Skip to content
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

Support Databricks struct literal #1542

Merged
merged 2 commits into from
Dec 2, 2024
Merged
Show file tree
Hide file tree
Changes from all 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
6 changes: 4 additions & 2 deletions src/ast/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -931,12 +931,14 @@ pub enum Expr {
Rollup(Vec<Vec<Expr>>),
/// ROW / TUPLE a single value, such as `SELECT (1, 2)`
Tuple(Vec<Expr>),
/// `BigQuery` specific `Struct` literal expression [1]
/// `Struct` literal expression
/// Syntax:
/// ```sql
/// STRUCT<[field_name] field_type, ...>( expr1 [, ... ])
///
/// [BigQuery](https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#struct_type)
/// [Databricks](https://docs.databricks.com/en/sql/language-manual/functions/struct.html)
/// ```
/// [1]: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#struct_type
Struct {
/// Struct values.
values: Vec<Expr>,
Expand Down
5 changes: 5 additions & 0 deletions src/dialect/bigquery.rs
Original file line number Diff line number Diff line change
Expand Up @@ -72,4 +72,9 @@ impl Dialect for BigQueryDialect {
fn require_interval_qualifier(&self) -> bool {
true
}

// See https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#constructing_a_struct
fn supports_struct_literal(&self) -> bool {
true
}
}
5 changes: 5 additions & 0 deletions src/dialect/databricks.rs
Original file line number Diff line number Diff line change
Expand Up @@ -59,4 +59,9 @@ impl Dialect for DatabricksDialect {
fn require_interval_qualifier(&self) -> bool {
true
}

// See https://docs.databricks.com/en/sql/language-manual/functions/struct.html
fn supports_struct_literal(&self) -> bool {
true
}
}
4 changes: 4 additions & 0 deletions src/dialect/generic.rs
Original file line number Diff line number Diff line change
Expand Up @@ -123,4 +123,8 @@ impl Dialect for GenericDialect {
fn supports_named_fn_args_with_assignment_operator(&self) -> bool {
true
}

fn supports_struct_literal(&self) -> bool {
true
}
}
10 changes: 10 additions & 0 deletions src/dialect/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -375,6 +375,16 @@ pub trait Dialect: Debug + Any {
false
}

/// Return true if the dialect supports the STRUCT literal
///
/// Example
/// ```sql
/// SELECT STRUCT(1 as one, 'foo' as foo, false)
/// ```
fn supports_struct_literal(&self) -> bool {
false
}

/// Dialect-specific infix parser override
///
/// This method is called to parse the next infix expression.
Expand Down
15 changes: 8 additions & 7 deletions src/parser/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1123,9 +1123,8 @@ impl<'a> Parser<'a> {
Keyword::MATCH if dialect_of!(self is MySqlDialect | GenericDialect) => {
Ok(Some(self.parse_match_against()?))
}
Keyword::STRUCT if dialect_of!(self is BigQueryDialect | GenericDialect) => {
self.prev_token();
Ok(Some(self.parse_bigquery_struct_literal()?))
Keyword::STRUCT if self.dialect.supports_struct_literal() => {
Ok(Some(self.parse_struct_literal()?))
}
Keyword::PRIOR if matches!(self.state, ParserState::ConnectBy) => {
let expr = self.parse_subexpr(self.dialect.prec_value(Precedence::PlusMinus))?;
Expand Down Expand Up @@ -2383,15 +2382,16 @@ impl<'a> Parser<'a> {
}
}

/// Bigquery specific: Parse a struct literal
/// Syntax
/// ```sql
/// -- typed
/// STRUCT<[field_name] field_type, ...>( expr1 [, ... ])
/// -- typeless
/// STRUCT( expr1 [AS field_name] [, ... ])
/// ```
fn parse_bigquery_struct_literal(&mut self) -> Result<Expr, ParserError> {
fn parse_struct_literal(&mut self) -> Result<Expr, ParserError> {
// Parse the fields definition if exist `<[field_name] field_type, ...>`
self.prev_token();
let (fields, trailing_bracket) =
self.parse_struct_type_def(Self::parse_struct_field_def)?;
if trailing_bracket.0 {
Expand All @@ -2401,6 +2401,7 @@ impl<'a> Parser<'a> {
);
}

// Parse the struct values `(expr1 [, ... ])`
self.expect_token(&Token::LParen)?;
let values = self
.parse_comma_separated(|parser| parser.parse_struct_field_expr(!fields.is_empty()))?;
Expand All @@ -2409,13 +2410,13 @@ impl<'a> Parser<'a> {
Ok(Expr::Struct { values, fields })
}

/// Parse an expression value for a bigquery struct [1]
/// Parse an expression value for a struct literal
/// Syntax
/// ```sql
/// expr [AS name]
/// ```
///
/// Parameter typed_syntax is set to true if the expression
/// For biquery [1], Parameter typed_syntax is set to true if the expression
/// is to be parsed as a field expression declared using typed
/// struct syntax [2], and false if using typeless struct syntax [3].
///
Expand Down
35 changes: 35 additions & 0 deletions tests/sqlparser_databricks.rs
Original file line number Diff line number Diff line change
Expand Up @@ -278,3 +278,38 @@ fn parse_use() {
);
}
}

#[test]
fn parse_databricks_struct_function() {
assert_eq!(
databricks_and_generic()
.verified_only_select("SELECT STRUCT(1, 'foo')")
.projection[0],
SelectItem::UnnamedExpr(Expr::Struct {
values: vec![
Expr::Value(number("1")),
Expr::Value(Value::SingleQuotedString("foo".to_string()))
],
fields: vec![]
})
);
assert_eq!(
databricks_and_generic()
.verified_only_select("SELECT STRUCT(1 AS one, 'foo' AS foo, false)")
.projection[0],
SelectItem::UnnamedExpr(Expr::Struct {
values: vec![
Expr::Named {
expr: Expr::Value(number("1")).into(),
name: Ident::new("one")
},
Expr::Named {
expr: Expr::Value(Value::SingleQuotedString("foo".to_string())).into(),
name: Ident::new("foo")
},
Expr::Value(Value::Boolean(false))
],
fields: vec![]
})
);
}