Java Code Examples for org.apache.lucene.index.Fields#terms()

public DfsOnlyRequest(Fields termVectorsFields, String[] indices, String[] types, Set<String> selectedFields) throws IOException {
    super(indices);

    // build a search request with a query of all the terms
    final BoolQueryBuilder boolBuilder = boolQuery();
    for (String fieldName : termVectorsFields) {
        if ((selectedFields != null) && (!selectedFields.contains(fieldName))) {
            continue;
        }
        Terms terms = termVectorsFields.terms(fieldName);
        TermsEnum iterator = terms.iterator();
        while (iterator.next() != null) {
            String text = iterator.term().utf8ToString();
            boolBuilder.should(QueryBuilders.termQuery(fieldName, text));
        }
    }
    // wrap a search request object
    this.searchRequest = new SearchRequest(indices).types(types).source(new SearchSourceBuilder().query(boolBuilder));
}
 

/**
 * A convenience method that tries to first get a {@link TokenStreamFromTermVector} for the
 * specified docId, then, falls back to using the passed in
 * {@link org.apache.lucene.document.Document} to retrieve the TokenStream.
 * This is useful when you already have the document, but would prefer to use
 * the vector first.
 *
 * @param reader The {@link org.apache.lucene.index.IndexReader} to use to try
 *        and get the vector from
 * @param docId The docId to retrieve.
 * @param field The field to retrieve on the document
 * @param document The document to fall back on
 * @param analyzer The analyzer to use for creating the TokenStream if the
 *        vector doesn't exist
 * @return The {@link org.apache.lucene.analysis.TokenStream} for the
 *         {@link org.apache.lucene.index.IndexableField} on the
 *         {@link org.apache.lucene.document.Document}
 * @throws IOException if there was an error loading
 */
@Deprecated // maintenance reasons LUCENE-6445
public static TokenStream getAnyTokenStream(IndexReader reader, int docId,
    String field, Document document, 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);
    }
  }

  // No token info stored so fall back to analyzing raw content
  if (ts == null) {
    ts = getTokenStream(document, field, analyzer);
  }
  return ts;
}
 

/**
 * A convenience method that tries a number of approaches to getting a token
 * stream. The cost of finding there are no termVectors in the index is
 * minimal (1000 invocations still registers 0 ms). So this "lazy" (flexible?)
 * approach to coding is probably acceptable
 * 
 * @return null if field not stored correctly
 * @throws IOException If there is a low-level I/O error
 */
@Deprecated // maintenance reasons LUCENE-6445
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);
    }
  }

  // No token info stored so fall back to analyzing raw content
  if (ts == null) {
    ts = getTokenStream(reader, docId, field, analyzer);
  }
  return ts;
}
 

/**
 * Returns a {@link TokenStream} with positions and offsets constructed from
 * field termvectors.  If the field has no termvectors or offsets
 * are not included in the termvector, return null.  See {@link #getTokenStream(org.apache.lucene.index.Terms)}
 * for an explanation of what happens when positions aren't present.
 *
 * @param reader the {@link IndexReader} to retrieve term vectors from
 * @param docId the document to retrieve termvectors for
 * @param field the field to retrieve termvectors for
 * @return a {@link TokenStream}, or null if offsets are not available
 * @throws IOException If there is a low-level I/O error
 *
 * @see #getTokenStream(org.apache.lucene.index.Terms)
 */
@Deprecated // maintenance reasons LUCENE-6445
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.hasOffsets()) {
    return null;
  }
  
  return getTokenStream(vector);
}
 

@Override
public void write(Fields fields, NormsProducer norms) throws IOException {

  for(String field : fields) {

    Terms terms = fields.terms(field);
    if (terms == null) {
      continue;
    }

    TermsEnum termsEnum = terms.iterator();

