maheshk114 commented on a change in pull request #1147: URL: https://github.com/apache/hive/pull/1147#discussion_r460522261
########## File path: ql/src/java/org/apache/hadoop/hive/ql/exec/vector/mapjoin/VectorMapJoinAntiJoinStringOperator.java ########## @@ -0,0 +1,371 @@ +/* + * 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.mapjoin; + +import org.apache.hadoop.hive.ql.CompilationOpContext; +import org.apache.hadoop.hive.ql.exec.JoinUtil; +import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector; +import org.apache.hadoop.hive.ql.exec.vector.VectorizationContext; +import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch; +import org.apache.hadoop.hive.ql.exec.vector.expressions.StringExpr; +import org.apache.hadoop.hive.ql.exec.vector.expressions.VectorExpression; +import org.apache.hadoop.hive.ql.exec.vector.mapjoin.hashtable.VectorMapJoinBytesHashSet; +import org.apache.hadoop.hive.ql.metadata.HiveException; +import org.apache.hadoop.hive.ql.plan.OperatorDesc; +import org.apache.hadoop.hive.ql.plan.VectorDesc; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.util.Arrays; + +// Single-Column String hash table import. +// Single-Column String specific imports. + +// TODO : Duplicate codes need to merge with semi join. +/* + * Specialized class for doing a vectorized map join that is an anti join on a Single-Column String + * using a hash set. + */ +public class VectorMapJoinAntiJoinStringOperator extends VectorMapJoinAntiJoinGenerateResultOperator { + + private static final long serialVersionUID = 1L; + + //------------------------------------------------------------------------------------------------ + + private static final String CLASS_NAME = VectorMapJoinAntiJoinStringOperator.class.getName(); + private static final Logger LOG = LoggerFactory.getLogger(CLASS_NAME); + + protected String getLoggingPrefix() { + return super.getLoggingPrefix(CLASS_NAME); + } + + //------------------------------------------------------------------------------------------------ + + // (none) + + // The above members are initialized by the constructor and must not be + // transient. + //--------------------------------------------------------------------------- + + // The hash map for this specialized class. + private transient VectorMapJoinBytesHashSet hashSet; + + //--------------------------------------------------------------------------- + // Single-Column String specific members. + // + + // The column number for this one column join specialization. + private transient int singleJoinColumn; + + //--------------------------------------------------------------------------- + // Pass-thru constructors. + // + + /** Kryo ctor. */ + protected VectorMapJoinAntiJoinStringOperator() { + super(); + } + + public VectorMapJoinAntiJoinStringOperator(CompilationOpContext ctx) { + super(ctx); + } + + public VectorMapJoinAntiJoinStringOperator(CompilationOpContext ctx, OperatorDesc conf, + VectorizationContext vContext, VectorDesc vectorDesc) throws HiveException { + super(ctx, conf, vContext, vectorDesc); + } + + //--------------------------------------------------------------------------- + // Process Single-Column String anti Join on a vectorized row batch. + // + + @Override + protected void commonSetup() throws HiveException { + super.commonSetup(); + + /* + * Initialize Single-Column String members for this specialized class. + */ + + singleJoinColumn = bigTableKeyColumnMap[0]; + } + + @Override + public void hashTableSetup() throws HiveException { + super.hashTableSetup(); + + /* + * Get our Single-Column String hash set information for this specialized class. + */ + + hashSet = (VectorMapJoinBytesHashSet) vectorMapJoinHashTable; + } + + @Override + public void processBatch(VectorizedRowBatch batch) throws HiveException { + + try { + + // Do the per-batch setup for an anti join. + + // (Currently none) + // antiPerBatchSetup(batch); + + // For anti joins, we may apply the filter(s) now. + for(VectorExpression ve : bigTableFilterExpressions) { + ve.evaluate(batch); + } + + final int inputLogicalSize = batch.size; + if (inputLogicalSize == 0) { + return; + } + + // Perform any key expressions. Results will go into