feat: Add Hive 4.0.0

CHANGELOG.md

@@ -10,6 +10,7 @@ All notable changes to this project will be documented in this file.
 - vector: Add version `0.40.0` ([#802]).
 - airflow: Add version `2.9.3` ([#809]).
 - kafka: Add version `3.8.0` ([#813]).
+- hive: Add version `4.0.0` ([#818]).
 
 ### Removed
 
@@ -27,6 +28,7 @@ All notable changes to this project will be documented in this file.
 [#809]: https://github.com/stackabletech/docker-images/pull/809
 [#811]: https://github.com/stackabletech/docker-images/pull/811
 [#813]: https://github.com/stackabletech/docker-images/pull/813
+[#818]: https://github.com/stackabletech/docker-images/pull/818
 
 ## [24.7.0] - 2024-07-24
 

hadoop/Dockerfile

@@ -63,7 +63,7 @@ COPY hadoop/stackable/patches /stackable/patches
 RUN curl --fail -L "https://repo.stackable.tech/repository/packages/hadoop/hadoop-${PRODUCT}-src.tar.gz" | tar -xzC . && \
     patches/apply_patches.sh ${PRODUCT} && \
     cd hadoop-${PRODUCT}-src && \
-    mvn clean package -Pdist,native -pl '!hadoop-tools/hadoop-pipes,!hadoop-yarn-project,!hadoop-mapreduce-project,!hadoop-minicluster' -Drequire.fuse=true -DskipTests -Dmaven.javadoc.skip=true && \
+    mvn --no-transfer-progress clean package -Pdist,native -pl '!hadoop-tools/hadoop-pipes,!hadoop-yarn-project,!hadoop-mapreduce-project,!hadoop-minicluster' -Drequire.fuse=true -DskipTests -Dmaven.javadoc.skip=true && \
     cp -r hadoop-dist/target/hadoop-${PRODUCT} /stackable/hadoop-${PRODUCT} && \
     # HDFS fuse-dfs is not part of the regular dist output, so we need to copy it in ourselves
     cp hadoop-hdfs-project/hadoop-hdfs-native-client/target/main/native/fuse-dfs/fuse_dfs /stackable/hadoop-${PRODUCT}/bin && \
@@ -100,7 +100,7 @@ WORKDIR /stackable
 
 RUN curl --fail -L "https://github.com/stackabletech/hdfs-utils/archive/refs/tags/v${HDFS_UTILS}.tar.gz" | tar -xzC . && \
     cd hdfs-utils-${HDFS_UTILS} && \
-    mvn clean package -P hadoop-${PRODUCT} -DskipTests -Dmaven.javadoc.skip=true && \
+    mvn --no-transfer-progress clean package -P hadoop-${PRODUCT} -DskipTests -Dmaven.javadoc.skip=true && \
     mkdir -p /stackable/hadoop-${PRODUCT}/share/hadoop/common/lib && \
     cp target/hdfs-utils-$HDFS_UTILS.jar /stackable/hadoop-${PRODUCT}/share/hadoop/common/lib/hdfs-utils-${HDFS_UTILS}.jar && \
     rm -rf /stackable/hdfs-utils-main

hive/Dockerfile

@@ -30,11 +30,25 @@ curl --fail -L "https://repo.stackable.tech/repository/packages/hive/apache-hive
 patches/apply_patches.sh ${PRODUCT}
 
 cd /stackable/apache-hive-${PRODUCT}-src/
-mvn --batch-mode --no-transfer-progress clean package -DskipTests --projects standalone-metastore
-mv standalone-metastore/target/apache-hive-metastore-${PRODUCT}-bin/apache-hive-metastore-${PRODUCT}-bin /stackable
 
