angerszhu created SPARK-33593:
---------------------------------
Summary: Parquet vector reader incorrect with binary partition
value
Key: SPARK-33593
URL: https://issues.apache.org/jira/browse/SPARK-33593
Project: Spark
Issue Type: Bug
Components: SQL
Affects Versions: 3.1.0
Reporter: angerszhu
{code:java}
test("Parquet vector reader incorrect with binary partition value") {
Seq(false, true).foreach(tag => {
withSQLConf("spark.sql.parquet.enableVectorizedReader" -> tag.toString) {
withTable("t1") {
sql(
"""CREATE TABLE t1(name STRING, id BINARY, part BINARY)
| USING PARQUET PARTITIONED BY (part)""".stripMargin)
sql(s"INSERT INTO t1 PARTITION(part = 'Spark SQL') VALUES('a',
X'537061726B2053514C')")
if (tag) {
checkAnswer(sql("SELECT name, cast(id as string), cast(part as
string) FROM t1"),
Row("a", "Spark SQL", ""))
} else {
checkAnswer(sql("SELECT name, cast(id as string), cast(part as
string) FROM t1"),
Row("a", "Spark SQL", "Spark SQL"))
}
}
}
})
}
{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
