Examples of WhitespaceAnalyzer

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
   * @throws Exception
   */
  public void testParsingAndSearching() throws Exception {
    String field = "content";
    boolean dbg = false;
    QueryParser qp = new QueryParser(Version.LUCENE_CURRENT, field, new WhitespaceAnalyzer());
    qp.setAllowLeadingWildcard(true);
    String docs[] = {
        "\\ abcdefg1",
        "\\79 hijklmn1",
        "\\\\ opqrstu1",
    };
    // queries that should find all docs
    String matchAll[] = {
        "*", "*1", "**1", "*?", "*?1", "?*1", "**", "***", "\\\\*"
    };
    // queries that should find no docs
    String matchNone[] = {
        "a*h", "a?h", "*a*h", "?a", "a?",
    };
    // queries that should be parsed to prefix queries
    String matchOneDocPrefix[][] = {
        {"a*", "ab*", "abc*", }, // these should find only doc 0
        {"h*", "hi*", "hij*", "\\\\7*"}, // these should find only doc 1
        {"o*", "op*", "opq*", "\\\\\\\\*"}, // these should find only doc 2
    };
    // queries that should be parsed to wildcard queries
    String matchOneDocWild[][] = {
        {"*a*", "*ab*", "*abc**", "ab*e*", "*g?", "*f?1", "abc**"}, // these should find only doc 0
        {"*h*", "*hi*", "*hij**", "hi*k*", "*n?", "*m?1", "hij**"}, // these should find only doc 1
        {"*o*", "*op*", "*opq**", "op*q*", "*u?", "*t?1", "opq**"}, // these should find only doc 2
    };

    // prepare the index
    RAMDirectory dir = new RAMDirectory();
    IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < docs.length; i++) {
      Document doc = new Document();
      doc.add(new Field(field,docs[i],Store.NO,Index.ANALYZED));
      iw.addDocument(doc);
    }
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

49
50
51
52
53
54
55
56
57
58
59
  @Override
  protected void setUp() throws Exception {
    super.setUp();
    dir = new RAMDirectory();
    appAnalyzer = new WhitespaceAnalyzer();
    IndexWriter writer = new IndexWriter(dir, appAnalyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
    int numDocs = 200;
    for (int i = 0; i < numDocs; i++) {
      Document doc = new Document();
      String variedFieldValue = variedFieldValues[i % variedFieldValues.length];
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

192
193
194
195
196
197
198
199
200
201
202
    numHits = search(a, "repetitiveField:vaguelyboring");
    assertTrue(numHits == 0);
  }
 
  public void testTokenStream() throws Exception {
    QueryAutoStopWordAnalyzer a = new QueryAutoStopWordAnalyzer(Version.LUCENE_CURRENT, new WhitespaceAnalyzer());
    a.addStopWords(reader, 10);
    TokenStream ts = a.tokenStream("repetitiveField", new StringReader("this boring"));
    TermAttribute termAtt = ts.getAttribute(TermAttribute.class);
    assertTrue(ts.incrementToken());
    assertEquals("this", termAtt.term());
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

151
152
153
154
155
156
157
  /**
   * subclass that acts just like whitespace analyzer for testing
   */
  private class QueryAutoStopWordSubclassAnalyzer extends QueryAutoStopWordAnalyzer {
    public QueryAutoStopWordSubclassAnalyzer(Version matchVersion) {
      super(matchVersion, new WhitespaceAnalyzer());
    }
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

47
48
49
50
51
52
53
54
55
56
57
 
  @Override
  public void setUp() throws Exception {
    super.setUp();
    RAMDirectory directory = new RAMDirectory();
    IndexWriter writer= new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < docFields.length; i++) {
      Document doc = new Document();
      doc.add(new Field(FIELD, docFields[i], Field.Store.NO, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

48
49
50
51
52
53
54
55
56
57
58
  @Override
  public void setUp() throws Exception {
    super.setUp();
    RAMDirectory directory = new RAMDirectory();
    IndexWriter writer= new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < docFields.length; i++) {
      Document doc = new Document();
      doc.add(new Field(field, docFields[i], Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
  public void testUpdateDocument() throws Exception {
    boolean optimize = true;

    Directory dir1 = new MockRAMDirectory();
    IndexWriter writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
                                         IndexWriter.MaxFieldLength.LIMITED);

    // create the index
    createIndexNoClose(!optimize, "index1", writer);

