Skip to content

[SPARK-38173][SQL][3.2] Quoted column cannot be recognized correctly when quotedRegexColumnNames is true #39473

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-38173][SQL][3.2] Quoted column cannot be recognized correctly when quotedRegexColumnNames is true #39473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 12 additions & 2 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2030,6 +2030,14 @@ class AstBuilder extends SqlBaseBaseVisitor[AnyRef] with SQLConfHelper with Logg
return false
}

/**
* Returns whether the pattern is a regex expression (instead of a normal
* string). Normal string is a string with all alphabets/digits and "_".
*/
private def isRegex(pattern: String): Boolean = {
pattern.exists(p => !Character.isLetterOrDigit(p) && p != '_')
}

/**
* Create a dereference expression. The return type depends on the type of the parent.
* If the parent is an [[UnresolvedAttribute]], it can be a [[UnresolvedAttribute]] or
Expand All @@ -2042,7 +2050,8 @@ class AstBuilder extends SqlBaseBaseVisitor[AnyRef] with SQLConfHelper with Logg
case unresolved_attr @ UnresolvedAttribute(nameParts) =>
ctx.fieldName.getStart.getText match {
case escapedIdentifier(columnNameRegex)
if conf.supportQuotedRegexColumnName && canApplyRegex(ctx) =>
if conf.supportQuotedRegexColumnName &&
isRegex(columnNameRegex) && canApplyRegex(ctx) =>
UnresolvedRegex(columnNameRegex, Some(unresolved_attr.name),
conf.caseSensitiveAnalysis)
case _ =>
Expand All @@ -2060,7 +2069,8 @@ class AstBuilder extends SqlBaseBaseVisitor[AnyRef] with SQLConfHelper with Logg
override def visitColumnReference(ctx: ColumnReferenceContext): Expression = withOrigin(ctx) {
ctx.getStart.getText match {
case escapedIdentifier(columnNameRegex)
if conf.supportQuotedRegexColumnName && canApplyRegex(ctx) =>
if conf.supportQuotedRegexColumnName &&
isRegex(columnNameRegex) && canApplyRegex(ctx) =>
UnresolvedRegex(columnNameRegex, None, conf.caseSensitiveAnalysis)
case _ =>
UnresolvedAttribute.quoted(ctx.getText)
Expand Down
13 changes: 13 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4259,6 +4259,19 @@ class SQLQuerySuite extends QueryTest with SharedSparkSession with AdaptiveSpark
sql("select * from test_temp_view"),
Row(1, 2, 3, 1, 2, 3, 1, 1))
}

test("SPARK-38173: Quoted column cannot be recognized correctly " +
"when quotedRegexColumnNames is true") {
withSQLConf(SQLConf.SUPPORT_QUOTED_REGEX_COLUMN_NAME.key -> "true") {
checkAnswer(
sql(
"""
|SELECT `(C3)?+.+`,T.`C1` * `C2` AS CC
|FROM (SELECT 3 AS C1,2 AS C2,1 AS C3) T
|""".stripMargin),
Row(3, 2, 6) :: Nil)
}
}
}

case class Foo(bar: Option[String])