Package org.apache.lucene.util.automaton

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

120
121
122
123
124
125
126
127
   *
   * This expression matches something either starting with the arabic
   * presentation forms block, or a supplementary character.
   */
  public void testSortOrder() throws IOException {
    Automaton a = new RegExp("((\uD866\uDF05)|\uFB94).*").toAutomaton();
    assertAutomatonHits(2, a);
  }
View Full Code Here
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
    assertEquals(two, qp.parse("/foo/ /bar/", df));
  }

  public void testStopwords() throws Exception {
    StandardQueryParser qp = new StandardQueryParser();
    CharacterRunAutomaton stopSet = new CharacterRunAutomaton(new RegExp("the|foo").toAutomaton());
    qp.setAnalyzer(new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopSet));

    Query result = qp.parse("a:the OR a:foo", "a");
    assertNotNull("result is null and it shouldn't be", result);
    assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
View Full Code Here
344
345
346
347
348
349
350
351
352
353
354
        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
101
102
103
104
105
106
107
108
109
110
111
  public void testPhraseQueryPositionIncrements() throws Exception {
    PhraseQuery expected = new PhraseQuery();
    expected.add(new Term("field", "1"));
    expected.add(new Term("field", "2"), 2);
   
    CharacterRunAutomaton stopList = new CharacterRunAutomaton(new RegExp("[sS][tT][oO][pP]").toAutomaton());

    Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false, stopList);

    QueryBuilder builder = new QueryBuilder(analyzer);
    assertEquals(expected, builder.createPhraseQuery("field", "1 stop 2"));
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
   
    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
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
   
    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
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.