Peach: Local-first video metadata scraper and media manager.
fix(queues): 取资料限时、旧壳保底、下载后处理先领、来源限速共用
longmeidaof87c0e6dfe04
diff --git a/docs/SOURCING.md b/docs/SOURCING.mdindex ad4e81f35..0c4e9a027 100644--- a/docs/SOURCING.md+++ b/docs/SOURCING.md@@ -404,7 +404,8 @@ minnano-av 也在 Cloudflare 后面,但对 HTTP 客户端是间歇拦截:202### 库内采集的节奏- javdb 的主机间隔由用户定:`library_processing.SOURCE_INTERVALS` 里 `javdb.com` 与 `jdbstatic.com` 都是 3 秒,- 两个主机要一起改。+ 两个主机要一起改。这份间隔由 `SOURCE_LIMITER` 整个进程共用:资料处理、取想要的资料、取新作资料与订阅检查+ 同时跑时,问同一主机仍按一条队排。- **FC2 的商品号在三家里只问 javdb**(`community_catalog.community_sources_for`)。本机来源证据里 AVBase 与 JavBus对 FC2 一份都没给过;javdb 能补约一半的演员与发行日,厂牌、标签、封面不给,所以它问得慢却砍不掉。- 一轮采集的长短约等于 javdb 请求数乘这个间隔(实测相差约一成)。`HostLimiter` 等的是「距上次满 N 秒」,别家的diff --git a/docs/adr/0042-feeds-discover-codes-not-files.md b/docs/adr/0042-feeds-discover-codes-not-files.mdindex f36c972de..a46910a53 100644--- a/docs/adr/0042-feeds-discover-codes-not-files.md+++ b/docs/adr/0042-feeds-discover-codes-not-files.md@@ -61,8 +61,9 @@ sukebei 两个响应头一个都不给(2026-09-22 实测)。304 只是省一取消忽略只恢复可见性,不自动派刮削。两列都不参与任何唯一约束。**六、刮削走现有来源链,由后继机制派。** 一轮拉取按 ADR-0040 声明一条后继-(`feed-scrape:<番号>,<番号>,…`),带上这一轮新建的壳,余下名额给没取到资料、-距上次尝试已过 12 小时的旧壳(手动点「检查」的那一轮不等这 12 小时)。资料已齐、只缺本机封面的+(`feed-scrape:<番号>,<番号>,…`),一批 24 部:这一轮新建的壳与还没取过资料的壳在前,+没取到资料、距上次尝试已过 12 小时的旧壳在后,并且至少留 6 个名额给后者(手动点「检查」的那一轮+不等这 12 小时)。一部最多问 90 秒,与媒体库资料处理同一份预算。资料已齐、只缺本机封面的旧壳另成一条 `feed-cover:<番号>,…`,按上次取图由远到近排,只取图、不写账本,走自己的后继通道;已在队里或正在跑的番号不再进下一批;活动页上一轮订阅因此是一行,不是一部一行。后继内部用diff --git a/docs/adr/0114-followups-a-download-goes-first-in-the-ledger-lane.md b/docs/adr/0114-followups-a-download-goes-first-in-the-ledger-lane.mdnew file mode 100644index 000000000..bcb0f9a90--- /dev/null+++ b/docs/adr/0114-followups-a-download-goes-first-in-the-ledger-lane.md@@ -0,0 +1,26 @@+# ADR-0114:云下载后处理在账本通道里先领++- 状态:已采纳+- 日期:2026-10-22+- 修订:ADR-0040「未决」里的后继优先级++## 背景++写账本的后继共用一条 `ledger` 通道,一次只跑一条(ADR-0040 第二条),按排队先后领取。+这条通道上有九种后继,其中取新作资料(ADR-0042 第六条)一批 24 部,来源连不上时每部要等满资料预算,+排着几批时要跑一到几个小时。云下载后处理排在它们后面,下好的文件要等这些后台批次跑完才认正片、+写番号、整理入库,而这正是用户刚做完、在等结果的那件事。++## 决策++**一、后继类型可以声明 `jumps_queue`。** 带这一项的后继在自己的通道里先于别的种类领取,+同一档里仍按 id 先排先跑。在途那一条不打断,插队只决定下一条领谁。++**二、目前只有云下载后处理插队。** 判据是「人刚做完一件事、在等它收尾」;补资料、补头像、+补样张这类后台存量不插队。新增插队的种类要能说出用户在等什么。++## 后果++- 下载后处理最多等通道上在途的那一条跑完,不再等整队后台批次。+- 云下载连续涌入时,后台批次会被推后;下载是用户一部部发起的,量有上限,不会把后台批次饿死。+- 通道仍是串行,账本写锁的约束不变。diff --git a/src/peach/download_postprocess.py b/src/peach/download_postprocess.pyindex 758ab7035..bc6095568 100644--- a/src/peach/download_postprocess.py+++ b/src/peach/download_postprocess.py@@ -203,4 +203,4 @@ def run(contract, key: str, handle) -> dict:TYPE = register(FollowupType(task_key=TASK_KEY, label=TASK_LABEL,- writes_ledger=True, run=run))+ writes_ledger=True, run=run, jumps_queue=True))diff --git a/src/peach/feed_followup.py b/src/peach/feed_followup.pyindex e9848ef5b..a85f1934d 100644--- a/src/peach/feed_followup.py+++ b/src/peach/feed_followup.py@@ -52,6 +52,10 @@ WANTED = ("title", "performers", "studio", "release_date")#: 旧壳;补封面那一批按上次尝试由远到近排。