Package org.apache.lucene.util.automaton

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

93
94
95
96
97
98
99
   * @param term regular expression.
   * @param flags optional RegExp features from {@link RegExp}
   * @param provider custom AutomatonProvider for named automata
   */
  public NodeRegexpQuery(final Term term, final int flags, final AutomatonProvider provider) {
    super(term, new RegExp(term.text(), flags).toAutomaton(provider));
  }
View Full Code Here
327
328
329
330
331
332
333
334
335
336
337
        System.out.println("TEST: got termsEnum=" + termsEnum);
      }
      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);
View Full Code Here
102
103
104
105
106
107
108
109
  private class DumbRegexpQuery extends MultiTermQuery {
    private final Automaton automaton;
   
    DumbRegexpQuery(Term term, int flags) {
      super(term.field());
      RegExp re = new RegExp(term.text(), flags);
      automaton = re.toAutomaton();
    }
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
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
   
    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
84
85
86
87
88
89
90
91
92
93
94
 
  // Test some regular expressions as tokenization patterns
  /** Test a configuration where each character is a term */
  public void testSingleChar() throws Exception {
    CharacterRunAutomaton single =
        new CharacterRunAutomaton(new RegExp(".").toAutomaton());
    Analyzer a = new MockAnalyzer(random(), single, false);
    assertAnalyzesTo(a, "foobar",
        new String[] { "f", "o", "o", "b", "a", "r" },
        new int[] { 0, 1, 2, 3, 4, 5 },
        new int[] { 1, 2, 3, 4, 5, 6 }
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
  }
 
  /** Test a configuration where two characters makes a term */
  public void testTwoChars() throws Exception {
    CharacterRunAutomaton single =
        new CharacterRunAutomaton(new RegExp("..").toAutomaton());
    Analyzer a = new MockAnalyzer(random(), single, false);
    assertAnalyzesTo(a, "foobar",
        new String[] { "fo", "ob", "ar"},
        new int[] { 0, 2, 4 },
        new int[] { 2, 4, 6 }
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
  }
 
  /** Test a configuration where three characters makes a term */
  public void testThreeChars() throws Exception {
    CharacterRunAutomaton single =
        new CharacterRunAutomaton(new RegExp("...").toAutomaton());
    Analyzer a = new MockAnalyzer(random(), single, false);
    assertAnalyzesTo(a, "foobar",
        new String[] { "foo", "bar"},
        new int[] { 0, 3 },
        new int[] { 3, 6 }
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
  }
 
  /** Test a configuration where word starts with one uppercase */
  public void testUppercase() throws Exception {
    CharacterRunAutomaton single =
        new CharacterRunAutomaton(new RegExp("[A-Z][a-z]*").toAutomaton());
    Analyzer a = new MockAnalyzer(random(), single, false);
    assertAnalyzesTo(a, "FooBarBAZ",
        new String[] { "Foo", "Bar", "B", "A", "Z"},
        new int[] { 0, 3, 6, 7, 8 },
        new int[] { 3, 6, 7, 8, 9 }
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
        new int[] { 2, 2, 1, 2 });
  }
 
  /** Test a configuration that behaves a lot like LengthFilter */
  public void testLength() throws Exception {
    CharacterRunAutomaton length5 = new CharacterRunAutomaton(new RegExp(".{5,}").toAutomaton());
    Analyzer a = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, true, length5);
    assertAnalyzesTo(a, "ok toolong fine notfine",
        new String[] { "ok", "fine" },
        new int[] { 1, 2 });
  }
View Full Code Here
TOP

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

  • io.crate.operation.operator.RegexpMatchOperator
  • org.apache.lucene.analysis.hunspell.Dictionary
  • org.apache.lucene.analysis.TestMockAnalyzer
  • org.apache.lucene.codecs.lucene41.TestBlockPostingsFormat3
  • org.apache.lucene.index.TestDuelingCodecs
  • org.apache.lucene.index.TestTermsEnum
  • org.apache.lucene.queryparser.flexible.standard.TestQPHelper
  • org.apache.lucene.queryparser.util.QueryParserTestBase
  • org.apache.lucene.search.highlight.HighlighterTest
  • org.apache.lucene.search.RegexpQuery
    • 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.