cloud-fan commented on code in PR #45105:
URL: https://github.com/apache/spark/pull/45105#discussion_r1495891034
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -174,4 +176,89 @@ class CollationSuite extends QueryTest with
SharedSparkSession {
Row(expected))
}
}
+
+ test("create table with collation") {
+ val tableName = "parquet_dummy_tbl"
+ val collationName = "UCS_BASIC_LCASE"
+ val collationId = CollationFactory.collationNameToId(collationName)
+
+ withTable(tableName) {
+ sql(
+ s"""
+ |CREATE TABLE $tableName (c1 STRING COLLATE '$collationName')
+ |USING PARQUET
+ |""".stripMargin)
+
+ sql(s"INSERT INTO $tableName VALUES ('aaa')")
+ sql(s"INSERT INTO $tableName VALUES ('AAA')")
+
+ checkAnswer(sql(s"SELECT DISTINCT COLLATION(c1) FROM $tableName"),
Seq(Row(collationName)))
+ assert(sql(s"select c1 FROM $tableName").schema.head.dataType ==
StringType(collationId))
+ val dd = sql(s"SELECT c1 FROM $tableName").toDF("c2")
+ dd.write.mode(SaveMode.Overwrite).parquet("/tmp/stefan_tbl")
+ }
+ }
+
+ test("create table with collations inside a struct") {
+ val tableName = "struct_collation_tbl"
+ val collationName = "UCS_BASIC_LCASE"
+ val collationId = CollationFactory.collationNameToId(collationName)
+
+ withTable(tableName) {
+ sql(
+ s"""
+ |CREATE TABLE $tableName
+ |(c1 STRUCT<name: STRING COLLATE '$collationName', age: INT>)
+ |USING PARQUET
+ |""".stripMargin)
+
+ sql(s"INSERT INTO $tableName VALUES (named_struct('name', 'aaa', 'id',
1))")
+ sql(s"INSERT INTO $tableName VALUES (named_struct('name', 'AAA', 'id',
2))")
+
+ checkAnswer(sql(s"SELECT DISTINCT collation(c1.name) FROM $tableName"),
+ Seq(Row(collationName)))
+ assert(sql(s"SELECT c1.name FROM $tableName").schema.head.dataType ==
StringType(collationId))
+ }
+ }
+
+ test("add collated column with alter table") {
+ val tableName = "alter_column_tbl"
+ val defaultCollation = "UCS_BASIC"
+ val collationName = "UCS_BASIC_LCASE"
+ val collationId = CollationFactory.collationNameToId(collationName)
+
+ withTable(tableName) {
+ sql(
+ s"""
+ |CREATE TABLE $tableName (c1 STRING)
+ |USING PARQUET
+ |""".stripMargin)
+
+ sql(s"INSERT INTO $tableName VALUES ('aaa')")
+ sql(s"INSERT INTO $tableName VALUES ('AAA')")
+
+ checkAnswer(sql(s"SELECT DISTINCT COLLATION(c1) FROM $tableName"),
+ Seq(Row(defaultCollation)))
+
+ sql(
+ s"""
+ |ALTER TABLE $tableName
+ |ADD COLUMN c2 STRING COLLATE '$collationName'
+ |""".stripMargin)
+
+ sql(
+ s"""
+ |ALTER TABLE $tableName
+ |ALTER COLUMN c2
+ |SET DEFAULT ''
Review Comment:
does this do anything? The INSERT below always provide the values.
--
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]
