flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From shghatge <...@git.apache.org>
Subject [GitHub] flink pull request: [FLINK-1520]Read edges and vertices from CSV f...
Date Thu, 02 Jul 2015 21:16:04 GMT
Github user shghatge commented on a diff in the pull request:

    https://github.com/apache/flink/pull/847#discussion_r33823720
  
    --- Diff: flink-staging/flink-gelly/src/main/java/org/apache/flink/graph/GraphCsvReader.java
---
    @@ -0,0 +1,471 @@
    +/*
    + * 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;
    +import com.google.common.base.Preconditions;
    +import org.apache.flink.api.common.functions.MapFunction;
    +import org.apache.flink.api.java.DataSet;
    +import org.apache.flink.api.java.io.CsvReader;
    +import org.apache.flink.api.java.tuple.Tuple2;
    +import org.apache.flink.api.java.tuple.Tuple3;
    +import org.apache.flink.core.fs.Path;
    +import org.apache.flink.api.java.ExecutionEnvironment;
    +import org.apache.flink.types.NullValue;
    +/**
    + * A class to build a Graph using path(s) provided to CSV file(s) with edge (vertices)
data
    + * The class also configures the CSV readers used to read edges(vertices) data such as
the field types,
    + * the delimiters (row and field),  the fields that should be included or skipped, and
other flags
    + * such as whether to skip the initial line as the header.
    + * The configuration is done using the functions provided in The {@link org.apache.flink.api.java.io.CsvReader}
class.
    + */
    +public class GraphCsvReader<K,VV,EV> {
    +
    +	private final Path vertexPath,edgePath;
    +	private final ExecutionEnvironment executionContext;
    +	protected CsvReader EdgeReader;
    +	protected CsvReader VertexReader;
    +	protected MapFunction<K, VV> mapper;
    +
    +//--------------------------------------------------------------------------------------------------------------------
    +
    +	public GraphCsvReader(Path vertexPath,Path edgePath, ExecutionEnvironment context) {
    +		this.vertexPath = vertexPath;
    +		this.edgePath = edgePath;
    +		this.VertexReader = new CsvReader(vertexPath,context);
    +		this.EdgeReader = new CsvReader(edgePath,context);
    +		this.mapper=null;
    +		this.executionContext=context;
    +	}
    +
    +	public GraphCsvReader(Path edgePath, ExecutionEnvironment context) {
    +		this.vertexPath = null;
    +		this.edgePath = edgePath;
    +		this.EdgeReader = new CsvReader(edgePath,context);
    +		this.VertexReader = null;
    +		this.mapper = null;
    +		this.executionContext=context;
    +	}
    +
    +	public GraphCsvReader(Path edgePath,final MapFunction<K, VV> mapper, ExecutionEnvironment
context) {
    +		this.vertexPath = null;
    +		this.edgePath = edgePath;
    +		this.EdgeReader = new CsvReader(edgePath,context);
    +		this.VertexReader = null;
    +		this.mapper = mapper;
    +		this.executionContext=context;
    +	}
    +
    +	public GraphCsvReader (String edgePath,ExecutionEnvironment context) {
    +		this(new Path(Preconditions.checkNotNull(edgePath, "The file path may not be null.")),
context);
    +
    +	}
    +
    +	public GraphCsvReader(String vertexPath, String edgePath, ExecutionEnvironment context)
{
    +		this(new Path(Preconditions.checkNotNull(vertexPath, "The file path may not be null.")),new
Path(Preconditions.checkNotNull(edgePath, "The file path may not be null.")), context);
    +	}
    +
    +
    +	public GraphCsvReader (String edgePath, final MapFunction<K, VV> mapper, ExecutionEnvironment
context) {
    +			this(new Path(Preconditions.checkNotNull(edgePath, "The file path may not be null.")),mapper,
context);
    +	}
    +
    +	public CsvReader getEdgeReader() {
    +		return this.EdgeReader;
    +	}
    +
    +	public CsvReader getVertexReader() {
    +		return this.VertexReader;
    +	}
    +	//--------------------------------------------------------------------------------------------------------------------
    +
    +	/**
    +	 * Specifies the types for the Graph fields and returns a Graph with those field types
    +	 *
    +	 * This method is overloaded for the case in which Vertices don't have a value
    +	 *
    +	 * @param type0 The type of CSV field 0 and 1 for the CSV reader used for reading Edge
data, the type of CSV field 0 for the CSV reader used for reading Vertex data  and the type
of Vetex ID in the returned Graph.
    --- End diff --
    
    Yes. I explained how it is passed to the edgeReader and vertexReader and at the end what
it signifies in the graph. i.e. Key type for vertex. Should I only keep the last part?


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message