Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer


  public void test() throws Exception {

    Directory dir = new RAMDirectory();

    IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.UNLIMITED);
    Document doc = new Document();
    doc.add(new Field("foo", "bar rab abr bra rba", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    doc.add(new Field("moo", "bar rab abr bra rba", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    iw.addDocument(doc);
    iw.close();
View Full Code Here


  protected void setUp() throws Exception {
    super.setUp();
    fieldInfos = new FieldInfos();
    DocHelper.setupDoc(testDoc);
    fieldInfos.add(testDoc);
    IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    writer.setUseCompoundFile(false);
    writer.addDocument(testDoc);
    writer.close();
  }
View Full Code Here

    File file = new File(path);
    _TestUtil.rmDir(file);
    FSDirectory tmpDir = FSDirectory.open(file);
    assertTrue(tmpDir != null);

    IndexWriter writer = new IndexWriter(tmpDir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    writer.setUseCompoundFile(false);
    writer.addDocument(testDoc);
    writer.close();

    assertTrue(fieldInfos != null);
View Full Code Here

      throw new IOException("java.io.tmpdir undefined, cannot run test");
    File indexDir = new File(tempDir, "testfieldswriterexceptions");

    try {
      Directory dir = new FaultyFSDirectory(indexDir);
      IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
      for(int i=0;i<2;i++)
        writer.addDocument(testDoc);
      writer.optimize();
      writer.close();
View Full Code Here

    public void setUp() throws Exception {
        super.setUp();

        index = new RAMDirectory();
        IndexWriter writer = new IndexWriter(index,
                                             new WhitespaceAnalyzer(),
                                             true, IndexWriter.MaxFieldLength.LIMITED);
        writer.setSimilarity(sim);

        // hed is the most important field, dek is secondary
View Full Code Here

  }

  public void testSimple() throws Exception {
    assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2");
    assertQueryEquals("term term term", null, "term term term");
    assertQueryEquals("t�rm term term", new WhitespaceAnalyzer(),
        "t�rm term term");
    assertQueryEquals("�mlaut", new WhitespaceAnalyzer(), "�mlaut");

    assertQueryEquals("\"\"", new KeywordAnalyzer(), "");
    assertQueryEquals("foo:\"\"", new KeywordAnalyzer(), "foo:");

    assertQueryEquals("a AND b", null, "+a +b");
View Full Code Here

    qp.setDefaultOperator(QueryParserWrapper.OR_OPERATOR);
    assertEquals(QueryParserWrapper.OR_OPERATOR, qp.getDefaultOperator());
  }

  public void testPunct() throws Exception {
    Analyzer a = new WhitespaceAnalyzer();
    assertQueryEquals("a&b", a, "a&b");
    assertQueryEquals("a&&b", a, "a&&b");
    assertQueryEquals(".NET", a, ".NET");
  }
View Full Code Here

    public void testSetBufferSize() throws IOException {
      File indexDir = new File(System.getProperty("tempDir"), "testSetBufferSize");
      MockFSDirectory dir = new MockFSDirectory(indexDir, newRandom());
      try {
        IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
        writer.setUseCompoundFile(false);
        for(int i=0;i<37;i++) {
          Document doc = new Document();
          doc.add(new Field("content", "aaa bbb ccc ddd" + i, Field.Store.YES, Field.Index.ANALYZED));
          doc.add(new Field("id", "" + i, Field.Store.YES, Field.Index.ANALYZED));
View Full Code Here

  }

  public void testFarsiRangeCollating() throws Exception {

    RAMDirectory ramDir = new RAMDirectory();
    IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true,
        IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    doc.add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES,
        Field.Index.NOT_ANALYZED));
    iw.addDocument(doc);
    iw.close();
    IndexSearcher is = new IndexSearcher(ramDir, true);

    QueryParserWrapper qp = new QueryParserWrapper("content",
        new WhitespaceAnalyzer());

    // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in
    // RuleBasedCollator. However, the Arabic Locale seems to order the Farsi
    // characters properly.
    Collator c = Collator.getInstance(new Locale("ar"));
View Full Code Here

        + "}", "{" + getDate(startDate, resolution) + " TO "
        + getDate(endDate, resolution) + "}");
  }

  public void testEscaped() throws Exception {
    Analyzer a = new WhitespaceAnalyzer();

    /*
     * assertQueryEquals("\\[brackets", a, "\\[brackets");
     * assertQueryEquals("\\[brackets", null, "brackets");
     * assertQueryEquals("\\\\", a, "\\\\"); assertQueryEquals("\\+blah", a,
View Full Code Here

TOP

Related Classes of org.apache.lucene.analysis.WhitespaceAnalyzer

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.