-ln -s /stackable/apache-hive-metastore-${PRODUCT}-bin/ /stackable/hive-metastore
-cp /stackable/bin/start-metastore /stackable/hive-metastore/bin
+if [[ "${PRODUCT}" == "3.1.3" ]] ; then
+  mvn --batch-mode --no-transfer-progress clean package -DskipTests --projects standalone-metastore
+  mv standalone-metastore/target/apache-hive-metastore-${PRODUCT}-bin/apache-hive-metastore-${PRODUCT}-bin /stackable
+else
+  # https://issues.apache.org/jira/browse/HIVE-20451 switched the metastore server packaging starting with 4.0.0
+  cd standalone-metastore
+  mvn --batch-mode --no-transfer-progress clean package -DskipTests --projects metastore-server
+
+  # We only seem to get a .tar.gz archive, so let's extract that to the correct location
+  cd /stackable
+  tar --extract -f /stackable/apache-hive-${PRODUCT}-src/standalone-metastore/metastore-server/target/apache-hive-standalone-metastore-server-${PRODUCT}-bin.tar.gz
+
+  # TODO: Remove once the fix https://github.com/apache/hive/pull/5419 is merged and released
+  # The schemaTool.sh is still pointing to the class location from Hive < 4.0.0, it seems like it was forgotten to update it
+  sed -i -e 's/CLASS=org.apache.hadoop.hive.metastore.tools.MetastoreSchemaTool/CLASS=org.apache.hadoop.hive.metastore.tools.schematool.MetastoreSchemaTool/' /stackable/apache-hive-metastore-${PRODUCT}-bin/bin/ext/schemaTool.sh
+fi
+
+cp /stackable/bin/start-metastore /stackable/apache-hive-metastore-${PRODUCT}-bin/bin
 rm -rf /stackable/apache-hive-${PRODUCT}-src
 
 curl --fail -L "https://repo.stackable.tech/repository/packages/jmx-exporter/jmx_prometheus_javaagent-${JMX_EXPORTER}.jar" -o "/stackable/jmx/jmx_prometheus_javaagent-${JMX_EXPORTER}.jar"

hive/stackable/patches/4.0.0/01-postgres-driver.patch

@@ -0,0 +1,24 @@
+diff --git a/standalone-metastore/metastore-server/pom.xml b/standalone-metastore/metastore-server/pom.xml
+index a8f680928c..7102f1b5ca 100644
+--- a/standalone-metastore/metastore-server/pom.xml
++++ b/standalone-metastore/metastore-server/pom.xml
+@@ -334,7 +334,6 @@
+     <dependency>
+       <groupId>org.postgresql</groupId>
+       <artifactId>postgresql</artifactId>
+-      <optional>true</optional>
+     </dependency>
+     <dependency>
+       <groupId>org.eclipse.jetty</groupId>
+diff --git a/standalone-metastore/pom.xml b/standalone-metastore/pom.xml
+index 28ac5ceb65..e3cbd821bd 100644
+--- a/standalone-metastore/pom.xml
++++ b/standalone-metastore/pom.xml
+@@ -397,7 +397,6 @@
+         <groupId>org.postgresql</groupId>
+         <artifactId>postgresql</artifactId>
+         <version>${postgres.version}</version>
+-        <scope>runtime</scope>
+       </dependency>
+       <dependency>
+         <groupId>org.apache.httpcomponents</groupId>

hive/stackable/patches/4.0.0/02-logging-dependencies.patch

@@ -0,0 +1,16 @@
+diff --git a/standalone-metastore/pom.xml b/standalone-metastore/pom.xml
+index 28ac5ceb65..03097e7f40 100644
+--- a/standalone-metastore/pom.xml
++++ b/standalone-metastore/pom.xml
+@@ -494,6 +494,11 @@
+       <groupId>com.fasterxml.jackson.core</groupId>
+       <artifactId>jackson-databind</artifactId>
+     </dependency>
++    <dependency>
++      <!-- Optional log4j dependency to be able to use the XmlLayout -->
++      <groupId>com.fasterxml.jackson.dataformat</groupId>
++      <artifactId>jackson-dataformat-xml</artifactId>
++    </dependency>
+   </dependencies>
+   <build>
+     <pluginManagement>

hive/versions.py

@@ -1,4 +1,16 @@
 versions = [
+    {
+        "product": "4.0.0",
+        "jmx_exporter": "1.0.1",
+        # Hive 4 must be built with Java 8 (according to GitHub README) but seems to run on Java 11
+        "java-base": "11",
+        "java-devel": "1.8.0",
+        "hadoop": "3.3.6",
+        # Keep consistent with the dependency from Hadoop: https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-aws/3.3.6
+        "aws_java_sdk_bundle": "1.12.367",
+        "azure_storage": "7.0.1",
+        "azure_keyvault_core": "1.0.0",
+    },
     {
         "product": "3.1.3",
         "jmx_exporter": "1.0.1",