Skip to content

feat: Add support for MSSQL table options #1414

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.

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

Merged
merged 4 commits into from
Sep 11, 2024
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
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
120 changes: 117 additions & 3 deletions src/ast/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1943,6 +1943,15 @@ pub enum CreateTableOptions {
/// e.g. `WITH (description = "123")`
///
/// <https://www.postgresql.org/docs/current/sql-createtable.html>
///
/// MSSQL supports more specific options that's not only key-value pairs.
///
/// WITH (
/// DISTRIBUTION = ROUND_ROBIN,
/// CLUSTERED INDEX (column_a DESC, column_b)
/// )
///
/// <https://learn.microsoft.com/en-us/sql/t-sql/statements/create-table-azure-sql-data-warehouse?view=aps-pdw-2016-au7#syntax>
With(Vec<SqlOption>),
/// Options specified using the `OPTIONS` keyword.
/// e.g. `OPTIONS(description = "123")`
Expand Down Expand Up @@ -5589,14 +5598,119 @@ pub struct HiveFormat {
#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub struct SqlOption {
pub struct ClusteredIndex {
pub name: Ident,
pub value: Expr,
pub asc: Option<bool>,
}

impl fmt::Display for ClusteredIndex {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", self.name)?;
match self.asc {
Some(true) => write!(f, " ASC"),
Some(false) => write!(f, " DESC"),
_ => Ok(()),
}
}
}

#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum TableOptionsClustered {
ColumnstoreIndex,
ColumnstoreIndexOrder(Vec<Ident>),
Index(Vec<ClusteredIndex>),
}

impl fmt::Display for TableOptionsClustered {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
TableOptionsClustered::ColumnstoreIndex => {
write!(f, "CLUSTERED COLUMNSTORE INDEX")
}
TableOptionsClustered::ColumnstoreIndexOrder(values) => {
write!(
f,
"CLUSTERED COLUMNSTORE INDEX ORDER ({})",
display_comma_separated(values)
)
}
TableOptionsClustered::Index(values) => {
write!(f, "CLUSTERED INDEX ({})", display_comma_separated(values))
}
}
}
}

/// Specifies which partition the boundary values on table partitioning belongs to.
#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum PartitionRangeDirection {
Left,
Right,
}

#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum SqlOption {
/// Clustered represents the clustered version of table storage for MSSQL.
///
/// <https://learn.microsoft.com/en-us/sql/t-sql/statements/create-table-azure-sql-data-warehouse?view=aps-pdw-2016-au7#TableOptions>
Clustered(TableOptionsClustered),
/// Single identifier options, e.g. `HEAP` for MSSQL.
///
/// <https://learn.microsoft.com/en-us/sql/t-sql/statements/create-table-azure-sql-data-warehouse?view=aps-pdw-2016-au7#TableOptions>
Ident(Ident),
/// Any option that consists of a key value pair where the value is an expression. e.g.
///
/// WITH(DISTRIBUTION = ROUND_ROBIN)
KeyValue { key: Ident, value: Expr },
/// One or more table partitions and represents which partition the boundary values belong to,
/// e.g.
///
/// PARTITION (id RANGE LEFT FOR VALUES (10, 20, 30, 40))
///
/// <https://learn.microsoft.com/en-us/sql/t-sql/statements/create-table-azure-sql-data-warehouse?view=aps-pdw-2016-au7#TablePartitionOptions>
Partition {
column_name: Ident,
range_direction: Option<PartitionRangeDirection>,
for_values: Vec<Expr>,
},
}

impl fmt::Display for SqlOption {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{} = {}", self.name, self.value)
match self {
SqlOption::Clustered(c) => write!(f, "{}", c),
SqlOption::Ident(ident) => {
write!(f, "{}", ident)
}
SqlOption::KeyValue { key: name, value } => {
write!(f, "{} = {}", name, value)
}
SqlOption::Partition {
column_name,
range_direction,
for_values,
} => {
let direction = match range_direction {
Some(PartitionRangeDirection::Left) => " LEFT",
Some(PartitionRangeDirection::Right) => " RIGHT",
None => "",
};

write!(
f,
"PARTITION ({} RANGE{} FOR VALUES ({}))",
column_name,
direction,
display_comma_separated(for_values)
)
}
}
}
}

