Skip to content

MySQL: Add support for DEFAULT CHARACTER SET in CREATE DATABASE #2182

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
mvzink wants to merge 1 commit into
base: main
Choose a base branch
from
+155 −0
Open

MySQL: Add support for DEFAULT CHARACTER SET in CREATE DATABASE #2182

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
24 changes: 24 additions & 0 deletions src/ast/helpers/stmt_create_database.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,10 @@ pub struct CreateDatabaseBuilder {
pub storage_serialization_policy: Option<StorageSerializationPolicy>,
/// Optional comment attached to the database.
pub comment: Option<String>,
/// Optional default character set (MySQL).
Copy link
Contributor

@iffyio iffyio Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we include a link to the mysql documentation for the doc comments?

pub default_charset: Option<String>,
/// Optional default collation (MySQL).
pub default_collation: Option<String>,
/// Optional catalog sync configuration.
pub catalog_sync: Option<String>,
/// Optional catalog sync namespace mode.
Expand Down Expand Up @@ -120,6 +124,8 @@ impl CreateDatabaseBuilder {
default_ddl_collation: None,
storage_serialization_policy: None,
comment: None,
default_charset: None,
default_collation: None,
catalog_sync: None,
catalog_sync_namespace_mode: None,
catalog_sync_namespace_flatten_delimiter: None,
Expand Down Expand Up @@ -218,6 +224,18 @@ impl CreateDatabaseBuilder {
self
}

/// Set the default character set for the database.
pub fn default_charset(mut self, default_charset: Option<String>) -> Self {
self.default_charset = default_charset;
self
}

/// Set the default collation for the database.
pub fn default_collation(mut self, default_collation: Option<String>) -> Self {
self.default_collation = default_collation;
self
}

/// Set the catalog sync for the database.
pub fn catalog_sync(mut self, catalog_sync: Option<String>) -> Self {
self.catalog_sync = catalog_sync;
Expand Down Expand Up @@ -272,6 +290,8 @@ impl CreateDatabaseBuilder {
default_ddl_collation: self.default_ddl_collation,
storage_serialization_policy: self.storage_serialization_policy,
comment: self.comment,
default_charset: self.default_charset,
default_collation: self.default_collation,
catalog_sync: self.catalog_sync,
catalog_sync_namespace_mode: self.catalog_sync_namespace_mode,
catalog_sync_namespace_flatten_delimiter: self.catalog_sync_namespace_flatten_delimiter,
Expand Down Expand Up @@ -302,6 +322,8 @@ impl TryFrom<Statement> for CreateDatabaseBuilder {
default_ddl_collation,
storage_serialization_policy,
comment,
default_charset,
default_collation,
catalog_sync,
catalog_sync_namespace_mode,
catalog_sync_namespace_flatten_delimiter,
Expand All @@ -323,6 +345,8 @@ impl TryFrom<Statement> for CreateDatabaseBuilder {
default_ddl_collation,
storage_serialization_policy,
comment,
default_charset,
default_collation,
catalog_sync,
catalog_sync_namespace_mode,
catalog_sync_namespace_flatten_delimiter,
Expand Down
14 changes: 14 additions & 0 deletions src/ast/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4285,6 +4285,10 @@ pub enum Statement {
storage_serialization_policy: Option<StorageSerializationPolicy>,
/// Optional comment.
comment: Option<String>,
/// Optional default character set (MySQL).
default_charset: Option<String>,
/// Optional default collation (MySQL).
default_collation: Option<String>,
/// Optional catalog sync identifier.
catalog_sync: Option<String>,
/// Catalog sync namespace mode.
Expand Down Expand Up @@ -5165,6 +5169,8 @@ impl fmt::Display for Statement {
default_ddl_collation,
storage_serialization_policy,
comment,
default_charset,
default_collation,
catalog_sync,
catalog_sync_namespace_mode,
catalog_sync_namespace_flatten_delimiter,
Expand Down Expand Up @@ -5224,6 +5230,14 @@ impl fmt::Display for Statement {
write!(f, " COMMENT = '{comment}'")?;
}

if let Some(charset) = default_charset {
write!(f, " DEFAULT CHARACTER SET {charset}")?;
}

if let Some(collation) = default_collation {
write!(f, " DEFAULT COLLATE {collation}")?;
}

if let Some(sync) = catalog_sync {
write!(f, " CATALOG_SYNC = '{sync}'")?;
}
Expand Down
24 changes: 24 additions & 0 deletions src/parser/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5294,6 +5294,8 @@ impl<'a> Parser<'a> {
let db_name = self.parse_object_name(false)?;
let mut location = None;
let mut managed_location = None;
let mut default_charset = None;
let mut default_collation = None;
loop {
match self.parse_one_of_keywords(&[Keyword::LOCATION, Keyword::MANAGEDLOCATION]) {
Some(Keyword::LOCATION) => location = Some(self.parse_literal_string()?),
Expand All @@ -5309,6 +5311,26 @@ impl<'a> Parser<'a> {
None
};

// Parse MySQL-style [DEFAULT] CHARACTER SET and [DEFAULT] COLLATE options
Copy link
Contributor

