Java Code Examples for org.apache.lucene.index.IndexOptions#DOCS_AND_FREQS_AND_POSITIONS

private static IndexOptions getIndexOptions(IndexInput input, byte b) throws IOException {
  switch (b) {
  case 0:
    return IndexOptions.NONE;
  case 1:
    return IndexOptions.DOCS;
  case 2:
    return IndexOptions.DOCS_AND_FREQS;
  case 3:
    return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
  case 4:
    return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
  default:
    // BUG
    throw new CorruptIndexException("invalid IndexOptions byte: " + b, input);
  }
}
 

private static IndexOptions getIndexOptions(IndexInput input, byte b) throws IOException {
  switch (b) {
  case 0:
    return IndexOptions.NONE;
  case 1:
    return IndexOptions.DOCS;
  case 2:
    return IndexOptions.DOCS_AND_FREQS;
  case 3:
    return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
  case 4:
    return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
  default:
    // BUG
    throw new CorruptIndexException("invalid IndexOptions byte: " + b, input);
  }
}
 

@Override
public IndexOptions indexOptions() {
  if (!indexed()) {
    return IndexOptions.NONE;
  }
  
  IndexOptions options = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
  if (omitTermFreqAndPositions()) {
    options = IndexOptions.DOCS;
  } else if (omitPositions()) {
    options = IndexOptions.DOCS_AND_FREQS;
  } else if (storeOffsetsWithPositions()) {
    options = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
  }

  return options;
}
 

/**
 * Utility method to create a {@link org.apache.lucene.document.FieldType}
 * based on the {@link SchemaField}
 */
public static org.apache.lucene.document.FieldType createFieldType(SchemaField field) {
  if (!field.indexed() && !field.stored()) {
    log.trace("Ignoring unindexed/unstored field: {}", field);
    return null;
  }
  org.apache.lucene.document.FieldType newType = new org.apache.lucene.document.FieldType();
  newType.setTokenized(field.isTokenized());
  newType.setStored(field.stored());
  newType.setOmitNorms(field.omitNorms());
  IndexOptions options = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
  if (field.omitTermFreqAndPositions()) {
    options = IndexOptions.DOCS;
  } else if (field.omitPositions()) {
    options = IndexOptions.DOCS_AND_FREQS;
  } else if (field.storeOffsetsWithPositions()) {
    options = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
  }
  newType.setIndexOptions(options);
  newType.setStoreTermVectors(field.storeTermVector());
  newType.setStoreTermVectorOffsets(field.storeTermOffsets());
  newType.setStoreTermVectorPositions(field.storeTermPositions());
  newType.setStoreTermVectorPayloads(field.storeTermPayloads());
  return newType;
}
 

private static IndexOptions nodeIndexOptionValue(final Object propNode) {
    final String value = propNode.toString();
    if (INDEX_OPTIONS_OFFSETS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
    } else if (INDEX_OPTIONS_POSITIONS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
    } else if (INDEX_OPTIONS_FREQS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS;
    } else if (INDEX_OPTIONS_DOCS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS;
    } else {
        throw new ElasticsearchParseException("failed to parse index option [{}]", value);
    }
}
 

public TermVectorLeafReader(String field, Terms terms) {
  fields = new Fields() {
    @Override
    public Iterator<String> iterator() {
      return Collections.singletonList(field).iterator();
    }

    @Override
    public Terms terms(String fld) throws IOException {
      if (!field.equals(fld)) {
        return null;
      }
      return terms;
    }

    @Override
    public int size() {
      return 1;
    }
  };

  IndexOptions indexOptions;
  if (!terms.hasFreqs()) {
    indexOptions = IndexOptions.DOCS;
  } else if (!terms.hasPositions()) {
    indexOptions = IndexOptions.DOCS_AND_FREQS;
  } else if (!terms.hasOffsets()) {
    indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
  } else {
    indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
  }
  FieldInfo fieldInfo = new FieldInfo(field, 0,
                                      true, true, terms.hasPayloads(),
                                      indexOptions, DocValuesType.NONE, -1, Collections.emptyMap(), 0, 0, 0, false);
  fieldInfos = new FieldInfos(new FieldInfo[]{fieldInfo});
}
 

