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

Package org.apache.lucene.util.automaton

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

org.apache.lucene.util.automaton.CharacterRunAutomaton
Automaton representation for matching char[].

    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        String goodWord = "goodtoken";
        CharacterRunAutomaton stopWords = new CharacterRunAutomaton(BasicAutomata.makeString("stoppedtoken"));
        // we disable MockTokenizer checks because we will forcefully limit the 
        // tokenstream and call end() before incrementToken() returns false.
        final MockAnalyzer analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopWords);
        analyzer.setEnableChecks(false);
        TermQuery query = new TermQuery(new Term("data", goodWord));

View Full Code Here

  
  public void testMaxSizeEndHighlight() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {
      @Override
      public void run() throws Exception {
        CharacterRunAutomaton stopWords = new CharacterRunAutomaton(new RegExp("i[nt]").toAutomaton());
        TermQuery query = new TermQuery(new Term("text", "searchterm"));


        String text = "this is a text with searchterm in it";
        SimpleHTMLFormatter fm = new SimpleHTMLFormatter();
        Highlighter hg = getHighlighter(query, "text", fm);

View Full Code Here

    assertQueryEqualsDOA("-term term term", null, "-term +term +term");
  }


  public void testBoost()
    throws Exception {
    CharacterRunAutomaton stopWords = new CharacterRunAutomaton(BasicAutomata.makeString("on"));
    Analyzer oneStopAnalyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopWords);
    CommonQueryParserConfiguration qp = getParserConfig(oneStopAnalyzer);
    Query q = getQuery("on^1.0",qp);
    assertNotNull(q);
    q = getQuery("\"hello\"^2.0",qp);

View Full Code Here

    assertEquals(two, getQuery("field:/foo/ field:/bar/",qp));
    assertEquals(two, getQuery("/foo/ /bar/",qp));
  }
  
  public void testStopwords() throws Exception {
    CharacterRunAutomaton stopSet = new CharacterRunAutomaton(new RegExp("the|foo").toAutomaton());
    CommonQueryParserConfiguration qp = getParserConfig(new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopSet));
    Query result = getQuery("field:the OR field:foo",qp);
    assertNotNull("result is null and it shouldn't be", result);
    assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery);
    assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: " + 0, ((BooleanQuery) result).clauses().size() == 0);

View Full Code Here

    }
    setDefaultField(oldDefaultField);
  }


  public void testPhraseQueryPositionIncrements() throws Exception {
    CharacterRunAutomaton stopStopList =
    new CharacterRunAutomaton(new RegExp("[sS][tT][oO][pP]").toAutomaton());


    CommonQueryParserConfiguration qp = getParserConfig(new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false, stopStopList));


    qp = getParserConfig(
                         new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false, stopStopList));

View Full Code Here

  /** checks condition of the concatenation of two strings */
  // note: this is pretty stupid, we really should subtract strip from the condition up front and just check the stem
  // but this is a little bit more complicated.
  private boolean checkCondition(int condition, char c1[], int c1off, int c1len, char c2[], int c2off, int c2len) {
    if (condition != 0) {
      CharacterRunAutomaton pattern = dictionary.patterns.get(condition);
      int state = pattern.getInitialState();
      for (int i = c1off; i < c1off + c1len; i++) {
        state = pattern.step(state, c1[i]);
        if (state == -1) {
          return false;
        }
      }
      for (int i = c2off; i < c2off + c2len; i++) {
        state = pattern.step(state, c2[i]);
        if (state == -1) {
          return false;
        }
      }
      return pattern.isAccept(state);
    }
    return true;
  }

View Full Code Here


    final Map<String, Analyzer> fieldAnalyzers = new TreeMap<>();
    fieldAnalyzers.put( "field", new MockAnalyzer( random(), MockTokenizer.WHITESPACE, true, MockTokenFilter.ENGLISH_STOPSET ) );
    fieldAnalyzers.put( "field_exact", new MockAnalyzer( random() ) );
    fieldAnalyzers.put( "field_super_exact", new MockAnalyzer( random(), MockTokenizer.WHITESPACE, false ) );
    fieldAnalyzers.put( "field_characters", new MockAnalyzer( random(), new CharacterRunAutomaton( new RegExp(".").toAutomaton() ), true ) );
    fieldAnalyzers.put( "field_tripples", new MockAnalyzer( random(), new CharacterRunAutomaton( new RegExp("...").toAutomaton() ), true ) );
    fieldAnalyzers.put( "field_sliced", fieldAnalyzers.get( "field" ) );
    fieldAnalyzers.put( "field_der_red", fieldAnalyzers.get( "field" ) );  // This is required even though we provide a token stream
    Analyzer analyzer = new AnalyzerWrapper() {
      public Analyzer getWrappedAnalyzer(String fieldName) {
        return fieldAnalyzers.get( fieldName );

View Full Code Here

    assertQueryEqualsDOA("term +term +term", null, "+term +term +term");
    assertQueryEqualsDOA("-term term term", null, "-term +term +term");
  }


  public void testBoost() throws Exception {
    CharacterRunAutomaton stopSet = new CharacterRunAutomaton(BasicAutomata.makeString("on"));
    Analyzer oneStopAnalyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopSet);


    PrecedenceQueryParser qp = new PrecedenceQueryParser();
    qp.setAnalyzer(oneStopAnalyzer);
    Query q = qp.parse("on^1.0", "field");

View Full Code Here

    assertQueryEqualsDOA("term +term +term", null, "+term +term +term");
    assertQueryEqualsDOA("-term term term", null, "-term +term +term");
  }


  public void testBoost() throws Exception {
    CharacterRunAutomaton stopSet = new CharacterRunAutomaton(BasicAutomata.makeString("on"));
    Analyzer oneStopAnalyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, stopSet);
    StandardQueryParser qp = new StandardQueryParser();
    qp.setAnalyzer(oneStopAnalyzer);


    Query q = qp.parse("on^1.0", "field");

View Full Code Here

    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

0 1 2 3 4 5 6 7 8

TOP

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

org.apache.lucene.analysis.core.TestDuelingAnalyzers

org.apache.lucene.analysis.hunspell.Dictionary

org.apache.lucene.analysis.hunspell.Stemmer

org.apache.lucene.analysis.TestMockAnalyzer

org.apache.lucene.index.TestIndexWriter

org.apache.lucene.queryparser.flexible.precedence.TestPrecedenceQueryParser

org.apache.lucene.queryparser.flexible.standard.TestQPHelper

org.apache.lucene.queryparser.util.QueryParserTestBase

org.apache.lucene.search.highlight.HighlighterTest

org.apache.lucene.search.postingshighlight.MultiTermHighlighting

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.