This is an automated email from the ASF dual-hosted git repository.
alamb pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 17b5e71707 Fix regression list Type Coercion List with inner type
struct which has large/view types (#14385)
17b5e71707 is described below
commit 17b5e71707326a25601bd58b3ad91a745b8a3e10
Author: Andrew Lamb <[email protected]>
AuthorDate: Mon Feb 3 12:22:15 2025 -0500
Fix regression list Type Coercion List with inner type struct which has
large/view types (#14385)
* Test for coercing inner structs
* Fix but, update tests
* Update tests
---
datafusion/expr-common/src/type_coercion/binary.rs | 15 +++---
datafusion/sqllogictest/test_files/case.slt | 53 ++++++++++++++++++++++
datafusion/sqllogictest/test_files/struct.slt | 8 ++--
3 files changed, 65 insertions(+), 11 deletions(-)
diff --git a/datafusion/expr-common/src/type_coercion/binary.rs
b/datafusion/expr-common/src/type_coercion/binary.rs
index ba87a53e5f..3be35490a4 100644
--- a/datafusion/expr-common/src/type_coercion/binary.rs
+++ b/datafusion/expr-common/src/type_coercion/binary.rs
@@ -566,18 +566,19 @@ fn type_union_resolution_coercion(
None
}
- let types = lhs
+ let coerced_types = lhs
.iter()
.map(|lhs_field| search_corresponding_coerced_type(lhs_field,
rhs))
.collect::<Option<Vec<_>>>()?;
- let fields = types
+ // preserve the field name and nullability
+ let orig_fields = std::iter::zip(lhs.iter(), rhs.iter());
+
+ let fields: Vec<FieldRef> = coerced_types
.into_iter()
- .enumerate()
- .map(|(i, datatype)| {
- Arc::new(Field::new(format!("c{i}"), datatype, true))
- })
- .collect::<Vec<FieldRef>>();
+ .zip(orig_fields)
+ .map(|(datatype, (lhs, rhs))| coerce_fields(datatype, lhs,
rhs))
+ .collect();
Some(DataType::Struct(fields.into()))
}
_ => {
diff --git a/datafusion/sqllogictest/test_files/case.slt
b/datafusion/sqllogictest/test_files/case.slt
index 46e9c86c75..8e470fe988 100644
--- a/datafusion/sqllogictest/test_files/case.slt
+++ b/datafusion/sqllogictest/test_files/case.slt
@@ -416,5 +416,58 @@ SELECT
end
FROM t;
+statement ok
+drop table t
+
+# Fix coercion of lists of structs
+# https://github.com/apache/datafusion/issues/14154
+
+statement ok
+create or replace table t as values
+(
+ 100, -- column1 int (so the case
isn't constant folded)
+ [{ 'foo': arrow_cast('baz', 'Utf8View') }], -- column2 has List of Struct w/
Utf8View
+ [{ 'foo': 'bar' }], -- column3 has List of Struct w/
Utf8
+ [{ 'foo': 'blarg' }] -- column4 has List of Struct w/
Utf8
+);
+
+# This case forces all branches to be coerced to the same type
+query ?
+SELECT
+ case
+ when column1 > 0 then column2
+ when column1 < 0 then column3
+ else column4
+ end
+FROM t;
+----
+[{foo: baz}]
+
+# different orders of the branches
+query ?
+SELECT
+ case
+ when column1 > 0 then column3 -- NB different order
+ when column1 < 0 then column4
+ else column2
+ end
+FROM t;
+----
+[{foo: bar}]
+
+# different orders of the branches
+query ?
+SELECT
+ case
+ when column1 > 0 then column4 -- NB different order
+ when column1 < 0 then column2
+ else column3
+ end
+FROM t;
+----
+[{foo: blarg}]
+
+
+
statement ok
drop table t
diff --git a/datafusion/sqllogictest/test_files/struct.slt
b/datafusion/sqllogictest/test_files/struct.slt
index d671798b7d..0afe39de17 100644
--- a/datafusion/sqllogictest/test_files/struct.slt
+++ b/datafusion/sqllogictest/test_files/struct.slt
@@ -459,14 +459,14 @@ create table t as values({r: 'a', c: 1}), ({r: 'b', c:
2.3});
query ?
select * from t;
----
-{c0: a, c1: 1.0}
-{c0: b, c1: 2.3}
+{r: a, c: 1.0}
+{r: b, c: 2.3}
query T
select arrow_typeof(column1) from t;
----
-Struct([Field { name: "c0", data_type: Utf8, nullable: true, dict_id: 0,
dict_is_ordered: false, metadata: {} }, Field { name: "c1", data_type: Float64,
nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
-Struct([Field { name: "c0", data_type: Utf8, nullable: true, dict_id: 0,
dict_is_ordered: false, metadata: {} }, Field { name: "c1", data_type: Float64,
nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
+Struct([Field { name: "r", data_type: Utf8, nullable: true, dict_id: 0,
dict_is_ordered: false, metadata: {} }, Field { name: "c", data_type: Float64,
nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
+Struct([Field { name: "r", data_type: Utf8, nullable: true, dict_id: 0,
dict_is_ordered: false, metadata: {} }, Field { name: "c", data_type: Float64,
nullable: true, dict_id: 0, dict_is_ordered: false, metadata: {} }])
statement ok
drop table t;
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
