Java Code Examples for org.apache.lucene.index.PostingsEnum#OFFSETS

public static PostingsEnum docs(Random random, TermsEnum termsEnum, PostingsEnum reuse, int flags) throws IOException {
  // TODO: simplify this method? it would be easier to randomly either use the flags passed, or do the random selection,
  // FREQS should be part fo the random selection instead of outside on its own?
  if (random.nextBoolean()) {
    if (random.nextBoolean()) {
      final int posFlags;
      switch (random.nextInt(4)) {
        case 0: posFlags = PostingsEnum.POSITIONS; break;
        case 1: posFlags = PostingsEnum.OFFSETS; break;
        case 2: posFlags = PostingsEnum.PAYLOADS; break;
        default: posFlags = PostingsEnum.ALL; break;
      }
      return termsEnum.postings(null, posFlags);
    }
    flags |= PostingsEnum.FREQS;
  }
  return termsEnum.postings(reuse, flags);
}
 

private int convertToLuceneFlags(int flags) {
    int lucenePositionsFlags = PostingsEnum.NONE;
    lucenePositionsFlags |= (flags & IndexLookup.FLAG_FREQUENCIES) > 0 ? PostingsEnum.FREQS : 0x0;
    lucenePositionsFlags |= (flags & IndexLookup.FLAG_POSITIONS) > 0 ? PostingsEnum.POSITIONS : 0x0;
    lucenePositionsFlags |= (flags & IndexLookup.FLAG_PAYLOADS) > 0 ? PostingsEnum.PAYLOADS : 0x0;
    lucenePositionsFlags |= (flags & IndexLookup.FLAG_OFFSETS) > 0 ? PostingsEnum.OFFSETS : 0x0;
    return lucenePositionsFlags;
}
 

@Override
public Terms terms(String field) throws IOException {
  // ensure the underlying PostingsEnum returns offsets.  It's sad we have to do this to use the SpanCollector.
  return new FilterTerms(super.terms(fieldName)) {
    @Override
    public TermsEnum iterator() throws IOException {
      return new FilterTermsEnum(in.iterator()) {
        @Override
        public PostingsEnum postings(PostingsEnum reuse, int flags) throws IOException {
          return super.postings(reuse, flags | PostingsEnum.OFFSETS);
        }
      };
    }
  };
}
 

/** 
 * Sets the current field for writing, and returns the
 * fixed length of long[] metadata (which is fixed per
 * field), called when the writing switches to another field. */
@Override
public void setField(FieldInfo fieldInfo) {
  this.fieldInfo = fieldInfo;
  indexOptions = fieldInfo.getIndexOptions();

  writeFreqs = indexOptions.compareTo(IndexOptions.DOCS_AND_FREQS) >= 0;
  writePositions = indexOptions.compareTo(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS) >= 0;
  writeOffsets = indexOptions.compareTo(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS) >= 0;        
  writePayloads = fieldInfo.hasPayloads();

  if (writeFreqs == false) {
    enumFlags = 0;
  } else if (writePositions == false) {
    enumFlags = PostingsEnum.FREQS;
  } else if (writeOffsets == false) {
    if (writePayloads) {
      enumFlags = PostingsEnum.PAYLOADS;
    } else {
      enumFlags = PostingsEnum.POSITIONS;
    }
  } else {
    if (writePayloads) {
      enumFlags = PostingsEnum.PAYLOADS | PostingsEnum.OFFSETS;
    } else {
      enumFlags = PostingsEnum.OFFSETS;
    }
  }
}
 

@Override
public int getRequiredPostings() {
  return PostingsEnum.PAYLOADS | PostingsEnum.OFFSETS;
}
 

private void mapOneVector(NamedList<Object> docNL, FieldOptions fieldOptions, IndexReader reader, int docID, TermsEnum termsEnum, String field) throws IOException {
  NamedList<Object> fieldNL = new NamedList<>();
  docNL.add(field, fieldNL);

  BytesRef text;
  PostingsEnum dpEnum = null;
  while((text = termsEnum.next()) != null) {
    String term = text.utf8ToString();
    NamedList<Object> termInfo = new NamedList<>();
    fieldNL.add(term, termInfo);
    final int freq = (int) termsEnum.totalTermFreq();
    if (fieldOptions.termFreq == true) {
      termInfo.add("tf", freq);
    }

    int dpEnumFlags = 0;
    dpEnumFlags |= fieldOptions.positions ? PostingsEnum.POSITIONS : 0;
    //payloads require offsets
    dpEnumFlags |= (fieldOptions.offsets || fieldOptions.payloads) ? PostingsEnum.OFFSETS : 0;
    dpEnumFlags |= fieldOptions.payloads ? PostingsEnum.PAYLOADS : 0;
    dpEnum = termsEnum.postings(dpEnum, dpEnumFlags);

    boolean atNextDoc = false;
    if (dpEnum != null) {
      dpEnum.nextDoc();
      atNextDoc = true;
    }

    if (atNextDoc && dpEnumFlags != 0) {
      NamedList<Integer> positionsNL = null;
      NamedList<Number> theOffsets = null;
      NamedList<String> thePayloads = null;

      for (int i = 0; i < freq; i++) {
        final int pos = dpEnum.nextPosition();
        if (fieldOptions.positions && pos >= 0) {
          if (positionsNL == null) {
            positionsNL = new NamedList<>();
            termInfo.add("positions", positionsNL);
          }
          positionsNL.add("position", pos);
        }

        int startOffset = fieldOptions.offsets ? dpEnum.startOffset() : -1;
        if (startOffset >= 0) {
          if (theOffsets == null) {
            theOffsets = new NamedList<>();
            termInfo.add("offsets", theOffsets);
          }
          theOffsets.add("start", dpEnum.startOffset());
          theOffsets.add("end", dpEnum.endOffset());
        }

        BytesRef payload = fieldOptions.payloads ? dpEnum.getPayload() : null;
        if (payload != null) {
          if (thePayloads == null) {
            thePayloads = new NamedList<>();
            termInfo.add("payloads", thePayloads);
          }
          thePayloads.add("payload", Base64.byteArrayToBase64(payload.bytes, payload.offset, payload.length));
        }
      }
    }
    
    int df = 0;
    if (fieldOptions.docFreq || fieldOptions.tfIdf) {
      df = reader.docFreq(new Term(field, text));
    }

    if (fieldOptions.docFreq) {
      termInfo.add("df", df);
    }

    // TODO: this is not TF/IDF by anyone's definition!
    if (fieldOptions.tfIdf) {
      double tfIdfVal = ((double) freq) / df;
      termInfo.add("tf-idf", tfIdfVal);
    }
  }
}
 

@Override
public int getRequiredPostings() {
  return PostingsEnum.PAYLOADS | PostingsEnum.OFFSETS;
}