use of org.dkpro.tc.features.pair.core.length.DiffNrOfTokensPairFeatureExtractor in project dkpro-tc by dkpro.
the class DiffNrOfTokensPairFeatureExtractorTest method testExtract.
@Test
public void testExtract() throws ResourceInitializationException, AnalysisEngineProcessException, TextClassificationException {
AnalysisEngineDescription desc = createEngineDescription(BreakIteratorSegmenter.class);
AnalysisEngine engine = createEngine(desc);
JCas jcas1 = engine.newJCas();
jcas1.setDocumentLanguage("en");
jcas1.setDocumentText("This is the text of view 1. And some more.");
engine.process(jcas1);
JCas jcas2 = engine.newJCas();
jcas2.setDocumentLanguage("en");
jcas2.setDocumentText("This is the text of view 2.");
engine.process(jcas2);
DiffNrOfTokensPairFeatureExtractor extractor = new DiffNrOfTokensPairFeatureExtractor();
Set<Feature> features = extractor.extract(jcas1, jcas2);
assertEquals(1, features.size());
for (Feature feature : features) {
assertFeature("DiffNrOfTokens", 4, feature);
}
}
Aggregations