mathias/gitea-mcp
1
0
Fork 0
Code Issues 8 Pull Requests Actions Packages Projects Releases Wiki Activity

perf(tools): linear duplicate-key scan keyed on SimpleFold orbit

Browse Source 
PR #66 review round 2: the pairwise EqualFold loop was quadratic, 7s of
CPU for ~90k keys under the 1 MiB body cap. foldKey maps each rune to
the smallest member of its unicode.SimpleFold orbit, equal exactly when
strings.EqualFold is, so the scan is a map lookup again. The scaling
test fails on the previous code (7.1s).

Refs #65

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
mathias
2026-10-05 07:05:00 +02:00
co-authored by Claude Opus 5.5
parent 31a3dd3e0e
commit cd61239451
2 changed files with 67 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/tools/tool.go
+25 -8
View File
@@ -8,6 +8,7 @@ import (
"reflect"
"regexp"
"strings"
"unicode"
"git.d-ma.be/mathias/gitea-mcp/internal/gitea"
"git.d-ma.be/mathias/gitea-mcp/internal/registry"
@@ -84,21 +85,18 @@ func scanJSONValue(dec *json.Decoder) error {
}
switch d {
case '{':
var seen []string
seen := map[string]string{}
for dec.More() {
kt, err := dec.Token()
if err != nil {
return err
}
k, _ := kt.(string)
// EqualFold, not ToLower: encoding/json folds the same way, so
// long s (U+017F) matches s and the Kelvin sign matches k.
for _, prev := range seen {
if strings.EqualFold(prev, k) {
return fmt.Errorf("duplicate argument keys %q and %q (keys must be unique ignoring case): %w", prev, k, gitea.ErrValidation)
}
fk := foldKey(k)
if prev, dup := seen[fk]; dup {
return fmt.Errorf("duplicate argument keys %q and %q (keys must be unique ignoring case): %w", prev, k, gitea.ErrValidation)
}
seen = append(seen, k)
seen[fk] = k
if err := scanJSONValue(dec); err != nil {
return err
}
@@ -114,6 +112,25 @@ func scanJSONValue(dec *json.Decoder) error {
return err
}
// foldKey maps every rune to the smallest member of its unicode.SimpleFold
// orbit, so foldKey(a) == foldKey(b) exactly when strings.EqualFold(a, b) —
// the folding encoding/json uses (long s == s, Kelvin sign == k). A map keyed
// on it keeps the duplicate scan linear (PR #66 review: a pairwise EqualFold
// loop cost 7s of CPU on ~90k keys).
func foldKey(s string) string {
var b strings.Builder
for _, r := range s {
min := r
for f := unicode.SimpleFold(r); f != r; f = unicode.SimpleFold(f) {
if f < min {
min = f
}
}
b.WriteRune(min)
}
return b.String()
}
// jsonFieldNames returns the json tag names of dst's top-level struct fields.
func jsonFieldNames(dst any) []string {
v := reflect.ValueOf(dst)