sheet-edit 多级表头审计修复(上轮讨论定稿的「立即做」批次):① locate.detect_multi_level 识别「分组行+重复子列名行」相邻形态,inspect 每 sheet 返回 multi_level_header——AI 第一轮即可判型,不再烧两轮试错;build_col_map 重复列名报错、_resolve_change 命中分组行时报错,文案一律直指 change.cells 出口(审计指正:这类表任何 header_row 都无解,此前建议修正 suggest 行号其实救不了,改口径为「检测并拒得明白」)。② apply 新增 cells 地址模式({sheet, cells:{D4:{old,new}}},与 match+set 互斥,允许可选 $)——多级表头从「不支持」降级为「坐标多确认一步」,old 校验/合并区防护/全簿逐格自检/LO 重算与列名模式完全同源,真正封死「terminal 裸改交付物」的危险兜底动机。③ header_row 支持 change 级覆盖(多 sheet 表头位置不一的隐患提前拆掉)。④ SKILL.md:工作流程/返回字段/cells 小节/硬约束加「禁止绕开技能手改」/边界与常见错误同步;清理 MergedCell 死 import。事故同款结构(大标题+合并分组+重复子列)16 项容器实测全过,含 old 校验拒绝无产物、非法地址、per-change 混单、插删链与 CSV 防回归
This commit is contained in:
@@ -32,6 +32,35 @@ def detect_header_row(ws, scan=10, col_cap=200) -> int:
|
||||
return best_row
|
||||
|
||||
|
||||
def detect_multi_level(ws, scan=10, col_cap=200):
|
||||
"""检测“分组行 + 重复子列名行”相邻出现的多级表头形态,返回 (分组行, 列名行) 或 None。
|
||||
|
||||
判定:相邻两行均全为字符串;上行值唯一且 ≥2 个(分组标题),下行有重复且 ≥3 个、格数多于上行
|
||||
(真列名在多组下重复)。只读不写,纯诊断用。"""
|
||||
max_c = min(ws.max_column, col_cap)
|
||||
prev = None # (row, 全字符串, 值列表)
|
||||
for r in range(1, min(scan, ws.max_row) + 1):
|
||||
vals = []
|
||||
ok = True
|
||||
for c in range(1, max_c + 1):
|
||||
v = ws.cell(r, c).value
|
||||
if v is None or v == '':
|
||||
continue
|
||||
if isinstance(v, str) and not v.startswith('='):
|
||||
vals.append(v.strip())
|
||||
else:
|
||||
ok = False
|
||||
break
|
||||
if prev is not None and ok and prev[1] and prev[2]:
|
||||
pu, cu = prev[2], vals
|
||||
if (len(pu) >= 2 and len(set(pu)) == len(pu)
|
||||
and len(cu) >= 3 and len(set(cu)) != len(cu)
|
||||
and len(cu) > len(pu)):
|
||||
return (prev[0], r)
|
||||
prev = (r, ok, vals)
|
||||
return None
|
||||
|
||||
|
||||
def value_eq(a, b) -> bool:
|
||||
if a is None and b is None:
|
||||
return True
|
||||
@@ -57,6 +86,13 @@ def build_col_map(ws, header_row: int) -> dict:
|
||||
if not name:
|
||||
continue
|
||||
if name in col_map:
|
||||
ml = detect_multi_level(ws)
|
||||
if ml:
|
||||
raise UserError(
|
||||
f"表头行 {header_row} 存在重复列名('{name}'),且检测到多级表头"
|
||||
f"(第 {ml[0]} 行分组、第 {ml[1]} 行子列名):列名模式无法唯一定位,"
|
||||
"请从 inspect 的 preview/formulas 确认目标坐标后改用 change.cells 地址模式"
|
||||
)
|
||||
raise UserError(f"表头行 {header_row} 存在重复列名: '{name}'")
|
||||
col_map[name] = c
|
||||
if not col_map:
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
"""sheet-edit 的各个 op 实现。"""
|
||||
import datetime
|
||||
import re
|
||||
import shutil
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import openpyxl
|
||||
from openpyxl.utils import get_column_letter
|
||||
from openpyxl.cell.cell import MergedCell
|
||||
from openpyxl.utils import column_index_from_string, get_column_letter
|
||||
from openpyxl.worksheet.cell_range import CellRange, MultiCellRange
|
||||
from openpyxl.worksheet.formula import ArrayFormula
|
||||
|
||||
@@ -74,6 +74,7 @@ def _sheet_info(ws, name, header_row, limit):
|
||||
'cols': ws.max_column,
|
||||
'header_row': header_row,
|
||||
'suggested_header_row': locate.detect_header_row(ws),
|
||||
'multi_level_header': None,
|
||||
'headers': [
|
||||
_json_safe(ws.cell(header_row, c).value)
|
||||
for c in range(1, ws.max_column + 1)
|
||||
@@ -84,6 +85,9 @@ def _sheet_info(ws, name, header_row, limit):
|
||||
'merged': [str(r) for r in ws.merged_cells.ranges],
|
||||
'truncated': False,
|
||||
}
|
||||
ml = locate.detect_multi_level(ws)
|
||||
if ml:
|
||||
info['multi_level_header'] = {'group_row': ml[0], 'column_row': ml[1]}
|
||||
for row in ws.iter_rows():
|
||||
for cell in row:
|
||||
v = cell.value
|
||||
@@ -173,44 +177,79 @@ def _resolve_change(wb, ch, header_row):
|
||||
raise UserError(
|
||||
f"sheet 不存在: {sheet}(可用: {', '.join(wb.sheetnames)})"
|
||||
)
|
||||
match = ch.get('match') or {}
|
||||
set_spec = ch.get('set') or {}
|
||||
if not isinstance(set_spec, dict) or not set_spec:
|
