Flink从入门到实战四[DataStream API]-5-Source-从集合中获取数据

Flink 从集合中获取数据，我们直接看代码：

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

import java.util.Arrays;

/**
 * Stream Source From Collection
 */
public class StreamSourceFromCollection {

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
		
		//从集合中获取数据
        DataStreamSource<String> dataStreamSource = env.fromCollection(Arrays.asList(
                "hello flink",
                "hello java",
                "hello world",
                "test",
                "source",
                "collection"));

        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = dataStreamSource.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] words = s.split(" ");
                Arrays.stream(words).forEach((String sp) -> collector.collect(new Tuple2<String, Integer>(sp, 1)));
            }
        }).keyBy(item -> item.f0)
                .sum(1);

        sum.print();
        env.execute();
    }
}

输出结果：

2> (collection,1)
5> (hello,1)
3> (java,1)
5> (hello,2)
11> (source,1)
5> (hello,3)
9> (world,1)
9> (test,1)
13> (flink,1)