test: MIXED 混合样本 + 端到端段落验证

tests/test_real_samples.py

@@ -36,4 +36,25 @@ def test_free_text_sample_detected():
     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)
+    assert any(t.extraction_method == "llm_from_free_text" for t in result.tables)
+
+
+def test_mixed_sample_segments_detected():
+    p = _x("要件定義_混合型.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 result.mixed, "混合样本应产出段落"
+    mixed = result.mixed[0]
+    assert len(mixed.paragraphs) == 2          # 表格段 + 碎片段（・/■ 连续）
+    assert [p.kind for p in mixed.paragraphs] == ["table", "free_text"]
+    # 表格段无碎片污染
+    table = [p.table for p in mixed.paragraphs if p.kind == "table"][0]
+    assert table.rows[0]["機能ID"].value == "F101"
+    assert len(table.rows) == 3
+    # 碎片段含 ・ 与 ■ 两行文本
+    ft = [p for p in mixed.paragraphs if p.kind == "free_text"][0]
+    assert "改修ポイント" in (ft.text or "")
+    assert "対象期間" in (ft.text or "")