public virtual void ConsumeToString()
{
CharacterReader r = new CharacterReader("One Two Two Four");
NUnit.Framework.Assert.AreEqual("One ", r.ConsumeTo("Two"));
NUnit.Framework.Assert.AreEqual('T', r.Consume());
NUnit.Framework.Assert.AreEqual("wo ", r.ConsumeTo("Two"));
NUnit.Framework.Assert.AreEqual('T', r.Consume());
NUnit.Framework.Assert.AreEqual("wo Four", r.ConsumeTo("Qux"));
}
// current doc we are building into
// the stack of open elements
// current base uri, for creating new elements
// currentToken is used only for error tracking.
// null when not tracking errors
// start tag to process
internal virtual void InitialiseParse(String input, String baseUri, ParseErrorList errors)
{
Validate.NotNull(input, "String input must not be null");
Validate.NotNull(baseUri, "BaseURI must not be null");
doc = new Document(baseUri);
reader = new CharacterReader(input);
this.errors = errors;
tokeniser = new Tokeniser(reader, errors);
stack = new List <iText.StyledXmlParser.Jsoup.Nodes.Element>(32);
this.baseUri = baseUri;
}
public virtual void MatchesAny()
{
char[] scan = new char[] { ' ', '\n', '\t' };
CharacterReader r = new CharacterReader("One\nTwo\tThree");
NUnit.Framework.Assert.IsFalse(r.MatchesAny(scan));
NUnit.Framework.Assert.AreEqual("One", r.ConsumeToAny(scan));
NUnit.Framework.Assert.IsTrue(r.MatchesAny(scan));
NUnit.Framework.Assert.AreEqual('\n', r.Consume());
NUnit.Framework.Assert.IsFalse(r.MatchesAny(scan));
}
public virtual void Mark()
{
CharacterReader r = new CharacterReader("one");
r.Consume();
r.Mark();
NUnit.Framework.Assert.AreEqual('n', r.Consume());
NUnit.Framework.Assert.AreEqual('e', r.Consume());
NUnit.Framework.Assert.IsTrue(r.IsEmpty());
r.RewindToMark();
NUnit.Framework.Assert.AreEqual('n', r.Consume());
}
public virtual void ConsumeToAny()
{
CharacterReader r = new CharacterReader("One &bar; qux");
NUnit.Framework.Assert.AreEqual("One ", r.ConsumeToAny('&', ';'));
NUnit.Framework.Assert.IsTrue(r.Matches('&'));
NUnit.Framework.Assert.IsTrue(r.Matches("&bar;"));
NUnit.Framework.Assert.AreEqual('&', r.Consume());
NUnit.Framework.Assert.AreEqual("bar", r.ConsumeToAny('&', ';'));
NUnit.Framework.Assert.AreEqual(';', r.Consume());
NUnit.Framework.Assert.AreEqual(" qux", r.ConsumeToAny('&', ';'));
}
public virtual void ConsumeToChar()
{
CharacterReader r = new CharacterReader("One Two Three");
NUnit.Framework.Assert.AreEqual("One ", r.ConsumeTo('T'));
NUnit.Framework.Assert.AreEqual("", r.ConsumeTo('T'));
// on Two
NUnit.Framework.Assert.AreEqual('T', r.Consume());
NUnit.Framework.Assert.AreEqual("wo ", r.ConsumeTo('T'));
NUnit.Framework.Assert.AreEqual('T', r.Consume());
NUnit.Framework.Assert.AreEqual("hree", r.ConsumeTo('T'));
}
public virtual void NextIndexOfString()
{
String @in = "One Two something Two Three Four";
CharacterReader r = new CharacterReader(@in);
NUnit.Framework.Assert.AreEqual(-1, r.NextIndexOf("Foo"));
NUnit.Framework.Assert.AreEqual(4, r.NextIndexOf("Two"));
NUnit.Framework.Assert.AreEqual("One Two ", r.ConsumeTo("something"));
NUnit.Framework.Assert.AreEqual(10, r.NextIndexOf("Two"));
NUnit.Framework.Assert.AreEqual("something Two Three Four", r.ConsumeToEnd());
NUnit.Framework.Assert.AreEqual(-1, r.NextIndexOf("Two"));
}
public virtual void RangeEquals()
{
