fix(adapter-wp): 内存上界注释纠正；错误前事件排空确定化；post_id 严格解析；嵌套畸形 fail-fast；类型收紧与测试钉

审查修复六项（wxr-stream）： - 内存上界表述纠正：saxes 按节点内部缓冲整个 text/CDATA 节点，对抗性单字段文件峰值 ≤ maxWxrBytes 的 UTF-16 表示（约 2×），并非与文件大小解耦；maxFieldLength/maxCdataLength 封顶的是本模块缓冲与产出字段长度 - parser.write/close 抛错前先排空待 yield 队列再重抛：错误前已完成事件的交付不依赖 chunk 划分（测试钉死单 chunk 与 7 字节切块一致） - wp:post_id / wp:term_id 严格解析：整串十进制 + Number.isSafeInteger，否则 null（表驱动测试：''/'0x10'/'12abc'/超安全域 → null） - 嵌套 item/wp:term 立即 WxrParseError（fail-fast，防外层截断产出） - Target.field 经 Exclude 收窄为纯文本字段，消除 as string 断言 - 测试钉死：提前 break 销毁上游流、text+CDATA 混合累计、限额错误 message 含行列位置 142 测试全绿（新增 12）。 Co-Authored-By: Claude Code <noreply@anthropic.com>
2026-10-21 09:21:41 +08:00
parent 25e8b9cb5c
commit 8edbbad45b
2 changed files with 177 additions and 41 deletions
@@ -51,6 +51,17 @@ async function captureRejection(p: Promise<unknown>): Promise<unknown> {
  throw new Error('期望抛出但未抛出')
 }

+/** 迭代到错误或完结：同时保留已交付事件与错误（审查 Fix 2 的交付确定性断言用） */
+async function collectUntilError(gen: AsyncGenerator<WxrEvent>): Promise<{ events: WxrEvent[]; error: unknown }> {
+  const events: WxrEvent[] = []
+  try {
+    for await (const ev of gen) events.push(ev)
+    return { events, error: null }
+  } catch (e) {
+    return { events, error: e }
+  }
+}
+
 function itemsOf(events: WxrEvent[]): WxrItem[] {
  return events
    .filter((ev): ev is Extract<WxrEvent, { kind: 'item' }> => ev.kind === 'item')
@@ -212,6 +223,21 @@ describe('parseWxrStream：限额防线（WxrLimitError，kind 区分）', () =>
    )) as WxrLimitError
    expect(err).toBeInstanceOf(WxrLimitError)
    expect(err.kind).toBe('cdata')
+    // 限额错误 message 附 saxes 行列位置（钉死，审查 Fix 6c）
+    expect(err.message).toMatch(/line \d+, column \d+/)
+  })
+
+  it('超限抛错前已完成事件确定性交付：单 chunk 与 7 字节切块产出一致（审查 Fix 2）', async () => {
+    const single = await collectUntilError(
+      parseWxrStream(fromString(SMALL_XML), { limits: { maxItems: 2 } }),
+    )
+    const chunked = await collectUntilError(
+      parseWxrStream(fromStringChunked(SMALL_XML), { limits: { maxItems: 2 } }),
+    )
+    expect(single.error).toBeInstanceOf(WxrLimitError)
+    expect(chunked.error).toBeInstanceOf(WxrLimitError)
+    expect(signature(single.events)).toStrictEqual(['item:1:post', 'item:2:post'])
+    expect(signature(chunked.events)).toStrictEqual(['item:1:post', 'item:2:post'])
  })

