[SPARK-3826][SQL]enable hive-thriftserver to support hive-0.13.1

In apache#2241 hive-thriftserver is not enabled. This patch enable hive-thriftserver to support hive-0.13.1 by using a shim layer refer to apache#2241. 1 A light shim layer(code in sql/hive-thriftserver/hive-version) for each different hive version to handle api compatibility 2 New pom profiles "hive-default" and "hive-versions"(copy from apache#2241) to activate different hive version 3 SBT cmd for different version as follows: hive-0.12.0 --- sbt/sbt -Phive,hadoop-2.3 -Phive-0.12.0 assembly hive-0.13.1 --- sbt/sbt -Phive,hadoop-2.3 -Phive-0.13.1 assembly 4 Since hive-thriftserver depend on hive subproject, this patch should be merged with apache#2241 to enable hive-0.13.1 for hive-thriftserver Author: wangfei <[email protected]> Author: scwf <[email protected]> Closes apache#2685 from scwf/shim-thriftserver1 and squashes the following commits: f26f3be [wangfei] remove clean to save time f5cac74 [wangfei] remove local hivecontext test 578234d [wangfei] use new shaded hive 18fb1ff [wangfei] exclude kryo in hive pom fa21d09 [wangfei] clean package assembly/assembly 8a4daf2 [wangfei] minor fix 0d7f6cf [wangfei] address comments f7c93ae [wangfei] adding build with hive 0.13 before running tests bcf943f [wangfei] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver1 c359822 [wangfei] reuse getCommandProcessor in hiveshim 52674a4 [scwf] sql/hive included since examples depend on it 3529e98 [scwf] move hive module to hive profile f51ff4e [wangfei] update and fix conflicts f48d3a5 [scwf] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver1 41f727b [scwf] revert pom changes 13afde0 [scwf] fix small bug 4b681f4 [scwf] enable thriftserver in profile hive-0.13.1 0bc53aa [scwf] fixed when result filed is null dfd1c63 [scwf] update run-tests to run hive-0.12.0 default now c6da3ce [scwf] Merge branch 'master' of https://github.com/apache/spark into shim-thriftserver 7c66b8e [scwf] update pom according spark-2706 ae47489 [scwf] update and fix conflicts
sadams · Oct 31, 2014 · 7c41d13 · 7c41d13
1 parent adb6415
commit 7c41d13
Show file tree

Hide file tree

Showing 12 changed files with 571 additions and 230 deletions.
diff --git a/assembly/pom.xml b/assembly/pom.xml
@@ -201,12 +201,6 @@
           <artifactId>spark-hive_${scala.binary.version}</artifactId>
           <version>${project.version}</version>
         </dependency>
-      </dependencies>
-    </profile>
-    <profile>
-      <!-- TODO: Move this to "hive" profile once 0.13 JDBC is supported -->
-      <id>hive-0.12.0</id>
-      <dependencies>
         <dependency>
           <groupId>org.apache.spark</groupId>
           <artifactId>spark-hive-thriftserver_${scala.binary.version}</artifactId>

diff --git a/dev/run-tests b/dev/run-tests
@@ -142,17 +142,24 @@ CURRENT_BLOCK=$BLOCK_BUILD
   # We always build with Hive because the PySpark Spark SQL tests need it.
   BUILD_MVN_PROFILE_ARGS="$SBT_MAVEN_PROFILES_ARGS -Phive -Phive-0.12.0"
 
-  echo "[info] Building Spark with these arguments: $BUILD_MVN_PROFILE_ARGS"
 
   # NOTE: echo "q" is needed because sbt on encountering a build file with failure
   #+ (either resolution or compilation) prompts the user for input either q, r, etc
   #+ to quit or retry. This echo is there to make it not block.
-  # NOTE: Do not quote $BUILD_MVN_PROFILE_ARGS or else it will be interpreted as a 
+  # NOTE: Do not quote $BUILD_MVN_PROFILE_ARGS or else it will be interpreted as a
   #+ single argument!
   # QUESTION: Why doesn't 'yes "q"' work?
   # QUESTION: Why doesn't 'grep -v -e "^\[info\] Resolving"' work?
+  # First build with 0.12 to ensure patches do not break the hive 12 build
+  echo "[info] Compile with hive 0.12"
   echo -e "q\n" \
-    | sbt/sbt $BUILD_MVN_PROFILE_ARGS clean package assembly/assembly \
+    | sbt/sbt $BUILD_MVN_PROFILE_ARGS clean hive/compile hive-thriftserver/compile \
+    | grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
+
+  # Then build with default version(0.13.1) because tests are based on this version
+  echo "[info] Building Spark with these arguments: $SBT_MAVEN_PROFILES_ARGS -Phive"
+  echo -e "q\n" \
+    | sbt/sbt $SBT_MAVEN_PROFILES_ARGS -Phive package assembly/assembly  \
     | grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
 }
 