CharacterReader r = new CharacterReader("Check\tCheck\tCheck\tCHOKE");
NUnit.Framework.Assert.IsTrue(r.RangeEquals(0, 5, "Check"));
NUnit.Framework.Assert.IsFalse(r.RangeEquals(0, 5, "CHOKE"));
NUnit.Framework.Assert.IsFalse(r.RangeEquals(0, 5, "Chec"));
NUnit.Framework.Assert.IsTrue(r.RangeEquals(6, 5, "Check"));
NUnit.Framework.Assert.IsFalse(r.RangeEquals(6, 5, "Chuck"));
NUnit.Framework.Assert.IsTrue(r.RangeEquals(12, 5, "Check"));
NUnit.Framework.Assert.IsFalse(r.RangeEquals(12, 5, "Cheeky"));
NUnit.Framework.Assert.IsTrue(r.RangeEquals(18, 5, "CHOKE"));
NUnit.Framework.Assert.IsFalse(r.RangeEquals(18, 5, "CHIKE"));
}
public virtual void Matches()
{
CharacterReader r = new CharacterReader("One Two Three");
NUnit.Framework.Assert.IsTrue(r.Matches('O'));
NUnit.Framework.Assert.IsTrue(r.Matches("One Two Three"));
NUnit.Framework.Assert.IsTrue(r.Matches("One"));
NUnit.Framework.Assert.IsFalse(r.Matches("one"));
NUnit.Framework.Assert.AreEqual('O', r.Consume());
NUnit.Framework.Assert.IsFalse(r.Matches("One"));
NUnit.Framework.Assert.IsTrue(r.Matches("ne Two Three"));
NUnit.Framework.Assert.IsFalse(r.Matches("ne Two Three Four"));
NUnit.Framework.Assert.AreEqual("ne Two Three", r.ConsumeToEnd());
NUnit.Framework.Assert.IsFalse(r.Matches("ne"));
}
public virtual void NextIndexOfChar()
{
String @in = "blah blah";
CharacterReader r = new CharacterReader(@in);
NUnit.Framework.Assert.AreEqual(-1, r.NextIndexOf('x'));
NUnit.Framework.Assert.AreEqual(3, r.NextIndexOf('h'));
String pull = r.ConsumeTo('h');
NUnit.Framework.Assert.AreEqual("bla", pull);
r.Consume();
NUnit.Framework.Assert.AreEqual(2, r.NextIndexOf('l'));
NUnit.Framework.Assert.AreEqual(" blah", r.ConsumeToEnd());
NUnit.Framework.Assert.AreEqual(-1, r.NextIndexOf('x'));
}
internal Tokeniser(CharacterReader reader, ParseErrorList errors)
{
// html input
// errors found while tokenising
// current tokenisation state
// the token we are about to emit on next read
// characters pending an emit. Will fall to charsBuilder if more than one
// buffers characters to output as one token, if more than one emit per read
// buffers data looking for </script>
// tag we are building up
// doctype building up
// comment building up
// the last start tag emitted, to test appropriate end tag
this.reader = reader;
this.errors = errors;
}
public virtual void Consume()
{
CharacterReader r = new CharacterReader("one");
NUnit.Framework.Assert.AreEqual(0, r.Pos());
NUnit.Framework.Assert.AreEqual('o', r.Current());
NUnit.Framework.Assert.AreEqual('o', r.Consume());
NUnit.Framework.Assert.AreEqual(1, r.Pos());
NUnit.Framework.Assert.AreEqual('n', r.Current());
NUnit.Framework.Assert.AreEqual(1, r.Pos());
NUnit.Framework.Assert.AreEqual('n', r.Consume());
NUnit.Framework.Assert.AreEqual('e', r.Consume());
NUnit.Framework.Assert.IsTrue(r.IsEmpty());
NUnit.Framework.Assert.AreEqual(CharacterReader.EOF, r.Consume());
NUnit.Framework.Assert.IsTrue(r.IsEmpty());
NUnit.Framework.Assert.AreEqual(CharacterReader.EOF, r.Consume());
}
public virtual void NextIndexOfUnmatched()
{
CharacterReader r = new CharacterReader("<[[one]]");
NUnit.Framework.Assert.AreEqual(-1, r.NextIndexOf("]]>"));
}
internal Tokeniser(CharacterReader reader, ParseErrorList errors)
{
this.reader = reader;
this.errors = errors;
}
