docs: 文档清理与重构 — 统一为 3 个核心文档

- 删除 5 个过时/残留文档(project_plan/agent_prompt/optimization_plan/report_db_design/deploy/README)
- 新建 docs/architecture.md(项目架构:11 包职责+数据模型+配置+产物)
- 重写 docs/user-guide.md(CLI 全量+增量/断点续跑+MCP+FAQ)
- 重写 README.md(精简入口+文档索引)
- 更新 continuation.md(追加本次记录)
- 更新 .gitignore(排除 data/* 运行产物)
This commit is contained in:
2026-08-22 17:10:39 +08:00
commit 65ead54b4f
101 changed files with 21093 additions and 0 deletions
+19
View File
@@ -0,0 +1,19 @@
"""日报结构化入库(Milestone 10)。
职责:日报内容(finance/intl)结构化后写入 MySQL(news_report / news_event),
供用户另行实现的 API/前端读取。本项目不提供 API 与前端。
"""
from .db import connect, exists_report, fetch_report, init_schema, load_db_config, save_report
from .models import EventRow, ReportData
__all__ = [
"EventRow",
"ReportData",
"connect",
"exists_report",
"fetch_report",
"init_schema",
"load_db_config",
"save_report",
]
+166
View File
@@ -0,0 +1,166 @@
"""日报结构化入库:DB 连接、建表、写入。"""
from __future__ import annotations
import json
import os
from dataclasses import dataclass
from typing import Any
import pymysql
from loguru import logger
from .models import ReportData
from .schema import _ALTER_ADD_SOURCES, DDL_STATEMENTS
@dataclass(frozen=True)
class DbConfig:
"""MySQL 连接配置(来自环境变量 NEWS_DB_*)。"""
host: str
port: int
user: str
password: str
name: str
def load_db_config() -> DbConfig:
"""从环境变量读取 NEWS_DB_*,缺失密码时抛异常(禁止默认密码)。"""
host = os.environ.get("NEWS_DB_HOST", "127.0.0.1")
port = int(os.environ.get("NEWS_DB_PORT", "13306"))
user = os.environ.get("NEWS_DB_USER", "myquant")
password = os.environ.get("NEWS_DB_PASSWORD", "")
name = os.environ.get("NEWS_DB_NAME", "myquant")
if not password:
logger.error("NEWS_DB_PASSWORD 未配置,请在 .env 中设置")
raise ValueError("NEWS_DB_PASSWORD 未配置")
return DbConfig(host=host, port=port, user=user, password=password, name=name)
def connect(cfg: DbConfig | None = None) -> pymysql.Connection:
"""建立短连接(autocommit=False)。失败时记录日志并抛出。"""
cfg = cfg or load_db_config()
try:
conn = pymysql.connect(
host=cfg.host,
port=cfg.port,
user=cfg.user,
password=cfg.password,
database=cfg.name,
charset="utf8mb4",
autocommit=False,
cursorclass=pymysql.cursors.DictCursor,
)
except Exception:
logger.exception("连接 MySQL 失败: host={} port={} user={}", cfg.host, cfg.port, cfg.user)
raise
logger.debug("MySQL 已连接: {}/{}", cfg.host, cfg.name)
return conn
def init_schema(conn: pymysql.Connection) -> None:
"""建表(CREATE TABLE IF NOT EXISTS ×2)+ 旧表 sources 列迁移,幂等。"""
with conn.cursor() as cur:
for ddl in DDL_STATEMENTS:
cur.execute(ddl)
# 旧库兼容:news_event 已存在但缺 sources 列时补列
try:
cur.execute(_ALTER_ADD_SOURCES)
logger.info("news_event 迁移:新增 sources 多源列")
except pymysql.err.OperationalError as e:
if e.args and "Duplicate column" in str(e.args[0]):
logger.debug("news_event.sources 列已存在,跳过迁移")
else:
raise
conn.commit()
logger.info("news_report / news_event 建表完成")
def save_report(conn: pymysql.Connection, report: ReportData) -> int:
"""事务内写入一份日报。
幂等策略:
- 主表按 (report_date, report_type, file_name) 唯一键 upsert;
- 事件表 DELETE 该 report 旧行后全量 INSERT(整份覆盖一致)。
返回 report_id。
"""
with conn.cursor() as cur:
stats_json = json.dumps(report.stats, ensure_ascii=False) if report.stats else None
cur.execute(
"""
INSERT INTO news_report
(report_date, report_type, file_name, generated_at, ai_summary, stats)
VALUES (%s, %s, %s, %s, %s, %s)
ON DUPLICATE KEY UPDATE
generated_at = VALUES(generated_at),
ai_summary = VALUES(ai_summary),
stats = VALUES(stats)
""",
(
report.report_date,
report.report_type,
report.file_name,
report.generated_at,
report.ai_summary,
stats_json,
),
)
cur.execute(
"SELECT id FROM news_report WHERE report_date=%s AND report_type=%s AND file_name=%s",
(report.report_date, report.report_type, report.file_name),
)
row = cur.fetchone()
if row is None: # pragma: no cover - 理论不可达
raise RuntimeError("写入 news_report 后查询不到 report_id")
report_id: int = row["id"]
cur.execute("DELETE FROM news_event WHERE report_id=%s", (report_id,))
for ev in report.events:
cur.execute(
"""
INSERT INTO news_event
