Examples of org.apache.lucene.index.Fields

org.apache.lucene.index.Fields
Flex API for access to fields and terms @lucene.experimental

    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

  }


  @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

    }
  }


  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

    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


  public static TokenStream getAnyTokenStream(IndexReader reader, int docId,
      String field, Document doc, 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

   */
  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

   * @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

  }


  @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

  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

   * @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

0 1 2 3 4 5 6 7 8 9

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

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.