feat: MergeHandler + TableExtractor（forward_fill / 表格提取）

src/genesis/parsers/merge_fill.py

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+from typing import Any
+
+
+def forward_fill(
+    matrix: list[list[Any]],
+    merged_ranges: list[tuple[int, int, int, int]],
+) -> list[list[Any]]:
+    """合并单元格：用左上角主格值填充范围内全部单元格。"""
+    out = [list(row) for row in matrix]
+    for (min_row, min_col, max_row, max_col) in merged_ranges:
+        if not out or min_row > len(out) or min_col > len(out[min_row - 1]):
+            continue
+        main_value = out[min_row - 1][min_col - 1]
+        for r in range(min_row, min(max_row, len(out)) + 1):
+            row = out[r - 1]
+            for c in range(min_col, min(max_col, len(row)) + 1):
+                row[c - 1] = main_value
+    return out

src/genesis/parsers/table_extractor.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+
+from typing import Any
+
+from genesis.data_models import CellValue, ExcelTable, Provenance, SheetType
+
+
+def column_letter(index: int) -> str:
+    """1 → A、27 → AA。"""
+    letters = ""
+    while index > 0:
+        index, rem = divmod(index - 1, 26)
+        letters = chr(65 + rem) + letters
+    return letters
+
+
+def extract_table(
+    sheet_name: str,
+    matrix: list[list[Any]],
+    file_name: str,
+    detected_type: SheetType,
+    header_row: int = 0,
+) -> ExcelTable:
+    """从矩阵提取表格：首行视为表头，其后为数据行。"""
+    if not matrix:
+        return ExcelTable(
+            name=sheet_name, detected_type=detected_type,
+            extraction_method="openpyxl", headers=[], rows=[],
+        )
+    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)):
+        row_dict = {}
+        for c, h in enumerate(headers):
+            raw = matrix[r][c] if c < len(matrix[r]) else None
+            row_dict[h] = CellValue(
+                value=raw,
+                provenance=Provenance(
+                    file_name=file_name,
+                    sheet_name=sheet_name,
+                    row=r - header_row,   # 数据行号从 1 开始
+                    column=column_letter(c + 1),
+                    column_header=h,
+                ),
+            )
+        rows.append(row_dict)
+    return ExcelTable(
+        name=sheet_name, detected_type=detected_type,
+        extraction_method="openpyxl", headers=headers, rows=rows,
+    )