Ted-Jiang commented on code in PR #2105:
URL: https://github.com/apache/arrow-rs/pull/2105#discussion_r924058393
##########
parquet/src/arrow/array_reader/byte_array_dictionary.rs:
##########
@@ -476,6 +477,68 @@ mod tests {
)
}
+ #[test]
+ fn test_dictionary_preservation_skip() {
+ let data_type = utf8_dictionary();
+
+ let data: Vec<_> = vec!["0", "1", "0", "1", "2", "1", "2"]
+ .into_iter()
+ .map(ByteArray::from)
+ .collect();
+ let (dict, encoded) = encode_dictionary(&data);
+
+ let column_desc = utf8_column();
+ let mut decoder = DictionaryDecoder::<i32, i32>::new(&column_desc);
+
+ decoder
+ .set_dict(dict, 3, Encoding::RLE_DICTIONARY, false)
+ .unwrap();
+
+ decoder
+ .set_data(Encoding::RLE_DICTIONARY, encoded, 7, Some(data.len()))
+ .unwrap();
+
+ let mut output = DictionaryBuffer::<i32, i32>::default();
+
+ // read two skip one
+ assert_eq!(decoder.read(&mut output, 0..2).unwrap(), 2);
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+
+ assert!(matches!(output, DictionaryBuffer::Dict { .. }));
+
+ // read two skip one
+ assert_eq!(decoder.read(&mut output, 2..4).unwrap(), 2);
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+
+ // read one and test on skip at the end
+ assert_eq!(decoder.read(&mut output, 4..5).unwrap(), 1);
+ assert_eq!(decoder.skip_values(4).unwrap(), 0);
+
+ let valid = vec![true, true, true, true, true];
+ let valid_buffer = Buffer::from_iter(valid.iter().cloned());
+ output.pad_nulls(0, 5, 5, valid_buffer.as_slice());
Review Comment:
@tustvold i found without `pad_nulls` then call `into_array` will return
empty.
Is there other way to change into array without padding🤔
--
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
