From 5b73abd0b74014d26b8f6bd1ac11fe6c262a82fd Mon Sep 17 00:00:00 2001
From: Qi Yu <yuqi@datastrato.com>
Date: Mon, 23 Sep 2024 10:07:56 +0800
Subject: [PATCH] [#4979] improvement(docker-hive): Add S3 related
 configuration to support Hive S3 schema/table. (#4980)

### What changes were proposed in this pull request?

Add S3-related configuration in the `hive-site.xml`

### Why are the changes needed?

To support create table with S3 location.

Fix: #4979

### Does this PR introduce _any_ user-facing change?

N/A

### How was this patch tested?

Test locally.
---
 dev/docker/hive/hive-site.xml | 21 +++++++++++++++++++++
 dev/docker/hive/start.sh      |  6 ++++++
 docs/docker-image-details.md  |  6 ++++++
 3 files changed, 33 insertions(+)

diff --git a/dev/docker/hive/hive-site.xml b/dev/docker/hive/hive-site.xml
index 3346d6be61f..477187153cb 100644
--- a/dev/docker/hive/hive-site.xml
+++ b/dev/docker/hive/hive-site.xml
@@ -42,4 +42,25 @@
     <value>hdfs://__REPLACE__HOST_NAME:9000/user/hive/warehouse</value>
     <description>location of default database for the warehouse</description>
   </property>
+
+  <property>
+    <name>fs.s3a.access.key</name>
+    <value>S3_ACCESS_KEY_ID</value>
+  </property>
+
+  <property>
+    <name>fs.s3a.secret.key</name>
+    <value>S3_SECRET_KEY_ID</value>
+  </property>
+
+  <property>
+    <name>fs.s3a.endpoint</name>
+    <value>S3_ENDPOINT_ID</value>
+  </property>
+
+  <property>
+    <name>fs.s3a.aws.credentials.provider</name>
+    <value>org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider,com.amazonaws.auth.EnvironmentVariableCredentialsProvider,org.apache.hadoop.fs.s3a.AnonymousAWSCredentialsProvider</value>
+  </property>
+
 </configuration>
diff --git a/dev/docker/hive/start.sh b/dev/docker/hive/start.sh
index 8bf1f12b97f..b9c545a0a7f 100644
--- a/dev/docker/hive/start.sh
+++ b/dev/docker/hive/start.sh
@@ -27,6 +27,8 @@ else
   ln -s ${HADOOP2_HOME} ${HADOOP_HOME}
 fi
 
+ cp ${HADOOP_HOME}/share/hadoop/tools/lib/*aws* ${HIVE_HOME}/lib
+
 # Copy Hadoop and Hive configuration file and update hostname
 cp -f ${HADOOP_TMP_CONF_DIR}/* ${HADOOP_CONF_DIR}
 cp -f ${HIVE_TMP_CONF_DIR}/* ${HIVE_CONF_DIR}
@@ -34,6 +36,10 @@ sed -i "s/__REPLACE__HOST_NAME/$(hostname)/g" ${HADOOP_CONF_DIR}/core-site.xml
 sed -i "s/__REPLACE__HOST_NAME/$(hostname)/g" ${HADOOP_CONF_DIR}/hdfs-site.xml
 sed -i "s/__REPLACE__HOST_NAME/$(hostname)/g" ${HIVE_CONF_DIR}/hive-site.xml
 
+sed -i "s|S3_ACCESS_KEY_ID|${S3_ACCESS_KEY}|g" ${HIVE_CONF_DIR}/hive-site.xml
+sed -i "s|S3_SECRET_KEY_ID|${S3_SECRET_KEY}|g" ${HIVE_CONF_DIR}/hive-site.xml
+sed -i "s|S3_ENDPOINT_ID|${S3_ENDPOINT}|g" ${HIVE_CONF_DIR}/hive-site.xml
+
 # Link mysql-connector-java after deciding where HIVE_HOME symbolic link points to.
 ln -s /opt/mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}/mysql-connector-java-${MYSQL_JDBC_DRIVER_VERSION}.jar ${HIVE_HOME}/lib
 
diff --git a/docs/docker-image-details.md b/docs/docker-image-details.md
index 629541ea026..ba061ccd988 100644
--- a/docs/docker-image-details.md
+++ b/docs/docker-image-details.md
@@ -147,6 +147,12 @@ You can use this kind of image to test the catalog of Apache Hive.
 
 Changelog
 
+- apache/gravitino-ci:hive-0.1.14 
+  - Add amazon S3 related configurations in the `hive-site.xml` file.
+    - `fs.s3a.access.key` The access key for the S3 bucket.
+    - `fs.s3a.secret.key` The secret key for the S3 bucket.
+    - `fs.s3a.endpoint` The endpoint for the S3 bucket.
+
 - apache/gravitino-ci:hive-0.1.13 (Switch to Apache official DockerHub repository)
   - Use Gravitino release 0.6.0 Dockerfile to build the image.