When hive.default.fileformat is other kinds of file types,

create textfile table cause a serde error
apache · Feb 13, 2018 · 979323a · 979323a
1 parent 14b5dbf
commit 979323a
Show file tree

Hide file tree

Showing 2 changed files with 23 additions and 2 deletions.
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/HiveSerDe.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/HiveSerDe.scala
@@ -31,7 +31,8 @@ object HiveSerDe {
     "sequencefile" ->
       HiveSerDe(
         inputFormat = Option("org.apache.hadoop.mapred.SequenceFileInputFormat"),
-        outputFormat = Option("org.apache.hadoop.mapred.SequenceFileOutputFormat")),
+        outputFormat = Option("org.apache.hadoop.mapred.SequenceFileOutputFormat"),
+        serde = Option("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe")),
 
     "rcfile" ->
       HiveSerDe(
@@ -54,7 +55,8 @@ object HiveSerDe {
     "textfile" ->
       HiveSerDe(
         inputFormat = Option("org.apache.hadoop.mapred.TextInputFormat"),
-        outputFormat = Option("org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat")),
+        outputFormat = Option("org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"),
+        serde = Option("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe")),
 
     "avro" ->
       HiveSerDe(

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveDDLCommandSuite.scala
@@ -615,6 +615,25 @@ class HiveDDLCommandSuite extends PlanTest with SQLTestUtils with TestHiveSingle
       assert(output == Some("org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat"))
       assert(serde == Some("org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe"))
     }
+
+    withSQLConf("hive.default.fileformat" -> "orc") {
+      val (desc, exists) = extractTableDesc(
+        "CREATE TABLE IF NOT EXISTS fileformat_test (id int) STORED AS textfile")
+      assert(exists)
+      assert(desc.storage.inputFormat == Some("org.apache.hadoop.mapred.TextInputFormat"))
+      assert(desc.storage.outputFormat ==
+        Some("org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat"))
+      assert(desc.storage.serde == Some("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"))
+    }
+
+    withSQLConf("hive.default.fileformat" -> "orc") {
+      val (desc, exists) = extractTableDesc(
+        "CREATE TABLE IF NOT EXISTS fileformat_test (id int) STORED AS sequencefile")
+      assert(exists)
+      assert(desc.storage.inputFormat == Some("org.apache.hadoop.mapred.SequenceFileInputFormat"))
+      assert(desc.storage.outputFormat == Some("org.apache.hadoop.mapred.SequenceFileOutputFormat"))
+      assert(desc.storage.serde == Some("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"))
+    }
   }
 
   test("table name with schema") {