/** * 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 /grid/0/dev/hadoopqa/jars/zebra.jar; a1 = load '1.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]); a = load '2.txt' as (a:int, b:float,c:long,d:double,e:chararray,f:bytearray,r1(f1:chararray,f2:chararray),m1:map[]); --dump a; a1order = order a1 by b; aorder = order a by b; store a1order into 'b1' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c];[d,e,f,r1,m1]'); store aorder into 'b2' using org.apache.hadoop.zebra.pig.TableStorer('[a,b,c];[d,e,f,r1,m1]'); rec1 = load 'b1' using org.apache.hadoop.zebra.pig.TableLoader(); rec2 = load 'b2' using org.apache.hadoop.zebra.pig.TableLoader(); --records1 = LOAD 'b1,b2' USING org.apache.hadoop.zebra.pig.TableLoader ('b,c,d,e,f,r1,m1,a', 'sorted'); joina = join rec1 by b, rec2 by b using "merge" ; --dump records1; dump joina;