wombatu-kun commented on code in PR #19026:
URL: https://github.com/apache/hudi/pull/19026#discussion_r3425213482
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestRecordLevelIndex.scala:
##########
@@ -393,6 +393,41 @@ class TestRecordLevelIndex extends
RecordLevelIndexTestBase with SparkDatasetMix
assertEquals(0, partition3Locations.size)
}
+ @Test
+ def testPartitionedRecordLevelIndexLookupUsesFullKey(): Unit = {
+ initMetaClient(HoodieTableType.COPY_ON_WRITE)
+ val dataGen = new HoodieTestDataGenerator()
+ val inserts = dataGen.generateInserts("001", 3)
+ val insertDf = toDataset(spark, inserts).withColumn("data_partition_path",
lit("partition1"))
+ val options = Map(HoodieWriteConfig.TBL_NAME.key -> "hoodie_test",
+ DataSourceWriteOptions.TABLE_TYPE.key ->
HoodieTableType.COPY_ON_WRITE.name(),
+ RECORDKEY_FIELD.key -> "_row_key",
+ PARTITIONPATH_FIELD.key -> "data_partition_path",
+ HoodieTableConfig.ORDERING_FIELDS.key -> "timestamp",
+ HoodieMetadataConfig.GLOBAL_RECORD_LEVEL_INDEX_ENABLE_PROP.key() ->
"false",
+ HoodieMetadataConfig.RECORD_LEVEL_INDEX_ENABLE_PROP.key() -> "true",
+ HoodieMetadataConfig.SECONDARY_INDEX_ENABLE_PROP.key() -> "false",
+ HoodieIndexConfig.INDEX_TYPE.key() -> RECORD_LEVEL_INDEX.name())
+ insertDf.write.format("hudi")
+ .options(options)
+ .mode(SaveMode.Overwrite)
+ .save(basePath)
+
+ val writeConfig = getWriteConfig(options)
+ val metadata = metadataWriter(writeConfig).getTableMetadata
+ val recordKeys = inserts.asScala.map(i =>
i.getRecordKey).asJava.stream().collect(Collectors.toList())
Review Comment:
`.stream().collect(Collectors.toList())` is redundant here: `.asJava`
already returns a `java.util.List[String]`, so this just allocates a second
copy. `inserts.asScala.map(_.getRecordKey).asJava` yields the same list.
--
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]
