fix: 里程碑2 最终评审 must-fix（header_row 接线 + formatting 回填）

_AI_USAGE_LOG.md

@@ -31,3 +31,4 @@
 | 2026-08-09 03:13 | Agent 实现 | 里程碑2 Task7 实现：ExcelParser 编排器（集成全部解析模块）。创建 src/genesis/parsers/excel_parser.py（ExcelParseResult dataclass：file_name/tables/comments/skipped；ExcelParser.parse 编排：open_workbook→逐 sheet sheet_matrix→空则跳过→detect_sheet_type→classify_sheet→FREE_TEXT 走 extract_text_blocks+build_free_text_table（带 detected_type）→否则 merged ranges 转 tuple 后 forward_fill+extract_table→collect_comments 汇总）与 tests/test_excel_parser.py（2 个用例：表型 sheet 两个（機能一覧 FUNCTION / バッチ一覧 BATCH 类型+行数断言）、自由记述 sheet extraction_method="llm_from_free_text"）；TDD 验证 RED（ImportError: No module named 'genesis.parsers.excel_parser'）→ GREEN（2 passed）；pytest 全量 36 passed；data_models.py 未改动；对照 dispatch 上下文说明：data_models 无 ParsedWorkbook 命名，按 brief 定义 ExcelParseResult | src/genesis/parsers/excel_parser.py, tests/test_excel_parser.py | deepseek-v4-flash-free |
 | 2026-08-09 03:20 | 测试验证 | 里程碑2 Task8 实现：真实样本集成测试。创建 tests/test_real_samples.py（3 个端到端用例，各样本缺失时 pytest.skip：新規開発→機能一覧 存在且 int rows+DB定義；追加改修→tables 非空且至少一表有数据行；自由記述→存在 extraction_method="llm_from_free_text" 的表）；全量验证 39 passed（含 3 个样本用例）；真实样本产物： 新規開発 6 表全 openpyxl（機能一覧9/画面一覧7/帳票一覧5/DB定義20/IF定義3/バッチ一覧3）； 追加改修 2 表 openpyxl（機能10/画面7）+ 改修ポイント 以 FREE_TEXT 分类改 1 行（MIXED 折叠落观察已确认）； 自由記述 3 表全 llm_from_free_text 各 1 行； 3 样本均 0 批注、无空 sheet。调研结论：MIXED 已知缺口#1 在真实样本未触发断言失败（无断言触发），按 brief 保持弱断言 | tests/test_real_samples.py | deepseek-v4-flash-free |
 
+| 2026-08-09 03:30 | 整体迭代 | 里程碑2 最终评审修正（must-fix x2）：① find_header_row 结果未传入 extract_table（恒 header_row=0，标题行置上的 sheet 会损坏表头）→ excel_parser.py 结构化路径改用 find_header_row(filled) 并 <0 回落 0；② cell_formatting 死代码（CellValue.formatting 恒 None，取消线/背景色到不了下游）→ extract_table 新增可选 formatting_map 参数，excel_parser 遍历 ws.iter_rows 构建 fmt_map 传入。tests/test_excel_parser.py 新增 2 用例（标题行表头定位、strikethrough 回填）；pytest 全量 41 passed | src/genesis/parsers/excel_parser.py, src/genesis/parsers/table_extractor.py, tests/test_excel_parser.py | deepseek-v4-flash-free |

src/genesis/parsers/excel_parser.py

@@ -6,10 +6,10 @@ from pathlib import Path
 from genesis.data_models import CellComment, ExcelTable
 from genesis.parsers.excel_reader import open_workbook, sheet_matrix
 from genesis.parsers.sheet_detector import detect_sheet_type
-from genesis.parsers.sheet_nature import SheetNature, classify_sheet
+from genesis.parsers.sheet_nature import SheetNature, classify_sheet, find_header_row
 from genesis.parsers.merge_fill import forward_fill
 from genesis.parsers.table_extractor import extract_table
-from genesis.parsers.formatting_detector import collect_comments
+from genesis.parsers.formatting_detector import cell_formatting, collect_comments
 from genesis.parsers.free_text_extractor import build_free_text_table, extract_text_blocks
 
