Skip to content

[SPARK-15264][SPARK-15274][SQL] CSV Reader Error on Blank Column Names #13041

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 6 commits into from
Closed

[SPARK-15264][SPARK-15274][SQL] CSV Reader Error on Blank Column Names #13041

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
17b3c58
fix SPARK-15264, add test cases
May 11, 2016
85d0843
Rename test case
bllchmbrs May 11, 2016
0ed0b4c
Fix according to @andrewor14 comments, rename C0 to _c0, fix null checks
May 11, 2016
e380f32
Merge branch 'master' of github.com:anabranch/spark
May 11, 2016
d665bea
fix tests
May 11, 2016
d983718
fix python test failure
May 11, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion python/pyspark/sql/readwriter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,7 @@ def csv(self, path, schema=None, sep=None, encoding=None, quote=None, escape=Non

>>> df = sqlContext.read.csv('python/test_support/sql/ages.csv')
>>> df.dtypes
[('C0', 'string'), ('C1', 'string')]
[('_c0', 'string'), ('_c1', 'string')]
"""
if schema is not None:
self.schema(schema)
Expand Down
6 changes: 4 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/DefaultSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,9 +61,11 @@ class DefaultSource extends FileFormat with DataSourceRegister {
val firstRow = new LineCsvReader(csvOptions).parseLine(firstLine)

val header = if (csvOptions.headerFlag) {
firstRow
firstRow.zipWithIndex.map { case (value, index) =>
if (value == null || value.isEmpty || value == csvOptions.nullValue) s"_c$index" else value
}
} else {
firstRow.zipWithIndex.map { case (value, index) => s"C$index" }
firstRow.zipWithIndex.map { case (value, index) => s"_c$index" }
Copy link
Member

@HyukjinKwon HyukjinKwon May 11, 2016 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why should this be _c?

Copy link
Contributor

@andrewor14 andrewor14 May 11, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

to be consistent with what Spark does with unnamed columns. See my comment above.

Copy link
Member

@HyukjinKwon HyukjinKwon May 11, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I see. Thanks.

}

val parsedRdd = tokenRdd(sparkSession, csvOptions, header, paths)
Expand Down
3 changes: 3 additions & 0 deletions sql/core/src/test/resources/cars-blank-column-name.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
"",,make,customer,comment
2012,"Tesla","S","bill","blank"
2013,"Tesla","S","c","something"
16 changes: 14 additions & 2 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
private val carsAltFile = "cars-alternative.csv"
private val carsUnbalancedQuotesFile = "cars-unbalanced-quotes.csv"
private val carsNullFile = "cars-null.csv"
private val carsBlankColName = "cars-blank-column-name.csv"
private val emptyFile = "empty.csv"
private val commentsFile = "comments.csv"
private val disableCommentsFile = "disable_comments.csv"
Expand Down Expand Up @@ -71,14 +72,14 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
if (withHeader) {
assert(df.schema.fieldNames === Array("year", "make", "model", "comment", "blank"))
} else {
assert(df.schema.fieldNames === Array("C0", "C1", "C2", "C3", "C4"))
assert(df.schema.fieldNames === Array("_c0", "_c1", "_c2", "_c3", "_c4"))
}
}

if (checkValues) {
val yearValues = List("2012", "1997", "2015")
val actualYears = if (!withHeader) "year" :: yearValues else yearValues
val years = if (withHeader) df.select("year").collect() else df.select("C0").collect()
val years = if (withHeader) df.select("year").collect() else df.select("_c0").collect()

years.zipWithIndex.foreach { case (year, index) =>
if (checkTypes) {
Expand Down Expand Up @@ -224,6 +225,17 @@ class CSVSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
assert(cars.select("year").collect().size === 2)
}

test("test for blank column names on read and select columns") {
val cars = spark.read
.format("csv")
.options(Map("header" -> "true", "inferSchema" -> "true"))
.load(testFile(carsBlankColName))

assert(cars.select("customer").collect().size == 2)
assert(cars.select("_c0").collect().size == 2)
assert(cars.select("_c1").collect().size == 2)
}

test("test for FAILFAST parsing mode") {
val exception = intercept[SparkException]{
spark.read
Expand Down