Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20937#discussion_r183227276
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala
---
@@ -175,11 +187,15 @@ object MultiLineJsonDataSource extends JsonDataSource
{
.values
}
- private def createParser(jsonFactory: JsonFactory, record:
PortableDataStream): JsonParser = {
+ private def createParser(
+ jsonFactory: JsonFactory,
+ record: PortableDataStream,
+ encoding: Option[String]): JsonParser = {
val path = new Path(record.getPath())
- CreateJacksonParser.inputStream(
- jsonFactory,
-
CodecStreams.createInputStreamWithCloseResource(record.getConfiguration, path))
+ val is =
CodecStreams.createInputStreamWithCloseResource(record.getConfiguration, path)
+
+ encoding.map(enc => CreateJacksonParser.inputStream(enc, jsonFactory,
is))
+ .getOrElse(CreateJacksonParser.inputStream(jsonFactory, is))
--- End diff --
Hm, @MaxGekk, wouldn't this also do a record per operation too?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