scratch columns. + if (bigTableKeyExpressions != null) { + for (VectorExpression ve : bigTableKeyExpressions) { + ve.evaluate(batch); + } + } + + /* + * Single-Column String specific declarations. + */ + + // The one join column for this specialized class. + BytesColumnVector joinColVector = (BytesColumnVector) batch.cols[singleJoinColumn]; + byte[][] vector = joinColVector.vector; + int[] start = joinColVector.start; + int[] length = joinColVector.length; + + /* + * Single-Column Long check for repeating. + */ + + // Check single column for repeating. + boolean allKeyInputColumnsRepeating = joinColVector.isRepeating; + + if (allKeyInputColumnsRepeating) { + + /* + * Repeating. + */ + + // All key input columns are repeating. Generate key once. Lookup once. + // Since the key is repeated, we must use entry 0 regardless of selectedInUse. + + /* + * Single-Column String specific repeated lookup. + */ + + JoinUtil.JoinResult joinResult; + if (!joinColVector.noNulls && joinColVector.isNull[0]) { + joinResult = JoinUtil.JoinResult.MATCH; + } else { + byte[] keyBytes = vector[0]; + int keyStart = start[0]; + int keyLength = length[0]; + joinResult = hashSet.contains(keyBytes, keyStart, keyLength, hashSetResults[0]); + if (joinResult == JoinUtil.JoinResult.NOMATCH) { + joinResult = JoinUtil.JoinResult.MATCH; + } else if (joinResult == JoinUtil.JoinResult.MATCH) { + joinResult = JoinUtil.JoinResult.NOMATCH; + } + } + + /* + * Common repeated join result processing. + */ + + if (LOG.isDebugEnabled()) { + LOG.debug(CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name()); + } + finishAntiRepeated(batch, joinResult, hashSetResults[0]); + } else { + + /* + * NOT Repeating. + */ + + if (LOG.isDebugEnabled()) { + LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated"); + } + + // We remember any matching rows in matchs / matchSize. At the end of the loop, + // selected / batch.size will represent both matching and non-matching rows for outer join. + // Only deferred rows will have been removed from selected. + int selected[] = batch.selected; + boolean selectedInUse = batch.selectedInUse; + + int hashSetResultCount = 0; + int allMatchCount = 0; + int spillCount = 0; + + /* + * Single-Column String specific variables. + */ + + int saveKeyBatchIndex = -1; + + // We optimize performance by only looking up the first key in a series of equal keys. + boolean haveSaveKey = false; + JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH; + + // Logical loop over the rows in the batch since the batch may have selected in use. + for (int logical = 0; logical < inputLogicalSize; logical++) { + int batchIndex = (selectedInUse ? selected[logical] : logical); + + /* + * Single-Column String get key. + */ + + // Implicit -- use batchIndex. + boolean isNull = !joinColVector.noNulls && joinColVector.isNull[batchIndex]; + + /* + * Equal key series checking. + */ + + if (isNull || !haveSaveKey || + !StringExpr.equal(vector[saveKeyBatchIndex], start[saveKeyBatchIndex], length[saveKeyBatchIndex], + vector[batchIndex], start[batchIndex], length[batchIndex])) { + + // New key. + + if (haveSaveKey) { + // Move on with our counts. + switch (saveJoinResult) { + case MATCH: + // We have extracted the existence from the hash set result, so we don't keep it. + break; + case SPILL: + // We keep the hash set result for its spill information. + hashSetResultCount++; + break; + case NOMATCH: + break; + } + } + + if (isNull) { + saveJoinResult = JoinUtil.JoinResult.NOMATCH; + haveSaveKey = false; + } else { + // Regardless of our matching result, we keep that information to make multiple use + // of it for a possible series of equal keys. + haveSaveKey = true; + + /* + * Single-Column String specific save key and lookup. + */ + + saveKeyBatchIndex = batchIndex; + + /* + * Single-Column String specific lookup key. + */ + + byte[] keyBytes = vector[batchIndex]; + int keyStart = start[batchIndex]; + int keyLength = length[batchIndex]; + saveJoinResult = hashSet.contains(keyBytes, keyStart, keyLength, hashSetResults[hashSetResultCount]); + if (saveJoinResult == JoinUtil.JoinResult.NOMATCH) { Review comment: done ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
