Examples of org.apache.lucene.analysis.ReusableAnalyzerBase

org.apache.lucene.analysis.ReusableAnalyzerBase
An convenience subclass of Analyzer that makes it easy to implement {@link TokenStream} reuse.
ReusableAnalyzerBase is a simplification of Analyzer that supports easy reuse for the most common use-cases. Analyzers such as {@link PerFieldAnalyzerWrapper} that behave differently depending upon thefield name need to subclass Analyzer directly instead.

To prevent consistency problems, this class does not allow subclasses to extend {@link #reusableTokenStream(String,Reader)} or{@link #tokenStream(String,Reader)} directly. Instead, subclasses mustimplement {@link #createComponents(String,Reader)}.

    assertTokenStreamContents(filter, new String[] {"i\u0316stanbul", "izmir",
        "\u0131\u0316sparta",});
  }
  
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new TurkishLowerCaseFilter(tokenizer));
      }

View Full Code Here

  public void testRandomStrings() throws Exception {
    checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);
  }
  
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new EnglishMinimalStemFilter(tokenizer));
      }

View Full Code Here

        "Finnish", "French", "German2", "German", "Hungarian", "Irish",
        "Italian", "Kp", "Lovins", "Norwegian", "Porter", "Portuguese",
        "Romanian", "Russian", "Spanish", "Swedish", "Turkish"
    };
    for (final String lang : langs) {
      Analyzer a = new ReusableAnalyzerBase() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new KeywordTokenizer(reader);
          return new TokenStreamComponents(tokenizer, new SnowballFilter(tokenizer, lang));
        }

View Full Code Here

    assertEquals("abcfed𩬅愯瀛", new String(buffer));
  }
  
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new ReverseStringFilter(TEST_VERSION_CURRENT, tokenizer));
      }

View Full Code Here

    };
    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
  }
  
  public void testEmptyTerm() throws IOException {
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new KeywordTokenizer(reader);
        return new TokenStreamComponents(tokenizer, new ReverseStringFilter(TEST_VERSION_CURRENT, tokenizer));
      }

View Full Code Here

        add(randomNonEmptyString(), randomNonEmptyString(), random.nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random.nextBoolean();
      
      final Analyzer analyzer = new ReusableAnalyzerBase() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.SIMPLE, true);
          return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, ignoreCase));
        }

View Full Code Here

        add(randomNonEmptyString(), randomNonEmptyString(), random.nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random.nextBoolean();
      
      final Analyzer analyzer = new ReusableAnalyzerBase() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new KeywordTokenizer(reader);
          return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, ignoreCase));
        }

View Full Code Here

        add(randomNonEmptyString(), randomNonEmptyString(), random.nextBoolean());
      }
      final SynonymMap map = b.build();
      final boolean ignoreCase = random.nextBoolean();
      
      final Analyzer analyzer = new ReusableAnalyzerBase() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
          Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.SIMPLE, true);
          return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, ignoreCase));
        }

View Full Code Here

      
    SolrSynonymParser parser = new SolrSynonymParser(true, true, new MockAnalyzer(random));
    parser.add(new StringReader(testFile));
    final SynonymMap map = parser.build();
      
    Analyzer analyzer = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, true);
        return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, true));
      }

View Full Code Here

    add("a", "aa", keepOrig);
    add("b", "bb", keepOrig);
    add("z x c v", "zxcv", keepOrig);
    add("x c", "xc", keepOrig);
    final SynonymMap map = b.build();
    Analyzer a = new ReusableAnalyzerBase() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
        return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, true));
      }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.analysis.ReusableAnalyzerBase

com.tigertext.lucene.LuceneServer

org.apache.lucene.analysis.ar.TestArabicNormalizationFilter

org.apache.lucene.analysis.ar.TestArabicStemFilter

org.apache.lucene.analysis.bg.TestBulgarianStemmer

org.apache.lucene.analysis.br.TestBrazilianStemmer

org.apache.lucene.analysis.charfilter.HTMLStripCharFilterTest

org.apache.lucene.analysis.cjk.TestCJKAnalyzer

org.apache.lucene.analysis.cjk.TestCJKWidthFilter

org.apache.lucene.analysis.cn.smart.TestSmartChineseAnalyzer

org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.