Expand Down
2 changes: 2 additions & 0 deletions src/keywords.rs
Original file line number Diff line number Diff line change
Expand Up @@ -165,6 +165,7 @@ define_keywords!(
COLLECTION,
COLUMN,
COLUMNS,
COLUMNSTORE,
COMMENT,
COMMIT,
COMMITTED,
Expand Down Expand Up @@ -354,6 +355,7 @@ define_keywords!(
HASH,
HAVING,
HEADER,
HEAP,
HIGH_PRIORITY,
HISTORY,
HIVEVAR,
Expand Down
108 changes: 100 additions & 8 deletions src/parser/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -6484,11 +6484,97 @@ impl<'a> Parser<'a> {
}
}

pub fn parse_sql_option(&mut self) -> Result<SqlOption, ParserError> {
pub fn parse_key_value(&mut self) -> Result<(Ident, Expr), ParserError> {
let name = self.parse_identifier(false)?;
self.expect_token(&Token::Eq)?;
let value = self.parse_expr()?;
Ok(SqlOption { name, value })

Ok((name, value))
}

pub fn parse_sql_option(&mut self) -> Result<SqlOption, ParserError> {
let is_mssql = dialect_of!(self is MsSqlDialect|GenericDialect);

match self.peek_token().token {
Token::Word(w) if w.keyword == Keyword::HEAP && is_mssql => {
Ok(SqlOption::Ident(self.parse_identifier(false)?))
}
Token::Word(w) if w.keyword == Keyword::PARTITION && is_mssql => {
self.parse_option_partition()
}
Token::Word(w) if w.keyword == Keyword::CLUSTERED && is_mssql => {
self.parse_option_clustered()
}
_ => {
let (name, value) = self.parse_key_value()?;
Ok(SqlOption::KeyValue { key: name, value })
}
}
}

pub fn parse_option_clustered(&mut self) -> Result<SqlOption, ParserError> {
if self.parse_keywords(&[
Keyword::CLUSTERED,
Keyword::COLUMNSTORE,
Keyword::INDEX,
Keyword::ORDER,
]) {
Ok(SqlOption::Clustered(
TableOptionsClustered::ColumnstoreIndexOrder(
self.parse_parenthesized_column_list(IsOptional::Mandatory, false)?,
),
))
} else if self.parse_keywords(&[Keyword::CLUSTERED, Keyword::COLUMNSTORE, Keyword::INDEX]) {
Ok(SqlOption::Clustered(
TableOptionsClustered::ColumnstoreIndex,
))
} else if self.parse_keywords(&[Keyword::CLUSTERED, Keyword::INDEX]) {
self.expect_token(&Token::LParen)?;

let columns = self.parse_comma_separated(|p| {
let name = p.parse_identifier(false)?;
let asc = p.parse_asc();

Ok(ClusteredIndex { name, asc })
})?;

self.expect_token(&Token::RParen)?;

Ok(SqlOption::Clustered(TableOptionsClustered::Index(columns)))
} else {
Err(ParserError::ParserError(
"invalid CLUSTERED sequence".to_string(),
))
}
}

pub fn parse_option_partition(&mut self) -> Result<SqlOption, ParserError> {
self.expect_keyword(Keyword::PARTITION)?;
self.expect_token(&Token::LParen)?;
let column_name = self.parse_identifier(false)?;

self.expect_keyword(Keyword::RANGE)?;
let range_direction = if self.parse_keyword(Keyword::LEFT) {
Some(PartitionRangeDirection::Left)
} else if self.parse_keyword(Keyword::RIGHT) {
Some(PartitionRangeDirection::Right)
} else {
None
};

self.expect_keywords(&[Keyword::FOR, Keyword::VALUES])?;
self.expect_token(&Token::LParen)?;

let for_values = self.parse_comma_separated(Parser::parse_expr)?;

self.expect_token(&Token::RParen)?;
self.expect_token(&Token::RParen)?;

Ok(SqlOption::Partition {
column_name,
range_direction,
for_values,
})
}

pub fn parse_partition(&mut self) -> Result<Partition, ParserError> {
Expand Down Expand Up @@ -10983,17 +11069,23 @@ impl<'a> Parser<'a> {
})
}

