/* * 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.pig.test.udf.storefunc; import java.io.IOException; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.InputFormat; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.RecordReader; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.pig.FileInputLoadFunc; import org.apache.pig.backend.hadoop.executionengine.mapReduceLayer.PigSplit; import org.apache.pig.data.DefaultTupleFactory; import org.apache.pig.data.Tuple; // This is a loader for data produced by DumpStore. // Line format: (field1, field2, ... fieldn)\n public class DumpLoader extends FileInputLoadFunc { protected RecordReader in = null; @Override public Tuple getNext() throws IOException { try { boolean notDone = in.nextKeyValue(); if (!notDone) { return null; } Text value = (Text) in.getCurrentValue(); String line = value.toString(); Tuple t = DefaultTupleFactory.getInstance().newTuple(); String tmp = line.substring(1, line.length() - 2); String[] fields = tmp.split(","); int i; for (i = 0; i < fields.length; i++) { t.append(fields[i].trim()); } return t; } catch (InterruptedException e) { throw new IOException(e); } } @Override public InputFormat getInputFormat() { return new TextInputFormat(); } @Override public void prepareToRead(RecordReader reader, PigSplit split) { in = reader; } @Override public void setLocation(String location, Job job) throws IOException { FileInputFormat.setInputPaths(job, location); } }