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

185
packaging/hudi-hive-bundle/pom.xml
View File

@@ -28,71 +28,28 @@
<packaging>jar</packaging>
<dependencies>
<!-- Hoodie -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr-bundle</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-service</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-metastore</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-common</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${thrift.version}</version>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libfb303</artifactId>
<version>0.9.3</version>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<!-- Apache commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
<exclusions>
<exclusion>
<!-- All other hoodie deps will come from hoodie-hadoop-mr-bundle -->
<groupId>org.apache.hudi</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- Logging -->
@@ -105,43 +62,93 @@
<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>
<!-- Parquet (Twitter) -->
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<!-- Thrift -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr-bundle</artifactId>
<version>${project.version}</version>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${thrift.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
<exclusions>
<exclusion>
<!-- All other hudi deps will come from hudi-hadoop-mr-bundle -->
<groupId>org.apache.hudi</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
<groupId>org.apache.thrift</groupId>
<artifactId>libfb303</artifactId>
<version>0.9.3</version>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<!-- Httpcomponents -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<!-- Hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</dependency>
<!-- Hive -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-service</artifactId>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-metastore</artifactId>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-common</artifactId>
</dependency>
</dependencies>