XuQianJin-Stars commented on code in PR #8308:
URL: https://github.com/apache/hudi/pull/8308#discussion_r1151328221
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestInsertTable.scala:
##########
@@ -1060,6 +1060,59 @@ class TestInsertTable extends HoodieSparkSqlTestBase {
}
}
+ test("Test Bulk Insert Into Bucket Index Table") {
+ withSQLConf("hoodie.sql.bulk.insert.enable" -> "true") {
+ withTempDir { tmp =>
+ val tableName = generateTableName
+ // Create a partitioned table
+ spark.sql(
+ s"""
+ |create table $tableName (
+ | id int,
+ | dt string,
+ | name string,
+ | price double,
+ | ts long
+ |) using hudi
+ | tblproperties (
+ | primaryKey = 'id,name',
+ | preCombineField = 'ts',
+ | hoodie.index.type = 'BUCKET',
+ | hoodie.bucket.index.hash.field = 'id,name')
+ | partitioned by (dt)
+ | location '${tmp.getCanonicalPath}'
+ """.stripMargin)
+
+ // Note: Do not write the field alias, the partition field must be
placed last.
+ spark.sql(
+ s"""
+ | insert into $tableName values
+ | (1, 'a1,1', 10, 1000, "2021-01-05"),
+ | (2, 'a2', 20, 2000, "2021-01-06"),
+ | (3, 'a3', 30, 3000, "2021-01-07")
+ """.stripMargin)
+
+ checkAnswer(s"select id, name, price, ts, dt from $tableName")(
+ Seq(1, "a1,1", 10.0, 1000, "2021-01-05"),
+ Seq(2, "a2", 20.0, 2000, "2021-01-06"),
+ Seq(3, "a3", 30.0, 3000, "2021-01-07")
+ )
+
+ spark.sql(
+ s"""
+ | insert into $tableName values
+ | (1, 'a1,1', 10, 1000, "2021-01-05")
Review Comment:
Is this sql insertion to verify the update?
--
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]
