spark-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From r...@apache.org
Subject spark git commit: [SPARK-13137][SQL] NullPoingException in schema inference for CSV when the first line is empty
Date Sun, 21 Feb 2016 21:22:01 GMT
Repository: spark
Updated Branches:
  refs/heads/master b6a873d6d -> 7eb83fefd


[SPARK-13137][SQL] NullPoingException in schema inference for CSV when the first line is empty

https://issues.apache.org/jira/browse/SPARK-13137

This PR adds a filter in schema inference so that it does not emit NullPointException.

Also, I removed `MAX_COMMENT_LINES_IN_HEADER `but instead used a monad chaining with `filter()`
and `first()`.

Lastly, I simply added a newline rather than adding a new file for this so that this is covered
with the original tests.

Author: hyukjinkwon <gurwls223@gmail.com>

Closes #11023 from HyukjinKwon/SPARK-13137.


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/7eb83fef
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/7eb83fef
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/7eb83fef

Branch: refs/heads/master
Commit: 7eb83fefd19e137d80a23b5174b66b14831c291a
Parents: b6a873d
Author: hyukjinkwon <gurwls223@gmail.com>
Authored: Sun Feb 21 13:21:59 2016 -0800
Committer: Reynold Xin <rxin@databricks.com>
Committed: Sun Feb 21 13:21:59 2016 -0800

----------------------------------------------------------------------
 .../sql/execution/datasources/csv/CSVOptions.scala      |  3 ---
 .../sql/execution/datasources/csv/CSVRelation.scala     | 12 +++++++-----
 sql/core/src/test/resources/cars.csv                    |  1 +
 3 files changed, 8 insertions(+), 8 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/7eb83fef/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
----------------------------------------------------------------------
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
index bea8e97..38aa2dd 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
@@ -75,9 +75,6 @@ private[sql] class CSVOptions(
   val ignoreLeadingWhiteSpaceFlag = getBool("ignoreLeadingWhiteSpace")
   val ignoreTrailingWhiteSpaceFlag = getBool("ignoreTrailingWhiteSpace")
 
-  // Limit the number of lines we'll search for a header row that isn't comment-prefixed
-  val MAX_COMMENT_LINES_IN_HEADER = 10
-
   // Parse mode flags
   if (!ParseModes.isValidMode(parseMode)) {
     logWarning(s"$parseMode is not a valid parse mode. Using ${ParseModes.DEFAULT}.")

http://git-wip-us.apache.org/repos/asf/spark/blob/7eb83fef/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
----------------------------------------------------------------------
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
index f8e3a1b..471ed0d 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVRelation.scala
@@ -154,12 +154,14 @@ private[csv] class CSVRelation(
     */
   private def findFirstLine(rdd: RDD[String]): String = {
     if (params.isCommentSet) {
-      rdd.take(params.MAX_COMMENT_LINES_IN_HEADER)
-        .find(!_.startsWith(params.comment.toString))
-        .getOrElse(sys.error(s"No uncommented header line in " +
-          s"first ${params.MAX_COMMENT_LINES_IN_HEADER} lines"))
+      val comment = params.comment.toString
+      rdd.filter { line =>
+        line.trim.nonEmpty && !line.startsWith(comment)
+      }.first()
     } else {
-      rdd.first()
+      rdd.filter { line =>
+        line.trim.nonEmpty
+      }.first()
     }
   }
 }

http://git-wip-us.apache.org/repos/asf/spark/blob/7eb83fef/sql/core/src/test/resources/cars.csv
----------------------------------------------------------------------
diff --git a/sql/core/src/test/resources/cars.csv b/sql/core/src/test/resources/cars.csv
index 2b9d74c..40ded57 100644
--- a/sql/core/src/test/resources/cars.csv
+++ b/sql/core/src/test/resources/cars.csv
@@ -1,3 +1,4 @@
+
 year,make,model,comment,blank
 "2012","Tesla","S","No comment",
 


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org


Mime
View raw message