/** * 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. */ register $zebraJar; --fs -rmr $outputDir rec1 = load '$outputDir/u3' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); rec2 = load '$outputDir/u4' using org.apache.hadoop.zebra.pig.TableLoader('count,seed,int1,str2,long1', 'sorted'); joina = join rec1 by long1, rec2 by long1 using "merge" ; E = foreach joina generate $0 as count, $1 as seed, $2 as int1, $3 as str2, $4 as long1; joinE = order E by long1 parallel 25; store joinE into '$outputDir/j2' using org.apache.hadoop.zebra.pig.TableStorer('');