Skip to content

[SPARK-37575][SQL][FOLLOWUP] Add legacy flag for the breaking change of write null value in csv to unquoted empty string #36110

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
anchovYu wants to merge 3 commits into from
Closed

[SPARK-37575][SQL][FOLLOWUP] Add legacy flag for the breaking change of write null value in csv to unquoted empty string #36110

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1b03262
add flag and tests for the breaking change
anchovYu Apr 7, 2022
c9d210c
Merge remote-tracking branch 'apache/master' into flags-null-to-csv
anchovYu Apr 14, 2022
21dc0ed
update conf name
anchovYu Apr 14, 2022
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
4 changes: 4 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/UnivocityGenerator.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ import com.univocity.parsers.csv.CsvWriter
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.util.{DateFormatter, DateTimeUtils, IntervalStringStyles, IntervalUtils, TimestampFormatter}
import org.apache.spark.sql.catalyst.util.LegacyDateFormats.FAST_DATE_FORMAT
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types._

class UnivocityGenerator(
Expand Down Expand Up @@ -95,6 +96,9 @@ class UnivocityGenerator(
while (i < row.numFields) {
if (!row.isNullAt(i)) {
values(i) = valueConverters(i).apply(row, i)
} else if (
SQLConf.get.getConf(SQLConf.LEGACY_NULL_VALUE_WRITTEN_AS_QUOTED_EMPTY_STRING_CSV)) {
values(i) = options.nullValue
}
i += 1
}
Expand Down
10 changes: 10 additions & 0 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3754,6 +3754,16 @@ object SQLConf {
.booleanConf
.createWithDefault(false)

val LEGACY_NULL_VALUE_WRITTEN_AS_QUOTED_EMPTY_STRING_CSV =
buildConf("spark.sql.legacy.nullValueWrittenAsQuotedEmptyStringCsv")
.internal()
.doc("When set to false, nulls are written as unquoted empty strings in CSV data source. " +
"If set to false, it restores the legacy behavior that nulls were written as quoted " +
"empty strings, `\"\"`.")
.version("3.3.0")
.booleanConf
.createWithDefault(false)

/**
* Holds information about keys that have been deprecated.
*
Expand Down
20 changes: 14 additions & 6 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 @@ -807,12 +807,20 @@ abstract class CSVSuite

test("SPARK-37575: null values should be saved as nothing rather than " +
"quoted empty Strings \"\" with default settings") {
withTempPath { path =>
Seq(("Tesla", null: String, ""))
.toDF("make", "comment", "blank")
.write
.csv(path.getCanonicalPath)
checkAnswer(spark.read.text(path.getCanonicalPath), Row("Tesla,,\"\""))
Seq("true", "false").foreach { confVal =>
withSQLConf(SQLConf.LEGACY_NULL_VALUE_WRITTEN_AS_QUOTED_EMPTY_STRING_CSV.key -> confVal) {
withTempPath { path =>
Seq(("Tesla", null: String, ""))
.toDF("make", "comment", "blank")
.write
.csv(path.getCanonicalPath)
if (confVal == "false") {
checkAnswer(spark.read.text(path.getCanonicalPath), Row("Tesla,,\"\""))
} else {
checkAnswer(spark.read.text(path.getCanonicalPath), Row("Tesla,\"\",\"\""))
}
}
}
}
}

Expand Down