1
0

[HUDI-91][HUDI-12]Migrate to spark 2.4.4, migrate to spark-avro library instead of databricks-avro, add support for Decimal/Date types

- Upgrade Spark to 2.4.4, Parquet to 1.10.1, Avro to 1.8.2
- Remove spark-avro from hudi-spark-bundle. Users need to provide --packages org.apache.spark:spark-avro:2.4.4 when running spark-shell or spark-submit
- Replace com.databricks:spark-avro with org.apache.spark:spark-avro
- Shade avro in hudi-hadoop-mr-bundle to make sure it does not conflict with hive's avro version.
This commit is contained in:
Udit Mehrotra
2020-01-12 15:03:11 -08:00
committed by Balaji Varadarajan
parent d9675c4ec0
commit ad50008a59
11 changed files with 128 additions and 79 deletions

View File

@@ -89,7 +89,7 @@
</relocation>
<relocation>
<pattern>org.apache.avro.</pattern>
<shadedPattern>${mr.bundle.avro.shade.prefix}org.apache.avro.</shadedPattern>
<shadedPattern>org.apache.hudi.org.apache.avro.</shadedPattern>
</relocation>
</relocations>
<createDependencyReducedPom>false</createDependencyReducedPom>
@@ -143,17 +143,7 @@
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
<scope>${mr.bundle.avro.scope}</scope>
<scope>compile</scope>
</dependency>
</dependencies>
<profiles>
<profile>
<id>mr-bundle-shade-avro</id>
<properties>
<mr.bundle.avro.scope>compile</mr.bundle.avro.scope>
<mr.bundle.avro.shade.prefix>org.apache.hudi.</mr.bundle.avro.shade.prefix>
</properties>
</profile>
</profiles>
</project>