Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/16296#discussion_r94699687
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveOptions.scala
---
@@ -0,0 +1,90 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.hive.execution
+
+import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap
+
+/**
+ * Options for the Hive data source.
+ */
+class HiveOptions(@transient private val parameters: CaseInsensitiveMap)
extends Serializable {
+ import HiveOptions._
+
+ def this(parameters: Map[String, String]) = this(new
CaseInsensitiveMap(parameters))
+
+ val format = parameters.get(FORMAT).map(_.toLowerCase)
+ val inputFormat = parameters.get(INPUT_FORMAT)
+ val outputFormat = parameters.get(OUTPUT_FORMAT)
+
+ if (inputFormat.isDefined != outputFormat.isDefined) {
+ throw new IllegalArgumentException("Cannot specify only inputFormat or
outputFormat, you " +
+ "have to specify both of them.")
+ }
+
+ if (format.isDefined && inputFormat.isDefined) {
+ throw new IllegalArgumentException("Cannot specify format and
inputFormat/outputFormat " +
+ "together for Hive data source.")
+ }
+
+ val serde = parameters.get(SERDE)
+
+ for (f <- format if serde.isDefined) {
+ if (!Set("sequencefile", "textfile", "rcfile").contains(f)) {
+ throw new IllegalArgumentException(s"format '$f' already specifies a
serde.")
+ }
+ }
+
+ val containsDelimiters =
delimiterOptions.keys.exists(parameters.contains)
--- End diff --
Add one more check? The `DELIMITED` clause cannot be used with a custom
serde. Previously, it is blocked by our parser.
```
row_format
: DELIMITED [FIELDS TERMINATED BY char [ESCAPED BY char]] [COLLECTION
ITEMS TERMINATED BY char]
[MAP KEYS TERMINATED BY char] [LINES TERMINATED BY char]
[NULL DEFINED AS char] -- (Note: Available in Hive 0.13 and later)
| SERDE serde_name [WITH SERDEPROPERTIES (property_name=property_value,
property_name=property_value, ...)]
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
