C# (CSharp) org.apache.lucene.analysis.ar ArabicNormalizationFilter 예제들

예제 #1

파일: TestArabicNormalizationFilter.cs 프로젝트: zfxsss/lucenenet

//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: private void check(final String input, final String expected) throws java.io.IOException
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
        private void check(string input, string expected)
        {
            ArabicLetterTokenizer     tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
            ArabicNormalizationFilter filter      = new ArabicNormalizationFilter(tokenStream);

            assertTokenStreamContents(filter, new string[] { expected });
        }

예제 #2

        /// <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 an <seealso cref="StandardTokenizer"/> filtered with
        ///         <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>,
        ///         <seealso cref="ArabicNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/>
        ///         if a stem exclusion set is provided and <seealso cref="ArabicStemFilter"/>. </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 = matchVersion.onOrAfter(org.apache.lucene.util.Version.LUCENE_31) ? new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
            Tokenizer   source = matchVersion.onOrAfter(Version.LUCENE_31) ? new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
            TokenStream result = new LowerCaseFilter(matchVersion, source);

            // the order here is important: the stopword list is not normalized!
            result = new StopFilter(matchVersion, result, stopwords);
            // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
            result = new ArabicNormalizationFilter(result);
            if (!stemExclusionSet.Empty)
            {
                result = new SetKeywordMarkerFilter(result, stemExclusionSet);
            }
            return(new TokenStreamComponents(source, new ArabicStemFilter(result)));
        }

예제 #3

파일: ArabicAnalyzer.cs 프로젝트: 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 an <seealso cref="StandardTokenizer"/> filtered with
 ///         <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>,
 ///         <seealso cref="ArabicNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/>
 ///         if a stem exclusion set is provided and <seealso cref="ArabicStemFilter"/>. </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 = matchVersion.onOrAfter(org.apache.lucene.util.Version.LUCENE_31) ? new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
     Tokenizer source = matchVersion.onOrAfter(Version.LUCENE_31) ? new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
     TokenStream result = new LowerCaseFilter(matchVersion, source);
     // the order here is important: the stopword list is not normalized!
     result = new StopFilter(matchVersion, result, stopwords);
     // TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
     result = new ArabicNormalizationFilter(result);
     if (!stemExclusionSet.Empty)
     {
       result = new SetKeywordMarkerFilter(result, stemExclusionSet);
     }
     return new TokenStreamComponents(source, new ArabicStemFilter(result));
 }

예제 #4

파일: TestArabicNormalizationFilter.cs 프로젝트: Cefa68000/lucenenet

 //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
 //ORIGINAL LINE: private void check(final String input, final String expected) throws java.io.IOException
 //JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
 private void check(string input, string expected)
 {
     ArabicLetterTokenizer tokenStream = new ArabicLetterTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
     ArabicNormalizationFilter filter = new ArabicNormalizationFilter(tokenStream);
     assertTokenStreamContents(filter, new string[]{expected});
 }