SEPURI-SAI-KRISHNA commented on code in PR #19648:
URL: https://github.com/apache/hudi/pull/19648#discussion_r3836395130
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/common/TestSlashSeparatedPartitionValue.scala:
##########
@@ -90,6 +90,113 @@ class TestSlashSeparatedPartitionValue extends
HoodieSparkSqlTestBase {
}
}
+ test("Test slash separated date partitions written through the row writer") {
+ withSQLConf("hoodie.spark.sql.insert.into.operation" -> "bulk_insert") {
+ withTempDir { tmp =>
+ val targetTable = generateTableName
+ val tablePath = s"${tmp.getCanonicalPath}/$targetTable"
+
+ spark.sql(
+ s"""
+ |create table $targetTable (
+ | `id` string,
+ | `name` string,
+ | `ts` bigint,
+ | `datestr` STRING
+ |) using hudi
+ | tblproperties (
+ | 'primaryKey' = 'id',
+ | 'type' = 'COW',
+ | 'preCombineField'='ts',
+ |
'hoodie.datasource.write.slash.separated.date.partitioning'='true'
+ | )
+ | partitioned by (`datestr`)
+ | location '$tablePath'
+ """.stripMargin)
+
+ // NOTE: The row writer derives the partition path off of an
[[InternalRow]], which used to
+ // blow up with a [[ClassCastException]]; a null partition value
used to NPE
+ spark.sql(
+ s"""
+ | insert into $targetTable values
+ | (1, 'a1', 1000, "2026-01-05"),
+ | (2, 'a2', 2000, "2026-01-06"),
+ | (3, 'a3', 3000, null)
+ """.stripMargin)
+
+ checkAnswer(s"select id, name, ts, _hoodie_partition_path, datestr
from $targetTable order by id")(
+ Seq("1", "a1", 1000, "2026/01/05", "2026-01-05"),
+ Seq("2", "a2", 2000, "2026/01/06", "2026-01-06"),
+ Seq("3", "a3", 3000, "__HIVE_DEFAULT_PARTITION__", null)
+ )
+
+ val metaClient = HoodieTableMetaClient.builder()
+
.setConf(HadoopFSUtils.getStorageConfWithCopy(spark.sparkContext.hadoopConfiguration))
+ .setBasePath(tablePath)
+ .build()
+ assertTrue(metaClient.getStorage.exists(new StoragePath(tablePath,
"2026/01/05")),
+ s"Partition path 2026/01/05 should exist")
+ assertTrue(metaClient.getStorage.exists(new StoragePath(tablePath,
"2026/01/06")),
+ s"Partition path 2026/01/06 should exist")
+ assertTrue(metaClient.getStorage.exists(new StoragePath(tablePath,
"__HIVE_DEFAULT_PARTITION__")),
+ s"Partition path __HIVE_DEFAULT_PARTITION__ should exist")
+ }
+ }
+ }
+
+ test("Test slash separated date partitions on a DATE typed partition
column") {
+ Seq("insert", "bulk_insert").foreach { operation =>
+ withSQLConf("hoodie.spark.sql.insert.into.operation" -> operation) {
+ withTempDir { tmp =>
+ val targetTable = generateTableName
+ val tablePath = s"${tmp.getCanonicalPath}/$targetTable"
+
+ spark.sql(
Review Comment:
Taken rather than ignored -- it paid for itself immediately, since the other
asks on this PR each needed another copy of the same block.
Extracted `createSlashPartitionedTable` (parameterized on partition-column
type, table type and the config value), `buildMetaClient`,
`assertPartitionDirsExist` and `assertMetadataTablePartitions`. The file went
from 268 lines to 267 while gaining two new tests and the metadata-table
assertions everywhere.
--
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]
