leesf commented on a change in pull request #2111:
URL: https://github.com/apache/hudi/pull/2111#discussion_r501676578
##########
File path:
hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/table/action/commit/TestUpsertPartitioner.java
##########
@@ -286,8 +303,48 @@ public void testUpsertPartitionerWithSmallInsertHandling()
throws Exception {
"Bucket 3 is INSERT");
assertEquals(4, insertBuckets.size(), "Total of 4 insert buckets");
- weights = new Double[] { 0.08, 0.31, 0.31, 0.31};
- cumulativeWeights = new Double[] { 0.08, 0.39, 0.69, 1.0};
+ weights = new Double[] {0.08, 0.31, 0.31, 0.31};
+ cumulativeWeights = new Double[] {0.08, 0.39, 0.69, 1.0};
+ assertInsertBuckets(weights, cumulativeWeights, insertBuckets);
+ }
+
+ @Test
+ public void testInsertPartitionerWithSmallInsertHandling() throws Exception {
+ final String testPartitionPath = "2016/09/26";
+ // Inserts .. Check updates go together & inserts subsplit, after
expanding smallest file
+ UpsertPartitioner partitioner = getInsertPartitioner(1000 * 1024, 400, 800
* 1024, testPartitionPath, false);
+ List<InsertBucketCumulativeWeightPair> insertBuckets =
partitioner.getInsertBuckets(testPartitionPath);
+
+ assertEquals(3, partitioner.numPartitions(), "Should have 3 partitions");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(0).bucketType,
+ "Bucket 0 is INSERT");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(1).bucketType,
+ "Bucket 1 is INSERT");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(2).bucketType,
+ "Bucket 2 is INSERT");
+ assertEquals(3, insertBuckets.size(), "Total of 3 insert buckets");
+
+ Double[] weights = {0.5, 0.25, 0.25};
+ Double[] cumulativeWeights = {0.5, 0.75, 1.0};
+ assertInsertBuckets(weights, cumulativeWeights, insertBuckets);
+
+ // Now with insert split size auto tuned
+ partitioner = getInsertPartitioner(1000 * 1024, 2400, 800 * 1024,
testPartitionPath, true);
+ insertBuckets = partitioner.getInsertBuckets(testPartitionPath);
+
+ assertEquals(4, partitioner.numPartitions(), "Should have 4 partitions");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(0).bucketType,
+ "Bucket 0 is INSERT");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(1).bucketType,
+ "Bucket 1 is INSERT");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(2).bucketType,
+ "Bucket 2 is INSERT");
+ assertEquals(BucketType.INSERT, partitioner.getBucketInfo(3).bucketType,
+ "Bucket 3 is INSERT");
Review comment:
ditto
----------------------------------------------------------------
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