@iffyio iffyio Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we move the default_charset and default_collation closer here to the loop? (misread for a second wondering if the values were being previously set elsewhere before the loop)

loop {
let has_default = self.parse_keyword(Keyword::DEFAULT);
if self.parse_keywords(&[Keyword::CHARACTER, Keyword::SET])
Copy link
Contributor

@iffyio iffyio Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if self.parse_keywords(&[Keyword::CHARACTER, Keyword::SET])
if default_charset.is_none() && self.parse_keywords(&[Keyword::CHARACTER, Keyword::SET])

|| self.parse_keyword(Keyword::CHARSET)
{
self.expect_token(&Token::Eq).ok();
default_charset = Some(self.parse_identifier()?.value);
} else if self.parse_keyword(Keyword::COLLATE) {
Copy link
Contributor

@iffyio iffyio Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
} else if self.parse_keyword(Keyword::COLLATE) {
} else if default_collation.is_none() && self.parse_keyword(Keyword::COLLATE) {

self.expect_token(&Token::Eq).ok();
Comment on lines +5320 to +5323
Copy link
Contributor

@iffyio iffyio Feb 3, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can we handle the errors in the calls to expect_token?

default_collation = Some(self.parse_identifier()?.value);
} else if has_default {
// DEFAULT keyword not followed by CHARACTER SET, CHARSET, or COLLATE
self.prev_token();
break;
} else {
break;
}
}

Ok(Statement::CreateDatabase {
db_name,
if_not_exists: ine,
Expand All @@ -5325,6 +5347,8 @@ impl<'a> Parser<'a> {
default_ddl_collation: None,
storage_serialization_policy: None,
comment: None,
default_charset,
default_collation,
catalog_sync: None,
catalog_sync_namespace_mode: None,
catalog_sync_namespace_flatten_delimiter: None,
Expand Down
93 changes: 93 additions & 0 deletions tests/sqlparser_mysql.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4354,3 +4354,96 @@ fn test_create_index_options() {
"CREATE INDEX idx_name ON t(c1, c2) USING BTREE LOCK = EXCLUSIVE ALGORITHM = DEFAULT",
);
}

#[test]
fn parse_create_database_with_charset() {
// Test DEFAULT CHARACTER SET with = sign
mysql_and_generic().verified_stmt("CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4");

// Test DEFAULT CHARACTER SET without = sign (normalized form)
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb DEFAULT CHARACTER SET = utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4",
);

// Test CHARACTER SET without DEFAULT
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb CHARACTER SET utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4",
);

// Test CHARSET shorthand
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb CHARSET utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4",
);

// Test DEFAULT CHARSET shorthand
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb DEFAULT CHARSET utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4",
);

// Test DEFAULT COLLATE
mysql_and_generic().verified_stmt("CREATE DATABASE mydb DEFAULT COLLATE utf8mb4_unicode_ci");

// Test COLLATE without DEFAULT
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb COLLATE utf8mb4_unicode_ci",
"CREATE DATABASE mydb DEFAULT COLLATE utf8mb4_unicode_ci",
);

// Test both CHARACTER SET and COLLATE together
mysql_and_generic().verified_stmt(
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4 DEFAULT COLLATE utf8mb4_unicode_ci",
);

// Test IF NOT EXISTS with CHARACTER SET
mysql_and_generic()
.verified_stmt("CREATE DATABASE IF NOT EXISTS mydb DEFAULT CHARACTER SET utf16");

// Test the exact syntax from the issue
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE IF NOT EXISTS noria DEFAULT CHARACTER SET = utf16",
"CREATE DATABASE IF NOT EXISTS noria DEFAULT CHARACTER SET utf16",
);
}

#[test]
fn parse_create_database_with_charset_errors() {
// Missing charset name after CHARACTER SET
assert!(mysql_and_generic()
.parse_sql_statements("CREATE DATABASE mydb DEFAULT CHARACTER SET")
.is_err());

// Missing charset name after CHARSET
assert!(mysql_and_generic()
.parse_sql_statements("CREATE DATABASE mydb CHARSET")
.is_err());

// Missing collation name after COLLATE
assert!(mysql_and_generic()
.parse_sql_statements("CREATE DATABASE mydb DEFAULT COLLATE")
.is_err());

// Equals sign but no value
assert!(mysql_and_generic()
.parse_sql_statements("CREATE DATABASE mydb CHARACTER SET =")
.is_err());
}

#[test]
fn parse_create_database_with_charset_option_ordering() {
// MySQL allows COLLATE before CHARACTER SET - output is normalized to CHARACTER SET first
// (matches MySQL's own SHOW CREATE DATABASE output order)
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb DEFAULT COLLATE utf8mb4_unicode_ci DEFAULT CHARACTER SET utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4 DEFAULT COLLATE utf8mb4_unicode_ci",
);

// COLLATE first without DEFAULT keywords
mysql_and_generic().one_statement_parses_to(
"CREATE DATABASE mydb COLLATE utf8mb4_unicode_ci CHARACTER SET utf8mb4",
"CREATE DATABASE mydb DEFAULT CHARACTER SET utf8mb4 DEFAULT COLLATE utf8mb4_unicode_ci",
);
}