Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fuzzy match performance improvements redo (#22561)

Browse source 
Release Notes:

- N/A
This commit is contained in:
Michael Sloan 2025-01-01 22:31:06 -07:00 • committed by GitHub
parent 28d1d2d939
commit 665717da9a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 89 additions and 96 deletions
Download patch file Download diff file Expand all files Collapse all files

41
crates/fuzzy/src/matcher.rs
View file

@ -14,7 +14,6 @@ pub struct Matcher<'a> {
lowercase_query: &'a [char],
query_char_bag: CharBag,
smart_case: bool,
max_results: usize,
min_score: f64,
match_positions: Vec<usize>,
last_positions: Vec<usize>,
@ -22,11 +21,6 @@ pub struct Matcher<'a> {
best_position_matrix: Vec<usize>,
}
pub trait Match: Ord {
fn score(&self) -> f64;
fn set_positions(&mut self, positions: Vec<usize>);
}
pub trait MatchCandidate {
fn has_chars(&self, bag: CharBag) -> bool;
fn to_string(&self) -> Cow<'_, str>;
@ -38,7 +32,6 @@ impl<'a> Matcher<'a> {
lowercase_query: &'a [char],
query_char_bag: CharBag,
smart_case: bool,
max_results: usize,
) -> Self {
Self {
query,
@ -50,10 +43,11 @@ impl<'a> Matcher<'a> {
score_matrix: Vec::new(),
best_position_matrix: Vec::new(),
smart_case,
max_results,
}
}
/// Filter and score fuzzy match candidates. Results are returned unsorted, in the same order as
/// the input candidates.
pub fn match_candidates<C: MatchCandidate, R, F>(
&mut self,
prefix: &[char],
@ -63,8 +57,7 @@ impl<'a> Matcher<'a> {
cancel_flag: &AtomicBool,
build_match: F,
) where
R: Match,
F: Fn(&C, f64) -> R,
F: Fn(&C, f64, &Vec<usize>) -> R,
{
let mut candidate_chars = Vec::new();
let mut lowercase_candidate_chars = Vec::new();
@ -103,20 +96,7 @@ impl<'a> Matcher<'a> {
);
if score > 0.0 {
let mut mat = build_match(&candidate, score);
if let Err(i) = results.binary_search_by(|m| mat.cmp(m)) {
if results.len() < self.max_results {
mat.set_positions(self.match_positions.clone());
results.insert(i, mat);
} else if i < results.len() {
results.pop();
mat.set_positions(self.match_positions.clone());
results.insert(i, mat);
}
if results.len() == self.max_results {
self.min_score = results.last().unwrap().score();
}
}
results.push(build_match(&candidate, score, &self.match_positions));
}
}
}
@ -325,18 +305,18 @@ mod tests {
#[test]
fn test_get_last_positions() {
let mut query: &[char] = &['d', 'c'];
let mut matcher = Matcher::new(query, query, query.into(), false, 10);
let mut matcher = Matcher::new(query, query, query.into(), false);
let result = matcher.find_last_positions(&['a', 'b', 'c'], &['b', 'd', 'e', 'f']);
assert!(!result);
query = &['c', 'd'];
let mut matcher = Matcher::new(query, query, query.into(), false, 10);
let mut matcher = Matcher::new(query, query, query.into(), false);
let result = matcher.find_last_positions(&['a', 'b', 'c'], &['b', 'd', 'e', 'f']);
assert!(result);
assert_eq!(matcher.last_positions, vec![2, 4]);
query = &['z', '/', 'z', 'f'];
let mut matcher = Matcher::new(query, query, query.into(), false, 10);
let mut matcher = Matcher::new(query, query, query.into(), false);
let result = matcher.find_last_positions(&['z', 'e', 'd', '/'], &['z', 'e', 'd', '/', 'f']);
assert!(result);
assert_eq!(matcher.last_positions, vec![0, 3, 4, 8]);
@ -451,7 +431,7 @@ mod tests {
});
}
let mut matcher = Matcher::new(&query, &lowercase_query, query_chars, smart_case, 100);
let mut matcher = Matcher::new(&query, &lowercase_query, query_chars, smart_case);
let cancel_flag = AtomicBool::new(false);
let mut results = Vec::new();
@ -462,16 +442,17 @@ mod tests {
path_entries.into_iter(),
&mut results,
&cancel_flag,
|candidate, score| PathMatch {
|candidate, score, positions| PathMatch {
score,
worktree_id: 0,
positions: Vec::new(),
positions: positions.clone(),
path: Arc::from(candidate.path),
path_prefix: "".into(),
distance_to_relative_ancestor: usize::MAX,
is_dir: false,
},
);
results.sort_by(|a, b| b.cmp(a));
results
.into_iter()