cms-website/tests/integration/import-full.test.ts

// Plan 3 Task 6 失败测试（先于实现）：编排集成 + 导入报告——四家写入器汇流。
// 覆盖契约（对照计划 Task 6 与前置事实 8/11/13、Task 3/5 审查移交清单）：
// 1. 全链（register wxr+media+media-map → 默认编排管道·真事件流）：content_entries=3 /
//    source_records=5 / terms=2+自建 0 / content_terms=1 / media_assets=2 / routes=12；
//    published_revision_id 全库 NULL（导入不发布——ADR-010）；mapConfig.locale 接线
//    （site.default_locale='zh-CN' → 全部 source_records.locale='zh-CN'——locale 只可能
//    来自编排接线，mini 无自带 locale）；报告 = 四家 counts 18 键全量 + 清洗统计 +
//    版本块 + issues 分组 + 路径块 + 适配器分段计时；
// 2. 二导幂等（换 key 重跑）：全部 counts 归零语义（termsProcessed/mediaDanglingRefs 等
//    按事件计键如实再现）、数据库行数不变、job 仍 succeeded_with_issues
//    （attachment 降级汇总 issue 必在——Plan 3 钉死语义：降级是处置事实非写入计数）；
// 3. 无 media 快照失败路径：media 域全 missing 报告不失败（空 manifest 语义已备）；
// 4. NULL-entry 占位行收编（Task 3 审查移交①）：六列命中 content_entry_id NULL 行 →
//    UPDATE 挂 entry（不撞 23505、sourceRecords 不虚增）；
// 5. stale 回收（义务④）：同 site 超 24h 的 queued/running 置 stale，新近 job 不受影响；
// 6. REPORT_WRITE_FAILED（Task 1 遗留）：报告写盘失败 → failed 终态、report_path 不落。
// 7. 失败报告部分冲刷（Task 6 审查 Fix 1）：事件流中途抛错 → job failed 且报告携带
//    eventsDispatched 进度计数 + 部分 content/term 计数（media/route finish 依赖库不调用）；
//    unsupported/error 事件的 reason/issue 归档 adapter 组（Fix 4——此前被丢弃）；
// 8. 主列表路径解析期防线（Fix 3）：--products-path/--news-path 含穿越段 →
//    INVALID_LIST_PATH 且零 job 行（建行前抛出——建行后再抛会留悬挂 running 行）。
// 9. HTML 报告与 issues 封顶（Task 8 兑现 Task 6 推迟项）：import.html 落盘且动态文本
//    全转义；issues 超上限（10k）→ 报告固化面截断 + issuesTruncated 计数；终态判定
//    用全量长度（截断不吞 succeeded_with_issues 事实）；对象层（import.json）保留原文。
// 运行于 globalSetup 临时库（ADR-015）；storage/报告根 os.tmpdir，finally 清理。
import { mkdir, mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join, resolve } from 'node:path'
import { fileURLToPath } from 'node:url'
import { describe, expect, it } from 'vitest'
import type { AdapterEvent } from '@sf/adapter-wp'
import { createImportJob, ImportError } from '../../apps/api/src/modules/import/import.service.js'
import { registerSource } from '../../apps/api/src/modules/source/register.service.js'
import { rand, withImmutableCleanup, withTestDb, type Db } from './helpers.js'

const FIXTURES_ROOT = fileURLToPath(new URL('../fixtures', import.meta.url))
const WXR_FIXTURE = resolve(FIXTURES_ROOT, 'wxr', 'mini.xml')

const PNG_SIG = Buffer.from([0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a])

/** 伪 PNG 体（魔数校验只看签名——载荷唯一避免跨测试撞哈希） */
function pngBytes(seed: string): Buffer {
  return Buffer.concat([PNG_SIG, Buffer.from(`png-body:${seed}`, 'latin1')])
}

