[HUDI-1089] Refactor hudi-client to support multi-engine (#1827)
- This change breaks `hudi-client` into `hudi-client-common` and `hudi-spark-client` modules - Simple usages of Spark using jsc.parallelize() has been redone using EngineContext#map, EngineContext#flatMap etc - Code changes in the PR, break classes into `BaseXYZ` parent classes with no spark dependencies living in `hudi-client-common` - Classes on `hudi-spark-client` are named `SparkXYZ` extending the parent classes with all the Spark dependencies - To simplify/cleanup, HoodieIndex#fetchRecordLocation has been removed and its usages in tests replaced with alternatives Co-authored-by: Vinoth Chandar <vinoth@apache.org>
This commit is contained in:
Mathieu
@@ -24,294 +24,14 @@
|
||||
<modelVersion>4.0.0</modelVersion>
|
||||
|
||||
<artifactId>hudi-client</artifactId>
|
||||
<packaging>jar</packaging>
|
||||
<packaging>pom</packaging>
|
||||
|
||||
<properties>
|
||||
<main.basedir>${project.parent.basedir}</main.basedir>
|
||||
</properties>
|
||||
|
||||
<build>
|
||||
<plugins>
|
||||
<plugin>
|
||||
<groupId>org.jacoco</groupId>
|
||||
<artifactId>jacoco-maven-plugin</artifactId>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.apache.maven.plugins</groupId>
|
||||
<artifactId>maven-jar-plugin</artifactId>
|
||||
<executions>
|
||||
<execution>
|
||||
<goals>
|
||||
<goal>test-jar</goal>
|
||||
</goals>
|
||||
<phase>test-compile</phase>
|
||||
</execution>
|
||||
</executions>
|
||||
<configuration>
|
||||
<skip>false</skip>
|
||||
</configuration>
|
||||
</plugin>
|
||||
<plugin>
|
||||
<groupId>org.apache.rat</groupId>
|
||||
<artifactId>apache-rat-plugin</artifactId>
|
||||
</plugin>
|
||||
</plugins>
|
||||
|
||||
<resources>
|
||||
<resource>
|
||||
<directory>src/main/resources</directory>
|
||||
</resource>
|
||||
<resource>
|
||||
<directory>src/test/resources</directory>
|
||||
</resource>
|
||||
</resources>
|
||||
</build>
|
||||
|
||||
<dependencies>
|
||||
<!-- Hoodie -->
|
||||
<dependency>
|
||||
<groupId>org.apache.hudi</groupId>
|
||||
<artifactId>hudi-common</artifactId>
|
||||
<version>${project.version}</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.hudi</groupId>
|
||||
<artifactId>hudi-timeline-service</artifactId>
|
||||
<version>${project.version}</version>
|
||||
</dependency>
|
||||
|
||||
<!-- Logging -->
|
||||
<dependency>
|
||||
<groupId>log4j</groupId>
|
||||
<artifactId>log4j</artifactId>
|
||||
</dependency>
|
||||
|
||||
<!-- Parquet -->
|
||||
<dependency>
|
||||
<groupId>org.apache.parquet</groupId>
|
||||
<artifactId>parquet-avro</artifactId>
|
||||
</dependency>
|
||||
|
||||
<!-- Spark -->
|
||||
<dependency>
|
||||
<groupId>org.apache.spark</groupId>
|
||||
<artifactId>spark-core_${scala.binary.version}</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.spark</groupId>
|
||||
<artifactId>spark-sql_${scala.binary.version}</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.spark</groupId>
|
||||
<artifactId>spark-avro_${scala.binary.version}</artifactId>
|
||||
<scope>provided</scope>
|
||||
</dependency>
|
||||
|
||||
<!-- Dropwizard Metrics -->
|
||||
<dependency>
|
||||
<groupId>io.dropwizard.metrics</groupId>
|
||||
<artifactId>metrics-graphite</artifactId>
|
||||
<exclusions>
|
||||
<exclusion>
|
||||
<groupId>com.rabbitmq</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
</exclusions>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.dropwizard.metrics</groupId>
|
||||
<artifactId>metrics-core</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.dropwizard.metrics</groupId>
|
||||
<artifactId>metrics-jmx</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.prometheus</groupId>
|
||||
<artifactId>simpleclient</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.prometheus</groupId>
|
||||
<artifactId>simpleclient_httpserver</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.prometheus</groupId>
|
||||
<artifactId>simpleclient_dropwizard</artifactId>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>io.prometheus</groupId>
|
||||
<artifactId>simpleclient_pushgateway</artifactId>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>com.beust</groupId>
|
||||
<artifactId>jcommander</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<!-- Hadoop -->
|
||||
<dependency>
|
||||
<groupId>org.apache.hadoop</groupId>
|
||||
