Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.ASCIIFoldingFilter

See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode The set of character conversions supported by this class is a superset of those supported by Lucene's {@link ISOLatin1AccentFilter} which stripsaccents from Latin1 characters. For example, 'à' will be replaced by 'a'.
112
113
114
115
116
117
118
119
120
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(Version.LUCENE_CURRENT, reader);
    result = new StandardFilter(result);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(result);
    return result;
  }
View Full Code Here
32
33
34
35
36
37
38
* &lt;/fieldType&gt;</pre>
* @version $Id: ASCIIFoldingFilterFactory.java 1073344 2011-02-22 14:35:02Z koji $
*/
public class ASCIIFoldingFilterFactory extends BaseTokenFilterFactory {
  public ASCIIFoldingFilter create(TokenStream input) {
    return new ASCIIFoldingFilter(input);
  }
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(LuceneVersion.getVersion(), reader);
    result = new StandardFilter(result);
    result = new LowerCaseFilter(result);
    result = new ASCIIFoldingFilter(result);
    List<String> list = Arrays.asList(ENGLISH_STOP_WORDS);
    Set<String> set = new HashSet<String>(list);
    result = new StopFilter(false, result, set, true);
    result = new EdgeNGramTokenFilter(result, Side.FRONT, 1, 20);
    return result;
View Full Code Here
35
36
37
38
39
40
41
    @Inject public ASCIIFoldingTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
        super(index, indexSettings, name, settings);
    }

    @Override public TokenStream create(TokenStream tokenStream) {
        return new ASCIIFoldingFilter(tokenStream);
    }
View Full Code Here
116
117
118
119
120
121
122
123
124
125
126
  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_31, reader);
    TokenStream result = new StandardFilter(Version.LUCENE_31, tokenizer);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new ASCIIFoldingFilter(result);
    result = new AlphaNumericMaxLengthFilter(result);
    result = new StopFilter(Version.LUCENE_31, result, stopwords);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
20
21
22
23
24
25
26
import org.apache.lucene.analysis.ASCIIFoldingFilter;
import org.apache.lucene.analysis.TokenStream;

public class ASCIIFoldingFilterFactory extends BaseTokenFilterFactory {
  public ASCIIFoldingFilter create(TokenStream input) {
    return new ASCIIFoldingFilter( input );
  }
View Full Code Here
45
46
47
48
49
50
51
52
53
    /** Constructs a {@link StandardTokenizer} filtered by a {@link
      StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
        TokenStream result = super.tokenStream(fieldName, reader);
        result = new ASCIIFoldingFilter(result);
       
        return result;
    }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
  public TokenStream tokenStream(String fieldName, java.io.Reader reader) {

    TokenStream result = new StandardTokenizer(Version.LUCENE_31, reader);
    result = new StandardFilter(Version.LUCENE_31, result);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new ASCIIFoldingFilter(result);
    result = new AlphaNumericMaxLengthFilter(result);
    result = new StopFilter(Version.LUCENE_31, result, stopSet);
    return new PorterStemFilter(result);
  }
View Full Code Here
112
113
114
115
116
117
118
119
120
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(LuceneTestCase.TEST_VERSION_CURRENT, reader);
    result = new StandardFilter(Version.LUCENE_31, result);
    result = new ASCIIFoldingFilter(result);
    result = new LowerCaseFilter(LuceneTestCase.TEST_VERSION_CURRENT, result);
    return result;
  }
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
  @Override
  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    Tokenizer tokenizer = new StandardTokenizer(LUCENE_VERSION, reader);
    TokenStream result = new StandardFilter(LUCENE_VERSION, tokenizer);
    result = new LowerCaseFilter(LUCENE_VERSION, result);
    result = new ASCIIFoldingFilter(result);
    result = new AlphaNumericMaxLengthFilter(result);
    result = new StopFilter(LUCENE_VERSION, result, stopwords);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(tokenizer, result);
  }
View Full Code Here
TOP

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

  • com.flaptor.indextank.query.IndexEngineAnalyzer
  • com.gentics.cr.lucene.autocomplete.AutocompleteAnalyzer
  • helpers.search.LinkItAnalyzer
  • org.apache.lucene.analysis.cn.smart.TestSmartChineseAnalyzer
  • org.apache.lucene.analysis.ngram.EdgeNGramTokenFilterTest
  • org.apache.lucene.analysis.ngram.NGramTokenFilterTest
  • org.apache.lucene.queryParser.analyzing.ASCIIAnalyzer
  • org.apache.mahout.text.MailArchivesClusteringAnalyzer
  • org.apache.solr.analysis.ASCIIFoldingFilterFactory
  • org.elasticsearch.index.analysis.ASCIIFoldingTokenFilterFactory
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.