1
0

[HUDI-1399] support a independent clustering spark job to asynchronously clustering (#2379)

* [HUDI-1481]  add  structured streaming and delta streamer clustering unit test

* [HUDI-1399] support a independent clustering spark job to asynchronously clustering

* [HUDI-1399]  support a  independent clustering spark job to asynchronously clustering

* [HUDI-1498] Read clustering plan from requested file for inflight instant (#2389)

* [HUDI-1399]  support  a independent clustering spark job with schedule generate instant time

Co-authored-by: satishkotha <satishkotha@uber.com>
This commit is contained in:
lw0090
2021-01-10 09:30:16 +08:00
committed by GitHub
parent 65866c45ec
commit 368c1a8f5c
10 changed files with 338 additions and 38 deletions

View File

@@ -152,7 +152,18 @@ public class TableSchemaResolver {
* @throws Exception
*/
public Schema getTableAvroSchema() throws Exception {
Option<Schema> schemaFromCommitMetadata = getTableSchemaFromCommitMetadata(true);
return getTableAvroSchema(true);
}
/**
* Gets schema for a hoodie table in Avro format, can choice if include metadata fields.
*
* @param includeMetadataFields choice if include metadata fields
* @return Avro schema for this table
* @throws Exception
*/
public Schema getTableAvroSchema(boolean includeMetadataFields) throws Exception {
Option<Schema> schemaFromCommitMetadata = getTableSchemaFromCommitMetadata(includeMetadataFields);
return schemaFromCommitMetadata.isPresent() ? schemaFromCommitMetadata.get() : getTableAvroSchemaFromDataFile();
}

View File

@@ -109,7 +109,7 @@ public interface HoodieTimeline extends Serializable {
/**
* Filter this timeline to just include the in-flights excluding compaction instants.
*
* @return New instance of HoodieTimeline with just in-flights excluding compaction inflights
* @return New instance of HoodieTimeline with just in-flights excluding compaction instants
*/
HoodieTimeline filterPendingExcludingCompaction();