This is an automated email from the ASF dual-hosted git repository.
github-bot 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 9b3d6a4909 Make lower and upper emit Utf8View for Utf8View input
(#20616)
9b3d6a4909 is described below
commit 9b3d6a4909e47b4e9edba6bef269452d231c13b0
Author: Kumar Ujjawal <[email protected]>
AuthorDate: Tue Mar 10 02:19:05 2026 +0530
Make lower and upper emit Utf8View for Utf8View input (#20616)
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax. For example
`Closes #123` indicates that this PR will close issue #123.
-->
- Part of https://github.com/apache/datafusion/issues/20585
## Rationale for this change
String UDFs should preserve string representation where feasible. lower
and upper previously accepted Utf8View input but emitted Utf8, causing
an unnecessary type downgrade. This aligns both with the expected
behavior of returning the same string type as its primary input.
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
## What changes are included in this PR?
- Updated lower and upper return type inference to emit Utf8View when
input is Utf8View
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
## Are these changes tested?
Yes
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
-->
## Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
---
datafusion/functions/src/string/common.rs | 10 ++---
datafusion/functions/src/string/lower.rs | 25 +++++++++---
datafusion/functions/src/string/upper.rs | 25 +++++++++---
datafusion/sqllogictest/test_files/functions.slt | 50 ++++++++++++++++++++++++
4 files changed, 94 insertions(+), 16 deletions(-)
diff --git a/datafusion/functions/src/string/common.rs
b/datafusion/functions/src/string/common.rs
index 77af82e25c..cc97c1b2c1 100644
--- a/datafusion/functions/src/string/common.rs
+++ b/datafusion/functions/src/string/common.rs
@@ -22,7 +22,7 @@ use std::sync::Arc;
use crate::strings::make_and_append_view;
use arrow::array::{
Array, ArrayRef, GenericStringArray, GenericStringBuilder,
NullBufferBuilder,
- OffsetSizeTrait, StringBuilder, StringViewArray, new_null_array,
+ OffsetSizeTrait, StringViewArray, StringViewBuilder, new_null_array,
};
use arrow::buffer::{Buffer, ScalarBuffer};
use arrow::datatypes::DataType;
@@ -358,10 +358,8 @@ where
>(array, op)?)),
DataType::Utf8View => {
let string_array = as_string_view_array(array)?;
- let mut string_builder = StringBuilder::with_capacity(
- string_array.len(),
- string_array.get_array_memory_size(),
- );
+ let mut string_builder =
+ StringViewBuilder::with_capacity(string_array.len());
for str in string_array.iter() {
if let Some(str) = str {
@@ -386,7 +384,7 @@ where
}
ScalarValue::Utf8View(a) => {
let result = a.as_ref().map(|x| op(x));
- Ok(ColumnarValue::Scalar(ScalarValue::Utf8(result)))
+ Ok(ColumnarValue::Scalar(ScalarValue::Utf8View(result)))
}
other => exec_err!("Unsupported data type {other:?} for function
{name}"),
},
diff --git a/datafusion/functions/src/string/lower.rs
b/datafusion/functions/src/string/lower.rs
index 3750d3d290..d91e4595c5 100644
--- a/datafusion/functions/src/string/lower.rs
+++ b/datafusion/functions/src/string/lower.rs
@@ -19,7 +19,6 @@ use arrow::datatypes::DataType;
use std::any::Any;
use crate::string::common::to_lower;
-use crate::utils::utf8_to_str_type;
use datafusion_common::Result;
use datafusion_common::types::logical_string;
use datafusion_expr::{
@@ -82,7 +81,7 @@ impl ScalarUDFImpl for LowerFunc {
}
fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
- utf8_to_str_type(&arg_types[0], "lower")
+ Ok(arg_types[0].clone())
}
fn invoke_with_args(&self, args: ScalarFunctionArgs) ->
Result<ColumnarValue> {
@@ -97,8 +96,7 @@ impl ScalarUDFImpl for LowerFunc {
#[cfg(test)]
mod tests {
use super::*;
- use arrow::array::{Array, ArrayRef, StringArray};
- use arrow::datatypes::DataType::Utf8;
+ use arrow::array::{Array, ArrayRef, StringArray, StringViewArray};
use arrow::datatypes::Field;
use datafusion_common::config::ConfigOptions;
use std::sync::Arc;
@@ -111,7 +109,7 @@ mod tests {
number_rows: input.len(),
args: vec![ColumnarValue::Array(input)],
arg_fields,
- return_field: Field::new("f", Utf8, true).into(),
+ return_field: Field::new("f", expected.data_type().clone(),
true).into(),
config_options: Arc::new(ConfigOptions::default()),
};
@@ -197,4 +195,21 @@ mod tests {
to_lower(input, expected)
}
+
+ #[test]
+ fn lower_utf8view() -> Result<()> {
+ let input = Arc::new(StringViewArray::from(vec![
+ Some("ARROW"),
+ None,
+ Some("TSCHÜSS"),
+ ])) as ArrayRef;
+
+ let expected = Arc::new(StringViewArray::from(vec![
+ Some("arrow"),
+ None,
+ Some("tschüss"),
+ ])) as ArrayRef;
+
+ to_lower(input, expected)
+ }
}
diff --git a/datafusion/functions/src/string/upper.rs
b/datafusion/functions/src/string/upper.rs
index a2a7db1848..80375f58c8 100644
--- a/datafusion/functions/src/string/upper.rs
+++ b/datafusion/functions/src/string/upper.rs
@@ -16,7 +16,6 @@
// under the License.
