Peach: Local-first video metadata scraper and media manager.
fix(entities): 隐藏验证失败的名录入口
longmeidaodb56a3986d3f
diff --git a/docs/REUSE.md b/docs/REUSE.mdindex a699ef870..0ff07677b 100644--- a/docs/REUSE.md+++ b/docs/REUSE.md@@ -357,7 +357,7 @@ A 盘垃圾隔离使用短名称 `peach-purge-<32 位 UUID>.peach-quarantine`,- 操作回执复用 Toast(Sonner 的栈,`frontend/src/react/toaster.tsx`;壳里只调 `toast()`/`actionReceipt()`);按钮以 Spinner 和 `aria-busy` 标明忙态。后台任务显示可恢复进度,断线自动重连。- 实体的统称由用户在资料页自选:菜单只列这条实体名下已有的写法,选中的提为规范名、换下的留成别名,扁平投影跟着改;先过确认弹层并点名两个写法,成功后发可撤销回执;不收自由文本,撞上另一条实体的规范名只报冲突。- 艺人入口审计复用 `entry_links` 的 JAV 目录闸与日文名选择、只读 SQLite 和 `review_csv`;`audit_performer_entry_names.py` 覆盖全部 performer,分别记录入口来源、名称选择和中文来源缺口,远端页面未请求时保留「未取得」。译名复核后的原日文名按 `performer-localization` 来源优先。`localize_performer_names.py --mapping-source` 标明 CSV 的真实复核来源,`--only` 限定实体并拒绝不完整的同人合并组;别名、兼容标签、来源留痕和备份沿用已有实现。未新增依赖。- - MISSAV 入口优先读取 `state/missav-actresses.json` 的实际名录 href,保留原字形、数字前缀与括号艺名;`directory_name_key` 仅对匹配折叠字形及纯汉字、假名名称的空白,英文名称空白保留。同名对应不同路径时不显示入口;未采全名录的缺项保留模板候选,不能判为站点未收录。七沢みあ、逢沢みゆ的 h1 与 canonical 已在用户 Chrome 验证,证据在 `peach-data/review/missav-native-slug-browser-evidence.json`;名录原始分页和全库匹配 CSV 在 `review/missav-directory/`。API 与全库审计共用 `entry_links.build`,派生入口不写 ledger,403 验证页记「未取得」。艺名选择沿用现名、读音排除与来源冲突复核。无新增依赖。+ - MISSAV 入口优先读取 `state/missav-actresses.json` 的实际名录 href,保留原字形、数字前缀与括号艺名;`directory_name_key` 仅对匹配折叠字形及纯汉字、假名名称的空白,英文名称空白保留。同名对应不同路径时不显示入口;明确 `verified=false` 的来源项阻止该名称入口及模板回退,页面重新核验后可解除。未采全名录的缺项保留模板候选,不能判为站点未收录。七沢みあ、逢沢みゆ的 h1 与 canonical 已在用户 Chrome 验证,证据在 `peach-data/review/missav-native-slug-browser-evidence.json`;名录原始分页和全库匹配 CSV 在 `review/missav-directory/`。API 与全库审计共用 `entry_links.build`,派生入口不写 ledger,403 验证页记「未取得」。艺名选择沿用现名、读音排除与来源冲突复核。无新增依赖。- FC2 作品计数复用 `ordered_multipart_items`,`web_catalog.video_work_key` 按账本代次缓存已确认的合集键;资料、名册、同台艺人、标签与补全共用。`/api/items.work_total` 供作品读数,`total` 仍用于文件分页;不确定分段不归组。出演名单展开复用 BoardUI `Button`。跨角色人工合并走 `merge_entity`,`user:identity-merge:<kind>` 的别名与墓碑共同证明旧资料页地址,单纯同名不跨角色跳转。- 馆藏分组缓存声明 `asset`、`asset_entity`、`entity` 依赖;下载进度和复核留痕不使分组重算,同键计算串行共用。作品计数通过 SQLite `create_function` 注册资产到作品的只读字典查找,沿用既有版次与分卷判据。下载后处理复用已绑定资产、整理备份及逐项外键基线比较(`performer_alias_followup`);单部采集只结算本资产候选,进度在 `state/download-processing/`,共享 CSV 仍受全库处理锁保护。资源查询缓存拒收缺字段和来源失败的旧结果。无新增依赖。- Application 管理路由与资源,域控制器适配原生宿主。文件检查含本地与网盘,来源等分、共用确认弹层;CloudDrive 分档建议首启与配置页共用。diff --git a/src/peach/entry_links.py b/src/peach/entry_links.pyindex 00880a27e..5bd55fd22 100644--- a/src/peach/entry_links.py+++ b/src/peach/entry_links.py@@ -342,8 +342,9 @@ class MissavDirectory:def path(self, japanese: str, canonical: str) -> str | None:for name in (japanese, canonical):- matches = self.paths.get(directory_name_key(name), ())- if matches:+ key = directory_name_key(name)+ if key in self.paths:+ matches = self.paths[key]return matches[0] if len(matches) == 1 else ""return "" if self.complete else None@@ -372,6 +373,7 @@ def directory_index(data: object) -> MissavDirectory | None:if not isinstance(entries, list):return Nonepaths: dict[str, dict[str, str]] = {}+ blocked: set[str] = set()for row in entries:if not isinstance(row, dict):continue@@ -386,8 +388,14 @@ def directory_index(data: object) -> MissavDirectory | None:names = _published_names(slug) + _published_names(str(row.get("name") or ""))for name in names:if name:- paths.setdefault(directory_name_key(name), {}).setdefault(slug, target.path)- return MissavDirectory({key: tuple(sorted(values.values())) for key, values in paths.items()},+ key = directory_name_key(name)+ bucket = paths.setdefault(key, {})+ if row.get("verified") is False:+ blocked.add(key)+ else:+ bucket.setdefault(slug, target.path)+ return MissavDirectory({key: () if key in blocked else tuple(sorted(values.values()))+ for key, values in paths.items()},complete=data.get("complete") is True)diff --git a/tests/test_entry_links.py b/tests/test_entry_links.pyindex 4299cb495..5c27a891e 100644--- a/tests/test_entry_links.py+++ b/tests/test_entry_links.py@@ -309,6 +309,23 @@ class MissavDirectoryTests(unittest.TestCase):return entry_links.directory_index({"source": entry_links.DIRECTORY_URL,"entries": rows, "complete": complete})+ def test_failed_source_page_has_no_template_fallback(self):+ address = "https://missav.ws/dm31/cn/actresses/Rina"+ for complete in (False, True):+ with self.subTest(complete=complete):+ directory = self.directory([{"name": "Rina", "url": address, "verified": False}],+ complete=complete)+ rows = entry_links.build(entry_links.defaults(), "RINA", [ref("javdb", "actor")],+ directory=directory)+ self.assertNotIn("missav", [row["site"] for row in rows])++ def test_conflicting_page_evidence_requires_a_verified_source(self):+ failed = {"name": "Rina", "url": "https://missav.ws/dm31/cn/actresses/Rina", "verified": False}+ alternate = {"name": "Rina", "url": "https://missav.ws/dm83/cn/actresses/Rina"}+ self.assertEqual(self.directory([failed, alternate]).path("Rina", "RINA"), "")+ restored = self.directory([{**failed, "verified": True}])+ self.assertEqual(restored.path("Rina", "RINA"), "/dm31/cn/actresses/Rina")+def test_site_glyphs_and_compound_stage_names_use_the_published_href(self):for canonical, jp, display, slug in (("北条麻妃", "北條麻妃", "北条麻妃", "北条麻妃"),