feat: 日报事件多新闻源入库(news_event.sources 列)

- ExtractedEvent 增加 sources 字段(主源居首去重,旧产物兜底 [source_id])
- extract_event(_async) 增加 sources 参数;run_event_extraction 读取
  deduped uniques 的 sources 透传
- reporter _load_events_from_dir 读取 sources → EventRow.sources
- news_event 建表加 sources TEXT 列;init_schema 幂等迁移旧表(捕获
  Duplicate column);save_report INSERT 写 JSON 多源
- 新增测试:ExtractedEvent/EventRow.sources 兜底与保序、_load_events_from_dir 多源

report_db/db.py

@@ -11,7 +11,7 @@ import pymysql
 from loguru import logger
 
 from .models import ReportData
-from .schema import DDL_STATEMENTS
+from .schema import _ALTER_ADD_SOURCES, DDL_STATEMENTS
 
 
 @dataclass(frozen=True)
@@ -60,10 +60,19 @@ def connect(cfg: DbConfig | None = None) -> pymysql.Connection:
 
 
 def init_schema(conn: pymysql.Connection) -> None:
-    """建表（CREATE TABLE IF NOT EXISTS ×2），幂等。"""
+    """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")
 
@@ -112,8 +121,8 @@ def save_report(conn: pymysql.Connection, report: ReportData) -> int:
                 """
                 INSERT INTO news_event
                     (report_id, section, rank, importance, event_type, title,
-                     summary, sentiment, source, url)
-                VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
+                     summary, sentiment, source, sources, url)
+                VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
                 """,
                 (
                     report_id,
@@ -125,6 +134,7 @@ def save_report(conn: pymysql.Connection, report: ReportData) -> int:
                     ev.summary,
                     ev.sentiment,
                     ev.source,
+                    json.dumps(ev.sources, ensure_ascii=False) if ev.sources else None,
                     ev.url,
                 ),
             )

report_db/models.py

@@ -18,7 +18,8 @@ class EventRow(BaseModel):
     title: str
     summary: str | None = None
     sentiment: str | None = None  # positive | negative | neutral | ''
-    source: str | None = None
+    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
 
 

report_db/schema.py

@@ -33,7 +33,8 @@ DDL_STATEMENTS: list[str] = [
         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 '来源',
+        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),
@@ -41,3 +42,9 @@ DDL_STATEMENTS: list[str] = [
     ) 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"
+)