Package org.apache.lucene.codecs

Examples of org.apache.lucene.codecs.PostingsWriterBase

169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
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
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
297
298
299
300
301
302
303
304
305
306
    final Random random = new Random(seed);
   
    random.nextInt(); // consume a random for buffersize

    PostingsWriterBase postingsWriter;
    if (random.nextBoolean()) {
      postingsWriter = new SepPostingsWriter(state, new MockIntStreamFactory(random), skipInterval);
    } else {
      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing Standard postings");
      }
      // TODO: randomize variables like acceptibleOverHead?!
      postingsWriter = new Lucene41PostingsWriter(state, skipInterval);
    }

    if (random.nextBoolean()) {
      final int totTFCutoff = TestUtil.nextInt(random, 1, 20);
      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing pulsing postings with totTFCutoff=" + totTFCutoff);
      }
      postingsWriter = new PulsingPostingsWriter(state, totTFCutoff, postingsWriter);
    }

    final FieldsConsumer fields;
    final int t1 = random.nextInt(4);

    if (t1 == 0) {
      boolean success = false;
      try {
        fields = new FSTTermsWriter(state, postingsWriter);
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }
    } else if (t1 == 1) {
      boolean success = false;
      try {
        fields = new FSTOrdTermsWriter(state, postingsWriter);
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }
    } else if (t1 == 2) {
      // Use BlockTree terms dict

      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing BlockTree terms dict");
      }

      // TODO: would be nice to allow 1 but this is very
      // slow to write
      final int minTermsInBlock = TestUtil.nextInt(random, 2, 100);
      final int maxTermsInBlock = Math.max(2, (minTermsInBlock-1)*2 + random.nextInt(100));

      boolean success = false;
      try {
        fields = new BlockTreeTermsWriter(state, postingsWriter, minTermsInBlock, maxTermsInBlock);
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }
    } else {

      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing Block terms dict");
      }

      boolean success = false;

      final TermsIndexWriterBase indexWriter;
      try {
        if (random.nextBoolean()) {
          state.termIndexInterval = TestUtil.nextInt(random, 1, 100);
          if (LuceneTestCase.VERBOSE) {
            System.out.println("MockRandomCodec: fixed-gap terms index (tii=" + state.termIndexInterval + ")");
          }
          indexWriter = new FixedGapTermsIndexWriter(state);
        } else {
          final VariableGapTermsIndexWriter.IndexTermSelector selector;
          final int n2 = random.nextInt(3);
          if (n2 == 0) {
            final int tii = TestUtil.nextInt(random, 1, 100);
            selector = new VariableGapTermsIndexWriter.EveryNTermSelector(tii);
           if (LuceneTestCase.VERBOSE) {
              System.out.println("MockRandomCodec: variable-gap terms index (tii=" + tii + ")");
            }
          } else if (n2 == 1) {
            final int docFreqThresh = TestUtil.nextInt(random, 2, 100);
            final int tii = TestUtil.nextInt(random, 1, 100);
            selector = new VariableGapTermsIndexWriter.EveryNOrDocFreqTermSelector(docFreqThresh, tii);
          } else {
            final long seed2 = random.nextLong();
            final int gap = TestUtil.nextInt(random, 2, 40);
            if (LuceneTestCase.VERBOSE) {
             System.out.println("MockRandomCodec: random-gap terms index (max gap=" + gap + ")");
            }
           selector = new VariableGapTermsIndexWriter.IndexTermSelector() {
                final Random rand = new Random(seed2);

                @Override
                public boolean isIndexTerm(BytesRef term, TermStats stats) {
                  return rand.nextInt(gap) == gap/2;
                }

                @Override
                  public void newField(FieldInfo fieldInfo) {
                }
              };
          }
          indexWriter = new VariableGapTermsIndexWriter(state, selector);
        }
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }

      success = false;
      try {
        fields = new BlockTermsWriter(indexWriter, state, postingsWriter);
        success = true;
      } finally {
        if (!success) {
          try {
            postingsWriter.close();
          } finally {
            indexWriter.close();
          }
        }
      }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    if (!LuceneTestCase.OLD_FORMAT_IMPERSONATION_IS_ACTIVE) {
      return super.fieldsConsumer(state);
    } else {
      PostingsWriterBase docs = new Lucene40PostingsWriter(state);
     
      // TODO: should we make the terms index more easily
      // pluggable?  Ie so that this codec would record which
      // index impl was used, and switch on loading?
      // Or... you must make a new Codec for this?
      boolean success = false;
      try {
        FieldsConsumer ret = new BlockTreeTermsWriter(state, docs, minBlockSize, maxBlockSize);
        success = true;
        return ret;
      } finally {
        if (!success) {
          docs.close();
        }
      }
    }
  }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
    super("NestedPulsing");
  }
 
