feat: MIXED 完整段落解析（分割→每段最优解析）

2026-08-09 04:07:07 +08:00
parent 539945be67
commit 1e3f702477
3 changed files with 106 additions and 2 deletions
@@ -34,3 +34,4 @@
 | 2026-08-09 03:30 | 整体迭代 | 里程碑2 最终评审修正（must-fix x2）：① find_header_row 结果未传入 extract_table（恒 header_row=0，标题行置上的 sheet 会损坏表头）→ excel_parser.py 结构化路径改用 find_header_row(filled) 并 <0 回落 0；② cell_formatting 死代码（CellValue.formatting 恒 None，取消线/背景色到不了下游）→ extract_table 新增可选 formatting_map 参数，excel_parser 遍历 ws.iter_rows 构建 fmt_map 传入。tests/test_excel_parser.py 新增 2 用例（标题行表头定位、strikethrough 回填）；pytest 全量 41 passed | src/genesis/parsers/excel_parser.py, src/genesis/parsers/table_extractor.py, tests/test_excel_parser.py | deepseek-v4-flash-free |
 | 2026-08-09 03:59 | Agent 实现 | 里程碑2.5 Task9 实现：段落分割器 split_paragraphs（MIXED 完整段落解析第一步，纯函数）。新建 src/genesis/parsers/paragraph_splitter.py（_is_blank_row 行空白判定 + split_paragraphs(matrix)→list[(start,end)] 含端点 0-based，以全空行为界返回段落区间，空矩阵→[]）与 tests/test_paragraph_splitter.py（5 用例：空矩阵/单段落无空行/中间空行分割/尾部空行不产生多余段落/前导空行从首个非空行开始）；TDD 验证 RED（ModuleNotFoundError: No module named 'genesis.parsers.paragraph_splitter'）→ GREEN（5 passed）；pytest 全量 46 passed（41 baseline + 5 新增）；不依赖 openpyxl 与 data_models；提交 34ef28b | src/genesis/parsers/paragraph_splitter.py, tests/test_paragraph_splitter.py | deepseek-v4-flash-free |
 | 2026-08-09 04:20 | Agent 实现 | 里程碑2.5 Task10 实现：data_models 扩展 MixedParagraph/MixedSheet 段落容器，并新增 ExcelParseResult.mixed 字段（默认空列表）。TDD：先追加 3 个测试（字段存在性与默认行为）确认 RED（ImportError: cannot import name 'MixedParagraph'），再在 data_models.py 末尾追加两个 dataclass（顶部 from typing 加 Literal、dataclasses 加 field），excel_parser.py 更新导入并为 ExcelParseResult 加 mixed 字段，确认 GREEN（3 passed），全量 pytest 49 passed（46 baseline + 3）。未修改既有类与字段，仅追加。 | src/genesis/data_models.py, src/genesis/parsers/excel_parser.py, tests/test_excel_parser.py | deepseek-v4-flash-free |
+| 2026-08-09 04:06 | Agent 实现 | 里程碑2.5 Task11 实现：MIXED 完整段落装配（分割→逐段最优解析）。excel_parser.py 新增 MIXED 分支：整表先 forward_fill（合并单元格）再按段切片；对每段 classify_sheet，TABLE 段用 find_header_row(seg)（段内相对，<0 回落 0）并抽出段内子 map seg_fmt_map（物理行 pr→段内 pr-s，修复 formatting_map 坐标错位）传给 extract_table（header_row=header_row）；非表格段归 FREE_TEXT（防二次 MIXED 递归），走 extract_text_blocks + build_free_text_table 构造 kind="free_text"。MixedParagraph 段落追加到 MixedSheet 并进 result.mixed，表/自由文本表进 result.tables。原 else 分支保留为 TABLE 专用，既有 TABLE/FREE_TEXT 路径不变。TDD：先追加 2 测试（段落分割/碎片捕获、表格段不在物理行 0 时的取消线回填）确认 RED（result.mixed 空 + IndexError），再实现确认 GREEN（9 passed），全量 pytest 51 passed（49 baseline + 2）。提交见 git log | src/genesis/parsers/excel_parser.py, tests/test_excel_parser.py | deepseek-v4-flash-free |
@@ -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
@@ -81,3 +81,58 @@ def test_mixed_sheet_holds_paragraphs():
    ms = MixedSheet(name="混合", paragraphs=[p1, p2])
    assert ms.name == "混合"
    assert [p.kind for p in ms.paragraphs] == ["table", "free_text"]
+
+
+def test_parse_mixed_sheet_segmented(tmp_path):
+    wb = new_workbook({
+        "混合": [
+            ["機能ID", "機能名"],
+            ["F101", "社員登録"],
+            ["F102", "退職処理"],
+            [],
+            ["・改修ポイント：F102 追加バリデーション"],
+            ["■対象画面：SC001"],
+        ],
+    })
+    path = save_workbook(tmp_path, wb)
+    result = ExcelParser().parse(path)
+    assert result.mixed, "混合 sheet 应产产出 mixed 段落"
+    ms = result.mixed[0]
+    assert ms.name == "混合"
+    kinds = [p.kind for p in ms.paragraphs]
+    assert "table" in kinds and "free_text" in kinds
+    # 表格段无碎片污染：table 段应含 2 数据行，机能ID 首行为 F101
+    tbl = [p.table for p in ms.paragraphs if p.kind == "table"][0]
+    assert tbl is not None and len(tbl.rows) == 2
+    assert tbl.rows[0]["機能ID"].value == "F101"
+    # 自由文本段捕获碎片
+    ft = [p for p in ms.paragraphs if p.kind == "free_text"][0]
+    assert "改修ポイント" in (ft.text or "")
+
+
+def test_parse_mixed_sheet_formatting_in_mid_segment(tmp_path):
+    # 表格段不在物理行 0（自由文本段在前），数据行 F101 设取消线 —— 锁住 formatting_map 坐标错位
+    from copy import copy
+    from openpyxl import Workbook
+    wb = Workbook()
+    ws = wb.active
+    ws.title = "混合"
+    data = [
+        ["■はじめに"], ["前提説明"], [],
+        ["機能ID", "機能名"], ["F101", "社員登録"], ["F102", "退職処理"],
+        [], ["・改修ポイント"],
+    ]
+    for r, row in enumerate(data, start=1):
+        for c, v in enumerate(row, start=1):
+            if v:
+                ws.cell(row=r, column=c, value=v)
+    font = copy(ws.cell(row=5, column=1).font)  # F101 所在物理行（第 5 行）
+    font.strike = True
+    ws.cell(row=5, column=1).font = font
+    path = save_workbook(tmp_path, wb)
+    result = ExcelParser().parse(path)
+    ms = result.mixed[0]
+    tbl = [p.table for p in ms.paragraphs if p.kind == "table"][0]
+    cv = tbl.rows[0]["機能ID"]  # F101
+    assert cv.formatting is not None
+    assert cv.formatting.strikethrough is True