From ff2fe56004209ffe8eb150a56cbd5dccfb8d774b Mon Sep 17 00:00:00 2001 From: Cheng Lian Date: Mon, 17 Nov 2014 16:31:05 -0800 Subject: [SPARK-4309][SPARK-4407][SQL] Date type support for Thrift server, and fixes for complex types This PR is exactly the same as #3178 except it reverts the `FileStatus.isDir` to `FileStatus.isDirectory` change, since it doesn't compile with Hadoop 1. [Review on Reviewable](https://reviewable.io/reviews/apache/spark/3298) Author: Cheng Lian Closes #3298 from liancheng/date-for-thriftserver and squashes the following commits: 866037e [Cheng Lian] Revers isDirectory to isDir (it breaks Hadoop 1 profile) 6f71d0b [Cheng Lian] Makes toHiveString static 26fa955 [Cheng Lian] Fixes complex type support in Hive 0.13.1 shim a92882a [Cheng Lian] Updates HiveShim for 0.13.1 73f442b [Cheng Lian] Adds Date support for HiveThriftServer2 (Hive 0.12.0) (cherry picked from commit 6b7f2f753d16ff038881772f1958e3f4fd5597a7) Signed-off-by: Michael Armbrust --- .../hive/thriftserver/HiveThriftServer2Suite.scala | 90 +++++++++++++++------- 1 file changed, 64 insertions(+), 26 deletions(-) (limited to 'sql/hive-thriftserver/src') diff --git a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suite.scala b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suite.scala index bba29b2bdc..23d12cbff3 100644 --- a/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suite.scala +++ b/sql/hive-thriftserver/src/test/scala/org/apache/spark/sql/hive/thriftserver/HiveThriftServer2Suite.scala @@ -19,9 +19,10 @@ package org.apache.spark.sql.hive.thriftserver import java.io.File import java.net.ServerSocket -import java.sql.{DriverManager, Statement} +import java.sql.{Date, DriverManager, Statement} import java.util.concurrent.TimeoutException +import scala.collection.JavaConversions._ import scala.collection.mutable.ArrayBuffer import scala.concurrent.duration._ import scala.concurrent.{Await, Promise} @@ -51,6 +52,15 @@ import org.apache.spark.sql.hive.HiveShim class HiveThriftServer2Suite extends FunSuite with Logging { Class.forName(classOf[HiveDriver].getCanonicalName) + object TestData { + def getTestDataFilePath(name: String) = { + Thread.currentThread().getContextClassLoader.getResource(s"data/files/$name") + } + + val smallKv = getTestDataFilePath("small_kv.txt") + val smallKvWithNull = getTestDataFilePath("small_kv_with_null.txt") + } + def randomListeningPort = { // Let the system to choose a random available port to avoid collision with other parallel // builds. @@ -145,12 +155,8 @@ class HiveThriftServer2Suite extends FunSuite with Logging { } } - val env = Seq( - // Resets SPARK_TESTING to avoid loading Log4J configurations in testing class paths - "SPARK_TESTING" -> "0", - // Prevents loading classes out of the assembly jar. Otherwise Utils.sparkVersion can't read - // proper version information from the jar manifest. - "SPARK_PREPEND_CLASSES" -> "") + // Resets SPARK_TESTING to avoid loading Log4J configurations in testing class paths + val env = Seq("SPARK_TESTING" -> "0") Process(command, None, env: _*).run(ProcessLogger( captureThriftServerOutput("stdout"), @@ -194,15 +200,12 @@ class HiveThriftServer2Suite extends FunSuite with Logging { test("Test JDBC query execution") { withJdbcStatement() { statement => - val dataFilePath = - Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt") - - val queries = - s"""SET spark.sql.shuffle.partitions=3; - |CREATE TABLE test(key INT, val STRING); - |LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE test; - |CACHE TABLE test; - """.stripMargin.split(";").map(_.trim).filter(_.nonEmpty) + val queries = Seq( + "SET spark.sql.shuffle.partitions=3", + "DROP TABLE IF EXISTS test", + "CREATE TABLE test(key INT, val STRING)", + s"LOAD DATA LOCAL INPATH '${TestData.smallKv}' OVERWRITE INTO TABLE test", + "CACHE TABLE test") queries.foreach(statement.execute) @@ -216,14 +219,10 @@ class HiveThriftServer2Suite extends FunSuite with Logging { test("SPARK-3004 regression: result set containing NULL") { withJdbcStatement() { statement => - val dataFilePath = - Thread.currentThread().getContextClassLoader.getResource( - "data/files/small_kv_with_null.txt") - val queries = Seq( "DROP TABLE IF EXISTS test_null", "CREATE TABLE test_null(key INT, val STRING)", - s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE test_null") + s"LOAD DATA LOCAL INPATH '${TestData.smallKvWithNull}' OVERWRITE INTO TABLE test_null") queries.foreach(statement.execute) @@ -270,13 +269,10 @@ class HiveThriftServer2Suite extends FunSuite with Logging { test("SPARK-4292 regression: result set iterator issue") { withJdbcStatement() { statement => - val dataFilePath = - Thread.currentThread().getContextClassLoader.getResource("data/files/small_kv.txt") - val queries = Seq( "DROP TABLE IF EXISTS test_4292", "CREATE TABLE test_4292(key INT, val STRING)", - s"LOAD DATA LOCAL INPATH '$dataFilePath' OVERWRITE INTO TABLE test_4292") + s"LOAD DATA LOCAL INPATH '${TestData.smallKv}' OVERWRITE INTO TABLE test_4292") queries.foreach(statement.execute) @@ -284,10 +280,52 @@ class HiveThriftServer2Suite extends FunSuite with Logging { Seq(238, 86, 311, 27, 165).foreach { key => resultSet.next() - assert(resultSet.getInt(1) == key) + assert(resultSet.getInt(1) === key) } statement.executeQuery("DROP TABLE IF EXISTS test_4292") } } + + test("SPARK-4309 regression: Date type support") { + withJdbcStatement() { statement => + val queries = Seq( + "DROP TABLE IF EXISTS test_date", + "CREATE TABLE test_date(key INT, value STRING)", + s"LOAD DATA LOCAL INPATH '${TestData.smallKv}' OVERWRITE INTO TABLE test_date") + + queries.foreach(statement.execute) + + assertResult(Date.valueOf("2011-01-01")) { + val resultSet = statement.executeQuery( + "SELECT CAST('2011-01-01' as date) FROM test_date LIMIT 1") + resultSet.next() + resultSet.getDate(1) + } + } + } + + test("SPARK-4407 regression: Complex type support") { + withJdbcStatement() { statement => + val queries = Seq( + "DROP TABLE IF EXISTS test_map", + "CREATE TABLE test_map(key INT, value STRING)", + s"LOAD DATA LOCAL INPATH '${TestData.smallKv}' OVERWRITE INTO TABLE test_map") + + queries.foreach(statement.execute) + + assertResult("""{238:"val_238"}""") { + val resultSet = statement.executeQuery("SELECT MAP(key, value) FROM test_map LIMIT 1") + resultSet.next() + resultSet.getString(1) + } + + assertResult("""["238","val_238"]""") { + val resultSet = statement.executeQuery( + "SELECT ARRAY(CAST(key AS STRING), value) FROM test_map LIMIT 1") + resultSet.next() + resultSet.getString(1) + } + } + } } -- cgit v1.2.3