lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

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

Browse Source 
- [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
Download Patch File Download Diff File Expand all files Collapse all files

203
hudi-hive/pom.xml
View File

@@ -31,6 +31,81 @@
</properties>
<dependencies>
<!-- Hoodie -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr</artifactId>
<version>${project.version}</version>
</dependency>
<!-- Logging -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</dependency>
<!-- Parquet (Twitter) -->
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${thrift.version}</version>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-pool</groupId>
<artifactId>commons-pool</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<!-- Httpcomponents -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<!-- Hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
@@ -48,66 +123,17 @@
<artifactId>hadoop-auth</artifactId>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${thrift.version}</version>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<!-- Apache commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-pool</groupId>
<artifactId>commons-pool</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<!-- Logging -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<!-- Hadoop Testing -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
</dependency>
<!-- Hive -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-service</artifactId>
@@ -139,64 +165,53 @@
<version>${hive.version}</version>
</dependency>
<!-- Hoodie - Test -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<classifier>tests</classifier>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-all</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
<classifier>tests</classifier>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.esotericsoftware.kryo</groupId>
<artifactId>kryo</artifactId>
<version>2.21</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.eclipse.jetty.aggregate</groupId>
<artifactId>jetty-all</artifactId>
<scope>test</scope>
</dependency>
<!-- Hadoop - Test -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<scope>test</scope>
</dependency>
</dependencies>
<build>
@@ -213,7 +228,7 @@
<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>