use crate::string::common::to_upper;
-use crate::utils::utf8_to_str_type;
use arrow::datatypes::DataType;
use datafusion_common::Result;
use datafusion_common::types::logical_string;
@@ -81,7 +80,7 @@ impl ScalarUDFImpl for UpperFunc {
}
fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
- utf8_to_str_type(&arg_types[0], "upper")
+ Ok(arg_types[0].clone())
}
fn invoke_with_args(&self, args: ScalarFunctionArgs) ->
Result<ColumnarValue> {
@@ -96,8 +95,7 @@ impl ScalarUDFImpl for UpperFunc {
#[cfg(test)]
mod tests {
use super::*;
- use arrow::array::{Array, ArrayRef, StringArray};
- use arrow::datatypes::DataType::Utf8;
+ use arrow::array::{Array, ArrayRef, StringArray, StringViewArray};
use arrow::datatypes::Field;
use datafusion_common::config::ConfigOptions;
use std::sync::Arc;
@@ -110,7 +108,7 @@ mod tests {
number_rows: input.len(),
args: vec![ColumnarValue::Array(input)],
arg_fields: vec![arg_field],
- return_field: Field::new("f", Utf8, true).into(),
+ return_field: Field::new("f", expected.data_type().clone(),
true).into(),
config_options: Arc::new(ConfigOptions::default()),
};
@@ -196,4 +194,21 @@ mod tests {
to_upper(input, expected)
}
+
+ #[test]
+ fn upper_utf8view() -> Result<()> {
+ let input = Arc::new(StringViewArray::from(vec![
+ Some("arrow"),
+ None,
+ Some("tschüß"),
+ ])) as ArrayRef;
+
+ let expected = Arc::new(StringViewArray::from(vec![
+ Some("ARROW"),
+ None,
+ Some("TSCHÜSS"),
+ ])) as ArrayRef;
+
+ to_upper(input, expected)
+ }
}
diff --git a/datafusion/sqllogictest/test_files/functions.slt
b/datafusion/sqllogictest/test_files/functions.slt
index fa852e98ac..ee11dc973b 100644
--- a/datafusion/sqllogictest/test_files/functions.slt
+++ b/datafusion/sqllogictest/test_files/functions.slt
@@ -435,6 +435,11 @@ SELECT upper(arrow_cast('foo', 'Dictionary(Int32, Utf8)'))
----
FOO
+query T
+SELECT upper(arrow_cast(arrow_cast('foo', 'Dictionary(Int32, Utf8)'),
'Dictionary(Int32, Utf8View)'))
+----
+FOO
+
query T
SELECT upper('árvore ação αβγ')
----
@@ -445,6 +450,26 @@ SELECT upper(arrow_cast('árvore ação αβγ',
'Dictionary(Int32, Utf8)'))
----
ÁRVORE AÇÃO ΑΒΓ
+query T
+SELECT arrow_typeof(upper('foo'))
+----
+Utf8
+
+query T
+SELECT arrow_typeof(upper(arrow_cast('foo', 'LargeUtf8')))
+----
+LargeUtf8
+
+query T
+SELECT arrow_typeof(upper(arrow_cast('foo', 'Utf8View')))
+----
+Utf8View
+
+query T
+SELECT arrow_typeof(upper(arrow_cast(arrow_cast('foo', 'Dictionary(Int32,
Utf8)'), 'Dictionary(Int32, Utf8View)')))
+----
+Utf8View
+
query T
SELECT btrim(' foo ')
----
@@ -490,6 +515,11 @@ SELECT lower(arrow_cast('FOObar', 'Dictionary(Int32,
Utf8)'))
----
foobar
+query T
+SELECT lower(arrow_cast(arrow_cast('FOObar', 'Dictionary(Int32, Utf8)'),
'Dictionary(Int32, Utf8View)'))
+----
+foobar
+
query T
SELECT lower('ÁRVORE AÇÃO ΑΒΓ')
----
@@ -500,6 +530,26 @@ SELECT lower(arrow_cast('ÁRVORE AÇÃO ΑΒΓ',
'Dictionary(Int32, Utf8)'))
----
árvore ação αβγ
+query T
+SELECT arrow_typeof(lower('FOObar'))
+----
+Utf8
+
+query T
+SELECT arrow_typeof(lower(arrow_cast('FOObar', 'LargeUtf8')))
+----
+LargeUtf8
+
+query T
+SELECT arrow_typeof(lower(arrow_cast('FOObar', 'Utf8View')))
+----
+Utf8View
+
+query T
+SELECT arrow_typeof(lower(arrow_cast(arrow_cast('FOObar', 'Dictionary(Int32,
Utf8)'), 'Dictionary(Int32, Utf8View)')))
+----
+Utf8View
+
query T
SELECT ltrim(' foo')
----
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
