fix(subscribe): 修复历史 note 双重 JSON 编码导致的订阅列表 500

2.0 时代旧代码对 JSON 列显式 json.dumps,导致 note 字段在库里是
字符串而非数组,响应模型按 List[int] 校验失败返回 500。

- 新增 3.0.7 数据迁移,解析并回写字符串型 note 为真正的 JSON 数组
- Subscribe 响应模型增加 note 字符串兼容解析,脏数据按空值处理
This commit is contained in:
jxxghp
2026-08-17 10:56:31 +08:00
parent eefe1ec931
commit 77b7960b7d
3 changed files with 131 additions and 1 deletions
+24 -1
View File
@@ -1,6 +1,7 @@
import json
from typing import Optional, List, Dict, Any, ClassVar from typing import Optional, List, Dict, Any, ClassVar
from pydantic import BaseModel, Field, ConfigDict, model_validator from pydantic import BaseModel, Field, ConfigDict, model_validator, field_validator
from app.schemas.media import OptionalMediaIdentityMixin from app.schemas.media import OptionalMediaIdentityMixin
from app.schemas.types import MediaSource, MediaType from app.schemas.types import MediaSource, MediaType
@@ -154,6 +155,28 @@ class Subscribe(OptionalMediaIdentityMixin, BaseModel):
model_config = ConfigDict(from_attributes=True) model_config = ConfigDict(from_attributes=True)
@field_validator("note", mode="before")
@classmethod
def _normalize_legacy_note(cls, value: Any) -> Any:
"""
兼容历史字符串型 note。
2.0 时代旧代码对 JSON 列显式做了 ``json.dumps``,历史数据可能是一层
或两层 JSON 编码的字符串(如 ``'[1, 2, 3]'``),不解析会触发响应
校验 500;解析失败按空值处理,避免脏数据阻塞整个订阅列表接口。
"""
if not isinstance(value, str):
return value
parsed = value
while isinstance(parsed, str):
try:
parsed = json.loads(parsed)
except (TypeError, ValueError):
return None
if isinstance(parsed, list):
return [item for item in parsed if isinstance(item, int)]
return None
@model_validator(mode="before") @model_validator(mode="before")
@classmethod @classmethod
def _normalize_empty_strings(cls, data: Any) -> Any: def _normalize_empty_strings(cls, data: Any) -> Any:
+76
View File
@@ -0,0 +1,76 @@
"""3.0.7
修复历史订阅 note 字段的双重 JSON 编码
Revision ID: 73370ce9bab7
Revises: f4c8d2a7b1e6
Create Date: 2026-08-17
"""
import json
from alembic import op
import sqlalchemy as sa
revision = "73370ce9bab7"
down_revision = "f4c8d2a7b1e6"
branch_labels = None
depends_on = None
def _parse_legacy_note(value: object):
"""解析历史写入的字符串型 note,兼容一层或两层 JSON 编码。
2.0 时代旧代码对 JSON 列显式做了 ``json.dumps(note)``SQLite 下 2.0.3
的列类型迁移又是空操作,导致读回的值是 ``'[1, 2, 3]'`` 这类字符串而非列表;
字符串会被响应模型按 ``List[int]`` 校验并触发 500。解析失败按空值处理,
不丢弃整型数组以外的历史内容。
"""
parsed = value
while isinstance(parsed, str):
try:
parsed = json.loads(parsed)
except (TypeError, ValueError):
return None
if isinstance(parsed, list) and all(isinstance(item, int) for item in parsed):
return parsed
return None
def _repair_subscribe_note() -> None:
"""把 subscribe 表中字符串型 note 回写为真正的 JSON 数组。
通过 sa.JSON 类型绑定参数写回,SQLite 与 PostgreSQL 都会按各自方言
序列化,保证后续按模型读回时得到整数列表。
"""
subscribe = sa.table(
"subscribe",
sa.column("id", sa.Integer()),
sa.column("note", sa.JSON()),
)
connection = op.get_bind()
rows = connection.execute(
sa.select(subscribe.c.id, subscribe.c.note)
).mappings().all()
for row in rows:
note = row["note"]
if not isinstance(note, str):
continue
repaired = _parse_legacy_note(note)
connection.execute(
subscribe.update()
.where(subscribe.c.id == row["id"])
.values(note=repaired)
)
def upgrade() -> None:
"""修复历史订阅 note 字段的双重 JSON 编码数据。"""
if "subscribe" not in sa.inspect(op.get_bind()).get_table_names():
return
_repair_subscribe_note()
def downgrade() -> None:
"""数据修复不可逆,降级不做任何操作。"""
pass
+31
View File
@@ -1424,3 +1424,34 @@ def test_create_subscribe_accepts_music_payload_with_empty_strings():
assert payload["type"] == MediaType.MUSIC.value assert payload["type"] == MediaType.MUSIC.value
assert payload["music_type"] == "album" assert payload["music_type"] == "album"
assert payload["total_tracks"] == 13 assert payload["total_tracks"] == 13
class _LegacyNoteRow:
"""携带历史字符串 note 的最小 ORM 替身。"""
def __init__(self, note):
self.note = note
@pytest.mark.parametrize(
("raw", "expected"),
[
("[1, 2, 3, 4]", [1, 2, 3, 4]), # 双重 JSON 编码的整型数组
("[1, 2]", [1, 2]),
("[]", []), # 双重编码的空数组
("null", None), # 双重编码的 null
("not json", None), # 无法解析的历史脏数据
([1, 2, 3], [1, 2, 3]), # 正常列表原样保留
(None, None), # 空值
],
)
def test_subscribe_note_normalizes_legacy_json_string(raw, expected):
"""历史字符串型 note 应被解析为整数列表,避免响应校验 500。"""
subscribe = Subscribe.model_validate(_LegacyNoteRow(note=raw))
assert subscribe.note == expected
def test_subscribe_note_strips_non_int_items_from_legacy_string():
"""历史脏数据中混入非整数元素时只保留整数,不阻塞整个订阅列表接口。"""
subscribe = Subscribe.model_validate(_LegacyNoteRow(note='[1, 2, "x", 3]'))
assert subscribe.note == [1, 2, 3]