Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/20096#discussion_r160004815
--- Diff:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaContinuousReader.scala
---
@@ -0,0 +1,224 @@
+/*
+ * 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 org.apache.kafka.clients.consumer.ConsumerRecord
+import org.apache.kafka.common.TopicPartition
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.SparkSession
+import org.apache.spark.sql.catalyst.expressions.UnsafeRow
+import org.apache.spark.sql.catalyst.expressions.codegen.{BufferHolder,
UnsafeRowWriter}
+import org.apache.spark.sql.catalyst.util.DateTimeUtils
+import
org.apache.spark.sql.kafka010.KafkaSource.{INSTRUCTION_FOR_FAIL_ON_DATA_LOSS_FALSE,
INSTRUCTION_FOR_FAIL_ON_DATA_LOSS_TRUE}
+import org.apache.spark.sql.sources.v2.reader._
+import
org.apache.spark.sql.sources.v2.streaming.reader.{ContinuousDataReader,
ContinuousReader, Offset, PartitionOffset}
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.unsafe.types.UTF8String
+
+/**
+ * A [[ContinuousReader]] for data from kafka.
+ *
+ * @param offsetReader a reader used to get kafka offsets. Note that the
actual data will be
+ * read by per-task consumers generated later.
+ * @param kafkaParams String params for per-task Kafka consumers.
+ * @param sourceOptions The
[[org.apache.spark.sql.sources.v2.DataSourceV2Options]] params which
+ * are not Kafka consumer params.
+ * @param metadataPath Path to a directory this reader can use for writing
metadata.
+ * @param initialOffsets The Kafka offsets to start reading data at.
+ * @param failOnDataLoss Flag indicating whether reading should fail in
data loss
+ * scenarios, where some offsets after the specified
initial ones can't be
+ * properly read.
+ */
+class KafkaContinuousReader(
+ offsetReader: KafkaOffsetReader,
+ kafkaParams: java.util.Map[String, Object],
--- End diff --
Since there are lots of different uses of java.util.* ... you can probably
rename java.util to ju. Thats what the file KafkaSourceProvider class does.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
