feat(import): term 物化与缺失自建
Plan 3 Task 2：createTermWriter 管道写入器——双源物化分类域。 - wp:term 事件：taxonomies（key→object_type 映射 + public_base_path 前置事实 9 常量）+ terms（source_id=term_id 字符串） - row 的 taxonomyRefs miss 时自建（source_id=auto:<nicename>、slug=nicename； phase2-smoke 实证真实 WXR 的 wp:term 表缺 category/post_tag 整域）；同 nicename 多次引用只建一条（内存 (taxonomy,slug) 索引 + UNIQUE 兜底） - 单遍流式 + 收编：WXR 文档序 items 先于 wp:term——row 先到自建、wp:term 后到 就地 UPDATE 扶正 source_id/name，两种顺序终态一致（测试钉死顺序无关性） - content_terms：is_primary 每 (entry, taxonomy) 首个 true 余 false（WP 单主分类 近似）；row 无 content entry → term 仍物化、关联跳过 + issue（禁静默） - ctx 加法扩展 events: AsyncIterable<AdapterEvent>（测试手构注入，Task 6 接真流） - Task 1 遗留两行：ImportErrorCode 补 REPORT_WRITE_FAILED、ctx.db 事务边界 JSDoc Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
浅念
@@ -0,0 +1,465 @@
|
||||
// Plan 3 Task 2 失败测试（先于实现）：term 物化（含自建缺失）。
|
||||
// 覆盖契约（对照计划 Task 2 与前置事实 1/9、phase2-smoke 移交项①）：
|
||||
// 1. mini.xml 全链：wp:term 事件 → taxonomies（key→object_type 映射 + public_base_path
|
||||
// 前置事实 9 常量）+ terms（source_id=term_id 字符串）+ content_terms（entry↔term，
|
||||
// is_primary 近似）。mini 文档序 items 先于 wp:term——row 先到时按 nicename 自建、
|
||||
// wp:term 后到**收编**（source_id/name 就地扶正，无 auto: 残留），终态与 term 先行序
|
||||
// 一致（顺序无关性）；
|
||||
// 2. 自建缺失（phase2-smoke：真实 WXR 的 wp:term 表缺 category/post_tag 整域）：row 的
|
||||
// taxonomyRefs (domain, nicename) 无对应 term → 自动建（source_id=auto:<nicename>、
|
||||
// slug=nicename、name=nicename——UniversalRow 不携带 <category> 文本，实现层 JSDoc 注明）；
|
||||
// 同 nicename 多次引用只建一条（应用层索引 + UNIQUE(site,taxonomy,source_id) 兜底）；
|
||||
// 3. content_terms：is_primary 每 (entry, taxonomy) 首个 true 余 false（WP 单主分类近似）；
|
||||
// row 无对应 content entry → term 仍物化、关联跳过 + issue（不静默丢弃）；
|
||||
// 4. counts：termsProcessed / autoCreatedTerms / contentTermsCreated；正常路径 issues 空；
|
||||
// 5. 幂等：同流重跑（换幂等键新 job）taxonomies/terms/content_terms 均不增行。
|
||||
// 运行于 globalSetup 临时库（ADR-015）；报告根用 os.tmpdir 临时目录，finally 清理。
|
||||
// content entry 由测试内 seed 模拟 Task 3 内容写入器的最小落库足迹——source_records.
