Files
logpile/internal/ingest/service.go
T
Mikhail ChusavitinandClaude Sonnet 5 4a4910f207 feat(privacy): scan ingested sources for customer-identifying data
Detection-only scan (internal/privacy) attached to every AnalysisResult:
a customer-domain guess plus a findings list (category, file, line, match,
hint), ported from the KB grep playbook. Runs on archive uploads and the
serialized Redfish tree; gated by LOGPILE_PRIVACY_SCAN (default on).

Surfaced at GET /api/privacy-scan, in the "Customer data" UI panel, and as
privacy_report.json in the raw-export bundle. IP policy keeps RFC1918 and
example ranges out of findings; allowlist covers standards-body and vendor
infrastructure domains. No customer tokens in the repo. See ADL-066 and
bible-local/docs/privacy-scan.md.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-02 15:24:32 +03:00

86 lines
2.4 KiB
Go

package ingest
import (
"bytes"
"encoding/json"
"fmt"
"strings"
"git.mchus.pro/mchus/logpile/internal/collector"
"git.mchus.pro/mchus/logpile/internal/models"
"git.mchus.pro/mchus/logpile/internal/parser"
"git.mchus.pro/mchus/logpile/internal/privacy"
)
type Service struct{}
type RedfishSourceMetadata struct {
TargetHost string
SourceTimezone string
Filename string
}
func NewService() *Service {
return &Service{}
}
func (s *Service) AnalyzeArchivePayload(filename string, payload []byte) (*models.AnalysisResult, string, error) {
p := parser.NewBMCParser()
if err := p.ParseFromReader(bytes.NewReader(payload), filename); err != nil {
return nil, "", err
}
return p.Result(), p.DetectedVendor(), nil
}
func (s *Service) AnalyzeRedfishRawPayloads(rawPayloads map[string]any, meta RedfishSourceMetadata) (*models.AnalysisResult, string, error) {
result, err := collector.ReplayRedfishFromRawPayloads(rawPayloads, nil)
if err != nil {
return nil, "", err
}
if result == nil {
return nil, "", fmt.Errorf("redfish replay returned nil result")
}
if strings.TrimSpace(result.Protocol) == "" {
result.Protocol = "redfish"
}
if strings.TrimSpace(result.SourceType) == "" {
result.SourceType = models.SourceTypeAPI
}
if strings.TrimSpace(result.TargetHost) == "" {
result.TargetHost = strings.TrimSpace(meta.TargetHost)
}
if strings.TrimSpace(result.SourceTimezone) == "" {
result.SourceTimezone = strings.TrimSpace(meta.SourceTimezone)
}
if strings.TrimSpace(result.Filename) == "" {
if strings.TrimSpace(meta.Filename) != "" {
result.Filename = strings.TrimSpace(meta.Filename)
} else if target := strings.TrimSpace(result.TargetHost); target != "" {
result.Filename = "redfish://" + target
} else {
result.Filename = "redfish://snapshot"
}
}
if scan := scanRedfishTreePrivacy(rawPayloads); scan != nil {
result.PrivacyScan = scan
}
return result, "redfish", nil
}
// scanRedfishTreePrivacy runs the customer-data scan over the serialized Redfish
// tree (the only text corpus a live/replayed collection carries).
func scanRedfishTreePrivacy(rawPayloads map[string]any) *models.PrivacyScan {
if !parser.PrivacyScanEnabled() || rawPayloads == nil {
return nil
}
tree, ok := rawPayloads["redfish_tree"]
if !ok {
return nil
}
body, err := json.Marshal(tree)
if err != nil || len(body) == 0 {
return nil
}
return privacy.Scan([]privacy.File{{Path: "redfish_tree.json", Content: body}})
}