yaooqinn commented on a change in pull request #31281:
URL: https://github.com/apache/spark/pull/31281#discussion_r563496408
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/CharVarcharTestSuite.scala
##########
@@ -37,31 +37,109 @@ trait CharVarcharTestSuite extends QueryTest with
SQLTestUtils {
assert(CharVarcharUtils.getRawType(f.metadata) == Some(dt))
}
- test("char type values should be padded: top-level columns") {
+ test("char type values should be padded or trimmed: top-level columns") {
withTable("t") {
sql(s"CREATE TABLE t(i STRING, c CHAR(5)) USING $format")
- sql("INSERT INTO t VALUES ('1', 'a')")
- checkAnswer(spark.table("t"), Row("1", "a" + " " * 4))
- checkColType(spark.table("t").schema(1), CharType(5))
+ (0 to 5).map(n => "a" + " " * n).foreach { v =>
+ sql(s"INSERT OVERWRITE t VALUES ('1', '$v')")
+ checkAnswer(spark.table("t"), Row("1", "a" + " " * 4))
+ checkColType(spark.table("t").schema(1), CharType(5))
+ }
sql("INSERT OVERWRITE t VALUES ('1', null)")
checkAnswer(spark.table("t"), Row("1", null))
+
+ val e = intercept[SparkException](sql("INSERT OVERWRITE t VALUES ('1',
'abcdef')"))
+ assert(e.getCause.getMessage.contains("Exceeds char/varchar type length
limitation: 5"))
}
}
- test("char type values should be padded: partitioned columns") {
+ test("char type values should be padded or trimmed: partitioned columns") {
+ withTable("t") {
+ sql(s"CREATE TABLE t(i STRING, c CHAR(5)) USING $format PARTITIONED BY
(c)")
+ (0 to 5).map(n => "a" + " " * n).foreach { v =>
+ sql(s"INSERT OVERWRITE t VALUES ('1', '$v')")
+ checkAnswer(spark.table("t"), Row("1", "a" + " " * 4))
+ checkColType(spark.table("t").schema(1), CharType(5))
+ }
+ val e1 = intercept[SparkException](sql("INSERT OVERWRITE t VALUES ('1',
'abcdef')"))
+ assert(e1.getCause.getMessage.contains("Exceeds char/varchar type length
limitation: 5"))
+ }
+
withTable("t") {
sql(s"CREATE TABLE t(i STRING, c CHAR(5)) USING $format PARTITIONED BY
(c)")
- sql("INSERT INTO t VALUES ('1', 'a')")
- checkAnswer(spark.table("t"), Row("1", "a" + " " * 4))
- checkColType(spark.table("t").schema(1), CharType(5))
+ (0 to 5).map(n => "a" + " " * n).foreach { v =>
+ sql(s"INSERT INTO t VALUES ('1', '$v')")
+ checkAnswer(spark.table("t"), Row("1", "a" + " " * 4))
+ sql(s"ALTER TABLE t DROP PARTITION(c='$v')")
Review comment:
good point, I will add one
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