/** 本文件写入的行清场：FK 反序（与 import-routes 同清单；两张不可变表走触发器开关） */
async function cleanupSiteRows(db: Db, siteId: string): Promise<void> {
  await db.execute(`delete from route_registry where site_id = '${siteId}'`)
  await db.execute(`delete from media_usages where site_id = '${siteId}'`)
  await db.execute(`delete from media_assets where site_id = '${siteId}'`)
  await db.execute(`delete from content_terms where site_id = '${siteId}'`)
  await db.execute(`delete from terms where site_id = '${siteId}'`)
  await db.execute(`delete from taxonomies where site_id = '${siteId}'`)
  await db.execute(`delete from source_records where site_id = '${siteId}'`)
  await db.execute(`delete from entry_locales where site_id = '${siteId}'`)
  await withImmutableCleanup(db, 'content_revisions', 'content_revisions_immutable', `site_id = '${siteId}'`)
  await db.execute(`delete from content_entries where site_id = '${siteId}'`)
  await db.execute(`delete from import_jobs where site_id = '${siteId}'`)
  await withImmutableCleanup(db, 'source_snapshots', 'source_snapshots_immutable', `site_id = '${siteId}'`)
  await db.execute(`delete from source_connections where site_id = '${siteId}'`)
  await db.execute(`delete from sites where id = '${siteId}'`)
}

interface Work {
  work: string
  storageRoot: string
  reportRoot: string
  allowedRoots: string[]
}

async function makeWork(prefix: string): Promise<Work> {
  const work = await mkdtemp(join(tmpdir(), `${prefix}-`))
  return {
    work,
    storageRoot: join(work, 'storage'),
    reportRoot: join(work, 'artifacts', 'import'),
    allowedRoots: [FIXTURES_ROOT, work],
  }
}

/** 全量登记（wxr + 媒体目录 + 侧车）——形态同 import-routes 全链用例；locale 可选注入 */
async function registerFull(
  db: Db,
  w: Work,
  spec: { locale?: string } = {},
): Promise<{ key: string; siteId: string; wxrId: string }> {
  const mediaDir = join(w.work, 'media')
  await mkdir(join(mediaDir, '2026/10'), { recursive: true })
  await writeFile(join(mediaDir, '2026/10/fixture-a.png'), pngBytes(`full-a-${rand()}`))
  const guidB = `b-${rand()}.png`
  await writeFile(join(mediaDir, guidB), pngBytes(`full-b-${rand()}`))
  const sidecarPath = join(w.work, 'media-map.json')
  await writeFile(
    sidecarPath,
    JSON.stringify([
      { sourceUrl: 'https://fixture.example/wp-content/uploads/2026/10/fixture-b.png', filePath: guidB },
    ]),
  )
  const key = `sffull-${rand()}`
  const reg = await registerSource(db, {
    siteKey: key,
    wxrPath: WXR_FIXTURE,
    mediaDir,
    mediaMapPath: sidecarPath,
    allowedRoots: w.allowedRoots,
    storageRoot: w.storageRoot,
    reportRoot: join(w.work, 'artifacts', 'register'),
    ...(spec.locale === undefined ? {} : { siteDefaults: { defaultLocale: spec.locale } }),
  })
  return { key, siteId: reg.siteId, wxrId: reg.snapshots.find((s) => s.kind === 'wxr')!.id }
}

/** 仅 wxr 登记（失败路径/收编场景——media_bundle/manual_url_list 缺席） */
async function registerWxrOnly(db: Db, w: Work): Promise<{ key: string; siteId: string; wxrId: string }> {
  const key = `sffull-${rand()}`
  const reg = await registerSource(db, {
    siteKey: key,
    wxrPath: WXR_FIXTURE,
    allowedRoots: w.allowedRoots,
    storageRoot: w.storageRoot,
    reportRoot: join(w.work, 'artifacts', 'register'),
  })
  return { key, siteId: reg.siteId, wxrId: reg.snapshots.find((s) => s.kind === 'wxr')!.id }
}

/** 导入报告读取（默认编排管道的产物断言面） */
async function readReport(w: Work, jobId: string): Promise<any> {
  return JSON.parse(await readFile(join(w.reportRoot, jobId, 'reports', 'import.json'), 'utf8'))
}

