feat: ExcelParser 编排器（类型/性质/提取/汇总）

src/genesis/parsers/excel_parser.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+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.merge_fill import forward_fill
+from genesis.parsers.table_extractor import extract_table
+from genesis.parsers.formatting_detector import collect_comments
+from genesis.parsers.free_text_extractor import build_free_text_table, extract_text_blocks
+
+
+@dataclass
+class ExcelParseResult:
+    file_name: str
+    tables: list[ExcelTable] = field(default_factory=list)
+    comments: list[CellComment] = field(default_factory=list)
+    skipped: list[str] = field(default_factory=list)
+
+
+class ExcelParser:
+    """要件定义 Excel 解析入口。"""
+
+    def parse(self, path: str | Path) -> ExcelParseResult:
+        wb = open_workbook(path)
+        file_name = Path(path).name
+        result = ExcelParseResult(file_name=file_name)
+        for ws in wb.worksheets:
+            matrix = sheet_matrix(ws)
+            if not matrix:
+                result.skipped.append(ws.title)
+                continue
+            detected_type = detect_sheet_type(ws.title, matrix)
+            nature = classify_sheet(matrix)
+            if nature == SheetNature.FREE_TEXT:
+                blocks = extract_text_blocks(matrix)
+                result.tables.append(
+                    build_free_text_table(ws.title, blocks, file_name, detected_type)
+                )
+            else:
+                merged = [
+                    (r.min_row, r.min_col, r.max_row, r.max_col)
+                    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))
+            result.comments.extend(collect_comments(ws, file_name))
+        return result