maropu commented on a change in pull request #23665: [SPARK-26745][SQL] Skip
empty lines in JSON-derived DataFrames when skipParsing optimization in effect
URL: https://github.com/apache/spark/pull/23665#discussion_r251271052
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/json/JsonSuite.scala
##########
@@ -2426,6 +2426,23 @@ class JsonSuite extends QueryTest with SharedSQLContext
with TestJsonData {
countForMalformedJSON(0, Seq(""))
}
+ test("count() for non-multiline input with empty lines") {
+ val withEmptyLineData = Array(Map("a" -> 1, "b" -> 2, "c" -> 3),
+ Map("a" -> 4, "b" -> 5, "c" -> 6),
+ Map("a" -> 7, "b" -> 8, "c" -> 9))
+ val df =
spark.read.json("src/test/resources/test-data/with-empty-line.json")
Review comment:
plz use `testFile`.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
