001/*
002 * Copyright (c) 2007-2016 Concurrent, Inc. All Rights Reserved.
003 *
004 * Project and contact information: http://www.cascading.org/
005 *
006 * This file is part of the Cascading project.
007 *
008 * Licensed under the Apache License, Version 2.0 (the "License");
009 * you may not use this file except in compliance with the License.
010 * You may obtain a copy of the License at
011 *
012 *     http://www.apache.org/licenses/LICENSE-2.0
013 *
014 * Unless required by applicable law or agreed to in writing, software
015 * distributed under the License is distributed on an "AS IS" BASIS,
016 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
017 * See the License for the specific language governing permissions and
018 * limitations under the License.
019 */
020
021package cascading.tuple.collect;
022
023import java.util.Collection;
024import java.util.Map;
025
026import cascading.provider.CascadingFactory;
027import cascading.tuple.Tuple;
028
029/**
030 * Interface TupleMapFactory allows developers to plugin alternative implementations of a "tuple map"
031 * used to back in memory "join" and "co-group" operations. Typically these implementations are
032 * "spillable", in that to prevent using up all memory in the JVM, after some threshold is met or event
033 * is triggered, values are persisted to disk.
034 * <p/>
035 * The {@link Map} classes returned must take a {@link cascading.tuple.Tuple} as a key, and a {@link Collection} of Tuples as
036 * a value. Further, {@link Map#get(Object)} must never return {@code null}, but on the first call to get() on the map
037 * an empty Collection must be created and stored.
038 * <p/>
039 * That is, {@link Map#put(Object, Object)} is never called on the map instance internally,
040 * only {@code map.get(groupTuple).add(valuesTuple)}.
041 * <p/>
042 * Using the {@link TupleCollectionFactory} to create the underlying Tuple Collections would allow that aspect
043 * to be pluggable as well.
044 * <p/>
045 * If the Map implementation implements the {@link Spillable} interface, it will receive a {@link Spillable.SpillListener}
046 * instance that calls back to the appropriate logging mechanism for the platform. This instance should be passed
047 * down to any child Spillable types, namely an implementation of {@link SpillableTupleList}.
048 * <p/>
049 * The default implementation for the Hadoop platform is the {@link cascading.tuple.hadoop.collect.HadoopTupleMapFactory}
050 * which created a {@link cascading.tuple.hadoop.collect.HadoopSpillableTupleMap} instance.
051 * <p/>
052 * The class {@link SpillableTupleMap} may be used as a base class.
053 *
054 * @see SpillableTupleMap
055 * @see cascading.tuple.hadoop.collect.HadoopTupleMapFactory
056 * @see TupleCollectionFactory
057 * @see cascading.tuple.hadoop.collect.HadoopTupleCollectionFactory
058 */
059public interface TupleMapFactory<Config> extends CascadingFactory<Config, Map<Tuple, Collection<Tuple>>>
060  {
061  String TUPLE_MAP_FACTORY = "cascading.factory.tuple.map.classname";
062  }