Skip to content

use HashSet from rustc-hash too #351

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

use HashSet from rustc-hash too #351

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.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
// This check is new and seems buggy (possibly with PyO3 interaction)
#![allow(clippy::borrow_deref_ref)]

use std::collections::HashSet;
use std::num::NonZeroU64;
use std::thread;

Expand All @@ -12,6 +11,7 @@ use pyo3::pybacked::PyBackedStr;
use pyo3::types::{PyBytes, PyList, PyTuple};
use pyo3::PyResult;
use rustc_hash::FxHashMap as HashMap;
use rustc_hash::FxHashSet as HashSet;

type Rank = u32;

Expand Down Expand Up @@ -317,7 +317,7 @@ impl CoreBPE {
if last_piece_token_len == 0 {
// If last_piece_token_len is zero, the last token was a special token and we have
// no unstable bytes
return (tokens, HashSet::new());
return (tokens, HashSet::default());
}
let (mut tokens, last_piece_token_len) =
self._increase_last_piece_token_len(tokens, last_piece_token_len);
Expand All @@ -331,7 +331,7 @@ impl CoreBPE {
// This would reduce the amount of retokenising when determining completions
// Refer to the logic in an older version of this file

let mut completions = HashSet::new();
let mut completions = HashSet::default();
if unstable_bytes.is_empty() {
return (tokens, completions);
}
Expand Down Expand Up @@ -514,7 +514,7 @@ impl CoreBPE {
Ok(text) => self._encode_ordinary_native(text),
Err(e) => {
let text = unsafe { std::str::from_utf8_unchecked(&bytes[..e.valid_up_to()]) };
let (tokens, last_piece_token_len) = self._encode_native(text, &HashSet::new());
let (tokens, last_piece_token_len) = self._encode_native(text, &HashSet::default());
let (mut tokens, last_piece_token_len) =
self._increase_last_piece_token_len(tokens, last_piece_token_len);
if !tokens.is_empty() && last_piece_token_len > 0 {
Expand Down