Support DuckDB struct syntax and support list of struct syntax (#1372)

Signed-off-by: jayzhan211 <jayzhan211@gmail.com>
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Co-authored-by: Ifeanyi Ubah <ify1992@yahoo.com>
This commit is contained in:
Jay Zhan 2024-08-15 21:02:42 +08:00 committed by GitHub
parent fab834dca3
commit 8c4d30bb6d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 209 additions and 33 deletions

View file

@ -302,7 +302,7 @@ pub enum DataType {
///
/// [hive]: https://docs.cloudera.com/cdw-runtime/cloud/impala-sql-reference/topics/impala-struct.html
/// [bigquery]: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#struct_type
Struct(Vec<StructField>),
Struct(Vec<StructField>, StructBracketKind),
/// Union
///
/// [duckdb]: https://duckdb.org/docs/sql/data_types/union.html
@ -517,9 +517,16 @@ impl fmt::Display for DataType {
}
write!(f, ")")
}
DataType::Struct(fields) => {
DataType::Struct(fields, bracket) => {
if !fields.is_empty() {
write!(f, "STRUCT<{}>", display_comma_separated(fields))
match bracket {
StructBracketKind::Parentheses => {
write!(f, "STRUCT({})", display_comma_separated(fields))
}
StructBracketKind::AngleBrackets => {
write!(f, "STRUCT<{}>", display_comma_separated(fields))
}
}
} else {
write!(f, "STRUCT")
}
@ -618,6 +625,17 @@ fn format_clickhouse_datetime_precision_and_timezone(
Ok(())
}
/// Type of brackets used for `STRUCT` literals.
#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum StructBracketKind {
/// Example: `STRUCT(a INT, b STRING)`
Parentheses,
/// Example: `STRUCT<a INT, b STRING>`
AngleBrackets,
}
/// Timestamp and Time data types information about TimeZone formatting.
///
/// This is more related to a display information than real differences between each variant. To

View file

@ -28,7 +28,8 @@ use serde::{Deserialize, Serialize};
use sqlparser_derive::{Visit, VisitMut};
pub use self::data_type::{
ArrayElemTypeDef, CharLengthUnits, CharacterLength, DataType, ExactNumberInfo, TimezoneInfo,
ArrayElemTypeDef, CharLengthUnits, CharacterLength, DataType, ExactNumberInfo,
StructBracketKind, TimezoneInfo,
};
pub use self::dcl::{AlterRoleOperation, ResetConfig, RoleOption, SetConfigValue};
pub use self::ddl::{

View file

@ -2266,6 +2266,23 @@ impl<'a> Parser<'a> {
))
}
/// Duckdb Struct Data Type <https://duckdb.org/docs/sql/data_types/struct.html#retrieving-from-structs>
fn parse_duckdb_struct_type_def(&mut self) -> Result<Vec<StructField>, ParserError> {
self.expect_keyword(Keyword::STRUCT)?;
self.expect_token(&Token::LParen)?;
let struct_body = self.parse_comma_separated(|parser| {
let field_name = parser.parse_identifier(false)?;
let field_type = parser.parse_data_type()?;
Ok(StructField {
field_name: Some(field_name),
field_type,
})
});
self.expect_token(&Token::RParen)?;
struct_body
}
/// Parse a field definition in a [struct] or [tuple].
/// Syntax:
///
@ -7495,12 +7512,20 @@ impl<'a> Parser<'a> {
))))
}
}
Keyword::STRUCT if dialect_of!(self is DuckDbDialect) => {
self.prev_token();
let field_defs = self.parse_duckdb_struct_type_def()?;
Ok(DataType::Struct(field_defs, StructBracketKind::Parentheses))
}
Keyword::STRUCT if dialect_of!(self is BigQueryDialect | GenericDialect) => {
self.prev_token();
let (field_defs, _trailing_bracket) =
self.parse_struct_type_def(Self::parse_struct_field_def)?;
trailing_bracket = _trailing_bracket;
Ok(DataType::Struct(field_defs))
Ok(DataType::Struct(
field_defs,
StructBracketKind::AngleBrackets,
))
}
Keyword::UNION if dialect_of!(self is DuckDbDialect | GenericDialect) => {
self.prev_token();