    TermsWriter termsWriter = addField(fieldInfos.fieldInfo(field));

    while (true) {
      BytesRef term = termsEnum.next();
      if (term == null) {
        break;
      }

      termsWriter.write(term, termsEnum, norms);
    }

    termsWriter.finish();
  }
}
 

@Override
public void write(Fields fields, NormsProducer normsProducer) throws IOException {
  BlockWriter blockWriter = new BlockWriter(blockOutput, targetNumBlockLines, deltaNumLines, blockEncoder);
  ByteBuffersDataOutput fieldsOutput = new ByteBuffersDataOutput();
  int fieldsNumber = 0;
  for (String field : fields) {
    Terms terms = fields.terms(field);
    if (terms != null) {
      TermsEnum termsEnum = terms.iterator();
      FieldInfo fieldInfo = fieldInfos.fieldInfo(field);
      fieldsNumber += writeFieldTerms(blockWriter, fieldsOutput, termsEnum, fieldInfo, normsProducer);
    }
  }
  writeFieldsMetadata(fieldsNumber, fieldsOutput);
  CodecUtil.writeFooter(dictionaryOutput);
}
 

private IterableRow getIterableRow(String rowId, IndexSearcherCloseable searcher) throws IOException {
  IndexReader indexReader = searcher.getIndexReader();
  BytesRef rowIdRef = new BytesRef(rowId);
  List<AtomicReaderTermsEnum> possibleRowIds = new ArrayList<AtomicReaderTermsEnum>();
  for (AtomicReaderContext atomicReaderContext : indexReader.leaves()) {
    AtomicReader atomicReader = atomicReaderContext.reader();
    Fields fields = atomicReader.fields();
    if (fields == null) {
      continue;
    }
    Terms terms = fields.terms(BlurConstants.ROW_ID);
    if (terms == null) {
      continue;
    }
    TermsEnum termsEnum = terms.iterator(null);
    if (!termsEnum.seekExact(rowIdRef, true)) {
      continue;
    }
    // need atomic read as well...
    possibleRowIds.add(new AtomicReaderTermsEnum(atomicReader, termsEnum));
  }
  if (possibleRowIds.isEmpty()) {
    return null;
  }
  return new IterableRow(rowId, getRecords(possibleRowIds));
}
 

private void estimateTermVectors(Map<String, Object> result) throws IOException {
  log.info("- estimating term vectors...");
  Map<String, Map<String, Object>> stats = new HashMap<>();
  for (LeafReaderContext leafReaderContext : reader.leaves()) {
    LeafReader leafReader = leafReaderContext.reader();
    Bits liveDocs = leafReader.getLiveDocs();
    for (int docId = 0; docId < leafReader.maxDoc(); docId += samplingStep) {
      if (liveDocs != null && !liveDocs.get(docId)) {
        continue;
      }
      Fields termVectors = leafReader.getTermVectors(docId);
      if (termVectors == null) {
        continue;
      }
      for (String field : termVectors) {
        Terms terms = termVectors.terms(field);
        if (terms == null) {
          continue;
        }
        estimateTermStats(field, terms, stats, true);
      }
    }
  }
  result.put(TERM_VECTORS, stats);
}
 

private int getTermWithSeekCount(Fields fields, String field) throws IOException {
  Terms terms = fields.terms(field);
  TermsEnum termsEnum = terms.iterator(null);
  SeekStatus seekStatus = termsEnum.seekCeil(new BytesRef(""));
  if (seekStatus == SeekStatus.END) {
    return 0;
  }
  System.out.println(termsEnum.term().utf8ToString());
  int count = 1;
  while (termsEnum.next() != null) {
    count++;
  }
  return count;
}
 

@Override
public DocIdSet getDocIdSet(AtomicReaderContext context, Bits acceptDocs) throws IOException {
  AtomicReader reader = context.reader();
  List<DocIdSet> list = new ArrayList<DocIdSet>();

