Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.SimpleAnalyzer
53
54
55
56
57
58
59
60
61
62
        JndiRegistry registry = new JndiRegistry(createJndiContext());
        registry.bind("std", new File("target/stdindexDir"));
        registry.bind("load_dir", new File("src/test/resources/sources"));
        registry.bind("stdAnalyzer", new StandardAnalyzer(Version.LUCENE_46));
        registry.bind("simple", new File("target/simpleindexDir"));
        registry.bind("simpleAnalyzer", new SimpleAnalyzer(Version.LUCENE_46));
        registry.bind("whitespace", new File("target/whitespaceindexDir"));
        registry.bind("whitespaceAnalyzer", new WhitespaceAnalyzer(Version.LUCENE_46));
        return registry;
    }
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
public class TestPerFieldAnalyzerWrapper extends BaseTokenStreamTestCase {
  public void testPerField() throws Exception {
    String text = "Qwerty";

    Map<String, Analyzer> analyzerPerField = new HashMap<String, Analyzer>();
    analyzerPerField.put("special", new SimpleAnalyzer(TEST_VERSION_CURRENT));

    PerFieldAnalyzerWrapper analyzer =
              new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(TEST_VERSION_CURRENT), analyzerPerField);

    TokenStream tokenStream = analyzer.tokenStream("field", text);
View Full Code Here
42
43
44
45
46
47
48
        .
    */

    @Override
    public Analyzer open(Assembler a, Resource root, Mode mode) {
      return new SimpleAnalyzer(TextIndexLucene.VER);
    }
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
public class TestPerFieldAnalyzerWrapper extends BaseTokenStreamTestCase {
  public void testPerField() throws Exception {
    String text = "Qwerty";

    Map<String, Analyzer> analyzerPerField = new HashMap<String, Analyzer>();
    analyzerPerField.put("special", new SimpleAnalyzer(TEST_VERSION_CURRENT));

    PerFieldAnalyzerWrapper analyzer =
              new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(TEST_VERSION_CURRENT), analyzerPerField);

    TokenStream tokenStream = analyzer.tokenStream("field",
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
  private Directory _directory;
 
  public VocabularySearcher(File dir) throws IOException {
                _directory = new SimpleFSDirectory(new File(dir, "luceneIndex"));
                Analyzer a = new SimpleAnalyzer(Version.LUCENE_43);
                IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_43,a);               

                writer = new IndexWriter(_directory,conf);
                writer.commit();
                r = DirectoryReader.open(_directory);
View Full Code Here
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
    BooleanQuery q = new BooleanQuery();
    q.add(q1, Occur.MUST);
    q.add(q2, Occur.MUST);

    if (s != null && s.trim().length() > 0) {
      SimpleAnalyzer analyzer = new SimpleAnalyzer(Version.LUCENE_36);
      if (s.indexOf(":") == -1) {
        // the query we need:
        // "projectId":projectId AND "type":type AND ("prefix":s* OR
        // "localPart":s* OR "label":s* OR "description":s*)
        BooleanQuery q3 = new BooleanQuery();
        q3.add(new WildcardQuery(new Term("prefix", s + "*")),
            Occur.SHOULD);

        TokenStream stream = analyzer.tokenStream("localPart",
            new StringReader(s));
        // get the TermAttribute from the TokenStream
        CharTermAttribute termAtt = (CharTermAttribute) stream
            .addAttribute(CharTermAttribute.class);

        stream.reset();
               
        while (stream.incrementToken()) {
          String tmp = termAtt.toString() + "*";
          q3.add(new WildcardQuery(new Term("localPart", tmp)),
              Occur.SHOULD);
        }
        stream.close();
        stream.end();

        stream = analyzer.tokenStream("description",
            new StringReader(s));
        // get the TermAttribute from the TokenStream
        termAtt = (CharTermAttribute) stream
            .addAttribute(CharTermAttribute.class);

        stream.reset();
        while (stream.incrementToken()) {
          String tmp = termAtt.toString() + "*";
          q3.add(new WildcardQuery(new Term("description", tmp)),
              Occur.SHOULD);
        }
        stream.close();
        stream.end();

        stream = analyzer.tokenStream("label", new StringReader(s));
        // get the TermAttribute from the TokenStream
        termAtt = (CharTermAttribute) stream
            .addAttribute(CharTermAttribute.class);

        stream.reset();
        while (stream.incrementToken()) {
          String tmp = termAtt.toString() + "*";
          q3.add(new WildcardQuery(new Term("label", tmp)),
              Occur.SHOULD);
        }
        stream.close();
        stream.end();

        q.add(q3, Occur.MUST);
        return q;
      } else {
        // the query we need:
        // "projectId":projectId AND "type":type AND ("prefix":p1 AND
        // "localPart":s*)
        String p1 = s.substring(0, s.indexOf(":"));
        String p2 = s.substring(s.indexOf(":") + 1);

        BooleanQuery q3 = new BooleanQuery();
        q3.add(new TermQuery(new Term("prefix", p1)), Occur.SHOULD);

        BooleanQuery q4 = new BooleanQuery();

