jonvex commented on code in PR #9774:
URL: https://github.com/apache/hudi/pull/9774#discussion_r1347994369
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestMORDataSource.scala:
##########
@@ -996,6 +996,48 @@ class TestMORDataSource extends HoodieSparkClientTestBase
with SparkDatasetMixin
.save(basePath)
}
+ @ParameterizedTest
+ @EnumSource(value = classOf[HoodieRecordType], names = Array("AVRO",
"SPARK"))
+ def testClusteringSamePrecombine(recordType: HoodieRecordType): Unit = {
+ var writeOpts = Map(
+ "hoodie.insert.shuffle.parallelism" -> "4",
+ "hoodie.upsert.shuffle.parallelism" -> "4",
+ DataSourceWriteOptions.RECORDKEY_FIELD.key -> "_row_key",
+ DataSourceWriteOptions.PARTITIONPATH_FIELD.key -> "partition",
+ DataSourceWriteOptions.PRECOMBINE_FIELD.key -> "timestamp",
+ HoodieWriteConfig.TBL_NAME.key -> "hoodie_test",
+ DataSourceWriteOptions.OPERATION.key() ->
DataSourceWriteOptions.UPSERT_OPERATION_OPT_VAL,
+ DataSourceWriteOptions.TABLE_TYPE.key()->
DataSourceWriteOptions.MOR_TABLE_TYPE_OPT_VAL,
+ "hoodie.clustering.inline"-> "true",
+ "hoodie.clustering.inline.max.commits" -> "2",
+ "hoodie.clustering.plan.strategy.sort.columns" -> "_row_key",
+ "hoodie.metadata.enable" -> "false",
+ "hoodie.datasource.write.row.writer.enable" -> "false"
+ )
+ if (recordType.equals(HoodieRecordType.SPARK)) {
+ writeOpts = Map(HoodieWriteConfig.RECORD_MERGER_IMPLS.key ->
classOf[HoodieSparkRecordMerger].getName,
+ HoodieStorageConfig.LOGFILE_DATA_BLOCK_FORMAT.key -> "parquet") ++
writeOpts
+ }
+ val records1 = recordsToStrings(dataGen.generateInserts("001", 10)).asScala
+ val inputDF1: Dataset[Row] =
spark.read.json(spark.sparkContext.parallelize(records1, 2))
+ inputDF1.write.format("org.apache.hudi")
+ .options(writeOpts)
+ .mode(SaveMode.Overwrite)
+ .save(basePath)
+
+ val records2 = recordsToStrings(dataGen.generateUniqueUpdates("002",
5)).asScala
Review Comment:
Ok added a test case with deletes. Good that you pointed this out because
my solution didn't handle delete blocks.
--
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]
