sunchao commented on code in PR #5364:
URL: https://github.com/apache/datafusion-comet/pull/5364#discussion_r3789854662
##########
native/spark-expr/src/datetime_funcs/to_time.rs:
##########
@@ -479,4 +482,153 @@ mod tests {
assert_eq!(string_to_time(" T12:30:45"), None);
assert_eq!(string_to_time(" T12:30"), None);
}
+
+ #[test]
+ fn test_spark_trim_all_control_bytes() {
+ let expected = string_to_time("12:30:45");
+
+ for byte in (0_u8..=0x20).chain(std::iter::once(0x7f)) {
+ let padding = char::from(byte);
+ for input in [
+ format!("{padding}12:30:45"),
+ format!("12:30:45{padding}"),
+ format!("{padding}12:30:45{padding}"),
+ ] {
+ assert_eq!(
+ string_to_time(&input),
+ expected,
+ "padding byte 0x{byte:02X} in {input:?}"
+ );
+ }
+
+ let interior = format!("12:{padding}30:45");
+ assert_eq!(
+ string_to_time(&interior),
+ None,
+ "interior padding byte 0x{byte:02X} in {interior:?}"
+ );
+ }
+ }
+
+ #[test]
+ fn test_unicode_whitespace_is_not_trimmed() {
+ for padding in [
+ '\u{0085}', '\u{00a0}', '\u{1680}', '\u{2000}', '\u{2003}',
'\u{2007}', '\u{2028}',
+ '\u{2029}', '\u{202f}', '\u{205f}', '\u{3000}',
+ ] {
+ assert!(padding.is_whitespace());
+
+ for input in [
+ format!("{padding}12:30:45"),
+ format!("12:30:45{padding}"),
+ format!("{padding}12:30:45{padding}"),
+ format!("12:{padding}30:45"),
+ format!("{padding}1:00:00 AM"),
+ format!("1:00:00{padding}AM"),
+ format!("1:00:00 AM{padding}"),
+ ] {
+ assert_eq!(
+ string_to_time(&input),
+ None,
+ "Unicode whitespace U+{:04X} in {input:?}",
+ padding as u32
+ );
+ }
+ }
+ }
+
+ #[test]
+ fn test_am_pm_control_byte_trimming() {
Review Comment:
Added Rust and Parquet-backed SQL coverage for `T` + `AM`/`PM` combinations
and padded `HH:mm` inputs. The Rust tests exercise all 34 trim bytes before
`T`, before the suffix, and after the suffix across both `HH:mm`/`HH:mm:ss`
forms and upper/lowercase suffixes. The full native suite (633 tests) and the
Spark 4.1 SQL fixture both pass.
--
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]
