack = new DescendableLinkedList<Element>();
this._baseUri = baseUri;
}
protected ParseErrorList _errors; // null when not tracking errors
protected virtual void InitialiseParse(string input, string baseUri, ParseErrorList errors)
{
if (input == null)
{
throw new ArgumentNullException("String input must not be null");
}
if (baseUri == null)
{
throw new ArgumentNullException("BaseURI must not be null");
}
_doc = new Document(baseUri);
_reader = new CharacterReader(input);
_errors = errors;
_tokeniser = new Tokeniser(_reader, errors);
_stack = new DescendableLinkedList <Element>();
this._baseUri = baseUri;
}
// 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.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)
{
char c = r.Consume();
switch (c)
{
case '>':
t.EmitDoctypePending();
t.Transition(Data);
break;
case _eof:
t.EmitDoctypePending();
t.Transition(Data);
break;
default:
// ignore char
break;
}
}
/// <summary>
/// Utility method to unescape HTML entities from a string
/// </summary>
/// <param name="s">HTML escaped string</param>
/// <param name="inAttribute">If the string is to be escaped in strict mode (as attributes are)</param>
/// <returns>An unescaped string</returns>
public static string UnescapeEntities(string s, bool inAttribute)
{
Tokeniser tokeniser = new Tokeniser(new CharacterReader(s), ParseErrorList.NoTracking());
return(tokeniser.UnescapeEntities(inAttribute));
}
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Consume();
switch (c)
{
case '\'':
t.Transition(AfterDoctypeSystemIdentifier);
break;
case _nullChar:
t.Error(this);
t.DoctypePending.SystemIdentifier.Append(_replacementChar);
break;
case '>':
t.Error(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
break;
case _eof:
t.EofError(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
break;
default:
t.DoctypePending.SystemIdentifier.Append(c);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.MatchesLetter())
{
string name = r.ConsumeLetterSequence();
t.DataBuffer.Append(name.ToLowerInvariant());
t.Emit(name);
return;
}
char c = r.Consume();
switch (c)
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
case '/':
case '>':
if (t.DataBuffer.ToString().Equals("script"))
{
t.Transition(ScriptDataEscaped);
}
else
{
t.Transition(ScriptDataDoubleEscaped);
}
t.Emit(c);
break;
default:
r.Unconsume();
t.Transition(ScriptDataDoubleEscaped);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Consume();
switch (c)
{
case '-':
t.Emit(c);
break;
case '<':
t.Emit(c);
t.Transition(ScriptDataDoubleEscapedLessthanSign);
break;
case '>':
t.Emit(c);
t.Transition(ScriptData);
break;
case _nullChar:
t.Error(this);
t.Emit(_replacementChar);
t.Transition(ScriptDataDoubleEscaped);
break;
case _eof:
t.EofError(this);
t.Transition(Data);
break;
default:
t.Emit(c);
t.Transition(ScriptDataDoubleEscaped);
break;
}
}
private void AnythingElse(Tokeniser t, CharacterReader r)
{
t.Emit("</" + t.DataBuffer.ToString());
t.Transition(ScriptDataEscaped);
}
private void AnythingElse(Tokeniser t, CharacterReader r)
{
t.Emit("</" + t.DataBuffer.ToString());
t.Transition(RawText);
}
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);
}
}
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);
}
}
// from < or </ in data, will have start or end tag pending
public override void Read(Tokeniser t, CharacterReader r)
{
// previous TagOpen state did NOT Consume, will have a letter char in current
string tagName = r.ConsumeToAny('\t', '\n', '\r', '\f', ' ', '/', '>', _nullChar).ToLowerInvariant();
t.TagPending.AppendTagName(tagName);
switch (r.Consume())
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
t.Transition(BeforeAttributeName);
break;
case '/':
t.Transition(SelfClosingStartTag);
break;
case '>':
t.EmitTagPending();
t.Transition(Data);
break;
case _nullChar: // replacement
t.TagPending.AppendTagName(_replacementStr);
break;
case _eof: // should Emit pending tag?
