feat: Sheet 性质判定（table/free_text/mixed）

src/genesis/parsers/sheet_nature.py

@@ -0,0 +1,44 @@
+from __future__ import annotations
+
+from enum import Enum
+from typing import Any
+
+
+class SheetNature(Enum):
+    TABLE = "table"
+    FREE_TEXT = "free_text"
+    MIXED = "mixed"
+
+
+def _non_empty(row: list[Any]) -> list[Any]:
+    return [c for c in row if c is not None and str(c).strip() != ""]
+
+
+def find_header_row(matrix: list[list[Any]]) -> int:
+    for i, row in enumerate(matrix):
+        if len(_non_empty(row)) >= 2:
+            return i
+    return -1
+
+
+def _free_text_like(matrix: list[list[Any]]) -> bool:
+    if not matrix:
+        return True
+    max_cols = max((len(row) for row in matrix), default=0)
+    if max_cols <= 1:
+        return True
+    non_empty_rows = [r for r in matrix if _non_empty(r)]
+    if len(non_empty_rows) / len(matrix) < 0.7:
+        return True
+    return find_header_row(matrix) == -1
+
+
+def classify_sheet(matrix: list[list[Any]]) -> SheetNature:
+    if _free_text_like(matrix):
+        return SheetNature.FREE_TEXT
+    header_row = find_header_row(matrix)
+    if header_row >= 0:
+        for row in matrix[header_row + 1:]:
+            if any(str(c).strip().startswith(("・", "■")) for c in _non_empty(row)):
+                return SheetNature.MIXED
+    return SheetNature.TABLE