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

perf: avoid allocs in unicodeFoldTransformer #53

Merged
merged 1 commit into from
May 3, 2023
Merged

perf: avoid allocs in unicodeFoldTransformer #53

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
26 changes: 14 additions & 12 deletions fuzzy/fuzzy.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
package fuzzy

import (
"bytes"
"unicode"
"unicode/utf8"

Expand Down Expand Up @@ -251,18 +250,21 @@ func stringTransform(s string, t transform.Transformer) (transformed string) {
type unicodeFoldTransformer struct{ transform.NopResetter }

func (unicodeFoldTransformer) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
runes := bytes.Runes(src)
var lowerRunes []rune
for _, r := range runes {
lowerRunes = append(lowerRunes, unicode.ToLower(r))
}

srcBytes := []byte(string(lowerRunes))
n := copy(dst, srcBytes)
if n < len(srcBytes) {
err = transform.ErrShortDst
n := 0
// Converting src to a string allocates.
// In theory, it need not; see https://go.dev/issue/27148.
// It is possible to write this loop using utf8.DecodeRune
// and thereby avoid allocations, but it is noticeably slower.
// So just let's wait for the compiler to get smarter.
for _, r := range string(src) {
r = unicode.ToLower(r)
x := utf8.RuneLen(r)
if x > len(dst[n:]) {
err = transform.ErrShortDst
break
}
n += utf8.EncodeRune(dst[n:], r)
}

return n, n, err
}

Expand Down