Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/17043#discussion_r103052166
--- Diff:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaWriter.scala
---
@@ -0,0 +1,106 @@
+/*
+ * 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.kafka010
+
+import java.{util => ju}
+
+import org.apache.spark.TaskContext
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.{AnalysisException, SparkSession}
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.execution.{QueryExecution, SQLExecution}
+import org.apache.spark.sql.types.{BinaryType, StringType}
+import org.apache.spark.util.Utils
+
+private[kafka010] object KafkaWriter extends Logging {
+ val TOPIC_ATTRIBUTE_NAME: String = "topic"
+ val KEY_ATTRIBUTE_NAME: String = "key"
+ val VALUE_ATTRIBUTE_NAME: String = "value"
+
+ def write(
+ sparkSession: SparkSession,
+ queryExecution: QueryExecution,
+ kafkaParameters: ju.Map[String, Object],
+ topic: Option[String] = None): Unit = {
+ val schema = queryExecution.logical.output
+ schema.find(p => p.name == TOPIC_ATTRIBUTE_NAME).getOrElse(
+ if (topic == None) {
+ throw new AnalysisException(s"topic option required when no " +
+ s"'$TOPIC_ATTRIBUTE_NAME' attribute is present. Use the " +
+ s"${KafkaSourceProvider.TOPIC_OPTION_KEY} option for setting a
topic.")
+ } else {
+ Literal(topic.get, StringType)
+ }
+ ).dataType match {
+ case StringType => // good
+ case _ =>
+ throw new AnalysisException(s"Topic type must be a String")
+ }
+ schema.find(p => p.name == KEY_ATTRIBUTE_NAME).getOrElse(
+ Literal(null, StringType)
+ ).dataType match {
+ case StringType | BinaryType => // good
+ case _ =>
+ throw new AnalysisException(s"$KEY_ATTRIBUTE_NAME attribute type "
+
+ s"must be a String or BinaryType")
+ }
+ schema.find(p => p.name == VALUE_ATTRIBUTE_NAME).getOrElse(
+ throw new AnalysisException(s"Required attribute
'$VALUE_ATTRIBUTE_NAME' not found")
+ ).dataType match {
+ case StringType | BinaryType => // good
+ case _ =>
+ throw new AnalysisException(s"$VALUE_ATTRIBUTE_NAME attribute type
" +
+ s"must be a String or BinaryType")
+ }
+ SQLExecution.withNewExecutionId(sparkSession, queryExecution) {
--- End diff --
This is trying to following FileFormatWriter but actually it's not
necessary because we don't need to use the file commit protocol.
How about this?
```Scala
SQLExecution.withNewExecutionId(sparkSession, queryExecution) {
queryExecution.toRdd.foreachPartition { iter =>
val writeTask = new KafkaWriteTask(kafkaParameters, schema, topic)
try {
writeTask.execute(iter)
} finally {
writeTask.close()
}
}
}
```
---
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
