Flink写入HDFS（文本，parquet，parquet+snappy）

flink版本：1.10.0

code:

    // 构建env环境
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.enableCheckpointing(1000*60) //1000*60 s一个checkpoint
    env.getCheckpointConfig.setCheckpointingMode(CheckpointingMode.EXACTLY_ONCE)
    env.setStateBackend(new RocksDBStateBackend(checkpointPath, true))
    env.getCheckpointConfig.enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION) //job取消，cp还在
    

    //任务失败会进行五次重试，重试间隔为50s
    env.setRestartStrategy(RestartStrategies.
      fixedDelayRestart(5, 
        50000)) 
    //kafak参数
    val properties = new Properties()
    properties.setProperty("bootstrap.servers", TEST_BROKERS)
    properties.setProperty("group.id", "toHdfs-Parquet-group")
    val kafkaConsumer = new FlinkKafkaConsumer[String](LAUNCHS_TOPIC, new SimpleStringSchema(), properties)
    val source = env.addSource(kafkaConsumer)
    // 解析json
    val kafkaSource=source.flatMap(new RichFlatMapFunction[String, LogSchema] {
   
      var gson:Gson=_
      override def open(parameters: Configuration): Unit = {
   
        gson=new Gson
      }
      override def flatMap(value: String, out: Collector[LogSchema]): Unit = {
   
        val LogSchema = gson.fromJson(value, classOf[LogSchema