efredine commented on code in PR #11200:
URL: https://github.com/apache/datafusion/pull/11200#discussion_r1663165859
##########
datafusion/core/src/datasource/physical_plan/parquet/statistics.rs:
##########
@@ -903,6 +917,21 @@ macro_rules! get_data_page_statistics {
new_empty_array(&DataType::Time64(unit.clone()))
}
})
+ },
+ Some(DataType::FixedSizeBinary(size)) => {
+ Ok(Arc::new(
+ FixedSizeBinaryArray::from(
+ [<$stat_type_prefix
FixedLenByteArrayDataPageStatsIterator>]::new($iterator).map(|x| {
+ x.into_iter().filter_map(|x| x).map(|x| {
+ if x.len().try_into() == Ok(*size) {
+ Some(x.data().to_vec())
+ } else {
+ None
+ }
+ })
+ }).flatten().collect::<Vec<_>>()
+ )
+ ))
Review Comment:
Ok - after some further research, the trick here is to use `try_from_iter`
instead. So:
```Rust
Some(DataType::FixedSizeBinary(size)) => {
Ok(Arc::new(
FixedSizeBinaryArray::try_from_iter(
[<$stat_type_prefix
FixedLenByteArrayDataPageStatsIterator>]::new($iterator).map(|x| {
x.into_iter().filter_map(|x| x.and_then(|x| {
if x.len().try_into() == Ok(*size) {
Some(x)
} else {
log::debug!(
"FixedSizeBinary({}) statistics
is a binary of size {}, ignoring it.",
size,
x.len(),
);
None
}
}))
})
.flatten()
).unwrap_or_else(|_| {
FixedSizeBinaryArray::new(*size, vec![].into(),
None)
})
))
},
```
--
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]