/** 单值计数便捷 */
async function countOf(db: Db, sql: string): Promise<number> {
  const rows = (await db.execute(sql)) as any
  return Number(rows[0].n)
}

describe('编排集成 + 导入报告（四家写入器汇流）', () => {
  it('全链（真事件流 + 默认编排管道）：18 键 counts 全量、published 全 NULL、locale 接线、清洗统计、issues 分组、报告路径/版本/计时块', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-chain')
      try {
        // locale 接线断言的实证设计（前置事实 8）：site 默认 locale 取 'zh-CN'——mini 无
        // 自带 locale，行 locale 只可能来自编排接线 mapConfig.locale=site.default_locale
        const { key, siteId, wxrId } = await registerFull(db, w, { locale: 'zh-CN' })
        try {
          const result = await createImportJob(db, {
            siteKey: key,
            snapshotId: wxrId,
            reportRoot: w.reportRoot,
          })
          expect(result.reused).toBe(false)
          // 悬空引用（media 203/204）×2 + attachment 降级汇总 ×1 → issues 非空
          expect(result.status).toBe('succeeded_with_issues')

          // 数据库行数对拍（计划 Task 6 钉死清单）
          expect(await countOf(db, `select count(*)::int as n from content_entries where site_id = '${siteId}'`)).toBe(3)
          expect(await countOf(db, `select count(*)::int as n from source_records where site_id = '${siteId}'`)).toBe(5)
          expect(await countOf(db, `select count(*)::int as n from terms where site_id = '${siteId}'`)).toBe(2)
          expect(await countOf(db, `select count(*)::int as n from content_terms where site_id = '${siteId}'`)).toBe(1)
          expect(await countOf(db, `select count(*)::int as n from media_assets where site_id = '${siteId}'`)).toBe(2)
          expect(await countOf(db, `select count(*)::int as n from route_registry where site_id = '${siteId}'`)).toBe(12)

          // published 全库 NULL（导入不发布——ADR-010）+ current 全设（导入产出工作修订）
          expect(
            await countOf(db, `select count(*)::int as n from entry_locales where site_id = '${siteId}' and published_revision_id is not null`),
          ).toBe(0)
          expect(
            await countOf(db, `select count(*)::int as n from entry_locales where site_id = '${siteId}' and current_revision_id is not null`),
          ).toBe(3)

          // locale 接线（前置事实 8）：全部 source_records 行 locale = site 默认（非空串）
          const locales = (await db.execute(`select distinct locale from source_records where site_id = '${siteId}'`)) as any
          expect(locales.map((r: any) => r.locale).sort()).toStrictEqual(['zh-CN'])

          // attachment 分派规则（前置事实 11）：2 条 attachment 行是 record-only 足迹（无 entry）
          expect(
            await countOf(db, `select count(*)::int as n from source_records where site_id = '${siteId}' and source_type = 'wp:attachment' and content_entry_id is null`),
          ).toBe(2)

          // content_terms：post 101 的 category 引用（is_primary=true——WP 单主分类近似）
          // （投影转 Boolean——postgres.js 原型差异会让 toStrictEqual 报"无视觉差异"失败）
          const ct = (await db.execute(`select ct.is_primary, t.slug from content_terms ct
            join terms t on t.id = ct.term_id where ct.site_id = '${siteId}'`)) as any
          expect(ct.map((r: any) => ({ isPrimary: Boolean(r.is_primary), slug: r.slug }))).toStrictEqual([
            { isPrimary: true, slug: 'company' },
          ])

          // 报告：四家 counts 18 键全量（全局命名空间求和聚合——键前缀互斥）
          const report = await readReport(w, result.jobId)
          expect(report.counts).toStrictEqual({
            contentEntries: 3,
            revisionsCreated: 3,
            sourceRecords: 5,
            skipped: 0,
            termsProcessed: 2,
            autoCreatedTerms: 0,
            contentTermsCreated: 1,
            mediaRegistered: 2,
            mediaFromSidecar: 1,
            mediaMissing: 0,
            mediaQuarantined: 0,
            mediaDanglingRefs: 2,
            mediaAmbiguous: 0,
            routesCreated: 12,
            routesUpdated: 0,
            routesRedirects: 2,
            routesCollisions: 0,
            routesExcludedQueries: 0,
          })

