feat: MIXED 完整段落解析（分割→每段最优解析）

src/genesis/parsers/excel_parser.py

@@ -3,11 +3,12 @@ from __future__ import annotations
 from dataclasses import dataclass, field
 from pathlib import Path
 
-from genesis.data_models import CellComment, ExcelTable, MixedSheet
+from genesis.data_models import CellComment, ExcelTable, MixedParagraph, MixedSheet
 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, find_header_row
 from genesis.parsers.merge_fill import forward_fill
+from genesis.parsers.paragraph_splitter import split_paragraphs
 from genesis.parsers.table_extractor import extract_table
 from genesis.parsers.formatting_detector import cell_formatting, collect_comments
 from genesis.parsers.free_text_extractor import build_free_text_table, extract_text_blocks
@@ -36,12 +37,59 @@ class ExcelParser:
                 continue
             detected_type = detect_sheet_type(ws.title, matrix)
             nature = classify_sheet(matrix)
-            if nature == SheetNature.FREE_TEXT:
+            if nature == SheetNature.MIXED:
+                # 合并单元格：整 sheet 先填充再按段切片
+                merged = [
+                    (r.min_row, r.min_col, r.max_row, r.max_col)
+                    for r in ws.merged_cells.ranges
+                ]
+                filled_all = forward_fill(matrix, merged) if merged else matrix
+                # 整 sheet 构建格式映射一次（按物理坐标）
+                fmt_map = {}
+                for row in ws.iter_rows():
+                    for cell in row:
+                        fmt = cell_formatting(cell)
+                        if fmt is not None:
+                            fmt_map[(cell.row - 1, cell.column - 1)] = fmt
+                mixed_sheet = MixedSheet(name=ws.title)
+                for (s, e) in split_paragraphs(matrix):
+                    seg = filled_all[s:e + 1]
+                    seg_nature = classify_sheet(seg)
+                    if seg_nature == SheetNature.TABLE:
+                        header_row = find_header_row(seg)
+                        if header_row < 0:
+                            header_row = 0
+                        # extract_table 的 formatting_map 用段内矩阵坐标 (r,c)；
+                        # 从整 sheet 物理 map 抽出段内子 map（物理行 pr → 段内 pr-s）
+                        seg_fmt_map = {}
+                        for (pr, pc), fmt in fmt_map.items():
+                            if s <= pr <= e:
+                                seg_fmt_map[(pr - s, pc)] = fmt
+                        table = extract_table(
+                            ws.title, seg, file_name, detected_type,
+                            header_row=header_row, formatting_map=seg_fmt_map,
+                        )
+                        result.tables.append(table)
+                        mixed_sheet.paragraphs.append(MixedParagraph(
+                            kind="table", matrix=seg, table=table,
+                            source_range=(s, e),
+                        ))
+                    else:
+                        blocks = extract_text_blocks(seg)
+                        table = build_free_text_table(ws.title, blocks, file_name, detected_type)
+                        result.tables.append(table)
+                        mixed_sheet.paragraphs.append(MixedParagraph(
+                            kind="free_text", matrix=seg,
+                            text="\n".join(blocks), source_range=(s, e),
+                        ))
+                result.mixed.append(mixed_sheet)
+            elif nature == SheetNature.FREE_TEXT:
                 blocks = extract_text_blocks(matrix)
                 result.tables.append(
                     build_free_text_table(ws.title, blocks, file_name, detected_type)
                 )
             else:
+                # 现有 TABLE 路径（MIXED 已独立，不折叠至此）
                 merged = [
                     (r.min_row, r.min_col, r.max_row, r.max_col)
                     for r in ws.merged_cells.ranges