spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [spark] kevinyu98 commented on a change in pull request #27130: [SPARK-25993][SQL][TESTS] Add test cases for CREATE EXTERNAL TABLE with subdirectories
Date Fri, 17 Jan 2020 18:50:03 GMT
kevinyu98 commented on a change in pull request #27130: [SPARK-25993][SQL][TESTS] Add test
cases for CREATE EXTERNAL TABLE with subdirectories
URL: https://github.com/apache/spark/pull/27130#discussion_r368083514
 
 

 ##########
 File path: sql/hive/src/test/scala/org/apache/spark/sql/hive/orc/HiveOrcSourceSuite.scala
 ##########
 @@ -170,4 +170,166 @@ class HiveOrcSourceSuite extends OrcSuite with TestHiveSingleton {
   test("SPARK-11412 read and merge orc schemas in parallel") {
     testMergeSchemasInParallel(OrcFileOperator.readOrcSchemasInParallel)
   }
+
+  test("SPARK-25993 CREATE EXTERNAL TABLE with subdirectories") {
+    Seq(true, false).foreach { convertMetastore =>
+      withSQLConf(HiveUtils.CONVERT_METASTORE_ORC.key -> s"$convertMetastore") {
+        withTempDir { dir =>
+          try {
+            val orcTblStatement1 =
+              s"""
+                 |CREATE EXTERNAL TABLE orc_tbl1(
+                 |  c1 int,
+                 |  c2 int,
+                 |  c3 string)
+                 |STORED AS orc
+                 |LOCATION '${s"${dir.getCanonicalPath}/l1/"}'""".stripMargin
+            sql(orcTblStatement1)
+
+            val orcTblInsertL1 =
+              s"INSERT INTO TABLE orc_tbl1 VALUES (1, 1, 'orc1'), (2, 2, 'orc2')".stripMargin
+            sql(orcTblInsertL1)
+
+            val orcTblStatement2 =
+            s"""
+               |CREATE EXTERNAL TABLE orc_tbl2(
+               |  c1 int,
+               |  c2 int,
+               |  c3 string)
+               |STORED AS orc
+               |LOCATION '${s"${dir.getCanonicalPath}/l1/l2/"}'""".stripMargin
+            sql(orcTblStatement2)
+
+            val orcTblInsertL2 =
+              s"INSERT INTO TABLE orc_tbl2 VALUES (3, 3, 'orc3'), (4, 4, 'orc4')".stripMargin
+            sql(orcTblInsertL2)
+
+            val orcTblStatement3 =
+            s"""
+               |CREATE EXTERNAL TABLE orc_tbl3(
+               |  c1 int,
+               |  c2 int,
+               |  c3 string)
+               |STORED AS orc
+               |LOCATION '${s"${dir.getCanonicalPath}/l1/l2/l3/"}'""".stripMargin
+            sql(orcTblStatement3)
+
+            val orcTblInsertL3 =
+              s"INSERT INTO TABLE orc_tbl3 VALUES (5, 5, 'orc5'), (6, 6, 'orc6')".stripMargin
+            sql(orcTblInsertL3)
+
+            withTable("tbl1", "tbl2", "tbl3", "tbl4", "tbl5", "tbl6") {
+              val topDirStatement =
+                s"""
+                   |CREATE EXTERNAL TABLE tbl1(
+                   |  c1 int,
+                   |  c2 int,
+                   |  c3 string)
+                   |STORED AS orc
+                   |LOCATION '${s"${dir.getCanonicalPath}"}'""".stripMargin
+              sql(topDirStatement)
+              val topDirSqlStatement = s"SELECT * FROM tbl1"
+              if (convertMetastore) {
+                checkAnswer(sql(topDirSqlStatement), Nil)
+              } else {
+                checkAnswer(sql(topDirSqlStatement),
+                  (1 to 6).map(i => Row(i, i, s"orc$i")))
+              }
+
+              val l1DirStatement =
+                s"""
+                   |CREATE EXTERNAL TABLE tbl2(
+                   |  c1 int,
+                   |  c2 int,
+                   |  c3 string)
+                   |STORED AS orc
+                   |LOCATION '${s"${dir.getCanonicalPath}/l1/"}'""".stripMargin
+              sql(l1DirStatement)
+              val l1DirSqlStatement = s"SELECT * FROM tbl2"
+              if (convertMetastore) {
+                checkAnswer(sql(l1DirSqlStatement),
+                  (1 to 2).map(i => Row(i, i, s"orc$i")))
+              } else {
+                checkAnswer(sql(l1DirSqlStatement),
+                  (1 to 6).map(i => Row(i, i, s"orc$i")))
 
 Review comment:
   done

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message