satishkotha commented on a change in pull request #2483:
URL: https://github.com/apache/hudi/pull/2483#discussion_r563962124
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestCOWDataSource.scala
##########
@@ -198,6 +198,31 @@ class TestCOWDataSource extends HoodieClientTestBase {
.mode(SaveMode.Append)
.save(basePath)
+ val records2 = recordsToStrings(dataGen.generateInserts("002", 5)).toList
+ val inputDF2 = spark.read.json(spark.sparkContext.parallelize(records2, 2))
+ inputDF2.write.format("org.apache.hudi")
+ .options(commonOpts)
+ .option(DataSourceWriteOptions.OPERATION_OPT_KEY,
DataSourceWriteOptions.INSERT_OVERWRITE_OPERATION_OPT_VAL)
+ .mode(SaveMode.Append)
+ .save(basePath)
+
+ val metaClient = new
HoodieTableMetaClient(spark.sparkContext.hadoopConfiguration, basePath, true)
+ val commits =
metaClient.getActiveTimeline.filterCompletedInstants().getInstants.toArray
+ .map(instant => (instant.asInstanceOf[HoodieInstant]).getAction)
+ assertEquals(2, commits.size)
+ assertEquals("commit", commits(0))
+ assertEquals("replacecommit", commits(1))
Review comment:
Hi, Can you also read back the records and verify that only records2
show up. (data in records1 doesnt show up)
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
