Examples of TermsEnum

org.apache.lucene.index.TermsEnum
Iterator to seek ( {@link #seekCeil(BytesRef)}, {@link #seekExact(BytesRef,boolean)}) or step through ( {@link #next} terms to obtain frequency information ({@link #docFreq}), {@link DocsEnum} or {@link DocsAndPositionsEnum} for the current term ({@link #docs}.
Term enumerations are always ordered by {@link #getComparator}. Each term in the enumeration is greater than the one before it.

The TermsEnum is unpositioned when you first obtain it and you must first successfully call {@link #next} or oneof the seek methods. @lucene.experimental

Examples of org.apache.lucene.index.TermsEnum

  protected TermsEnum getTermsEnum(final Terms terms, final AttributeSource atts) throws IOException {
    if (lowerTerm != null && upperTerm != null && lowerTerm.compareTo(upperTerm) > 0) {
      return TermsEnum.EMPTY;
    }


    final TermsEnum tenum = terms.iterator(null);


    if ((lowerTerm == null || (includeLower && lowerTerm.length == 0)) && upperTerm == null) {
      return tenum;
    }
    return new TermRangeTermsEnum(tenum,

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum


  private int countTerms(final MultiNodeTermQuery q) throws Exception {
    final Terms terms = MultiFields.getTerms(index.reader, q.getField());
    if (terms == null)
      return 0;
    final TermsEnum termEnum = q.getTermsEnum(terms);
    assertNotNull(termEnum);
    int count = 0;
    BytesRef cur, last = null;
    while ((cur = termEnum.next()) != null) {
      count++;
      if (last != null) {
        assertTrue(last.compareTo(cur) < 0);
      }
      last = BytesRef.deepCopyOf(cur);

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum


  private int countTerms(final MultiNodeTermQuery q) throws Exception {
    final Terms terms = MultiFields.getTerms(index.reader, q.getField());
    if (terms == null)
      return 0;
    final TermsEnum termEnum = q.getTermsEnum(terms);
    assertNotNull(termEnum);
    int count = 0;
    BytesRef cur, last = null;
    while ((cur = termEnum.next()) != null) {
      count++;
      if (last != null) {
        assertTrue(last.compareTo(cur) < 0);
      }
      last = BytesRef.deepCopyOf(cur);

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

      for (AtomicReaderContext context : leaves) {
        AtomicReader atomicReader = context.reader();
        Fields fields = atomicReader.fields();
        Terms terms = fields.terms(BlurConstants.ROW_ID);
        if (terms != null) {
          TermsEnum termsEnum = terms.iterator(null);
          BytesRef ref = null;
          while ((ref = termsEnum.next()) != null) {
            key.set(ref.bytes, ref.offset, ref.length);
            int partition = blurPartitioner.getPartition(key, null, numberOfShards);
            if (shardId != partition) {
              return false;
            }

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

        try {
            List<Term> terms = new ArrayList<Term>();
            Terms t = MultiFields.getTerms(reader, FieldNames.FULLTEXT);
            Automaton a = WildcardQuery.toAutomaton(newFulltextTerm(token));
            CompiledAutomaton ca = new CompiledAutomaton(a);
            TermsEnum te = ca.getTermsEnum(t);
            BytesRef text;
            while ((text = te.next()) != null) {
                terms.add(newFulltextTerm(text.utf8ToString()));
            }
            return terms.toArray(new Term[terms.size()]);
        } catch (IOException e) {
            LOG.error("Building fulltext query failed", e.getMessage());

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

        try {
            List<Term> terms = new ArrayList<Term>();
            Terms t = MultiFields.getTerms(reader, FieldNames.FULLTEXT);
            Automaton a = WildcardQuery.toAutomaton(newFulltextTerm(token));
            CompiledAutomaton ca = new CompiledAutomaton(a);
            TermsEnum te = ca.getTermsEnum(t);
            BytesRef text;
            while ((text = te.next()) != null) {
                terms.add(newFulltextTerm(text.utf8ToString()));
            }
            return terms.toArray(new Term[terms.size()]);
        } catch (IOException e) {
            LOG.error("Building fulltext query failed", e.getMessage());