MAX_BATCH = 24+#: 取资料那一批至少留给重试旧壳的名额。订阅一轮能发现几十部新番号,不留就一部旧壳也+#: 轮不到:没取到资料的那些会一直停在页面上没有标题。+RETRY_SHARE = 6+#: 缺封面或上次没取到资料的壳,定时拉取隔多久再试一次。新片的封面常常晚于番号出现,#: 所以不是试一次就放弃;但也不该每拉一轮源就把同一批再问一遍。人手点的那一次不等:#: 点「检查」本身就是要现在取。@@ -111,11 +115,12 @@ def has_local_cover(cover_root: Path, code: str) -> bool:return bool(key) and cover_settled(Path(cover_root) / f"{key}.jpg")-def backlog(connection, cover_root: Path, *, exclude=(), now: datetime | None = None,- limit: int = MAX_BATCH, retry_after: timedelta = RETRY_AFTER,- hidden: frozenset[str] = feeds.DEFAULT_HIDDEN_COMPILATIONS) -> list[str]:- """还没取过资料,或上次没取到、已经过了 `retry_after` 的壳。资料齐了只缺封面的归- `cover_backlog`。+def scrape_batch(connection, fresh=(), *, exclude=(), now: datetime | None = None,+ retry_after: timedelta = RETRY_AFTER,+ hidden: frozenset[str] = feeds.DEFAULT_HIDDEN_COMPILATIONS) -> list[str]:+ """下一批取资料的番号:这一轮新发现的 `fresh` 与还没取过资料的壳在前,上次没取到、+ 已经过了 `retry_after` 的壳在后,并且至少留 `RETRY_SHARE` 个名额给后者。资料齐了只缺+ 封面的归 `cover_backlog`。已忽略的不算:人说了不想看,就不再替它花配额。已经入库的壳本来就不在表里(入库即从列表里消失,ADR-0042 第三条),这里同样用番号键排除掉。取回标题后认出是@@ -124,9 +129,17 @@ def backlog(connection, cover_root: Path, *, exclude=(), now: datetime | None ="""moment = now or datetime.now(timezone.utc)cutoff = feeds.stamp(moment - retry_after)- rows = _candidates(connection,- "(d.scraped_at IS NULL OR (d.scrape_error IS NOT NULL AND d.scraped_at<?))",- (cutoff,), "COALESCE(d.scraped_at,''), ")+ fresh = list(dict.fromkeys(code for code in fresh if code))+ skip = [*exclude, *fresh]+ untried = _first(_candidates(connection, "d.scraped_at IS NULL", (), ""),+ skip, hidden, MAX_BATCH)+ retries = _first(_candidates(connection, "d.scrape_error IS NOT NULL AND d.scraped_at<?",+ (cutoff,), "d.scraped_at, "), skip, hidden, MAX_BATCH)+ head = [*fresh, *untried][:MAX_BATCH - min(len(retries), RETRY_SHARE)]+ return head + retries[:MAX_BATCH - len(head)]+++def _first(rows, exclude, hidden, limit: int) -> list[str]:found: list[str] = []for row in _visible(rows, exclude, hidden):found.append(row["code"])@@ -141,7 +154,7 @@ def cover_backlog(connection, cover_root: Path, *, exclude=(), now: datetime | N"""资料已经齐、本机还没有封面、上次取图已经过了 `retry_after` 的壳。上次取图的时间读逐番号的取图记录(`record_cover_attempt`),没试过的排最前,其余由远到近;- 同样远的新片在前。排除规则与 `backlog` 相同。+ 同样远的新片在前。排除规则与 `scrape_batch` 相同。"""from .catalog_rules import is_korean_mib_code@@ -202,10 +215,24 @@ def collect(provider, code: str) -> tuple[dict, str | None]:问哪几家由 `metadata_routes` 决定,与刮削链同一份判据;这里没有本机证据可给,所以只传番号本身。一家都没给就抛——调用方把原因写进壳的 `scrape_error`,页面上那一行因此能说清是「还没取」还是「取不到」。++ 一部最多问多久与媒体库资料处理同一份预算(`ACTION_BUDGETS['querying_metadata']`):+ 来源连不上时每家要等满超时再退避重试,不设上限一部能耗掉几分钟,整批和排在后面的+ 后继都跟着等。"""