一种方法是使用官方databricks网站中的DataFrameFlattener隐式类found。
首先,您需要为 modules 列定义 JSON 架构,然后将数据框展平,如下所示。这里我假设文件test_json.txt
会有下一个内容:
{
"p1":"v1",
"p2":"v2",
"p3":"v3",
"modules": "{ \"nest11\":\"n1v1\", \"nest12\":\"n1v2\", \"nest13\": { \"nest21\": \"n2v1\" } }"
}
代码如下:
import org.apache.spark.sql.functions.col
import org.apache.spark.sql.{Column, DataFrame}
import org.apache.spark.sql.types.{DataType, StructType, StringType}
implicit class DataFrameFlattener(df: DataFrame) {
def flattenSchema: DataFrame = {
df.select(flatten(Nil, df.schema): _*)
}
protected def flatten(path: Seq[String], schema: DataType): Seq[Column] = schema match {
case s: StructType => s.fields.flatMap(f => flatten(path :+ f.name, f.dataType))
case other => col(path.map(n => s"`$n`").mkString(".")).as(path.mkString(".")) :: Nil
}
}
val schema = (new StructType)
.add("nest11", StringType)
.add("nest12", StringType)
.add("nest13", (new StructType).add("nest21", StringType, false))
val df = spark.read
.option("multiLine", true).option("mode", "PERMISSIVE")
.json("C:\\temp\\test_json.txt")
df.withColumn("modules", from_json($"modules", schema))
.select($"*")
.flattenSchema
这应该是输出:
+--------------+--------------+---------------------+---+---+---+
|modules.nest11|modules.nest12|modules.nest13.nest21|p1 |p2 |p3 |
+--------------+--------------+---------------------+---+---+---+
|n1v1 |n1v2 |n2v1 |v1 |v2 |v3 |
+--------------+--------------+---------------------+---+---+---+
如果您需要进一步说明,请告诉我。