feat: FormattingDetector（取消线/背景色/批注）

2026-08-09 03:00:01 +08:00
parent 0051ad52b4
commit 5818dd01e4
3 changed files with 107 additions and 0 deletions
@@ -26,4 +26,5 @@
 | 2026-08-08 | Agent 实现 | 里程碑2 Task2 实现：SheetDetector 类型识别。新建 src/genesis/parsers/sheet_detector.py（名称关键词→表头关键词→GENERIC 三级判定，detect_sheet_type(sheet_name, matrix)->SheetType）与 tests/test_sheet_detector.py（3 用例：名称/表头/未知）；TDD 验证 RED（ModuleNotFoundError）→ GREEN（3 passed）；修正 brief 缺陷：brief 原始 NAME_KEYWORDS 无法匹配「コード管理」判为 MASTER（不含"マスタ"），最小补入 ("コード", MASTER)；pytest 全量 20 passed；提交 66753e4 | src/genesis/parsers/sheet_detector.py, tests/test_sheet_detector.py | deepseek-v4-flash-free |
 | 2026-08-08 | Agent 实现 | 里程碑2 Task3 实现：Sheet 性质判定。新建 src/genesis/parsers/sheet_nature.py（纯函数：SheetNature 枚举 TABLE/FREE_TEXT/MIXED、find_header_row 表头行定位、classify_sheet 按 design §3.5.2 启发式判定）与 tests/test_sheet_nature.py（4 用例）；TDD RED→GREEN；pytest 全量 24 passed | src/genesis/parsers/sheet_nature.py, tests/test_sheet_nature.py | deepseek-v4-flash-free |
 | 2026-08-08 23:04 | Agent 实现 | 里程碑2 Task4 实现：MergeHandler 与 TableExtractor。新建 src/genesis/parsers/merge_fill.py（forward_fill 合并单元格展开，(min_row,min_col,max_row,max_col) 1-based 范围用左上主格值填充，边界保护）与 src/genesis/parsers/table_extractor.py（column_letter 1→A/27→AA；extract_table 首行表头→其后为数据行，构建 CellValue+Provenance(row=r-header_row 从 1 起、column 字母、column_header)，无矩阵时返回空表）及 tests/test_table_extractor.py（4 用例：纵向/横向合并、列字母、基本提取）；TDD 验证 RED（ImportError: No module named 'genesis.parsers.merge_fill'）→ GREEN（4 passed）；pytest 全量 28 passed；data_models.py 未改动；提交 63d0c90 | src/genesis/parsers/merge_fill.py, src/genesis/parsers/table_extractor.py, tests/test_table_extractor.py | deepseek-v4-flash-free |
+| 2026-08-09 02:59 | Agent 实现 | 里程碑2 Task5 实现：FormattingDetector（取消线/背景色/批注）。新建 src/genesis/parsers/formatting_detector.py（cell_formatting 检测 strike/字体色/背景色，纯默认单元格返回 None；cell_comment 返回 CellComment；collect_comments 遍历 ws.iter_rows 收集批注）与 tests/test_formatting_detector.py（4 用例）；TDD 验证 RED（ImportError）→ GREEN（4 passed）；修正 brief 两处 openpyxl 3.1.5 兼容问题（① 字体 Style 对象不可变，测试用 copy 副本设 strike；② 默认 theme 色 .rgb 返回错误文本而非 None，新增 _to_rgb_hex 严格校验仅接受 6/8 位十六进制并排除纯黑）；pytest 全量 32 passed；data_models.py 未改动 | src/genesis/parsers/formatting_detector.py, tests/test_formatting_detector.py | deepseek-v4-flash-free |

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+from genesis.data_models import CellComment, CellFormatting
+from genesis.parsers.provenance import build_source_uri
+
+_BLACK_RGB = ("00000000", "FF000000")
+
+
+def _to_rgb_hex(color) -> str | None:
+    """将 openpyxl Color 转为 RGB 十六进制；非 RGB 主题色/默认色返回 None"""
+    if color is None:
+        return None
+    try:
+        value = str(color.rgb)
+    except Exception:
+        return None
+    if not value or value in _BLACK_RGB:
+        return None
+    if len(value) not in (6, 8):
+        return None
+    if not all(ch in "0123456789ABCDEFabcdef" for ch in value):
+        return None
+    return value
+
+
+def cell_formatting(cell) -> CellFormatting | None:
+    strike = bool(cell.font.strike)
+    font_color = _to_rgb_hex(getattr(cell.font, "color", None))
+    bg_color = None
+    fill = cell.fill
+    if fill is not None:
+        bg_color = _to_rgb_hex(getattr(fill, "fgColor", None))
+    if strike or font_color or bg_color:
+        return CellFormatting(
+            strikethrough=strike, font_color=font_color, bg_color=bg_color,
+        )
+    return None
+
+
+def cell_comment(cell, file_name: str) -> CellComment | None:
+    if cell.comment is None:
+        return None
+    return CellComment(
+        author=cell.comment.author or "",
+        text=cell.comment.text or "",
+        source_uri=build_source_uri(file_name, cell.parent.title, cell.coordinate),
+    )
+
+
+def collect_comments(ws, file_name: str) -> list[CellComment]:
+    result = []
+    for row in ws.iter_rows():
+        for cell in row:
+            cm = cell_comment(cell, file_name)
+            if cm is not None:
+                result.append(cm)
+    return result
@@ -0,0 +1,49 @@
+from copy import copy
+
+from openpyxl import Workbook
+from openpyxl.comments import Comment
+
+from genesis.data_models import CellComment, CellFormatting
+from genesis.parsers.formatting_detector import (
+    cell_comment, cell_formatting, collect_comments,
+)
+
+
+def make_wb():
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "機能一覧"
+    ws["A1"] = "F001"
+    font = copy(ws["A1"].font)
+    font.strike = True
+    ws["A1"].font = font
+    ws["A2"] = "F002"
+    ws["A2"].comment = Comment("要確認", "reviewer")
+    return wb
+
+
+def test_cell_formatting_detects_strike():
+    fmt = cell_formatting(make_wb().active["A1"])
+    assert fmt is not None
+    assert fmt.strikethrough is True
+
+
+def test_cell_formatting_none_when_plain():
+    wb = Workbook()
+    ws = wb.active
+    ws["A1"] = "x"
+    assert cell_formatting(ws["A1"]) is None
+
+
+def test_cell_comment_returns_obj():
+    wb = make_wb()
+    cm = cell_comment(wb.active["A2"], "f.xlsx")
+    assert isinstance(cm, CellComment)
+    assert cm.author == "reviewer"
+    assert cm.text == "要確認"
+    assert cm.source_uri == "f.xlsx#機能一覧!A2"
+
+
+def test_collect_comments():
+    comments = collect_comments(make_wb().active, "f.xlsx")
+    assert len(comments) == 1