05-Flink入门案例-代码实现-DataSet-了解 && DataStream-匿名内部类-处理批

代码实现-DataSet-了解

package cn.itcast.hello;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

/**
 * Author itcast
 * Desc 演示Flink-DataSet-API-实现WordCount
 */
public class WordCount {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        //TODO 1.source
        DataSet<String> lines = env.fromElements("itcast hadoop spark", "itcast hadoop spark", "itcast hadoop", "itcast");

        //TODO 2.transformation
        //切割
        /*
        @FunctionalInterface
        public interface FlatMapFunction<T, O> extends Function, Serializable {
            void flatMap(T value, Collector<O> out) throws Exception;
        }
         */
        DataSet<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String value, Collector<String> out) throws Exception {
                //value表示每一行数据
                String[] arr = value.split(" ");
                for (String word : arr) {
                    out.collect(word);
                }
            }
        });

        //记为1
        /*
        @FunctionalInterface
        public interface MapFunction<T, O> extends Function, Serializable {
            O map(T value) throws Exception;
        }
         */
        DataSet<Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                //value就是每一个单词
                return Tuple2.of(value, 1);
            }
        });

        //分组
        UnsortedGrouping<Tuple2<String, Integer>> grouped = wordAndOne.groupBy(0);

        //聚合
        AggregateOperator<Tuple2<String, Integer>> result = grouped.sum(1);

        //TODO 3.sink
        result.print();

    }
}

代码实现-DataStream-匿名内部类-处理批

package cn.itcast.hello;

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

/**
 * Author itcast
 * Desc 演示Flink-DataStream-API-实现WordCount
 * 注意:在Flink1.12中DataStream既支持流处理也支持批处理,如何区分?
 */
public class WordCount2 {
    public static void main(String[] args) throws Exception {
        //TODO 0.env
        //ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //env.setRuntimeMode(RuntimeExecutionMode.BATCH);//注意:使用DataStream实现批处理
        //env.setRuntimeMode(RuntimeExecutionMode.STREAMING);//注意:使用DataStream实现流处理
        //env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);//注意:使用DataStream根据数据源自动选择使用流还是批

        //TODO 1.source
        //DataSet<String> lines = env.fromElements("itcast hadoop spark", "itcast hadoop spark", "itcast hadoop", "itcast");
        DataStream<String> lines = env.fromElements("itcast hadoop spark", "itcast hadoop spark", "itcast hadoop", "itcast");

        //TODO 2.transformation
        //切割
        /*
        @FunctionalInterface
        public interface FlatMapFunction<T, O> extends Function, Serializable {
            void flatMap(T value, Collector<O> out) throws Exception;
        }
         */
        DataStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String value, Collector<String> out) throws Exception {
                //value就是每一行数据
                String[] arr = value.split(" ");
                for (String word : arr) {
                    out.collect(word);
                }
            }
        });

        //记为1
        /*
        @FunctionalInterface
        public interface MapFunction<T, O> extends Function, Serializable {
            O map(T value) throws Exception;
        }
         */
        DataStream<Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public Tuple2<String, Integer> map(String value) throws Exception {
                //value就是一个个单词
                return Tuple2.of(value, 1);
            }
        });

        //分组:注意DataSet中分组是groupBy,DataStream分组是keyBy
        //wordAndOne.keyBy(0);
        /*
        @FunctionalInterface
        public interface KeySelector<IN, KEY> extends Function, Serializable {
            KEY getKey(IN value) throws Exception;
        }
         */
        KeyedStream<Tuple2<String, Integer>, String> grouped = wordAndOne.keyBy(t -> t.f0);

        //聚合
        SingleOutputStreamOperator<Tuple2<String, Integer>> result = grouped.sum(1);

        //TODO 3.sink
        result.print();

        //TODO 4.execute/启动并等待程序结束
        env.execute();
    }
}