This is an automated email from the ASF dual-hosted git repository.
maxgekk 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 fe7bdce8d12
[SPARK-43820][SPARK-43822][SPARK-43823][SPARK-43826][SPARK-43827] Assign names
to the error class _LEGACY_ERROR_TEMP_241[1-7]
fe7bdce8d12 is described below
commit fe7bdce8d121e2733e82706177d34f0342db0cbe
Author: Jiaan Geng <[email protected]>
AuthorDate: Sun May 28 13:50:59 2023 +0300
[SPARK-43820][SPARK-43822][SPARK-43823][SPARK-43826][SPARK-43827] Assign
names to the error class _LEGACY_ERROR_TEMP_241[1-7]
### What changes were proposed in this pull request?
The pr aims to assign a name to the error class _LEGACY_ERROR_TEMP_241[1-7].
### Why are the changes needed?
Improve the error framework.
### Does this PR introduce _any_ user-facing change?
'No'.
### How was this patch tested?
Exists test cases.
Closes #41339 from beliefer/2411-2417.
Authored-by: Jiaan Geng <[email protected]>
Signed-off-by: Max Gekk <[email protected]>
---
core/src/main/resources/error/error-classes.json | 45 +++++++++-----------
.../sql/catalyst/analysis/CheckAnalysis.scala | 32 ++++++++-------
.../sql/catalyst/analysis/AnalysisErrorSuite.scala | 20 ++++++---
.../sql-tests/analyzer-results/percentiles.sql.out | 48 +++++++++++-----------
.../sql-tests/results/percentiles.sql.out | 48 +++++++++++-----------
5 files changed, 99 insertions(+), 94 deletions(-)
diff --git a/core/src/main/resources/error/error-classes.json
b/core/src/main/resources/error/error-classes.json
index 10a483396e6..3a11001ad9d 100644
--- a/core/src/main/resources/error/error-classes.json
+++ b/core/src/main/resources/error/error-classes.json
@@ -617,6 +617,11 @@
"Not found an encoder of the type <typeName> to Spark SQL internal
representation. Consider to change the input type to one of supported at
'<docroot>/sql-ref-datatypes.html'."
]
},
+ "EVENT_TIME_IS_NOT_ON_TIMESTAMP_TYPE" : {
+ "message" : [
+ "The event time <eventName> has the invalid type <eventType>, but
expected \"TIMESTAMP\"."
+ ]
+ },
"FAILED_EXECUTE_UDF" : {
"message" : [
"Failed to execute user defined function (<functionName>: (<signature>)
=> <result>)."
@@ -1371,6 +1376,11 @@
],
"sqlState" : "42903"
},
+ "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC" : {
+ "message" : [
+ "Cannot specify ORDER BY or a window frame for <aggFunc>."
+ ]
+ },
"INVALID_WRITE_DISTRIBUTION" : {
"message" : [
"The requested write distribution is invalid."
@@ -1393,6 +1403,11 @@
}
}
},
+ "JOIN_CONDITION_IS_NOT_BOOLEAN_TYPE" : {
+ "message" : [
+ "The join condition <joinCondition> has the invalid type
<conditionType>, expected \"BOOLEAN\"."
+ ]
+ },
"LOCATION_ALREADY_EXISTS" : {
"message" : [
"Cannot name the managed table as <identifier>, as its associated
location <location> already exists. Please pick a different table name, or
remove the existing location first."
@@ -1785,6 +1800,11 @@
],
"sqlState" : "22023"
},
+ "SEED_EXPRESSION_IS_UNFOLDABLE" : {
+ "message" : [
+ "The seed expression <seedExpr> of the expression <exprWithSeed> must be
foldable."
+ ]
+ },
"SORT_BY_WITHOUT_BUCKETING" : {
"message" : [
"sortBy must be used together with bucketBy."
@@ -5441,31 +5461,6 @@
"failed to evaluate expression <sqlExpr>: <msg>"
]
},
- "_LEGACY_ERROR_TEMP_2411" : {
- "message" : [
- "Cannot specify order by or frame for '<aggFunc>'."
