fix: 清理音乐刮削结果中 album_type 等字段的尾部空格 (#6327)

MusicBrainz 和 ListenBrainz 模块从 API 响应中提取 album_type、
secondary_types 时直接使用 dict.get() 取值,未做 strip() 处理,
导致部分结果带有尾部空格(如 'Album '、'Broadcast ')。

修复:
- MusicBrainz 新增 _stripped() 工具方法,3 处 album_type 赋值统一清理
- ListenBrainz 新增 _stripped() 工具方法,_fresh_release_to_info 中清理
- Pydantic schema 层增加 field_validator 作为兜底安全网
- 新增 9 个回归测试覆盖所有场景
This commit is contained in:
jxxghp
2026-08-15 20:35:02 +08:00
parent dd38c16400
commit 78b0063d4c
4 changed files with 187 additions and 14 deletions
+11 -6
View File
@@ -265,10 +265,9 @@ class ListenBrainzModule(_ModuleBase):
return None return None
artist_name = str(release.get("artist_credit_name") or "").strip() artist_name = str(release.get("artist_credit_name") or "").strip()
release_date = release.get("release_date") or None release_date = release.get("release_date") or None
category_parts = [ primary_type = cls._stripped(release.get("release_group_primary_type"))
release.get("release_group_primary_type"), secondary_type = cls._stripped(release.get("release_group_secondary_type"))
release.get("release_group_secondary_type"), category_parts = [primary_type, secondary_type]
]
return MusicInfo( return MusicInfo(
media_source=cls._source, media_source=cls._source,
media_id=str(media_id), media_id=str(media_id),
@@ -279,12 +278,12 @@ class ListenBrainzModule(_ModuleBase):
album=str(title), album=str(title),
album_artist=artist_name or None, album_artist=artist_name or None,
album_id=str(media_id), album_id=str(media_id),
album_type=release.get("release_group_primary_type") or None, album_type=primary_type,
year=cls._year(release_date), year=cls._year(release_date),
release_date=release_date, release_date=release_date,
cover_url=cls._release_cover(release.get("caa_release_mbid")) cover_url=cls._release_cover(release.get("caa_release_mbid"))
or cls._release_group_cover(media_id), or cls._release_group_cover(media_id),
category=" / ".join(str(part) for part in category_parts if part), category=" / ".join(part for part in category_parts if part),
genres=[str(tag) for tag in release.get("release_tags") or [] if tag], genres=[str(tag) for tag in release.get("release_tags") or [] if tag],
names=[str(title)], names=[str(title)],
detail_link=f"{cls._album_detail_url}/{media_id}", detail_link=f"{cls._album_detail_url}/{media_id}",
@@ -321,6 +320,12 @@ class ListenBrainzModule(_ModuleBase):
return [] return []
return [str(artist_mbids[0])] if artist_mbids and artist_mbids[0] else [] return [str(artist_mbids[0])] if artist_mbids and artist_mbids[0] else []
@staticmethod
def _stripped(value: Any) -> Optional[str]:
"""去除 ListenBrainz 响应字段两端的空白,空值返回 None。"""
text = str(value).strip() if value is not None else ""
return text or None
@staticmethod @staticmethod
def _year(release_date: Any) -> Optional[int]: def _year(release_date: Any) -> Optional[int]:
"""从 ListenBrainz 发行日期提取年份。""" """从 ListenBrainz 发行日期提取年份。"""
+13 -7
View File
@@ -729,8 +729,8 @@ class MusicBrainzModule(_ModuleBase):
title=str(title), title=str(title),
artists=artists, artists=artists,
artist_ids=artist_ids, artist_ids=artist_ids,
album_type=release_group.get("primary-type"), album_type=cls._stripped(release_group.get("primary-type")),
secondary_types=[str(item) for item in release_group.get("secondary-types") or []], secondary_types=[cls._stripped(item) for item in release_group.get("secondary-types") or [] if cls._stripped(item)],
release_date=detail.get("date") or None, release_date=detail.get("date") or None,
cover_url=cls._build_cover_url(group_id), cover_url=cls._build_cover_url(group_id),
genres=cls._names_of(detail.get("genres")), genres=cls._names_of(detail.get("genres")),
@@ -1387,8 +1387,8 @@ class MusicBrainzModule(_ModuleBase):
album = (release or {}).get("title") album = (release or {}).get("title")
artists, artist_ids = cls._artist_credits(recording.get("artist-credit")) artists, artist_ids = cls._artist_credits(recording.get("artist-credit"))
album_artists, _ = cls._artist_credits((release or {}).get("artist-credit")) album_artists, _ = cls._artist_credits((release or {}).get("artist-credit"))