    // writer.flush(false, true, true);

    // get a reader
    IndexReader r1 = writer.getReader();
    assertTrue(r1.isCurrent());

    String id10 = r1.document(10).getField("id").stringValue();
   
    Document newDoc = r1.document(10);
    newDoc.removeField("id");
    newDoc.add(new Field("id", Integer.toString(8000), Store.YES, Index.NOT_ANALYZED));
    writer.updateDocument(new Term("id", id10), newDoc);
    assertFalse(r1.isCurrent());

    IndexReader r2 = writer.getReader();
    assertTrue(r2.isCurrent());
    assertEquals(0, count(new Term("id", id10), r2));
    assertEquals(1, count(new Term("id", Integer.toString(8000)), r2));
   
    r1.close();
    writer.close();
    assertTrue(r2.isCurrent());
   
    IndexReader r3 = IndexReader.open(dir1, true);
    assertTrue(r3.isCurrent());
    assertTrue(r2.isCurrent());
    assertEquals(0, count(new Term("id", id10), r3));
    assertEquals(1, count(new Term("id", Integer.toString(8000)), r3));

    writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
                             IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    doc.add(new Field("field", "a b c", Field.Store.NO, Field.Index.ANALYZED));
    writer.addDocument(doc);
    assertTrue(r2.isCurrent());
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
   */
  public void testAddIndexes() throws Exception {
    boolean optimize = false;

    Directory dir1 = new MockRAMDirectory();
    IndexWriter writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer.setInfoStream(infoStream);
    // create the index
    createIndexNoClose(!optimize, "index1", writer);
    writer.flush(false, true, true);

    // create a 2nd index
    Directory dir2 = new MockRAMDirectory();
    IndexWriter writer2 = new IndexWriter(dir2, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer2.setInfoStream(infoStream);
    createIndexNoClose(!optimize, "index2", writer2);
    writer2.close();

View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
 
  public void testAddIndexes2() throws Exception {
    boolean optimize = false;

    Directory dir1 = new MockRAMDirectory();
    IndexWriter writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer.setInfoStream(infoStream);

    // create a 2nd index
    Directory dir2 = new MockRAMDirectory();
    IndexWriter writer2 = new IndexWriter(dir2, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer2.setInfoStream(infoStream);
    createIndexNoClose(!optimize, "index2", writer2);
    writer2.close();
View Full Code Here

Examples of org.apache.lucene.analysis.WhitespaceAnalyzer

220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
   */
  public void testDeleteFromIndexWriter() throws Exception {
    boolean optimize = true;

    Directory dir1 = new MockRAMDirectory();
    IndexWriter writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer.setReaderTermsIndexDivisor(2);
    writer.setInfoStream(infoStream);
    // create the index
    createIndexNoClose(!optimize, "index1", writer);
    writer.flush(false, true, true);
    // get a reader
    IndexReader r1 = writer.getReader();

    String id10 = r1.document(10).getField("id").stringValue();

    // deleted IW docs should not show up in the next getReader
    writer.deleteDocuments(new Term("id", id10));
    IndexReader r2 = writer.getReader();
    assertEquals(1, count(new Term("id", id10), r1));
    assertEquals(0, count(new Term("id", id10), r2));
   
    String id50 = r1.document(50).getField("id").stringValue();
    assertEquals(1, count(new Term("id", id50), r1));
   
    writer.deleteDocuments(new Term("id", id50));
   
    IndexReader r3 = writer.getReader();
    assertEquals(0, count(new Term("id", id10), r3));
    assertEquals(0, count(new Term("id", id50), r3));
   
    String id75 = r1.document(75).getField("id").stringValue();
    writer.deleteDocuments(new TermQuery(new Term("id", id75)));
    IndexReader r4 = writer.getReader();
    assertEquals(1, count(new Term("id", id75), r3));
    assertEquals(0, count(new Term("id", id75), r4));
   
    r1.close();
    r2.close();
    r3.close();
    r4.close();
    writer.close();
       
    // reopen the writer to verify the delete made it to the directory
    writer = new IndexWriter(dir1, new WhitespaceAnalyzer(),
        IndexWriter.MaxFieldLength.LIMITED);
    writer.setInfoStream(infoStream);
    IndexReader w2r1 = writer.getReader();
    assertEquals(0, count(new Term("id", id10), w2r1));
    w2r1.close();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.