From 6ef8408f432dde643aee2ba7078f59d2776f84ce Mon Sep 17 00:00:00 2001
From: jxxghp <jxxghp@gmail.com>
Date: Mon, 12 Oct 2026 17:49:40 +0800
Subject: [PATCH] fix(bangumi): merge tmdb classification metadata for aux
 source (#6968)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bangumi 等主识别源缺少 original_language/origin_country 标准字段，引用这些字段的分类规则整体失效并落入未分类；TMDB 辅助补充已有 genre_ids 合并，补齐语言与国家标准字段，仅填充主来源缺失值。
---
 app/chain/media/auxiliary.py |  9 +++++
 tests/test_tmdb_auxiliary.py | 73 ++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

diff --git a/app/chain/media/auxiliary.py b/app/chain/media/auxiliary.py
index 77c65b15c..c53bd50b1 100644
--- a/app/chain/media/auxiliary.py
+++ b/app/chain/media/auxiliary.py
@@ -42,6 +42,15 @@ class MediaAuxiliaryOwner(_MediaOwnerBase):
         mediainfo.tmdb_info = tmdb_media.tmdb_info or mediainfo.tmdb_info
         if not mediainfo.genre_ids:
             mediainfo.genre_ids = list(tmdb_media.genre_ids or [])
+        # Bangumi/AniList 等主来源没有语言与国家标准字段，引用这些字段的
+        # 分类规则会整体失效并落入未分类；已关联 TMDB 详情时补齐标准事实，
+        # 仅填充主来源缺失的字段，不覆盖主来源自身的投影。
+        if not mediainfo.original_language:
+            mediainfo.original_language = tmdb_media.original_language
+        if not mediainfo.origin_country:
+            mediainfo.origin_country = list(tmdb_media.origin_country or [])
+        if not mediainfo.production_countries:
+            mediainfo.production_countries = list(tmdb_media.production_countries or [])
         for field in ("imdb_id", "tvdb_id", "tvdb_slug", "collection_id"):
             if not getattr(mediainfo, field, None):
                 setattr(mediainfo, field, getattr(tmdb_media, field, None))
diff --git a/tests/test_tmdb_auxiliary.py b/tests/test_tmdb_auxiliary.py
index d43dddb77..7fca051bc 100644
--- a/tests/test_tmdb_auxiliary.py
+++ b/tests/test_tmdb_auxiliary.py
@@ -3,6 +3,7 @@ from types import SimpleNamespace
 from unittest.mock import Mock, patch
 
 from app.chain.media import MediaChain
+from app.domain.classification.facts import build_classification_facts
 from app.domain.context import MediaInfo
 from app.domain.metainfo import MetaInfo
 from app.runtime.extensions.module.dispatcher import ModuleInvocationDispatcher
@@ -135,6 +136,78 @@ def test_supplement_tmdb_does_not_override_custom_category() -> None:
     assert result.tmdb_id == 9876
 
 
+def test_supplement_tmdb_merges_classification_metadata_for_bangumi_primary() -> None:
+    """Bangumi 主识别缺少语言与国家时，必须从关联 TMDB 详情补齐分类标准字段。"""
+    primary = MediaInfo(
+        bangumi_info={
+            "id": 378862,
+            "name": "お兄ちゃんはおしまい！",
+            "name_cn": "别当欧尼酱了！",
+            "platform": "TV",
+            "date": "2023-01-05",
+        }
+    )
+    tmdb_media = MediaInfo(
+        tmdb_info={
+            "id": 198152,
+            "media_type": MediaType.TV,
+            "name": "别当欧尼酱了！",
+            "first_air_date": "2023-01-05",
+            "genre_ids": [16],
+            "original_language": "ja",
+            "origin_country": ["JP"],
+        }
+    )
+
+    result = _make_chain(tmdb_media).supplement_tmdb_info(primary)
+
+    assert result is primary
+    assert result.media_source == MediaSource.Bangumi
+    assert result.media_id == "378862"
+    assert result.tmdb_id == 198152
+    assert result.genre_ids == [16]
+    assert result.original_language == "ja"
+    assert result.origin_country == ["JP"]
+    # 分类事实必须能读到补充后的语言与国家，规则才能命中而不是落入未分类。
+    facts = build_classification_facts(result)
+    assert facts.media.language == "ja"
+    assert facts.media.countries == ["JP"]
+    assert facts.media.genre_keys == ["animation"]
+
+
+def test_supplement_tmdb_keeps_primary_language_and_country_fields() -> None:
+    """主来源已有的语言与国家标准字段不被 TMDB 辅助结果覆盖。"""
+    primary = MediaInfo(
+        media_source=MediaSource.Douban,
+        media_id="35593344",
+        type=MediaType.MOVIE,
+        title="测试电影",
+        original_language="zh",
+        origin_country=["CN"],
+        production_countries=[{"iso_3166_1": "CN", "name": "中国大陆"}],
+    )
+    tmdb_media = MediaInfo(
+        tmdb_info={
+            "id": 9876,
+            "media_type": MediaType.MOVIE,
+            "title": "Test Movie",
+            "genre_ids": [28],
+            "original_language": "en",
+            "origin_country": ["US"],
+            "production_countries": [{"iso_3166_1": "US", "name": "United States"}],
+        }
+    )
+
+    result = _make_chain(tmdb_media).supplement_tmdb_info(primary)
+
+    assert result is primary
+    assert result.original_language == "zh"
+    assert result.origin_country == ["CN"]
+    assert result.production_countries == [{"iso_3166_1": "CN", "name": "中国大陆"}]
+    # 主来源缺失的流派仍按原语义补齐。
+    assert result.genre_ids == [28]
+
+
 def test_tmdb_supplement_uses_current_season_year_and_keeps_season_zero() -> None:
     """电视剧优先使用当前季年份，并且特别季季号不能退化为空。"""
     media = MediaInfo(