test: 真实样本集成测试（3 类型 xlsx）

tests/test_real_samples.py

@@ -0,0 +1,39 @@
+from pathlib import Path
+
+import pytest
+
+from genesis.parsers.excel_parser import ExcelParser
+
+SAMPLES = Path(__file__).resolve().parents[1] / "samples"
+
+
+def _x(name: str) -> Path:
+    return SAMPLES / name
+
+
+def test_new_dev_sample_has_tables():
+    p = _x("要件定義_新規開発.xlsx")
+    if not p.exists():
+        pytest.skip("样本缺失")
+    result = ExcelParser().parse(p)
+    by_name = {t.name: t for t in result.tables}
+    assert "機能一覧" in by_name
+    assert by_name["機能一覧"].rows
+    assert any(t.name == "DB定義" for t in result.tables)
+
+
+def test_additional_modification_has_tables():
+    p = _x("要件定義_追加改修.xlsx")
+    if not p.exists():
+        pytest.skip("样本缺失")
+    result = ExcelParser().parse(p)
+    assert result.tables
+    assert any(t.rows for t in result.tables)
+
+
+def test_free_text_sample_detected():
+    p = _x("要件定義_自由記述.xlsx")
+    if not p.exists():
+        pytest.skip("样本缺失")
+    result = ExcelParser().parse(p)
+    assert any(t.extraction_method == "llm_from_free_text" for t in result.tables)