          // 清洗统计（分派循环收集 row 事件 sanitizeDiffs/changed）：mini 仅 post 101 正文
          // img 自闭合规范化零 diff 变形（changedRows=1、无 diff 条目——sparse 形态）
          expect(report.sanitize).toStrictEqual({ changedRows: 1, byDiffType: {} })

          // issues 分组（按写入器前缀）：flat issues 保持全量（3 条），分组归位
          expect(report.issues).toHaveLength(3)
          expect(report.issueGroups).toStrictEqual({
            content: [],
            term: [],
            media: report.issues.filter((i: string) => i.includes('悬空')),
            route: report.issues.filter((i: string) => i.includes('attachment 页降级')),
            adapter: [],
            orchestrator: [],
          })
          expect(report.issueGroups.media).toHaveLength(2)
          expect(report.issueGroups.route).toHaveLength(1)

          // 路径块（前置事实 9：CLI 参数来源记入报告——缺省值）+ 版本块 + 分段计时（真流）
          expect(report.paths).toStrictEqual({ productsPath: '/products/', newsPath: '/news/' })
          expect(report.versions).toStrictEqual({
            adapter: report.versions.adapter,
            mapping: report.versions.mapping,
            sanitizer: report.versions.sanitizer,
            parser: report.versions.parser,
          })
          expect(Object.keys(report.versions).sort()).toStrictEqual(['adapter', 'mapping', 'parser', 'sanitizer'])
          expect(typeof report.adapterTiming.parseMs).toBe('number')
          expect(typeof report.adapterTiming.sanitizeMs).toBe('number')
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('二导幂等（换 key）：全部写入计数归零、数据库行数不变、job 仍 succeeded_with_issues（降级汇总 issue 必在）', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-idem')
      try {
        const { key, siteId, wxrId } = await registerFull(db, w)
        try {
          const base = { siteKey: key, snapshotId: wxrId, reportRoot: w.reportRoot } as const
          const first = await createImportJob(db, { ...base })
          expect(first.status).toBe('succeeded_with_issues')

          const again = await createImportJob(db, { ...base, idempotencyKey: `sffull-rerun-${rand()}` })
          expect(again.reused).toBe(false)
          expect(again.status).toBe('succeeded_with_issues')

          // 写入计数全零语义：按事件计的键（termsProcessed/mediaDanglingRefs）如实再现
          const report = await readReport(w, again.jobId)
          expect(report.counts).toStrictEqual({
            contentEntries: 0,
            revisionsCreated: 0,
            sourceRecords: 0,
            skipped: 3,
            termsProcessed: 2,
            autoCreatedTerms: 0,
            contentTermsCreated: 0,
            mediaRegistered: 0,
            mediaFromSidecar: 0,
            mediaMissing: 0,
            mediaQuarantined: 0,
            mediaDanglingRefs: 2,
            mediaAmbiguous: 0,
            routesCreated: 0,
            routesUpdated: 0,
            routesRedirects: 0,
            routesCollisions: 0,
            routesExcludedQueries: 0,
          })

          // 数据库行数不变（幂等：零新行零修订零更新）
          expect(await countOf(db, `select count(*)::int as n from content_entries where site_id = '${siteId}'`)).toBe(3)
          expect(await countOf(db, `select count(*)::int as n from content_revisions where site_id = '${siteId}'`)).toBe(3)
          expect(await countOf(db, `select count(*)::int as n from source_records where site_id = '${siteId}'`)).toBe(5)
          expect(await countOf(db, `select count(*)::int as n from terms where site_id = '${siteId}'`)).toBe(2)
          expect(await countOf(db, `select count(*)::int as n from content_terms where site_id = '${siteId}'`)).toBe(1)
          expect(await countOf(db, `select count(*)::int as n from media_assets where site_id = '${siteId}'`)).toBe(2)
          expect(await countOf(db, `select count(*)::int as n from media_usages where site_id = '${siteId}'`)).toBe(3)
          expect(await countOf(db, `select count(*)::int as n from route_registry where site_id = '${siteId}'`)).toBe(12)

