viirya commented on code in PR #3572: URL: https://github.com/apache/arrow-rs/pull/3572#discussion_r1082878810
########## arrow-cast/src/cast.rs: ########## @@ -3344,42 +3350,23 @@ where Ok(Arc::new(b.finish())) } -// Packs the data as a StringDictionaryArray, if possible, with the -// key types of K -fn pack_string_to_dictionary<K>( - array: &ArrayRef, - cast_options: &CastOptions, -) -> Result<ArrayRef, ArrowError> -where - K: ArrowDictionaryKeyType, -{ - let cast_values = cast_with_options(array, &DataType::Utf8, cast_options)?; - let values = cast_values.as_any().downcast_ref::<StringArray>().unwrap(); - let mut b = StringDictionaryBuilder::<K>::with_capacity(values.len(), 1024, 1024); - - // copy each element one at a time - for i in 0..values.len() { - if values.is_null(i) { - b.append_null(); - } else { - b.append(values.value(i))?; - } - } - Ok(Arc::new(b.finish())) -} - -// Packs the data as a BinaryDictionaryArray, if possible, with the +// Packs the data as a GenericByteDictionaryBuilder, if possible, with the // key types of K -fn pack_binary_to_dictionary<K>( +fn pack_byte_to_dictionary<K, T>( array: &ArrayRef, cast_options: &CastOptions, ) -> Result<ArrayRef, ArrowError> where K: ArrowDictionaryKeyType, + T: ByteArrayType, { - let cast_values = cast_with_options(array, &DataType::Binary, cast_options)?; - let values = cast_values.as_any().downcast_ref::<BinaryArray>().unwrap(); - let mut b = BinaryDictionaryBuilder::<K>::with_capacity(values.len(), 1024, 1024); + let cast_values = cast_with_options(array, &T::DATA_TYPE, cast_options)?; Review Comment: It's necessary as this supports that the source type is different than the value type of dictionary. -- 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: github-unsubscr...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org