ggangadharan commented on code in PR #6861: URL: https://github.com/apache/hive/pull/6861#discussion_r4270392049
########## ql/src/java/org/apache/hadoop/hive/ql/exec/vector/ptf/VectorPTFEvaluatorNTile.java: ########## @@ -0,0 +1,153 @@ +/* + * 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.hadoop.hive.ql.exec.vector.ptf; + +import java.util.Arrays; +import java.util.List; + +import org.apache.hadoop.hive.ql.exec.vector.ColumnVector.Type; +import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.hadoop.hive.ql.exec.vector.expressions.ConstantVectorExpression; +import org.apache.hadoop.hive.ql.exec.vector.expressions.VectorExpression; +import org.apache.hadoop.hive.ql.metadata.HiveException; +import org.apache.hadoop.hive.ql.plan.ptf.WindowFrameDef; + +/** + * Evaluates {@code ntile(n)} as a <b>group-aggregated streaming</b> evaluator (see + * {@link VectorPTFEvaluatorBase}). + * + * <p>NTILE divides the rows of a partition into {@code n} buckets and returns the 1-based bucket + * number of the current row. When the partition size is not divisible by {@code n}, the first + * {@code partitionSize % n} buckets each get one extra row, matching {@code GenericUDAFNTile}. + * The result depends only on row position and partition size, never on peer groups. + * + * <p>The partition is buffered so {@link #setPartitionSize(int)} is known before output is + * written. Bucket boundaries are then derived on the fly while the batches are replayed, so the + * evaluator keeps O(1) state regardless of partition size, and a batch that falls entirely within + * one bucket is emitted as a repeating vector. + * + * <p>The number of buckets must be a positive integer constant (e.g. {@code ntile(4)}); the + * Vectorizer leaves any other form to row mode. + */ +public class VectorPTFEvaluatorNTile extends VectorPTFEvaluatorBase { + + private final int numBuckets; + + // Per-partition bucket layout, set up by addStreamingGroupResults. + private int bucketSize; + private int largerBucketCount; + + // Replay position within the partition. + private int currentBucket; + private int rowsLeftInBucket; + + public VectorPTFEvaluatorNTile(WindowFrameDef windowFrameDef, + VectorExpression numBucketsExpression, int outputColumnNum) { + super(windowFrameDef, outputColumnNum); + if (!(numBucketsExpression instanceof ConstantVectorExpression)) { Review Comment: Done, thanks. Used the same pattern in Vectorizer.isPositiveIntConstant -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