 
@@ -46,6 +46,20 @@ class ExcelParser:
                     for r in ws.merged_cells.ranges
                 ]
                 filled = forward_fill(matrix, merged) if merged else matrix
-                result.tables.append(extract_table(ws.title, filled, file_name, detected_type))
+                header_row = find_header_row(filled)
+                if header_row < 0:
+                    header_row = 0
+                fmt_map = {}
+                for row in ws.iter_rows():
+                    for cell in row:
+                        fmt = cell_formatting(cell)
+                        if fmt is not None:
+                            fmt_map[(cell.row - 1, cell.column - 1)] = fmt
+                result.tables.append(
+                    extract_table(
+                        ws.title, filled, file_name, detected_type,
+                        header_row=header_row, formatting_map=fmt_map,
+                    )
+                )
             result.comments.extend(collect_comments(ws, file_name))
         return result

src/genesis/parsers/table_extractor.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import Any
 
-from genesis.data_models import CellValue, ExcelTable, Provenance, SheetType
+from genesis.data_models import CellFormatting, CellValue, ExcelTable, Provenance, SheetType
 
 
 def column_letter(index: int) -> str:
@@ -20,13 +20,18 @@ def extract_table(
     file_name: str,
     detected_type: SheetType,
     header_row: int = 0,
+    formatting_map: dict[tuple[int, int], CellFormatting] | None = None,
 ) -> ExcelTable:
-    """从矩阵提取表格：首行视为表头，其后为数据行。"""
+    """从矩阵提取表格：首行视为表头，其后为数据行。
+
+    formatting_map：矩阵坐标 (row, col)（0 起）→ CellFormatting，用于还原取消线/背景色等样式。
+    """
     if not matrix:
         return ExcelTable(
             name=sheet_name, detected_type=detected_type,
             extraction_method="openpyxl", headers=[], rows=[],
         )
+    fmt_map = formatting_map or {}
     headers = [str(c) if c is not None else "" for c in matrix[header_row]]
     rows = []
     for r in range(header_row + 1, len(matrix)):
@@ -42,6 +47,7 @@ def extract_table(
                     column=column_letter(c + 1),
                     column_header=h,
                 ),
+                formatting=fmt_map.get((r, c)),
             )
         rows.append(row_dict)
     return ExcelTable(

tests/test_excel_parser.py

@@ -24,3 +24,36 @@ def test_parse_free_text_sheet(tmp_path):
     result = ExcelParser().parse(path)
     assert len(result.tables) == 1
     assert result.tables[0].extraction_method == "llm_from_free_text"
+
+
+def test_parse_uses_detected_header_row(tmp_path):
+    # 标题行（单格）在首行，真实表头在第二行
+    wb = new_workbook({
+        "機能一覧": [["機能一覧"], ["機能ID", "機能名"], ["A001", "社員登録"]],
+    })
+    path = save_workbook(tmp_path, wb)
+    result = ExcelParser().parse(path)
+    t = result.tables[0]
+    assert t.headers == ["機能ID", "機能名"]
+    assert len(t.rows) == 1
+    assert t.rows[0]["機能ID"].value == "A001"
+
+
+def test_parse_attaches_strikethrough_formatting(tmp_path):
+    from copy import copy
+    from openpyxl import Workbook
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "機能一覧"
+    ws["A1"] = "機能ID"
+    ws["B1"] = "機能名"
+    ws["A2"] = "A001"
+    ws["B2"] = "社員登録"
+    font = copy(ws["A2"].font)
+    font.strike = True
+    ws["A2"].font = font
+    path = save_workbook(tmp_path, wb)
+    result = ExcelParser().parse(path)
+    cv = result.tables[0].rows[0]["機能ID"]
+    assert cv.formatting is not None
+    assert cv.formatting.strikethrough is True