+ from .jav_cover_fetch import DeadlineExceeded+ from .library_processing import ACTION_BUDGETS+ from .processing_control import deadline_after+chain = metadata_routes.route_for_code(code)- found = provider.community(- code, route=metadata_routes.community_route(code))+ budget = ACTION_BUDGETS["querying_metadata"]+ try:+ found = provider.community(+ code, deadline=deadline_after(budget),+ route=metadata_routes.community_route(code))+ except DeadlineExceeded as error:+ raise DeadlineExceeded(+ f"来源链 {'、'.join(chain)} 在 {budget:g} 秒内没有答复") from errorfields: dict[str, object] = {}cover: str | None = Nonefor _source, payload in found:@@ -395,7 +422,7 @@ def run(contract, key: str, handle) -> dict:unreachable += 1except Exception: # noqa: BLE001 - 取不到封面这一部照样有资料,下一轮再试pass- # 记下这一次尝试,没取到资料的 `backlog` 按它隔 `RETRY_AFTER` 再试;封面的重试另看取图记录。+ # 记下这一次尝试,没取到资料的由 `scrape_batch` 按它隔 `RETRY_AFTER` 再试;封面的重试另看取图记录。with contract.database.write_transaction() as connection:connection.execute("UPDATE feed_discovery SET scraped_at=? WHERE id=?",(feeds.stamp(), int(row["id"])))diff --git a/src/peach/followups.py b/src/peach/followups.pyindex de6ac31d7..243e726f6 100644--- a/src/peach/followups.py+++ b/src/peach/followups.py@@ -100,12 +100,16 @@ class FollowupType:`run(contract, key, handle)` 返回一份摘要字典,异常一律算这一条失败——后继失败不回滚也不改判父任务(ADR-0040 第四条),所以这里不往上抛。++ `jumps_queue` 的后继在自己的通道里先于别的种类领取(ADR-0114):给人刚做完的那件事+ 收尾的后继,人在等它;补资料、补头像这类后台存量不急。"""task_key: strlabel: strwrites_ledger: boolrun: Callable[[object, str, TaskRunHandle], dict]+ jumps_queue: bool = False@propertydef lane(self) -> str:@@ -133,6 +137,11 @@ def lanes() -> dict[str, tuple[str, ...]]:return {lane: tuple(sorted(keys)) for lane, keys in grouped.items()}+def _ahead(keys) -> tuple[str, ...]:+ """这几类里插队先领的那些(`FollowupType.jumps_queue`)。"""+ return tuple(key for key in keys if key in REGISTRY and REGISTRY[key].jumps_queue)++class FollowupRunner:"""把库里排着的后继跑掉。每条通道一个线程,通道内串行。@@ -198,7 +207,7 @@ class FollowupRunner:done = 0for keys in lanes().values():while True:- run = self.store.claim_followup(keys)+ run = self.store.claim_followup(keys, first=_ahead(keys))if run is None:breakself._execute(run)@@ -209,7 +218,7 @@ class FollowupRunner:def _work(self, keys: tuple[str, ...]) -> None:while not self._stopping:- run = self.store.claim_followup(keys)+ run = self.store.claim_followup(keys, first=_ahead(keys))if run is None:from .update_tasks import is_pausingdb = getattr(getattr(self.store, 'database', None), 'db_path', None)diff --git a/src/peach/jav_cover_fetch.py b/src/peach/jav_cover_fetch.pyindex 69630615b..3d6d4e8e4 100644--- a/src/peach/jav_cover_fetch.py+++ b/src/peach/jav_cover_fetch.py@@ -191,17 +191,21 @@ class CoverConnectError(Unavailable):class HostLimitedTransport:- """把请求间隔按主机分别计算;不同官方站点互不阻塞。"""