Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/16976#discussion_r102681341
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
---
@@ -958,4 +975,77 @@ class CSVSuite extends QueryTest with SharedSQLContext
with SQLTestUtils {
checkAnswer(df, Row(1, null))
}
}
+
+ test("SPARK-19610: Parse normal multi-line CSV files") {
+ val primitiveFieldAndType = Seq(
+ """"
+ |string","integer
+ |
+ |
+ |","long
+ |
+ |","bigInteger",double,boolean,null""".stripMargin,
+ """"this is a
+ |simple
+ |string.","
+ |
+ |10","
+ |21474836470","92233720368547758070","
+ |
+ |1.7976931348623157E308",true,""".stripMargin)
+
+ withTempPath { path =>
+
primitiveFieldAndType.toDF("value").coalesce(1).write.text(path.getAbsolutePath)
+
+ val df = spark.read
+ .option("header", true)
+ .option("wholeFile", true)
+ .csv(path.getAbsolutePath)
+
+ // Check if headers have new lines in the names.
+ val actualFields = df.schema.fieldNames.toSeq
+ val expectedFields =
+ Seq("\nstring", "integer\n\n\n", "long\n\n", "bigInteger",
"double", "boolean", "null")
--- End diff --
Default quote is `"`. This behaviour is definately with original CSV.
```scala
scala> Seq("\"1\"").toDF.write.text("/tmp/abc")
scala> spark.read.csv("/tmp/abc").show()
+---+
|_c0|
+---+
| 1|
+---+
```
---
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
