Skip to content

[SPARK-24068][BACKPORT-2.3] Propagating DataFrameReader's options to Text datasource on schema inferring #21292

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 5 commits into from
Closed

[SPARK-24068][BACKPORT-2.3] Propagating DataFrameReader's options to Text datasource on schema inferring #21292

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9092faa
Propagating DataFrameReader's options to the text datasource on schem…
MaxGekk Apr 27, 2018
7b4a6b4
Make textOptions serializable
MaxGekk Apr 28, 2018
fe6c3c2
Adding @transient to textOptions because they shouldn't be serialized
MaxGekk May 5, 2018
831441b
Removing the separate val for textOptions
MaxGekk May 6, 2018
f6ab928
Removing unused imports
MaxGekk May 6, 2018
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 sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/json/JSONOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ import org.apache.spark.sql.catalyst.util._
* Most of these map directly to Jackson's internal options, specified in [[JsonParser.Feature]].
*/
private[sql] class JSONOptions(
@transient private val parameters: CaseInsensitiveMap[String],
@transient val parameters: CaseInsensitiveMap[String],
defaultTimeZoneId: String,
defaultColumnNameOfCorruptRecord: String)
extends Logging with Serializable {
Expand Down
6 changes: 4 additions & 2 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 @@ -184,7 +184,8 @@ object TextInputCSVDataSource extends CSVDataSource {
DataSource.apply(
sparkSession,
paths = paths,
className = classOf[TextFileFormat].getName
className = classOf[TextFileFormat].getName,
options = options.parameters
).resolveRelation(checkFilesExist = false))
.select("value").as[String](Encoders.STRING)
} else {
Expand Down Expand Up @@ -248,7 +249,8 @@ object MultiLineCSVDataSource extends CSVDataSource {
options: CSVOptions): RDD[PortableDataStream] = {
val paths = inputPaths.map(_.getPath)
val name = paths.mkString(",")
val job = Job.getInstance(sparkSession.sessionState.newHadoopConf())
val job = Job.getInstance(sparkSession.sessionState.newHadoopConfWithOptions(
options.parameters))
FileInputFormat.setInputPaths(job, paths: _*)
val conf = job.getConfiguration

Expand Down
2 changes: 1 addition & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ import org.apache.spark.internal.Logging
import org.apache.spark.sql.catalyst.util._

class CSVOptions(
@transient private val parameters: CaseInsensitiveMap[String],
@transient val parameters: CaseInsensitiveMap[String],
defaultTimeZoneId: String,
defaultColumnNameOfCorruptRecord: String)
extends Logging with Serializable {
Expand Down
2 changes: 0 additions & 2 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/UnivocityParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,6 @@ package org.apache.spark.sql.execution.datasources.csv

import java.io.InputStream
import java.math.BigDecimal
import java.text.NumberFormat
import java.util.Locale

import scala.util.Try
import scala.util.control.NonFatal
Expand Down
16 changes: 10 additions & 6 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/json/JsonDataSource.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,7 @@ object TextInputJsonDataSource extends JsonDataSource {
sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: JSONOptions): StructType = {
val json: Dataset[String] = createBaseDataset(sparkSession, inputPaths)
val json: Dataset[String] = createBaseDataset(sparkSession, inputPaths, parsedOptions)
inferFromDataset(json, parsedOptions)
}

Expand All @@ -104,13 +104,15 @@ object TextInputJsonDataSource extends JsonDataSource {

private def createBaseDataset(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus]): Dataset[String] = {
inputPaths: Seq[FileStatus],
parsedOptions: JSONOptions): Dataset[String] = {
val paths = inputPaths.map(_.getPath.toString)
sparkSession.baseRelationToDataFrame(
DataSource.apply(
sparkSession,
paths = paths,
className = classOf[TextFileFormat].getName
className = classOf[TextFileFormat].getName,
options = parsedOptions.parameters
).resolveRelation(checkFilesExist = false))
.select("value").as(Encoders.STRING)
}
Expand Down Expand Up @@ -144,16 +146,18 @@ object MultiLineJsonDataSource extends JsonDataSource {
sparkSession: SparkSession,
inputPaths: Seq[FileStatus],
parsedOptions: JSONOptions): StructType = {
val json: RDD[PortableDataStream] = createBaseRdd(sparkSession, inputPaths)
val json: RDD[PortableDataStream] = createBaseRdd(sparkSession, inputPaths, parsedOptions)
val sampled: RDD[PortableDataStream] = JsonUtils.sample(json, parsedOptions)
JsonInferSchema.infer(sampled, parsedOptions, createParser)
}

private def createBaseRdd(
sparkSession: SparkSession,
inputPaths: Seq[FileStatus]): RDD[PortableDataStream] = {
inputPaths: Seq[FileStatus],
parsedOptions: JSONOptions): RDD[PortableDataStream] = {
val paths = inputPaths.map(_.getPath)
val job = Job.getInstance(sparkSession.sessionState.newHadoopConf())
val job = Job.getInstance(sparkSession.sessionState.newHadoopConfWithOptions(
parsedOptions.parameters))
val conf = job.getConfiguration
val name = paths.mkString(",")
FileInputFormat.setInputPaths(job, paths: _*)
Expand Down