/// Parse an expression, optionally followed by ASC or DESC (used in ORDER BY)
pub fn parse_order_by_expr(&mut self) -> Result<OrderByExpr, ParserError> {
let expr = self.parse_expr()?;

let asc = if self.parse_keyword(Keyword::ASC) {
/// Parsae ASC or DESC, returns an Option with true if ASC, false of DESC or `None` if none of
/// them.
pub fn parse_asc(&mut self) -> Option<bool> {
Copy link
Contributor

Choose a reason for hiding this comment

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

maybe this can be more generic in naming like parse_asc_desc or parse_sort_direction etc? thinking since asc itself isnt the only thing being parsed as the name currently suggests

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Since it was used to only represent if asc (true/false) I wanted to use something like is_asc but I found zero examples of is_ prefixed methods so stuck to parse. I think parse_asc_desc is fine but it's a bit confusing that it doesn't return an enum or either of them but a boolean. Hopefully the description is good enough, I opted to use parse_asc_desc!

if self.parse_keyword(Keyword::ASC) {
Some(true)
} else if self.parse_keyword(Keyword::DESC) {
Some(false)
} else {
None
};
}
}

/// Parse an expression, optionally followed by ASC or DESC (used in ORDER BY)
pub fn parse_order_by_expr(&mut self) -> Result<OrderByExpr, ParserError> {
let expr = self.parse_expr()?;

let asc = self.parse_asc();

let nulls_first = if self.parse_keywords(&[Keyword::NULLS, Keyword::FIRST]) {
Some(true)
Expand Down
28 changes: 14 additions & 14 deletions tests/sqlparser_bigquery.rs
Original file line number Diff line number Diff line change
Expand Up @@ -268,8 +268,8 @@ fn parse_create_view_with_options() {
ViewColumnDef {
name: Ident::new("age"),
data_type: None,
options: Some(vec![SqlOption {
name: Ident::new("description"),
options: Some(vec![SqlOption::KeyValue {
key: Ident::new("description"),
value: Expr::Value(Value::DoubleQuotedString("field age".to_string())),
}])
},
Expand All @@ -288,8 +288,8 @@ fn parse_create_view_with_options() {
unreachable!()
};
assert_eq!(
&SqlOption {
name: Ident::new("description"),
&SqlOption::KeyValue {
key: Ident::new("description"),
value: Expr::Value(Value::DoubleQuotedString(
"a view that expires in 2 days".to_string()
)),
Expand Down Expand Up @@ -415,8 +415,8 @@ fn parse_create_table_with_options() {
},
ColumnOptionDef {
name: None,
option: ColumnOption::Options(vec![SqlOption {
name: Ident::new("description"),
option: ColumnOption::Options(vec![SqlOption::KeyValue {
key: Ident::new("description"),
value: Expr::Value(Value::DoubleQuotedString(
"field x".to_string()
)),
Expand All @@ -430,8 +430,8 @@ fn parse_create_table_with_options() {
collation: None,
options: vec![ColumnOptionDef {
name: None,
option: ColumnOption::Options(vec![SqlOption {
name: Ident::new("description"),
option: ColumnOption::Options(vec![SqlOption::KeyValue {
key: Ident::new("description"),
value: Expr::Value(Value::DoubleQuotedString(
"field y".to_string()
)),
Expand All @@ -449,12 +449,12 @@ fn parse_create_table_with_options() {
Ident::new("age"),
])),
Some(vec![
SqlOption {
name: Ident::new("partition_expiration_days"),
SqlOption::KeyValue {
key: Ident::new("partition_expiration_days"),
value: Expr::Value(number("1")),
},
SqlOption {
name: Ident::new("description"),
SqlOption::KeyValue {
key: Ident::new("description"),
value: Expr::Value(Value::DoubleQuotedString(
"table option description".to_string()
)),
Expand Down Expand Up @@ -2010,8 +2010,8 @@ fn test_bigquery_create_function() {
function_body: Some(CreateFunctionBody::AsAfterOptions(Expr::Value(number(
"42"
)))),
options: Some(vec![SqlOption {
name: Ident::new("x"),
options: Some(vec![SqlOption::KeyValue {
key: Ident::new("x"),
value: Expr::Value(Value::SingleQuotedString("y".into())),
}]),
behavior: None,
Expand Down
Loading
Loading