|
||||
// content_entry_id 是 term 关联的消费接缝（Task 6 编排时由内容写入器保证存在）。
|
||||
import { createReadStream } from 'node:fs'
|
||||
import { mkdtemp, readFile, rm } 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 { runWxrAdapter, type AdapterEvent } from '@sf/adapter-wp'
|
||||
import type { UniversalRow } from '@sf/contracts'
|
||||
import type { ImportJobContext, ImportPipeline } from '../../apps/api/src/modules/import/import.service.js'
|
||||
import { createImportJob } from '../../apps/api/src/modules/import/import.service.js'
|
||||
import { createTermWriter } from '../../apps/api/src/modules/import/term-writer.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')
|
||||
|
||||
/** 手构事件流的 AsyncIterable 包装（每次调用产新迭代器——重跑各流独立） */
|
||||
async function* eventsOf(events: AdapterEvent[]): AsyncGenerator<AdapterEvent, void, void> {
|
||||
yield* events
|
||||
}
|
||||
|
||||
/** db.execute 行对象规整：postgres.js 行对象的原型差异会让 toStrictEqual 报"无视觉差异"失败——浅拷贝到普通对象 */
|
||||
function plain(rows: any[]): any[] {
|
||||
return rows.map((r) => ({ ...r }))
|
||||
}
|
||||
|
||||
/** 手构 row 事件（全必填字段的最小 UniversalRow） */
|
||||
function rowEvent(spec: {
|
||||
sourceType?: string
|
||||
sourceId: string
|
||||
taxonomyRefs: Array<{ taxonomy: string; sourceTermId: string }>
|
||||
}): AdapterEvent {
|
||||
const row: UniversalRow = {
|
||||
sourceType: spec.sourceType ?? 'wp:post',
|
||||
sourceId: spec.sourceId,
|
||||
status: 'publish',
|
||||
locale: 'en',
|
||||
taxonomyRefs: spec.taxonomyRefs,
|
||||
attachmentRefs: [],
|
||||
seo: {},
|
||||
knownFields: {},
|
||||
extras: {},
|
||||
rawLocation: `wxr://item/${spec.sourceId}`,
|
||||
}
|
||||
return { kind: 'row', row, issues: [], sanitizeDiffs: [], changed: false }
|
||||
}
|
||||
|
||||
/** 手构 wp:term 事件 */
|
||||
function termEvent(spec: { termId: number | null; taxonomy: string; slug: string; name: string }): AdapterEvent {
|
||||
return {
|
||||
kind: 'term',
|
||||
term: {
|
||||
rawLocation: `wxr://term/${spec.slug}`,
|
||||
termId: spec.termId,
|
||||
taxonomy: spec.taxonomy,
|
||||
slug: spec.slug,
|
||||
name: spec.name,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 模拟 Task 3 内容写入器的最小落库足迹：content_entries + source_records（含
|
||||
* content_entry_id 接缝列）。幂等（identity 命中即复用）——重跑场景同流再 seed 不增行。
|
||||
*/
|
||||
async function seedContentEntry(
|
||||
ctx: ImportJobContext,
|
||||
spec: { sourceType: string; sourceId: string; typeKey: string; locale?: string },
|
||||
): Promise<void> {
|
||||
const locale = spec.locale ?? 'en'
|
||||
const found = (await ctx.db.execute(`select content_entry_id from source_records
|
||||
where site_id = '${ctx.siteId}' and source_connection_id = '${ctx.connectionId}'
|
||||
and source_type = '${spec.sourceType}' and source_id = '${spec.sourceId}' and locale = '${locale}'
|
||||
and content_entry_id is not null
|
||||
order by created_at desc limit 1`)) as any
|
||||
if (found.length > 0) return
|
||||
const entry = (await ctx.db.execute(`insert into content_entries (id, site_id, type_key, lifecycle_status)
|
||||
values (gen_random_uuid(), '${ctx.siteId}', '${spec.typeKey}', 'active') returning id`)) as any
|
||||
await ctx.db.execute(`insert into source_records (id, site_id, source_connection_id, source_snapshot_id, import_job_id,
|
||||
source_type, source_id, locale, raw_location, parse_status, content_entry_id)
|
||||
values (gen_random_uuid(), '${ctx.siteId}', '${ctx.connectionId}', '${ctx.wxrSnapshot.id}', '${ctx.jobId}',
|
||||
'${spec.sourceType}', '${spec.sourceId}', '${locale}', 'wxr://item/${spec.sourceId}', 'mapped', '${entry[0].id}')`)
|
||||
}
|
||||
|
||||
/** 测试管道：先 seed（模拟内容写入器足迹）再跑 term 写入器——Task 6 编排的雏形 */
|
||||
function seededTermWriter(seed: (ctx: ImportJobContext) => Promise<void>): ImportPipeline {