||||
raise UserError("change.set 必须是非空对象")
|
||||
|
||||
hr = _int(ch, 'header_row', header_row) # change 级可覆盖全局 header_row
|
||||
ws = wb[sheet]
|
||||
col_map = locate.build_col_map(ws, header_row)
|
||||
row = locate.find_row(ws, col_map, match, header_row)
|
||||
|
||||
set_spec = ch.get('set')
|
||||
cells_spec = ch.get('cells')
|
||||
if set_spec is not None and cells_spec is not None:
|
||||
raise UserError("change 只能二选一:match+set(列名定位)或 cells(地址定位)")
|
||||
if cells_spec is not None:
|
||||
return _resolve_cells(ws, sheet, cells_spec)
|
||||
|
||||
match = ch.get('match') or {}
|
||||
if not isinstance(set_spec, dict) or not set_spec:
|
||||
raise UserError("change.set 必须是非空对象(多级表头等无法按列名定位的表改用 change.cells)")
|
||||
|
||||
ml = locate.detect_multi_level(ws)
|
||||
if ml and hr == ml[0]:
|
||||
raise UserError(
|
||||
f"检测到多级表头(第 {ml[0]} 行分组、第 {ml[1]} 行子列名):列名模式无法唯一定位,"
|
||||
"请从 inspect 的 preview/formulas 确认目标坐标后改用 change.cells 地址模式"
|
||||
)
|
||||
col_map = locate.build_col_map(ws, hr)
|
||||
row = locate.find_row(ws, col_map, match, hr)
|
||||
|
||||
items = []
|
||||
for col_name, spec in set_spec.items():
|
||||
if not isinstance(spec, dict) or 'old' not in spec or 'new' not in spec:
|
||||
raise UserError(
|
||||
f"set['{col_name}'] 必须是 {{\"old\": ..., \"new\": ...}} 格式"
|
||||
)
|
||||
col = locate.find_col(col_map, col_name)
|
||||
actual = ws.cell(row, col).value
|
||||
if isinstance(actual, ArrayFormula):
|
||||
raise UserError(
|
||||
f"{sheet}!{get_column_letter(col)}{row} 是数组公式,"
|
||||
"本工具不支持修改(请在 Excel/WPS 手工处理)"
|
||||
)
|
||||
new = spec['new']
|
||||
if isinstance(new, (dict, list)):
|
||||
raise UserError(f"set['{col_name}'].new 只能是数字/字符串/布尔/null,收到 {new!r}")
|
||||
items.append({
|
||||
'sheet': sheet,
|
||||
'row': row,
|
||||
'col': col,
|
||||
'col_name': col_name,
|
||||
'match': dict(match),
|
||||
'expected_old': spec['old'],
|
||||
'actual_old': actual,
|
||||
'new': new,
|
||||
})
|
||||
items.append(_mk_item(ws, sheet, row, col, col_name, spec, dict(match)))
|
||||
return items
|
||||
|
||||
|
||||
_ADDR_RE = re.compile(r'^\$?([A-Za-z]{1,3})\$?(\d{1,7})$')
|
||||
|
||||
|
||||
def _resolve_cells(ws, sheet, cells_spec):
|
||||
"""地址模式:cells = {"C5": {"old": ..., "new": ...}, ...}。多级表头等列名不可用场景的正经出口,
|
||||
old 校验/合并区防护/全簿自检/重算与列名模式完全同源。"""
|
||||
if not isinstance(cells_spec, dict) or not cells_spec:
|
||||
raise UserError("change.cells 必须是非空对象:地址 → {\"old\": ..., \"new\": ...}")
|
||||
items = []
|
||||
for addr, spec in cells_spec.items():
|
||||
m = _ADDR_RE.match(str(addr).strip())
|
||||
if not m:
|
||||
raise UserError(f"非法单元格地址: {addr!r}(形如 C5,允许可选 $ 绝对符)")
|
||||
col = column_index_from_string(m.group(1).upper())
|
||||
row = int(m.group(2))
|
||||
items.append(_mk_item(ws, sheet, row, col, str(addr).strip().upper(), spec, {}))
|
||||
return items
|
||||
|
||||
|
||||
def _mk_item(ws, sheet, row, col, label, spec, match_info):
|
||||
if not isinstance(spec, dict) or 'old' not in spec or 'new' not in spec:
|
||||
raise UserError(f"'{label}' 的设值必须是 {{\"old\": ..., \"new\": ...}} 格式")
|
||||
actual = ws.cell(row, col).value
|
||||
if isinstance(actual, ArrayFormula):
|
||||
raise UserError(
|
||||
f"{sheet}!{get_column_letter(col)}{row} 是数组公式,"
|
||||
"本工具不支持修改(请在 Excel/WPS 手工处理)"
|
||||
)
|
||||
new = spec['new']
|
||||
if isinstance(new, (dict, list)):
|
||||
raise UserError(f"'{label}'.new 只能是数字/字符串/布尔/null,收到 {new!r}")
|
||||
return {
|
||||
'sheet': sheet,
|
||||
'row': row,
|
||||
'col': col,
|
||||
'col_name': label,
|
||||
'match': match_info,
|
||||
'expected_old': spec['old'],
|
||||
'actual_old': actual,
|
||||
'new': new,
|
||||
}
|
||||
|
||||
|
||||
def _verify_apply(out_path, before, plan):
|
||||
with tempfile.TemporaryDirectory() as td:
|
||||
xlsx = convert.to_workbook(out_path, Path(td))
|
||||
|
||||
Reference in New Issue
Block a user