t.EofError(this);
t.Transition(Data);
break;
// no default, as covered with above ConsumeToAny
}
}
public abstract void Read(Tokeniser t, CharacterReader r);
public override void Read(Tokeniser t, CharacterReader r)
{
string data = r.ConsumeTo("]]>");
t.Emit(data);
r.MatchConsume("]]>");
t.Transition(Data);
}
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())
{
string name = r.ConsumeLetterSequence();
t.TagPending.AppendTagName(name.ToLowerInvariant());
t.DataBuffer.Append(name);
return;
}
if (t.IsAppropriateEndTagToken() && !r.IsEmpty())
{
char c = r.Consume();
switch (c)
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
t.Transition(BeforeAttributeName);
break;
case '/':
t.Transition(SelfClosingStartTag);
break;
case '>':
t.EmitTagPending();
t.Transition(Data);
break;
default:
t.DataBuffer.Append(c);
AnythingElse(t, r);
break;
}
}
else
{
AnythingElse(t, r);
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
switch (r.Consume())
{
case '/':
t.CreateTempBuffer();
t.Transition(ScriptDataEndTagOpen);
break;
case '!':
t.Emit("<!");
t.Transition(ScriptDataEscapeStart);
break;
default:
t.Emit("<");
r.Unconsume();
t.Transition(ScriptData);
break;
}
}
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.Transition(ScriptDataEndTagName);
}
else
{
t.Emit("</");
t.Transition(ScriptData);
}
}
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)
{
if (r.Matches('-'))
{
t.Emit('-');
t.AdvanceTransition(ScriptDataEscapedDashDash);
}
else
{
t.Transition(ScriptData);
}
}
// from tagname <xxx
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Consume();
switch (c)
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
break; // ignore whitespace
case '/':
t.Transition(SelfClosingStartTag);
break;
case '>':
t.EmitTagPending();
t.Transition(Data);
break;
case _nullChar:
t.Error(this);
t.TagPending.NewAttribute();
r.Unconsume();
t.Transition(AttributeName);
break;
case _eof:
t.EofError(this);
t.Transition(Data);
break;
case '"':
case '\'':
case '<':
case '=':
t.Error(this);
t.TagPending.NewAttribute();
t.TagPending.AppendAttributeName(c);
t.Transition(AttributeName);
break;
default: // A-Z, anything else
t.TagPending.NewAttribute();
r.Unconsume();
t.Transition(AttributeName);
break;
}
}
public override void Read(Tokeniser t, CharacterReader r)
{
char c = r.Consume();
switch (c)
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
break;
case '"':
// set system id to empty string
t.Transition(DoctypeSystemIdentifierDoubleQuoted);
break;
case '\'':
// set public id to empty string
t.Transition(DoctypeSystemIdentifierSingleQuoted);
break;
case '>':
t.Error(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
break;
case _eof:
t.EofError(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
break;
default:
t.Error(this);
t.DoctypePending.ForceQuirks = true;
t.Transition(BogusDoctype);
break;
}
}
/// <summary>
/// Utility method to unescape HTML entities from a string
/// </summary>
/// <param name="s">HTML escaped string</param>
/// <param name="inAttribute">If the string is to be escaped in strict mode (as attributes are)</param>
/// <returns>An unescaped string</returns>
public static string UnescapeEntities(string s, bool inAttribute) {
Tokeniser tokeniser = new Tokeniser(new CharacterReader(s), ParseErrorList.NoTracking());
return tokeniser.UnescapeEntities(inAttribute);
}
public override void Read(Tokeniser t, CharacterReader r)
{
if (r.IsEmpty())
{
t.EofError(this);
t.Transition(Data);
return;
}
char c = r.Consume();
switch (c)
{
case '-':
t.Emit(c);
t.Transition(ScriptDataEscapedDashDash);
break;
case '<':
t.Transition(ScriptDataEscapedLessThanSign);
break;
case _nullChar:
t.Error(this);
t.Emit(_replacementChar);
t.Transition(ScriptDataEscaped);
break;
default:
t.Emit(c);
t.Transition(ScriptDataEscaped);
break;
}
}
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)
{
char c = r.Consume();
switch (c)
{
case '\t':
case '\n':
case '\r':
case '\f':
case ' ':
break;
case '>':
t.EmitDoctypePending();
t.Transition(Data);
break;
case _eof:
t.EofError(this);
t.DoctypePending.ForceQuirks = true;
t.EmitDoctypePending();
t.Transition(Data);
break;
default:
t.Error(this);
t.Transition(BogusDoctype);
break;
// NOT force quirks
}
}