- ]
- },
- "_LEGACY_ERROR_TEMP_2413" : {
- "message" : [
- "Input argument to <argName> must be a constant."
- ]
- },
- "_LEGACY_ERROR_TEMP_2414" : {
- "message" : [
- "Event time must be defined on a window or a timestamp, but <evName> is
of type <evType>."
- ]
- },
- "_LEGACY_ERROR_TEMP_2416" : {
- "message" : [
- "join condition '<join>' of type <type> is not a boolean."
- ]
- },
- "_LEGACY_ERROR_TEMP_2417" : {
- "message" : [
- "join condition '<condition>' of type <dataType> is not a boolean."
- ]
- },
"_LEGACY_ERROR_TEMP_2418" : {
"message" : [
"Input argument tolerance must be a constant."
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index 43f12fabf70..cafabb22d10 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -329,8 +329,8 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
if w.windowSpec.orderSpec.nonEmpty ||
w.windowSpec.frameSpecification !=
SpecifiedWindowFrame(RowFrame, UnboundedPreceding,
UnboundedFollowing) =>
agg.failAnalysis(
- errorClass = "_LEGACY_ERROR_TEMP_2411",
- messageParameters = Map("aggFunc" ->
agg.aggregateFunction.prettyName))
+ errorClass = "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
+ messageParameters = Map("aggFunc" ->
toSQLExpr(agg.aggregateFunction)))
case _: AggregateExpression | _: FrameLessOffsetWindowFunction |
_: AggregateWindowFunction => // OK
case other =>
@@ -344,8 +344,10 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
case e: ExpressionWithRandomSeed if !e.seedExpression.foldable =>
e.failAnalysis(
- errorClass = "_LEGACY_ERROR_TEMP_2413",
- messageParameters = Map("argName" -> e.prettyName))
+ errorClass = "SEED_EXPRESSION_IS_UNFOLDABLE",
+ messageParameters = Map(
+ "seedExpr" -> toSQLExpr(e.seedExpression),
+ "exprWithSeed" -> toSQLExpr(e)))
case p: Parameter =>
p.failAnalysis(
@@ -363,10 +365,10 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
case _: TimestampType =>
case _ =>
etw.failAnalysis(
- errorClass = "_LEGACY_ERROR_TEMP_2414",
+ errorClass = "EVENT_TIME_IS_NOT_ON_TIMESTAMP_TYPE",
messageParameters = Map(
- "evName" -> etw.eventTime.name,
- "evType" -> etw.eventTime.dataType.catalogString))
+ "eventName" -> toSQLId(etw.eventTime.name),
+ "eventType" -> toSQLType(etw.eventTime.dataType)))
}
case f: Filter if f.condition.dataType != BooleanType =>
f.failAnalysis(
@@ -378,18 +380,18 @@ trait CheckAnalysis extends PredicateHelper with
LookupCatalog with QueryErrorsB
case j @ Join(_, _, _, Some(condition), _) if condition.dataType !=
BooleanType =>
j.failAnalysis(
- errorClass = "_LEGACY_ERROR_TEMP_2416",
+ errorClass = "JOIN_CONDITION_IS_NOT_BOOLEAN_TYPE",
messageParameters = Map(
- "join" -> condition.sql,
- "type" -> condition.dataType.catalogString))
+ "joinCondition" -> toSQLExpr(condition),
+ "conditionType" -> toSQLType(condition.dataType)))
case j @ AsOfJoin(_, _, _, Some(condition), _, _, _)
if condition.dataType != BooleanType =>
- j.failAnalysis(
- errorClass = "_LEGACY_ERROR_TEMP_2417",
- messageParameters = Map(
- "condition" -> condition.sql,
- "dataType" -> condition.dataType.catalogString))
+ throw SparkException.internalError(
+ msg = s"join condition '${toSQLExpr(condition)}' " +
+ s"of type ${toSQLType(condition.dataType)} is not a boolean.",
+ context = j.origin.getQueryContext,
+ summary = j.origin.context.summary)
case j @ AsOfJoin(_, _, _, _, _, _, Some(toleranceAssertion)) =>
if (!toleranceAssertion.foldable) {
diff --git
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala
index 1dcecebd5dc..198c44f69ae 100644
---
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala
+++
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala
@@ -361,10 +361,11 @@ class AnalysisErrorSuite extends AnalysisTest {
errorClass = "DATATYPE_MISMATCH.FILTER_NOT_BOOLEAN",
messageParameters = Map("sqlExpr" -> "\"1\"", "filter" -> "\"1\"", "type"
-> "\"INT\""))
- errorTest(
+ errorClassTest(
"non-boolean join conditions",
