This is an automated email from the ASF dual-hosted git repository.
wenchen 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 21b1d11ddd6a [SPARK-53385][SQL] Refactor Identifier evaluation out
21b1d11ddd6a is described below
commit 21b1d11ddd6a229714dfd0db2828a1f80ca11a70
Author: Vladimir Golubev <vladimir.golu...@databricks.com>
AuthorDate: Wed Aug 27 14:54:27 2025 +0800
[SPARK-53385][SQL] Refactor Identifier evaluation out
### What changes were proposed in this pull request?
Refactor Identifier evaluation out.
### Why are the changes needed?
To have compatibility between Analyzers.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Existing tests.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #52126 from
vladimirg-db/vladimir-golubev_data/refactor-identifier-evaluation-out.
Authored-by: Vladimir Golubev <vladimir.golu...@databricks.com>
Signed-off-by: Wenchen Fan <wenc...@databricks.com>
---
.../catalyst/analysis/IdentifierResolution.scala | 51 ++++++++++++++++++++++
.../analysis/ResolveIdentifierClause.scala | 39 +++--------------
2 files changed, 57 insertions(+), 33 deletions(-)
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/IdentifierResolution.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/IdentifierResolution.scala
new file mode 100644
index 000000000000..e274c1e2162a
--- /dev/null
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/IdentifierResolution.scala
@@ -0,0 +1,51 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.catalyst.analysis
+
+import org.apache.spark.sql.catalyst.expressions.{AliasHelper, EvalHelper,
Expression}
+import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
+import org.apache.spark.sql.types.StringType
+
+object IdentifierResolution extends AliasHelper with EvalHelper {
+ def evalIdentifierExpr(expr: Expression): Seq[String] = {
+ trimAliases(prepareForEval(expr)) match {
+ case e if !e.foldable =>
+ expr.failAnalysis(
+ errorClass = "NOT_A_CONSTANT_STRING.NOT_CONSTANT",
+ messageParameters = Map("name" -> "IDENTIFIER", "expr" -> expr.sql)
+ )
+ case e if e.dataType != StringType =>
+ expr.failAnalysis(
+ errorClass = "NOT_A_CONSTANT_STRING.WRONG_TYPE",
+ messageParameters =
+ Map("name" -> "IDENTIFIER", "expr" -> expr.sql, "dataType" ->
e.dataType.catalogString)
+ )
+ case e =>
+ e.eval() match {
+ case null =>
+ expr.failAnalysis(
+ errorClass = "NOT_A_CONSTANT_STRING.NULL",
+ messageParameters = Map("name" -> "IDENTIFIER", "expr" ->
expr.sql)
+ )
+ case other =>
+ // Parse the identifier string to name parts.
+ CatalystSqlParser.parseMultipartIdentifier(other.toString)
+ }
+ }
+ }
+}
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveIdentifierClause.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveIdentifierClause.scala
index 96ed8a63585d..7150c81ad64e 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveIdentifierClause.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveIdentifierClause.scala
@@ -19,20 +19,18 @@ package org.apache.spark.sql.catalyst.analysis
import scala.collection.mutable
-import org.apache.spark.sql.catalyst.expressions.{AliasHelper, EvalHelper,
Expression, SubqueryExpression, VariableReference}
-import org.apache.spark.sql.catalyst.parser.CatalystSqlParser
+import org.apache.spark.sql.catalyst.expressions.{Expression,
SubqueryExpression, VariableReference}
import org.apache.spark.sql.catalyst.plans.logical.{CreateView, LogicalPlan}
import org.apache.spark.sql.catalyst.rules.{Rule, RuleExecutor}
import org.apache.spark.sql.catalyst.trees.TreePattern._
import org.apache.spark.sql.errors.QueryCompilationErrors
import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.types.StringType
/**
* Resolves the identifier expressions and builds the original
plans/expressions.
*/
class ResolveIdentifierClause(earlyBatches:
Seq[RuleExecutor[LogicalPlan]#Batch])
- extends Rule[LogicalPlan] with AliasHelper with EvalHelper {
+ extends Rule[LogicalPlan] {
private val executor = new RuleExecutor[LogicalPlan] {
override def batches: Seq[Batch] = earlyBatches.asInstanceOf[Seq[Batch]]
@@ -70,7 +68,8 @@ class ResolveIdentifierClause(earlyBatches:
Seq[RuleExecutor[LogicalPlan]#Batch]
referredTempVars.get ++= collectTemporaryVariablesInLogicalPlan(p)
}
-
executor.execute(p.planBuilder.apply(evalIdentifierExpr(p.identifierExpr),
p.children))
+ executor.execute(p.planBuilder.apply(
+ IdentifierResolution.evalIdentifierExpr(p.identifierExpr),
p.children))
case other =>
other.transformExpressionsWithPruning(_.containsAnyPattern(UNRESOLVED_IDENTIFIER))
{
case e: ExpressionWithUnresolvedIdentifier if
e.identifierExpr.resolved =>
@@ -79,7 +78,8 @@ class ResolveIdentifierClause(earlyBatches:
Seq[RuleExecutor[LogicalPlan]#Batch]
referredTempVars.get ++=
collectTemporaryVariablesInExpressionTree(e)
}
- e.exprBuilder.apply(evalIdentifierExpr(e.identifierExpr),
e.otherExprs)
+ e.exprBuilder.apply(
+ IdentifierResolution.evalIdentifierExpr(e.identifierExpr),
e.otherExprs)
}
}
@@ -104,31 +104,4 @@ class ResolveIdentifierClause(earlyBatches:
Seq[RuleExecutor[LogicalPlan]#Batch]
}
collectTempVars(child)
}
-
- private def evalIdentifierExpr(expr: Expression): Seq[String] = {
- trimAliases(prepareForEval(expr)) match {
- case e if !e.foldable => expr.failAnalysis(
- errorClass = "NOT_A_CONSTANT_STRING.NOT_CONSTANT",
- messageParameters = Map(
- "name" -> "IDENTIFIER",
- "expr" -> expr.sql))
- case e if e.dataType != StringType => expr.failAnalysis(
- errorClass = "NOT_A_CONSTANT_STRING.WRONG_TYPE",
- messageParameters = Map(
- "name" -> "IDENTIFIER",
- "expr" -> expr.sql,
- "dataType" -> e.dataType.catalogString))
- case e =>
- e.eval() match {
- case null => expr.failAnalysis(
- errorClass = "NOT_A_CONSTANT_STRING.NULL",
- messageParameters = Map(
- "name" -> "IDENTIFIER",
- "expr" -> expr.sql))
- case other =>
- // Parse the identifier string to name parts.
- CatalystSqlParser.parseMultipartIdentifier(other.toString)
- }
- }
- }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