          // 降级汇总 issue 必在（Plan 3 钉死：降级是处置事实，重跑如实再现）+ 悬空 2 条
          const downgrade = report.issues.filter((i: string) => i.includes('attachment 页降级'))
          expect(downgrade).toHaveLength(1)
          expect(downgrade[0]).toContain('2 条')
          expect(report.issues.filter((i: string) => i.includes('悬空'))).toHaveLength(2)
          expect(report.issues).toHaveLength(3)
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('无 media 快照（只 wxr）：media 域全 missing 报告不失败（空 manifest 语义）+ 主列表路径参数入报告', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-nomedia')
      try {
        const { key, siteId, wxrId } = await registerWxrOnly(db, w)
        try {
          const result = await createImportJob(db, {
            siteKey: key,
            snapshotId: wxrId,
            reportRoot: w.reportRoot,
            productsPath: '/shop/',
          })
          expect(result.status).toBe('succeeded_with_issues')

          // 空清单语义：2 attachment 全 missing（不插行）、5 引用全悬空、路由 8 行
          // （3 站点页 + 3 内容 + 2 分类——301/asset 无资产可指）
          expect(await countOf(db, `select count(*)::int as n from media_assets where site_id = '${siteId}'`)).toBe(0)
          expect(await countOf(db, `select count(*)::int as n from route_registry where site_id = '${siteId}'`)).toBe(8)
          expect(
            await countOf(db, `select count(*)::int as n from route_registry where site_id = '${siteId}' and route_path = '/shop/'`),
          ).toBe(1)
          expect(
            await countOf(db, `select count(*)::int as n from route_registry where site_id = '${siteId}' and route_path = '/products/'`),
          ).toBe(0)

          const report = await readReport(w, result.jobId)
          expect(report.counts.mediaMissing).toBe(2)
          expect(report.counts.mediaRegistered).toBe(0)
          expect(report.counts.mediaDanglingRefs).toBe(5)
          expect(report.counts.routesCreated).toBe(8)
          expect(report.paths).toStrictEqual({ productsPath: '/shop/', newsPath: '/news/' })
          // attachment 301 目标缺席逐条报告（§7.6）+ missing/悬空——全部在 issues
          expect(report.issues.filter((i: string) => i.includes('301 目标缺席'))).toHaveLength(2)
          expect(report.issues.filter((i: string) => i.includes('missing'))).toHaveLength(2)
          expect(report.issues.filter((i: string) => i.includes('悬空'))).toHaveLength(5)
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('NULL-entry 占位行收编（Task 3 审查移交①）：六列命中 content_entry_id NULL 行 → UPDATE 挂 entry、不撞 23505、sourceRecords 不虚增', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-adopt')
      try {
        const { key, siteId, wxrId } = await registerWxrOnly(db, w)
        try {
          // 外源占位行（seed 模拟：六列身份 = wp:post/101 本快照、entry NULL）
          const seedJob = (await db.execute(`insert into import_jobs (id, site_id, source_snapshot_id, status,
            mapping_version, idempotency_key, attempt) values (gen_random_uuid(), '${siteId}', '${wxrId}',
            'succeeded', 'seed', 'seed-${rand()}', 1) returning id`)) as any
          const connRow = (await db.execute(`select source_connection_id from source_snapshots where id = '${wxrId}'`)) as any
          const seeded = (await db.execute(`insert into source_records (id, site_id, source_connection_id,
            source_snapshot_id, import_job_id, source_type, source_id, locale, raw_location, parse_status,
            content_entry_id) values (gen_random_uuid(), '${siteId}', '${connRow[0].source_connection_id}',
            '${wxrId}', '${seedJob[0].id}', 'wp:post', '101', 'en', 'wxr://item/101', 'imported', NULL)
            returning id`)) as any

          const result = await createImportJob(db, { siteKey: key, snapshotId: wxrId, reportRoot: w.reportRoot })
          expect(result.status).toBe('succeeded_with_issues')

