feat: FormattingDetector（取消线/背景色/批注）

src/genesis/parsers/formatting_detector.py

@@ -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