@Override
public void setField(FieldInfo fieldInfo) {
  super.setField(fieldInfo);
  if (fieldInfo.getIndexOptions() != IndexOptions.DOCS_AND_FREQS_AND_POSITIONS) {
    throw new IllegalArgumentException("field must be index using IndexOptions.DOCS_AND_FREQS_AND_POSITIONS");
  }
  // LUCENE-5693: because CheckIndex cross-checks term vectors with postings even for deleted docs, and because our PF only indexes the
  // non-deleted documents on flush, CheckIndex will see this as corruption:
  if (fieldInfo.hasVectors()) {
    throw new IllegalArgumentException("field cannot index term vectors: CheckIndex will report this as index corruption");
  }
  lastState = emptyState;
}
 

private static IndexOptions nodeIndexOptionValue(final Object propNode) {
    final String value = propNode.toString();
    if (INDEX_OPTIONS_OFFSETS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS;
    } else if (INDEX_OPTIONS_POSITIONS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
    } else if (INDEX_OPTIONS_FREQS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS_AND_FREQS;
    } else if (INDEX_OPTIONS_DOCS.equalsIgnoreCase(value)) {
        return IndexOptions.DOCS;
    } else {
        throw new ElasticsearchParseException("failed to parse index option [{}]", value);
    }
}
 

/**
 * Parse common field attributes such as {@code doc_values} or {@code store}.
 */
public static void parseField(FieldMapper.Builder builder, String name, Map<String, Object> fieldNode, Mapper.TypeParser.ParserContext parserContext) {
    Version indexVersionCreated = parserContext.indexVersionCreated();
    for (Iterator<Map.Entry<String, Object>> iterator = fieldNode.entrySet().iterator(); iterator.hasNext();) {
        Map.Entry<String, Object> entry = iterator.next();
        final String propName = Strings.toUnderscoreCase(entry.getKey());
        final Object propNode = entry.getValue();
        if (propName.equals("index_name") && indexVersionCreated.before(Version.V_2_0_0_beta1)) {
            builder.indexName(propNode.toString());
            iterator.remove();
        } else if (propName.equals("store")) {
            builder.store(parseStore(name, propNode.toString()));
            iterator.remove();
        } else if (propName.equals("index")) {
            parseIndex(name, propNode.toString(), builder);
            iterator.remove();
        } else if (propName.equals(DOC_VALUES)) {
            builder.docValues(nodeBooleanValue(propNode));
            iterator.remove();
        } else if (propName.equals("boost")) {
            builder.boost(nodeFloatValue(propNode));
            iterator.remove();
        } else if (propName.equals("omit_norms")) {
            builder.omitNorms(nodeBooleanValue(propNode));
            iterator.remove();
        } else if (propName.equals("norms")) {
            final Map<String, Object> properties = nodeMapValue(propNode, "norms");
            for (Iterator<Entry<String, Object>> propsIterator = properties.entrySet().iterator(); propsIterator.hasNext();) {
                Entry<String, Object> entry2 = propsIterator.next();
                final String propName2 = Strings.toUnderscoreCase(entry2.getKey());
                final Object propNode2 = entry2.getValue();
                if (propName2.equals("enabled")) {
                    builder.omitNorms(!nodeBooleanValue(propNode2));
                    propsIterator.remove();
                } else if (propName2.equals(Loading.KEY)) {
                    builder.normsLoading(Loading.parse(nodeStringValue(propNode2, null), null));
                    propsIterator.remove();
                }
            }
            DocumentMapperParser.checkNoRemainingFields(propName, properties, parserContext.indexVersionCreated());
            iterator.remove();
        } else if (propName.equals("omit_term_freq_and_positions")) {
            final IndexOptions op = nodeBooleanValue(propNode) ? IndexOptions.DOCS : IndexOptions.DOCS_AND_FREQS_AND_POSITIONS;
            if (indexVersionCreated.onOrAfter(Version.V_1_0_0_RC2)) {
                throw new ElasticsearchParseException("'omit_term_freq_and_positions' is not supported anymore - use ['index_options' : 'docs']  instead");
            }
            // deprecated option for BW compat
            builder.indexOptions(op);
            iterator.remove();
        } else if (propName.equals("index_options")) {
            builder.indexOptions(nodeIndexOptionValue(propNode));
            iterator.remove();
        } else if (propName.equals("include_in_all")) {
            builder.includeInAll(nodeBooleanValue(propNode));
            iterator.remove();
        } else if (propName.equals("postings_format") && indexVersionCreated.before(Version.V_2_0_0_beta1)) {
            // ignore for old indexes
            iterator.remove();
        } else if (propName.equals("doc_values_format") && indexVersionCreated.before(Version.V_2_0_0_beta1)) {
            // ignore for old indexes
            iterator.remove();
        } else if (propName.equals("similarity")) {
            builder.similarity(parserContext.similarityLookupService().similarity(propNode.toString()));
            iterator.remove();
        } else if (propName.equals("fielddata")) {
            final Settings settings = Settings.builder().put(SettingsLoader.Helper.loadNestedFromMap(nodeMapValue(propNode, "fielddata"))).build();
            builder.fieldDataSettings(settings);
            iterator.remove();
        } else if (propName.equals("copy_to")) {
            if (parserContext.isWithinMultiField()) {
                if (indexVersionCreated.after(Version.V_2_1_0) ||
                    (indexVersionCreated.after(Version.V_2_0_1) && indexVersionCreated.before(Version.V_2_1_0))) {
                    throw new MapperParsingException("copy_to in multi fields is not allowed. Found the copy_to in field [" + name + "] which is within a multi field.");
                } else {
                    ESLoggerFactory.getLogger("mapping [" + parserContext.type() + "]").warn("Found a copy_to in field [" + name + "] which is within a multi field. This feature has been removed and the copy_to will be ignored.");
                    // we still parse this, otherwise the message will only appear once and the copy_to removed. After that it will appear again. Better to have it always.
                }
            }
            parseCopyFields(propNode, builder);
            iterator.remove();
        }
    }
    if (indexVersionCreated.before(Version.V_2_2_0)) {
        // analyzer, search_analyzer, term_vectors were accepted on all fields
        // before 2.2, even though it made little sense
        parseAnalyzersAndTermVectors(builder, name, fieldNode, parserContext);
    }
}
 

