Spark找不到窗口函数

Question

使用https://stackoverflow.com/a/32407543/5379015中提供的解决方案，我尝试重新创建相同的查询，但使用编程语法代替Dataframe API，如下所示：

import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.sql.hive.HiveContext
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.functions._

object HiveContextTest {
  def main(args: Array[String]) {
    val conf = new SparkConf().setAppName("HiveContextTest")
    val sc = new SparkContext(conf)
    val sqlContext = new HiveContext(sc)
    import sqlContext.implicits._

    val df = sc.parallelize(
      ("foo", 1) :: ("foo", 2) :: ("bar", 1) :: ("bar", 2) :: Nil
    ).toDF("k", "v")


    // using dataframe api works fine

    val w = Window.partitionBy($"k").orderBy($"v")
    df.select($"k",$"v", rowNumber().over(w).alias("rn")).show


    //using programmatic syntax doesn't work

    df.registerTempTable("df")
    val w2 = sqlContext.sql("select k,v,rowNumber() over (partition by k order by v) as rn from df")
    w2.show()

  }
}

第一个df.select($"k",$"v", rowNumber().over(w).alias("rn")).show工作正常，但w2.show()结果

Exception in thread "main" org.apache.spark.sql.AnalysisException: Couldn't find window function rowNumber;

有没有人对如何使用程序语法使这项工作有任何想法？提前谢谢了。

Answer 1

与rowNumber等效的SQL是row_number：

SELECT k, v, row_number() OVER (PARTITION BY k ORDER BY v) AS rn FROM df