This is an automated email from the ASF dual-hosted git repository.
iffyio pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-sqlparser-rs.git
The following commit(s) were added to refs/heads/main by this push:
new e406422b Add support for cluster by expressions (#1883)
e406422b is described below
commit e406422bacb6a8d1a09f053faaa1f9a063dc0f40
Author: Artem Osipov <[email protected]>
AuthorDate: Mon Jun 16 13:33:16 2025 +0300
Add support for cluster by expressions (#1883)
Co-authored-by: osipovartem <[email protected]>
---
src/ast/dml.rs | 4 +++-
src/ast/helpers/stmt_create_table.rs | 6 +++---
src/dialect/snowflake.rs | 2 +-
src/parser/mod.rs | 2 +-
tests/sqlparser_bigquery.rs | 4 ++--
tests/sqlparser_snowflake.rs | 26 +++++++++++++++++++++-----
6 files changed, 31 insertions(+), 13 deletions(-)
diff --git a/src/ast/dml.rs b/src/ast/dml.rs
index da82a4ed..292650c8 100644
--- a/src/ast/dml.rs
+++ b/src/ast/dml.rs
@@ -175,7 +175,9 @@ pub struct CreateTable {
pub partition_by: Option<Box<Expr>>,
/// BigQuery: Table clustering column list.
///
<https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#table_option_list>
- pub cluster_by: Option<WrappedCollection<Vec<Ident>>>,
+ /// Snowflake: Table clustering list which contains base column,
expressions on base columns.
+ ///
<https://docs.snowflake.com/en/user-guide/tables-clustering-keys#defining-a-clustering-key-for-a-table>
+ pub cluster_by: Option<WrappedCollection<Vec<Expr>>>,
/// Hive: Table clustering column list.
///
<https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL#LanguageManualDDL-CreateTable>
pub clustered_by: Option<ClusteredBy>,
diff --git a/src/ast/helpers/stmt_create_table.rs
b/src/ast/helpers/stmt_create_table.rs
index 542d30ea..d66a869b 100644
--- a/src/ast/helpers/stmt_create_table.rs
+++ b/src/ast/helpers/stmt_create_table.rs
@@ -90,7 +90,7 @@ pub struct CreateTableBuilder {
pub primary_key: Option<Box<Expr>>,
pub order_by: Option<OneOrManyWithParens<Expr>>,
pub partition_by: Option<Box<Expr>>,
- pub cluster_by: Option<WrappedCollection<Vec<Ident>>>,
+ pub cluster_by: Option<WrappedCollection<Vec<Expr>>>,
pub clustered_by: Option<ClusteredBy>,
pub inherits: Option<Vec<ObjectName>>,
pub strict: bool,
@@ -279,7 +279,7 @@ impl CreateTableBuilder {
self
}
- pub fn cluster_by(mut self, cluster_by:
Option<WrappedCollection<Vec<Ident>>>) -> Self {
+ pub fn cluster_by(mut self, cluster_by:
Option<WrappedCollection<Vec<Expr>>>) -> Self {
self.cluster_by = cluster_by;
self
}
@@ -542,7 +542,7 @@ impl TryFrom<Statement> for CreateTableBuilder {
#[derive(Default)]
pub(crate) struct CreateTableConfiguration {
pub partition_by: Option<Box<Expr>>,
- pub cluster_by: Option<WrappedCollection<Vec<Ident>>>,
+ pub cluster_by: Option<WrappedCollection<Vec<Expr>>>,
pub inherits: Option<Vec<ObjectName>>,
pub table_options: CreateTableOptions,
}
diff --git a/src/dialect/snowflake.rs b/src/dialect/snowflake.rs
index 990e2ea2..ea0b94a6 100644
--- a/src/dialect/snowflake.rs
+++ b/src/dialect/snowflake.rs
@@ -453,7 +453,7 @@ pub fn parse_create_table(
parser.expect_keyword_is(Keyword::BY)?;
parser.expect_token(&Token::LParen)?;
let cluster_by = Some(WrappedCollection::Parentheses(
- parser.parse_comma_separated(|p|
p.parse_identifier())?,
+ parser.parse_comma_separated(|p| p.parse_expr())?,
));
parser.expect_token(&Token::RParen)?;
diff --git a/src/parser/mod.rs b/src/parser/mod.rs
index 2c208e2e..73cc3e0e 100644
--- a/src/parser/mod.rs
+++ b/src/parser/mod.rs
@@ -7316,7 +7316,7 @@ impl<'a> Parser<'a> {
if dialect_of!(self is BigQueryDialect | GenericDialect) {
if self.parse_keywords(&[Keyword::CLUSTER, Keyword::BY]) {
cluster_by = Some(WrappedCollection::NoWrapping(
- self.parse_comma_separated(|p| p.parse_identifier())?,
+ self.parse_comma_separated(|p| p.parse_expr())?,
));
};
diff --git a/tests/sqlparser_bigquery.rs b/tests/sqlparser_bigquery.rs
index b64f190f..6a303577 100644
--- a/tests/sqlparser_bigquery.rs
+++ b/tests/sqlparser_bigquery.rs
@@ -536,8 +536,8 @@ fn parse_create_table_with_options() {
(
Some(Box::new(Expr::Identifier(Ident::new("_PARTITIONDATE")))),
Some(WrappedCollection::NoWrapping(vec![
- Ident::new("userid"),
- Ident::new("age"),
+ Expr::Identifier(Ident::new("userid")),
+ Expr::Identifier(Ident::new("age")),
])),
CreateTableOptions::Options(vec![
SqlOption::KeyValue {
diff --git a/tests/sqlparser_snowflake.rs b/tests/sqlparser_snowflake.rs
index 7a164c24..7d734ca2 100644
--- a/tests/sqlparser_snowflake.rs
+++ b/tests/sqlparser_snowflake.rs
@@ -471,15 +471,31 @@ fn test_snowflake_create_table_if_not_exists() {
#[test]
fn test_snowflake_create_table_cluster_by() {
- match snowflake().verified_stmt("CREATE TABLE my_table (a INT) CLUSTER BY
(a, b)") {
+ match snowflake().verified_stmt("CREATE TABLE my_table (a INT) CLUSTER BY
(a, b, my_func(c))") {
Statement::CreateTable(CreateTable {
name, cluster_by, ..
}) => {
assert_eq!("my_table", name.to_string());
assert_eq!(
Some(WrappedCollection::Parentheses(vec![
- Ident::new("a"),
- Ident::new("b"),
+ Expr::Identifier(Ident::new("a")),
+ Expr::Identifier(Ident::new("b")),
+ Expr::Function(Function {
+ name: ObjectName::from(vec![Ident::new("my_func")]),
+ uses_odbc_syntax: false,
+ parameters: FunctionArguments::None,
+ args: FunctionArguments::List(FunctionArgumentList {
+ args:
vec![FunctionArg::Unnamed(FunctionArgExpr::Expr(
+ Expr::Identifier(Ident::new("c"))
+ ))],
+ duplicate_treatment: None,
+ clauses: vec![],
+ }),
+ filter: None,
+ null_treatment: None,
+ over: None,
+ within_group: vec![],
+ }),
])),
cluster_by
)
@@ -903,8 +919,8 @@ fn test_snowflake_create_iceberg_table_all_options() {
assert_eq!("my_table", name.to_string());
assert_eq!(
Some(WrappedCollection::Parentheses(vec![
- Ident::new("a"),
- Ident::new("b"),
+ Expr::Identifier(Ident::new("a")),
+ Expr::Identifier(Ident::new("b")),
])),
cluster_by
);
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
