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

@@ -27,45 +27,90 @@
<artifactId>hudi-hadoop-mr-bundle</artifactId>
<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>
<exclusions>
<exclusion>
<!-- other hudi deps will come from hudi-hive-bundle -->
<!-- other hoodie deps will come from hoodie-hive-bundle -->
<groupId>org.apache.hudi</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- Avro -->
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<!-- Parquet -->
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<!-- Parquet (Twitter) -->
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-hadoop-bundle</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>com.twitter.common</groupId>
<artifactId>objectsize</artifactId>
<version>0.0.12</version>
</dependency>
<!-- Hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</dependency>
<!-- Hive -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
@@ -92,7 +137,7 @@
<artifactId>hive-shims</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-serde</artifactId>
<version>${hive.version}</version>
@@ -109,49 +154,9 @@
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</dependency>
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-hadoop-bundle</artifactId>
</dependency>
<dependency>
<groupId>com.twitter.common</groupId>
<artifactId>objectsize</artifactId>
<version>0.0.12</version>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo</artifactId>
<scope>test</scope>
</dependency>
<dependency>
@@ -159,6 +164,7 @@
<artifactId>junit</artifactId>
<scope>test</scope>
</dependency>
</dependencies>
<build>

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>

View File

@@ -28,46 +28,16 @@
<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>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${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-io</groupId>
<artifactId>commons-io</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr-bundle</artifactId>
<version>${project.version}</version>
</dependency>
<!-- Logging -->
@@ -80,30 +50,70 @@
<artifactId>slf4j-log4j12</artifactId>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
</dependency>
<!-- Parquet (Twitter) -->
<dependency>
<groupId>com.twitter</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<!-- Thrift -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hadoop-mr-bundle</artifactId>
<version>${project.version}</version>
<groupId>org.apache.thrift</groupId>
<artifactId>libthrift</artifactId>
<version>${thrift.version}</version>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</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-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>
</dependencies>

View File

@@ -127,6 +127,8 @@
<pattern>parquet.schema</pattern>
<shadedPattern>org.apache.hudi.parquet.schema</shadedPattern>
</relocation>
<!-- TODO: Revisit GH ISSUE #533 & PR#633-->
<!--
<relocation>
<pattern>org.apache.hive.jdbc.</pattern>
<shadedPattern>org.apache.hudi.org.apache.hive.jdbc.</shadedPattern>
@@ -155,6 +157,11 @@
<pattern>org.apache.hadoop.hive.service.</pattern>
<shadedPattern>org.apache.hudi.org.apache.hadoop_hive.service.</shadedPattern>
</relocation>
<relocation>
<pattern>org.apache.hadoop.hive.serde2.</pattern>
<shadedPattern>org.apache.hudi.org.apache.hadoop_hive.serde2.</shadedPattern>
</relocation>
-->
<relocation>
<pattern>com.esotericsoftware.kryo.</pattern>
<shadedPattern>org.apache.hudi.com.esotericsoftware.kryo.</shadedPattern>
@@ -177,9 +184,8 @@
<exclude>org.apache.derby:derby</exclude>
<exclude>org.apache.hadoop:*</exclude>
<exclude>org.apache.hbase:*</exclude>
<!-- Just include hive-common, hive-service, hive-metastore and hive-jdbc -->
<!-- Just include hive-common, hive-serde, hive-service, hive-metastore and hive-jdbc -->
<exclude>org.apache.hive:hive-exec</exclude>
<exclude>org.apache.hive:hive-serde</exclude>
<exclude>org.apache.hive:hive-shims</exclude>
<exclude>org.apache.spark:*</exclude>
</excludes>
@@ -206,102 +212,18 @@
</build>
<dependencies>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<!-- Scala -->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<!-- Hoodie -->
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_2.11</artifactId>
<version>3.0.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<dependency>
<groupId>com.databricks</groupId>
<artifactId>spark-avro_2.11</artifactId>
<version>4.0.0</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-service</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-metastore</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-common</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-configuration2</artifactId>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
@@ -318,16 +240,141 @@
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-spark</artifactId>
<version>${project.version}</version>
</dependency>
</dependency>
<!-- Logging -->
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
</dependency>
<!-- Fasterxml -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
</dependency>
<!-- Avro -->
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro</artifactId>
</dependency>
<!-- Spark -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<!-- Spark (Packages) -->
<dependency>
<groupId>com.databricks</groupId>
<artifactId>spark-avro_2.11</artifactId>
<version>4.0.0</version>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-configuration2</artifactId>
</dependency>
<!-- Hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<scope>provided</scope>
</dependency>
<!-- Hive - Compile -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
<classifier>standalone</classifier>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- TODO: Reinvestigate PR 633 -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-service</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-serde</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-metastore</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-common</artifactId>
<version>${hive.version}</version>
<scope>compile</scope>
</dependency>
<!-- TODO: Reinvestigate PR 633 -->
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_2.11</artifactId>
<version>${scalatest.version}</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>

