Ted-Jiang commented on code in PR #2097:
URL: https://github.com/apache/arrow-rs/pull/2097#discussion_r924003572
##########
parquet/src/arrow/array_reader/byte_array_dictionary.rs:
##########
@@ -459,7 +481,75 @@ mod tests {
None,
Some("1"),
Some("2"),
- None
+ None,
+ ]
+ )
+ }
+
+ #[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, 14, Some(data.len()))
+ .unwrap();
+
+ let mut output = DictionaryBuffer::<i32, i32>::default();
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+ assert_eq!(decoder.read(&mut output, 0..2).unwrap(), 2);
+
+ let mut valid = vec![false, false, false, true, false, true];
+ let valid_buffer = Buffer::from_iter(valid.iter().cloned());
+ output.pad_nulls(0, 2, valid.len(), valid_buffer.as_slice());
+
+ assert!(matches!(output, DictionaryBuffer::Dict { .. }));
+
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+ assert_eq!(decoder.read(&mut output, 0..3).unwrap(), 3);
Review Comment:
Yes it should be, but like previous test read two range '0..3' and '0..4'
https://github.com/apache/arrow-rs/blob/a7f6a6e9261f2320ed34500d6d649efc97617161/parquet/src/arrow/array_reader/byte_array_dictionary.rs#L444-L453
it seems it total read 7 values
https://github.com/apache/arrow-rs/blob/a7f6a6e9261f2320ed34500d6d649efc97617161/parquet/src/arrow/array_reader/byte_array_dictionary.rs#L468-L486
--
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