  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase docsWriter = null;
    PostingsWriterBase pulsingWriterInner = null;
    PostingsWriterBase pulsingWriter = null;
   
    // Terms dict
    boolean success = false;
    try {
      docsWriter = new Lucene41PostingsWriter(state);
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    return getName() + "(freqCutoff=" + freqCutoff + " minBlockSize=" + minBlockSize + " maxBlockSize=" + maxBlockSize + ")";
  }

  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase docsWriter = null;

    // Terms that have <= freqCutoff number of docs are
    // "pulsed" (inlined):
    PostingsWriterBase pulsingWriter = null;

    // Terms dict
    boolean success = false;
    try {
      docsWriter = wrappedPostingsBaseFormat.postingsWriterBase(state);
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
    super("Lucene41WithOrds");
  }

  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase docs = new Lucene41PostingsWriter(state);

    // TODO: should we make the terms index more easily
    // pluggable?  Ie so that this codec would record which
    // index impl was used, and switch on loading?
    // Or... you must make a new Codec for this?
    TermsIndexWriterBase indexWriter;
    boolean success = false;
    try {
      indexWriter = new FixedGapTermsIndexWriter(state);
      success = true;
    } finally {
      if (!success) {
        docs.close();
      }
    }

    success = false;
    try {
      // Must use BlockTermsWriter (not BlockTree) because
      // BlockTree doens't support ords (yet)...
      FieldsConsumer ret = new BlockTermsWriter(indexWriter, state, docs);
      success = true;
      return ret;
    } finally {
      if (!success) {
        try {
          docs.close();
        } finally {
          indexWriter.close();
        }
      }
    }
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
    }
  }

  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase postingsWriter = new SepPostingsWriter(state, new MockIntFactory(baseBlockSize));

    boolean success = false;
    TermsIndexWriterBase indexWriter;
    try {
      indexWriter = new FixedGapTermsIndexWriter(state);
      success = true;
    } finally {
      if (!success) {
        postingsWriter.close();
      }
    }

    success = false;
    try {
      FieldsConsumer ret = new BlockTermsWriter(indexWriter, state, postingsWriter);
      success = true;
      return ret;
    } finally {
      if (!success) {
        try {
          postingsWriter.close();
        } finally {
          indexWriter.close();
        }
      }
    }
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
    }
  }

  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase postingsWriter = new SepPostingsWriter(state, new MockIntFactory(blockSize));

    boolean success = false;
    TermsIndexWriterBase indexWriter;
    try {
      indexWriter = new FixedGapTermsIndexWriter(state);
      success = true;
    } finally {
      if (!success) {
        postingsWriter.close();
      }
    }

    success = false;
    try {
      FieldsConsumer ret = new BlockTermsWriter(indexWriter, state, postingsWriter);
      success = true;
      return ret;
    } finally {
      if (!success) {
        try {
          postingsWriter.close();
        } finally {
          indexWriter.close();
        }
      }
    }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
  }

  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {

    PostingsWriterBase postingsWriter = new SepPostingsWriter(state, new MockSingleIntFactory());

    boolean success = false;
    TermsIndexWriterBase indexWriter;
    try {
      indexWriter = new FixedGapTermsIndexWriter(state);
      success = true;
    } finally {
      if (!success) {
        postingsWriter.close();
      }
    }

    success = false;
    try {
      FieldsConsumer ret = new BlockTermsWriter(indexWriter, state, postingsWriter);
      success = true;
      return ret;
    } finally {
      if (!success) {
        try {
          postingsWriter.close();
        } finally {
          indexWriter.close();
        }
      }
    }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
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
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
    final Random random = new Random(seed);
   
    random.nextInt(); // consume a random for buffersize

    PostingsWriterBase postingsWriter;
    if (random.nextBoolean()) {
      postingsWriter = new SepPostingsWriter(state, new MockIntStreamFactory(random), skipInterval);
    } else {
      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing Standard postings");
      }
      // TODO: randomize variables like acceptibleOverHead?!
      postingsWriter = new Lucene41PostingsWriter(state, skipInterval);
    }

    if (random.nextBoolean()) {
      final int totTFCutoff = _TestUtil.nextInt(random, 1, 20);
      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing pulsing postings with totTFCutoff=" + totTFCutoff);
      }
      postingsWriter = new PulsingPostingsWriter(totTFCutoff, postingsWriter);
    }

    final FieldsConsumer fields;

    if (random.nextBoolean()) {
      // Use BlockTree terms dict

      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing BlockTree terms dict");
      }

