Package org.apache.lucene.index

Examples of org.apache.lucene.index.TermDocs

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
        BitSet bits = new BitSet(reader.maxDoc());
        //Match all search terms.
        for (int i=0; i < searchTerms.length; i++) {
            //Get an enumeration of all the documents that match the specified
            //field value.
            TermDocs matchingDocs = reader.termDocs(searchTerms[i]);
            try {
                if (matchingDocs != null) {
                    while(matchingDocs.next()) {
                        bits.set(matchingDocs.doc());
                    }
                }
            }
            finally {
                if (matchingDocs != null) {
                    matchingDocs.close();
                }
            }
        }
        return bits;
    }
View Full Code Here
116
117
118
119
120
121
122
123
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
156
        term = new Term(name,val);
      }
     
      @Override
      public DocIdSetIterator iterator() throws IOException {
        final TermDocs td = _reader.termDocs(term);
        if (td==null){
          return EmptyDocIdSet.getInstance().iterator();
        }
        return new DocIdSetIterator(){

          private int _doc = -1;
          @Override
          public int advance(int target) throws IOException {
            if (td.skipTo(target)){
              _doc = td.doc();
            }
            else{
              td.close();
              _doc= DocIdSetIterator.NO_MORE_DOCS;
            }
            return _doc;
          }

          @Override
          public int docID() {
            return _doc;
          }

          @Override
          public int nextDoc() throws IOException {
            if (td.next()){
              _doc = td.doc();
            }
            else{
              td.close();
              _doc = DocIdSetIterator.NO_MORE_DOCS;
            }
            return _doc;
          }
         
View Full Code Here
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
   
    IntArrayList minIDList=new IntArrayList();
      IntArrayList maxIDList=new IntArrayList();
      IntArrayList freqList = new IntArrayList();
     
    TermDocs termDocs = null;
    TermEnum termEnum = null;
    int t = 0; // current term number
    mterms.add(null);
    minIDList.add(-1);
      maxIDList.add(-1);
      freqList.add(0);
    t++;
    try {
      termDocs = reader.termDocs();
      termEnum = reader.terms(new Term(_indexFieldName, ""));
      do {
        if (termEnum == null)
          break;
        Term term = termEnum.term();
        if (term == null || !_indexFieldName.equals(term.field()))
          break;

        // store term text
        // we expect that there is at most one term per document
        if (t > MAX_VAL_COUNT) {
          throw new IOException("maximum number of value cannot exceed: "
              + MAX_VAL_COUNT);
        }
        String val = term.text();
        mterms.add(val);
        int bit = (0x00000001 << (t-1));
        termDocs.seek(termEnum);
        //freqList.add(termEnum.docFreq());  // removed because the df doesn't take into account the num of deletedDocs
        int df = 0;
        int minID=-1;
            int maxID=-1;
            if(termDocs.next())
            {
              df++;
                  int docid = termDocs.doc();
                  order.add(docid, order.get(docid) | bit);
                  minID = docid;
                  while (termDocs.next())
              {
                    df++;
                    docid = termDocs.doc();
                    order.add(docid, order.get(docid) | bit);
              }
          maxID = docid;
            }
              freqList.add(df);
        minIDList.add(minID);
            maxIDList.add(maxID);
        t++;
      } while (termEnum.next());
    } finally {
      try {
        if (termDocs != null) {
          termDocs.close();
        }
      } finally {
        if (termEnum != null) {
          termEnum.close();
        }
View Full Code Here
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
   *
   * @return a Lucene document of the representative bookmark
   */
  public Document findLeadDocument(String urlHash) {
    IndexReader reader = null;
    TermDocs termDocs = null;
    Document leadDoc = null;
    try {
      boolean exists = IndexReader.indexExists(indexDirectory);
      if (exists == true) {
        reader = IndexReader.open(indexDirectory);
        Term key = new Term(DocumentCreator.FIELD_URL_MD5, urlHash);
        termDocs = reader.termDocs(key);
        boolean found = false;
        while (termDocs.next() && found == false) {
          int pos = termDocs.doc();
          // use FieldSelector for more efficient loading of Fields.
          // load only what's needed to determine a leading document
          Document d = reader.document(pos, new FieldSelector() {
            private static final long serialVersionUID = 1426724242925499003L;