+ """把请求间隔按主机分别计算;不同官方站点互不阻塞。++ 给了 `limiter` 就按它等:几个传输共用一份间隔,同时跑的任务问同一主机也不会叠在一起。+ """def __init__(self, inner: HttpxTransport, interval: float, *,intervals: dict[str, float] | None = None,- clock=time.monotonic, sleeper=time.sleep) -> None:+ clock=time.monotonic, sleeper=time.sleep,+ limiter: HostLimiter | None = None) -> None:self.inner = innerself.interval = max(0.0, interval)self.clock = clockself.sleeper = sleeper- self.limiter = HostLimiter(dict(intervals or {}), default_interval=self.interval,- clock=clock, sleeper=sleeper)+ self.limiter = limiter or HostLimiter(dict(intervals or {}), default_interval=self.interval,+ clock=clock, sleeper=sleeper)def __call__(self, request: HttpRequest, timeout: float, limit: int):self.limiter.wait(request.url)diff --git a/src/peach/library_processing.py b/src/peach/library_processing.pyindex 873191800..a5563ba3a 100644--- a/src/peach/library_processing.py+++ b/src/peach/library_processing.py@@ -42,6 +42,7 @@ from .jobs import DiskGuardfrom .media_probe import probe_unmeasuredfrom .media_sources import cost_forfrom .media_processing_policy import metadata_only+from .scripting import HostLimiterfrom .strm import skip_background_readfrom .record_rehome import reattach_infrom .processing_traffic import ProcessingTraffic@@ -78,6 +79,10 @@ MISS_TTL_SECONDS = 7 * 24 * 3600#: 那条批量线仍按 5 秒跑。撞上 403 不再是盲等 24 小时——`scraping_access.FIRST_BLOCKED_PAUSE`#: 先停 15 分钟,连着再撞才翻倍,所以这一档收紧的代价是有限且可观测的(docs/SOURCING.md)。SOURCE_INTERVALS = {'javdb.com': 3.0, 'jdbstatic.com': 3.0}+#: 按 `SOURCE_INTERVALS` 等的那一份间隔,整个进程共用。取想要的资料、取新作资料、资料处理+#: 各起各的 provider,间隔若各算各的,几条同时跑时问同一主机的请求就叠在一起,配额照样按+#: 出口 IP 一份算。+SOURCE_LIMITER = HostLimiter(SOURCE_INTERVALS, default_interval=2.0)SOURCE_LABELS = {'r18dev': 'r18.dev', 'dmm': 'DMM / FANZA', 'avbase': 'AVBase', 'javbus': 'JavBus', 'javdb': 'javdb','fc2': 'FC2', 'fc2cmadb': 'FC2CMADB', 'fc2ppvdb': 'FC2PPV-DB', 'javten': 'JAVten','javarchive': 'JavArchive',@@ -316,7 +321,7 @@ class LibraryMetadataProvider:self.transport = HostLimitedTransport(SourceTransport(secrets_root, max_requests=MAX_SOURCE_REQUESTS,max_bytes=MAX_SOURCE_BYTES, max_seconds=MAX_SOURCE_SECONDS),- 2.0, intervals=SOURCE_INTERVALS)+ 2.0, limiter=SOURCE_LIMITER)#: 由本机浏览器过验证的来源累计等人点验证的秒数(`_excuse`)。调用方拿它前后相减,把这段时间#: 从单项动作预算里扣掉:一个站第一次弹验证窗口时,那一问要等 `min(40, timeout) + 120` 秒,diff --git a/src/peach/task_runs.py b/src/peach/task_runs.pyindex 64f9c452a..dbd3a425d 100644--- a/src/peach/task_runs.py+++ b/src/peach/task_runs.py@@ -521,30 +521,32 @@ class TaskRunStore:return Nonereturn int(cursor.lastrowid)- def claim_followup(self, task_keys) -> TaskRun | None:+ def claim_followup(self, task_keys, first=()) -> TaskRun | None:from .update_tasks import admission, UpdateBusytry:with admission(self.database.db_path):- return self._claim_followup(task_keys)+ return self._claim_followup(task_keys, first)except UpdateBusy:return None- def _claim_followup(self, task_keys) -> TaskRun | None:+ def _claim_followup(self, task_keys, first=()) -> TaskRun | None:"""领走这几类里最早的一条待跑后继并标 `running`;没有就返回 None。