Examples of org.apache.lucene.analysis.PerFieldAnalyzerWrapper

org.apache.lucene.analysis.PerFieldAnalyzerWrapper
This analyzer is used to facilitate scenarios where different fields require different analysis techniques. Use {@link #addAnalyzer}to add a non-default analyzer on a field name basis.
Example usage:
```
 PerFieldAnalyzerWrapper aWrapper = new PerFieldAnalyzerWrapper(new StandardAnalyzer()); aWrapper.addAnalyzer("firstname", new KeywordAnalyzer()); aWrapper.addAnalyzer("lastname", new KeywordAnalyzer()); 
```
In this example, StandardAnalyzer will be used for all fields except "firstname" and "lastname", for which KeywordAnalyzer will be used.
A PerFieldAnalyzerWrapper can be used like any other analyzer, for both indexing and query parsing.

            String analyzerPrefix = fullPrefix + ".fields." + field;
            Analyzer analyzer = pluginRegistry.getBeanByFullPrefix(analyzerPrefix, Analyzer.class);
            analyzers.put(field, analyzer);
        }


        return new PerFieldAnalyzerWrapper(defaultAnalyzer, analyzers);
    }

View Full Code Here

   *
   * @return Returns the <code>Analyzer</code> that is used for all analyzation
   * of Fields and Queries.
   */
  public static Analyzer createAnalyzer() {
    PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new DefaultAnalyzer());


    /* Standard (Lowercase, Letter, Stop,...) */
    StandardAnalyzer stdAnalyzer;
    if (DISABLE_STOP_WORDS)
      stdAnalyzer = new StandardAnalyzer(Collections.EMPTY_SET);
    else
      stdAnalyzer = new StandardAnalyzer();


    analyzer.addAnalyzer(String.valueOf(INews.TITLE), stdAnalyzer);
    analyzer.addAnalyzer(String.valueOf(INews.DESCRIPTION), stdAnalyzer);
    analyzer.addAnalyzer(String.valueOf(INews.ATTACHMENTS_CONTENT), stdAnalyzer);


    /* Simple (Lowercase, Whitespace Tokzenizer) */
    LowercaseWhitespaceAnalyzer simpleAnalyzer = new LowercaseWhitespaceAnalyzer();
    analyzer.addAnalyzer(String.valueOf(INews.AUTHOR), simpleAnalyzer);
    analyzer.addAnalyzer(String.valueOf(INews.LABEL), simpleAnalyzer);


    /* Simple (Lowercase, Delim Tokenizer) */
    analyzer.addAnalyzer(String.valueOf(INews.CATEGORIES), new LowercaseDelimiterAnalyzer('\n'));


    return analyzer;
  }

View Full Code Here

        } catch (Exception e) {
            logger.error("failed to return search analyzer. are the analyzers specified correctly in server.conf? {language='"+language+"', class='"+className+"'}",e);
            logger.error("recovering by returning default archiver analyzer. indexing and search may be impaired. urgent fix required.");
            analyzer = new ArchivaAnalyzer();
        } 
        PerFieldAnalyzerWrapper wrapper = new PerFieldAnalyzerWrapper(analyzer);
        
        if (operation==Operation.INDEX) {
          wrapper.addAnalyzer("to", new EmailAnalyzer());
          wrapper.addAnalyzer("from", new EmailAnalyzer());
          wrapper.addAnalyzer("cc", new EmailAnalyzer());
          wrapper.addAnalyzer("bcc", new EmailAnalyzer());
          wrapper.addAnalyzer("deliveredto", new EmailAnalyzer());
          wrapper.addAnalyzer("attachname", new FileNameAnalyzer());
        } else {
          wrapper.addAnalyzer("to", new WhitespaceAnalyzer());
           wrapper.addAnalyzer("from", new WhitespaceAnalyzer());
           wrapper.addAnalyzer("cc", new WhitespaceAnalyzer());
           wrapper.addAnalyzer("bcc", new WhitespaceAnalyzer());
           wrapper.addAnalyzer("deliveredto", new WhitespaceAnalyzer());
           wrapper.addAnalyzer("attachname", new FileNameAnalyzer());
        }
        return wrapper;
    }

View Full Code Here

     * Create a {@link Analyzer} which is used to index the {@link MailboxMembership}'s
     * 
     * @return analyzer
     */
    public static Analyzer createAnalyzer() {
        PerFieldAnalyzerWrapper wrapper = new PerFieldAnalyzerWrapper(new ImapSearchAnalyzer());
        return wrapper;
    }

View Full Code Here

        myFilter      = diskFilter;
      
      
      }
      
      PerFieldAnalyzerWrapper qAnalyzer = new PerFieldAnalyzerWrapper(analyzer);
      QueryParser    queryParser = new QueryParser(DOCUMENT_KEY,qAnalyzer);
      
      //add any keyword fields
      if(query.isSetKeyword_fields()){      
        for(String field : query.keyword_fields)
          qAnalyzer.addAnalyzer(field, kwAnalyzer);
      }
      
      //parse query
      //TODO: Cache?
      try{

View Full Code Here

                                   String usResult,
                                   String frResult,
                                   String svResult,
                                   String dkResult) throws Exception {
    RAMDirectory indexStore = new RAMDirectory();
    PerFieldAnalyzerWrapper analyzer
      = new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(TEST_VERSION_CURRENT));
    analyzer.addAnalyzer("US", usAnalyzer);
    analyzer.addAnalyzer("France", franceAnalyzer);
    analyzer.addAnalyzer("Sweden", swedenAnalyzer);
    analyzer.addAnalyzer("Denmark", denmarkAnalyzer);
    IndexWriter writer = new IndexWriter(indexStore, new IndexWriterConfig(
        TEST_VERSION_CURRENT, analyzer));


    // document data:
    // the tracer field is used to determine which document was hit

View Full Code Here

0 1 2

TOP

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

com.flaptor.hounder.searcher.query.QueryParser

com.flaptor.indextank.index.lsi.LsiIndex

com.gentics.cr.lucene.indexer.index.LuceneAnalyzerFactory

com.gnizr.core.search.DocumentCreator

com.senseidb.plugin.analyzer.LucenePerFieldAnalyzerFactory

com.stimulus.archiva.language.AnalyzerFactory

er.indexing.ERIndex

org.apache.cocoon.components.search.analyzer.ConfigurablePerFieldAnalyzer

org.apache.james.mailbox.store.lucene.LuceneMessageSearchIndex

org.apache.lucene.analysis.CollationTestBase

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.