From ea626b6acf0de0ff3b0678372f30ba6f84ae2b09 Mon Sep 17 00:00:00 2001
From: Yin Huai <yhuai@databricks.com>
Date: Wed, 12 Feb 2020 00:12:45 +0800
Subject: [PATCH] [SPARK-30783] Exclude hive-service-rpc

### What changes were proposed in this pull request?
Exclude hive-service-rpc from build.

### Why are the changes needed?
hive-service-rpc 2.3.6 and spark sql's thrift server module have duplicate classes. Leaving hive-service-rpc 2.3.6 in the class path means that spark can pick up classes defined in hive instead of its thrift server module, which can cause hard to debug runtime errors due to class loading order and compilation errors for applications depend on spark.

 If you compare hive-service-rpc 2.3.6's jar (https://search.maven.org/remotecontent?filepath=org/apache/hive/hive-service-rpc/2.3.6/hive-service-rpc-2.3.6.jar) and spark thrift server's jar (e.g. https://repository.apache.org/content/groups/snapshots/org/apache/spark/spark-hive-thriftserver_2.12/3.0.0-SNAPSHOT/spark-hive-thriftserver_2.12-3.0.0-20200207.021914-364.jar), you will see that all of classes provided by hive-service-rpc-2.3.6.jar are covered by spark thrift server's jar. https://issues.apache.org/jira/browse/SPARK-30783 has output of jar tf for both jars.

### Does this PR introduce any user-facing change?
No

### How was this patch tested?
Existing tests.

Closes #27533 from yhuai/SPARK-30783.

Authored-by: Yin Huai <yhuai@databricks.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
---
 dev/deps/spark-deps-hadoop-2.7-hive-2.3 |  1 -
 dev/deps/spark-deps-hadoop-3.2-hive-2.3 |  1 -
 pom.xml                                 | 20 ++++++++++++++++++++
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/dev/deps/spark-deps-hadoop-2.7-hive-2.3 b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
index 42bdf112ef..c50cf96dc9 100644
--- a/dev/deps/spark-deps-hadoop-2.7-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
@@ -87,7 +87,6 @@ hive-jdbc/2.3.6//hive-jdbc-2.3.6.jar
 hive-llap-common/2.3.6//hive-llap-common-2.3.6.jar
 hive-metastore/2.3.6//hive-metastore-2.3.6.jar
 hive-serde/2.3.6//hive-serde-2.3.6.jar
-hive-service-rpc/2.3.6//hive-service-rpc-2.3.6.jar
 hive-shims-0.23/2.3.6//hive-shims-0.23-2.3.6.jar
 hive-shims-common/2.3.6//hive-shims-common-2.3.6.jar
 hive-shims-scheduler/2.3.6//hive-shims-scheduler-2.3.6.jar
diff --git a/dev/deps/spark-deps-hadoop-3.2-hive-2.3 b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
index 6006fa4b43..c37ce7fab3 100644
--- a/dev/deps/spark-deps-hadoop-3.2-hive-2.3
+++ b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
@@ -86,7 +86,6 @@ hive-jdbc/2.3.6//hive-jdbc-2.3.6.jar
 hive-llap-common/2.3.6//hive-llap-common-2.3.6.jar
 hive-metastore/2.3.6//hive-metastore-2.3.6.jar
 hive-serde/2.3.6//hive-serde-2.3.6.jar
-hive-service-rpc/2.3.6//hive-service-rpc-2.3.6.jar
 hive-shims-0.23/2.3.6//hive-shims-0.23-2.3.6.jar
 hive-shims-common/2.3.6//hive-shims-common-2.3.6.jar
 hive-shims-scheduler/2.3.6//hive-shims-scheduler-2.3.6.jar
diff --git a/pom.xml b/pom.xml
index a8d6ac932b..925fa28a29 100644
--- a/pom.xml
+++ b/pom.xml
@@ -1452,6 +1452,11 @@
             <groupId>${hive.group}</groupId>
             <artifactId>hive-service</artifactId>
           </exclusion>
+          <exclusion>
+            <!-- All classes are covered by spark's hive-thriftserver module -->
+            <groupId>${hive.group}</groupId>
+            <artifactId>hive-service-rpc</artifactId>
+          </exclusion>
           <exclusion>
             <groupId>${hive.group}</groupId>
             <artifactId>hive-shims</artifactId>
@@ -1508,6 +1513,11 @@
             <groupId>${hive.group}</groupId>
             <artifactId>hive-service</artifactId>
           </exclusion>
+          <exclusion>
+            <!-- All classes are covered by spark's hive-thriftserver module -->
+            <groupId>${hive.group}</groupId>
+            <artifactId>hive-service-rpc</artifactId>
+          </exclusion>
           <exclusion>
             <groupId>${hive.group}</groupId>
             <artifactId>hive-shims</artifactId>
@@ -1761,6 +1771,11 @@
             <groupId>${hive.group}</groupId>
             <artifactId>hive-service</artifactId>
           </exclusion>
+          <exclusion>
+            <!-- All classes are covered by spark's hive-thriftserver module -->
+            <groupId>${hive.group}</groupId>
+            <artifactId>hive-service-rpc</artifactId>
+          </exclusion>
           <exclusion>
             <groupId>${hive.group}</groupId>
             <artifactId>hive-shims</artifactId>
@@ -1911,6 +1926,11 @@
             <artifactId>groovy-all</artifactId>
           </exclusion>
           <!-- Begin of Hive 2.3 exclusion -->
+          <exclusion>
+            <!-- All classes are covered by spark's hive-thriftserver module -->
+            <groupId>${hive.group}</groupId>
+            <artifactId>hive-service-rpc</artifactId>
+          </exclusion>
           <!-- parquet-hadoop-bundle:1.8.1 conflict with 1.10.1 -->
           <exclusion>
             <groupId>org.apache.parquet</groupId>