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)}.

    final boolean keepOrig = false;
    add("a b", "ab", keepOrig);
    add("a b", "ab", keepOrig);
    add("a b", "ab", 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

    final boolean keepOrig = false;
    add("a b", "ab", keepOrig);
    add("a b", "ab", keepOrig);
    add("a b", "ab", 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

  public void testRecursion() throws Exception {
    b = new SynonymMap.Builder(true);
    final boolean keepOrig = false;
    add("zoo", "zoo", 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

    b = new SynonymMap.Builder(true);
    final boolean keepOrig = false;
    add("zoo", "zoo", keepOrig);
    add("zoo", "zoo zoo", 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

    ArabicStemFilter filter = new ArabicStemFilter(tokenStream);
    assertTokenStreamContents(filter, new String[]{expected});
  }
  
  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 ArabicStemFilter(tokenizer));
      }

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

  public void testRecursion3() throws Exception {
    b = new SynonymMap.Builder(true);
    final boolean keepOrig = true;
    add("zoo zoo", "zoo", 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

    b = new SynonymMap.Builder(true);
    final boolean keepOrig = true;
    add("zoo zoo", "zoo", keepOrig);
    add("zoo", "zoo zoo", 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

  public void testMultiwordOffsets() throws Exception {
    b = new SynonymMap.Builder(true);
    final boolean keepOrig = true;
    add("national hockey league", "nhl", 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

        path.length());
  }
  
  /** 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 PathHierarchyTokenizer(reader);
        return new TokenStreamComponents(tokenizer, tokenizer);
      }

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.