View File

@@ -28,8 +28,6 @@
<packaging>jar</packaging>
<properties>
<log4j.version>1.2.17</log4j.version>
<junit.version>4.10</junit.version>
<checkstyle.skip>true</checkstyle.skip>
<notice.dir>${project.basedir}/src/main/resources/META-INF</notice.dir>
<notice.file>HUDI_NOTICE.txt</notice.file>
@@ -205,6 +203,98 @@
</repositories>
<dependencies>
<!-- Hoodie -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-spark</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-utilities</artifactId>
<version>${project.version}</version>
</dependency>
<!-- Logging -->
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</dependency>
<!-- Fasterxml -->
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-scala_2.11</artifactId>
</dependency>
<!-- Avro -->
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro-mapred</artifactId>
</dependency>
<!-- Parquet -->
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
</dependency>
<!-- Spark -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- Dropwizard Metrics -->
<dependency>
<groupId>io.dropwizard.metrics</groupId>
<artifactId>metrics-core</artifactId>
</dependency>
<dependency>
<groupId>io.javalin</groupId>
<artifactId>javalin</artifactId>
@@ -212,21 +302,114 @@
</dependency>
<dependency>
<groupId>io.dropwizard.metrics</groupId>
<groupId>com.yammer.metrics</groupId>
<artifactId>metrics-core</artifactId>
<version>2.2.0</version>
</dependency>
<!-- Used for SQL templating -->
<dependency>
<groupId>org.antlr</groupId>
<artifactId>stringtemplate</artifactId>
<version>4.0.2</version>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.module</groupId>
<artifactId>jackson-module-scala_2.11</artifactId>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>bijection-avro_2.11</artifactId>
<version>0.9.2</version>
</dependency>
<!-- Kafka -->
<dependency>
<groupId>io.confluent</groupId>
<artifactId>kafka-avro-serializer</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>common-config</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>common-utils</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>kafka-schema-registry-client</artifactId>
<version>3.0.0</version>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-pool</groupId>
<artifactId>commons-pool</artifactId>
</dependency>
<!-- Httpcomponents -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<!-- Hadoop -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- Hive -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
<classifier>standalone</classifier>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<!-- Hoodie - Test -->
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
<classifier>tests</classifier>
<type>test-jar</type>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
@@ -235,7 +418,6 @@
<type>test-jar</type>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
@@ -245,17 +427,7 @@
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-spark</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<classifier>tests</classifier>
</dependency>
<!-- Hadoop - Test -->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
@@ -275,7 +447,13 @@
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<classifier>tests</classifier>
</dependency>
<!-- Hive - Test -->
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-exec</artifactId>
@@ -283,191 +461,11 @@
<scope>test</scope>
</dependency>
<dependency>
<groupId>${hive.groupid}</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${hive.version}</version>
<classifier>standalone</classifier>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</exclusion>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-utilities</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
<classifier>tests</classifier>
<type>test-jar</type>
<scope>test</scope>
</dependency>
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>commons-pool</groupId>
<artifactId>commons-pool</artifactId>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpcore</artifactId>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-common</artifactId>
<exclusions>
<exclusion>
<groupId>javax.servlet</groupId>
<artifactId>servlet-api</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<dependency>
<groupId>com.yammer.metrics</groupId>
<artifactId>metrics-core</artifactId>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>${spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
<version>${spark.version}</version>
</dependency>
<!-- Used for SQL templating -->
<dependency>
<groupId>org.antlr</groupId>
<artifactId>stringtemplate</artifactId>
<version>4.0.2</version>
</dependency>
<dependency>
<groupId>com.beust</groupId>
<artifactId>jcommander</artifactId>
</dependency>
<dependency>
<groupId>org.mockito</groupId>
<artifactId>mockito-all</artifactId>
<version>1.10.19</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro-mapred</artifactId>
<version>1.7.7</version>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-avro</artifactId>
</dependency>
<dependency>
<groupId>org.apache.parquet</groupId>
<artifactId>parquet-hadoop</artifactId>
</dependency>
<dependency>
<groupId>com.twitter</groupId>
<artifactId>bijection-avro_2.11</artifactId>
<version>0.9.2</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>kafka-avro-serializer</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>common-config</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>common-utils</artifactId>
<version>3.0.0</version>
</dependency>
<dependency>
<groupId>io.confluent</groupId>
<artifactId>kafka-schema-registry-client</artifactId>
<version>3.0.0</version>
</dependency>
</dependencies>
</project>