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.

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

Support explicit type and name during table creation #10273

Merged
merged 5 commits into from
Jun 14, 2024
Merged

Support explicit type and name during table creation #10273

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
ed7a7b9
temp cargo commit
duongcongtoai Apr 28, 2024
3a4c2b5
chore: update test
duongcongtoai Apr 28, 2024
c7cbf72
fmt
duongcongtoai Apr 28, 2024
60fae2b
update cli cargo lock
duongcongtoai May 1, 2024
6173106
Merge remote-tracking branch 'origin/main' into 10207-explicit-struct
duongcongtoai Jun 8, 2024
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
20 changes: 19 additions & 1 deletion datafusion/sql/src/planner.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,6 +439,25 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
}
SQLDataType::Bytea => Ok(DataType::Binary),
SQLDataType::Interval => Ok(DataType::Interval(IntervalUnit::MonthDayNano)),
SQLDataType::Struct(fields) => {
let fields = fields
.iter()
.enumerate()
.map(|(idx, field)| {
let data_type = self.convert_data_type(&field.field_type)?;
let field_name = match &field.field_name{
Some(ident) => ident.clone(),
None => Ident::new(format!("c{idx}"))
};
Ok(Arc::new(Field::new(
self.normalizer.normalize(field_name),
data_type,
true,
)))
})
.collect::<Result<Vec<_>>>()?;
Ok(DataType::Struct(Fields::from(fields)))
}
// Explicitly list all other types so that if sqlparser
// adds/changes the `SQLDataType` the compiler will tell us on upgrade
// and avoid bugs like https://github.com/apache/datafusion/issues/3059
Expand Down Expand Up @@ -472,7 +491,6 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
| SQLDataType::Bytes(_)
| SQLDataType::Int64
| SQLDataType::Float64
| SQLDataType::Struct(_)
| SQLDataType::JSONB
| SQLDataType::Unspecified
=> not_impl_err!(
Expand Down
27 changes: 27 additions & 0 deletions datafusion/sqllogictest/test_files/struct.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,33 @@ CREATE TABLE values(
(3, 3.3, 'c', NULL)
;


# named and named less struct fields
statement ok
CREATE TABLE struct_values (
Copy link
Contributor

Choose a reason for hiding this comment

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

nice!

s1 struct<INT>,
s2 struct<a INT,b VARCHAR>
) AS VALUES
(struct(1), struct(1, 'string1')),
(struct(2), struct(2, 'string2')),
(struct(3), struct(3, 'string3'))
;

query ??
select * from struct_values;
----
{c0: 1} {a: 1, b: string1}
{c0: 2} {a: 2, b: string2}
{c0: 3} {a: 3, b: string3}

query TT
select arrow_typeof(s1), arrow_typeof(s2) from struct_values;
----
Struct([Field { name: "c0", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }]) Struct([Field { name: "a", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }, Field { name: "b", data_type: Utf8, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
Struct([Field { name: "c0", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }]) Struct([Field { name: "a", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }, Field { name: "b", data_type: Utf8, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
Struct([Field { name: "c0", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }]) Struct([Field { name: "a", data_type: Int32, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }, Field { name: "b", data_type: Utf8, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])


# struct[i]
query IRT
select struct(1, 3.14, 'h')['c0'], struct(3, 2.55, 'b')['c1'], struct(2, 6.43, 'a')['c2'];
Expand Down