1
0

[HUDI-1040] Make Hudi support Spark 3 (#2208)

* Fix flaky MOR unit test

* Update Spark APIs to make it be compatible with both spark2 & spark3

* Refactor bulk insert v2 part to make Hudi be able to compile with Spark3

* Add spark3 profile to handle fasterxml & spark version

* Create hudi-spark-common module & refactor hudi-spark related modules

Co-authored-by: Wenning Ding <wenningd@amazon.com>
This commit is contained in:
wenningd
2020-12-09 15:52:23 -08:00
committed by GitHub
parent 3a91d26d62
commit fce1453fa6
79 changed files with 1040 additions and 172 deletions

33
pom.xml
View File

@@ -39,7 +39,7 @@
<module>hudi-cli</module>
<module>hudi-client</module>
<module>hudi-hadoop-mr</module>
<module>hudi-spark</module>
<module>hudi-spark-datasource</module>
<module>hudi-timeline-service</module>
<module>hudi-utilities</module>
<module>hudi-sync</module>
@@ -84,6 +84,9 @@
<java.version>1.8</java.version>
<fasterxml.version>2.6.7</fasterxml.version>
<fasterxml.jackson.databind.version>2.6.7.3</fasterxml.jackson.databind.version>
<fasterxml.jackson.module.scala.version>2.6.7.1</fasterxml.jackson.module.scala.version>
<fasterxml.jackson.dataformat.yaml.version>2.7.4</fasterxml.jackson.dataformat.yaml.version>
<kafka.version>2.0.0</kafka.version>
<glassfish.version>2.17</glassfish.version>
<parquet.version>1.10.1</parquet.version>
@@ -103,9 +106,12 @@
<http.version>4.4.1</http.version>
<spark.version>2.4.4</spark.version>
<flink.version>1.11.2</flink.version>
<spark2.version>2.4.4</spark2.version>
<spark3.version>3.0.0</spark3.version>
<avro.version>1.8.2</avro.version>
<scala.version>2.11.12</scala.version>
<scala.binary.version>2.11</scala.binary.version>
<scala12.version>2.12.10</scala12.version>
<apache-rat-plugin.version>0.12</apache-rat-plugin.version>
<scala-maven-plugin.version>3.3.1</scala-maven-plugin.version>
<scalatest.version>3.0.1</scalatest.version>
@@ -432,7 +438,7 @@
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
<version>${fasterxml.version}.3</version>
<version>${fasterxml.jackson.databind.version}</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.datatype</groupId>
@@ -442,7 +448,7 @@
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-scala_${scala.binary.version}</artifactId>
<version>${fasterxml.version}.1</version>
<version>${fasterxml.jackson.module.scala.version}</version>
</dependency>
<!-- Glassfish -->
@@ -1306,7 +1312,7 @@
<profile>
<id>scala-2.12</id>
<properties>
<scala.version>2.12.10</scala.version>
<scala.version>${scala12.version}</scala.version>
<scala.binary.version>2.12</scala.binary.version>
</properties>
<activation>
@@ -1341,6 +1347,25 @@
</plugins>
</build>
</profile>
<profile>
<id>spark3</id>
<properties>
<spark.version>${spark3.version}</spark.version>
<scala.version>${scala12.version}</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<kafka.version>2.4.1</kafka.version>
<fasterxml.version>2.10.0</fasterxml.version>
<fasterxml.jackson.databind.version>2.10.0</fasterxml.jackson.databind.version>
<fasterxml.jackson.module.scala.version>2.10.0</fasterxml.jackson.module.scala.version>
<fasterxml.jackson.dataformat.yaml.version>2.10.0</fasterxml.jackson.dataformat.yaml.version>
</properties>
<activation>
<property>
<name>spark3</name>
</property>
</activation>
</profile>
</profiles>
</project>