        TokenStream stream = analyzer.tokenStream("localPart",
            new StringReader(p2));
        // get the TermAttribute from the TokenStream
        CharTermAttribute termAtt = (CharTermAttribute) stream
            .addAttribute(CharTermAttribute.class);

View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
    System.out.println( "Going to create fake index..." );

    FSDirectory directory = FSDirectory.open(
        new File( getIndexBaseDir(), Detective.class.getCanonicalName() )
    );
    SimpleAnalyzer analyzer = new SimpleAnalyzer( Version.LUCENE_CURRENT );
    IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_CURRENT, analyzer);
    IndexWriter iw = new IndexWriter( directory, cfg );
    IndexFillRunnable filler = new IndexFillRunnable( iw );
    ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool( WORKER_THREADS );
    for ( int batch = 0; batch <= INDEX_ELEMENTS; batch++ ) {
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
  private void assertFindsN(int expectedToFind, String queryString) throws ParseException {
    openSession().beginTransaction();
    try {
      FullTextSession fullTextSession = Search.getFullTextSession( getSession() );
      QueryParser queryParser = new QueryParser( TestConstants.getTargetLuceneVersion(), "", new SimpleAnalyzer( TestConstants.getTargetLuceneVersion() ) );
      Query query = queryParser.parse( queryString );
      FullTextQuery fullTextQuery = fullTextSession.createFullTextQuery(
          query,
          LargeDocument.class
      );
View Full Code Here
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
    // The equipment field is the manufacturer field  in the
    // Departments entity after being massaged by passing it
    // through the EquipmentType class. This field is in
    // the Lucene document but not in the Department entity itself.
    QueryParser parser = new QueryParser( TestConstants.getTargetLuceneVersion(), "equipment", new SimpleAnalyzer( TestConstants.getTargetLuceneVersion() ) );

    // Check the second ClassBridge annotation
    Query query = parser.parse( "equiptype:Cisco" );
    org.hibernate.search.FullTextQuery hibQuery = session.createFullTextQuery( query, Departments.class );
    List<Departments> result = hibQuery.list();
    assertNotNull( result );
    assertEquals( "incorrect number of results returned", 2, result.size() );
    for ( Departments d : result ) {
      assertEquals( "incorrect manufacturer", "C", d.getManufacturer() );
    }

    // No data cross-ups.
    query = parser.parse( "branchnetwork:Kent Lewin" );
    hibQuery = session.createFullTextQuery( query, Departments.class );
    result = hibQuery.list();
    assertNotNull( result );
    assertTrue( "problem with field cross-ups", result.size() == 0 );

    // Non-ClassBridge field.
    parser = new QueryParser( TestConstants.getTargetLuceneVersion(), "branchHead", new SimpleAnalyzer( TestConstants.getTargetLuceneVersion() ) );
    query = parser.parse( "branchHead:Kent Lewin" );
    hibQuery = session.createFullTextQuery( query, Departments.class );
    result = hibQuery.list();
    assertNotNull( result );
    assertTrue( "incorrect entity returned, wrong branch head", result.size() == 1 );
    assertEquals( "incorrect entity returned", "Kent Lewin", ( result.get( 0 ) ).getBranchHead() );

    // Check other ClassBridge annotation.
    parser = new QueryParser( TestConstants.getTargetLuceneVersion(), "branchnetwork", new SimpleAnalyzer( TestConstants.getTargetLuceneVersion() ) );
    query = parser.parse( "branchnetwork:st. george 1D" );
    hibQuery = session.createFullTextQuery( query, Departments.class );
    result = hibQuery.list();
    assertNotNull( result );
    assertEquals( "incorrect entity returned, wrong network", "1D", ( result.get( 0 ) ).getNetwork() );
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
public class TestPerFieldAnalyzerWrapper extends BaseTokenStreamTestCase {
  public void testPerField() throws Exception {
    String text = "Qwerty";

    Map<String, Analyzer> analyzerPerField = new HashMap<>();
    analyzerPerField.put("special", new SimpleAnalyzer(TEST_VERSION_CURRENT));

    PerFieldAnalyzerWrapper analyzer =
              new PerFieldAnalyzerWrapper(new WhitespaceAnalyzer(TEST_VERSION_CURRENT), analyzerPerField);

    TokenStream tokenStream = analyzer.tokenStream("field", text);
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.core.SimpleAnalyzer

  • org.apache.camel.component.lucene.LuceneIndexAndQueryProducerTest
  • org.apache.jena.query.text.assembler.SimpleAnalyzerAssembler
  • org.apache.lucene.analysis.miscellaneous.TestPerFieldAnalyzerWrapper
  • org.carrot2.source.lucene.FSDirectoryWrapperTest
  • org.carrot2.source.lucene.LuceneDocumentSourceTest
  • org.deri.grefine.rdf.vocab.imp.VocabularySearcher
  • org.elasticsearch.index.analysis.SimpleAnalyzerProvider
  • org.hibernate.search.store.impl.DirectoryProviderHelper
  • org.hibernate.search.test.compression.CompressionTest
  • org.hibernate.search.test.configuration.ProgrammaticMappingTest
    • 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.