          // 占位行被收编：挂 entry + checksum 前移（非新建行——sourceRecords=4 不是 5）
          const adopted = (await db.execute(`select content_entry_id, normalized_checksum from source_records
            where id = '${seeded[0].id}'`)) as any
          expect(adopted[0].content_entry_id).not.toBeNull()
          expect(adopted[0].normalized_checksum).not.toBeNull()
          const el = (await db.execute(`select current_revision_id, published_revision_id from entry_locales
            where site_id = '${siteId}' and content_entry_id = '${adopted[0].content_entry_id}'`)) as any
          expect(el[0].current_revision_id).not.toBeNull()
          expect(el[0].published_revision_id).toBeNull()

          const report = await readReport(w, result.jobId)
          expect(report.counts.contentEntries).toBe(3)
          expect(report.counts.revisionsCreated).toBe(3)
          expect(report.counts.sourceRecords).toBe(4) // 101 收编非新建（2 attachment + 111/121）
          expect(report.counts.skipped).toBe(0)
          // 收编行照常参与 term 关联与路由（101 的 entry 锚点就位）
          expect(report.counts.contentTermsCreated).toBe(1)
          expect(report.counts.routesCreated).toBe(8)
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('stale 回收（义务④）：同 site 超 24h 的 queued/running 置 stale；新近 job 不受影响；新 job 正常推进', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-stale')
      try {
        const { key, siteId, wxrId } = await registerWxrOnly(db, w)
        try {
          const oldH = 25
          const freshH = 1
          const seed = async (status: string, hoursAgo: number, idem: string): Promise<string> => {
            const rows = (await db.execute(`insert into import_jobs (id, site_id, source_snapshot_id, status,
              mapping_version, idempotency_key, attempt, started_at, created_at) values (gen_random_uuid(),
              '${siteId}', '${wxrId}', '${status}', 'seed', '${idem}', 1,
              now() - interval '${hoursAgo} hours', now() - interval '${hoursAgo} hours') returning id`)) as any
            return rows[0].id
          }
          const oldRunning = await seed('running', oldH, `stale-run-${rand()}`)
          const oldQueued = await seed('queued', oldH + 2, `stale-q-${rand()}`)
          const freshRunning = await seed('running', freshH, `stale-fresh-${rand()}`)

          const result = await createImportJob(db, {
            siteKey: key,
            snapshotId: wxrId,
            reportRoot: w.reportRoot,
            pipeline: async () => ({ counts: {}, issues: [] }),
          })
          expect(result.status).toBe('succeeded')

