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

Package org.apache.lucene.util.automaton

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

org.apache.lucene.util.automaton.Automaton
Finite-state automaton with regular expression operations.
Class invariants:
- An automaton is either represented explicitly (with {@link State} and{@link Transition} objects) or with a singleton string (see{@link #getSingleton()} and {@link #expandSingleton()}) in case the automaton is known to accept exactly one string. (Implicitly, all states and transitions of an automaton are reachable from its initial state.)
- Automata are always reduced (see {@link #reduce()}) and have no transitions to dead states (see {@link #removeDeadTransitions()}).
- If an automaton is nondeterministic, then {@link #isDeterministic()}returns false (but the converse is not required).
- Automata provided as input to operations are generally assumed to be disjoint.
If the states or transitions are manipulated manually, the {@link #restoreInvariant()} and {@link #setDeterministic(boolean)} methodsshould be used afterwards to restore representation invariants that are assumed by the built-in automata operations.

Note: This class has internal mutable state and is not thread safe. It is the caller's responsibility to ensure any necessary synchronization if you wish to use the same Automaton from multiple threads. In general it is instead recommended to use a {@link RunAutomaton} for multithreaded matching: it is immutable, thread safe, and much faster.
@lucene.experimental

    final TokenStream ts = new CannedTokenStream(
      new Token[] {
        token("abc", 1, 1),
        token("xyz", 0, 1)
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton a1 = BasicAutomata.makeString("abc");
    final Automaton a2 = BasicAutomata.makeString("xyz");
    final Automaton expected = BasicOperations.union(a1, a2);
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

      new Token[] {
        token("abc", 1, 1),
        token("xyz", 0, 2),
        token("def", 1, 1),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton a1 = BasicAutomata.makeString("xyz");
    final Automaton a2 = join("abc", "def");
                                                                   
    final Automaton expected = BasicOperations.union(a1, a2);
    //toDot(actual);
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

      new Token[] {
        token("a", 1, 1),
        token("X", 0, 2),
        token("b", 2, 1),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton a1 = BasicOperations.union(
                                               join(s2a("a"), SEP_A, HOLE_A),
                                               BasicAutomata.makeString("X"));
    final Automaton expected = BasicOperations.concatenate(a1,
                                                           join(SEP_A, s2a("b")));
    //toDot(actual);
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

      new Token[] {
        token("xyz", 1, 1),
        token("abc", 0, 3),
        token("def", 2, 1),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton expected = BasicOperations.union(
                                                     join(s2a("xyz"), SEP_A, HOLE_A, SEP_A, s2a("def")),
                                                     BasicAutomata.makeString("abc"));
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

        token("abc", 1, 1),
        token("xyz", 0, 3),
        token("def", 1, 1),
        token("ghi", 1, 1),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton a1 = BasicAutomata.makeString("xyz");
    final Automaton a2 = join("abc", "def", "ghi");
    final Automaton expected = BasicOperations.union(a1, a2);
    //toDot(actual);
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

  public void testStartsWithHole() throws Exception {
    final TokenStream ts = new CannedTokenStream(
      new Token[] {
        token("abc", 2, 1),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton expected = join(HOLE_A, SEP_A, s2a("abc"));
    //toDot(actual);
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here

    final TokenStream ts = new CannedTokenStream(
      new Token[] {
        token("a", 1, 1),
        token("X", 0, 10),
      });
    final Automaton actual = (new TokenStreamToAutomaton()).toAutomaton(ts);
    final Automaton expected = BasicOperations.union(BasicAutomata.makeString("a"),
                                                     BasicAutomata.makeString("X"));
    assertTrue(BasicOperations.sameLanguage(expected, actual));
  }

View Full Code Here


    //System.out.println("lookup key=" + key + " num=" + num);
    final BytesRef utf8Key = new BytesRef(key);
    try {


      Automaton lookupAutomaton = toLookupAutomaton(key);


      final CharsRef spare = new CharsRef();


      //System.out.println("  now intersect exactFirst=" + exactFirst);

View Full Code Here

    TokenStream ts = indexAnalyzer.tokenStream("", new StringReader(surfaceForm.utf8ToString()));


    // Create corresponding automaton: labels are bytes
    // from each analyzed token, with byte 0 used as
    // separator between tokens:
    Automaton automaton = ts2a.toAutomaton(ts);
    ts.end();
    ts.close();


    replaceSep(automaton);

View Full Code Here


  final Automaton toLookupAutomaton(final CharSequence key) throws IOException {
    // TODO: is there a Reader from a CharSequence?
    // Turn tokenstream into automaton:
    TokenStream ts = queryAnalyzer.tokenStream("", new StringReader(key.toString()));
    Automaton automaton = (getTokenStreamToAutomaton()).toAutomaton(ts);
    ts.end();
    ts.close();


    // TODO: we could use the end offset to "guess"
    // whether the final token was a partial token; this

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

org.apache.jackrabbit.oak.plugins.index.lucene.LuceneIndex

org.apache.jackrabbit.oak.plugins.index.lucene.LucenePropertyIndex

org.apache.lucene.analysis.core.TestDuelingAnalyzers

org.apache.lucene.analysis.TestGraphTokenizers

org.apache.lucene.analysis.TokenStreamToAutomaton

org.apache.lucene.index.TestIndexWriter

org.apache.lucene.index.TestTermsEnum

org.apache.lucene.search.FuzzyTermsEnum

org.apache.lucene.search.postingshighlight.MultiTermHighlighting

org.apache.lucene.search.suggest.analyzing.AnalyzingSuggester

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.