            public FieldSelectorResult accept(String field) {
              if (field.equals(DocumentCreator.FIELD_INDEX_TYPE)) {
                return FieldSelectorResult.LOAD_AND_BREAK;
              } else {
                return FieldSelectorResult.NO_LOAD;
              }
            }
          });
          String[] values = d
              .getValues(DocumentCreator.FIELD_INDEX_TYPE);
          if (values != null) {
            List<String> vList = Arrays.asList(values);
            if (vList.contains(DocumentCreator.INDEX_TYPE_LEAD) == true) {
              leadDoc = reader.document(pos);
              found = true;
            }
          }
        }
      }
    } catch (Exception e) {
      logger.error("FindLeadDocument failed to find doc: " + urlHash
          + ", exception=" + e);
    } finally {
      try {
        if (termDocs != null) {
          termDocs.close();
        }
        if (reader != null) {
          reader.close();
        }
      } catch (Exception e) {
View Full Code Here
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
   *
   * @return a Lucene document of a non-representative bookmark
   */
  public Document findNonLeadDocument(String urlHash) {
    IndexReader reader = null;
    TermDocs termDocs = null;
    Document leadDoc = null;
    try {
      boolean exists = IndexReader.indexExists(indexDirectory);
      if (exists == true) {
        reader = IndexReader.open(indexDirectory);
        Term key = new Term(DocumentCreator.FIELD_URL_MD5, urlHash);
        termDocs = reader.termDocs(key);
        boolean found = false;
        while (termDocs.next() && found == false) {
          int pos = termDocs.doc();
          // use FieldSelector for more efficient loading of Fields.
          // load only what's needed to determine a leading document
          Document d = reader.document(pos, new FieldSelector() {
            private static final long serialVersionUID = 1426724242925499003L;

            public FieldSelectorResult accept(String field) {
              if (field.equals(DocumentCreator.FIELD_INDEX_TYPE)) {
                return FieldSelectorResult.LOAD_AND_BREAK;
              } else {
                return FieldSelectorResult.NO_LOAD;
              }
            }

          });
          String[] values = d
              .getValues(DocumentCreator.FIELD_INDEX_TYPE);
          if (values != null) {
            List<String> vList = Arrays.asList(values);
            if (vList.contains(DocumentCreator.INDEX_TYPE_LEAD) == false) {
              leadDoc = reader.document(pos);
              found = true;
            }
          } else {
            leadDoc = reader.document(pos);
            found = true;
          }
        }
      }
    } catch (Exception e) {
      logger.error("FindLeadDocument failed to find doc hash: " + urlHash
          + ", exception=" + e);
    } finally {
      try {
        if (termDocs != null) {
          termDocs.close();
        }
        if (reader != null) {
          reader.close();
        }
      } catch (Exception e) {
View Full Code Here
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
121
122
123
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
156
    IntArrayList freqList = new IntArrayList();

    int length = maxDoc + 1;
    TermValueList<T> list = listFactory == null ? (TermValueList<T>) new TermStringList()
        : listFactory.createTermList();
    TermDocs termDocs = reader.termDocs();
    TermEnum termEnum = reader.terms(new Term(field, ""));
    int t = 0; // current term number

    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    // int df = 0;
    t++;
    try
    {
      do
      {
        Term term = termEnum.term();
        if (term == null || term.field() != field)
          break;

        if (t > order.maxValue())
        {
          throw new IOException("maximum number of value cannot exceed: "
              + order.maxValue());
        }
        // store term text
        // we expect that there is at most one term per document
        if (t >= length)
          throw new RuntimeException("there are more terms than "
              + "documents in field \"" + field
              + "\", but it's impossible to sort on " + "tokenized fields");
        list.add(term.text());
        termDocs.seek(termEnum);
        // freqList.add(termEnum.docFreq()); // doesn't take into account
        // deldocs
        int minID = -1;
        int maxID = -1;
        int df = 0;
        if (termDocs.next())
        {
          df++;
          int docid = termDocs.doc();
          order.add(docid, t);
          minID = docid;
          while (termDocs.next())
          {
            df++;
            docid = termDocs.doc();
            order.add(docid, t);
          }
          maxID = docid;
        }
        freqList.add(df);
        minIDList.add(minID);
        maxIDList.add(maxID);

        t++;
      } while (termEnum.next());
    } finally
    {
      termDocs.close();
      termEnum.close();
    }
    list.seal();

    this.valArray = list;
View Full Code Here
70
71
72
73
74
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
    long t0 = System.currentTimeMillis();
    int maxdoc = reader.maxDoc();
    BufferedLoader loader = getBufferedLoader(maxdoc, workArea);

    TermEnum tenum = null;
    TermDocs tdoc = null;
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>)new TermStringList() : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;
   
    _overflow = false;
    try
    {
      tdoc = reader.termDocs();
      tenum = reader.terms(new Term(fieldName, ""));
      if (tenum != null)
      {
        do
        {
          Term term = tenum.term();
          if (term == null || !fieldName.equals(term.field()))
            break;

          String val = term.text();

          if (val != null)
          {
            list.add(val);

            tdoc.seek(tenum);
            //freqList.add(tenum.docFreq()); // removed because the df doesn't take into account the num of deletedDocs
            int df = 0;
            int minID = -1;
            int maxID = -1;
            if(tdoc.next())
            {
              df++;
              int docid = tdoc.doc();
              if(!loader.add(docid, t)) logOverflow(fieldName);
              minID = docid;
              while(tdoc.next())
              {
                df++;
                docid = tdoc.doc();
                if(!loader.add(docid, t)) logOverflow(fieldName);
              }
              maxID = docid;
            }
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }

          t++;
        }
        while (tenum.next());
      }
    }
    finally
    {
      try
      {
        if (tdoc != null)
        {
          tdoc.close();
        }
      }
      finally
      {
        if (tenum != null)
View Full Code Here
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
    {
      throw new RuntimeException("failed to load due to " + e.toString(), e);
    }
   
