HyukjinKwon commented on a change in pull request #33212:
URL: https://github.com/apache/spark/pull/33212#discussion_r664430269
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JacksonParser.scala
##########
@@ -404,6 +407,19 @@ class JacksonParser(
}
}
+ // When the input schema is setting to `nullable = false`, make sure the
field is not null.
+ var index = 0
+ while (badRecordException.isEmpty && !skipRow && index < schema.length) {
Review comment:
Can we fix `parseJsonToken` instead by passing `nullable` bool flag?
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala
##########
@@ -2924,6 +2924,50 @@ abstract class JsonSuite
}
}
}
+
+ test("SPARK-35912: nullability with different parse mode -- struct") {
+ val input =
+ """
+ |{
+ | "c1": {
+ | "c2": 1
+ | }
+ |}
+ |""".stripMargin
+ val json = spark.createDataset(spark.sparkContext.parallelize(input ::
Nil))(Encoders.STRING)
+
+ val load = (mode: String, schema: StructType) => {
+ spark.read
+ .option("mode", mode)
+ .schema(schema)
+ .json(json)
+ }
+
+ Seq(true, false).foreach { nullable =>
+ val schema = StructType(Seq(
+ StructField("c1",
+ StructType(Seq(
+ StructField("c2", IntegerType, nullable = false),
+ StructField("not_exist_col", IntegerType, nullable = false)
+ )),
+ nullable = nullable))
+ )
+
+ checkAnswer(load("DROPMALFORMED", schema), Seq.empty)
+
+ val exception = intercept[SparkException] {
+ load("FAILFAST", schema).collect
+ }.getMessage
+ assert(exception.contains(
+ "the null value found when parsing non-nullable field not_exist_col."))
+
+ val e = intercept[SparkException] {
+ load("PERMISSIVE", schema).collect()
+ }
+ assert(e.getMessage.contains(
+ "the null value found when parsing non-nullable field not_exist_col."))
Review comment:
I think we should better permissively allow this case?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
