neilconway commented on code in PR #26377: URL: https://github.com/apache/datafusion/pull/26377#discussion_r4285714513
########## datafusion/sqllogictest/test_files/functions.slt: ########## @@ -486,6 +486,72 @@ BAR Dictionary(Int32, Utf8) statement ok DROP TABLE upper_dictionary_test +# The array is not all ASCII, so each row is converted on its own: ASCII rows, +# and rows with non-ASCII characters at the start, middle and end, including +# values longer than the 12 bytes a Utf8View can store inline. +statement ok +CREATE TABLE upper_mixed_test AS +SELECT column1 AS id, + arrow_cast(column2, 'Utf8') AS utf8, + arrow_cast(column2, 'LargeUtf8') AS large_utf8, + arrow_cast(column2, 'Utf8View') AS utf8view +FROM (VALUES +(1, 'datafusion'), +(2, 'a long ascii-only value'), +(3, ''), +(4, NULL), +(5, 'éa'), +(6, 'über alles, then ascii'), +(7, 'straße'), +(8, 'a long value ending in ß'), +(9, 'ⱦx'), +(10, '农历新年 new year')); + +query T +SELECT upper(utf8) FROM upper_mixed_test ORDER BY id Review Comment: Good idea; done. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
