Kev1n8 commented on code in PR #6181:
URL: https://github.com/apache/arrow-rs/pull/6181#discussion_r1702807080
##########
parquet/src/arrow/arrow_reader/statistics.rs:
##########
@@ -943,7 +973,58 @@ macro_rules! get_data_page_statistics {
}
Ok(Arc::new(builder.finish()))
},
- _ => unimplemented!()
+ Some(DataType::Utf8View) => {
+ let mut builder = StringViewBuilder::new();
+ let iterator = [<$stat_type_prefix
ByteArrayDataPageStatsIterator>]::new($iterator);
+ for x in iterator {
+ for x in x.into_iter() {
+ let Some(x) = x else {
+ builder.append_null(); // no statistics value
+ continue;
+ };
+
+ let Ok(x) = std::str::from_utf8(x.data()) else {
+ builder.append_null();
+ continue;
+ };
+
+ builder.append_value(x);
+ }
+ }
+ Ok(Arc::new(builder.finish()))
+ },
+ Some(DataType::BinaryView) => {
+ let mut builder = BinaryViewBuilder::new();
+ let iterator = [<$stat_type_prefix
ByteArrayDataPageStatsIterator>]::new($iterator);
+ for x in iterator {
+ for x in x.into_iter() {
+ let Some(x) = x else {
+ builder.append_null(); // no statistics value
+ continue;
+ };
+
+ builder.append_value(x);
+ }
+ }
+ Ok(Arc::new(builder.finish()))
+ },
+ Some(DataType::Null) |
+ Some(DataType::Duration(_)) |
+ Some(DataType::Interval(_)) |
+ Some(DataType::List(_)) |
+ Some(DataType::ListView(_)) |
+ Some(DataType::FixedSizeList(_, _)) |
+ Some(DataType::LargeList(_)) |
+ Some(DataType::LargeListView(_)) |
+ Some(DataType::Struct(_)) |
+ Some(DataType::Union(_, _)) |
+ Some(DataType::Map(_, _)) |
+ Some(DataType::RunEndEncoded(_, _)) => {
+ let len = $iterator.count();
+ // don't know how to extract statistics, so return a null
array
+ Ok(new_null_array($data_type.unwrap(), len))
+ },
+ None => unimplemented!() // not sure how to handle this
Review Comment:
Oh, I must have misunderstood the demand.
--
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]
