如何使用Scala在spark上存储时间戳数据

name := "Spark Timestamp Example"
version := "1.0"
scalaVersion := "2.12.10"

libraryDependencies ++= Seq(
  "org.apache.spark" %% "spark-core" % "3.2.0",
  "org.apache.spark" %% "spark-sql" % "3.2.0"
)

import org.apache.spark.sql.SparkSession

val spark = SparkSession.builder()
  .appName("Spark Timestamp Example")
  .master("local[*]")  // 在本地模式下运行，使用所有可用的CPU核心
  .getOrCreate()

import org.apache.spark.sql.functions._

val timestampData = Seq(
  "2022-01-01 10:00:00",
  "2022-01-02 12:30:00",
  "2022-01-03 15:45:00"
)

val df = spark.createDataFrame(timestampData.map(Tuple1.apply)).toDF("timestamp")

df.write
  .format("parquet")  // 存储格式为Parquet
  .mode("overwrite")  // 如果目标路径已存在，覆盖原有数据
  .save("hdfs://path/to/save/timestamp_data.parquet")