Spark Streaming と Flink の比較

import org.apache.spark.streaming.{StreamingContext, Seconds}
import org.apache.spark.streaming.StreamingContext._
import org.apache.spark.sql.SparkSession

// 创建 SparkSession 和 StreamingContext
val spark = SparkSession.builder().master("local[*]").appName("StreamingAggregation").getOrCreate()
val ssc = new StreamingContext(spark.sparkContext, Seconds(1))

// 从文件数据流中创建 DStream
val lines = ssc.textFileStream("sensor_data.txt")

// 提取传感器 ID 和数值
val values = lines.map(line => (line.split(",")(0), line.split(",")(1).toDouble))

// 计算每分钟平均值
val windowedCounts = values.window(Seconds(60), Seconds(60)).mapValues(v => (v, 1)).reduceByKey((a, b) => (a._1 + b._1, a._2 + b._2))
val averages = windowedCounts.map(pair => (pair._1, pair._2._1 / pair._2._2))

// 打印结果
averages.foreachRDD(rdd => rdd.foreach(println))

// 启动 StreamingContext
ssc.start()
ssc.awaitTermination()

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class FlinkStreamingAggregation {

    public static void main(String[] args) throws Exception {
        // 创建 StreamExecutionEnvironment
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 从文件数据流中创建 DataStream
        DataStream<String> lines = env.readTextFile("sensor_data.txt");

        // 提取传感器 ID 和数值
        DataStream<Tuple2<String, Double>> values = lines
                .flatMap(s -> Arrays.stream(s.split(","))
                        .map(v -> new Tuple2<>(v.split("_")[0], Double.parseDouble(v.split("_")[1])))
                        .iterator());

        // 计算每分钟平均值
        DataStream<Tuple2<String, Double>> averages = values
                .keyBy(0)
                .timeWindow(Time.seconds(60), Time.seconds(60))
                .reduce((a, b) -> new Tuple2<>(a.f0, (a.f1 + b.f1) / 2));

        // 打印结果
        averages.print();

        // 执行 Pipeline
        env.execute("StreamingAggregation");
    }
}