rahil-c commented on code in PR #14001:
URL: https://github.com/apache/hudi/pull/14001#discussion_r2386364155
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestPayloadDeprecationFlow.scala:
##########
@@ -173,10 +244,52 @@ class TestPayloadDeprecationFlow extends
SparkClientFunctionalTestHarness {
option(OPERATION.key(), "delete").
option(HoodieCompactionConfig.INLINE_COMPACT.key(), "false").
option(HoodieCompactionConfig.INLINE_COMPACT_NUM_DELTA_COMMITS.key(),
"1").
+ option(HoodieCleanConfig.CLEANER_COMMITS_RETAINED.key(), "3").
+ option(HoodieCleanConfig.AUTO_CLEAN.key(), "false").
+ option(HoodieArchivalConfig.AUTO_ARCHIVE.key(), "true").
+ option(HoodieArchivalConfig.COMMITS_ARCHIVAL_BATCH_SIZE.key(), "1").
+ option(HoodieArchivalConfig.MIN_COMMITS_TO_KEEP.key(), "2").
+ option(HoodieArchivalConfig.MAX_COMMITS_TO_KEEP.key(), "3").
+ option(HoodieClusteringConfig.INLINE_CLUSTERING.key(), "true").
+ option(HoodieClusteringConfig.INLINE_CLUSTERING_MAX_COMMITS.key(), "2").
+ option(HoodieClusteringConfig.PLAN_STRATEGY_SMALL_FILE_LIMIT.key(),
"512000").
+ option(HoodieClusteringConfig.PLAN_STRATEGY_TARGET_FILE_MAX_BYTES.key(),
"512000").
mode(SaveMode.Append).
save(basePath)
- // 6. Validate.
+ // 6. Add INSERT operation.
+ val insertData = Seq(
+ (13, 6L, "rider-G", "driver-G", 25.50, "i", "13.1", 13, 1, "i"),
+ (13, 7L, "rider-H", "driver-H", 30.25, "i", "13.1", 13, 1, "i"))
+ val insertDataFrame = spark.createDataFrame(insertData).toDF(columns: _*)
+ insertDataFrame.write.format("hudi").
+ option(OPERATION.key(), DataSourceWriteOptions.INSERT_OPERATION_OPT_VAL).
+ option(HoodieCompactionConfig.INLINE_COMPACT.key(), "false").
+ option(HoodieCleanConfig.CLEANER_COMMITS_RETAINED.key(), "3").
+ option(HoodieCleanConfig.AUTO_CLEAN.key(), "false").
+ option(HoodieArchivalConfig.AUTO_ARCHIVE.key(), "true").
+ option(HoodieArchivalConfig.COMMITS_ARCHIVAL_BATCH_SIZE.key(), "1").
+ option(HoodieArchivalConfig.MIN_COMMITS_TO_KEEP.key(), "2").
+ option(HoodieArchivalConfig.MAX_COMMITS_TO_KEEP.key(), "3").
+ option(HoodieClusteringConfig.INLINE_CLUSTERING.key(), "true").
+ option(HoodieClusteringConfig.INLINE_CLUSTERING_MAX_COMMITS.key(), "2").
+ option(HoodieClusteringConfig.PLAN_STRATEGY_SMALL_FILE_LIMIT.key(),
"512000").
+ option(HoodieClusteringConfig.PLAN_STRATEGY_TARGET_FILE_MAX_BYTES.key(),
"512000").
+ mode(SaveMode.Append).
+ save(basePath)
+
+ // Final validation of table management operations after all writes
+ metaClient = HoodieTableMetaClient.builder()
Review Comment:
Yes I think there is an issue with reload api, not sure what @nsivabalan
plan is for this pr https://github.com/apache/hudi/pull/13979/files
--
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]
