Skip to content

[SPARK-32685][SQL] When specify serde, default filed.delim is '\t' #30942

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
AngersZhuuuu wants to merge 4 commits into from
Closed

[SPARK-32685][SQL] When specify serde, default filed.delim is '\t' #30942

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fc1eb28
[SPARK-32685][SQL] When specify serde, default filed.delim is '\t'
AngersZhuuuu Dec 28, 2020
f069204
Add UT
AngersZhuuuu Dec 28, 2020
79e78f3
Update HiveScriptTransformationSuite.scala
AngersZhuuuu Dec 28, 2020
d8282a4
Update SparkSqlParser.scala
AngersZhuuuu Dec 28, 2020
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
7 changes: 6 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/SparkSqlParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -505,7 +505,12 @@ class SparkSqlAstBuilder extends AstBuilder {
} else {
None
}
(Seq.empty, Option(name), props.toSeq, recordHandler)
val finalProps = if (!props.contains("field.delim")) {

@cloud-fan cloud-fan Dec 28, 2020

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

is this case sensitive?

@AngersZhuuuu AngersZhuuuu Dec 28, 2020

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

is this case sensitive?

Yes, case sensitive
image

props.toSeq ++ Seq("field.delim" -> "\t")

@cloud-fan cloud-fan Dec 28, 2020

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

what's the behavior now? which delimiter do we use by default before this PR?

@AngersZhuuuu AngersZhuuuu Dec 28, 2020

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

what's the behavior now? which delimiter do we use by default before this PR?

No default we use '\u0001'

} else {
props.toSeq
}
(Seq.empty, Option(name), finalProps, recordHandler)

case null =>
// Use default (serde) format.
Expand Down
63 changes: 63 additions & 0 deletions ...ve/src/test/scala/org/apache/spark/sql/hive/execution/HiveScriptTransformationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ import org.apache.hadoop.hive.serde2.`lazy`.LazySimpleSerDe
import org.scalatest.exceptions.TestFailedException

import org.apache.spark.{SparkException, TestUtils}
import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, Expression}
import org.apache.spark.sql.execution._
import org.apache.spark.sql.functions._
Expand Down Expand Up @@ -438,4 +439,66 @@ class HiveScriptTransformationSuite extends BaseScriptTransformationSuite with T
assert(e2.contains("array<double> cannot be converted to Hive TypeInfo"))
}
}

test("SPARK-32685: When use specified serde, filed.delim's default value is '\t'") {
val query1 = sql(
"""
|SELECT split(value, "\t") FROM (
|SELECT TRANSFORM(a, b, c)
|USING 'cat'
|FROM (SELECT 1 AS a, 2 AS b, 3 AS c) t
|) temp;
""".stripMargin)
checkAnswer(query1, identity, Row(Seq("2", "3")) :: Nil)

val query2 = sql(
"""
|SELECT split(value, "\t") FROM (
|SELECT TRANSFORM(a, b, c)
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
|USING 'cat'
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
| WITH SERDEPROPERTIES (
| 'serialization.last.column.takes.rest' = 'true'
| )
|FROM (SELECT 1 AS a, 2 AS b, 3 AS c) t
|) temp;
""".stripMargin)
checkAnswer(query2, identity, Row(Seq("2", "3")) :: Nil)

val query3 = sql(
"""
|SELECT split(value, "&") FROM (
|SELECT TRANSFORM(a, b, c)
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
| WITH SERDEPROPERTIES (
| 'field.delim' = '&'
| )
|USING 'cat'
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
| WITH SERDEPROPERTIES (
| 'serialization.last.column.takes.rest' = 'true',
| 'field.delim' = '&'
| )
|FROM (SELECT 1 AS a, 2 AS b, 3 AS c) t
|) temp;
""".stripMargin)
checkAnswer(query3, identity, Row(Seq("2", "3")) :: Nil)

val query4 = sql(
"""
|SELECT split(value, "&") FROM (
|SELECT TRANSFORM(a, b, c)
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
|USING 'cat'
| ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
| WITH SERDEPROPERTIES (
| 'serialization.last.column.takes.rest' = 'true',
| 'field.delim' = '&'
| )
|FROM (SELECT 1 AS a, 2 AS b, 3 AS c) t
|) temp;
""".stripMargin)
checkAnswer(query4, identity, Row(null) :: Nil)
}
}