public void testNestedToXML () { LabelAlphabet dict = new LabelAlphabet (); String document = "the quick brown fox leapt over the lazy dog"; StringTokenization toks = new StringTokenization (document, new CharSequenceLexer ()); Label O = dict.lookupLabel ("O"); Label ANML = dict.lookupLabel ("ANIMAL"); Label VB = dict.lookupLabel ("VERB"); Label JJ = dict.lookupLabel ("ADJ"); Label MAMMAL = dict.lookupLabel ("MAMMAL"); LabelSequence tags = new LabelSequence (new Label[] { O, ANML, ANML, ANML, VB, O, ANML, ANML, ANML }); LabeledSpans spans = new DefaultTokenizationFilter ().constructLabeledSpans (dict, document, O, toks, tags); Span foxToken = toks.subspan (3, 4); spans.add (new LabeledSpan (foxToken, MAMMAL, false)); Span bigDogToken = toks.subspan (7, 8); spans.add (new LabeledSpan (bigDogToken, JJ, false)); DocumentExtraction extr = new DocumentExtraction ("Test", dict, toks, spans, null, "O"); String actualXml = extr.toXmlString(); String expectedXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\r\n" + "<doc>the <ANIMAL>quick brown <MAMMAL>fox </MAMMAL></ANIMAL><VERB>leapt </VERB>over <ANIMAL>the <ADJ>lazy </ADJ>dog</ANIMAL></doc>\r\n"; assertEquals (expectedXml, actualXml); }
public void testNestedToXML () { LabelAlphabet dict = new LabelAlphabet (); String document = "the quick brown fox leapt over the lazy dog"; StringTokenization toks = new StringTokenization (document, new CharSequenceLexer ()); Label O = dict.lookupLabel ("O"); Label ANML = dict.lookupLabel ("ANIMAL"); Label VB = dict.lookupLabel ("VERB"); Label JJ = dict.lookupLabel ("ADJ"); Label MAMMAL = dict.lookupLabel ("MAMMAL"); LabelSequence tags = new LabelSequence (new Label[] { O, ANML, ANML, ANML, VB, O, ANML, ANML, ANML }); LabeledSpans spans = new DefaultTokenizationFilter ().constructLabeledSpans (dict, document, O, toks, tags); Span foxToken = toks.subspan (3, 4); spans.add (new LabeledSpan (foxToken, MAMMAL, false)); Span bigDogToken = toks.subspan (7, 8); spans.add (new LabeledSpan (bigDogToken, JJ, false)); DocumentExtraction extr = new DocumentExtraction ("Test", dict, toks, spans, null, "O"); String actualXml = extr.toXmlString(); String expectedXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\r\n" + "<doc>the <ANIMAL>quick brown <MAMMAL>fox </MAMMAL></ANIMAL><VERB>leapt </VERB>over <ANIMAL>the <ADJ>lazy </ADJ>dog</ANIMAL></doc>\r\n"; assertEquals (expectedXml, actualXml); }