This is an automated email from the ASF dual-hosted git repository.
LuciferYang pushed a commit to branch branch-4.x
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.x by this push:
new 041867bc797d [SPARK-58283][SQL] Assign names to the error conditions
_LEGACY_ERROR_TEMP_1138-1141
041867bc797d is described below
commit 041867bc797d4424acfb6d8ba6d2a6ad94090a78
Author: YangJie <[email protected]>
AuthorDate: Fri Jul 24 10:36:25 2026 +0800
[SPARK-58283][SQL] Assign names to the error conditions
_LEGACY_ERROR_TEMP_1138-1141
### What changes were proposed in this pull request?
Resolve four legacy error conditions raised while resolving a data source
provider in `DataSource.lookupDataSource`, converting them to proper top-level
names in `error-conditions.json`:
- `_LEGACY_ERROR_TEMP_1138` → `ORC_DATA_SOURCE_REQUIRES_HIVE_SUPPORT`
(`0A000`)
- `_LEGACY_ERROR_TEMP_1139` → `AVRO_DATA_SOURCE_NOT_ENABLED` (`42K02`)
- `_LEGACY_ERROR_TEMP_1140` → `KAFKA_DATA_SOURCE_NOT_ENABLED` (`42K02`)
- `_LEGACY_ERROR_TEMP_1141` → `MULTIPLE_DATA_SOURCES` (`42710`)
The message text is preserved verbatim from the legacy entries.
### Why are the changes needed?
The error-conditions README disallows new `_LEGACY_ERROR_TEMP_*` entries
and asks existing ones to be resolved. This resolves four of them.
They are kept as top-level names rather than folded into the existing
`DATA_SOURCE_NOT_FOUND` / `MULTIPLE_XML_DATA_SOURCE`: the Avro/Kafka errors are
`AnalysisException`s (not the `SparkClassNotFoundException` of
`DATA_SOURCE_NOT_FOUND`) and carry module-specific deployment guidance, and the
multiple-sources error mirrors the existing XML-specific
`MULTIPLE_XML_DATA_SOURCE` but for the generic provider path.
### Does this PR introduce _any_ user-facing change?
No. Only the error condition names are assigned; the message text is
unchanged. The `_LEGACY_ERROR_TEMP_*` names are not part of the public API.
### How was this patch tested?
Updated the existing `checkError` assertions to the new condition names in
`SQLQuerySuite`, `DDLSuite`, `ResolvedDataSourceSuite`, and
`DDLSourceLoadSuite`. `build/sbt "sql/testOnly *ResolvedDataSourceSuite
*DDLSourceLoadSuite *SQLQuerySuite *InMemoryCatalogedDDLSuite" "core/testOnly
org.apache.spark.SparkThrowableSuite"` passes.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Claude Code (Opus 4.8)
Closes #57456 from LuciferYang/assign-name-legacy-1138-1141.
Authored-by: YangJie <[email protected]>
Signed-off-by: yangjie01 <[email protected]>
(cherry picked from commit 9ce65b275b690cd53b2613537dc004b757b23318)
Signed-off-by: yangjie01 <[email protected]>
---
.../src/main/resources/error/error-conditions.json | 44 ++++++++++++----------
.../spark/sql/errors/QueryCompilationErrors.scala | 8 ++--
.../scala/org/apache/spark/sql/SQLQuerySuite.scala | 2 +-
.../spark/sql/execution/command/DDLSuite.scala | 2 +-
.../spark/sql/sources/DDLSourceLoadSuite.scala | 4 +-
.../sql/sources/ResolvedDataSourceSuite.scala | 4 +-
6 files changed, 34 insertions(+), 30 deletions(-)
diff --git a/common/utils/src/main/resources/error/error-conditions.json
b/common/utils/src/main/resources/error/error-conditions.json
index 0ec3f4d76ed7..0f18ffdb5a46 100644
--- a/common/utils/src/main/resources/error/error-conditions.json
+++ b/common/utils/src/main/resources/error/error-conditions.json
@@ -362,6 +362,12 @@
],
"sqlState" : "22004"
},
+ "AVRO_DATA_SOURCE_NOT_ENABLED" : {
+ "message" : [
+ "Failed to find data source: <provider>. Avro is built-in but external
data source module since Spark 2.4. Please deploy the application as per the
deployment section of Apache Avro Data Source Guide."
