This is an automated email from the ASF dual-hosted git repository.
cloud-fan 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 4b38f9c84833 [SPARK-58193][SQL] Classify Databricks syntax errors by
message
4b38f9c84833 is described below
commit 4b38f9c84833a90995ca67ab8fd1e7cf9a5bf9a6
Author: Alek Jarmov <[email protected]>
AuthorDate: Mon Jul 20 22:18:18 2026 +0800
[SPARK-58193][SQL] Classify Databricks syntax errors by message
### What changes were proposed in this pull request?
Recognize remote Databricks parse errors when the JDBC driver reports the
SYNTAX_ERROR condition only in its message.
Optimise `isSyntaxErrorBestEffort` for Databricks to catch syntax error
even if SQLState is missing.
### Why are the changes needed?
To improve the error classification.
### Does this PR introduce _any_ user-facing change?
Update the user-facing-change section from No: matching this driver error
now produces Spark's JDBC_EXTERNAL_ENGINE_SYNTAX_ERROR classification during
schema resolution or query execution.
### How was this patch tested?
Added a unit-test and checked a case on a Databricks workspace
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Claude 4.7
Closes #57333 from alekjarmov/alekjarmov/classify-databricks-syntax-errors.
Authored-by: Alek Jarmov <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>
---
.../main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala | 7 +++++--
.../src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala | 9 ++++++++-
2 files changed, 13 insertions(+), 3 deletions(-)
diff --git
a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala
b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala
index a56aa90d6d72..0c606ce71f91 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/jdbc/DatabricksDialect.scala
@@ -55,9 +55,12 @@ private case class DatabricksDialect() extends JdbcDialect
with NoLegacyJDBCErro
case _ => None
}
- // See https://docs.databricks.com/aws/en/error-messages/sqlstates
+ // See https://docs.databricks.com/aws/en/error-messages/sqlstates.
+ // The driver may report syntax errors with a non-class-42 SQLState.
override def isSyntaxErrorBestEffort(exception: SQLException): Boolean = {
- Option(exception.getSQLState).exists(_.startsWith("42"))
+ Option(exception.getSQLState).exists(_.startsWith("42")) ||
+ Option(exception.getMessage)
+ .exists(_.toUpperCase(Locale.ROOT).contains("SYNTAX_ERROR"))
}
override def quoteIdentifier(colName: String): String = {
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 58797e68b8ab..de863b244be8 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
@@ -18,7 +18,7 @@
package org.apache.spark.sql.jdbc
import java.math.BigDecimal
-import java.sql.{Connection, Date, DriverManager, ResultSet, Statement,
Timestamp}
+import java.sql.{Connection, Date, DriverManager, ResultSet, SQLException,
Statement, Timestamp}
import java.time.{Instant, LocalDate, LocalDateTime}
import java.time.format.DateTimeFormatter
import java.util.{Calendar, GregorianCalendar, Properties, TimeZone}
@@ -2608,6 +2608,13 @@ class JDBCSuite extends SharedSparkSession {
.getJDBCType(BinaryType).map(_.databaseTypeDefinition).get == "BINARY")
}
+ test("SPARK-58193: DatabricksDialect syntax error detection") {
+ val dialect = DatabricksDialect()
+ assert(dialect.isSyntaxErrorBestEffort(
+ new SQLException("[parse_syntax_error] Syntax error at or near 'SQL'",
"07000")))
+ assert(!dialect.isSyntaxErrorBestEffort(new SQLException("Connection
reset", "08001")))
+ }
+
test("SPARK-45425: Mapped TINYINT to ShortType for MsSqlServerDialect") {
val msSqlServerDialect = JdbcDialects.get("jdbc:sqlserver")
val metadata = new MetadataBuilder().putLong("scale", 1)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
