mirror of
https://github.com/go-gitea/gitea.git
synced 2026-08-24 08:50:04 +00:00
SEONGHYUN HONG
84b67d50a6
### Description
`NaturalSortCompare` (`modules/base/natural_sort.go`) compares two
numeric run parts by **raw string length**:
```go
if len(part1) != len(part2) {
return len(part1) - len(part2)
}
```
"Longer digit string = larger number" only holds without leading zeros.
With zero-padded numbers the comparison inverts:
- `file0001` vs `file2` → claims `file0001 > file2`, but `1 < 2`
- `a08` vs `a9` → claims `a08 > a9`, but `8 < 9`
This affects any natural-ordered listing where zero-padded and shorter
unpadded numbers mix (branch/tag/file names, etc.).
### Fix
Strip leading zeros before comparing digit-count magnitude; on equal
magnitude fall back to collation, then to the original length so fewer
leading zeros sort first. Added a small `naturalSortTrimZeros` helper
(keeps one char so `"000"` → `"0"`).
Signed-off-by: Seonghyun Hong <s3onghyun.hong@gmail.com>
Signed-off-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: silverwind <me@silverwind.io>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
85 lines
2.3 KiB
Go
85 lines
2.3 KiB
Go
// Copyright 2017 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package base
|
|
|
|
import (
|
|
"strings"
|
|
"unicode/utf8"
|
|
|
|
"golang.org/x/text/collate"
|
|
"golang.org/x/text/language"
|
|
)
|
|
|
|
func naturalSortGetRune(str string, pos int) (r rune, size int, has bool) {
|
|
if pos >= len(str) {
|
|
return 0, 0, false
|
|
}
|
|
r, size = utf8.DecodeRuneInString(str[pos:])
|
|
if r == utf8.RuneError {
|
|
r, size = rune(str[pos]), 1 // if invalid input, treat it as a single byte ascii
|
|
}
|
|
return r, size, true
|
|
}
|
|
|
|
func naturalSortAdvance(str string, pos int) (end int, isNumber bool) {
|
|
end = pos
|
|
for {
|
|
r, size, has := naturalSortGetRune(str, end)
|
|
if !has {
|
|
break
|
|
}
|
|
isCurRuneNum := '0' <= r && r <= '9'
|
|
if end == pos {
|
|
isNumber = isCurRuneNum
|
|
end += size
|
|
} else if isCurRuneNum == isNumber {
|
|
end += size
|
|
} else {
|
|
break
|
|
}
|
|
}
|
|
return end, isNumber
|
|
}
|
|
|
|
// naturalSortTrimZeros strips leading '0's, keeping one character so "000" collapses to "0"
|
|
func naturalSortTrimZeros(num string) string {
|
|
i := 0
|
|
for i < len(num)-1 && num[i] == '0' {
|
|
i++
|
|
}
|
|
return num[i:]
|
|
}
|
|
|
|
// NaturalSortCompare compares two strings so that they could be sorted in natural order
|
|
func NaturalSortCompare(s1, s2 string) int {
|
|
// There is a bug in Golang's collate package: https://github.com/golang/go/issues/67997
|
|
// text/collate: CompareString(collate.Numeric) returns wrong result for "0.0" vs "1.0" #67997
|
|
// So we need to handle the number parts by ourselves
|
|
c := collate.New(language.English, collate.Numeric)
|
|
pos1, pos2 := 0, 0
|
|
for pos1 < len(s1) && pos2 < len(s2) {
|
|
end1, isNum1 := naturalSortAdvance(s1, pos1)
|
|
end2, isNum2 := naturalSortAdvance(s2, pos2)
|
|
part1, part2 := s1[pos1:end1], s2[pos2:end2]
|
|
if isNum1 && isNum2 {
|
|
if part1 != part2 {
|
|
num1, num2 := naturalSortTrimZeros(part1), naturalSortTrimZeros(part2)
|
|
if len(num1) != len(num2) {
|
|
return len(num1) - len(num2) // without leading zeros, more digits means larger value
|
|
}
|
|
if cmp := strings.Compare(num1, num2); cmp != 0 {
|
|
return cmp // equal digit count, so byte order is numeric order
|
|
}
|
|
return len(part1) - len(part2) // equal value, fewer leading zeros sorts first
|
|
}
|
|
} else {
|
|
if cmp := c.CompareString(part1, part2); cmp != 0 {
|
|
return cmp
|
|
}
|
|
}
|
|
pos1, pos2 = end1, end2
|
|
}
|
|
return len(s1) - len(s2)
|
|
}
|