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

    }


    boolean hasPayloads = tpv.hasPayloads();


    // code to reconstruct the original sequence of Tokens
    TermsEnum termsEnum = tpv.iterator(null);
    int totalTokens = 0;
    while(termsEnum.next() != null) {
      totalTokens += (int) termsEnum.totalTermFreq();
    }
    Token tokensInOriginalOrder[] = new Token[totalTokens];
    ArrayList<Token> unsortedTokens = null;
    termsEnum = tpv.iterator(null);
    BytesRef text;
    DocsAndPositionsEnum dpEnum = null;
    while ((text = termsEnum.next()) != null) {


      dpEnum = termsEnum.docsAndPositions(null, dpEnum);
      if (dpEnum == null) {
        throw new IllegalArgumentException(
            "Required TermVector Offset information was not found");
      }
      final String term = text.utf8ToString();

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

      @Override
      public Scorer scorer(AtomicReaderContext context, boolean scoreDocsInOrder,
                           boolean topScorer, Bits acceptDocs) throws IOException {


        DrillSidewaysScorer.DocsEnumsAndFreq[] dims = new DrillSidewaysScorer.DocsEnumsAndFreq[drillDownTerms.length];
        TermsEnum termsEnum = null;
        String lastField = null;
        int nullCount = 0;
        for(int dim=0;dim<dims.length;dim++) {
          dims[dim] = new DrillSidewaysScorer.DocsEnumsAndFreq();
          dims[dim].sidewaysCollector = drillSidewaysCollectors[dim];
          String field = drillDownTerms[dim][0].field();
          dims[dim].dim = drillDownTerms[dim][0].text();
          if (lastField == null || !lastField.equals(field)) {
            AtomicReader reader = context.reader();
            Terms terms = reader.terms(field);
            if (terms != null) {
              termsEnum = terms.iterator(null);
            } else {
              termsEnum = null;
            }
            lastField = field;
          }
          dims[dim].docsEnums = new DocsEnum[drillDownTerms[dim].length];
          if (termsEnum == null) {
            nullCount++;
            continue;
          }
          for(int i=0;i<drillDownTerms[dim].length;i++) {
            if (termsEnum.seekExact(drillDownTerms[dim][i].bytes())) {
              DocsEnum docsEnum = termsEnum.docs(null, null, 0);
              if (docsEnum != null) {
                dims[dim].docsEnums[i] = docsEnum;
                dims[dim].maxCost = Math.max(dims[dim].maxCost, docsEnum.cost());
              }
            }

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

      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);

View Full Code Here

Examples of org.apache.lucene.index.TermsEnum

      if (terms == null) {
        throw new IllegalArgumentException("need at least one suggestion");
      }


      // Move all ngrams into an FST:
      TermsEnum termsEnum = terms.iterator(null);


      Outputs<Long> outputs = PositiveIntOutputs.getSingleton();
      Builder<Long> builder = new Builder<Long>(FST.INPUT_TYPE.BYTE1, outputs);


      IntsRef scratchInts = new IntsRef();
      while (true) {
        BytesRef term = termsEnum.next();
        if (term == null) {
          break;
        }
        int ngramCount = countGrams(term);
        if (ngramCount > grams) {
          throw new IllegalArgumentException("tokens must not contain separator byte; got token=" + term + " but gramCount=" + ngramCount + ", which is greater than expected max ngram size=" + grams);
        }
        if (ngramCount == 1) {
          totTokens += termsEnum.totalTermFreq();
        }


        builder.add(Util.toIntsRef(term, scratchInts), encodeWeight(termsEnum.totalTermFreq()));
      }


      fst = builder.finish();
      if (fst == null) {
        throw new IllegalArgumentException("need at least one suggestion");

View Full Code Here

0 1 2 3 4 5

TOP

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.