mayya-sharipova commented on code in PR #992: URL: https://github.com/apache/lucene/pull/992#discussion_r914126920
########## lucene/core/src/java/org/apache/lucene/index/VectorValuesConsumer.java: ########## @@ -0,0 +1,93 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.index; + +import java.io.IOException; +import org.apache.lucene.codecs.Codec; +import org.apache.lucene.codecs.KnnVectorsFormat; +import org.apache.lucene.codecs.KnnVectorsWriter; +import org.apache.lucene.store.Directory; +import org.apache.lucene.store.IOContext; +import org.apache.lucene.util.Accountable; +import org.apache.lucene.util.IOUtils; +import org.apache.lucene.util.InfoStream; + +/** + * Streams vector values for indexing to the given codec's vectors writer. The codec's vectors + * writer is responsible for buffering and processing vectors. + */ +class VectorValuesConsumer { + private final Codec codec; + private final Directory directory; + private final SegmentInfo segmentInfo; + private final InfoStream infoStream; + + private Accountable accountable = Accountable.NULL_ACCOUNTABLE; + private KnnVectorsWriter writer; + + VectorValuesConsumer( + Codec codec, Directory directory, SegmentInfo segmentInfo, InfoStream infoStream) { + this.codec = codec; + this.directory = directory; + this.segmentInfo = segmentInfo; + this.infoStream = infoStream; + } + + private void initKnnVectorsWriter(String fieldName) throws IOException { + if (writer == null) { + KnnVectorsFormat fmt = codec.knnVectorsFormat(); + if (fmt == null) { + throw new IllegalStateException( + "field=\"" + + fieldName + + "\" was indexed as vectors but codec does not support vectors"); + } + SegmentWriteState initialWriteState = + new SegmentWriteState(infoStream, directory, segmentInfo, null, null, IOContext.DEFAULT); + writer = fmt.fieldsWriter(initialWriteState); + accountable = writer; + } + } + + public void addField(FieldInfo fieldInfo) throws IOException { + initKnnVectorsWriter(fieldInfo.name); + writer.addField(fieldInfo); + } + + public void addValue(FieldInfo fieldInfo, int docID, float[] vectorValue) throws IOException { + writer.addValue(fieldInfo, docID, vectorValue); + } + + void flush(SegmentWriteState state, Sorter.DocMap sortMap) throws IOException { Review Comment: No, I don't think we need it: we pass the information about segment's maxDoc to `writer.flush`. Also stored fields writers need to be passed every doc even though it doesn't contain stored fields, while vectors' writers only need to be passed docs that contain vectors. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