|
||||
return async (ctx) => {
|
||||
await seed(ctx)
|
||||
return createTermWriter()(ctx)
|
||||
}
|
||||
}
|
||||
|
||||
/** 本文件写入的行清场：FK 反序（terms 自引用单语句全删安全；快照不可变走触发器开关） */
|
||||
async function cleanupSiteRows(db: Db, siteId: string): Promise<void> {
|
||||
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 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 = '${siteId}'`)
|
||||
}
|
||||
|
||||
/** mini 三内容行的 seed（前置事实 11 的 typeKey 映射：wp:post→news_article、wp:page→basic_page、wp:product→product） */
|
||||
async function seedMiniEntries(ctx: ImportJobContext): Promise<void> {
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:post', sourceId: '101', typeKey: 'news_article' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:product', sourceId: '111', typeKey: 'product' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:page', sourceId: '121', typeKey: 'basic_page' })
|
||||
}
|
||||
|
||||
describe('term 物化（含自建缺失）', () => {
|
||||
it('mini.xml 全链：taxonomies 常量映射 + terms(source_id=term_id) + content_terms(is_primary) + 收编（row 先到 wp:term 后到）+ counts/issues', async () => {
|
||||
await withTestDb(async (db) => {
|
||||
const work = await mkdtemp(join(tmpdir(), 'sf-terms-'))
|
||||
try {
|
||||
const key = `sfterm-${rand()}`
|
||||
const reg = await registerSource(db, {
|
||||
siteKey: key,
|
||||
wxrPath: WXR_FIXTURE,
|
||||
allowedRoots: [FIXTURES_ROOT],
|
||||
storageRoot: join(work, 'storage'),
|
||||
reportRoot: join(work, 'artifacts', 'register'),
|
||||
})
|
||||
try {
|
||||
const wxr = reg.snapshots.find((s) => s.kind === 'wxr')!
|
||||
const result = await createImportJob(db, {
|
||||
siteKey: key,
|
||||
snapshotId: wxr.id,
|
||||
reportRoot: join(work, 'artifacts', 'import'),
|
||||
events: runWxrAdapter(createReadStream(WXR_FIXTURE), { mapConfig: { locale: 'en' } }),
|
||||
pipeline: seededTermWriter(seedMiniEntries),
|
||||
})
|
||||
expect(result.reused).toBe(false)
|
||||
expect(result.status).toBe('succeeded')
|
||||
|
||||
// taxonomies：key→object_type 映射 + 前置事实 9 常量（public_base_path 仅记录）
|
||||
const tax = (await db.execute(`select key, object_type, public_base_path from taxonomies
|
||||
where site_id = '${reg.siteId}' order by key`)) as any
|
||||
expect(plain(tax)).toStrictEqual([
|
||||
{ key: 'category', object_type: 'post', public_base_path: '/category/' },
|
||||
{ key: 'product_cat', object_type: 'product', public_base_path: '/product-category/' },
|
||||
])
|
||||
|
||||
// terms：source_id=term_id 字符串；mini 文档序 items 先于 wp:term——post 101 的
|
||||
// category/company 引用先到（自建 auto:company），wp:term 31 后到收编扶正
|
||||
const termsRows = (await db.execute(`select t.source_id, t.slug, t.name, x.key as taxonomy
|
||||
from terms t join taxonomies x on x.id = t.taxonomy_id
|
||||
where t.site_id = '${reg.siteId}' order by x.key`)) as any
|
||||
expect(plain(termsRows)).toStrictEqual([
|
||||
{ source_id: '31', slug: 'company', name: 'Company', taxonomy: 'category' },
|
||||
{ source_id: '32', slug: 'pipe-fittings', name: 'Pipe Fittings', taxonomy: 'product_cat' },
|
||||
])
|
||||
const autoLeft = (await db.execute(`select count(*)::int as n from terms
|
||||
where site_id = '${reg.siteId}' and source_id like 'auto:%'`)) as any
|
||||
expect(autoLeft[0].n).toBe(0)
|
||||
|
||||
// content_terms：post 101 ↔ category/company（单引用即首引用，is_primary=true）
|
||||
const ct = (await db.execute(`select content_entry_id, term_id, is_primary from content_terms
|
||||
where site_id = '${reg.siteId}'`)) as any
|
||||
expect(ct).toHaveLength(1)
|
||||
const entry101 = (await db.execute(`select content_entry_id from source_records
|
||||
where site_id = '${reg.siteId}' and source_type = 'wp:post' and source_id = '101'`)) as any
|
||||