(report_id, section, rank, importance, event_type, title,
summary, sentiment, source, sources, url)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
""",
(
report_id,
ev.section,
ev.rank,
ev.importance,
ev.event_type,
ev.title,
ev.summary,
ev.sentiment,
ev.source,
json.dumps(ev.sources, ensure_ascii=False) if ev.sources else None,
ev.url,
),
)
conn.commit()
logger.info("日报已入库: report_id={} date={} type={} events={}",
report_id, report.report_date, report.report_type, len(report.events))
return report_id
def fetch_report(conn: pymysql.Connection, report_id: int) -> dict[str, Any] | None:
"""读侧辅助(联调/测试用),返回主表行。"""
with conn.cursor() as cur:
cur.execute("SELECT * FROM news_report WHERE id=%s", (report_id,))
return cur.fetchone()
def exists_report(
conn: pymysql.Connection,
report_date: Any,
report_type: str,
file_name: str,
) -> bool:
"""判断主表是否已存在该唯一键记录(历史导入幂等用)。"""
with conn.cursor() as cur:
cur.execute(
"SELECT 1 FROM news_report WHERE report_date=%s AND report_type=%s AND file_name=%s",
(report_date, report_type, file_name),
)
return cur.fetchone() is not None
+35
View File
@@ -0,0 +1,35 @@
"""日报结构化入库:数据模型。"""
from __future__ import annotations
from datetime import date, datetime
from typing import Any
from pydantic import BaseModel, Field
class EventRow(BaseModel):
"""一条事件记录,对应 news_event 一行。"""
section: str # xwlb | news | cninfo | intl
rank: int # 板块内序号(从 1 开始)
importance: int | None = None
event_type: str | None = None
title: str
summary: str | None = None
sentiment: str | None = None # positive | negative | neutral | ''
source: str | None = None # 主源
sources: list[str] | None = None # 全部来源(主源居首),多源新闻记录
url: str | None = None
class ReportData(BaseModel):
"""一份完整日报:news_report 一行 + news_event 多行。"""
report_date: date
report_type: str # finance | intl
file_name: str = "" # 源文件名(新生成日报可为空)
generated_at: datetime
ai_summary: str | None = None
stats: dict[str, Any] = Field(default_factory=dict)
events: list[EventRow] = Field(default_factory=list)
+50
View File
@@ -0,0 +1,50 @@
"""MySQL DDL:日报结构化入库(表前缀 news_,目标 MariaDB 10.11)。
与 project_plan.md「十八、Milestone 10」及 docs/report_db_design.md 保持一致。
"""
from __future__ import annotations
DDL_STATEMENTS: list[str] = [
# 日报主表
"""
CREATE TABLE IF NOT EXISTS news_report (
id BIGINT UNSIGNED AUTO_INCREMENT PRIMARY KEY,
report_date DATE NOT NULL COMMENT '日报日期',
report_type VARCHAR(16) NOT NULL COMMENT 'finance=A股日报 / intl=国际财经日报',
file_name VARCHAR(160) NOT NULL DEFAULT '' COMMENT '源文件名(历史解析);新生成可为空',
generated_at DATETIME NOT NULL COMMENT '生成时间',
ai_summary TEXT NULL COMMENT 'AI 摘要全文',
stats JSON NULL COMMENT '数据总览统计快照(管道/情绪/重要度/事件类型/来源分布)',
created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
UNIQUE KEY uk_report_file (report_date, report_type, file_name),
KEY idx_report_date (report_date)
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci COMMENT='每日日报主表'
""",
# 日报事件明细
"""
CREATE TABLE IF NOT EXISTS news_event (
id BIGINT UNSIGNED AUTO_INCREMENT PRIMARY KEY,
report_id BIGINT UNSIGNED NOT NULL COMMENT 'FK → news_report.id',
section VARCHAR(16) NOT NULL COMMENT '板块: xwlb=新闻联播 / news=财经新闻 / cninfo=公告调研 / intl=国际重要事件',
rank INT NOT NULL DEFAULT 0 COMMENT '板块内序号',
importance INT NULL COMMENT '重要度 1-5',
event_type VARCHAR(64) NULL COMMENT '事件类型',
title VARCHAR(512) NOT NULL COMMENT '标题',
summary TEXT NULL COMMENT '摘要/正文',
sentiment VARCHAR(8) NULL COMMENT 'positive/negative/neutral',
source VARCHAR(64) NULL COMMENT '主来源',
sources TEXT NULL COMMENT '全部来源 JSON 数组(主源居首),多源新闻记录',
url VARCHAR(512) NULL COMMENT '原文链接',
created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
KEY idx_report_section (report_id, section),
KEY idx_title (title(255))
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci COMMENT='日报事件明细'
""",
]
# 旧库迁移:为已存在的 news_event 表补充 sources 列(MySQL 无 ADD COLUMN IF NOT EXISTS)
_ALTER_ADD_SOURCES = (
"ALTER TABLE news_event ADD COLUMN sources TEXT NULL "
"COMMENT '全部来源 JSON 数组(主源居首),多源新闻记录' AFTER source"
)