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);
}
}
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) {
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);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matchesLetter()) {
String name = r.consumeLetterSequence();
t.dataBuffer.append(name.toLowerCase());
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);
}
}
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) {
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) {
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.consume()) {
case '/':
t.createTempBuffer();
t.transition(ScriptDataEndTagOpen);
break;
case '!':
t.emit("<!");
t.transition(ScriptDataEscapeStart);
break;
default:
t.emit("<");
r.unconsume();
t.transition(ScriptData);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matches('-')) {
t.emit('-');
t.advanceTransition(ScriptDataEscapedDashDash);
} else {
t.transition(ScriptData);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matchesLetter()) {
t.createTagPending(false);
t.transition(ScriptDataEndTagName);
} else {
t.emit("</");
t.transition(ScriptData);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matches('/')) {
t.createTempBuffer();
t.advanceTransition(RawtextEndTagOpen);
} else {
t.emit('<');
t.transition(Rawtext);
}
}
void read(Tokeniser t, CharacterReader r) {
if (r.matches('/')) {
t.emit('/');
t.createTempBuffer();
t.advanceTransition(ScriptDataDoubleEscapeEnd);
} else {
t.transition(ScriptDataDoubleEscaped);
}
}
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) {
// 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);
}
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);
}
}
// 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;
}
}
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 rcdata
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 < 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;
}
}
void read(Tokeniser t, CharacterReader r) {
String data = r.consumeTo("]]>");
t.emit(data);
r.matchConsume("]]>");
t.transition(Data);
}
void read(Tokeniser t, CharacterReader r) {
Character c = t.consumeCharacterReference(null, false);
if (c == null) t.emit('&');
else t.emit(c);
t.transition(Rcdata);
}
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);
}
