yihua commented on code in PR #12964:
URL: https://github.com/apache/hudi/pull/12964#discussion_r2110731022
##########
hudi-spark-datasource/hudi-spark-common/pom.xml:
##########
@@ -187,38 +186,52 @@
<version>${project.version}</version>
</dependency>
- <!-- Spark -->
+ <!-- hadoop -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-common</artifactId>
+ <version>${hadoop.version}</version>
<exclusions>
<exclusion>
- <groupId>javax.servlet</groupId>
- <artifactId>*</artifactId>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-sql_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-hdfs</artifactId>
</dependency>
+ <!-- Netty -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-hive_${scala.binary.version}</artifactId>
+ <groupId>io.netty</groupId>
+ <artifactId>netty-all</artifactId>
+ <version>4.1.66.Final</version>
</dependency>
+ <!-- Spark -->
+ <dependency>
+ <groupId>org.apache.spark</groupId>
+ <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <exclusions>
+ <exclusion>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
+ </exclusion>
Review Comment:
Similarly, why should this be excluded?
##########
hudi-spark-datasource/hudi-spark-common/pom.xml:
##########
@@ -187,38 +186,52 @@
<version>${project.version}</version>
</dependency>
- <!-- Spark -->
+ <!-- hadoop -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-common</artifactId>
+ <version>${hadoop.version}</version>
<exclusions>
<exclusion>
- <groupId>javax.servlet</groupId>
- <artifactId>*</artifactId>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-sql_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-hdfs</artifactId>
</dependency>
Review Comment:
Hadoop dependencies should be marked as `provided`.
##########
hudi-spark-datasource/hudi-spark-common/pom.xml:
##########
@@ -187,38 +186,52 @@
<version>${project.version}</version>
</dependency>
- <!-- Spark -->
+ <!-- hadoop -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-common</artifactId>
+ <version>${hadoop.version}</version>
<exclusions>
<exclusion>
- <groupId>javax.servlet</groupId>
- <artifactId>*</artifactId>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-sql_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-hdfs</artifactId>
</dependency>
+ <!-- Netty -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-hive_${scala.binary.version}</artifactId>
+ <groupId>io.netty</groupId>
+ <artifactId>netty-all</artifactId>
+ <version>4.1.66.Final</version>
Review Comment:
How is this version determined? Also, should this be provided, as Spark
runtime should provide this? Let's be careful on adding new compile time
dependency which can cause conflicts in production deployment.
##########
hudi-spark-datasource/hudi-spark-common/pom.xml:
##########
@@ -187,38 +186,52 @@
<version>${project.version}</version>
</dependency>
- <!-- Spark -->
+ <!-- hadoop -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-common</artifactId>
+ <version>${hadoop.version}</version>
<exclusions>
<exclusion>
- <groupId>javax.servlet</groupId>
- <artifactId>*</artifactId>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-sql_${scala.binary.version}</artifactId>
+ <groupId>org.apache.hadoop</groupId>
+ <artifactId>hadoop-hdfs</artifactId>
</dependency>
+ <!-- Netty -->
<dependency>
- <groupId>org.apache.spark</groupId>
- <artifactId>spark-hive_${scala.binary.version}</artifactId>
+ <groupId>io.netty</groupId>
+ <artifactId>netty-all</artifactId>
+ <version>4.1.66.Final</version>
</dependency>
+ <!-- Spark -->
+ <dependency>
+ <groupId>org.apache.spark</groupId>
+ <artifactId>spark-core_${scala.binary.version}</artifactId>
+ <exclusions>
+ <exclusion>
+ <groupId>org.apache.commons</groupId>
+ <artifactId>commons-lang3</artifactId>
+ </exclusion>
+ <exclusion>
+ <groupId>javax.servlet</groupId>
+ <artifactId>*</artifactId>
+ </exclusion>
+ </exclusions>
+ </dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.binary.version}</artifactId>
- <classifier>tests</classifier>
- <scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
- <artifactId>spark-core_${scala.binary.version}</artifactId>
- <classifier>tests</classifier>
- <scope>test</scope>
Review Comment:
Why removing this?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
