1
0

[HUDI-1296] Support Metadata Table in Spark Datasource (#4789)

* Bootstrapping initial support for Metadata Table in Spark Datasource

- Consolidated Avro/Row conversion utilities to center around Spark's AvroDeserializer ; removed duplication
- Bootstrapped HoodieBaseRelation
- Updated HoodieMergeOnReadRDD to be able to handle Metadata Table
- Modified MOR relations to be able to read different Base File formats (Parquet, HFile)
This commit is contained in:
Alexey Kudinkin
2022-02-24 13:23:13 -08:00
committed by GitHub
parent 521338b4d9
commit 85e8a5c4de
56 changed files with 1634 additions and 1010 deletions

View File

@@ -32,10 +32,14 @@ public class ComplexAvroKeyGenerator extends BaseKeyGenerator {
public ComplexAvroKeyGenerator(TypedProperties props) {
super(props);
this.recordKeyFields = Arrays.stream(props.getString(KeyGeneratorOptions.RECORDKEY_FIELD_NAME.key())
.split(",")).map(String::trim).filter(s -> !s.isEmpty()).collect(Collectors.toList());
this.partitionPathFields = Arrays.stream(props.getString(KeyGeneratorOptions.PARTITIONPATH_FIELD_NAME.key())
.split(",")).map(String::trim).filter(s -> !s.isEmpty()).collect(Collectors.toList());
this.recordKeyFields = Arrays.stream(props.getString(KeyGeneratorOptions.RECORDKEY_FIELD_NAME.key()).split(","))
.map(String::trim)
.filter(s -> !s.isEmpty())
.collect(Collectors.toList());
this.partitionPathFields = Arrays.stream(props.getString(KeyGeneratorOptions.PARTITIONPATH_FIELD_NAME.key()).split(","))
.map(String::trim)
.filter(s -> !s.isEmpty())
.collect(Collectors.toList());
}
@Override