Github user andralungu commented on a diff in the pull request: https://github.com/apache/flink/pull/1105#discussion_r39276971 --- Diff: flink-staging/flink-gelly/src/main/java/org/apache/flink/graph/library/TriangleCount.java --- @@ -0,0 +1,208 @@ +/* + * 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.flink.graph.library; + +import org.apache.flink.api.common.functions.FlatJoinFunction; +import org.apache.flink.api.common.functions.GroupReduceFunction; +import org.apache.flink.api.common.functions.MapFunction; +import org.apache.flink.api.common.functions.ReduceFunction; +import org.apache.flink.api.java.DataSet; +import org.apache.flink.api.java.tuple.Tuple1; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.graph.GraphAlgorithm; +import org.apache.flink.graph.Graph; +import org.apache.flink.graph.Vertex; +import org.apache.flink.graph.Edge; +import org.apache.flink.graph.EdgeDirection; +import org.apache.flink.graph.NeighborsFunctionWithVertexValue; +import org.apache.flink.graph.utils.VertexToTuple2Map; +import org.apache.flink.types.NullValue; +import org.apache.flink.util.Collector; + +import java.util.Iterator; +import java.util.TreeMap; + +/** + * Triangle Count Algorithm. + * + * This algorithm operates in three phases. First, vertices select neighbors with id greater than theirs + * and send messages to them. Each received message is then propagated to neighbors with higher id. + * Finally, if a node encounters the target id in the list of received messages, it increments the number + * of triangles found. + * + * For skewed graphs, we recommend calling the GSATriangleCount library method as it uses the more restrictive + * `reduceOnNeighbors` function which internally makes use of combiners to speed up computation. + * + * This implementation is non - iterative. + * + * The algorithm takes an undirected, unweighted graph as input and outputs a DataSet of + * Tuple1 which contains a single integer representing the number of triangles. + */ +public class TriangleCount implements + GraphAlgorithm<Long, NullValue, NullValue, DataSet<Tuple1<Integer>>> { --- End diff -- For the Tuple1 comment: I wanted to be consistent with the other examples. If you run it on a cluster, you'd like the result printed in a file. You could print it with regular Java functions, but `writeAsCsv` and `print` were more appealing (to me at least) :) For the key type: At some point, you check that your id is lower than the neighbors' ids... How would that comparison be made if you don't know the type. If let's say you received String, you'd need to do `Long.parseLong`.... If you know a way, I'd gladly change it, but I don't think this is the only library method that has the key type problem... Even ConnectedComponents uses Long. Maybe we can open a JIRA for that...
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---