/** Prints a Field for human consumption. */
@Override
public String toString() {
  StringBuilder result = new StringBuilder();
  if (stored()) {
    result.append("stored");
  }
  if (indexOptions != IndexOptions.NONE) {
    if (result.length() > 0)
      result.append(",");
    result.append("indexed");
    if (tokenized()) {
      result.append(",tokenized");
    }
    if (storeTermVectors()) {
      result.append(",termVector");
    }
    if (storeTermVectorOffsets()) {
      result.append(",termVectorOffsets");
    }
    if (storeTermVectorPositions()) {
      result.append(",termVectorPosition");
    }
    if (storeTermVectorPayloads()) {
      result.append(",termVectorPayloads");
    }
    if (omitNorms()) {
      result.append(",omitNorms");
    }
    if (indexOptions != IndexOptions.DOCS_AND_FREQS_AND_POSITIONS) {
      result.append(",indexOptions=");
      result.append(indexOptions);
    }
  }
  if (dimensionCount != 0) {
    if (result.length() > 0) {
      result.append(",");
    }
    result.append("pointDimensionCount=");
    result.append(dimensionCount);
    result.append(",pointIndexDimensionCount=");
    result.append(indexDimensionCount);
    result.append(",pointNumBytes=");
    result.append(dimensionNumBytes);
  }
  if (docValuesType != DocValuesType.NONE) {
    if (result.length() > 0) {
      result.append(",");
    }
    result.append("docValuesType=");
    result.append(docValuesType);
  }
  
  return result.toString();
}