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.bogus = true; comment.data.append(r.consumeTo('>')); // todo: replace nullChar with replaceChar t.emit(comment); t.advanceTransition(Data); } },
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.matches('-')) { t.emit('-'); t.advanceTransition(ScriptDataEscapeStartDash); } else { t.transition(ScriptData); } } },
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) { if (r.matches('/')) { t.emit('/'); t.createTempBuffer(); t.advanceTransition(ScriptDataDoubleEscapeEnd); } else { t.transition(ScriptDataDoubleEscaped); } } },
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.matchesLetter()) { t.createTempBuffer(); t.dataBuffer.append(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) { if (r.matchesLetter()) { t.createTagPending(false); t.tagPending.appendTagName(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.createTagPending(false); t.tagPending.appendTagName(r.current()); t.dataBuffer.append(r.current()); t.advanceTransition(RCDATAEndTagName); } else { t.emit("</"); t.transition(Rcdata); } } },
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)); } } },
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.consumeData(); t.emit(data); break; } } },
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; } } },
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); } } },
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) { 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.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(DocumentType.PUBLIC_KEY)) { t.doctypePending.pubSysKey = DocumentType.PUBLIC_KEY; t.transition(AfterDoctypePublicKeyword); } else if (r.matchConsumeIgnoreCase(DocumentType.SYSTEM_KEY)) { t.doctypePending.pubSysKey = DocumentType.SYSTEM_KEY; t.transition(AfterDoctypeSystemKeyword); } else { t.error(this); t.doctypePending.forceQuirks = true; t.advanceTransition(BogusDoctype); } } },
private static void readData(Tokeniser t, CharacterReader r, TokeniserState current, TokeniserState advance) { switch (r.current()) { case '<': t.advanceTransition(advance); break; case nullChar: t.error(current); r.advance(); t.emit(replacementChar); break; case eof: t.emit(new Token.EOF()); break; default: String data = r.consumeToAny('<', nullChar); // todo - why hunt for null here? Just consumeTo'<'? t.emit(data); break; } }
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.createTempBuffer(); t.transition(CdataSection); } else { t.error(this); t.advanceTransition(BogusComment); // advance so this character gets in bogus comment data's rewind } } },
void read(Tokeniser t, CharacterReader r) { if (r.matches('/')) { t.createTempBuffer(); t.advanceTransition(RCDATAEndTagOpen); } else if (r.matchesLetter() && t.appropriateEndTagName() != null && !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 = t.createTagPending(false).name(t.appropriateEndTagName()); t.emitTagPending(); r.unconsume(); // undo "<" t.transition(Data); } else { t.emit("<"); t.transition(Rcdata); } } },