diff --git a/pom.xml b/pom.xml
@@ -129,7 +129,7 @@
     <flume.version>1.4.0</flume.version>
     <zookeeper.version>3.4.5</zookeeper.version>
     <!-- Version used in Maven Hive dependency -->
-    <hive.version>0.13.1</hive.version>
+    <hive.version>0.13.1a</hive.version>
     <!-- Version used for internal directory structure -->
     <hive.version.short>0.13.1</hive.version.short>
     <derby.version>10.10.1.1</derby.version>
@@ -240,6 +240,18 @@
         <enabled>false</enabled>
       </snapshots>
     </repository>
+    <repository>
+      <!-- This is temporarily included to fix issues with Hive 0.13 -->
+      <id>spark-staging-hive13</id>
+      <name>Spring Staging Repository Hive 13</name>
+      <url>https://oss.sonatype.org/content/repositories/orgspark-project-1089/</url>
+      <releases>
+        <enabled>true</enabled>
+      </releases>
+      <snapshots>
+        <enabled>false</enabled>
+      </snapshots>
+    </repository>
   </repositories>
   <pluginRepositories>
     <pluginRepository>
@@ -908,9 +920,9 @@
                  by Spark SQL for code generation. -->
             <compilerPlugins>
               <compilerPlugin>
-                  <groupId>org.scalamacros</groupId>
-                  <artifactId>paradise_${scala.version}</artifactId>
-                  <version>${scala.macros.version}</version>
+                <groupId>org.scalamacros</groupId>
+                <artifactId>paradise_${scala.version}</artifactId>
+                <version>${scala.macros.version}</version>
               </compilerPlugin>
             </compilerPlugins>
           </configuration>
@@ -1314,14 +1326,19 @@
       </dependencies>
     </profile>
     <profile>
-      <id>hive-0.12.0</id>
+      <id>hive</id>
       <activation>
         <activeByDefault>false</activeByDefault>
       </activation>
-      <!-- TODO: Move this to "hive" profile once 0.13 JDBC is supported -->
       <modules>
         <module>sql/hive-thriftserver</module>
       </modules>
+    </profile>
+    <profile>
+      <id>hive-0.12.0</id>
+      <activation>
+        <activeByDefault>false</activeByDefault>
+      </activation>
       <properties>
         <hive.version>0.12.0-protobuf-2.5</hive.version>
         <hive.version.short>0.12.0</hive.version.short>

diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py
@@ -1400,33 +1400,6 @@ def hql(self, hqlQuery):
 
 class LocalHiveContext(HiveContext):
 
-    """Starts up an instance of hive where metadata is stored locally.
-
-    An in-process metadata data is created with data stored in ./metadata.
-    Warehouse data is stored in in ./warehouse.
-
-    >>> import os
-    >>> hiveCtx = LocalHiveContext(sc)
-    >>> try:
-    ...     supress = hiveCtx.sql("DROP TABLE src")
-    ... except Exception:
-    ...     pass
-    >>> kv1 = os.path.join(os.environ["SPARK_HOME"],
-    ...        'examples/src/main/resources/kv1.txt')
-    >>> supress = hiveCtx.sql(
-    ...     "CREATE TABLE IF NOT EXISTS src (key INT, value STRING)")
-    >>> supress = hiveCtx.sql("LOAD DATA LOCAL INPATH '%s' INTO TABLE src"
-    ...        % kv1)
-    >>> results = hiveCtx.sql("FROM src SELECT value"
-    ...      ).map(lambda r: int(r.value.split('_')[1]))
-    >>> num = results.count()
-    >>> reduce_sum = results.reduce(lambda x, y: x + y)
-    >>> num
-    500
-    >>> reduce_sum
-    130091
-    """
-
     def __init__(self, sparkContext, sqlContext=None):
         HiveContext.__init__(self, sparkContext, sqlContext)
         warnings.warn("LocalHiveContext is deprecated. "

diff --git a/sql/hive-thriftserver/pom.xml b/sql/hive-thriftserver/pom.xml
@@ -70,6 +70,24 @@
         <groupId>org.scalatest</groupId>
         <artifactId>scalatest-maven-plugin</artifactId>
       </plugin>
+      <plugin>
+        <groupId>org.codehaus.mojo</groupId>
+        <artifactId>build-helper-maven-plugin</artifactId>
+        <executions>
+          <execution>
+            <id>add-default-sources</id>
+            <phase>generate-sources</phase>
+            <goals>
+              <goal>add-source</goal>
+            </goals>
+            <configuration>
+              <sources>
+                <source>v${hive.version.short}/src/main/scala</source>
+              </sources>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-deploy-plugin</artifactId>

diff --git a/...ql/hive/thriftserver/SparkSQLDriver.scala → ...thriftserver/AbstractSparkSQLDriver.scala b/...ql/hive/thriftserver/SparkSQLDriver.scala → ...thriftserver/AbstractSparkSQLDriver.scala
@@ -29,11 +29,11 @@ import org.apache.hadoop.hive.ql.processors.CommandProcessorResponse
 import org.apache.spark.Logging
 import org.apache.spark.sql.hive.{HiveContext, HiveMetastoreTypes}
 
