Cargo.toml

[dependencies]
rand = "0.8.5"
xorfilter-rs = { git = "https://github.com/datafuse-extras/xorfilter", features = [
    "cbordata",
], tag = "databend-alpha.4" }

xor8_test.rs

use std::collections::HashSet;

use rand::Rng;
use xorfilter::{BuildHasherDefault, Xor8Builder};

fn random() -> Vec<u8> {
    let mut rng = rand::thread_rng();
    let bytes: Vec<u8> = (0..100).map(|_| rng.gen()).collect();
    bytes
}

fn run(value_num: usize) {
    let mut b = Xor8Builder::<BuildHasherDefault>::default();
    let mut set = HashSet::with_capacity(value_num);
    for _ in 0..value_num {
        let key = random();
        set.insert(key.clone());
        b.insert(&key);
        // b.populate(&[random(), random()]);
    }
    let filter = b.build().unwrap();
    let bs = filter.to_bytes();
    println!(
        "key_num:{}, len:{}, byte_per_key:{}",
        set.len(),
        bs.len(),
        bs.len() as f64 / value_num.max(1) as f64
    )
}

pub fn main() {
    run(0);
    run(1);
    run(5);
    run(10);
    run(100);
    run(1000);
    run(2000);
    run(3000);
    run(4000);
    run(8000);
}

key_num:0, len:54, byte_per_key:54
key_num:1, len:57, byte_per_key:57
key_num:5, len:63, byte_per_key:12.6
key_num:10, len:69, byte_per_key:6.9
key_num:100, len:177, byte_per_key:1.77
key_num:1000, len:1284, byte_per_key:1.284
key_num:2000, len:2514, byte_per_key:1.257
key_num:3000, len:3744, byte_per_key:1.248
key_num:4000, len:4974, byte_per_key:1.2435
key_num:8000, len:9894, byte_per_key:1.23675