mirror of
https://github.com/stardrophere/InsightRadar.git
synced 2026-06-06 00:52:50 +08:00
stardrophere
295 lines
12 KiB
Python
295 lines
12 KiB
Python
from datetime import datetime, timezone, time
|
|
from typing import Optional, Any
|
|
import enum
|
|
|
|
from sqlalchemy import (
|
|
String, Integer, BigInteger, Text, Boolean, DateTime, Time,
|
|
Float, JSON, ForeignKey, Enum, UniqueConstraint, Index
|
|
)
|
|
from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column, relationship
|
|
|
|
|
|
# ==========================================
|
|
# 0. 全局基类与枚举定义
|
|
# ==========================================
|
|
|
|
class Base(DeclarativeBase):
|
|
"""SQLAlchemy 2.0 声明式基类"""
|
|
pass
|
|
|
|
|
|
class SourceType(str, enum.Enum):
|
|
HOT_TREND = "HOT_TREND"
|
|
RSS_FEED = "RSS_FEED"
|
|
API = "API"
|
|
|
|
|
|
class TargetType(str, enum.Enum):
|
|
EVENT = "EVENT"
|
|
TREND = "TREND"
|
|
ARTICLE = "ARTICLE"
|
|
|
|
|
|
class TaskStatus(str, enum.Enum):
|
|
SUCCESS = "SUCCESS"
|
|
ERROR = "ERROR"
|
|
|
|
|
|
class GenderType(str, enum.Enum):
|
|
MALE = "MALE"
|
|
FEMALE = "FEMALE"
|
|
OTHER = "OTHER"
|
|
UNKNOWN = "UNKNOWN"
|
|
|
|
|
|
def utcnow():
|
|
"""获取带UTC时区的当前时间 (推荐实践)"""
|
|
return datetime.now(timezone.utc)
|
|
|
|
|
|
# ==========================================
|
|
# 模块一：信息源管理
|
|
# ==========================================
|
|
class InfoSource(Base):
|
|
__tablename__ = "info_sources"
|
|
|
|
id: Mapped[int] = mapped_column(primary_key=True, autoincrement=True)
|
|
source_name: Mapped[str] = mapped_column(String(100), comment="信息源名称")
|
|
source_type: Mapped[SourceType] = mapped_column(Enum(SourceType))
|
|
home_url: Mapped[Optional[str]] = mapped_column(String(255))
|
|
is_enabled: Mapped[bool] = mapped_column(Boolean, default=True)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块二：AI 语义聚类中枢 (大事件池)
|
|
# ==========================================
|
|
class UnifiedEvent(Base):
|
|
__tablename__ = "unified_events"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
unified_title: Mapped[str] = mapped_column(String(255), comment="AI统一标题")
|
|
ai_comprehensive_summary: Mapped[Optional[str]] = mapped_column(Text, comment="AI全局深度总结")
|
|
|
|
# SQLite 没有原生 Vector 类型，存为用逗号分隔的字符串或JSON，Postgres可换成 PGVector
|
|
center_embedding: Mapped[Optional[str]] = mapped_column(Text, comment="中心向量")
|
|
hot_score: Mapped[int] = mapped_column(Integer, default=0, comment="聚合热度得分")
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块三：内容存储库 (热搜 & 新闻子节点)
|
|
# ==========================================
|
|
class TrendingEvent(Base):
|
|
__tablename__ = "trending_events"
|
|
__table_args__ = (
|
|
UniqueConstraint("source_id", "external_id", name="idx_unique_external_trend"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"))
|
|
unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id"))
|
|
|
|
external_id: Mapped[str] = mapped_column(String(32), comment="32位MD5哈希指纹防重")
|
|
title_embedding: Mapped[Optional[str]] = mapped_column(Text)
|
|
|
|
icon_url: Mapped[Optional[str]] = mapped_column(String(500))
|
|
current_headline: Mapped[str] = mapped_column(String(255))
|
|
event_url: Mapped[Optional[str]] = mapped_column(String(500))
|
|
app_link: Mapped[Optional[str]] = mapped_column(String(500))
|
|
current_ranking: Mapped[Optional[int]] = mapped_column(Integer)
|
|
brief_snippet: Mapped[Optional[str]] = mapped_column(Text)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
class NewsArticle(Base):
|
|
__tablename__ = "news_articles"
|
|
__table_args__ = (
|
|
UniqueConstraint("source_id", "external_id", name="idx_unique_external_article"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"))
|
|
unified_event_id: Mapped[Optional[int]] = mapped_column(ForeignKey("unified_events.id"))
|
|
|
|
external_id: Mapped[str] = mapped_column(String(32))
|
|
title_embedding: Mapped[Optional[str]] = mapped_column(Text)
|
|
|
|
cover_image_url: Mapped[Optional[str]] = mapped_column(String(500))
|
|
article_title: Mapped[str] = mapped_column(String(255))
|
|
article_url: Mapped[Optional[str]] = mapped_column(String(500))
|
|
author_name: Mapped[Optional[str]] = mapped_column(String(100))
|
|
original_summary: Mapped[Optional[str]] = mapped_column(Text)
|
|
publish_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True))
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块四：热度与轨迹追踪
|
|
# ==========================================
|
|
class HeadlineRevision(Base):
|
|
__tablename__ = "headline_revisions"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id"))
|
|
previous_headline: Mapped[str] = mapped_column(String(255))
|
|
revised_headline: Mapped[str] = mapped_column(String(255))
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
class RankingLog(Base):
|
|
__tablename__ = "ranking_logs"
|
|
__table_args__ = (
|
|
Index("idx_event_time", "event_id", "observed_at"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