-private[hive] class SparkSQLDriver(val context: HiveContext = SparkSQLEnv.hiveContext)
-  extends Driver with Logging {
+private[hive] abstract class AbstractSparkSQLDriver(
+    val context: HiveContext = SparkSQLEnv.hiveContext) extends Driver with Logging {
 
-  private var tableSchema: Schema = _
-  private var hiveResponse: Seq[String] = _
+  private[hive] var tableSchema: Schema = _
+  private[hive] var hiveResponse: Seq[String] = _
 
   override def init(): Unit = {
   }
@@ -74,16 +74,6 @@ private[hive] class SparkSQLDriver(val context: HiveContext = SparkSQLEnv.hiveCo
 
   override def getSchema: Schema = tableSchema
 
-  override def getResults(res: JArrayList[String]): Boolean = {
-    if (hiveResponse == null) {
-      false
-    } else {
-      res.addAll(hiveResponse)
-      hiveResponse = null
-      true
-    }
-  }
-
   override def destroy() {
     super.destroy()
     hiveResponse = null

diff --git a/...hriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala b/...hriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala
@@ -38,6 +38,8 @@ import org.apache.hadoop.hive.shims.ShimLoader
 import org.apache.thrift.transport.TSocket
 
 import org.apache.spark.Logging
+import org.apache.spark.sql.hive.HiveShim
+import org.apache.spark.sql.hive.thriftserver.HiveThriftServerShim
 
 private[hive] object SparkSQLCLIDriver {
   private var prompt = "spark-sql"
@@ -116,7 +118,7 @@ private[hive] object SparkSQLCLIDriver {
       }
     }
 
-    if (!sessionState.isRemoteMode && !ShimLoader.getHadoopShims.usesJobShell()) {
+    if (!sessionState.isRemoteMode) {
       // Hadoop-20 and above - we need to augment classpath using hiveconf
       // components.
       // See also: code in ExecDriver.java
@@ -258,7 +260,7 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging {
     } else {
       var ret = 0
       val hconf = conf.asInstanceOf[HiveConf]
-      val proc: CommandProcessor = CommandProcessorFactory.get(tokens(0), hconf)
+      val proc: CommandProcessor = HiveShim.getCommandProcessor(Array(tokens(0)), hconf)
 
       if (proc != null) {
         if (proc.isInstanceOf[Driver] || proc.isInstanceOf[SetProcessor]) {

diff --git a/...riftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIService.scala b/...riftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIService.scala
@@ -24,6 +24,7 @@ import java.util.{List => JList}
 import javax.security.auth.login.LoginException
 
 import org.apache.commons.logging.Log
+import org.apache.hadoop.security.UserGroupInformation
 import org.apache.hadoop.hive.conf.HiveConf
 import org.apache.hadoop.hive.shims.ShimLoader
 import org.apache.hive.service.Service.STATE
@@ -44,15 +45,17 @@ private[hive] class SparkSQLCLIService(hiveContext: HiveContext)
     val sparkSqlSessionManager = new SparkSQLSessionManager(hiveContext)
     setSuperField(this, "sessionManager", sparkSqlSessionManager)
     addService(sparkSqlSessionManager)
+    var sparkServiceUGI: UserGroupInformation = null
 
-    try {
-      HiveAuthFactory.loginFromKeytab(hiveConf)
-      val serverUserName = ShimLoader.getHadoopShims
-        .getShortUserName(ShimLoader.getHadoopShims.getUGIForConf(hiveConf))
-      setSuperField(this, "serverUserName", serverUserName)
-    } catch {
-      case e @ (_: IOException | _: LoginException) =>
-        throw new ServiceException("Unable to login to kerberos with given principal/keytab", e)
+    if (ShimLoader.getHadoopShims().isSecurityEnabled()) {
+      try {
+        HiveAuthFactory.loginFromKeytab(hiveConf)
+        sparkServiceUGI = ShimLoader.getHadoopShims.getUGIForConf(hiveConf)
+        HiveThriftServerShim.setServerUserName(sparkServiceUGI, this)
+      } catch {
+        case e @ (_: IOException | _: LoginException) =>
+          throw new ServiceException("Unable to login to kerberos with given principal/keytab", e)
+      }
     }
 
     initCompositeService(hiveConf)