  Fields fields = reader.fields();
  Terms terms = fields.terms(_fieldName);
  if (terms == null) {
    // if field is not present then show nothing.
    return DocIdSet.EMPTY_DOCIDSET;
  }
  TermsEnum iterator = terms.iterator(null);
  BytesRef bytesRef;
  DocumentVisibilityEvaluator visibilityEvaluator = new DocumentVisibilityEvaluator(_authorizations);
  while ((bytesRef = iterator.next()) != null) {
    if (isVisible(visibilityEvaluator, bytesRef)) {
      DocIdSet docIdSet = _filterCacheStrategy.getDocIdSet(_fieldName, bytesRef, reader);
      if (docIdSet != null) {
        list.add(docIdSet);
      } else {
        // Do not use acceptDocs because we want the acl cache to be version
        // agnostic.
        DocsEnum docsEnum = iterator.docs(null, null);
        list.add(buildCache(reader, docsEnum, bytesRef));
      }
    }
  }
  return getLogicalOr(list);
}
 

private static void applyFamily(OpenBitSet bits, String family, AtomicReader atomicReader, int primeDocRowId,
    int numberOfDocsInRow, Bits liveDocs) throws IOException {
  Fields fields = atomicReader.fields();
  Terms terms = fields.terms(BlurConstants.FAMILY);
  TermsEnum iterator = terms.iterator(null);
  BytesRef text = new BytesRef(family);
  int lastDocId = primeDocRowId + numberOfDocsInRow;
  if (iterator.seekExact(text, true)) {
    DocsEnum docs = iterator.docs(liveDocs, null, DocsEnum.FLAG_NONE);
    int doc = primeDocRowId;
    while ((doc = docs.advance(doc)) < lastDocId) {
      bits.set(doc - primeDocRowId);
    }
  }
}
 

private void checkTerms(IndexSearcher searcher, String fieldName) throws IOException {
  IndexReader reader = searcher.getIndexReader();
  for (AtomicReaderContext context : reader.leaves()) {
    AtomicReader atomicReader = context.reader();
    Fields fields = atomicReader.fields();
    Terms terms = fields.terms(fieldName);
    TermsEnum iterator = terms.iterator(null);
    BytesRef bytesRef = iterator.next();
    if (bytesRef != null) {
      System.out.println(bytesRef.utf8ToString());
      fail("There are only restricted terms for this field [" + fieldName + "]");
    }
  }
}
 

private void dummy() throws IOException {
    Fields fields = MultiFields.getFields(this.reader);
    Terms terms = fields.terms("field");
    TermsEnum iterator = terms.iterator(null);
    BytesRef byteRef = null;
    while ((byteRef = iterator.next()) != null) {
        String term = new String(byteRef.bytes, byteRef.offset,
                byteRef.length);
        Term termInstance = new Term("tokens", term);
        long termFreq = this.reader.totalTermFreq(termInstance);
        this.TermFreqMap.put(term, termFreq);
        System.out.println(termFreq);
    }
}
 

private int getTermCount(Fields fields, String field) throws IOException {
  Terms terms = fields.terms(field);
  TermsEnum termsEnum = terms.iterator(null);
  int count = 0;
  while (termsEnum.next() != null) {
    count++;
  }
  return count;
}
 

@Override
public void write(Fields fields, NormsProducer norms) throws IOException {
  delegateFieldsConsumer.write(fields, norms);

  for (String field : fields) {
    CompletionTermWriter termWriter = new CompletionTermWriter();
    Terms terms = fields.terms(field);
    if (terms == null) {
      // this can happen from ghost fields, where the incoming Fields iterator claims a field exists but it does not
      continue;
    }
    TermsEnum termsEnum = terms.iterator();

    // write terms
    BytesRef term;
    while ((term = termsEnum.next()) != null) {
      termWriter.write(term, termsEnum);
    }

    // store lookup, if needed
    long filePointer = dictOut.getFilePointer();
    if (termWriter.finish(dictOut)) {
      seenFields.put(field, new CompletionMetaData(filePointer,
          termWriter.minWeight,
          termWriter.maxWeight,
          termWriter.type));
    }
  }
}
 