+ ],
+ "sqlState" : "42K02"
+ },
"AVRO_INCOMPATIBLE_READ_TYPE" : {
"message" : [
"Cannot convert Avro <avroPath> to SQL <sqlPath> because the original
encoded data type is <avroType>, however you're trying to read the field as
<sqlType>, which would lead to an incorrect answer.",
@@ -5432,6 +5438,12 @@
],
"sqlState" : "42K0E"
},
+ "KAFKA_DATA_SOURCE_NOT_ENABLED" : {
+ "message" : [
+ "Failed to find data source: <provider>. Please deploy the application
as per the deployment section of Structured Streaming + Kafka Integration
Guide."
+ ],
+ "sqlState" : "42K02"
+ },
"KLL_INVALID_INPUT_SKETCH_BUFFER" : {
"message" : [
"Invalid call to <function>; only valid KLL sketch buffers are supported
as inputs (such as those produced by the `kll_sketch_agg` function)."
@@ -5724,6 +5736,12 @@
],
"sqlState" : "0A000"
},
+ "MULTIPLE_DATA_SOURCES" : {
+ "message" : [
+ "Multiple sources found for <provider> (<sourceNames>), please specify
the fully qualified class name."
+ ],
+ "sqlState" : "42710"
+ },
"MULTIPLE_EVENT_TIME_COLUMNS" : {
"message" : [
"More than one event time columns are available. Please ensure there is
at most one event time column per stream. event time columns: <eventTimeCols>"
@@ -6196,6 +6214,12 @@
],
"sqlState" : "22023"
},
+ "ORC_DATA_SOURCE_REQUIRES_HIVE_SUPPORT" : {
+ "message" : [
+ "Hive built-in ORC data source must be used with Hive support enabled.
Please use the native ORC data source by setting 'spark.sql.orc.impl' to
'native'."
+ ],
+ "sqlState" : "0A000"
+ },
"ORDER_BY_POS_OUT_OF_RANGE" : {
"message" : [
"ORDER BY position <index> is not in select list (valid range is [1,
<size>])."
@@ -9840,26 +9864,6 @@
"Unable to resolve <name> given [<outputStr>]."
]
},
- "_LEGACY_ERROR_TEMP_1138" : {
- "message" : [
- "Hive built-in ORC data source must be used with Hive support enabled.
Please use the native ORC data source by setting 'spark.sql.orc.impl' to
'native'."
- ]
- },
- "_LEGACY_ERROR_TEMP_1139" : {
- "message" : [
- "Failed to find data source: <provider>. Avro is built-in but external
data source module since Spark 2.4. Please deploy the application as per the
deployment section of Apache Avro Data Source Guide."
- ]
- },
- "_LEGACY_ERROR_TEMP_1140" : {
- "message" : [
- "Failed to find data source: <provider>. Please deploy the application
as per the deployment section of Structured Streaming + Kafka Integration
Guide."
- ]
- },
- "_LEGACY_ERROR_TEMP_1141" : {
- "message" : [
- "Multiple sources found for <provider> (<sourceNames>), please specify
the fully qualified class name."
- ]
- },
"_LEGACY_ERROR_TEMP_1143" : {
"message" : [
"The data to be inserted needs to have the same number of columns as the
target table: target table has <targetSize> column(s) but the inserted data has
<actualSize> column(s), which contain <staticPartitionsSize> partition
column(s) having assigned constant values."
