void read(Tokeniser t, CharacterReader r) {
if (r.matchesLetter()) {
t.createTagPending(false);
t.tagPending.appendTagName(Character.toLowerCase(r.current()));
t.dataBuffer.append(r.current());
t.advanceTransition(ScriptDataEscapedEndTagName);
} else {
t.emit("</");
t.transition(ScriptDataEscaped);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matchesLetter()) {
t.createTempBuffer();
t.dataBuffer.append(Character.toLowerCase(r.current()));
t.emit("<" + r.current());
t.advanceTransition(ScriptDataDoubleEscapeStart);
} else if (r.matches('/')) {
t.createTempBuffer();
t.advanceTransition(ScriptDataEscapedEndTagOpen);
} else {
t.emit('<');
t.transition(ScriptDataEscaped);
}
}
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);
}
}
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);
}
}
void read(Tokeniser t, CharacterReader r) {
switch (r.current()) {
case nullChar:
t.error(this);
r.advance();
t.emit(replacementChar);
break;
case eof:
t.emit(new Token.EOF());
break;
default:
String data = r.consumeTo(nullChar);
t.emit(data);
break;
}
}
void read(Tokeniser t, CharacterReader r) {
switch (r.current()) {
case '<':
t.advanceTransition(ScriptDataLessthanSign);
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;
}
}
void read(Tokeniser t, CharacterReader r) {
char c = r.current();
switch (c) {
case '-':
t.advanceTransition(CommentEndDash);
break;
case nullChar:
t.error(this);
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));
}
}
// in data state, gather characters until a character reference or tag is found
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;
}
}
// from < in data
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;
}
}
