majdyz commented on code in PR #43451:
URL: https://github.com/apache/spark/pull/43451#discussion_r1365683194
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala:
##########
@@ -1087,6 +1087,27 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
}
}
+ test("SPARK-45604: schema mismatch failure error on timestamp_nz to
array<timestamp_nz>") {
+ import testImplicits._
+
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+ val timestamp = java.time.LocalDateTime.of(1, 2, 3, 4, 5)
+ val df1 = Seq((1, timestamp)).toDF()
+ val df2 = Seq((2, Array(timestamp))).toDF()
+ df1.write.mode("overwrite").parquet(s"$path/parquet")
+ df2.write.mode("append").parquet(s"$path/parquet")
+
+ withSQLConf(SQLConf.PARQUET_VECTORIZED_READER_ENABLED.key -> "true") {
+ val e = intercept[SparkException] {
+ spark.read.schema(df2.schema).parquet(s"$path/parquet").collect()
+ }
+ assert(e.getCause.isInstanceOf[SparkException])
+
assert(e.getCause.getCause.isInstanceOf[SchemaColumnConvertNotSupportedException])
Review Comment:
Added a subtask here: https://issues.apache.org/jira/browse/SPARK-45608
--
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]
