Package org.apache.lucene.util.automaton

Examples of org.apache.lucene.util.automaton.CompiledAutomaton

328
329
330
331
332
333
334
335
336
337
338
      }
      BytesRef term;
      int ord = 0;

      Automaton automaton = new RegExp(".*", RegExp.NONE).toAutomaton();   
      final TermsEnum termsEnum2 = terms.intersect(new CompiledAutomaton(automaton, false, false), null);

      while((term = termsEnum.next()) != null) {
        BytesRef term2 = termsEnum2.next();
        assertNotNull(term2);
        assertEquals(term, term2);
View Full Code Here
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
   
    if (deep) {
      int numIntersections = atLeast(3);
      for (int i = 0; i < numIntersections; i++) {
        String re = AutomatonTestUtil.randomRegexp(random());
        CompiledAutomaton automaton = new CompiledAutomaton(new RegExp(re, RegExp.NONE).toAutomaton());
        if (automaton.type == CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
          // TODO: test start term too
          TermsEnum leftIntersection = leftTerms.intersect(automaton, null);
          TermsEnum rightIntersection = rightTerms.intersect(automaton, null);
          assertTermsEnumEquals(info, leftReader, leftIntersection, rightIntersection, rarely());
View Full Code Here
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
    }

    private Term[] expandTerms(String field, String queryStr) throws XPathException {
        List<Term> termList = new ArrayList<>(8);
        Automaton automaton = WildcardQuery.toAutomaton(new Term(field, queryStr));
        CompiledAutomaton compiled = new CompiledAutomaton(automaton);
        IndexReader reader = null;
        try {
            reader = index.getReader();

            for (AtomicReaderContext atomic : reader.leaves()) {
                Terms terms = atomic.reader().terms(field);
                if (terms != null) {
                    TermsEnum termsEnum = compiled.getTermsEnum(terms);
                    BytesRef data = termsEnum.next();
                    while (data != null) {
                        String term = data.utf8ToString();
                        termList.add(new Term(field, term));
                        data = termsEnum.next();
View Full Code Here
151
152
153
154
155
156
157
158
159
160
161
162
  protected TermsEnum getAutomatonEnum(int editDistance, BytesRef lastTerm)
      throws IOException {
    final List<CompiledAutomaton> runAutomata = initAutomata(editDistance);
    if (editDistance < runAutomata.size()) {
      //if (BlockTreeTermsWriter.DEBUG) System.out.println("FuzzyTE.getAEnum: ed=" + editDistance + " lastTerm=" + (lastTerm==null ? "null" : lastTerm.utf8ToString()));
      final CompiledAutomaton compiled = runAutomata.get(editDistance);
      return new AutomatonFuzzyTermsEnum(terms.intersect(compiled, lastTerm == null ? null : compiled.floor(lastTerm, new BytesRef())),
                                         runAutomata.subList(0, editDistance + 1).toArray(new CompiledAutomaton[editDistance + 1]));
    } else {
      return null;
    }
  }
View Full Code Here
177
178
179
180
181
182
183
184
185
186
        if (realPrefixLength > 0) {
          Automaton prefix = BasicAutomata.makeString(
            UnicodeUtil.newString(termText, 0, realPrefixLength));
          a = BasicOperations.concatenate(prefix, a);
        }
        runAutomata.add(new CompiledAutomaton(a, true, false));
      }
    }
    return runAutomata;
  }
View Full Code Here
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
   
    if (deep) {
      int numIntersections = atLeast(3);
      for (int i = 0; i < numIntersections; i++) {
        String re = AutomatonTestUtil.randomRegexp(random());
        CompiledAutomaton automaton = new CompiledAutomaton(new RegExp(re, RegExp.NONE).toAutomaton());
        if (automaton.type == CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
          // TODO: test start term too
          TermsEnum leftIntersection = leftTerms.intersect(automaton, null);
          TermsEnum rightIntersection = rightTerms.intersect(automaton, null);
          assertTermsEnumEquals(info, leftReader, leftIntersection, rightIntersection, rarely());
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
   
    if (deep) {
      int numIntersections = atLeast(3);
      for (int i = 0; i < numIntersections; i++) {
        String re = AutomatonTestUtil.randomRegexp(random());
        CompiledAutomaton automaton = new CompiledAutomaton(new RegExp(re, RegExp.NONE).toAutomaton());
        if (automaton.type == CompiledAutomaton.AUTOMATON_TYPE.NORMAL) {
          // TODO: test start term too
          TermsEnum leftIntersection = leftTerms.intersect(automaton, null);
          TermsEnum rightIntersection = rightTerms.intersect(automaton, null);
          assertTermsEnum(leftIntersection, rightIntersection, rarely());
View Full Code Here
329
330
331
332
333
334
335
336
337
338
339
      }
      BytesRef term;
      int ord = 0;

      Automaton automaton = new RegExp(".*", RegExp.NONE).toAutomaton();   
      final TermsEnum termsEnum2 = terms.intersect(new CompiledAutomaton(automaton, false, false), null);

      while((term = termsEnum.next()) != null) {
        BytesRef term2 = termsEnum2.next();
        assertNotNull(term2);
        assertEquals(term, term2);
View Full Code Here
264
265
266
267
268
269
270
271
272
273
274
          System.out.println("TEST: reduce the automaton");
        }
        a.reduce();
      }

      final CompiledAutomaton c = new CompiledAutomaton(a, true, false);

      final BytesRef[] acceptTermsArray = new BytesRef[acceptTerms.size()];
      final Set<BytesRef> acceptTermsSet = new HashSet<BytesRef>();
      int upto = 0;
      for(String s : acceptTerms) {
View Full Code Here
742
743
744
745
746
747
748
749
750
751
752
    DirectoryReader r = w.getReader();
    w.close();
    AtomicReader sub = getOnlySegmentReader(r);
    Terms terms = sub.fields().terms("field");
    Automaton automaton = new RegExp(".*", RegExp.NONE).toAutomaton();   
    CompiledAutomaton ca = new CompiledAutomaton(automaton, false, false);   
    TermsEnum te = terms.intersect(ca, null);
    assertEquals("aaa", te.next().utf8ToString());
    assertEquals(0, te.docs(null, null, DocsEnum.FLAG_NONE).nextDoc());
    assertEquals("bbb", te.next().utf8ToString());
    assertEquals(1, te.docs(null, null, DocsEnum.FLAG_NONE).nextDoc());
View Full Code Here
TOP

Related Classes of org.apache.lucene.util.automaton.CompiledAutomaton

  • org.apache.jackrabbit.oak.plugins.index.lucene.LuceneIndex
  • org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex
  • org.apache.lucene.codecs.lucene41.TestBlockPostingsFormat3
  • org.apache.lucene.index.SingleTermsEnum
  • org.apache.lucene.index.TestDuelingCodecs
  • org.apache.lucene.index.TestTermsEnum
  • org.apache.lucene.search.AutomatonQuery
  • org.apache.lucene.search.FuzzyTermsEnum
  • org.apache.lucene.search.PrefixTermsEnum
  • org.apache.lucene.util.BytesRef
    • 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.