category_parts = [release_group.get("primary-type")] category_parts = [cls._stripped(release_group.get("primary-type"))]
category_parts.extend(release_group.get("secondary-types") or []) category_parts.extend(cls._stripped(item) for item in release_group.get("secondary-types") or [])
return MusicInfo( return MusicInfo(
media_source=cls._source, media_source=cls._source,
media_id=str(media_id), media_id=str(media_id),
@@ -1398,7 +1398,7 @@ class MusicBrainzModule(_ModuleBase):
album=album, album=album,
album_artist=" / ".join(album_artists) if album_artists else None, album_artist=" / ".join(album_artists) if album_artists else None,
album_id=str(release_group["id"]) if release_group.get("id") else None, album_id=str(release_group["id"]) if release_group.get("id") else None,
album_type=release_group.get("primary-type"), album_type=cls._stripped(release_group.get("primary-type")),
year=cls._year(release_date), year=cls._year(release_date),
release_date=release_date, release_date=release_date,
duration=cls._duration_seconds(recording.get("length")), duration=cls._duration_seconds(recording.get("length")),
@@ -1427,8 +1427,8 @@ class MusicBrainzModule(_ModuleBase):
title=str(title), title=str(title),
artists=artists, artists=artists,
artist_ids=artist_ids, artist_ids=artist_ids,
album_type=release_group.get("primary-type"), album_type=cls._stripped(release_group.get("primary-type")),
secondary_types=[str(item) for item in release_group.get("secondary-types") or []], secondary_types=[cls._stripped(item) for item in release_group.get("secondary-types") or [] if cls._stripped(item)],
release_date=release_group.get("first-release-date") or None, release_date=release_group.get("first-release-date") or None,
cover_url=cls._build_cover_url(media_id), cover_url=cls._build_cover_url(media_id),
genres=cls._names_of(release_group.get("genres")), genres=cls._names_of(release_group.get("genres")),
@@ -1627,6 +1627,12 @@ class MusicBrainzModule(_ModuleBase):
except (TypeError, ValueError): except (TypeError, ValueError):
return None return None
@staticmethod
def _stripped(value: Any) -> Optional[str]:
"""去除 MusicBrainz 响应字段两端的空白,空值返回 None。"""
text = str(value).strip() if value is not None else ""
return text or None
@staticmethod @staticmethod
def _optional_int(value: Any) -> Optional[int]: def _optional_int(value: Any) -> Optional[int]:
"""将 MusicBrainz 的碟号、音轨号等计数字段转换为可选整数。""" """将 MusicBrainz 的碟号、音轨号等计数字段转换为可选整数。"""
+13 -1
View File
@@ -1,6 +1,6 @@
from typing import Literal, Optional, Union from typing import Literal, Optional, Union
from pydantic import BaseModel, Field from pydantic import BaseModel, Field, field_validator
from app.schemas.common import JsonData from app.schemas.common import JsonData
from app.schemas.media import OptionalMediaIdentityMixin, RequiredMediaIdentityMixin from app.schemas.media import OptionalMediaIdentityMixin, RequiredMediaIdentityMixin
@@ -83,6 +83,12 @@ class MusicInfo(OptionalMediaIdentityMixin, BaseModel):
overview: Optional[str] = None overview: Optional[str] = None
vote_average: float = 0.0 vote_average: float = 0.0
@field_validator("album_type", mode="before")
@classmethod
def _strip_album_type(cls, v: Optional[str]) -> Optional[str]:
"""去除专辑类型字段两端的空白,防止数据源返回带空格的值。"""
return v.strip() if isinstance(v, str) and v.strip() else None
def __getattr__(self, name: str) -> None: def __getattr__(self, name: str) -> None:
"""影视专用字段兜底返回 None:音乐模型不存在这些字段,避免下游逐点安全访问。 """影视专用字段兜底返回 None:音乐模型不存在这些字段,避免下游逐点安全访问。
@@ -144,6 +150,12 @@ class MusicAlbumInfo(OptionalMediaIdentityMixin, BaseModel):
overview: Optional[str] = None overview: Optional[str] = None
vote_average: float = 0.0 vote_average: float = 0.0
@field_validator("album_type", mode="before")
@classmethod
def _strip_album_type(cls, v: Optional[str]) -> Optional[str]:
"""去除专辑类型字段两端的空白,防止数据源返回带空格的值。"""
return v.strip() if isinstance(v, str) and v.strip() else None
class MusicArtistInfo(OptionalMediaIdentityMixin, BaseModel): class MusicArtistInfo(OptionalMediaIdentityMixin, BaseModel):
