DifferenceBroadcast.java
/*
* Copyright © 2014 - 2021 Leipzig University (Database Research Group)
*
* Licensed 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.gradoop.flink.model.impl.operators.difference;
import org.apache.flink.api.java.DataSet;
import org.gradoop.common.model.api.entities.Edge;
import org.gradoop.common.model.api.entities.GraphHead;
import org.gradoop.common.model.api.entities.Vertex;
import org.gradoop.flink.model.api.epgm.BaseGraph;
import org.gradoop.flink.model.api.epgm.BaseGraphCollection;
import org.gradoop.flink.model.impl.functions.graphcontainment.GraphsContainmentFilterBroadcast;
import org.gradoop.flink.model.impl.functions.epgm.Id;
import org.gradoop.flink.model.impl.functions.graphcontainment.InAnyGraphBroadcast;
import org.gradoop.common.model.impl.id.GradoopId;
/**
* Returns a collection with all base graphs that are contained in the
* first input collection but not in the second.
* Graph equality is based on their respective identifiers.
* <p>
* This operator implementation requires that a list of subgraph identifiers
* in the resulting graph collections fits into the workers main memory.
*
* @param <G> type of the graph head
* @param <V> the vertex type
* @param <E> the edge type
* @param <LG> type of the base graph instance
* @param <GC> type of the graph collection
*/
public class DifferenceBroadcast<
G extends GraphHead,
V extends Vertex,
E extends Edge,
LG extends BaseGraph<G, V, E, LG, GC>,
GC extends BaseGraphCollection<G, V, E, LG, GC>> extends Difference<G, V, E, LG, GC> {
/**
* Computes the resulting vertices by collecting a list of resulting
* subgraphs and checking if the vertex is contained in that list.
*
* @param newGraphHeads graph dataset of the resulting graph collection
* @return vertex set of the resulting graph collection
*/
@Override
protected DataSet<V> computeNewVertices(DataSet<G> newGraphHeads) {
DataSet<GradoopId> identifiers = newGraphHeads
.map(new Id<>());
return firstCollection.getVertices()
.filter(new InAnyGraphBroadcast<>())
.withBroadcastSet(identifiers, GraphsContainmentFilterBroadcast.GRAPH_IDS);
}
}