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/arrow-datafusion.git
The following commit(s) were added to refs/heads/main by this push:
new 8326f577bc upper and lower functions only work correctly on ascii
character #9053 (#9054)
8326f577bc is described below
commit 8326f577bc3331d73da3663bf33fc4438ed46a0e
Author: Bruce Ritchie <[email protected]>
AuthorDate: Mon Jan 29 15:36:19 2024 -0500
upper and lower functions only work correctly on ascii character #9053
(#9054)
---
datafusion/physical-expr/src/string_expressions.rs | 4 ++--
datafusion/sqllogictest/test_files/functions.slt | 22 +++++++++++++++++++++-
2 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/datafusion/physical-expr/src/string_expressions.rs
b/datafusion/physical-expr/src/string_expressions.rs
index d5344773cf..34a436ebe3 100644
--- a/datafusion/physical-expr/src/string_expressions.rs
+++ b/datafusion/physical-expr/src/string_expressions.rs
@@ -343,7 +343,7 @@ pub fn instr<T: OffsetSizeTrait>(args: &[ArrayRef]) ->
Result<ArrayRef> {
/// Converts the string to all lower case.
/// lower('TOM') = 'tom'
pub fn lower(args: &[ColumnarValue]) -> Result<ColumnarValue> {
- handle(args, |string| string.to_ascii_lowercase(), "lower")
+ handle(args, |string| string.to_lowercase(), "lower")
}
enum TrimType {
@@ -555,7 +555,7 @@ where
/// Converts the string to all upper case.
/// upper('tom') = 'TOM'
pub fn upper(args: &[ColumnarValue]) -> Result<ColumnarValue> {
- handle(args, |string| string.to_ascii_uppercase(), "upper")
+ handle(args, |string| string.to_uppercase(), "upper")
}
/// Prints random (v4) uuid values per row
diff --git a/datafusion/sqllogictest/test_files/functions.slt
b/datafusion/sqllogictest/test_files/functions.slt
index d3f81cc61e..7a4d7ef197 100644
--- a/datafusion/sqllogictest/test_files/functions.slt
+++ b/datafusion/sqllogictest/test_files/functions.slt
@@ -623,10 +623,20 @@ SELECT upper('foo')
FOO
query T
-select upper(arrow_cast('foo', 'Dictionary(Int32, Utf8)'))
+SELECT upper(arrow_cast('foo', 'Dictionary(Int32, Utf8)'))
----
FOO
+query T
+SELECT upper('árvore ação αβγ')
+----
+ÁRVORE AÇÃO ΑΒΓ
+
+query T
+SELECT upper(arrow_cast('árvore ação αβγ', 'Dictionary(Int32, Utf8)'))
+----
+ÁRVORE AÇÃO ΑΒΓ
+
query T
SELECT btrim(' foo ')
----
@@ -672,6 +682,16 @@ SELECT lower(arrow_cast('FOObar', 'Dictionary(Int32,
Utf8)'))
----
foobar
+query T
+SELECT lower('ÁRVORE AÇÃO ΑΒΓ')
+----
+árvore ação αβγ
+
+query T
+SELECT lower(arrow_cast('ÁRVORE AÇÃO ΑΒΓ', 'Dictionary(Int32, Utf8)'))
+----
+árvore ação αβγ
+
query T
SELECT ltrim(' foo')
----
