feat: M9 日报结构化入库（HTML 改为写入 MySQL news_report/news_event，report_type=intl）

- 新增 report_db/ 包（models/schema/db，复用 news 项目实现，幂等 upsert） - reporter.py: _build_report_data + generate_report 写库返回 report_id - pipeline/cli 适配 report_id 返回值；HTML 渲染/上传保留 deprecated - 新增 tests/test_report_db.py；.env.example 增加 NEWS_DB_* 配置 - 已部署 pi5 并验证：真实生成 report_id=184（12 事件）+ 幂等覆盖
2026-08-04 11:09:17 +08:00
parent e1ec5f836d
commit d4a55bcaaa
14 changed files with 669 additions and 69 deletions
@@ -0,0 +1,179 @@
+"""日报结构化入库：模型 + _build_report_data 组装（纯逻辑，不连 DB）。"""
+
+from __future__ import annotations
+
+import json
+from collections import Counter
+from datetime import date, datetime
+
+import pytest
+from pydantic import ValidationError
+
+from report_db.models import EventRow, ReportData
+from scheduler.reporter import _build_report_data
+
+# --------------------------------------------------------------------------- #
+# 模型默认值
+# --------------------------------------------------------------------------- #
+
+
+class TestEventRow:
+    def test_minimal(self) -> None:
+        ev = EventRow(section="intl", rank=1, title="标题")
+        assert ev.importance is None
+        assert ev.sentiment is None
+
+    def test_full(self) -> None:
+        ev = EventRow(
+            section="intl", rank=2, importance=4, event_type="地缘政治",
+            title="t", summary="s", sentiment="negative", source="InvestingLive",
+            url="https://x.com/1",
+        )
+        assert ev.sentiment == "negative"
+
+    def test_missing_title_raises(self) -> None:
+        with pytest.raises(ValidationError):
+            EventRow(section="intl", rank=1)  # type: ignore[call-arg]
+
+
+class TestReportData:
+    def test_defaults(self) -> None:
+        r = ReportData(
+            report_date=date(2026, 8, 4),
+            report_type="intl",
+            generated_at=datetime(2026, 8, 4, 8, 0),
+        )
+        assert r.file_name == ""
+        assert r.stats == {}
+        assert r.events == []
+
+    def test_with_events(self) -> None:
+        r = ReportData(
+            report_date=date(2026, 8, 4),
+            report_type="intl",
+            generated_at=datetime(2026, 8, 4, 8, 0),
+            ai_summary="摘要",
+            events=[EventRow(section="intl", rank=1, title="t")],
+        )
+        assert len(r.events) == 1
+
+
+# --------------------------------------------------------------------------- #
+# _build_report_data（intl 结构）
+# --------------------------------------------------------------------------- #
+
+
+def _fake_high_event(title_zh: str, importance: int, *,
+                     event_type: str = "其他", sentiment: str = "neutral",
+                     summary_zh: str = "摘要", source_id: str = "investinglive",
+                     url: str = "https://investinglive.com/news/1") -> dict:
+    """构造 _dedup_events 之后的事件结构（含 article 属性）。"""
+    return {
+        "importance": importance,
+        "sentiment": sentiment,
+        "summary_zh": summary_zh,
+        "event_type": event_type,
+        "stock_codes": [],
+        "article": {
+            "title": f"EN {title_zh}",
+            "title_zh": title_zh,
+            "url": url,
+            "source_id": source_id,
+        },
+    }
+
+
+class TestBuildReportData:
+    def test_sections_and_ranks(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        high = [
+            _fake_high_event("新闻A", 5),
+            _fake_high_event("新闻B", 4),
+            _fake_high_event("新闻C", 3),
+        ]
+        r = _build_report_data(
+            now, {"raw_total": 100, "proc": 90}, high,
+            Counter(), Counter(), Counter(), Counter(), "AI摘要",
+        )
+        assert r.report_date == date(2026, 8, 4)
+        assert r.report_type == "intl"
+        assert r.file_name == ""
+        assert r.ai_summary == "AI摘要"
+        assert [(e.section, e.rank) for e in r.events] == [
+            ("intl", 1), ("intl", 2), ("intl", 3),
+        ]
+
+    def test_field_mapping(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        high = [_fake_high_event("英伟达财报超预期", 5, event_type="公司财报",
+                                 sentiment="positive", summary_zh="营收超预期",
+                                 source_id="investinglive",
+                                 url="https://investinglive.com/news/42")]
+        r = _build_report_data(now, {}, high, Counter(), Counter(), Counter(),
+                               Counter(), "")
+        ev = r.events[0]
+        assert ev.title == "英伟达财报超预期"          # title_zh 优先
+        assert ev.importance == 5
+        assert ev.event_type == "公司财报"
+        assert ev.summary == "营收超预期"
+        assert ev.sentiment == "positive"
+        assert ev.url == "https://investinglive.com/news/42"
+        assert ev.source == "InvestingLive"           # 域名 → 源展示名
+
+    def test_source_fallback_without_url(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        ev = _fake_high_event("无URL事件", 4, url="")
+        r = _build_report_data(now, {}, [ev], Counter(), Counter(), Counter(),
+                               Counter(), "")
+        assert r.events[0].url is None
+        # url 为空时回退 source_id → sources.yaml 展示名
+        assert r.events[0].source == "InvestingLive"
+
+    def test_stats_snapshot(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        high = [
+            _fake_high_event("A", 5, event_type="宏观", sentiment="positive"),
+            _fake_high_event("B", 4, event_type="宏观", sentiment="negative"),
+        ]
+        r = _build_report_data(
+            now,
+            {"raw_total": 120, "proc": 100, "deduped": 90,
+             "emb_count": 80, "qdrant_count": 75},
+            high,
+            Counter({"positive": 1, "negative": 1}),
+            Counter({5: 1, 4: 1}),
+            Counter({"宏观": 2}),
+            Counter({"investinglive": 2}),
+            "摘要",
+        )
+        # stats 可 JSON 序列化（入库时 json.dumps）
+        json.dumps(r.stats, ensure_ascii=False)
+        assert r.stats["pipeline"]["raw_total"] == 120
+        assert r.stats["sentiment"] == {"positive": 1, "negative": 1}
+        assert r.stats["importance"] == [
+            {"importance": 4, "count": 1}, {"importance": 5, "count": 1},
+        ]
+        assert r.stats["event_types"] == [{"event_type": "宏观", "count": 2}]
+        assert r.stats["source_dist"] == [{"source": "InvestingLive", "count": 2}]
+
+    def test_title_truncated(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        ev = _fake_high_event("长" * 600, 4)
+        r = _build_report_data(now, {}, [ev], Counter(), Counter(), Counter(),
+                               Counter(), "")
+        assert len(r.events[0].title) == 512
+
+    def test_empty_events(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        r = _build_report_data(now, {}, [], Counter(), Counter(), Counter(),
+                               Counter(), "")
+        assert r.events == []
+        assert r.ai_summary is None
+
+    def test_question_mark_sentiment_normalized(self) -> None:
+        now = datetime(2026, 8, 4, 8, 0, 0)
+        ev = _fake_high_event("未分类情绪", 4, sentiment="?")
+        r = _build_report_data(now, {}, [ev], Counter(), Counter(), Counter(),
+                               Counter(), "")
+        # "?" 不写入 DB，留 None
+        assert r.events[0].sentiment is None