scala实现

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

val parentWindowSpec = Window.orderBy("parent_id")
val childWindowSpec = Window.partitionBy(
    "parent_version", "service_id"
    ).orderBy("product_relation_id")

val df = spark.read.options(
    Map("inferSchema"->"true","delimiter"->",","header"->"true")
    ).csv("product.csv")

val df2 = df.withColumn(
    "parent_version", dense_rank.over(parentWindowSpec)
    ).withColumn(
    "child_version",row_number.over(childWindowSpec) - 1)

val df3 = df2.withColumn("id", 
    when(col("product_name") === lit("Parent"), 
        concat(lit("1."), col("parent_version")))
    .otherwise(concat(lit("1."), col("parent_version"),lit("."),col("child_version")))
).drop("parent_version").drop("child_version")

输出：

scala> df3.show
21/03/26 11:55:01 WARN WindowExec: No Partition Defined for Window operation! Moving all data to a single partition, this can cause serious performance degradation.
+---------+----------+-------------------+------------+-----+
|parent_id|service_id|product_relation_id|product_name|   id|
+---------+----------+-------------------+------------+-----+
|      100|         1|                1-A|      Parent|  1.1|
|      100|         1|                1-A|      Child1|1.1.1|
|      100|         1|                1-A|      Child2|1.1.2|
|      100|         1|                1-A|      Child3|1.1.3|
|      100|         1|                1-A|      Child4|1.1.4|
|      100|         2|                1-B|      Parent|  1.1|
|      100|         2|                1-B|      Child1|1.1.1|
|      100|         2|                1-B|      Child2|1.1.2|
|      100|         2|                1-B|      Child3|1.1.3|
|      100|         2|                1-B|      Child4|1.1.4|
|      100|         3|                1-C|      Parent|  1.1|
|      100|         3|                1-C|      Child1|1.1.1|
|      100|         3|                1-C|      Child2|1.1.2|
|      100|         3|                1-C|      Child3|1.1.3|
|      100|         3|                1-C|      Child4|1.1.4|
|      200|         5|                1-D|      Parent|  1.2|
|      200|         5|                1-D|      Child1|1.2.1|
|      200|         5|                1-D|      Child2|1.2.2|
|      200|         5|                1-D|      Child3|1.2.3|
|      200|         5|                1-D|      Child4|1.2.4|
+---------+----------+-------------------+------------+-----+
only showing top 20 rows