const term31 = (await db.execute(`select id from terms
|
||||
where site_id = '${reg.siteId}' and source_id = '31'`)) as any
|
||||
expect(ct[0].content_entry_id).toBe(entry101[0].content_entry_id)
|
||||
expect(ct[0].term_id).toBe(term31[0].id)
|
||||
expect(ct[0].is_primary).toBe(true)
|
||||
|
||||
// 报告：counts 三键（自建终态 0——瞬态自建已被收编）+ issues 空（正常路径）
|
||||
const report = JSON.parse(
|
||||
await readFile(join(work, 'artifacts', 'import', result.jobId, 'reports', 'import.json'), 'utf8'),
|
||||
) as { status: string; counts: Record<string, number>; issues: string[] }
|
||||
expect(report.status).toBe('succeeded')
|
||||
expect(report.counts).toStrictEqual({
|
||||
termsProcessed: 2,
|
||||
autoCreatedTerms: 0,
|
||||
contentTermsCreated: 1,
|
||||
})
|
||||
expect(report.issues).toStrictEqual([])
|
||||
} finally {
|
||||
await cleanupSiteRows(db, reg.siteId)
|
||||
}
|
||||
} finally {
|
||||
await rm(work, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
it('自建缺失 term（手构缺表场景）：auto: 前缀 + 同 nicename 单条 + is_primary 规则 + 无 entry 跳过关联 + 未知 taxonomy 兜底', async () => {
|
||||
await withTestDb(async (db) => {
|
||||
const work = await mkdtemp(join(tmpdir(), 'sf-terms-'))
|
||||
try {
|
||||
const key = `sfterm-${rand()}`
|
||||
const reg = await registerSource(db, {
|
||||
siteKey: key,
|
||||
wxrPath: WXR_FIXTURE,
|
||||
allowedRoots: [FIXTURES_ROOT],
|
||||
storageRoot: join(work, 'storage'),
|
||||
reportRoot: join(work, 'artifacts', 'register'),
|
||||
})
|
||||
try {
|
||||
const wxr = reg.snapshots.find((s) => s.kind === 'wxr')!
|
||||
// 缺表场景：category/post_tag 无任何 wp:term 事件（照真实 hesupipe WXR）；
|
||||
// nav_menu 是表外 taxonomy（wp:term 有、常量表无——兜底映射钉行为）
|
||||
const events: AdapterEvent[] = [
|
||||
rowEvent({ sourceId: '501', taxonomyRefs: [{ taxonomy: 'category', sourceTermId: 'company-news' }] }),
|
||||
rowEvent({ sourceId: '502', taxonomyRefs: [{ taxonomy: 'category', sourceTermId: 'company-news' }] }),
|
||||
rowEvent({
|
||||
sourceId: '503',
|
||||
taxonomyRefs: [
|
||||
{ taxonomy: 'category', sourceTermId: 'news-a' },
|
||||
{ taxonomy: 'category', sourceTermId: 'news-b' },
|
||||
],
|
||||
}),
|
||||
rowEvent({
|
||||
sourceType: 'wp:product',
|
||||
sourceId: '504',
|
||||
taxonomyRefs: [
|
||||
{ taxonomy: 'product_cat', sourceTermId: 'pc-1' },
|
||||
{ taxonomy: 'product_tag', sourceTermId: 'pt-1' },
|
||||
],
|
||||
}),
|
||||
// 505 故意不 seed entry：term 仍物化、关联跳过 + issue
|
||||
rowEvent({ sourceId: '505', taxonomyRefs: [{ taxonomy: 'post_tag', sourceTermId: 'orphan-tag' }] }),
|
||||
termEvent({ termId: 77, taxonomy: 'nav_menu', slug: 'mainmenu', name: 'Main Menu' }),
|
||||
]
|
||||
const result = await createImportJob(db, {
|
||||
siteKey: key,
|
||||
snapshotId: wxr.id,
|
||||
reportRoot: join(work, 'artifacts', 'import'),
|
||||
events: eventsOf(events),
|
||||
pipeline: seededTermWriter(async (ctx) => {
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:post', sourceId: '501', typeKey: 'news_article' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:post', sourceId: '502', typeKey: 'news_article' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:post', sourceId: '503', typeKey: 'news_article' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:product', sourceId: '504', typeKey: 'product' })
|
||||
}),
|
||||
})
|
||||
expect(result.status).toBe('succeeded_with_issues')
|
||||
|
||||
// 自建 terms：source_id=auto:<nicename>、slug=nicename、name=nicename；
|
||||
// company-news 两处引用只建一条（应用层索引；UNIQUE(site,taxonomy,source_id) 兜底）
|
||||
const autoTerms = (await db.execute(`select t.source_id, t.slug, t.name, x.key as taxonomy
|
||||
from terms t join taxonomies x on x.id = t.taxonomy_id
|
||||
where t.site_id = '${reg.siteId}' and t.source_id like 'auto:%' order by t.source_id`)) as any
