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
This commit is contained in:
2026-08-12 12:56:04 +08:00
parent 182f788857
commit 794ce6c853
10 changed files with 129 additions and 7 deletions
+25
View File
@@ -121,6 +121,31 @@ def test_event_types_constant_includes_common() -> None:
assert must in EVENT_TYPES
# --------------------------------------------------------------------------- #
# ExtractedEvent.sources 多源字段
# --------------------------------------------------------------------------- #
def test_extracted_event_sources_defaults_to_main_source() -> None:
"""未提供 sources 时兜底为 [source_id](兼容旧产物)。"""
ev = ExtractedEvent(
source_id="cls", url="https://x/1", url_hash="h1", title="t",
event=EventExtraction(sentiment="positive", importance=3, event_type="重大合同"),
provider="deepseek", model="m",
)
assert ev.sources == ["cls"]
def test_extracted_event_sources_keeps_main_first_and_dedup() -> None:
"""sources 保主源居首、去重保序。"""
ev = ExtractedEvent(
source_id="cls", url="https://x/1", url_hash="h1", title="t",
sources=["sina", "cls", "eastmoney", "sina"],
event=EventExtraction(sentiment="neutral", importance=2, event_type="其他"),
provider="deepseek", model="m",
)
assert ev.sources == ["cls", "sina", "eastmoney"]
# --------------------------------------------------------------------------- #
# JSON 提取与解析
# --------------------------------------------------------------------------- #