  it('maxFieldLength=10：单字段累计超限抛 kind fieldLength（防单个 title 灌爆内存）', async () => {
@@ -362,3 +388,74 @@ describe('parseWxrStream：畸形 XML → WxrParseError（带 saxes 行列位置
    expect(err.message).toContain('unclosed')
  })
 })
+
+describe('parseWxrStream：wp:post_id / wp:term_id 严格整数解析（审查 Fix 3）', () => {
+  it.each([
+    ['', null],
+    ['0x10', null],
+    ['12abc', null],
+    ['-7', -7],
+    ['99999999999999999999', null],
+    ['101', 101],
+  ])('post_id 输入 %j → %j', async (raw, expected) => {
+    const xml =
+      '<?xml version="1.0"?><rss version="2.0" xmlns:wp="http://wordpress.org/export/1.2/"><channel>' +
+      `<item><title>t</title><wp:post_id>${raw}</wp:post_id><wp:post_type>post</wp:post_type></item>` +
+      '</channel></rss>'
+    const events = await collect(parseWxrStream(fromString(xml)))
+    expect(itemsOf(events)[0]?.postId).toBe(expected)
+  })
+
+  it('term_id 同一规则：非纯数字 → null', async () => {
+    const xml =
+      '<?xml version="1.0"?><rss version="2.0" xmlns:wp="http://wordpress.org/export/1.2/"><channel>' +
+      '<wp:term><wp:term_id>0x10</wp:term_id><wp:term_taxonomy>category</wp:term_taxonomy></wp:term>' +
+      '</channel></rss>'
+    const events = await collect(parseWxrStream(fromString(xml)))
+    expect(events[0]?.kind === 'term' && events[0].term.termId).toBeNull()
+  })
+})
+
+describe('parseWxrStream：嵌套畸形 fail-fast（审查 Fix 4）', () => {
+  it('item 内嵌 item：立即 WxrParseError，外层不被截断产出', async () => {
+    const xml =
+      '<?xml version="1.0"?><rss version="2.0" xmlns:wp="http://wordpress.org/export/1.2/"><channel>' +
+      '<item><title>outer</title><wp:post_id>1</wp:post_id><wp:post_type>post</wp:post_type>' +
+      '<item><wp:post_id>2</wp:post_id><wp:post_type>post</wp:post_type></item>' +
+      '</item></channel></rss>'
+    const { events, error } = await collectUntilError(parseWxrStream(fromString(xml)))
+    expect(error).toBeInstanceOf(WxrParseError)
+    expect((error as WxrParseError).message).toContain('嵌套')
+    expect(events).toStrictEqual([]) // 嵌套发生在 item 中途——错误前无已完成事件
+  })
+
+  it('wp:term 内嵌 wp:term：同样 fail-fast', async () => {
+    const xml =
+      '<?xml version="1.0"?><rss version="2.0" xmlns:wp="http://wordpress.org/export/1.2/"><channel>' +
+      '<wp:term><wp:term_id>1</wp:term_id><wp:term_taxonomy>category</wp:term_taxonomy>' +
+      '<wp:term><wp:term_id>2</wp:term_id></wp:term>' +
+      '</wp:term></channel></rss>'
+    const err = (await captureRejection(collect(parseWxrStream(fromString(xml))))) as WxrParseError
+    expect(err).toBeInstanceOf(WxrParseError)
+    expect(err.message).toContain('嵌套')
+  })
+})
+
+describe('parseWxrStream：流契约钉死（审查 Fix 6）', () => {
+  it('消费方提前 break：上游流被销毁（finally 兜底契约）', async () => {
+    const stream = fromString(SMALL_XML)
+    for await (const _ev of parseWxrStream(stream)) {
+      break // 收到首个事件即退出
+    }
+    expect(stream.destroyed).toBe(true)
+  })
+
+  it('text 与 CDATA 混合内容累计为同一字段值', async () => {
+    const xml =
+      '<?xml version="1.0"?><rss version="2.0" xmlns:wp="http://wordpress.org/export/1.2/"><channel>' +
+      '<item><title>pre<![CDATA[mid]]>post</title><wp:post_id>5</wp:post_id><wp:post_type>post</wp:post_type></item>' +
+      '</channel></rss>'
+    const events = await collect(parseWxrStream(fromString(xml)))
+    expect(itemsOf(events)[0]?.title).toBe('premidpost')
+  })
+})