etseidl commented on code in PR #8762:
URL: https://github.com/apache/arrow-rs/pull/8762#discussion_r2527904585
##########
parquet/src/bloom_filter/mod.rs:
##########
@@ -244,29 +244,8 @@ fn num_of_bits_from_ndv_fpp(ndv: u64, fpp: f64) -> usize {
}
impl Sbbf {
- /// Create a new [Sbbf] with given number of distinct values and false
positive probability.
- /// Will return an error if `fpp` is greater than or equal to 1.0 or less
than 0.0.
- pub(crate) fn new_with_ndv_fpp(ndv: u64, fpp: f64) -> Result<Self,
ParquetError> {
- if !(0.0..1.0).contains(&fpp) {
- return Err(ParquetError::General(format!(
- "False positive probability must be between 0.0 and 1.0, got
{fpp}"
- )));
- }
- let num_bits = num_of_bits_from_ndv_fpp(ndv, fpp);
- Ok(Self::new_with_num_of_bytes(num_bits / 8))
- }
-
- /// Create a new [Sbbf] with given number of bytes, the exact number of
bytes will be adjusted
- /// to the next power of two bounded by [BITSET_MIN_LENGTH] and
[BITSET_MAX_LENGTH].
- pub(crate) fn new_with_num_of_bytes(num_bytes: usize) -> Self {
- let num_bytes = optimal_num_of_bytes(num_bytes);
- assert_eq!(num_bytes % size_of::<Block>(), 0);
- let num_blocks = num_bytes / size_of::<Block>();
- let bitset = vec![Block::ZERO; num_blocks];
- Self(bitset)
- }
-
- pub(crate) fn new(bitset: &[u8]) -> Self {
+ /// Create a new [Sbbf] from raw bitset bytes.
Review Comment:
Would it be better to add a public function `as_slice` to return the bitset?
Reading the proposed example I'm not sure how one would get the header length
from the serialized `Sbbf`.
--
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]
