Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Allow using an arbitrary hash_fn for generation #294

Merged
merged 1 commit into from
Oct 28, 2023
Merged

Allow using an arbitrary hash_fn for generation #294

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
21 changes: 13 additions & 8 deletions phf_generator/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
//! [phf]: https://docs.rs/phf

#![doc(html_root_url = "https://docs.rs/phf_generator/0.11")]
use phf_shared::{HashKey, PhfHash};
use phf_shared::{HashKey, Hashes, PhfHash};
use rand::distributions::Standard;
use rand::rngs::SmallRng;
use rand::{Rng, SeedableRng};
Expand All @@ -19,23 +19,28 @@ pub struct HashState {
}

pub fn generate_hash<H: PhfHash>(entries: &[H]) -> HashState {
generate_hash_with_hash_fn(entries, phf_shared::hash)
}

pub fn generate_hash_with_hash_fn<T, F>(entries: &[T], hash_fn: F) -> HashState
where
F: Fn(&T, &HashKey) -> Hashes,
{
SmallRng::seed_from_u64(FIXED_SEED)
.sample_iter(Standard)
.find_map(|key| try_generate_hash(entries, key))
.find_map(|key| {
let hashes: Vec<_> = entries.iter().map(|entry| hash_fn(entry, &key)).collect();
try_generate_hash(&hashes, key)
})
.expect("failed to solve PHF")
}

fn try_generate_hash<H: PhfHash>(entries: &[H], key: HashKey) -> Option<HashState> {
fn try_generate_hash(hashes: &[Hashes], key: HashKey) -> Option<HashState> {
struct Bucket {
idx: usize,
keys: Vec<usize>,
}

let hashes: Vec<_> = entries
.iter()
.map(|entry| phf_shared::hash(entry, &key))
.collect();

let buckets_len = (hashes.len() + DEFAULT_LAMBDA - 1) / DEFAULT_LAMBDA;
let mut buckets = (0..buckets_len)
.map(|i| Bucket {
Expand Down