C# (CSharp) org.apache.lucene.analysis.de GermanStemFilter Examples

Example #1

File: TestGermanAnalyzer.cs Project: WakeflyCBass/lucenenet

 //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
 //ORIGINAL LINE: public void testWithKeywordAttribute() throws java.io.IOException
 public virtual void testWithKeywordAttribute()
 {
     CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
     set.add("fischen");
     GermanStemFilter filter = new GermanStemFilter(new SetKeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader("Fischen Trinken")), set));
     assertTokenStreamContents(filter, new string[] {"fischen", "trink"});
 }

Example #2

File: GermanAnalyzer.cs Project: zfxsss/lucenenet

        /// <summary>
        /// Creates
        /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
        /// used to tokenize all the text in the provided <seealso cref="Reader"/>.
        /// </summary>
        /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
        ///         built from a <seealso cref="StandardTokenizer"/> filtered with
        ///         <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
        ///         , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
        ///         provided, <seealso cref="GermanNormalizationFilter"/> and <seealso cref="GermanLightStemFilter"/> </returns>
        protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
        {
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
            Tokenizer   source = new StandardTokenizer(matchVersion, reader);
            TokenStream result = new StandardFilter(matchVersion, source);

            result = new LowerCaseFilter(matchVersion, result);
            result = new StopFilter(matchVersion, result, stopwords);
            result = new SetKeywordMarkerFilter(result, exclusionSet);
            if (matchVersion.onOrAfter(Version.LUCENE_36))
            {
                result = new GermanNormalizationFilter(result);
                result = new GermanLightStemFilter(result);
            }
            else if (matchVersion.onOrAfter(Version.LUCENE_31))
            {
                result = new SnowballFilter(result, new German2Stemmer());
            }
            else
            {
                result = new GermanStemFilter(result);
            }
            return(new TokenStreamComponents(source, result));
        }

Example #3

//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testWithKeywordAttribute() throws java.io.IOException
        public virtual void testWithKeywordAttribute()
        {
            CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);

            set.add("fischen");
            GermanStemFilter filter = new GermanStemFilter(new SetKeywordMarkerFilter(new LowerCaseTokenizer(TEST_VERSION_CURRENT, new StringReader("Fischen Trinken")), set));

            assertTokenStreamContents(filter, new string[] { "fischen", "trink" });
        }

Example #4

File: GermanAnalyzer.cs Project: Cefa68000/lucenenet

 /// <summary>
 /// Creates
 /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
 /// used to tokenize all the text in the provided <seealso cref="Reader"/>.
 /// </summary>
 /// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
 ///         built from a <seealso cref="StandardTokenizer"/> filtered with
 ///         <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
 ///         , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
 ///         provided, <seealso cref="GermanNormalizationFilter"/> and <seealso cref="GermanLightStemFilter"/> </returns>
 protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
 {
     //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
     //ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
     Tokenizer source = new StandardTokenizer(matchVersion, reader);
     TokenStream result = new StandardFilter(matchVersion, source);
     result = new LowerCaseFilter(matchVersion, result);
     result = new StopFilter(matchVersion, result, stopwords);
     result = new SetKeywordMarkerFilter(result, exclusionSet);
     if (matchVersion.onOrAfter(Version.LUCENE_36))
     {
       result = new GermanNormalizationFilter(result);
       result = new GermanLightStemFilter(result);
     }
     else if (matchVersion.onOrAfter(Version.LUCENE_31))
     {
       result = new SnowballFilter(result, new German2Stemmer());
     }
     else
     {
       result = new GermanStemFilter(result);
     }
     return new TokenStreamComponents(source, result);
 }