df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
83 lines
3.2 KiB
Python
83 lines
3.2 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""공주시 전용 규칙 B: F 하나에 G가 여러 개이고 그 G들이 전부 L=페이지면
|
|
→ 1행으로 합치고(G/H/I/J 비움), K=첫 G의 URL, 수량(M)=G들의 M 합.
|
|
G 중 하나라도 페이지가 아니면(게시판/사이트 등) 그 그룹은 합치지 않음.
|
|
|
|
평탄화/재병합/스타일은 _dedup_all 재사용.
|
|
사용: python -X utf8 _gongju_collapse.py [--write]
|
|
"""
|
|
import sys, shutil, importlib.util, warnings
|
|
import openpyxl
|
|
warnings.filterwarnings('ignore')
|
|
|
|
spec = importlib.util.spec_from_file_location('dd', __file__.replace('_gongju_collapse.py', '_dedup_all.py'))
|
|
dd = importlib.util.module_from_spec(spec); spec.loader.exec_module(dd)
|
|
|
|
XLSX = r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\충청남도\2.공주시\충청남도_공주시.xlsx'
|
|
|
|
|
|
def mval(x):
|
|
try:
|
|
return int(x)
|
|
except Exception:
|
|
return 1
|
|
|
|
|
|
def collapse(rows):
|
|
out, groups = [], []
|
|
i, n = 0, len(rows)
|
|
while i < n:
|
|
v = rows[i]['vals']
|
|
D, E, F, G = v.get(4), v.get(5), v.get(6), v.get(7)
|
|
if F not in (None, '') and G not in (None, ''):
|
|
j = i
|
|
while (j < n and rows[j]['vals'].get(4) == D and rows[j]['vals'].get(5) == E
|
|
and rows[j]['vals'].get(6) == F and rows[j]['vals'].get(7) not in (None, '')):
|
|
j += 1
|
|
grp = rows[i:j]
|
|
all_page = all(g['vals'].get(12) == '페이지' for g in grp)
|
|
leaf = all(all(g['vals'].get(c) in (None, '') for c in (8, 9, 10)) for g in grp)
|
|
if len(grp) >= 2 and all_page and leaf:
|
|
msum = sum(mval(g['vals'].get(13)) for g in grp)
|
|
first = dict(grp[0]); nv = dict(first['vals'])
|
|
for c in (7, 8, 9, 10):
|
|
nv[c] = None
|
|
nv[13] = msum
|
|
first['vals'] = nv
|
|
out.append(first)
|
|
groups.append({'D': D, 'E': E, 'F': F, 'n': len(grp),
|
|
'ms': [mval(g['vals'].get(13)) for g in grp],
|
|
'gs': [g['vals'].get(7) for g in grp],
|
|
'sum': msum, 'k': nv.get(11)})
|
|
i = j
|
|
continue
|
|
out.extend(grp); i = j; continue
|
|
out.append(rows[i]); i += 1
|
|
return out, groups
|
|
|
|
|
|
def main():
|
|
write = '--write' in sys.argv
|
|
wb = openpyxl.load_workbook(XLSX)
|
|
ws = wb.active
|
|
rows = dd.load_flat(ws)
|
|
out, groups = collapse(rows)
|
|
removed = len(rows) - len(out)
|
|
print(f'합칠 F그룹: {len(groups)}개 / 제거행 {removed} ({len(rows)}→{len(out)})\n')
|
|
for g in groups:
|
|
ms = '+'.join(str(m) for m in g['ms'])
|
|
print(f" [{g['E']} > {g['F']}] G {g['n']}개({'/'.join(str(x) for x in g['gs'])[:50]})")
|
|
print(f" → 1행, M={ms}={g['sum']}, K={g['k']}")
|
|
if write and groups:
|
|
bak = XLSX.replace('.xlsx', '_backup_collapse전.xlsx')
|
|
shutil.copy(XLSX, bak)
|
|
dd.write_back(ws, out)
|
|
wb.save(XLSX)
|
|
print(f'\n저장 완료. 백업: {bak}')
|
|
elif not write:
|
|
print('\n(DRY — 실제 적용하려면 --write)')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|