|
||||
expect(plain(autoTerms)).toStrictEqual([
|
||||
{ source_id: 'auto:company-news', slug: 'company-news', name: 'company-news', taxonomy: 'category' },
|
||||
{ source_id: 'auto:news-a', slug: 'news-a', name: 'news-a', taxonomy: 'category' },
|
||||
{ source_id: 'auto:news-b', slug: 'news-b', name: 'news-b', taxonomy: 'category' },
|
||||
{ source_id: 'auto:orphan-tag', slug: 'orphan-tag', name: 'orphan-tag', taxonomy: 'post_tag' },
|
||||
{ source_id: 'auto:pc-1', slug: 'pc-1', name: 'pc-1', taxonomy: 'product_cat' },
|
||||
{ source_id: 'auto:pt-1', slug: 'pt-1', name: 'pt-1', taxonomy: 'product_tag' },
|
||||
])
|
||||
|
||||
// 未知 taxonomy 兜底（非静默）：nav_menu → object_type 'post'、/nav_menu/ + issue
|
||||
const navTax = (await db.execute(`select object_type, public_base_path from taxonomies
|
||||
where site_id = '${reg.siteId}' and key = 'nav_menu'`)) as any
|
||||
expect(plain(navTax)).toStrictEqual([{ object_type: 'post', public_base_path: '/nav_menu/' }])
|
||||
const navTerm = (await db.execute(`select t.source_id, t.name from terms t
|
||||
join taxonomies x on x.id = t.taxonomy_id
|
||||
where t.site_id = '${reg.siteId}' and x.key = 'nav_menu'`)) as any
|
||||
expect(plain(navTerm)).toStrictEqual([{ source_id: '77', name: 'Main Menu' }])
|
||||
|
||||
// content_terms：is_primary 每 (entry, taxonomy) 首个 true 余 false；
|
||||
// 505 无 entry → 不关联（term 已物化）
|
||||
const ct = (await db.execute(`select r.source_id as row_id, x.key as taxonomy, t.slug, c.is_primary
|
||||
from content_terms c
|
||||
join source_records r on r.content_entry_id = c.content_entry_id
|
||||
join terms t on t.id = c.term_id
|
||||
join taxonomies x on x.id = t.taxonomy_id
|
||||
where c.site_id = '${reg.siteId}' order by r.source_id, t.slug`)) as any
|
||||
expect(plain(ct)).toStrictEqual([
|
||||
{ row_id: '501', taxonomy: 'category', slug: 'company-news', is_primary: true },
|
||||
{ row_id: '502', taxonomy: 'category', slug: 'company-news', is_primary: true },
|
||||
{ row_id: '503', taxonomy: 'category', slug: 'news-a', is_primary: true },
|
||||
{ row_id: '503', taxonomy: 'category', slug: 'news-b', is_primary: false },
|
||||
{ row_id: '504', taxonomy: 'product_cat', slug: 'pc-1', is_primary: true },
|
||||
{ row_id: '504', taxonomy: 'product_tag', slug: 'pt-1', is_primary: true },
|
||||
])
|
||||
|
||||
// 报告：自建 6（orphan-tag 计入——物化不依赖 entry）；两条 issue（505 无 entry + nav_menu 兜底）
|
||||
const report = JSON.parse(
|
||||
await readFile(join(work, 'artifacts', 'import', result.jobId, 'reports', 'import.json'), 'utf8'),
|
||||
) as { status: string; counts: Record<string, number>; issues: string[] }
|
||||
expect(report.counts).toStrictEqual({
|
||||
termsProcessed: 1,
|
||||
autoCreatedTerms: 6,
|
||||
contentTermsCreated: 6,
|
||||
})
|
||||
expect(report.issues).toHaveLength(2)
|
||||
expect(report.issues.some((i) => i.includes('505') && i.includes('content entry'))).toBe(true)
|
||||
expect(report.issues.some((i) => i.includes('nav_menu'))).toBe(true)
|
||||
} finally {
|
||||
await cleanupSiteRows(db, reg.siteId)
|
||||
}
|
||||
} finally {
|
||||
await rm(work, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
it('顺序无关性（term 先行序）：wp:term 先到 → row 后到直连既有 term，零自建、终态与 row 先行序一致', async () => {
|
||||
await withTestDb(async (db) => {
|
||||
const work = await mkdtemp(join(tmpdir(), 'sf-terms-'))
|
||||
try {
|
||||
const key = `sfterm-${rand()}`
|
||||
const reg = await registerSource(db, {
|
||||
siteKey: key,
|
||||
wxrPath: WXR_FIXTURE,
|
||||
allowedRoots: [FIXTURES_ROOT],
|
||||
storageRoot: join(work, 'storage'),
|
||||
reportRoot: join(work, 'artifacts', 'register'),
|
||||
})
|
||||
try {
|
||||
const wxr = reg.snapshots.find((s) => s.kind === 'wxr')!
