mirrors/tantivy
2
0
Fork 1
mirror of https://github.com/quickwit-oss/tantivy.git synced 2026-06-19 09:16:45 +00:00
Code Issues Projects Releases Packages Wiki Activity

Relying on upstream version of datasketch and stop using HLL 4. (#2936)

Browse source 
We were relying on a fork for:

a bugfix in LIST serialization
a better API exposing a new Coupon type, required for caching coupons.
We also stop using HLL8 in hope to fix
https://datadoghq.atlassian.net/browse/CLOUDPREM-625

Co-authored-by: Paul Masurel <paul.masurel@datadoghq.com>
This commit is contained in:
Paul Masurel 2026-05-19 13:29:35 +02:00 • committed by GitHub
commit 46b3fb9ed3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 9 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Cargo.toml
View file

@ -65,7 +65,7 @@ tantivy-bitpacker = { version = "0.10", path = "./bitpacker" }
common = { version = "0.11", path = "./common/", package = "tantivy-common" }
tokenizer-api = { version = "0.7", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
sketches-ddsketch = { version = "0.4", features = ["use_serde"] }
datasketches = { git = "https://github.com/fulmicoton-dd/datasketches-rust", rev = "7635fb8" }
datasketches = { version = "0.3.0", features = ["hll"] }
futures-util = { version = "0.3.28", optional = true }
futures-channel = { version = "0.3.28", optional = true }
fnv = "1.0.7"

12
src/aggregation/metric/cardinality.rs
View file

@ -166,8 +166,12 @@ impl CouponCache {
let should_use_dense =
highest_term_ord < 1_000_000u64 || highest_term_ord < num_terms as u64 * 3u64;
if should_use_dense {
let mut coupon_map: Vec<Coupon> = vec![Coupon::EMPTY; highest_term_ord as usize + 1];
for (term_ord, coupon) in term_ords.into_iter().zip(coupons.into_iter()) {
// We don't really care about the value here. We will populate all the values we will
// read anyway.
let uninitialized_coupon = Coupon::from_hash(0);
let mut coupon_map: Vec<Coupon> =
vec![uninitialized_coupon; highest_term_ord as usize + 1];
for (term_ord, coupon) in term_ords.into_iter().zip(coupons) {
coupon_map[term_ord as usize] = coupon;
}
CouponCache::Dense {
@ -821,7 +825,7 @@ impl<'de> Deserialize<'de> for CardinalityCollector {
impl CardinalityCollector {
fn new(salt: u8) -> Self {
Self {
sketch: HllSketch::new(LG_K, HllType::Hll4),
sketch: HllSketch::new(LG_K, HllType::Hll8),
salt,
}
}
@ -852,7 +856,7 @@ impl CardinalityCollector {
let mut union = HllUnion::new(LG_K);
union.update(&self.sketch);
union.update(&right.sketch);
self.sketch = union.to_sketch(HllType::Hll4);
self.sketch = union.to_sketch(HllType::Hll8);
Ok(())
}
}