- `task_keys` 是调用方这条通道负责的任务种类。按 id 升序领:后继之间没有优先级- (ADR-0040 未决),先声明的先跑是唯一说得清的顺序。+ `task_keys` 是调用方这条通道负责的任务种类,`first` 是其中插队先领的那几类+ (ADR-0114)。同一档里按 id 升序领,先声明的先跑。"""keys = tuple(dict.fromkeys(str(key) for key in task_keys or ()))if not self.enabled or not keys:return None+ ahead = tuple(dict.fromkeys(str(key) for key in first or ())) or ("",)marks = ",".join("?" * len(keys))moment = stamp()with self.database.write_transaction(notify=False) as connection:row = connection.execute(f"SELECT id FROM task_run WHERE followup_key IS NOT NULL "- f"AND status='pending' AND task_key IN ({marks}) ORDER BY id LIMIT 1",- keys).fetchone()+ f"AND status='pending' AND task_key IN ({marks}) "+ f"ORDER BY task_key IN ({','.join('?' * len(ahead))}) DESC, id LIMIT 1",+ (*keys, *ahead)).fetchone()if row is None:return Nonerun_id = int(row["id"])diff --git a/src/peach/web_feeds.py b/src/peach/web_feeds.pyindex 7b679c48d..385ecffee 100644--- a/src/peach/web_feeds.py+++ b/src/peach/web_feeds.py@@ -38,11 +38,11 @@ _NOT_MODIFIED = 304def _transport(contract):from .jav_cover_fetch import HostLimitedTransport- from .library_processing import SOURCE_INTERVALS+ from .library_processing import SOURCE_LIMITERfrom .scraping_access import SourceTransportreturn HostLimitedTransport(- SourceTransport(contract.follow_secrets_root), 2.0, intervals=SOURCE_INTERVALS)+ SourceTransport(contract.follow_secrets_root), 2.0, limiter=SOURCE_LIMITER)def fetch(transport, url: str, *, etag: str | None = None,@@ -201,16 +201,15 @@ def _execute_check(contract, body, job_id: str) -> dict:if close:close()contract.cache_bust()- # 取资料:新发现的先排,余下名额给没取到资料的旧壳,同一批一条后继。只缺封面的另成一批+ # 取资料:新发现的先排,没取到资料的旧壳留着保底名额,同一批一条后继。只缺封面的另成一批# 补封面。定时那一轮只带到了重试时间的,手动点的那一轮全带;已在队里的番号都不再带。retry_after = feed_followup.RETRY_AFTER if body.get("automatic") else timedelta(0)hidden = web_settings.hidden_compilations(contract.database)busy = feed_followup.in_flight(contract.task_runs)fresh = [code for code in dict.fromkeys(codes) if normalise_code_key(code) not in busy]with contract.database.read_connection() as connection:- batch = fresh + feed_followup.backlog(- connection, contract.cover_root, exclude=[*codes, *busy], retry_after=retry_after,- limit=max(0, feed_followup.MAX_BATCH - len(fresh)), hidden=hidden)+ batch = feed_followup.scrape_batch(+ connection, fresh, exclude=[*codes, *busy], retry_after=retry_after, hidden=hidden)covers = feed_followup.cover_backlog(connection, contract.cover_root, exclude=[*codes, *batch, *busy],retry_after=retry_after, hidden=hidden)diff --git a/tests/test_feeds_web.py b/tests/test_feeds_web.pyindex 98e5aaeac..0f14b0691 100644--- a/tests/test_feeds_web.py+++ b/tests/test_feeds_web.py@@ -409,7 +409,7 @@ class FeedWebTest(FeedWebFixture):def _backlog(self) -> list[str]:hidden = web_settings.hidden_compilations(self.contract.database)with self.contract.database.read_connection() as connection:- return feed_followup.backlog(connection, self.contract.cover_root, hidden=hidden)+ return feed_followup.scrape_batch(connection, hidden=hidden)def test_a_group_compilation_is_neither_listed_counted_nor_rescheduled(self):self._compilation("波多野結衣、篠田ゆう")@@ -656,8 +656,45 @@ class FeedWebTest(FeedWebFixture):connection.execute("UPDATE feed_discovery SET scrape_error='来源连接未取得' WHERE code='HMN-071'")self.assertEqual(self._cover_backlog(), ['SSIS-950'])with self.contract.database.read_connection() as connection:- self.assertEqual(feed_followup.backlog(connection, self.contract.cover_root, hidden=frozenset(),- retry_after=timedelta(0)), ['HMN-071'])+ self.assertEqual(feed_followup.scrape_batch(connection, hidden=frozenset(),+ retry_after=timedelta(0)), ['HMN-071'])++ def test_failed_old_rows_keep_a_share_of_a_batch_full_of_new_codes(self):+ """一轮发现的新番号比一批还多时,上次没取到资料的旧壳仍有保底名额,不被挤到轮不上。"""+ fresh = [f"NEW-{number:03d}" for number in range(feed_followup.MAX_BATCH + 10)]+ self._add()+ with self.contract.database.write_transaction() as connection:+ for number in range(feed_followup.RETRY_SHARE + 2):+ connection.execute(+ "INSERT INTO feed_discovery(code,source_id,title,link,release_date,discovered_at,"+ "scraped_at,scrape_error) VALUES(?,1,'',NULL,'2026-09-22',?,?,'来源连接未取得')",+ (f"OLD-{number:03d}", feeds.stamp(), f"2026-01-{number + 1:02d}T00:00:00Z"))+ with self.contract.database.read_connection() as connection:+ batch = feed_followup.scrape_batch(connection, fresh, hidden=frozenset(),+ retry_after=timedelta(0))+ self.assertEqual(len(batch), feed_followup.MAX_BATCH)+ self.assertEqual(batch[:feed_followup.MAX_BATCH - feed_followup.RETRY_SHARE],+ fresh[:feed_followup.MAX_BATCH - feed_followup.RETRY_SHARE])+ # 保底名额给最久没试过的那几部。+ self.assertEqual(batch[-feed_followup.RETRY_SHARE:],+ [f"OLD-{number:03d}" for number in range(feed_followup.RETRY_SHARE)])++ def test_scraping_one_code_stops_at_the_metadata_budget(self):+ """来源连不上时一部最多问到资料预算为止,原因写成哪几家在多少秒内没答复。"""+ from peach.jav_cover_fetch import DeadlineExceeded+ from peach.library_processing import ACTION_BUDGETS++ seen = {}++ class Silent:+ def community(self, code, *, deadline=None, route=None):+ seen["remaining"] = float(deadline) - time.monotonic()+ raise DeadlineExceeded("动作预算已用尽")++ with self.assertRaisesRegex(DeadlineExceeded, "秒内没有答复"):+ self._collect(Silent(), "SSIS-950")+ self.assertLessEqual(seen["remaining"], ACTION_BUDGETS["querying_metadata"])+ self.assertGreater(seen["remaining"], ACTION_BUDGETS["querying_metadata"] - 5)def test_codes_already_queued_are_not_planned_again(self):"""在队里的那一批还没跑完,下一轮检查只带新的番号,不把同一批换个组合再派一条。"""