Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
74 changes: 58 additions & 16 deletions datafusion/functions/src/string/common.rs
Original file line number Diff line number Diff line change
Expand Up @@ -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, StringBuilder, StringViewArray, StringViewBuilder, new_null_array,
};
use arrow::buffer::{Buffer, ScalarBuffer};
use arrow::datatypes::DataType;
Expand Down Expand Up @@ -332,17 +332,34 @@ fn string_trim<T: OffsetSizeTrait, Tr: Trimmer>(args: &[ArrayRef]) -> Result<Arr
}

pub(crate) fn to_lower(args: &[ColumnarValue], name: &str) -> Result<ColumnarValue> {
case_conversion(args, |string| string.to_lowercase(), name)
case_conversion(
args,
|string| string.to_lowercase(),
name,
Utf8ViewOutput::Utf8,
)
}

pub(crate) fn to_upper(args: &[ColumnarValue], name: &str) -> Result<ColumnarValue> {
case_conversion(args, |string| string.to_uppercase(), name)
case_conversion(
args,
|string| string.to_uppercase(),
name,
Utf8ViewOutput::Utf8View,
)
}

#[derive(Debug, Clone, Copy)]
enum Utf8ViewOutput {
Utf8,
Utf8View,
}

fn case_conversion<'a, F>(
args: &'a [ColumnarValue],
op: F,
name: &str,
utf8view_output: Utf8ViewOutput,
) -> Result<ColumnarValue>
where
F: Fn(&'a str) -> String,
Expand All @@ -358,20 +375,38 @@ 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(),
);

for str in string_array.iter() {
if let Some(str) = str {
string_builder.append_value(op(str));
} else {
string_builder.append_null();
match utf8view_output {
Utf8ViewOutput::Utf8 => {
let mut string_builder = StringBuilder::with_capacity(
string_array.len(),
string_array.get_array_memory_size(),
);

for str in string_array.iter() {
if let Some(str) = str {
string_builder.append_value(op(str));
} else {
string_builder.append_null();
}
}

Ok(ColumnarValue::Array(Arc::new(string_builder.finish())))
}
Utf8ViewOutput::Utf8View => {
let mut string_builder =
StringViewBuilder::with_capacity(string_array.len());

for str in string_array.iter() {
if let Some(str) = str {
string_builder.append_value(op(str));
} else {
string_builder.append_null();
}
}

Ok(ColumnarValue::Array(Arc::new(string_builder.finish())))
}
}

Ok(ColumnarValue::Array(Arc::new(string_builder.finish())))
}
other => exec_err!("Unsupported data type {other:?} for function {name}"),
},
Expand All @@ -386,7 +421,14 @@ where
}
ScalarValue::Utf8View(a) => {
let result = a.as_ref().map(|x| op(x));
Ok(ColumnarValue::Scalar(ScalarValue::Utf8(result)))
match utf8view_output {
Utf8ViewOutput::Utf8 => {
Ok(ColumnarValue::Scalar(ScalarValue::Utf8(result)))
}
Utf8ViewOutput::Utf8View => {
Ok(ColumnarValue::Scalar(ScalarValue::Utf8View(result)))
}
}
}
other => exec_err!("Unsupported data type {other:?} for function {name}"),
},
Expand Down
28 changes: 24 additions & 4 deletions datafusion/functions/src/string/upper.rs
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,11 @@ impl ScalarUDFImpl for UpperFunc {
}

fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
utf8_to_str_type(&arg_types[0], "upper")
if arg_types[0] == DataType::Utf8View {
Ok(DataType::Utf8View)
} else {
utf8_to_str_type(&arg_types[0], "upper")
}
}

fn invoke_with_args(&self, args: ScalarFunctionArgs) -> Result<ColumnarValue> {
Expand All @@ -96,8 +100,7 @@ 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;
Expand All @@ -110,7 +113,7 @@ 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()),
};

Expand Down Expand Up @@ -196,4 +199,21 @@ 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)
}
}
15 changes: 15 additions & 0 deletions datafusion/sqllogictest/test_files/functions.slt
Original file line number Diff line number Diff line change
Expand Up @@ -445,6 +445,21 @@ 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 btrim(' foo ')
----
Expand Down