MaxGekk commented on code in PR #40810:
URL: https://github.com/apache/spark/pull/40810#discussion_r1174421492
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala:
##########
@@ -2345,11 +2345,13 @@ private[sql] object QueryExecutionErrors extends
QueryErrorsBase {
cause = null)
}
- def failedMergingSchemaError(schema: StructType, e: SparkException):
Throwable = {
+ def failedMergingSchemaError(
+ leftSchema: StructType,
+ rightSchema: StructType,
+ e: SparkException): Throwable = {
new SparkException(
- errorClass = "_LEGACY_ERROR_TEMP_2247",
- messageParameters = Map(
- "schema" -> schema.treeString),
+ errorClass = "CANNOT_MERGE_SCHEMAS",
+ messageParameters = Map("left" -> leftSchema.treeString, "right" ->
rightSchema.treeString),
Review Comment:
Could you wrap schemas by `toSQLType()` instead of `rightSchema`, please.
BTW, the error occurs in PySpark, SQL, R, we show it in some common form as a
SQL type.
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetSchemaSuite.scala:
##########
@@ -980,20 +980,24 @@ class ParquetSchemaSuite extends ParquetSchemaTest {
}
}
- test("schema merging failure error message") {
+ test("CANNOT_MERGE_SCHEMAS: Failed merging schemas") {
import testImplicits._
withTempPath { dir =>
val path = dir.getCanonicalPath
- spark.range(3).write.parquet(s"$path/p=1")
- spark.range(3).select($"id" cast IntegerType as Symbol("id"))
- .write.parquet(s"$path/p=2")
-
- val message = intercept[SparkException] {
- spark.read.option("mergeSchema", "true").parquet(path).schema
- }.getMessage
-
- assert(message.contains("Failed merging schema"))
+ val df1 = spark.range(3)
+ df1.write.parquet(s"$path/p=1")
+ val df2 = spark.range(3).select($"id" cast IntegerType as Symbol("id"))
+ df2.write.parquet(s"$path/p=2")
+ checkError(
+ exception = intercept[SparkException] {
+ spark.read.option("mergeSchema", "true").parquet(path)
+ },
+ errorClass = "CANNOT_MERGE_SCHEMAS",
+ sqlState = "42KD9",
+ parameters = Map(
+ "left" -> df1.schema.treeString,
+ "right" -> df2.schema.treeString))
Review Comment:
Just embed the SQL types, please.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
