feat(sanitize): in-place, length-preserving log de-identification
Adds internal/sanitize: rewrites the customer-identifying spans that internal/privacy detects (domain/FQDN/e-mail/AD/public-IP/timezone) with same-length neutral fillers, in place, without changing the file format. - Fillers keep byte length: "sigma.sbrf.ru" -> "xxxxx.xxxx.xx", IP -> "00.000.000.00", "Europe/Moscow" -> "Etc/Universal" (same-length valid neutral IANA zone), offset "180" -> "000". Timestamps are not recomputed. - Lossless recursive archive walk (tar/.sds/gz/tgz/zip): entry names, modes, and all embedded timestamps preserved; untouched zip entries copied raw; member payload length unchanged so tar headers stay byte-identical; only the .gz/.zip compression layer is rebuilt. 0 redactions -> byte-identical output. - privacy.FindSpans is the one matcher shared by detection and redaction; fillers are recognised by isRedactionFiller so a re-scan / second pass is a no-op. New privacy FPs fixed along the way: syslog selectors (local7.info), "MEVersion" firmware quads, *.conf_bak vendor templates, bundled viewer domains. - Binary members (FRU.bin, localtime, redis-dump.rdb, SOL captures) and unreadable nested archives are reported in Result.SkippedBinary, never edited. - Surfaces: POST /api/sanitize (+ GET /api/sanitize/download), the "Обезличить и скачать копию" button in the Customer-data panel, and logpile -sanitize <file> (restores mtime/atime). Verified: re-parsing a sanitized Dell TSR / xFusion / Inspur onekeylog / H3C .sds yields the identical hardware inventory; re-scan is clean. ADL-067, bible-local/docs/log-sanitization.md. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Sonnet 5
parent
e74e01ad05
commit
a63bb17438
@@ -28,6 +28,7 @@ import (
|
||||
"git.mchus.pro/mchus/logpile/internal/ingest"
|
||||
"git.mchus.pro/mchus/logpile/internal/models"
|
||||
"git.mchus.pro/mchus/logpile/internal/parser"
|
||||
"git.mchus.pro/mchus/logpile/internal/sanitize"
|
||||
chartviewer "reanimator/chart/viewer"
|
||||
)
|
||||
|
||||
@@ -1273,7 +1274,15 @@ func (s *Server) handleGetPrivacyScan(w http.ResponseWriter, r *http.Request) {
|
||||
jsonResponse(w, map[string]any{"loaded": false})
|
||||
return
|
||||
}
|
||||
jsonResponse(w, result.PrivacyScan)
|
||||
jsonResponse(w, struct {
|
||||
*models.PrivacyScan
|
||||
Sanitizable bool `json:"sanitizable"`
|
||||
}{result.PrivacyScan, s.canSanitizeCurrent()})
|
||||
}
|
||||
|
||||
func (s *Server) canSanitizeCurrent() bool {
|
||||
pkg := s.GetRawExport()
|
||||
return pkg != nil && pkg.Source.Kind == "file_bytes" && sanitize.CanSanitize(pkg.Source.Filename)
|
||||
}
|
||||
|
||||
func (s *Server) handleGetStatus(w http.ResponseWriter, r *http.Request) {
|
||||
@@ -1721,6 +1730,7 @@ func (s *Server) handleClear(w http.ResponseWriter, r *http.Request) {
|
||||
s.SetResult(nil)
|
||||
s.SetDetectedVendor("")
|
||||
s.SetRawExport(nil)
|
||||
s.setSanitizeArtifact(nil)
|
||||
for _, artifact := range s.clearAllConvertArtifacts() {
|
||||
if strings.TrimSpace(artifact.Path) != "" {
|
||||
_ = os.Remove(artifact.Path)
|
||||
|
||||
Reference in New Issue
Block a user