diff --git a/tests/test_followups.py b/tests/test_followups.pyindex b804425ee..c7d260017 100644--- a/tests/test_followups.py+++ b/tests/test_followups.py@@ -210,6 +210,29 @@ class RunnerTests(LedgerTestCase):self.assertEqual({row.status for row in self.store.children(parent.id)}, {"succeeded"})+ def test_a_type_that_jumps_the_queue_is_claimed_before_earlier_ones_in_its_lane(self):+ """下载后处理这类人在等的后继,排在已经在排的后台批次前面;同一档里仍是先排先跑。"""+ order = []++ def record(_contract, key, _handle):+ order.append(key)+ return {"outcome": key}++ urgent = FollowupType(task_key="urgent", label="urgent", writes_ledger=True,+ run=record, jumps_queue=True)+ parent = self.parent()+ with registered(echo_type("backlog", run=record), urgent):+ self.store.enqueue_followups(parent.id, [+ ("backlog:1", "backlog", "甲"), ("backlog:2", "backlog", "乙"),+ ("urgent:1", "urgent", "丙"), ("urgent:2", "urgent", "丁")])+ self.assertEqual(FollowupRunner(self.contract()).drain(), 4)+ self.assertEqual(order, ["urgent:1", "urgent:2", "backlog:1", "backlog:2"])++ def test_the_download_postprocess_jumps_the_ledger_lane(self):+ from peach import download_postprocess+ self.assertTrue(download_postprocess.TYPE.writes_ledger)+ self.assertTrue(download_postprocess.TYPE.jumps_queue)+def test_types_that_do_not_write_the_ledger_get_their_own_lane(self):with registered(echo_type("ledger-a"), echo_type("cheap", writes_ledger=False)):self.assertEqual(sorted(lanes()), ["cheap", followups_module.LEDGER_LANE])diff --git a/tests/test_metadata_library.py b/tests/test_metadata_library.pyindex 8c67c06de..71fbfa6ad 100644--- a/tests/test_metadata_library.py+++ b/tests/test_metadata_library.py@@ -1312,6 +1312,17 @@ class LibraryNfoTests(unittest.TestCase):from peach.library_processing import SOURCE_INTERVALSself.assertEqual(SOURCE_INTERVALS, {'javdb.com': 3.0, 'jdbstatic.com': 3.0})+ def test_every_provider_waits_on_one_shared_host_interval(self):+ """取想要的资料、取新作资料与资料处理各起一个 provider;同时跑时问 javdb 也要排同一条队。"""+ from peach.library_processing import SOURCE_LIMITER, LibraryMetadataProvider+ from peach.web_feeds import _transport+ with tempfile.TemporaryDirectory() as root:+ first, second = LibraryMetadataProvider(root), LibraryMetadataProvider(root)+ feed = _transport(SimpleNamespace(follow_secrets_root=Path(root)))+ self.assertIs(first.transport.limiter, SOURCE_LIMITER)+ self.assertIs(second.transport.limiter, SOURCE_LIMITER)+ self.assertIs(feed.limiter, SOURCE_LIMITER)+def test_community_sources_are_asked_once_per_code_and_say_why_they_failed(self):"""资料和封面两步都要社区来源的结果,javdb 的配额经不起同一部片问两遍。"""from peach.jav_cover_fetch import NotFound, Unavailable