org.apache.hadoop.hive.ql.optimizer.BucketMapJoinOptimizer Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of hive-exec Show documentation
The newest version!
/**
 * 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.optimizer;

import java.util.ArrayList;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
import java.util.Stack;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.hive.ql.exec.MapJoinOperator;
import org.apache.hadoop.hive.ql.lib.DefaultGraphWalker;
import org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher;
import org.apache.hadoop.hive.ql.lib.Dispatcher;
import org.apache.hadoop.hive.ql.lib.GraphWalker;
import org.apache.hadoop.hive.ql.lib.Node;
import org.apache.hadoop.hive.ql.lib.NodeProcessor;
import org.apache.hadoop.hive.ql.lib.NodeProcessorCtx;
import org.apache.hadoop.hive.ql.lib.Rule;
import org.apache.hadoop.hive.ql.lib.RuleRegExp;
import org.apache.hadoop.hive.ql.parse.ParseContext;
import org.apache.hadoop.hive.ql.parse.SemanticException;

/**
 * this transformation does bucket map join optimization.
 */
public class BucketMapJoinOptimizer implements Transform {

  private static final Log LOG = LogFactory.getLog(GroupByOptimizer.class
      .getName());

  public BucketMapJoinOptimizer() {
  }

  @Override
  public ParseContext transform(ParseContext pctx) throws SemanticException {

    Map opRules = new LinkedHashMap();
    BucketJoinProcCtx bucketMapJoinOptimizeCtx =
        new BucketJoinProcCtx(pctx.getConf());

    // process map joins with no reducers pattern
    opRules.put(new RuleRegExp("R1",
        MapJoinOperator.getOperatorName() + "%"),
        getBucketMapjoinProc(pctx));

    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    Dispatcher disp = new DefaultRuleDispatcher(getDefaultProc(), opRules,
        bucketMapJoinOptimizeCtx);
    GraphWalker ogw = new DefaultGraphWalker(disp);

    // Create a list of topop nodes
    List topNodes = new ArrayList();
    topNodes.addAll(pctx.getTopOps().values());
    ogw.startWalking(topNodes, null);

    return pctx;
  }

  private NodeProcessor getBucketMapjoinProc(ParseContext pctx) {
    return new BucketMapjoinProc(pctx);
  }

  private NodeProcessor getDefaultProc() {
    return new NodeProcessor() {
      @Override
      public Object process(Node nd, Stack stack,
          NodeProcessorCtx procCtx, Object... nodeOutputs)
          throws SemanticException {
        return null;
      }
    };
  }
}