public void matches() { CharacterReader r = new CharacterReader("One Two Three"); Assert.IsTrue(r.Matches('O')); Assert.IsTrue(r.Matches("One Two Three")); Assert.IsTrue(r.Matches("One")); Assert.IsFalse(r.Matches("one")); Assert.AreEqual('O', r.Consume()); Assert.IsFalse(r.Matches("One")); Assert.IsTrue(r.Matches("ne Two Three")); Assert.IsFalse(r.Matches("ne Two Three Four")); Assert.AreEqual("ne Two Three", r.ConsumeToEnd()); Assert.IsFalse(r.Matches("ne")); }
public void matchesIgnoreCase() { CharacterReader r = new CharacterReader("One Two Three"); Assert.IsTrue(r.MatchesIgnoreCase("O")); Assert.IsTrue(r.MatchesIgnoreCase("o")); Assert.IsTrue(r.Matches('O')); Assert.IsFalse(r.Matches('o')); Assert.IsTrue(r.MatchesIgnoreCase("One Two Three")); Assert.IsTrue(r.MatchesIgnoreCase("ONE two THREE")); Assert.IsTrue(r.MatchesIgnoreCase("One")); Assert.IsTrue(r.MatchesIgnoreCase("one")); Assert.AreEqual('O', r.Consume()); Assert.IsFalse(r.MatchesIgnoreCase("One")); Assert.IsTrue(r.MatchesIgnoreCase("NE Two Three")); Assert.IsFalse(r.MatchesIgnoreCase("ne Two Three Four")); Assert.AreEqual("ne Two Three", r.ConsumeToEnd()); Assert.IsFalse(r.MatchesIgnoreCase("ne")); }
public char?ConsumeCharacterReference(char?additionalAllowedCharacter, bool inAttribute) { if (_reader.IsEmpty()) { return(null); } if (additionalAllowedCharacter != null && additionalAllowedCharacter == _reader.Current()) { return(null); } if (_reader.MatchesAny('\t', '\n', '\r', '\f', ' ', '<', '&')) { return(null); } _reader.Mark(); if (_reader.MatchConsume("#")) { // numbered bool isHexMode = _reader.MatchConsumeIgnoreCase("X"); string numRef = isHexMode ? _reader.ConsumeHexSequence() : _reader.ConsumeDigitSequence(); if (numRef.Length == 0) { // didn't match anything CharacterReferenceError("Numeric reference with no numerals"); _reader.RewindToMark(); return(null); } if (!_reader.MatchConsume(";")) { CharacterReferenceError("Missing semicolon"); // missing semi } int charval = -1; try { int numbase = isHexMode ? 16 : 10; charval = Convert.ToInt32(numRef, numbase); } catch (FormatException) { } // skip if (charval == -1 || (charval >= 0xD800 && charval <= 0xDFFF) || charval > 0x10FFFF) { CharacterReferenceError("Character outside of valid range"); return(ReplacementChar); } else { // todo: implement number replacement table // todo: check for extra illegal unicode points as parse errors return((char)charval); } } else { // named // get as many letters as possible, and look for matching entities. unconsume backwards till a match is found string nameRef = _reader.ConsumeLetterThenDigitSequence(); bool looksLegit = _reader.Matches(';'); // found if a base named entity without a ;, or an extended entity with the ;. bool found = (Entities.IsBaseNamedEntity(nameRef) || (Entities.IsNamedEntity(nameRef) && looksLegit)); if (!found) { _reader.RewindToMark(); if (looksLegit) { CharacterReferenceError(string.Format("Invalid named referenece '{0}'", nameRef)); } return(null); } if (inAttribute && (_reader.MatchesLetter() || _reader.MatchesDigit() || _reader.MatchesAny('=', '-', '_'))) { // don't want that to match _reader.RewindToMark(); return(null); } if (!_reader.MatchConsume(";")) { CharacterReferenceError("Missing semicolon"); // missing semi } return(Entities.GetCharacterByName(nameRef)); } }
public void consumeToAny() { CharacterReader r = new CharacterReader("One &bar; qux"); Assert.AreEqual("One ", r.ConsumeToAny('&', ';')); Assert.IsTrue(r.Matches('&')); Assert.IsTrue(r.Matches("&bar;")); Assert.AreEqual('&', r.Consume()); Assert.AreEqual("bar", r.ConsumeToAny('&', ';')); Assert.AreEqual(';', r.Consume()); Assert.AreEqual(" qux", r.ConsumeToAny('&', ';')); }
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.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); } }
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); } }
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); } }