diff options
author | Daoyuan Wang <daoyuan.wang@intel.com> | 2015-04-13 18:26:00 -0700 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2015-04-13 18:26:00 -0700 |
commit | b45059d0d7809a986ba07a447deb71f11ec6afe4 (patch) | |
tree | a290a7ea475fa41e010ad1223ddae7e5bda8a681 | |
parent | 3782e1f2bec07b5ffbc8503e40591e96fce67256 (diff) | |
download | spark-b45059d0d7809a986ba07a447deb71f11ec6afe4.tar.gz spark-b45059d0d7809a986ba07a447deb71f11ec6afe4.tar.bz2 spark-b45059d0d7809a986ba07a447deb71f11ec6afe4.zip |
[SPARK-5794] [SQL] fix add jar
Author: Daoyuan Wang <daoyuan.wang@intel.com>
Closes #4586 from adrian-wang/addjar and squashes the following commits:
efdd602 [Daoyuan Wang] move jar to another place
6c707e8 [Daoyuan Wang] restrict hive version for test
32c4fb8 [Daoyuan Wang] fix style and add a test
9957d87 [Daoyuan Wang] use sessionstate classloader in makeRDDforTable
0810e71 [Daoyuan Wang] remove variable substitution
1898309 [Daoyuan Wang] fix classnotfound
95a40da [Daoyuan Wang] support env argus in add jar, and set add jar ret to 0
5 files changed, 23 insertions, 4 deletions
diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala index 6272cdedb3..62c061bef6 100644 --- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala +++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala @@ -33,7 +33,7 @@ import org.apache.hadoop.hive.common.{HiveInterruptCallback, HiveInterruptUtils, import org.apache.hadoop.hive.conf.HiveConf import org.apache.hadoop.hive.ql.Driver import org.apache.hadoop.hive.ql.exec.Utilities -import org.apache.hadoop.hive.ql.processors.{SetProcessor, CommandProcessor, CommandProcessorFactory} +import org.apache.hadoop.hive.ql.processors.{AddResourceProcessor, SetProcessor, CommandProcessor, CommandProcessorFactory} import org.apache.hadoop.hive.ql.session.SessionState import org.apache.hadoop.hive.shims.ShimLoader import org.apache.thrift.transport.TSocket @@ -264,7 +264,8 @@ private[hive] class SparkSQLCLIDriver extends CliDriver with Logging { val proc: CommandProcessor = HiveShim.getCommandProcessor(Array(tokens(0)), hconf) if (proc != null) { - if (proc.isInstanceOf[Driver] || proc.isInstanceOf[SetProcessor]) { + if (proc.isInstanceOf[Driver] || proc.isInstanceOf[SetProcessor] || + proc.isInstanceOf[AddResourceProcessor]) { val driver = new SparkSQLDriver driver.init() diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala index d35291543c..e556c74ffb 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala @@ -35,6 +35,7 @@ import org.apache.spark.broadcast.Broadcast import org.apache.spark.rdd.{EmptyRDD, HadoopRDD, RDD, UnionRDD} import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.types.DateUtils +import org.apache.spark.util.Utils /** * A trait for subclasses that handle table scans. @@ -76,7 +77,9 @@ class HadoopTableReader( override def makeRDDForTable(hiveTable: HiveTable): RDD[Row] = makeRDDForTable( hiveTable, - relation.tableDesc.getDeserializerClass.asInstanceOf[Class[Deserializer]], + Class.forName( + relation.tableDesc.getSerdeClassName, true, sc.sessionState.getConf.getClassLoader) + .asInstanceOf[Class[Deserializer]], filterOpt = None) /** diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala index 99dc58646d..902a12785e 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/commands.scala @@ -80,7 +80,7 @@ case class AddJar(path: String) extends RunnableCommand { val hiveContext = sqlContext.asInstanceOf[HiveContext] hiveContext.runSqlHive(s"ADD JAR $path") hiveContext.sparkContext.addJar(path) - Seq.empty[Row] + Seq(Row(0)) } } diff --git a/sql/hive/src/test/resources/hive-hcatalog-core-0.13.1.jar b/sql/hive/src/test/resources/hive-hcatalog-core-0.13.1.jar Binary files differnew file mode 100644 index 0000000000..37af9aafad --- /dev/null +++ b/sql/hive/src/test/resources/hive-hcatalog-core-0.13.1.jar diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index 1222fbabd8..300b1f7920 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -813,6 +813,21 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { sql("DROP TABLE alter1") } + test("ADD JAR command 2") { + // this is a test case from mapjoin_addjar.q + val testJar = TestHive.getHiveFile("hive-hcatalog-core-0.13.1.jar").getCanonicalPath + val testData = TestHive.getHiveFile("data/files/sample.json").getCanonicalPath + if (HiveShim.version == "0.13.1") { + sql(s"ADD JAR $testJar") + sql( + """CREATE TABLE t1(a string, b string) + |ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe'""".stripMargin) + sql(s"""LOAD DATA LOCAL INPATH "$testData" INTO TABLE t1""") + sql("select * from src join t1 on src.key = t1.a") + sql("DROP TABLE t1") + } + } + test("ADD FILE command") { val testFile = TestHive.getHiveFile("data/files/v1.txt").getCanonicalFile sql(s"ADD FILE $testFile") |