Package org.apache.lucene.codecs

Examples of org.apache.lucene.codecs.TermVectorsReader

191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
    }
    reader.close();
  }

  public void testReader() throws IOException {
    TermVectorsReader reader = Codec.getDefault().termVectorsFormat().vectorsReader(dir, seg.info, fieldInfos, newIOContext(random()));
    for (int j = 0; j < 5; j++) {
      Terms vector = reader.get(j).terms(testFields[0]);
      assertNotNull(vector);
      assertEquals(testTerms.length, vector.size());
      TermsEnum termsEnum = vector.iterator(null);
      for (int i = 0; i < testTerms.length; i++) {
        final BytesRef text = termsEnum.next();
        assertNotNull(text);
        String term = text.utf8ToString();
        //System.out.println("Term: " + term);
        assertEquals(testTerms[i], term);
      }
      assertNull(termsEnum.next());
    }
    reader.close();
  }
View Full Code Here
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
    }
    reader.close();
  }
 
  public void testDocsEnum() throws IOException {
    TermVectorsReader reader = Codec.getDefault().termVectorsFormat().vectorsReader(dir, seg.info, fieldInfos, newIOContext(random()));
    for (int j = 0; j < 5; j++) {
      Terms vector = reader.get(j).terms(testFields[0]);
      assertNotNull(vector);
      assertEquals(testTerms.length, vector.size());
      TermsEnum termsEnum = vector.iterator(null);
      DocsEnum docsEnum = null;
      for (int i = 0; i < testTerms.length; i++) {
        final BytesRef text = termsEnum.next();
        assertNotNull(text);
        String term = text.utf8ToString();
        //System.out.println("Term: " + term);
        assertEquals(testTerms[i], term);
       
        docsEnum = _TestUtil.docs(random(), termsEnum, null, docsEnum, DocsEnum.FLAG_NONE);
        assertNotNull(docsEnum);
        int doc = docsEnum.docID();
        assertEquals(-1, doc);
        assertTrue(docsEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
        assertEquals(DocIdSetIterator.NO_MORE_DOCS, docsEnum.nextDoc());
      }
      assertNull(termsEnum.next());
    }
    reader.close();
  }
View Full Code Here
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
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
    }
    reader.close();
  }

  public void testPositionReader() throws IOException {
    TermVectorsReader reader = Codec.getDefault().termVectorsFormat().vectorsReader(dir, seg.info, fieldInfos, newIOContext(random()));
    BytesRef[] terms;
    Terms vector = reader.get(0).terms(testFields[0]);
    assertNotNull(vector);
    assertEquals(testTerms.length, vector.size());
    TermsEnum termsEnum = vector.iterator(null);
    DocsAndPositionsEnum dpEnum = null;
    for (int i = 0; i < testTerms.length; i++) {
      final BytesRef text = termsEnum.next();
      assertNotNull(text);
      String term = text.utf8ToString();
      //System.out.println("Term: " + term);
      assertEquals(testTerms[i], term);

      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      assertNotNull(dpEnum);
      int doc = dpEnum.docID();
      assertEquals(-1, doc);
      assertTrue(dpEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
      assertEquals(dpEnum.freq(), positions[i].length);
      for (int j = 0; j < positions[i].length; j++) {
        assertEquals(positions[i][j], dpEnum.nextPosition());
      }
      assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum.nextDoc());

      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      doc = dpEnum.docID();
      assertEquals(-1, doc);
      assertTrue(dpEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
      assertNotNull(dpEnum);
      assertEquals(dpEnum.freq(), positions[i].length);
      for (int j = 0; j < positions[i].length; j++) {
        assertEquals(positions[i][j], dpEnum.nextPosition());
        assertEquals(j*10, dpEnum.startOffset());
        assertEquals(j*10 + testTerms[i].length(), dpEnum.endOffset());
      }
      assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum.nextDoc());
    }

