MaxGekk commented on code in PR #44872:
URL: https://github.com/apache/spark/pull/44872#discussion_r1466709296
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala:
##########
@@ -3212,6 +3215,26 @@ abstract class CSVSuite
assert(CSVOptions.getAlternativeOption("codec").contains("compression"))
assert(CSVOptions.getAlternativeOption("preferDate").isEmpty)
}
+
+ test("SPARK-46862: column pruning in the multi-line mode") {
+ val data =
+ """"jobID","Name","City","Active"
+ |"1","DE","","Yes"
+ |"5",",","",","
+ |"3","SA","","No"
+ |"10","abcd""efgh"" \ndef","",""
+ |"8","SE","","No"""".stripMargin
+
+ withTempPath { path =>
+ Files.write(path.toPath, data.getBytes(StandardCharsets.UTF_8))
+ val df = spark.read
+ .option("multiline", "true")
+ .option("header", "true")
+ .option("escape", "\"")
+ .csv(path.getCanonicalPath)
+ assert(df.count() === 5)
Review Comment:
`count()` returns 4 without the changes.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
