Examples of org.apache.lucene.analysis.standard.StandardAnalyzer

  {
    List<FacetHandler<?>> facetHandlers = new ArrayList<FacetHandler<?>>();
    /* Underlying time facet for DynamicTimeRangeFacetHandler */
    facetHandlers.add(new RangeFacetHandler("timeinmillis", new PredefinedTermListFactory(Long.class, DynamicTimeRangeFacetHandler.NUMBER_FORMAT),null));
    Directory idxDir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(idxDir,new StandardAnalyzer(Version.LUCENE_29),MaxFieldLength.UNLIMITED);
    
    long now = System.currentTimeMillis();
    DecimalFormat df = new DecimalFormat(DynamicTimeRangeFacetHandler.NUMBER_FORMAT);
    for(long l=0; l<53; l++)
    {

  {
    super(testname);
    _ramDir = new RAMDirectory();
    try
    {
      IndexWriter writer = new IndexWriter(_ramDir,new StandardAnalyzer(Version.LUCENE_CURRENT),MaxFieldLength.UNLIMITED);
      writer.close();
    }
    catch(Exception ioe)
    {
      fail("unable to load test");

    doc.add(createFieldLastUpdated(bookmark.getLastUpdated()));    
    return doc;
  }


  public static Analyzer createDocumentAnalyzer(){
    PerFieldAnalyzerWrapper wrapper = new PerFieldAnalyzerWrapper(new StandardAnalyzer());
    wrapper.addAnalyzer(DocumentCreator.FIELD_BOOKMARK_ID,new KeywordAnalyzer());
    wrapper.addAnalyzer(DocumentCreator.FIELD_URL_MD5,new KeywordAnalyzer());
    wrapper.addAnalyzer(DocumentCreator.FIELD_TAG, new KeywordAnalyzer());
    wrapper.addAnalyzer(DocumentCreator.FIELD_USER,new KeywordAnalyzer());
    return wrapper;

   */
  Analyzer createAnalyzer() {
    PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new DefaultAnalyzer());


    /* Standard (Lowercase, Letter, Stop,...) */
    StandardAnalyzer 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) */

   */
  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);

   *
   * @param indexDir - The directory from which the index can be retrieved.
   */
  public ChannelSearcher(String indexDir) throws IOException {
    this.indexDir = indexDir;
    this.analyzer = new StandardAnalyzer();
    this.searcher = new IndexSearcher(indexDir);
    this.nrOfHits = 0;
  }

   * @param indexDir - The directory in which the index files are stored.
   */
  public ChannelIndexer(String indexDir) {
    this.indexDir = indexDir;
    this.nrOfIndexedItems = 0;
    this.analyzer = new StandardAnalyzer();
  }

    Set stopWords = StopFilter.makeStopSet(StopAnalyzer.ENGLISH_STOP_WORDS);
    
    Analyzer[] analyzers = new Analyzer[] { 
        new SimpleAnalyzer(),
        new StopAnalyzer(),
        new StandardAnalyzer(),
        PatternAnalyzer.DEFAULT_ANALYZER,
//        new WhitespaceAnalyzer(),
//        new PatternAnalyzer(PatternAnalyzer.NON_WORD_PATTERN, false, null),
//        new PatternAnalyzer(PatternAnalyzer.NON_WORD_PATTERN, true, stopWords),        
//        new SnowballAnalyzer("English", StopAnalyzer.ENGLISH_STOP_WORDS),

        // The HTML escaping forces us to first fragment with internal placeholders...
        Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(INTERNAL_BEGIN_HIT, INTERNAL_END_HIT), new QueryScorer(query));
        highlighter.setTextFragmenter(fragmenter);
        try {
            // Use the same analyzer as the indexer!
            TokenStream tokenStream = new StandardAnalyzer().tokenStream(null, new StringReader(indexedText));


            String unescapedFragements =
                    highlighter.getBestFragments(tokenStream, indexedText, numOfFragments, getFragmentSeparator());


            String escapedFragments = WikiUtil.escapeHtml(WikiUtil.removeMacros(unescapedFragements), false, false);

        try {
            PhraseQuery query = new PhraseQuery();
            query.setSlop(0);


            TokenStream includeStream =
                    new StandardAnalyzer().tokenStream(null, new StringReader(escape(terms).toLowerCase()));


            while (true) {
                Token t = includeStream.next();
                if (t == null) break;
                query.add( new Term(fieldName, t.termText()) );

Related Classes of org.apache.lucene.analysis.standard.StandardAnalyzer

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.