Spark-SQL 读写Parquet文件

• 读Parquet格式wenjian

import org.apache.spark.sql.{DataFrame, SparkSession}

object CreateDataFrameFromParquet {
  def main(args: Array[String]): Unit = {

    //创建SparkSession(是对SparkContext的包装和增强)
    val spark: SparkSession = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()
    
    val df: DataFrame = spark.read.parquet("src/main/scala/data/user.parquet")

    df.show(2)

    df.printSchema()
    
    spark.stop()
  }
}

 

• 写入到Parquet格式文件中

import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{DataFrame, Row, SparkSession}
import org.apache.spark.sql.types.{DoubleType, IntegerType, StringType, StructField, StructType}

object WriteToParquet {
  def main(args: Array[String]): Unit = {
    //创建SparkSession
    val spark: SparkSession = SparkSession.builder()
      .appName(this.getClass.getSimpleName)
      .master("local[*]")
      .getOrCreate()

    val sc: SparkContext = spark.sparkContext

    val lines: RDD[String] = sc.textFile("src/main/scala/data/user.txt")
    //row的字段没有名字 没有类型
    val rdd1: RDD[Row] = lines.map(e => {
      val split = e.split(",")
      Row(split(0), split(1).toInt, split(2).toDouble)
    })

    //关联schema(字段名称、字段类型、是否可以为空)
    val schema: StructType = StructType(
      Array(
        StructField("name", StringType),
        StructField("age", IntegerType),
        StructField("fv", DoubleType)
      )
    )
    //将RowRDD与StructType中的schema关联
    val df1: DataFrame = spark.createDataFrame(rdd1, schema)

    df1.write.parquet("src/main/scala/data/outpar")

    sc.stop()
    spark.stop()
  }
}