alamb commented on code in PR #6870:
URL: https://github.com/apache/arrow-rs/pull/6870#discussion_r1887309722
##########
parquet/src/column/writer/mod.rs:
##########
@@ -878,24 +878,44 @@ impl<'a, E: ColumnValueEncoder> GenericColumnWriter<'a,
E> {
}
}
+ /// Returns `true` if this column's logical type is a UTF-8 string.
+ fn is_utf8(&self) -> bool {
+ self.get_descriptor().logical_type() == Some(LogicalType::String)
+ || self.get_descriptor().converted_type() == ConvertedType::UTF8
+ }
+
fn truncate_min_value(&self, truncation_length: Option<usize>, data:
&[u8]) -> (Vec<u8>, bool) {
truncation_length
.filter(|l| data.len() > *l)
- .and_then(|l| match str::from_utf8(data) {
- Ok(str_data) => truncate_utf8(str_data, l),
- Err(_) => Some(data[..l].to_vec()),
- })
+ .and_then(|l|
+ // don't do extra work if this column isn't UTF-8
+ if self.is_utf8() {
+ match str::from_utf8(data) {
+ Ok(str_data) => truncate_utf8(str_data, l),
+ Err(_) => Some(data[..l].to_vec()),
Review Comment:
Thank you
--
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]
