Package org.apache.lucene.util.automaton

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

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
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
741
742
743
744
745
746
747
748
749
750
751
    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
796
797
798
799
800
801
802
803
804
805
806
    w.close();
    AtomicReader sub = getOnlySegmentReader(r);
    Terms terms = sub.fields().terms("field");

    Automaton automaton = new RegExp(".*d", RegExp.NONE).toAutomaton();
    CompiledAutomaton ca = new CompiledAutomaton(automaton, false, false);   
    TermsEnum te;
   
    // should seek to startTerm
    te = terms.intersect(ca, new BytesRef("aad"));
    assertEquals("abd", te.next().utf8ToString());
View Full Code Here
850
851
852
853
854
855
856
857
858
859
860
    w.close();
    AtomicReader sub = getOnlySegmentReader(r);
    Terms terms = sub.fields().terms("field");

    Automaton automaton = new RegExp(".*", RegExp.NONE).toAutomaton();  // accept ALL
    CompiledAutomaton ca = new CompiledAutomaton(automaton, false, false);   

    TermsEnum te = terms.intersect(ca, null);
    DocsEnum de;

    assertEquals("", te.next().utf8ToString());
View Full Code Here
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
   
    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
768
769
770
771
772
773
774
775
776
777
778
779
        try {
            List<Term> terms = new ArrayList<Term>();
            Term onTerm = newFulltextTerm(token, fieldName);
            Terms t = MultiFields.getTerms(reader, onTerm.field());
            Automaton a = WildcardQuery.toAutomaton(onTerm);
            CompiledAutomaton ca = new CompiledAutomaton(a);
            TermsEnum te = ca.getTermsEnum(t);
            BytesRef text;
            while ((text = te.next()) != null) {
                terms.add(newFulltextTerm(text.utf8ToString(), fieldName));
            }
            return terms.toArray(new Term[terms.size()]);
View Full Code Here
802
803
804
805
806
807
808
809
810
811
812
813
        try {
            List<Term> terms = new ArrayList<Term>();
            Term onTerm = newFulltextTerm(token, fieldName);
            Terms t = MultiFields.getTerms(reader, onTerm.field());
            Automaton a = WildcardQuery.toAutomaton(onTerm);
            CompiledAutomaton ca = new CompiledAutomaton(a);
            TermsEnum te = ca.getTermsEnum(t);
            BytesRef text;
            while ((text = te.next()) != null) {
                terms.add(newFulltextTerm(text.utf8ToString(), fieldName));
            }
            return terms.toArray(new Term[terms.size()]);
View Full Code Here
238
239
240
241
242
243
244
245
246
247
248
   
    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
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
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.