Skip to content

Only parse FROM identifier in CTE if using Hive #2241

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
Viicos wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Only parse FROM identifier in CTE if using Hive #2241

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
2 changes: 1 addition & 1 deletion src/parser/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13958,7 +13958,7 @@ impl<'a> Parser<'a> {
closing_paren_token: closing_paren_token.into(),
}
};
if self.parse_keyword(Keyword::FROM) {
if dialect_of!(self is HiveDialect) && self.parse_keyword(Keyword::FROM) {
Copy link
Contributor

@iffyio iffyio Mar 2, 2026

Choose a reason for hiding this comment

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

not sure I follow the intent of the PR, is it rather that hive should support supports_from_first_select (i.e. what's the difference in behavior from hive vs other dialects)?

Copy link
Author

@Viicos Viicos Mar 2, 2026

Choose a reason for hiding this comment

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

I gave more context in the issue I created; I'm not knowledgeable enough about Hive to understand if it should support FROM first selects, and it is unclear (see also #235 (comment)) why this FROM token parsing was introduced here. Maybe the intent was indeed to support FROM first selects, but I'd rather not break things here so that's why I only gated this FROM parsing for Hive.

cte.from = Some(self.parse_identifier()?);
}
Ok(cte)
Expand Down
123 changes: 123 additions & 0 deletions tests/sqlparser_common.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16073,6 +16073,129 @@ fn test_select_from_first() {
}
}

#[test]
fn test_select_from_first_with_cte() {
let dialects = all_dialects_where(|d| d.supports_from_first_select());
let q = "WITH test AS (FROM t SELECT a) FROM test SELECT 1";

let ast = dialects.verified_query(q);

let expected = Query {
with: Some(With {
with_token: AttachedToken::empty(),
recursive: false,
cte_tables: vec![Cte {
alias: TableAlias {
explicit: false,
name: Ident {
value: "test".to_string(),
quote_style: None,
span: Span::empty(),
},
columns: vec![],
},
query: Box::new(Query {
with: None,
body: Box::new(SetExpr::Select(Box::new(Select {
select_token: AttachedToken::empty(),
optimizer_hints: vec![],
distinct: None,
select_modifiers: None,
top: None,
projection: vec![SelectItem::UnnamedExpr(Expr::Identifier(Ident {
value: "a".to_string(),
quote_style: None,
span: Span::empty(),
}))],
exclude: None,
top_before_distinct: false,
into: None,
from: vec![TableWithJoins {
relation: table_from_name(ObjectName::from(vec![Ident {
value: "t".to_string(),
quote_style: None,
span: Span::empty(),
}])),
joins: vec![],
}],
lateral_views: vec![],
prewhere: None,
selection: None,
group_by: GroupByExpr::Expressions(vec![], vec![]),
cluster_by: vec![],
distribute_by: vec![],
sort_by: vec![],
having: None,
named_window: vec![],
window_before_qualify: false,
qualify: None,
value_table_mode: None,
connect_by: vec![],
flavor: SelectFlavor::FromFirst,
}))),
order_by: None,
limit_clause: None,
fetch: None,
locks: vec![],
for_clause: None,
settings: None,
format_clause: None,
pipe_operators: vec![],
}),
from: None,
materialized: None,
closing_paren_token: AttachedToken::empty(),
}],
}),
body: Box::new(SetExpr::Select(Box::new(Select {
select_token: AttachedToken::empty(),
optimizer_hints: vec![],
distinct: None,
select_modifiers: None,
top: None,
projection: vec![SelectItem::UnnamedExpr(Expr::Value(ValueWithSpan {
value: test_utils::number("1"),
span: Span::empty(),
}))],
exclude: None,
top_before_distinct: false,
into: None,
from: vec![TableWithJoins {
relation: table_from_name(ObjectName::from(vec![Ident {
value: "test".to_string(),
quote_style: None,
span: Span::empty(),
}])),
joins: vec![],
}],
lateral_views: vec![],
prewhere: None,
selection: None,
group_by: GroupByExpr::Expressions(vec![], vec![]),
cluster_by: vec![],
distribute_by: vec![],
sort_by: vec![],
having: None,
named_window: vec![],
window_before_qualify: false,
qualify: None,
value_table_mode: None,
connect_by: vec![],
flavor: SelectFlavor::FromFirst,
}))),
order_by: None,
limit_clause: None,
fetch: None,
locks: vec![],
for_clause: None,
settings: None,
format_clause: None,
pipe_operators: vec![],
};
assert_eq!(expected, ast);
assert_eq!(ast.to_string(), q);
}

#[test]
fn test_geometric_unary_operators() {
// Number of points in path or polygon
Expand Down