albertlockett commented on code in PR #8069:
URL: https://github.com/apache/arrow-rs/pull/8069#discussion_r2304941663
##########
parquet/src/arrow/arrow_writer/mod.rs:
##########
@@ -1058,21 +1058,29 @@ impl ArrowColumnWriterFactory {
self.get_arrow_column_writer(f[1].data_type(), props,
leaves, out)?
}
_ => unreachable!("invalid map type"),
- }
+ },
ArrowDataType::Dictionary(_, value_type) => match
value_type.as_ref() {
- ArrowDataType::Utf8 | ArrowDataType::LargeUtf8 |
ArrowDataType::Binary | ArrowDataType::LargeBinary => {
- out.push(bytes(leaves.next().unwrap())?)
- }
+ ArrowDataType::Utf8
+ | ArrowDataType::LargeUtf8
+ | ArrowDataType::Binary
+ | ArrowDataType::LargeBinary =>
out.push(bytes(leaves.next().unwrap())?),
ArrowDataType::Utf8View | ArrowDataType::BinaryView => {
out.push(bytes(leaves.next().unwrap())?)
}
- ArrowDataType::FixedSizeBinary(_) => {
+ ArrowDataType::FixedSizeBinary(_) =>
out.push(bytes(leaves.next().unwrap())?),
+ _ => out.push(col(leaves.next().unwrap())?),
+ },
+ ArrowDataType::RunEndEncoded(_run_ends, value_type) => match
value_type.data_type() {
Review Comment:
This looks correct to me, assuming the RunArray's values are primitive types
(It looks like we're making the same assumption for dictionary types, so this
is probably OK)
--
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]
