This is an automated email from the ASF dual-hosted git repository.
yao pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 6afa6cc3c16e [SPARK-48399][SQL] Teradata: ByteType should map to
BYTEINT instead of BYTE(binary)
6afa6cc3c16e is described below
commit 6afa6cc3c16e21f94087ebb6adb01bd1ff397086
Author: Kent Yao <y...@apache.org>
AuthorDate: Fri May 24 10:13:49 2024 +0800
[SPARK-48399][SQL] Teradata: ByteType should map to BYTEINT instead of
BYTE(binary)
### What changes were proposed in this pull request?
According to the doc of Teradata and Teradata jdbc, BYTE represents binary
type in Teradata, while BYTEINT is used for tinyint.
-
https://docs.teradata.com/r/Enterprise_IntelliFlex_VMware/SQL-Data-Types-and-Literals/Numeric-Data-Types/BYTEINT-Data-Type
-
https://teradata-docs.s3.amazonaws.com/doc/connectivity/jdbc/reference/current/frameset.html
### Why are the changes needed?
Bugfix
### Does this PR introduce _any_ user-facing change?
Yes, ByteType used to be stored as binary type in Teradata, now it has
become BYTEINT.
(The use-case seems rare, the migration guide or legacy config are pending
reviewer's comments)
### How was this patch tested?
new tests
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #46715 from yaooqinn/SPARK-48399.
Authored-by: Kent Yao <y...@apache.org>
Signed-off-by: Kent Yao <y...@apache.org>
---
.../scala/org/apache/spark/sql/jdbc/TeradataDialect.scala | 1 +
.../test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala | 15 +++++----------
2 files changed, 6 insertions(+), 10 deletions(-)
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/TeradataDialect.scala
b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/TeradataDialect.scala
index 7acd22a3f10b..95a9f60b64ed 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/TeradataDialect.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/TeradataDialect.scala
@@ -42,6 +42,7 @@ private case class TeradataDialect() extends JdbcDialect {
override def getJDBCType(dt: DataType): Option[JdbcType] = dt match {
case StringType => Some(JdbcType("VARCHAR(255)", java.sql.Types.VARCHAR))
case BooleanType => Option(JdbcType("CHAR(1)", java.sql.Types.CHAR))
+ case ByteType => Option(JdbcType("BYTEINT", java.sql.Types.TINYINT))
case _ => None
}
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
index 0a792f44d3e2..e4116b565818 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
@@ -1477,16 +1477,11 @@ class JDBCSuite extends QueryTest with
SharedSparkSession {
}
}
- test("SPARK-15648: teradataDialect StringType data mapping") {
- val teradataDialect = JdbcDialects.get("jdbc:teradata://127.0.0.1/db")
- assert(teradataDialect.getJDBCType(StringType).
- map(_.databaseTypeDefinition).get == "VARCHAR(255)")
- }
-
- test("SPARK-15648: teradataDialect BooleanType data mapping") {
- val teradataDialect = JdbcDialects.get("jdbc:teradata://127.0.0.1/db")
- assert(teradataDialect.getJDBCType(BooleanType).
- map(_.databaseTypeDefinition).get == "CHAR(1)")
+ test("SPARK-48399: TeradataDialect jdbc data mapping") {
+ val dialect = JdbcDialects.get("jdbc:teradata://127.0.0.1/db")
+ assert(dialect.getJDBCType(StringType).map(_.databaseTypeDefinition).get
== "VARCHAR(255)")
+ assert(dialect.getJDBCType(BooleanType).map(_.databaseTypeDefinition).get
== "CHAR(1)")
+ assert(dialect.getJDBCType(ByteType).map(_.databaseTypeDefinition).get ==
"BYTEINT")
}
test("SPARK-38846: TeradataDialect catalyst type mapping") {
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
