1
0

[HUDI-68] Pom cleanup & demo automation (#846)

- [HUDI-172] Cleanup Maven POM/Classpath
  - Fix ordering of dependencies in poms, to enable better resolution
  - Idea is to place more specific ones at the top
  - And place dependencies which use them below them
- [HUDI-68] : Automate demo steps on docker setup
 - Move hive queries from hive cli to beeline
 - Standardize on taking query input from text command files
 - Deltastreamer ingest, also does hive sync in a single step
 - Spark Incremental Query materialized as a derived Hive table using datasource
 - Fix flakiness in HDFS spin up and output comparison
 - Code cleanup around streamlining and loc reduction
 - Also fixed pom to not shade some hive classs in spark, to enable hive sync
This commit is contained in:
vinoth chandar
2019-08-22 20:18:50 -07:00
committed by GitHub
parent 92eed6aca8
commit 6edf0b9def
34 changed files with 2382 additions and 1681 deletions

View File

@@ -43,7 +43,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.5</version>
<version>${maven-jar-plugin.version}</version>
<executions>
<execution>
<goals>
@@ -79,77 +79,20 @@
</build>
<dependencies>
<dependency>
<groupId>org.rocksdb</groupId>
<artifactId>rocksdbjni</artifactId>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>${junit.version}</version>
<scope>test</scope>
</dependency>
<!-- Fasterxml -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
<version>${fasterxml.version}</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</dependency>
<!-- Avro -->
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
<version>${parquet.version}</version>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-all</artifactId>
<version>1.10.19</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.4</version>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>fluent-hc</artifactId>
<version>4.5.4</version>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo</artifactId>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
@@ -161,21 +104,91 @@
</exclusion>
</exclusions>
</dependency>
<!-- Parquet -->
<dependency>
<groupId>com.github.stefanbirkner</groupId>
<artifactId>system-rules</artifactId>
<version>1.16.0</version>
<scope>test</scope>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<!-- Twitter -->
<dependency>
<groupId>com.twitter.common</groupId>
<artifactId>objectsize</artifactId>
<version>0.0.12</version>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<!-- Httpcomponents -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>fluent-hc</artifactId>
</dependency>
<dependency>
<groupId>com.twitter.common</groupId>
<artifactId>objectsize</artifactId>
<version>0.0.12</version>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<dependency>
<groupId>org.rocksdb</groupId>
<artifactId>rocksdbjni</artifactId>
</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-common</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-all</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo-shaded</artifactId>
<version>4.0.2</version>
</dependency>
<dependency>
<groupId>com.github.stefanbirkner</groupId>
<artifactId>system-rules</artifactId>
<version>1.16.0</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>