コード例 #1
0
        public void Normalize_SimpleSentence()
        {
            var normalizer = new TokenNormalizer();

            var tokens = normalizer.Normalize(new List <string> {
                "This", "is", "a", "sentence", ".", " "
            });

            Assert.AreEqual(4, tokens.Count);
            Assert.AreEqual("this", tokens[0]);
        }
コード例 #2
0
        public void Normalize_GermanCharacters()
        {
            var normalizer = new TokenNormalizer();

            var tokens = normalizer.Normalize(new List <string> {
                "Straße", "München", ".", "Fußgängerübergänge", "Größenmaßstäbe"
            });

            Assert.AreEqual(4, tokens.Count);
            Assert.AreEqual("strasse", tokens[0]);
            Assert.AreEqual("muenchen", tokens[1]);
            Assert.AreEqual("fussgaengeruebergaenge", tokens[2]);
            Assert.AreEqual("groessenmassstaebe", tokens[3]);
        }