wgtmac commented on a change in pull request #952: URL: https://github.com/apache/orc/pull/952#discussion_r775949338
########## File path: java/core/src/java/org/apache/orc/impl/SelectedColumnVector.java ########## @@ -0,0 +1,55 @@ +/* + * 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.orc.impl; + +import org.apache.hadoop.hive.ql.exec.vector.ColumnVector; + +import java.util.function.Function; + +public class SelectedColumnVector extends InternalColumnVector { + + private final int[] selected; + + public SelectedColumnVector(ColumnVector columnVector, int[] selected) { + super(columnVector); + this.selected = selected; + } + + @Override + public void ensureSize(int size, boolean preserveData) { + throw new UnsupportedOperationException( + "The ensureSize operation is not supported for SelectedColumnVector"); + } + + @Override + public boolean isNull(int offset) { + return columnVector.isNull[getValueOffset(offset)]; + } + + @Override + public int getValueOffset(int offset) { + return selected[offset]; Review comment: What the main reason for using an int array as the selected vector? ########## File path: java/core/src/java/org/apache/orc/impl/WriterImpl.java ########## @@ -683,20 +683,22 @@ public void addUserMetadata(String name, ByteBuffer value) { @Override public void addRowBatch(VectorizedRowBatch batch) throws IOException { + InternalVectorizedRowBatch internalBatch = InternalVectorizedRowBatch.encapsulation(batch); + int batchSize = internalBatch.size(); try { // If this is the first set of rows in this stripe, tell the tree writers // to prepare the stripe. - if (batch.size != 0 && rowsInStripe == 0) { + if (batchSize != 0 && rowsInStripe == 0) { treeWriter.prepareStripe(stripes.size() + 1); } if (buildIndex) { // Batch the writes up to the rowIndexStride so that we can get the // right size indexes. int posn = 0; - while (posn < batch.size) { - int chunkSize = Math.min(batch.size - posn, + while (posn < batchSize) { + int chunkSize = Math.min(batchSize - posn, rowIndexStride - rowsInIndex); - treeWriter.writeRootBatch(batch, posn, chunkSize); + treeWriter.writeRootBatch(internalBatch, posn, chunkSize); Review comment: If I understand correctly, the selected vector only applies to each row in the root VectorizedRowBatch. We can simply use a bool array in the root VectorizedRowBatch to indicate whether each row is selected or not. Then we can split the input VectorizedRowBatch into smaller pieces of continuously selected VectorizedRowBatchs and thus change posn & chunkSize accordingly. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
