Package org.apache.lucene.index

Examples of org.apache.lucene.index.Fields

97
98
99
100
101
102
103
104
105
106
107
108
109
   */
  public static TokenStream getAnyTokenStream(IndexReader reader, int docId,
      String field, Analyzer analyzer) throws IOException {
    TokenStream ts = null;

    Fields vectors = reader.getTermVectors(docId);
    if (vectors != null) {
      Terms vector = vectors.terms(field);
      if (vector != null) {
        ts = getTokenStream(vector);
      }
    }

View Full Code Here
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
   * @throws IOException If there is a low-level I/O error
   */
  public static TokenStream getTokenStreamWithOffsets(IndexReader reader, int docId,
                                                      String field) throws IOException {

    Fields vectors = reader.getTermVectors(docId);
    if (vectors == null) {
      return null;
    }

    Terms vector = vectors.terms(field);
    if (vector == null) {
      return null;
    }

    if (!vector.hasPositions() || !vector.hasOffsets()) {
View Full Code Here
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 static TermStats[] getHighFreqTerms(IndexReader reader, int numTerms, String field, Comparator<TermStats> comparator) throws Exception {
    TermStatsQueue tiq = null;
   
    if (field != null) {
      Fields fields = MultiFields.getFields(reader);
      if (fields == null) {
        throw new RuntimeException("field " + field + " not found");
      }
      Terms terms = fields.terms(field);
      if (terms != null) {
        TermsEnum termsEnum = terms.iterator(null);
        tiq = new TermStatsQueue(numTerms, comparator);
        tiq.fill(field, termsEnum);
      }
    } else {
      Fields fields = MultiFields.getFields(reader);
      if (fields == null) {
        throw new RuntimeException("no fields found for this index");
      }
      tiq = new TermStatsQueue(numTerms, comparator);
      for (String fieldName : fields) {
        Terms terms = fields.terms(fieldName);
        if (terms != null) {
          tiq.fill(fieldName, terms.iterator(null));
        }
      }
    }
View Full Code Here
739
740
741
742
743
744
745
746
747
748
749
    in.document(docMap.newToOld(docID), visitor);
  }
 
  @Override
  public Fields fields() throws IOException {
    Fields fields = in.fields();
    if (fields == null) {
      return null;
    } else {
      return new SortingFields(fields, in.getFieldInfos(), docMap);
    }
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
    }
  }

  private static List<Term> sample(Random random, IndexReader reader, int size) throws IOException {
    List<Term> sample = new ArrayList<Term>();
    Fields fields = MultiFields.getFields(reader);
    for (String field : fields) {
      Terms terms = fields.terms(field);
      assertNotNull(terms);
      TermsEnum termsEnum = terms.iterator(null);
      while (termsEnum.next() != null) {
        if (sample.size() >= size) {
          int pos = random.nextInt(size);
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
  public void collectTermContext(IndexReader reader,
      List<AtomicReaderContext> leaves, TermContext[] contextArray,
      Term[] queryTerms) throws IOException {
    TermsEnum termsEnum = null;
    for (AtomicReaderContext context : leaves) {
      final Fields fields = context.reader().fields();
      if (fields == null) {
        // reader has no fields
        continue;
      }
      for (int i = 0; i < queryTerms.length; i++) {
        Term term = queryTerms[i];
        TermContext termContext = contextArray[i];
        final Terms terms = fields.terms(term.field());
        if (terms == null) {
          // field does not exist
          continue;
        }
        termsEnum = terms.iterator(termsEnum);
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
   
    Set<String> termSet = fieldQuery.getTermSet( fieldName );
    // just return to make null snippet if un-matched fieldName specified when fieldMatch == true
    if( termSet == null ) return;

    final Fields vectors = reader.getTermVectors(docId);
    if (vectors == null) {
      // null snippet
      return;
    }

    final Terms vector = vectors.terms(fieldName);
    if (vector == null) {
      // null snippet
      return;
    }
View Full Code Here
705
706
707
708
709
710
711
712
713
714
715
716
717
718
   * @param docNum the id of the lucene document from which to find terms
   */
  public PriorityQueue<Object[]> retrieveTerms(int docNum) throws IOException {
    Map<String, Int> termFreqMap = new HashMap<String, Int>();
    for (String fieldName : fieldNames) {
      final Fields vectors = ir.getTermVectors(docNum);
      final Terms vector;
      if (vectors != null) {
        vector = vectors.terms(fieldName);
      } else {
        vector = null;
      }

      // field does not store term vector info
View Full Code Here
364
365
366
367
368
369
370
371
372
373
374
375
    assertEquals(1, s.search(new TermQuery(new Term("tokenized_reader", "xyz")), 1).totalHits);
    assertEquals(1, s.search(new TermQuery(new Term("tokenized_tokenstream", "abc")), 1).totalHits);
    assertEquals(1, s.search(new TermQuery(new Term("tokenized_tokenstream", "xyz")), 1).totalHits);

    for(String field : new String[] {"tv", "tv_pos", "tv_off", "tv_pos_off"}) {
      Fields tvFields = r.getTermVectors(0);
      Terms tvs = tvFields.terms(field);
      assertNotNull(tvs);
      assertEquals(2, tvs.size());
      TermsEnum tvsEnum = tvs.iterator(null);
      assertEquals(new BytesRef("abc"), tvsEnum.next());
      final DocsAndPositionsEnum dpEnum = tvsEnum.docsAndPositions(null, null);
View Full Code Here
736
737
738
739
740
741
742
743
744
745
746
747
  }

  @Override
  public Fields get(int docID) throws IOException {
    if (tvx != null) {
      Fields fields = new TVFields(docID);
      if (fields.size() == 0) {
        // TODO: we can improve writer here, eg write 0 into
        // tvx file, so we know on first read from tvx that
        // this doc has no TVs
        return null;
      } else {
View Full Code Here
TOP

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

  • com.browseengine.bobo.sort.SortCollectorImpl
  • com.tistory.devyongsik.crescent.admin.service.IndexFileManageServiceImpl
  • org.apache.blur.index.ExitableReader$ExitableFilterAtomicReader
  • org.apache.blur.lucene.warmup.IndexWarmup
  • org.apache.blur.manager.writer.FieldBasedWarmer
  • org.apache.blur.manager.writer.IndexImporter
  • org.apache.blur.utils.BlurUtil
  • org.apache.lucene.analysis.TestMockAnalyzer
  • org.apache.lucene.benchmark.byTask.TestPerfTasksLogic
  • org.apache.lucene.codecs.asserting.AssertingTermVectorsFormat$AssertingTermVectorsReader
    • 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.