Skip to content

[SPARK-52832][SQL][3.5] Fix JDBC dialect identifier quoting #58393

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

Open
holdenk wants to merge 1 commit into
base: branch-3.5
Choose a base branch
from
+24 −13
Open

[SPARK-52832][SQL][3.5] Fix JDBC dialect identifier quoting #58393

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
4 changes: 3 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/jdbc/JdbcDialects.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,9 @@ abstract class JdbcDialect extends Serializable with Logging {
* name is a reserved keyword, or in case it contains characters that require quotes (e.g. space).
*/
def quoteIdentifier(colName: String): String = {
s""""$colName""""
// By ANSI standard, quotes are escaped with another quotes.
val escapedColName = colName.replace("\"", "\"\"")
s""""$escapedColName""""
}

/**
Expand Down
8 changes: 7 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/jdbc/MySQLDialect.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,13 @@ private case object MySQLDialect extends JdbcDialect with SQLConfHelper {
}

override def quoteIdentifier(colName: String): String = {
s"`$colName`"
// Per MySQL documentation: https://dev.mysql.com/doc/refman/8.4/en/identifiers.html
//
// Identifier quote characters can be included within an identifier if you quote the
// identifier. If the character to be included within the identifier is the same as
// that used to quote the identifier itself, then you need to double the character.
val escapedColName = colName.replace("`", "``")
s"`$escapedColName`"
}

override def schemasExists(conn: Connection, options: JDBCOptions, schema: String): Boolean = {
Expand Down
25 changes: 14 additions & 11 deletions sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -834,17 +834,20 @@ class JDBCSuite extends QueryTest with SharedSparkSession {
}

test("quote column names by jdbc dialect") {
val MySQL = JdbcDialects.get("jdbc:mysql://127.0.0.1/db")
val Postgres = JdbcDialects.get("jdbc:postgresql://127.0.0.1/db")
val Derby = JdbcDialects.get("jdbc:derby:db")

val columns = Seq("abc", "key")
val MySQLColumns = columns.map(MySQL.quoteIdentifier(_))
val PostgresColumns = columns.map(Postgres.quoteIdentifier(_))
val DerbyColumns = columns.map(Derby.quoteIdentifier(_))
assert(MySQLColumns === Seq("`abc`", "`key`"))
assert(PostgresColumns === Seq(""""abc"""", """"key""""))
assert(DerbyColumns === Seq(""""abc"""", """"key""""))
val mySQLDialect = JdbcDialects.get("jdbc:mysql://127.0.0.1/db")
val postgresDialect = JdbcDialects.get("jdbc:postgresql://127.0.0.1/db")
val derbyDialect = JdbcDialects.get("jdbc:derby:db")
val oracleDialect = JdbcDialects.get("jdbc:oracle:thin:@//localhost:1521/orcl")

val columns = Seq("abc", "key", "double_quote\"", "back`")
val mySQLColumns = columns.map(mySQLDialect.quoteIdentifier)
val postgresColumns = columns.map(postgresDialect.quoteIdentifier)
val derbyColumns = columns.map(derbyDialect.quoteIdentifier)
val oracleColumns = columns.map(oracleDialect.quoteIdentifier)
assertResult(Seq("`abc`", "`key`", "`double_quote\"`", "`back```"))(mySQLColumns)
assertResult(Seq("\"abc\"", "\"key\"", "\"double_quote\"\"\"", "\"back`\""))(postgresColumns)
assertResult(Seq("\"abc\"", "\"key\"", "\"double_quote\"\"\"", "\"back`\""))(derbyColumns)
assertResult(Seq("\"abc\"", "\"key\"", "\"double_quote\"\"\"", "\"back`\""))(oracleColumns)
}

test("compile filters") {
Expand Down