Analyzer for German language. Supports an external list of stopwords (words that will not be indexed at all) and an external list of exclusions (word that will not be stemmed, but indexed). A default set of stopwords is used unless an alternative list is specified, the exclusion list is empty by default.
Inheritance: Lucene.Net.Analysis.Analyzer
GermanAnalyzer Class Documentation
Example #1
0
 public virtual void TestReusableTokenStream()
 {
     Analyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT);
     CheckOneTerm(a, "Tisch", "tisch");
     CheckOneTerm(a, "Tische", "tisch");
     CheckOneTerm(a, "Tischen", "tisch");
 }
Example #2
0
        public virtual void TestReusableTokenStream()
        {
            Analyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT);

            CheckOneTerm(a, "Tisch", "tisch");
            CheckOneTerm(a, "Tische", "tisch");
            CheckOneTerm(a, "Tischen", "tisch");
        }
Example #3
0
        public virtual void TestGermanSpecials()
        {
            GermanAnalyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT);

            // a/o/u + e is equivalent to the umlaut form
            CheckOneTerm(a, "Schaltflächen", "schaltflach");
            CheckOneTerm(a, "Schaltflaechen", "schaltflach");
            // here they are with the old stemmer
            a = new GermanAnalyzer(LuceneVersion.LUCENE_30);
            CheckOneTerm(a, "Schaltflächen", "schaltflach");
            CheckOneTerm(a, "Schaltflaechen", "schaltflaech");
        }
Example #4
0
        public virtual void TestGermanSpecials()
        {
            GermanAnalyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT);
            // a/o/u + e is equivalent to the umlaut form
            CheckOneTerm(a, "Schaltflächen", "schaltflach");
            CheckOneTerm(a, "Schaltflaechen", "schaltflach");
            // here they are with the old stemmer
#pragma warning disable 612, 618
            a = new GermanAnalyzer(LuceneVersion.LUCENE_30);
#pragma warning restore 612, 618
            CheckOneTerm(a, "Schaltflächen", "schaltflach");
            CheckOneTerm(a, "Schaltflaechen", "schaltflaech");
        }
Example #5
0
        public virtual void TestStemExclusionTable()
        {
            GermanAnalyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, new CharArraySet(TEST_VERSION_CURRENT, AsSet("tischen"), false));

            CheckOneTerm(a, "tischen", "tischen");
        }
Example #6
0
 public virtual void TestStemExclusionTable()
 {
     GermanAnalyzer a = new GermanAnalyzer(TEST_VERSION_CURRENT, CharArraySet.EMPTY_SET, new CharArraySet(TEST_VERSION_CURRENT, AsSet("tischen"), false));
     CheckOneTerm(a, "tischen", "tischen");
 }
Example #7
0
 public void TestReusableTokenStream()
 {
     Analyzer a = new GermanAnalyzer(Version.LUCENE_CURRENT);
     CheckReuse(a, "Tisch", "tisch");
     CheckReuse(a, "Tische", "tisch");
     CheckReuse(a, "Tischen", "tisch");
 }
Example #8
0
 public void TestExclusionTableReuse()
 {
     var a = new GermanAnalyzer(Version.LUCENE_CURRENT);
     CheckReuse(a, "tischen", "tisch");
     a.SetStemExclusionTable(new[] { "tischen" });
     CheckReuse(a, "tischen", "tischen");
 }