public void testNormalScenario()
{
TagExtractor extractor = new TagExtractor("abstract", 10);
Assert.AreEqual(extractor.count(), 0);
LangProfile profile = new LangProfile("en");
// normal
extractor.setTag("abstract");
extractor.add("This is a sample text.");
profile.update(extractor.closeTag());
Assert.AreEqual(extractor.count(), 1);
Assert.AreEqual(profile.n_words[0], 17); // Thisisasampletext
Assert.AreEqual(profile.n_words[1], 22); // _T, Th, hi, ...
Assert.AreEqual(profile.n_words[2], 17); // _Th, Thi, his, ...
// too short
extractor.setTag("abstract");
extractor.add("sample");
profile.update(extractor.closeTag());
Assert.AreEqual(extractor.count(), 1);
// other tags
extractor.setTag("div");
extractor.add("This is a sample text which is enough long.");
profile.update(extractor.closeTag());
Assert.AreEqual(extractor.count(), 1);
}