/**
 * Find words for a more-like-this query former.
 *
 * @param docNum the id of the lucene document from which to find terms
 */
private PriorityQueue<ScoreTerm> retrieveTerms(int docNum) throws IOException {
  Map<String, Map<String, Int>> field2termFreqMap = new HashMap<>();
  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
    if (vector == null) {
      Document d = ir.document(docNum);
      IndexableField[] fields = d.getFields(fieldName);
      for (IndexableField field : fields) {
        final String stringValue = field.stringValue();
        if (stringValue != null) {
          addTermFrequencies(new StringReader(stringValue), field2termFreqMap, fieldName);
        }
      }
    } else {
      addTermFrequencies(field2termFreqMap, vector, fieldName);
    }
  }

  return createQueue(field2termFreqMap);
}
 

private TermIteratorQueue<FieldTerms> createFieldTermsQueue(Fields fields, List<FieldMetadata> fieldMetadataList) throws IOException {
  TermIteratorQueue<FieldTerms> fieldQueue = new TermIteratorQueue<>(fieldMetadataList.size());
  for (FieldMetadata fieldMetadata : fieldMetadataList) {
    Terms terms = fields.terms(fieldMetadata.getFieldInfo().name);
    if (terms != null) {
      FieldTerms fieldTerms = new FieldTerms(fieldMetadata, terms.iterator());
      if (fieldTerms.nextTerm()) {
        // There is at least one term for the field.
        fieldQueue.add(fieldTerms);
      }
    }
  }
  return fieldQueue;
}
 

@Override
public void write(Fields fields, NormsProducer norms) throws IOException {
  for(String field : fields) {
    Terms terms = fields.terms(field);
    if (terms == null) {
      continue;
    }
    FieldInfo fieldInfo = fieldInfos.fieldInfo(field);
    boolean hasFreq = fieldInfo.getIndexOptions().compareTo(IndexOptions.DOCS_AND_FREQS) >= 0;
    TermsEnum termsEnum = terms.iterator();
    TermsWriter termsWriter = new TermsWriter(fieldInfo);

    long sumTotalTermFreq = 0;
    long sumDocFreq = 0;
    FixedBitSet docsSeen = new FixedBitSet(maxDoc);

    while (true) {
      BytesRef term = termsEnum.next();
      if (term == null) {
        break;
      }
          
      BlockTermState termState = postingsWriter.writeTerm(term, termsEnum, docsSeen, norms);
      if (termState != null) {
        termsWriter.finishTerm(term, termState);
        sumTotalTermFreq += termState.totalTermFreq;
        sumDocFreq += termState.docFreq;
      }
    }

    termsWriter.finish(hasFreq ? sumTotalTermFreq : -1, sumDocFreq, docsSeen.cardinality());
  }
}
 

private Terms getReadMaskTerms(Fields in, String field) throws IOException {
  return in.terms(field + FilterAccessControlFactory.READ_MASK_SUFFIX);
}
 

/**
 * Get a token stream by un-inverting the term vector. This method returns null if {@code tvFields} is null
 * or if the field has no term vector, or if the term vector doesn't have offsets.  Positions are recommended on the
 * term vector but it isn't strictly required.
 *
 * @param field The field to get term vectors from.
 * @param tvFields from {@link IndexReader#getTermVectors(int)}. Possibly null. For performance, this instance should
 *                 be re-used for the same document (e.g. when highlighting multiple fields).
 * @param maxStartOffset Terms with a startOffset greater than this aren't returned.  Use -1 for no limit.
 *                       Suggest using {@link Highlighter#getMaxDocCharsToAnalyze()} - 1
 * @return a token stream from term vectors. Null if no term vectors with the right options.
 */
public static TokenStream getTermVectorTokenStreamOrNull(String field, Fields tvFields, int maxStartOffset)
    throws IOException {
  if (tvFields == null) {
    return null;
  }
  final Terms tvTerms = tvFields.terms(field);
  if (tvTerms == null || !tvTerms.hasOffsets()) {
    return null;
  }
  return new TokenStreamFromTermVector(tvTerms, maxStartOffset);
}