Skip to content

[SPARK-19919][SQL] Defer throwing the exception for empty paths in CSV datasource into DataSource #17256

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
HyukjinKwon wants to merge 3 commits into from
Closed

[SPARK-19919][SQL] Defer throwing the exception for empty paths in CSV datasource into DataSource #17256

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9d91da1
Defer input path validation into DataSource in CSV datasource
HyukjinKwon Mar 11, 2017
04e620c
Fix test
HyukjinKwon Mar 12, 2017
87d3fc8
Swap names (infer and inferSchema)
HyukjinKwon Mar 13, 2017
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
29 changes: 20 additions & 9 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,10 +54,21 @@ abstract class CSVDataSource extends Serializable {
/**
* Infers the schema from `inputPaths` files.
*/
def infer(
final def infer(
Copy link
Member Author

@HyukjinKwon HyukjinKwon Mar 12, 2017

Choose a reason for hiding this comment

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

This resembles JsonDataSource's one.

sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: CSVOptions): Option[StructType]
parsedOptions: CSVOptions): Option[StructType] = {
if (inputPaths.nonEmpty) {
Some(inferSchema(sparkSession, inputPaths, parsedOptions))
} else {
None
}
}

protected def inferSchema(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: CSVOptions): StructType

/**
* Generates a header from the given row which is null-safe and duplicate-safe.
Expand Down Expand Up @@ -128,13 +139,13 @@ object TextInputCSVDataSource extends CSVDataSource {
UnivocityParser.parseIterator(lines, shouldDropHeader, parser)
}

override def infer(
override def inferSchema(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: CSVOptions): Option[StructType] = {
parsedOptions: CSVOptions): StructType = {
val csv = createBaseDataset(sparkSession, inputPaths, parsedOptions)
val maybeFirstLine = CSVUtils.filterCommentAndEmpty(csv, parsedOptions).take(1).headOption
Some(inferFromDataset(sparkSession, csv, maybeFirstLine, parsedOptions))
inferFromDataset(sparkSession, csv, maybeFirstLine, parsedOptions)
}

/**
Expand Down Expand Up @@ -199,10 +210,10 @@ object WholeFileCSVDataSource extends CSVDataSource {
parser)
}

override def infer(
override def inferSchema(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: CSVOptions): Option[StructType] = {
parsedOptions: CSVOptions): StructType = {
val csv = createBaseRdd(sparkSession, inputPaths, parsedOptions)
csv.flatMap { lines =>
UnivocityParser.tokenizeStream(
Expand All @@ -221,10 +232,10 @@ object WholeFileCSVDataSource extends CSVDataSource {
parsedOptions.headerFlag,
new CsvParser(parsedOptions.asParserSettings))
}
Some(CSVInferSchema.infer(tokenRDD, header, parsedOptions))
CSVInferSchema.infer(tokenRDD, header, parsedOptions)
case None =>
// If the first row could not be read, just return the empty schema.
Some(StructType(Nil))
StructType(Nil)
}
}

Expand Down
2 changes: 0 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,6 @@ class CSVFileFormat extends TextBasedFileFormat with DataSourceRegister {
sparkSession: SparkSession,
options: Map[String, String],
files: Seq[FileStatus]): Option[StructType] = {
require(files.nonEmpty, "Cannot infer schema from an empty set of files")

val parsedOptions =
new CSVOptions(options, sparkSession.sessionState.conf.sessionLocalTimeZone)

Expand Down
6 changes: 4 additions & 2 deletions sql/core/src/test/scala/org/apache/spark/sql/test/DataFrameReaderWriterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,9 +370,11 @@ class DataFrameReaderWriterSuite extends QueryTest with SharedSQLContext with Be
val schema = df.schema

// Reader, without user specified schema
intercept[IllegalArgumentException] {
val message = intercept[AnalysisException] {
testRead(spark.read.csv(), Seq.empty, schema)
}
}.getMessage
assert(message.contains("Unable to infer schema for CSV. It must be specified manually."))

testRead(spark.read.csv(dir), data, schema)
testRead(spark.read.csv(dir, dir), data ++ data, schema)
testRead(spark.read.csv(Seq(dir, dir): _*), data ++ data, schema)
Expand Down