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

5
hudi-cli/hudi-cli.sh
View File

@@ -1,7 +1,7 @@
#!/usr/bin/env bash
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
HUDI_JAR=`ls $DIR/target/hudi-cli-*-SNAPSHOT.jar | grep -v source | grep -v javadoc`
HOODIE_JAR=`ls $DIR/target/hudi-cli-*-SNAPSHOT.jar | grep -v source | grep -v javadoc`
if [ -z "$HADOOP_CONF_DIR" ]; then
echo "setting hadoop conf dir"
HADOOP_CONF_DIR="/etc/hadoop/conf"
@@ -13,5 +13,4 @@ fi
if [ -z "$CLIENT_JAR" ]; then
echo "client jar location not set"
fi
echo "java -cp ${HADOOP_CONF_DIR}:${SPARK_CONF_DIR}:$DIR/target/lib/*:$HUDI_JAR:${CLIENT_JAR} -DSPARK_CONF_DIR=${SPARK_CONF_DIR} -DHADOOP_CONF_DIR=${HADOOP_CONF_DIR} org.springframework.shell.Bootstrap"
java -cp ${HADOOP_CONF_DIR}:${SPARK_CONF_DIR}:$DIR/target/lib/*:$HUDI_JAR:${CLIENT_JAR} -DSPARK_CONF_DIR=${SPARK_CONF_DIR} -DHADOOP_CONF_DIR=${HADOOP_CONF_DIR} org.springframework.shell.Bootstrap
java -cp ${HADOOP_CONF_DIR}:${SPARK_CONF_DIR}:$DIR/target/lib/*:$HOODIE_JAR:${CLIENT_JAR} -DSPARK_CONF_DIR=${SPARK_CONF_DIR} -DHADOOP_CONF_DIR=${HADOOP_CONF_DIR} org.springframework.shell.Bootstrap $@

98
hudi-cli/pom.xml
View File

@@ -29,8 +29,6 @@
<properties>
<spring.shell.version>1.2.0.RELEASE</spring.shell.version>
<jar.mainclass>org.springframework.shell.Bootstrap</jar.mainclass>
<log4j.version>1.2.17</log4j.version>
<junit.version>4.10</junit.version>
<notice.dir>${project.basedir}/src/main/resources/META-INF</notice.dir>
</properties>
@@ -61,7 +59,7 @@
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.1</version>
<version>${scala-maven-plugin.version}</version>
</plugin>
</plugins>
</pluginManagement>
@@ -133,23 +131,42 @@
<dependencies>
<!-- Scala -->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<!-- Hoodie -->
<dependency>
<groupId>org.springframework.shell</groupId>
<artifactId>spring-shell</artifactId>
<version>${spring.shell.version}</version>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>de.vandermeer</groupId>
<artifactId>asciitable</artifactId>
<version>0.2.5</version>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-utilities</artifactId>
<version>${project.version}</version>
</dependency>
<!-- Logging -->
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
</dependency>
<!-- Spark -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
@@ -159,6 +176,24 @@
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<!-- Apache Commons -->
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.shell</groupId>
<artifactId>spring-shell</artifactId>
<version>${spring.shell.version}</version>
</dependency>
<dependency>
<groupId>de.vandermeer</groupId>
<artifactId>asciitable</artifactId>
<version>0.2.5</version>
</dependency>
<dependency>
<groupId>com.jakewharton.fliptables</groupId>
<artifactId>fliptables</artifactId>
@@ -166,60 +201,25 @@
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>${log4j.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-hive</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-client</artifactId>
<version>${project.version}</version>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
</dependency>
<!-- Hadoop -->
<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.hudi</groupId>
<artifactId>hudi-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit-dep</artifactId>
<version>${junit.version}</version>
<version>${junit-dep.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
</dependency>
<dependency>
<groupId>joda-time</groupId>
<artifactId>joda-time</artifactId>
<version>2.9.6</version>
</dependency>
<dependency>
<groupId>org.apache.hudi</groupId>
<artifactId>hudi-utilities</artifactId>
<version>${project.version}</version>
</dependency>
</dependencies>
</project>

15
hudi-cli/src/main/java/org/apache/hudi/cli/commands/CompactionCommand.java
View File

@@ -217,12 +217,23 @@ public class CompactionCommand implements CommandMarker {
final String sparkMemory,
@CliOption(key = "retry", unspecifiedDefaultValue = "1", help = "Number of retries")
final String retry,
@CliOption(key = "compactionInstant", mandatory = true, help = "Base path for the target hoodie dataset")
final String compactionInstantTime) throws Exception {
@CliOption(key = "compactionInstant", mandatory = false, help = "Base path for the target hoodie dataset")
String compactionInstantTime) throws Exception {
boolean initialized = HoodieCLI.initConf();
HoodieCLI.initFS(initialized);
if (HoodieCLI.tableMetadata.getTableType() == HoodieTableType.MERGE_ON_READ) {
if (null == compactionInstantTime) {
// pick outstanding one with lowest timestamp
Option<String> firstPendingInstant = HoodieCLI.tableMetadata.reloadActiveTimeline()
.filterCompletedAndCompactionInstants().filter(instant -> instant.getAction()
.equals(HoodieTimeline.COMPACTION_ACTION)).firstInstant().map(HoodieInstant::getTimestamp);
if (!firstPendingInstant.isPresent()) {
return "NO PENDING COMPACTION TO RUN";
}
compactionInstantTime = firstPendingInstant.get();
}
String sparkPropertiesPath = Utils.getDefaultPropertiesFile(
scala.collection.JavaConversions.propertiesAsScalaMap(System.getProperties()));
SparkLauncher sparkLauncher = SparkUtil.initLauncher(sparkPropertiesPath);