event_id: Mapped[int] = mapped_column(ForeignKey("trending_events.id"))
|
|
ranking_position: Mapped[int] = mapped_column(Integer)
|
|
observed_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块五：多态话题与多态评论
|
|
# ==========================================
|
|
class ExtractedTopic(Base):
|
|
__tablename__ = "extracted_topics"
|
|
__table_args__ = (
|
|
Index("idx_topic_keyword", "topic_keyword"),
|
|
Index("idx_polymorphic_topics", "target_type", "target_id"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
target_type: Mapped[TargetType] = mapped_column(Enum(TargetType))
|
|
target_id: Mapped[int] = mapped_column(BigInteger)
|
|
topic_keyword: Mapped[str] = mapped_column(String(100))
|
|
relevance_score: Mapped[Optional[float]] = mapped_column(Float)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
class DiscussionComment(Base):
|
|
__tablename__ = "discussion_comments"
|
|
__table_args__ = (
|
|
Index("idx_polymorphic_comments", "target_type", "target_id"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
target_type: Mapped[TargetType] = mapped_column(Enum(TargetType))
|
|
target_id: Mapped[int] = mapped_column(BigInteger)
|
|
|
|
commenter_name: Mapped[Optional[str]] = mapped_column(String(100))
|
|
comment_content: Mapped[str] = mapped_column(Text)
|
|
likes_count: Mapped[int] = mapped_column(Integer, default=0)
|
|
external_comment_id: Mapped[Optional[str]] = mapped_column(String(32))
|
|
comment_time: Mapped[Optional[datetime]] = mapped_column(DateTime(timezone=True))
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块六：用户画像与多渠道高可用推送系统
|
|
# ==========================================
|
|
class AppUser(Base):
|
|
__tablename__ = "app_users"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
email: Mapped[str] = mapped_column(String(150), unique=True, index=True)
|
|
password_hash: Mapped[Optional[str]] = mapped_column(String(255))
|
|
|
|
nickname: Mapped[Optional[str]] = mapped_column(String(100))
|
|
avatar_url: Mapped[Optional[str]] = mapped_column(String(500))
|
|
gender: Mapped[GenderType] = mapped_column(Enum(GenderType), default=GenderType.UNKNOWN)
|
|
|
|
# 核心：万能扩展收纳箱 (SQLite 完美支持通过 SQLAlchemy 存储 JSON)
|
|
metadata_: Mapped[Optional[Any]] = mapped_column("metadata", JSON, comment="自定义扩展偏好")
|
|
|
|
timezone: Mapped[str] = mapped_column(String(50), default="Asia/Shanghai")
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
class UserPushEndpoint(Base):
|
|
__tablename__ = "user_push_endpoints"
|
|
__table_args__ = (
|
|
UniqueConstraint("user_id", "channel_type", name="idx_unique_user_channel"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"))
|
|
channel_type: Mapped[str] = mapped_column(String(50), comment="如 EMAIL, WECHAT")
|
|
channel_account: Mapped[str] = mapped_column(String(255))
|
|
is_active: Mapped[bool] = mapped_column(Boolean, default=True)
|
|
priority_level: Mapped[int] = mapped_column(Integer, default=1, comment="1最高，降级重试")
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow)
|
|
|
|
|
|
class UserTopicPreference(Base):
|
|
__tablename__ = "user_topic_preferences"
|
|
__table_args__ = (
|
|
UniqueConstraint("user_id", "interested_keyword", name="idx_unique_preference"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"))
|
|
interested_keyword: Mapped[str] = mapped_column(String(100))
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
class UserDeliverySchedule(Base):
|
|
__tablename__ = "user_delivery_schedules"
|
|
__table_args__ = (
|
|
UniqueConstraint("user_id", "delivery_time", name="idx_unique_schedule"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"))
|
|
delivery_time: Mapped[time] = mapped_column(Time, comment="如 08:30:00")
|
|
is_active: Mapped[bool] = mapped_column(Boolean, default=True)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
class DeliveryHistory(Base):
|
|
__tablename__ = "delivery_history"
|
|
__table_args__ = (
|
|
UniqueConstraint("user_id", "target_type", "target_id", name="idx_prevent_duplicate_push"),
|
|
)
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
user_id: Mapped[int] = mapped_column(ForeignKey("app_users.id"))
|
|
target_type: Mapped[TargetType] = mapped_column(Enum(TargetType))
|
|
target_id: Mapped[int] = mapped_column(BigInteger)
|
|
status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus))
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
|
|
|
|
|
# ==========================================
|
|
# 模块七：系统任务监控
|
|
# ==========================================
|
|
class DataSyncTask(Base):
|
|
__tablename__ = "data_sync_tasks"
|
|
|
|
id: Mapped[int] = mapped_column(BigInteger, primary_key=True, autoincrement=True)
|
|
source_id: Mapped[int] = mapped_column(ForeignKey("info_sources.id"))
|
|
items_fetched: Mapped[int] = mapped_column(Integer, default=0)
|
|
task_status: Mapped[TaskStatus] = mapped_column(Enum(TaskStatus))
|
|
error_trace: Mapped[Optional[str]] = mapped_column(Text)
|
|
|
|
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|