NJAHNAVI2907 commented on code in PR #55661:
URL: https://github.com/apache/spark/pull/55661#discussion_r3221971071
##########
sql/core/src/test/scala/org/apache/spark/sql/VariantEndToEndSuite.scala:
##########
@@ -185,6 +185,28 @@ class VariantEndToEndSuite extends SharedSparkSession {
checkAnswer(variantDF, Seq(Row(expected)))
}
+ test("SPARK-56654: parse_json/from_json reject unpaired UTF-16 surrogates by
default") {
+ val invalidJson = "\"\\uD835\""
+ val df = Seq(invalidJson).toDF("j")
+ checkAnswer(df.selectExpr("try_parse_json(j)"), Seq(Row(null)))
+ checkAnswer(df.selectExpr("from_json(j, 'variant')"), Seq(Row(null)))
+
+ val parseJsonError = intercept[SparkException] {
+ df.selectExpr("parse_json(j)").collect()
+ }
+ val cause = Option(parseJsonError.getCause).getOrElse(parseJsonError)
+ assert(cause.getMessage.contains("MALFORMED_RECORD_IN_PARSING"),
+ s"Unexpected error message: ${cause.getMessage}")
Review Comment:
done
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