      // TODO: would be nice to allow 1 but this is very
      // slow to write
      final int minTermsInBlock = _TestUtil.nextInt(random, 2, 100);
      final int maxTermsInBlock = Math.max(2, (minTermsInBlock-1)*2 + random.nextInt(100));

      boolean success = false;
      try {
        fields = new BlockTreeTermsWriter(state, postingsWriter, minTermsInBlock, maxTermsInBlock);
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }
    } else {

      if (LuceneTestCase.VERBOSE) {
        System.out.println("MockRandomCodec: writing Block terms dict");
      }

      boolean success = false;

      final TermsIndexWriterBase indexWriter;
      try {
        if (random.nextBoolean()) {
          state.termIndexInterval = _TestUtil.nextInt(random, 1, 100);
          if (LuceneTestCase.VERBOSE) {
            System.out.println("MockRandomCodec: fixed-gap terms index (tii=" + state.termIndexInterval + ")");
          }
          indexWriter = new FixedGapTermsIndexWriter(state);
        } else {
          final VariableGapTermsIndexWriter.IndexTermSelector selector;
          final int n2 = random.nextInt(3);
          if (n2 == 0) {
            final int tii = _TestUtil.nextInt(random, 1, 100);
            selector = new VariableGapTermsIndexWriter.EveryNTermSelector(tii);
           if (LuceneTestCase.VERBOSE) {
              System.out.println("MockRandomCodec: variable-gap terms index (tii=" + tii + ")");
            }
          } else if (n2 == 1) {
            final int docFreqThresh = _TestUtil.nextInt(random, 2, 100);
            final int tii = _TestUtil.nextInt(random, 1, 100);
            selector = new VariableGapTermsIndexWriter.EveryNOrDocFreqTermSelector(docFreqThresh, tii);
          } else {
            final long seed2 = random.nextLong();
            final int gap = _TestUtil.nextInt(random, 2, 40);
            if (LuceneTestCase.VERBOSE) {
             System.out.println("MockRandomCodec: random-gap terms index (max gap=" + gap + ")");
            }
           selector = new VariableGapTermsIndexWriter.IndexTermSelector() {
                final Random rand = new Random(seed2);

                @Override
                public boolean isIndexTerm(BytesRef term, TermStats stats) {
                  return rand.nextInt(gap) == gap/2;
                }

                @Override
                  public void newField(FieldInfo fieldInfo) {
                }
              };
          }
          indexWriter = new VariableGapTermsIndexWriter(state, selector);
        }
        success = true;
      } finally {
        if (!success) {
          postingsWriter.close();
        }
      }

      success = false;
      try {
        fields = new BlockTermsWriter(indexWriter, state, postingsWriter);
        success = true;
      } finally {
        if (!success) {
          try {
            postingsWriter.close();
          } finally {
            indexWriter.close();
          }
        }
      }
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
* Read-write version of {@link Lucene40PostingsFormat} for testing.
*/
public class Lucene40RWPostingsFormat extends Lucene40PostingsFormat {
  @Override
  public FieldsConsumer fieldsConsumer(SegmentWriteState state) throws IOException {
    PostingsWriterBase docs = new Lucene40PostingsWriter(state);

    // TODO: should we make the terms index more easily
    // pluggable?  Ie so that this codec would record which
    // index impl was used, and switch on loading?
    // Or... you must make a new Codec for this?
    boolean success = false;
    try {
      FieldsConsumer ret = new BlockTreeTermsWriter(state, docs, minBlockSize, maxBlockSize);
      success = true;
      return ret;
    } finally {
      if (!success) {
        docs.close();
      }
    }
  }
View Full Code Here
TOP

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

  • org.apache.lucene.codecs.appending.AppendingRWPostingsFormat
  • org.apache.lucene.codecs.idversion.IDVersionPostingsFormat
  • org.apache.lucene.codecs.lucene40.Lucene40RWPostingsFormat
  • org.apache.lucene.codecs.lucene41.Lucene41PostingsFormat
  • org.apache.lucene.codecs.lucene41ords.Lucene41WithOrds
  • org.apache.lucene.codecs.memory.FSTOrdPostingsFormat
  • org.apache.lucene.codecs.memory.FSTOrdPulsing41PostingsFormat
  • org.apache.lucene.codecs.memory.FSTPostingsFormat
  • org.apache.lucene.codecs.memory.FSTPulsing41PostingsFormat
  • org.apache.lucene.codecs.mockintblock.MockFixedIntBlockPostingsFormat
    • 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.