"""标准化音乐艺术家信息。""" """标准化音乐艺术家信息。"""
+150
View File
@@ -0,0 +1,150 @@
"""音乐刮削结果中 album_type 等字段不应包含两端空白(Issue #6327)。"""
from app.modules.listenbrainz import ListenBrainzModule
from app.modules.musicbrainz import MusicBrainzModule
from app.schemas.music import MusicAlbumInfo as SchemaMusicAlbumInfo
from app.schemas.music import MusicInfo as SchemaMusicInfo
class TestMusicBrainzAlbumTypeStripped:
"""MusicBrainz 模块应将 album_type 和 secondary_types 两端空白去除。"""
def test_release_to_album_album_type_stripped(self):
"""专辑详情中 primary-type 带尾部空格时应被清理。"""
detail = {
"id": "release-1",
"title": "Test Album",
"artist-credit": [{"name": "Artist", "artist": {"id": "a1"}}],
"release-group": {
"id": "rg-1",
"primary-type": "Album ",
"secondary-types": ["Compilation ", " Soundtrack"],
},
"date": "2024-01-01",
"media": [],
}
album = MusicBrainzModule._release_to_album(detail)
assert album is not None
assert album.album_type == "Album"
assert album.secondary_types == ["Compilation", "Soundtrack"]
def test_recording_to_info_album_type_stripped(self):
"""歌曲识别结果中 album_type 和 category 不应包含空白。"""
recording = {
"id": "rec-1",
"title": "Test Song",
"artist-credit": [{"name": "Artist", "artist": {"id": "a1"}}],
"length": 300000,
"isrcs": ["USRC10000001"],
"genres": [],
"releases": [
{
"id": "rel-1",
"title": "Test Single",
"artist-credit": [{"name": "Artist", "artist": {"id": "a1"}}],
"release-group": {
"id": "rg-1",
"primary-type": "Single ",
"secondary-types": [" Remix "],
},
},
],
}
info = MusicBrainzModule._recording_to_info(recording)
assert info is not None
assert info.album_type == "Single"
assert info.category == "Single / Remix"
def test_release_group_to_album_strips_types(self):
"""Release Group 浏览结果中 album_type 和 secondary_types 应被清理。"""
release_group = {
"id": "rg-1",
"title": "Test EP",
"artist-credit": [{"name": "Artist", "artist": {"id": "a1"}}],
"primary-type": "EP ",
"secondary-types": ["Live ", " Compilation "],
"first-release-date": "2024",
"rating": {"value": "4", "votes-count": "10"},
}
album = MusicBrainzModule._release_group_to_album(release_group)
assert album is not None
assert album.album_type == "EP"
assert album.secondary_types == ["Live", "Compilation"]
class TestListenBrainzAlbumTypeStripped:
"""ListenBrainz 模块应将 album_type 和 category 两端空白去除。"""
def test_fresh_release_to_info_strips_album_type(self):
"""新发行条目中 release_group_primary_type 带空格时应被清理。"""
release = {
"release_group_mbid": "rg-1",
"release_name": "Test Album",
"artist_credit_name": "Artist",
"release_group_primary_type": "Album ",
"release_group_secondary_type": " Compilation ",
"release_date": "2024-01-01",
}
info = ListenBrainzModule._fresh_release_to_info(release)
assert info is not None
assert info.album_type == "Album"
assert info.category == "Album / Compilation"
def test_fresh_release_to_info_handles_none_type(self):
"""空白的 release_group_primary_type 应返回 None。"""
release = {
"release_group_mbid": "rg-1",
"release_name": "Test Album",
"artist_credit_name": "Artist",
"release_group_primary_type": " ",
"release_date": "2024-01-01",
}
info = ListenBrainzModule._fresh_release_to_info(release)
assert info is not None
assert info.album_type is None
class TestSchemaAlbumTypeValidator:
"""Pydantic schema 应作为兜底清理 album_type 两端空白。"""
def test_music_info_schema_strips_album_type(self):
"""MusicInfo schema 构造时 album_type 尾部空格应被去除。"""
info = SchemaMusicInfo(
album_type="Broadcast ",
title="Test",
)
assert info.album_type == "Broadcast"
def test_music_album_info_schema_strips_album_type(self):
"""MusicAlbumInfo schema 构造时 album_type 尾部空格应被去除。"""
album = SchemaMusicAlbumInfo(
album_type="EP ",
title="Test EP",
)
assert album.album_type == "EP"
def test_schema_blank_album_type_becomes_none(self):
"""纯空白的 album_type 应被归一为 None。"""
info = SchemaMusicInfo(
album_type=" ",
title="Test",
)
assert info.album_type is None
def test_schema_none_album_type_stays_none(self):
"""None 值的 album_type 应保持不变。"""
info = SchemaMusicInfo(
album_type=None,
title="Test",
)
assert info.album_type is None