xuzifu666 commented on code in PR #9866:
URL: https://github.com/apache/hudi/pull/9866#discussion_r1361413342
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestInsertTable.scala:
##########
@@ -1968,6 +1968,110 @@ class TestInsertTable extends HoodieSparkSqlTestBase {
})
}
+ test("Test multiple partition fields pruning") {
+
+ withRecordType()(withTempDir { tmp =>
+ val targetTable = generateTableName
+ spark.sql(
+ s"""
+ |create table ${targetTable} (
+ | `id` string,
+ | `name` string,
+ | `dt` bigint,
+ | `day` STRING,
+ | `hour` INT
+ |) using hudi
+ |tblproperties (
+ | 'primaryKey' = 'id',
+ | 'type' = 'mor',
+ | 'preCombineField'='dt',
+ | 'hoodie.index.type' = 'BUCKET',
+ | 'hoodie.bucket.index.hash.field' = 'id',
+ | 'hoodie.bucket.index.num.buckets'=512
+ | )
+ |partitioned by (`day`,`hour`)
+ |location '${tmp.getCanonicalPath}/$targetTable'
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
10 as `hour`
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
11 as `hour`
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
12 as `hour`
+ |""".stripMargin)
Review Comment:
done， had consolidate these statements into a single SQL
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/TestInsertTable.scala:
##########
@@ -1968,6 +1968,110 @@ class TestInsertTable extends HoodieSparkSqlTestBase {
})
}
+ test("Test multiple partition fields pruning") {
+
+ withRecordType()(withTempDir { tmp =>
+ val targetTable = generateTableName
+ spark.sql(
+ s"""
+ |create table ${targetTable} (
+ | `id` string,
+ | `name` string,
+ | `dt` bigint,
+ | `day` STRING,
+ | `hour` INT
+ |) using hudi
+ |tblproperties (
+ | 'primaryKey' = 'id',
+ | 'type' = 'mor',
+ | 'preCombineField'='dt',
+ | 'hoodie.index.type' = 'BUCKET',
+ | 'hoodie.bucket.index.hash.field' = 'id',
+ | 'hoodie.bucket.index.num.buckets'=512
+ | )
+ |partitioned by (`day`,`hour`)
+ |location '${tmp.getCanonicalPath}/$targetTable'
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
10 as `hour`
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
11 as `hour`
+ |""".stripMargin)
+ spark.sql(
+ s"""
+ |insert into ${targetTable}
+ |select '1' as id, 'aa' as name, 123 as dt, '2023-10-12' as `day`,
12 as `hour`
+ |""".stripMargin)
Review Comment:
done， had consolidate these statements into a single SQL
--
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: commits-unsubscr...@hudi.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