          const st = (rows: string[]) =>
            (db.execute(`select status, finished_at from import_jobs where id in (${rows.map((r) => `'${r}'`).join(',')})`) as any) as Promise<any>
          const oldRows = await st([oldRunning, oldQueued])
          for (const r of oldRows) {
            expect(r.status).toBe('stale')
            expect(r.finished_at).not.toBeNull()
          }
          const freshRows = await st([freshRunning])
          expect(freshRows[0].status).toBe('running') // 未超时不动（心跳列决策留 ADR-017）
          expect(freshRows[0].finished_at).toBeNull()
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('REPORT_WRITE_FAILED（Task 1 遗留）：报告目录不可建 → failed 终态、error_code 落列、report_path 不落', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-rwfail')
      try {
        const { key, siteId, wxrId } = await registerWxrOnly(db, w)
        try {
          // 用普通文件占住报告根：mkdir <file>/<jobId>/reports 必败（ENOTDIR/EEXIST）
          const blocker = join(w.work, 'blocker')
          await writeFile(blocker, 'not a directory')
          const result = await createImportJob(db, {
            siteKey: key,
            snapshotId: wxrId,
            reportRoot: blocker,
            pipeline: async () => ({ counts: { ok: 1 }, issues: [] }),
          })
          expect(result.status).toBe('failed')
          expect(result.reportPath).toBeNull()
          const job = (await db.execute(`select status, error_code, error_summary, report_path, finished_at
            from import_jobs where id = '${result.jobId}'`)) as any
          expect(job[0].status).toBe('failed')
          expect(job[0].error_code).toBe('REPORT_WRITE_FAILED')
          expect(String(job[0].error_summary)).toMatch(/^\[report\] /)
          expect(job[0].report_path).toBeNull() // 文件不存在不悬挂路径
          expect(job[0].finished_at).not.toBeNull()
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('失败报告部分冲刷（Fix 1）：事件流中途抛错 → failed + 报告含 eventsDispatched 与部分 content/term 计数；unsupported/error reason 归档 adapter 组（Fix 4）', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-flush')
      try {
        const { key, siteId } = await registerWxrOnly(db, w)
        try {
          // 手构流 + 真编排（注入 events 而不注入 pipeline）：3 个事件成功分派后，
          // 第 4 次拉取抛错——分派循环内炸（非写入器抛），编排器须冲刷部分产出后重抛
          async function* bomb(): AsyncGenerator<AdapterEvent, void, void> {
            yield {
              kind: 'row',
              row: {
                sourceType: 'wp:post',
                sourceId: '301',
                status: 'publish',
                locale: 'en',
                taxonomyRefs: [{ taxonomy: 'category', sourceTermId: 'company' }],
                attachmentRefs: [],
                seo: {},
                knownFields: {},
                extras: {},
                rawLocation: 'wxr://item/301',
              },
              issues: [],
              sanitizeDiffs: [],
              changed: false,
            }
            yield {
              kind: 'unsupported',
              sourceType: 'wp:nav_menu_item',
              reason: 'post_type 未配置映射',
              rawLocation: 'wxr://item/7',
              postId: '68',
            }
            yield { kind: 'error', sourceType: 'wp:post', issue: 'post_id 缺失或非法', rawLocation: 'wxr://item/9' }
            throw new Error('BOOM: 事件流在第 4 次拉取时爆炸')
          }
          const result = await createImportJob(db, { siteKey: key, reportRoot: w.reportRoot, events: bomb() })
          expect(result.status).toBe('failed')
          expect(result.reportPath).not.toBeNull()

          const job = (await db.execute(`select error_code, error_summary, report_path, finished_at
            from import_jobs where id = '${result.jobId}'`)) as any
          expect(job[0].error_code).toBe('PIPELINE_FAILED')
          expect(String(job[0].error_summary)).toMatch(/^\[pipeline\] /)
          expect(job[0].report_path).not.toBeNull() // 失败也落报告（部分产出可审计）
          expect(job[0].finished_at).not.toBeNull()