    Terms freqVector = reader.get(0).terms(testFields[1]); //no pos, no offset
    assertNotNull(freqVector);
    assertEquals(testTerms.length, freqVector.size());
    termsEnum = freqVector.iterator(null);
    assertNotNull(termsEnum);
    for (int i = 0; i < testTerms.length; i++) {
      final BytesRef text = termsEnum.next();
      assertNotNull(text);
      String term = text.utf8ToString();
      //System.out.println("Term: " + term);
      assertEquals(testTerms[i], term);
      assertNotNull(termsEnum.docs(null, null));
      assertNull(termsEnum.docsAndPositions(null, null)); // no pos
    }
    reader.close();
  }
View Full Code Here
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
    }
    reader.close();
  }

  public void testOffsetReader() throws IOException {
    TermVectorsReader reader = Codec.getDefault().termVectorsFormat().vectorsReader(dir, seg.info, fieldInfos, newIOContext(random()));
    Terms vector = reader.get(0).terms(testFields[0]);
    assertNotNull(vector);
    TermsEnum termsEnum = vector.iterator(null);
    assertNotNull(termsEnum);
    assertEquals(testTerms.length, vector.size());
    DocsAndPositionsEnum dpEnum = null;
    for (int i = 0; i < testTerms.length; i++) {
      final BytesRef text = termsEnum.next();
      assertNotNull(text);
      String term = text.utf8ToString();
      assertEquals(testTerms[i], term);

      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      assertNotNull(dpEnum);
      assertTrue(dpEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
      assertEquals(dpEnum.freq(), positions[i].length);
      for (int j = 0; j < positions[i].length; j++) {
        assertEquals(positions[i][j], dpEnum.nextPosition());
      }
      assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum.nextDoc());

      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      assertTrue(dpEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
      assertNotNull(dpEnum);
      assertEquals(dpEnum.freq(), positions[i].length);
      for (int j = 0; j < positions[i].length; j++) {
        assertEquals(positions[i][j], dpEnum.nextPosition());
        assertEquals(j*10, dpEnum.startOffset());
        assertEquals(j*10 + testTerms[i].length(), dpEnum.endOffset());
      }
      assertEquals(DocIdSetIterator.NO_MORE_DOCS, dpEnum.nextDoc());
    }
    reader.close();
  }
View Full Code Here
732
733
734
735
736
737
738
739
740
741
742
    for (AtomicReader reader : mergeState.readers) {
      final SegmentReader matchingSegmentReader = mergeState.matchingSegmentReaders[idx++];
      CompressingTermVectorsReader matchingVectorsReader = null;
      if (matchingSegmentReader != null) {
        final TermVectorsReader vectorsReader = matchingSegmentReader.getTermVectorsReader();
        // we can only bulk-copy if the matching reader is also a CompressingTermVectorsReader
        if (vectorsReader != null && vectorsReader instanceof CompressingTermVectorsReader) {
          matchingVectorsReader = (CompressingTermVectorsReader) vectorsReader;
        }
      }
View Full Code Here
302
303
304
305
306
307
308
309
310
311
312
313
    return core.termVectorsLocal.get();
  }

  @Override
  public Fields getTermVectors(int docID) throws IOException {
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null) {
      return null;
    }
    checkBounds(docID);
    return termVectorsReader.get(docID);
  }
View Full Code Here
305
306
307
308
309
310
311
312
313
314
315
316
    return core.termVectorsLocal.get();
  }

  @Override
  public Fields getTermVectors(int docID) throws IOException {
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null) {
      return null;
    }
    checkBounds(docID);
    return termVectorsReader.get(docID);
  }
View Full Code Here
314
315
316
317
318
319
320
321
322
323
324
325
    return core.termVectorsLocal.get();
  }

  @Override
  public Fields getTermVectors(int docID) throws IOException {
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null) {
      return null;
    }
    checkBounds(docID);
    return termVectorsReader.get(docID);
  }
View Full Code Here
575
576
577
578
579
580
581
582
583
584
585
586
587
   
    // stored fields
    getFieldsReader().checkIntegrity();
   
    // term vectors
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader != null) {
      termVectorsReader.checkIntegrity();
    }
   
    // terms/postings
    if (core.fields != null) {
      core.fields.checkIntegrity();
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
    return core.termVectorsLocal.get();
  }

  @Override
  public Fields getTermVectors(int docID) throws IOException {
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null) {
      return null;
    }
    checkBounds(docID);
    return termVectorsReader.get(docID);
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.codecs.TermVectorsReader

  • org.apache.lucene.codecs.compressing.CompressingTermVectorsWriter
  • org.apache.lucene.codecs.lucene40.Lucene40TermVectorsWriter
  • org.apache.lucene.index.SegmentReader
  • org.apache.lucene.index.TestTermVectorsReader
    • 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.