    TermEnum tenum = null;
    TermDocs tdoc = null;
    TermValueList<T> list = (listFactory == null ? (TermValueList<T>)new TermStringList() : listFactory.createTermList());
    IntArrayList minIDList = new IntArrayList();
    IntArrayList maxIDList = new IntArrayList();
    IntArrayList freqList = new IntArrayList();

    int t = 0; // current term number
    list.add(null);
    minIDList.add(-1);
    maxIDList.add(-1);
    freqList.add(0);
    t++;

    _overflow = false;
    try
    {
      tdoc = reader.termDocs();
      tenum = reader.terms(new Term(fieldName, ""));
      if (tenum != null)
      {
        do
        {
          Term term = tenum.term();
          if(term == null || !fieldName.equals(term.field()))
            break;
         
          String val = term.text();
         
          if (val != null)
          {
            list.add(val);
           
            tdoc.seek(tenum);
            //freqList.add(tenum.docFreq()); // removed because the df doesn't take into account the num of deletedDocs
            int df = 0;
            int minID = -1;
            int maxID = -1;
            if(tdoc.next())
            {
              df++;
              int docid = tdoc.doc();
              if (!_nestedArray.addData(docid, t)) logOverflow(fieldName);
              minID = docid;
              while(tdoc.next())
              {
                df++;
                docid = tdoc.doc();
                if(!_nestedArray.addData(docid, t)) logOverflow(fieldName);
              }
              maxID = docid;
            }
            freqList.add(df);
            minIDList.add(minID);
            maxIDList.add(maxID);
          }
         
          t++;
        }
        while (tenum.next());
      }
    }
    finally
    {
      try
      {
        if (tdoc != null)
        {
          tdoc.close();
        }
      }
      finally
      {
        if (tenum != null)
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
    public BitSet bits(IndexReader reader) throws IOException {
        //Create a new BitSet with a capacity equal to the size of the index.
        BitSet bits = new BitSet(reader.maxDoc());
        //Get an enumeration of all the documents that match the specified field
        //value.
        TermDocs matchingDocs = reader.termDocs(searchTerm);
        try {
            while(matchingDocs.next()) {
                bits.set(matchingDocs.doc());
            }
        }
        finally {
            if (matchingDocs != null) {
                matchingDocs.close();
            }
        }
        return bits;
    }
View Full Code Here
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
      assertEquals(aprioriTermEnum.term(), testTermEnum.term());
      assertTrue(aprioriTermEnum.docFreq() == testTermEnum.docFreq());

      // compare termDocs seeking

      TermDocs aprioriTermDocsSeeker = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocsSeeker = testReader.termDocs(testTermEnum.term());

      while (aprioriTermDocsSeeker.next()) {
        assertTrue(testTermDocsSeeker.skipTo(aprioriTermDocsSeeker.doc()));
        assertEquals(aprioriTermDocsSeeker.doc(), testTermDocsSeeker.doc());
      }

      aprioriTermDocsSeeker.close();
      testTermDocsSeeker.close();

      // compare documents per term

      assertEquals(aprioriReader.docFreq(aprioriTermEnum.term()), testReader.docFreq(testTermEnum.term()));

      TermDocs aprioriTermDocs = aprioriReader.termDocs(aprioriTermEnum.term());
      TermDocs testTermDocs = testReader.termDocs(testTermEnum.term());

      while (true) {
        if (!aprioriTermDocs.next()) {
          assertFalse(testTermDocs.next());
          break;
        }
        assertTrue(testTermDocs.next());

        assertEquals(aprioriTermDocs.doc(), testTermDocs.doc());
        assertEquals(aprioriTermDocs.freq(), testTermDocs.freq());
      }

      aprioriTermDocs.close();
      testTermDocs.close();

      // compare term positions

      TermPositions testTermPositions = testReader.termPositions(testTermEnum.term());
      TermPositions aprioriTermPositions = aprioriReader.termPositions(aprioriTermEnum.term());
View Full Code Here
TOP

Related Classes of org.apache.lucene.index.TermDocs

  • com.browseengine.bobo.facets.data.FacetDataCache
  • com.browseengine.bobo.facets.data.MultiValueFacetDataCache
  • com.browseengine.bobo.facets.filter.AdaptiveFacetFilter$TermListRandomAccessDocIdSet$TermDocIdSet
  • com.browseengine.bobo.facets.impl.CompactMultiValueFacetHandler
  • com.esri.gpt.catalog.lucene.AclFilter
  • com.esri.gpt.catalog.lucene.LuceneIndexAdapter
  • com.gnizr.core.search.SearchIndexManager
  • org.apache.jackrabbit.core.query.lucene.AbstractExcerpt
  • org.apache.jackrabbit.core.query.lucene.CachingIndexReader
  • org.apache.jackrabbit.core.query.lucene.CachingIndexReader$CacheInitializer
    • 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.