          const report = await readReport(w, result.jobId)
          expect(report.status).toBe('failed')
          expect(report.error.code).toBe('PIPELINE_FAILED')
          // 部分冲刷面：成功分派的 3 事件的 content/term 计数 + 进度计数 eventsDispatched
          //（media/route finish 依赖库与先序产物——失败路径不调用，其键缺席）
          expect(report.counts).toStrictEqual({
            eventsDispatched: 3,
            contentEntries: 1,
            revisionsCreated: 1,
            sourceRecords: 3,
            skipped: 0,
            unsupportedRecords: 1,
            failedRecords: 1,
            termsProcessed: 0,
            autoCreatedTerms: 1,
            contentTermsCreated: 1,
          })
          // unsupported/error 的 reason/issue 归档 adapter 组（Fix 4——此前被静默丢弃）
          expect(report.issueGroups.adapter).toHaveLength(2)
          expect(report.issueGroups.adapter[0]).toContain('不支持对象')
          expect(report.issueGroups.adapter[0]).toContain('post_type 未配置映射')
          expect(report.issueGroups.adapter[1]).toContain('适配器错误')
          expect(report.issueGroups.adapter[1]).toContain('post_id 缺失或非法')
          // 冲刷的 issue 同时在 flat 清单；content/term/media/route 组空（本流无其问题）
          expect(report.issues).toHaveLength(2)
          expect(report.issueGroups).toStrictEqual({
            content: [],
            term: [],
            media: [],
            route: [],
            adapter: report.issues,
            orchestrator: [],
          })
          // 落库审计：已分派事件的部分写入保留（各写入器单语句已提交，失败不回滚）
          expect(await countOf(db, `select count(*)::int as n from content_entries where site_id = '${siteId}'`)).toBe(1)
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('主列表路径解析期防线（Fix 3）：--products-path/--news-path 含穿越段 → INVALID_LIST_PATH、零 job 行（建行前抛出）', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-path')
      try {
        const { key, siteId } = await registerWxrOnly(db, w)
        try {
          const cases: Array<[string, { productsPath?: string; newsPath?: string }]> = [
            ['productsPath 穿越段', { productsPath: '/../x/' }],
            ['newsPath 穿越段', { newsPath: '/news/../../etc/' }],
          ]
          for (const [label, paths] of cases) {
            const err: ImportError = await createImportJob(db, {
              siteKey: key,
              reportRoot: w.reportRoot,
              ...paths,
            }).then(
              () => {
                throw new Error(`用例「${label}」不应成功`)
              },
              (e: ImportError) => e,
            )
            expect(err, label).toBeInstanceOf(ImportError)
            expect(err.code, label).toBe('INVALID_LIST_PATH')
            expect(err.message, label).toContain('..') // 消息携带原始入参（操作者可定位）
          }
          // 零 job 行：解析期失败（建行前）——建行后再抛会留悬挂 running 行
          expect(await countOf(db, `select count(*)::int as n from import_jobs where site_id = '${siteId}'`)).toBe(0)
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })

  it('HTML 报告与 issues 封顶（Task 8）：import.html 落盘且转义；issues 超上限 → 截断 + issuesTruncated、终态判定用全量长度、JSON 对象层留原文', async () => {
    await withTestDb(async (db) => {
      const w = await makeWork('sf-full-html')
      try {
        const { key, siteId } = await registerWxrOnly(db, w)
        try {
          // 恶意 payload（清洗前 excerpt 形态）+ 超上限 issues（10_003 条）
          const payload = '<script src="https://evil.example/x.js"></script>'
          const total = 10_003
          const issues = Array.from({ length: total }, (_, i) =>
            i === 0 ? `${payload}悬空 attachment 引用：${i}` : `悬空 attachment 引用：${i}`,
          )
          const result = await createImportJob(db, {
            siteKey: key,
            reportRoot: w.reportRoot,
            pipeline: async () => ({ counts: { contentEntries: 0 }, issues, issueGroups: { media: issues } }),
          })
          // 终态判定在截断前的全量长度上做（截断是报告固化层语义，不吞终态事实）
          expect(result.status).toBe('succeeded_with_issues')

          const report = await readReport(w, result.jobId)
          expect(report.issues).toHaveLength(10_000)
          expect(report.issuesTruncated).toBe(3)
          expect(report.issueGroups.media).toHaveLength(10_000) // 各组同限截断
          expect(report.issues[0]).toContain('<script') // JSON 对象层保留原文（转义只在渲染层）

          // HTML：落盘（与 import.json 同目录）+ 全动态文本转义 + 封顶注记
          const html = await readFile(join(w.reportRoot, result.jobId, 'reports', 'import.html'), 'utf8')
          expect(html).not.toContain('<script') // 骨架无 script，出现即 XSS 面
          expect(html).toContain('&lt;script src=&quot;https://evil.example/x.js&quot;&gt;')
          expect(html).toContain('（另有 3 条超出固化上限，仅计数）')
          expect(html).toContain('悬空 attachment 引用：0')
        } finally {
          await cleanupSiteRows(db, siteId)
        }
      } finally {
        await rm(w.work, { recursive: true, force: true })
      }
    })
  })
})