flink source 示例demo

DataSource From Collection

package com.house.flink.source;

import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

import java.util.ArrayList;

/**
 * 获取collection集合当作数据源
 */
public class StreamingFromCollection {

    public static void main(String[] args) throws Exception {
        //获取Flink的运行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        ArrayList<Integer> data = new ArrayList<>();
        data.add(15);
        data.add(20);
        data.add(22);
        data.add(27);
        data.add(17);
        // 从集合中获取数据源
        DataStreamSource<Integer> collectionData = env.fromCollection(data);
        //通map对数据进行处理
        DataStream<Integer> numberStream = collectionData.map(value ->value*5);
//        DataStream<Integer> numberStream = collectionData.map(new MapFunction<Integer, Integer>() {
//            @Override
//            public Integer map(Integer integer) throws Exception {
//                return 3+integer;
//            }
//        });

        //打印处理结果
        numberStream.print();
        env.execute("StreamingFromCollection");


    }
}

datasource from file

/*
 * 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 com.house.flink.wordcount;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class WordCount {

	public static void main(String[] args) throws Exception {

		final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
		DataStream<String> 	text = env.readTextFile("/Users/haozhang/env/bigdata/**");

		DataStream<Tuple2<String, Integer>> counts =
			text.flatMap(new Tokenizer())
			.keyBy(0).sum(1);
		counts.print();
		env.execute("Streaming WordCount");
	}

	// *************************************************************************
	// USER FUNCTIONS
	// *************************************************************************

	/**
	 * Implements the string tokenizer that splits sentences into words as a
	 * user-defined FlatMapFunction. The function takes a line (String) and
	 * splits it into multiple pairs in the form of "(word,1)" ({@code Tuple2<String,
	 * Integer>}).
	 */
	public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

		@Override
		public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {
			// normalize and split the line
			String[] tokens = value.toLowerCase().split("\\W+");

			// emit the pairs
			for (String token : tokens) {
				if (token.length() > 0) {
					out.collect(new Tuple2<>(token, 1));
				}
			}
		}
	}

}