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
index 5f0f23b6de55..2065c0c2e605 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
@@ -1970,19 +1970,19 @@ private[sql] object QueryCompilationErrors extends
QueryErrorsBase with Compilat
def orcNotUsedWithHiveEnabledError(): Throwable = {
new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_1138",
+ errorClass = "ORC_DATA_SOURCE_REQUIRES_HIVE_SUPPORT",
messageParameters = Map.empty)
}
def failedToFindAvroDataSourceError(provider: String): Throwable = {
new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_1139",
+ errorClass = "AVRO_DATA_SOURCE_NOT_ENABLED",
messageParameters = Map("provider" -> provider))
}
def failedToFindKafkaDataSourceError(provider: String): Throwable = {
new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_1140",
+ errorClass = "KAFKA_DATA_SOURCE_NOT_ENABLED",
messageParameters = Map("provider" -> provider))
}
@@ -1996,7 +1996,7 @@ private[sql] object QueryCompilationErrors extends
QueryErrorsBase with Compilat
def findMultipleDataSourceError(provider: String, sourceNames: Seq[String]):
Throwable = {
new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_1141",
+ errorClass = "MULTIPLE_DATA_SOURCES",
messageParameters = Map(
"provider" -> provider,
"sourceNames" -> sourceNames.mkString(", ")))
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
index d7908279deb5..03d3a122da16 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -1676,7 +1676,7 @@ class SQLQuerySuite extends SharedSparkSession with
AdaptiveSparkPlanHelper
exception = intercept[AnalysisException] {
sql(s"select id from `org.apache.spark.sql.hive.orc`.`file_path`")
},
- condition = "_LEGACY_ERROR_TEMP_1138"
+ condition = "ORC_DATA_SOURCE_REQUIRES_HIVE_SUPPORT"
)
e = intercept[AnalysisException] {
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
index b9daebb60e4e..a52baaeac42b 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/execution/command/DDLSuite.scala
@@ -196,7 +196,7 @@ class InMemoryCatalogedDDLSuite extends DDLSuite with
SharedSparkSession {
exception = intercept[AnalysisException] {
sql("CREATE TABLE t LIKE s USING org.apache.spark.sql.hive.orc")
},
- condition = "_LEGACY_ERROR_TEMP_1138",
+ condition = "ORC_DATA_SOURCE_REQUIRES_HIVE_SUPPORT",
parameters = Map.empty
)
}
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLSourceLoadSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLSourceLoadSuite.scala
index 43dfed277cbe..89e17c2c8e22 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLSourceLoadSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/sources/DDLSourceLoadSuite.scala
@@ -30,7 +30,7 @@ class DDLSourceLoadSuite extends DataSourceTest with
SharedSparkSession {
exception = intercept[AnalysisException] {
spark.read.format("Fluet da Bomb").load()
},
- condition = "_LEGACY_ERROR_TEMP_1141",
+ condition = "MULTIPLE_DATA_SOURCES",
parameters = Map(
"provider" -> "Fluet da Bomb",
"sourceNames" -> ("org.apache.spark.sql.sources.FakeSourceOne, " +
@@ -49,7 +49,7 @@ class DDLSourceLoadSuite extends DataSourceTest with
SharedSparkSession {
exception = intercept[AnalysisException] {
spark.read.format("Fake external source").load()
},
- condition = "_LEGACY_ERROR_TEMP_1141",
+ condition = "MULTIPLE_DATA_SOURCES",
parameters = Map(
"provider" -> "Fake external source",
"sourceNames" -> ("org.apache.fakesource.FakeExternalSourceOne, " +
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/sources/ResolvedDataSourceSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/sources/ResolvedDataSourceSuite.scala
index ee40d70c8829..ab42fc1ddb2f 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/sources/ResolvedDataSourceSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/sources/ResolvedDataSourceSuite.scala
@@ -84,7 +84,7 @@ class ResolvedDataSourceSuite extends SharedSparkSession {
exception = intercept[AnalysisException] {
getProvidingClass(provider)
},
- condition = "_LEGACY_ERROR_TEMP_1139",
+ condition = "AVRO_DATA_SOURCE_NOT_ENABLED",
parameters = Map("provider" -> provider)
)
}
@@ -95,7 +95,7 @@ class ResolvedDataSourceSuite extends SharedSparkSession {
exception = intercept[AnalysisException] {
getProvidingClass("kafka")
},
- condition = "_LEGACY_ERROR_TEMP_1140",
+ condition = "KAFKA_DATA_SOURCE_NOT_ENABLED",
parameters = Map("provider" -> "kafka")
)
}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
