LokiStack/backend/services/ai_redact_test.go

package services

import (
	"strings"
	"testing"
)

// 脱敏的两条底线：
//   1) 凭据必须挡住（否则把 key 发给外部模型）；
//   2) 排查必需的信息必须留着（IP/端口/命名空间/错误码），
//      否则模型给不出有用结论 —— 这比"脱得太干净"更常见。
func TestRedactText(t *testing.T) {
	in := `2026-10-30 12:00:01 ERROR redis client: dial tcp 172.19.16.17:6379: connect: connection refused
password=Sup3rS3cret! user-admin
Authorization: Bearer eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxIn0.abcdefghijklmn
url: mysql://appuser:P@ssw0rd@10.2.3.4:3306/cex
contact: ops@example.com phone: 13800138000
accessKey=AKIAIOSFODNN7EXAMPLE`

	out, invalid := RedactText(in, nil)
	if len(invalid) != 0 {
		t.Fatalf("内置规则不应产生无效正则: %v", invalid)
	}

	mustRedact := []string{"Sup3rS3cret", "eyJhbGciOiJIUzI1NiJ9", "P@ssw0rd", "ops@example.com", "13800138000", "AKIAIOSFODNN7EXAMPLE"}
	for _, secret := range mustRedact {
		if strings.Contains(out, secret) {
			t.Errorf("敏感内容未脱敏: %q\n%s", secret, out)
		}
	}

	mustKeep := []string{"172.19.16.17:6379", "connection refused", "10.2.3.4:3306", "redis"}
	for _, keep := range mustKeep {
		if !strings.Contains(out, keep) {
			t.Errorf("排查必需的信息被误删: %q\n%s", keep, out)
		}
	}
}

// 用户自定义正则写错不能拖垮整次分析：跳过并在返回值里报告。
func TestRedactTextInvalidExtraRule(t *testing.T) {
	out, invalid := RedactText("hello internal-id-12345", []string{`(unclosed`, `internal-id-\d+`})
	if len(invalid) != 1 || invalid[0] != `(unclosed` {
		t.Errorf("应报告 1 条无效规则，实际 %v", invalid)
	}
	if strings.Contains(out, "internal-id-12345") {
		t.Errorf("有效自定义规则应生效: %s", out)
	}
}

// 模型经常不按 JSON 返回，解析必须宽容，不能只报"解析失败"。
func TestParseAIResultTolerance(t *testing.T) {
	cases := []struct {
		name string
		in   string
		want string // 期望的 summary 片段
	}{
		{
			name: "标准 JSON",
			in:   `{"summary":"日志量正常","findings":[],"actions":[],"unknowns":[]}`,
			want: "日志量正常",
		},
		{
			name: "包了 ```json 代码块",
			in:   "```json\n{\"summary\":\"体积上涨 2 倍\",\"findings\":[{\"title\":\"t\",\"evidence\":\"e\",\"severity\":\"high\"}],\"actions\":[],\"unknowns\":[]}\n```",
			want: "体积上涨 2 倍",
		},
		{
			name: "前后加了解释",
			in:   `分析如下：{"summary":"存在告警","findings":[],"actions":[],"unknowns":[]} 希望有帮助`,
			want: "存在告警",
		},
		{
			name: "纯文本（降级）",
			in:   "看起来一切正常，没有异常日志。",
			want: "看起来一切正常",
		},
	}
	for _, c := range cases {
		t.Run(c.name, func(t *testing.T) {
			got := parseAIResult(c.in)
			if !strings.Contains(got.Summary, c.want) {
				t.Errorf("summary 不符: got %q want contains %q", got.Summary, c.want)
			}
		})
	}
}