C# (CSharp) org.apache.lucene.analysis.ga IrishLowerCaseFilter 예제들

예제 #1

파일: TestIrishLowerCaseFilter.cs 프로젝트: zfxsss/lucenenet

        /// <summary>
        /// Test lowercase
        /// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testIrishLowerCaseFilter() throws Exception
        public virtual void testIrishLowerCaseFilter()
        {
            TokenStream          stream = new MockTokenizer(new StringReader("nAthair tUISCE hARD"), MockTokenizer.WHITESPACE, false);
            IrishLowerCaseFilter filter = new IrishLowerCaseFilter(stream);

            assertTokenStreamContents(filter, new string[] { "n-athair", "t-uisce", "hard" });
        }

예제 #2

        /// <summary>
        /// Creates a
        /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
        /// which tokenizes all the text in the provided <seealso cref="Reader"/>.
        /// </summary>
        /// <returns> A
        ///         <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
        ///         built from an <seealso cref="StandardTokenizer"/> filtered with
        ///         <seealso cref="StandardFilter"/>, <seealso cref="IrishLowerCaseFilter"/>, <seealso cref="StopFilter"/>
        ///         , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
        ///         provided and <seealso cref="SnowballFilter"/>. </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);
            StopFilter  s      = new StopFilter(matchVersion, result, HYPHENATIONS);

            if (!matchVersion.onOrAfter(Version.LUCENE_44))
            {
                s.EnablePositionIncrements = false;
            }
            result = s;
            result = new ElisionFilter(result, DEFAULT_ARTICLES);
            result = new IrishLowerCaseFilter(result);
            result = new StopFilter(matchVersion, result, stopwords);
            if (!stemExclusionSet.Empty)
            {
                result = new SetKeywordMarkerFilter(result, stemExclusionSet);
            }
            result = new SnowballFilter(result, new IrishStemmer());
            return(new TokenStreamComponents(source, result));
        }

예제 #3

파일: TestIrishLowerCaseFilter.cs 프로젝트: Cefa68000/lucenenet

 /// <summary>
 /// Test lowercase
 /// </summary>
 //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
 //ORIGINAL LINE: public void testIrishLowerCaseFilter() throws Exception
 public virtual void testIrishLowerCaseFilter()
 {
     TokenStream stream = new MockTokenizer(new StringReader("nAthair tUISCE hARD"), MockTokenizer.WHITESPACE, false);
     IrishLowerCaseFilter filter = new IrishLowerCaseFilter(stream);
     assertTokenStreamContents(filter, new string[] {"n-athair", "t-uisce", "hard"});
 }

예제 #4

파일: IrishAnalyzer.cs 프로젝트: Cefa68000/lucenenet

 /// <summary>
 /// Creates a
 /// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
 /// which tokenizes all the text in the provided <seealso cref="Reader"/>.
 /// </summary>
 /// <returns> A
 ///         <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
 ///         built from an <seealso cref="StandardTokenizer"/> filtered with
 ///         <seealso cref="StandardFilter"/>, <seealso cref="IrishLowerCaseFilter"/>, <seealso cref="StopFilter"/>
 ///         , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
 ///         provided and <seealso cref="SnowballFilter"/>. </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);
     StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS);
     if (!matchVersion.onOrAfter(Version.LUCENE_44))
     {
       s.EnablePositionIncrements = false;
     }
     result = s;
     result = new ElisionFilter(result, DEFAULT_ARTICLES);
     result = new IrishLowerCaseFilter(result);
     result = new StopFilter(matchVersion, result, stopwords);
     if (!stemExclusionSet.Empty)
     {
       result = new SetKeywordMarkerFilter(result, stemExclusionSet);
     }
     result = new SnowballFilter(result, new IrishStemmer());
     return new TokenStreamComponents(source, result);
 }