<artifactId>hadoop-client</artifactId>
|
||||
<exclusions>
|
||||
<exclusion>
|
||||
<groupId>javax.servlet</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
</exclusions>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.hadoop</groupId>
|
||||
<artifactId>hadoop-hdfs</artifactId>
|
||||
<classifier>tests</classifier>
|
||||
<!-- Need these exclusions to make sure JavaSparkContext can be setup. https://issues.apache.org/jira/browse/SPARK-1693 -->
|
||||
<exclusions>
|
||||
<exclusion>
|
||||
<groupId>org.mortbay.jetty</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>javax.servlet.jsp</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>javax.servlet</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
</exclusions>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.hadoop</groupId>
|
||||
<artifactId>hadoop-common</artifactId>
|
||||
<classifier>tests</classifier>
|
||||
<exclusions>
|
||||
<exclusion>
|
||||
<groupId>org.mortbay.jetty</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>javax.servlet.jsp</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>javax.servlet</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
</exclusions>
|
||||
</dependency>
|
||||
|
||||
<!-- Hbase -->
|
||||
<dependency>
|
||||
<groupId>org.apache.hbase</groupId>
|
||||
<artifactId>hbase-client</artifactId>
|
||||
<version>${hbase.version}</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.hbase</groupId>
|
||||
<artifactId>hbase-server</artifactId>
|
||||
<version>${hbase.version}</version>
|
||||
<scope>provided</scope>
|
||||
</dependency>
|
||||
|
||||
<!-- Hoodie - Tests -->
|
||||
<dependency>
|
||||
<groupId>org.apache.hudi</groupId>
|
||||
<artifactId>hudi-common</artifactId>
|
||||
<version>${project.version}</version>
|
||||
<classifier>tests</classifier>
|
||||
<type>test-jar</type>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.apache.hudi</groupId>
|
||||
<artifactId>hudi-hadoop-mr</artifactId>
|
||||
<version>${project.version}</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<!-- HBase - Tests -->
|
||||
<dependency>
|
||||
<groupId>org.apache.hbase</groupId>
|
||||
<artifactId>hbase-testing-util</artifactId>
|
||||
<version>${hbase.version}</version>
|
||||
<scope>test</scope>
|
||||
<exclusions>
|
||||
<exclusion>
|
||||
<groupId>org.codehaus.jackson</groupId>
|
||||
<artifactId>jackson-mapper-asl</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>org.codehaus.jackson</groupId>
|
||||
<artifactId>jackson-core-asl</artifactId>
|
||||
</exclusion>
|
||||
<exclusion>
|
||||
<groupId>javax.xml.bind</groupId>
|
||||
<artifactId>*</artifactId>
|
||||
</exclusion>
|
||||
</exclusions>
|
||||
</dependency>
|
||||
|
||||
<!-- Hive - Tests -->
|
||||
<dependency>
|
||||
<groupId>${hive.groupid}</groupId>
|
||||
<artifactId>hive-exec</artifactId>
|
||||
<version>${hive.version}</version>
|
||||
<scope>test</scope>
|
||||
<classifier>${hive.exec.classifier}</classifier>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>${hive.groupid}</groupId>
|
||||
<artifactId>hive-metastore</artifactId>
|
||||
<version>${hive.version}</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.jupiter</groupId>
|
||||
<artifactId>junit-jupiter-api</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.jupiter</groupId>
|
||||
<artifactId>junit-jupiter-engine</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.vintage</groupId>
|
||||
<artifactId>junit-vintage-engine</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.jupiter</groupId>
|
||||
<artifactId>junit-jupiter-params</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.mockito</groupId>
|
||||
<artifactId>mockito-junit-jupiter</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.platform</groupId>
|
||||
<artifactId>junit-platform-runner</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.platform</groupId>
|
||||
<artifactId>junit-platform-suite-api</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
|
||||
<dependency>
|
||||
<groupId>org.junit.platform</groupId>
|
||||
<artifactId>junit-platform-commons</artifactId>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
</dependencies>
|
||||
<modules>
|
||||
<module>hudi-client-common</module>
|
||||
<module>hudi-spark-client</module>
|
||||
</modules>
|
||||
</project>
|
||||
|
||||
Reference in New Issue
Block a user