Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/17255#discussion_r105597144 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala --- @@ -17,32 +17,30 @@ package org.apache.spark.sql.execution.datasources.json -import scala.reflect.ClassTag - import com.fasterxml.jackson.core.{JsonFactory, JsonParser} import com.google.common.io.ByteStreams import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.FileStatus -import org.apache.hadoop.io.{LongWritable, Text} +import org.apache.hadoop.io.Text import org.apache.hadoop.mapreduce.Job -import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat, TextInputFormat} +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat import org.apache.spark.TaskContext import org.apache.spark.input.{PortableDataStream, StreamInputFormat} import org.apache.spark.rdd.{BinaryFileRDD, RDD} -import org.apache.spark.sql.{AnalysisException, SparkSession} +import org.apache.spark.sql.{AnalysisException, Dataset, Encoders, SparkSession} import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.json.{CreateJacksonParser, JacksonParser, JSONOptions} -import org.apache.spark.sql.execution.datasources.{CodecStreams, HadoopFileLinesReader, PartitionedFile} +import org.apache.spark.sql.execution.datasources.{CodecStreams, DataSource, HadoopFileLinesReader, PartitionedFile} +import org.apache.spark.sql.execution.datasources.text.TextFileFormat import org.apache.spark.sql.types.StructType import org.apache.spark.unsafe.types.UTF8String import org.apache.spark.util.Utils /** * Common functions for parsing JSON files - * @tparam T A datatype containing the unparsed JSON, such as [[Text]] or [[String]] */ -abstract class JsonDataSource[T] extends Serializable { +abstract class JsonDataSource extends Serializable { --- End diff -- The changes in this file basically resembles `CSVDataSource`. (Note that this is almost identical if https://github.com/apache/spark/pull/17256 is merged).
--- 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