testRelation.join(testRelation, condition = Some(Literal(1))),
- "condition" :: "'1'" :: "not a boolean" ::
Literal(1).dataType.simpleString :: Nil)
+ errorClass = "JOIN_CONDITION_IS_NOT_BOOLEAN_TYPE",
+ messageParameters = Map("joinCondition" -> "\"1\"", "conditionType" ->
"\"INT\""))
errorClassTest(
"missing group by",
@@ -964,10 +965,17 @@ class AnalysisErrorSuite extends AnalysisTest {
}
test("SPARK-33909: Check rand functions seed is legal at analyzer side") {
- Seq(Rand("a".attr), Randn("a".attr)).foreach { r =>
- val plan = Project(Seq(r.as("r")), testRelation)
- assertAnalysisError(plan,
- s"Input argument to ${r.prettyName} must be a constant." :: Nil)
+ Seq((Rand("a".attr), "\"rand(a)\""),
+ (Randn("a".attr), "\"randn(a)\"")).foreach {
+ case (r, expectedArg) =>
+ val plan = Project(Seq(r.as("r")), testRelation)
+ assertAnalysisErrorClass(plan,
+ expectedErrorClass = "SEED_EXPRESSION_IS_UNFOLDABLE",
+ expectedMessageParameters = Map(
+ "seedExpr" -> "\"a\"",
+ "exprWithSeed" -> expectedArg),
+ caseSensitive = false
+ )
}
Seq(
Rand(1.0) -> ("\"rand(1.0)\"", "\"1.0\"", "\"DOUBLE\""),
diff --git
a/sql/core/src/test/resources/sql-tests/analyzer-results/percentiles.sql.out
b/sql/core/src/test/resources/sql-tests/analyzer-results/percentiles.sql.out
index f4c05039b7f..9c945687830 100644
--- a/sql/core/src/test/resources/sql-tests/analyzer-results/percentiles.sql.out
+++ b/sql/core/src/test/resources/sql-tests/analyzer-results/percentiles.sql.out
@@ -206,9 +206,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -232,9 +232,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -257,9 +257,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -283,9 +283,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -309,9 +309,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -334,9 +334,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -416,9 +416,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -443,9 +443,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -469,9 +469,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -496,9 +496,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -523,9 +523,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -549,9 +549,9 @@ ORDER BY salary
-- !query analysis
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
diff --git a/sql/core/src/test/resources/sql-tests/results/percentiles.sql.out
b/sql/core/src/test/resources/sql-tests/results/percentiles.sql.out
index 38319875c71..1e307d9a061 100644
--- a/sql/core/src/test/resources/sql-tests/results/percentiles.sql.out
+++ b/sql/core/src/test/resources/sql-tests/results/percentiles.sql.out
@@ -179,9 +179,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -207,9 +207,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -234,9 +234,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -262,9 +262,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -290,9 +290,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -317,9 +317,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -409,9 +409,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -438,9 +438,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -466,9 +466,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -495,9 +495,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_cont"
+ "aggFunc" : "\"percentile_cont(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -524,9 +524,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "percentile_disc"
+ "aggFunc" : "\"percentile_disc(salary, 0.25)\""
},
"queryContext" : [ {
"objectType" : "",
@@ -552,9 +552,9 @@ struct<>
-- !query output
org.apache.spark.sql.AnalysisException
{
- "errorClass" : "_LEGACY_ERROR_TEMP_2411",
+ "errorClass" : "INVALID_WINDOW_SPEC_FOR_AGGREGATION_FUNC",
"messageParameters" : {
- "aggFunc" : "median"
+ "aggFunc" : "\"median(salary)\""
},
"queryContext" : [ {
"objectType" : "",
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