|
||||
const events: AdapterEvent[] = [
|
||||
termEvent({ termId: 31, taxonomy: 'category', slug: 'company', name: 'Company' }),
|
||||
termEvent({ termId: 88, taxonomy: 'product_tag', slug: 'special', name: 'Special' }),
|
||||
rowEvent({ sourceId: '101', taxonomyRefs: [{ taxonomy: 'category', sourceTermId: 'company' }] }),
|
||||
rowEvent({
|
||||
sourceType: 'wp:product',
|
||||
sourceId: '111',
|
||||
taxonomyRefs: [{ taxonomy: 'product_tag', sourceTermId: 'special' }],
|
||||
}),
|
||||
]
|
||||
const result = await createImportJob(db, {
|
||||
siteKey: key,
|
||||
snapshotId: wxr.id,
|
||||
reportRoot: join(work, 'artifacts', 'import'),
|
||||
events: eventsOf(events),
|
||||
pipeline: seededTermWriter(async (ctx) => {
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:post', sourceId: '101', typeKey: 'news_article' })
|
||||
await seedContentEntry(ctx, { sourceType: 'wp:product', sourceId: '111', typeKey: 'product' })
|
||||
}),
|
||||
})
|
||||
expect(result.status).toBe('succeeded')
|
||||
|
||||
// 与 mini 序（row 先到 + 收编）同一终态：source_id=term_id、name=wp:term 权威名
|
||||
const termsRows = (await db.execute(`select t.source_id, t.slug, t.name, x.key as taxonomy
|
||||
from terms t join taxonomies x on x.id = t.taxonomy_id
|
||||
where t.site_id = '${reg.siteId}' order by x.key`)) as any
|
||||
expect(plain(termsRows)).toStrictEqual([
|
||||
{ source_id: '31', slug: 'company', name: 'Company', taxonomy: 'category' },
|
||||
{ source_id: '88', slug: 'special', name: 'Special', taxonomy: 'product_tag' },
|
||||
])
|
||||
const taxRows = (await db.execute(`select key, object_type, public_base_path from taxonomies
|
||||
where site_id = '${reg.siteId}' order by key`)) as any
|
||||
expect(plain(taxRows)).toStrictEqual([
|
||||
{ key: 'category', object_type: 'post', public_base_path: '/category/' },
|
||||
{ key: 'product_tag', object_type: 'product', public_base_path: '/product-tag/' },
|
||||
])
|
||||
|
||||
// term 先行序全程零自建；两条关联均挂真实 term
|
||||
const report = JSON.parse(
|
||||
await readFile(join(work, 'artifacts', 'import', result.jobId, 'reports', 'import.json'), 'utf8'),
|
||||
) as { status: string; counts: Record<string, number>; issues: string[] }
|
||||
expect(report.counts).toStrictEqual({
|
||||
termsProcessed: 2,
|
||||
autoCreatedTerms: 0,
|
||||
contentTermsCreated: 2,
|
||||
})
|
||||
expect(report.issues).toStrictEqual([])
|
||||
const ct = (await db.execute(`select r.source_id as row_id, t.source_id as term_source_id, c.is_primary
|
||||
from content_terms c
|
||||
join source_records r on r.content_entry_id = c.content_entry_id
|
||||
join terms t on t.id = c.term_id
|
||||
where c.site_id = '${reg.siteId}' order by r.source_id`)) as any
|
||||
expect(plain(ct)).toStrictEqual([
|
||||
{ row_id: '101', term_source_id: '31', is_primary: true },
|
||||
{ row_id: '111', term_source_id: '88', is_primary: true },
|
||||
])
|
||||
} finally {
|
||||
await cleanupSiteRows(db, reg.siteId)
