XiangpengHao commented on code in PR #5871:
URL: https://github.com/apache/arrow-rs/pull/5871#discussion_r1635433312
##########
arrow-cast/src/cast/dictionary.rs:
##########
@@ -85,10 +85,65 @@ pub(crate) fn dictionary_cast<K: ArrowDictionaryKeyType>(
Ok(new_array)
}
+ Utf8View => {
+ // `unpack_dictionary` can handle Utf8View/BinaryView types, but
incurs unnecessary data copy of the value buffer.
+ // we handle it here to avoid the copy.
+ let dict_array = array
+ .as_dictionary::<K>()
+ .downcast_dict::<StringArray>()
+ .unwrap();
+
+ let string_view = view_from_dict_values::<K, StringViewType,
GenericStringType<i32>>(
+ dict_array.values(),
+ dict_array.keys(),
+ );
+ Ok(Arc::new(string_view))
+ }
+ BinaryView => {
+ // `unpack_dictionary` can handle Utf8View/BinaryView types, but
incurs unnecessary data copy of the value buffer.
+ // we handle it here to avoid the copy.
+ let dict_array = array
+ .as_dictionary::<K>()
+ .downcast_dict::<BinaryArray>()
+ .unwrap();
+
+ let binary_view = view_from_dict_values::<K, BinaryViewType,
BinaryType>(
+ dict_array.values(),
+ dict_array.keys(),
+ );
+ Ok(Arc::new(binary_view))
+ }
_ => unpack_dictionary::<K>(array, to_type, cast_options),
}
}
+fn view_from_dict_values<K: ArrowDictionaryKeyType, T: ByteViewType, V:
ByteArrayType>(
+ array: &GenericByteArray<V>,
+ keys: &PrimitiveArray<K>,
+) -> GenericByteViewArray<T> {
+ let value_buffer = array.values();
+ let value_offsets = array.value_offsets();
+ let mut builder = GenericByteViewBuilder::<T>::with_capacity(keys.len());
+ builder.append_block(value_buffer.clone());
+ for i in keys.iter() {
Review Comment:
ops, I checked in a `append_view_unchecked`.
But if we do `try_append_view`, it is even slower than the
`unpack_dictionary` approach
--
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]
