tustvold commented on code in PR #2076:
URL: https://github.com/apache/arrow-rs/pull/2076#discussion_r922665853
##########
parquet/src/arrow/array_reader/byte_array.rs:
##########
@@ -653,6 +776,57 @@ mod tests {
}
}
+ #[test]
+ fn test_byte_array_decoder_skip() {
+ let (pages, encoded_dictionary) =
+ byte_array_all_encodings(vec!["hello", "world", "a", "b"]);
+
+ let column_desc = utf8_column();
+ let mut decoder = ByteArrayColumnValueDecoder::new(&column_desc);
+
+ decoder
+ .set_dict(encoded_dictionary, 4, Encoding::RLE_DICTIONARY, false)
+ .unwrap();
+
+ for (encoding, page) in pages {
+ let mut output = OffsetBuffer::<i32>::default();
+ decoder.set_data(encoding, page, 4, Some(4)).unwrap();
+
+ assert_eq!(decoder.read(&mut output, 0..1).unwrap(), 1);
+
+ assert_eq!(output.values.as_slice(), "hello".as_bytes());
+ assert_eq!(output.offsets.as_slice(), &[0, 5]);
+
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+ assert_eq!(decoder.skip_values(1).unwrap(), 1);
+
+ assert_eq!(decoder.read(&mut output, 0..1).unwrap(), 1);
Review Comment:
Because for backwards compatibility we need to support decoding to a slice,
as opposed to a container that tracks its length
--
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]