|
||||
}
|
||||
} finally {
|
||||
await rm(work, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
it('幂等重跑（换幂等键新 job 同流）：taxonomies/terms/content_terms 均不增行、关联零新增', async () => {
|
||||
await withTestDb(async (db) => {
|
||||
const work = await mkdtemp(join(tmpdir(), 'sf-terms-'))
|
||||
try {
|
||||
const key = `sfterm-${rand()}`
|
||||
const reg = await registerSource(db, {
|
||||
siteKey: key,
|
||||
wxrPath: WXR_FIXTURE,
|
||||
allowedRoots: [FIXTURES_ROOT],
|
||||
storageRoot: join(work, 'storage'),
|
||||
reportRoot: join(work, 'artifacts', 'register'),
|
||||
})
|
||||
try {
|
||||
const wxr = reg.snapshots.find((s) => s.kind === 'wxr')!
|
||||
const base = {
|
||||
siteKey: key,
|
||||
snapshotId: wxr.id,
|
||||
reportRoot: join(work, 'artifacts', 'import'),
|
||||
pipeline: seededTermWriter(seedMiniEntries),
|
||||
}
|
||||
const first = await createImportJob(db, {
|
||||
...base,
|
||||
events: runWxrAdapter(createReadStream(WXR_FIXTURE), { mapConfig: { locale: 'en' } }),
|
||||
})
|
||||
expect(first.status).toBe('succeeded')
|
||||
const before = (await db.execute(`select
|
||||
(select count(*)::int from taxonomies where site_id = '${reg.siteId}') as taxonomies,
|
||||
(select count(*)::int from terms where site_id = '${reg.siteId}') as terms,
|
||||
(select count(*)::int from content_terms where site_id = '${reg.siteId}') as content_terms`)) as any
|
||||
expect(plain(before)[0]).toStrictEqual({ taxonomies: 2, terms: 2, content_terms: 1 })
|
||||
|
||||
// 同流重跑：显式幂等键（默认键会复用既有 job 不重跑——那是 Task 1 语义，此处钉写入器幂等）
|
||||
const again = await createImportJob(db, {
|
||||
...base,
|
||||
idempotencyKey: `sfterm-rerun-${rand()}`,
|
||||
events: runWxrAdapter(createReadStream(WXR_FIXTURE), { mapConfig: { locale: 'en' } }),
|
||||
})
|
||||
expect(again.reused).toBe(false)
|
||||
expect(again.status).toBe('succeeded')
|
||||
const after = (await db.execute(`select
|
||||
(select count(*)::int from taxonomies where site_id = '${reg.siteId}') as taxonomies,
|
||||
(select count(*)::int from terms where site_id = '${reg.siteId}') as terms,
|
||||
(select count(*)::int from content_terms where site_id = '${reg.siteId}') as content_terms`)) as any
|
||||
expect(plain(after)[0]).toStrictEqual({ taxonomies: 2, terms: 2, content_terms: 1 })
|
||||
|
||||
// 重跑计数：事件仍处理（termsProcessed=2），但物化/关联零新增
|
||||
const report = JSON.parse(
|
||||
await readFile(join(work, 'artifacts', 'import', again.jobId, 'reports', 'import.json'), 'utf8'),
|
||||
) as { counts: Record<string, number>; issues: string[] }
|
||||
expect(report.counts).toStrictEqual({
|
||||
termsProcessed: 2,
|
||||
autoCreatedTerms: 0,
|
||||
contentTermsCreated: 0,
|
||||
})
|
||||
expect(report.issues).toStrictEqual([])
|
||||
} finally {
|
||||
await cleanupSiteRows(db, reg.siteId)
|
||||
}
|
||||
} finally {
|
||||
await rm(work, { recursive: true, force: true })
|
||||
}
|
||||
})
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user