DB_JOB/_스크립트/_collapse_all.py
hehihoho3 df16c98366 백업: DB수집 전체 스냅샷 (공공기관2 정리 전)
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 18:15:40 +09:00

128 lines
5.2 KiB
Python

# -*- coding: utf-8 -*-
"""규칙 B 전 사이트 적용: F 하나에 G가 여러 개이고 그 G들이 전부 L=페이지면
→ 1행으로 합치고(G/H/I/J 비움), K=첫 G URL, 수량(M)=G들의 M 합. (공주시와 동일)
안전장치:
· G 중 하나라도 페이지가 아니면(게시판/사이트) 합치지 않음.
· 합칠 때 공공누리: O유형=그룹 합집합(숫자 오름차순,콤마,공백없음), Q=하나라도 Y면 Y,
P=게시판 우선(없으면 게시물). 부착 정보 손실 방지하며 합침.
· G가 잎일 때만(H/I/J 비어있음). 더 깊은 중첩은 건드리지 않음.
공주시(완료)·계룡시(검수완료)는 제외.
사용: python -X utf8 _collapse_all.py dry [기관...]
python -X utf8 _collapse_all.py run [기관...]
"""
import os, re, sys, shutil, importlib.util, warnings
import openpyxl
warnings.filterwarnings('ignore')
TYPE_PAT = re.compile(r'(\d)\s*유형')
def merge_kogl(grp):
"""그룹 G행들의 O/P/Q 통합. 반환 (O, P, Q)."""
types = set()
for g in grp:
o = g['vals'].get(15)
if isinstance(o, str):
for m in TYPE_PAT.finditer(o):
types.add(int(m.group(1)))
if types:
O = ','.join(f'{n}유형' for n in sorted(types))
else:
O = '미부착'
Ps = [g['vals'].get(16) for g in grp]
P = '게시판' if '게시판' in Ps else ('게시물' if '게시물' in Ps else None)
Qs = [g['vals'].get(17) for g in grp]
Q = 'Y' if 'Y' in Qs else ('N' if 'N' in Qs else None)
return O, (P if O != '미부착' else None), (Q if O != '미부착' else None)
spec = importlib.util.spec_from_file_location('dd', __file__.replace('_collapse_all.py', '_dedup_all.py'))
dd = importlib.util.module_from_spec(spec); spec.loader.exec_module(dd)
EXCLUDE = {'공주시', '계룡시'}
def mval(x):
try:
return int(x)
except Exception:
return 1
def collapse(rows):
out, groups, held = [], [], []
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)
has_attach = any(g['vals'].get(15) not in (None, '', '미부착') for g in grp)
if len(grp) >= 2 and all_page and leaf:
msum = sum(mval(g['vals'].get(13)) for g in grp)
O, P, Q = merge_kogl(grp)
first = dict(grp[0]); nv = dict(first['vals'])
for c in (7, 8, 9, 10):
nv[c] = None
nv[13] = msum
nv[15] = O; nv[16] = P; nv[17] = Q
first['vals'] = nv
out.append(first)
groups.append({'E': E, 'F': F, 'n': len(grp), 'sum': msum, 'O': O})
if has_attach:
held.append({'E': E, 'F': F, 'O': O})
i = j
continue
out.extend(grp); i = j; continue
out.append(rows[i]); i += 1
return out, groups, held
def main():
mode = sys.argv[1] if len(sys.argv) > 1 else 'dry'
only = set(a for a in sys.argv[2:] if not a.startswith('--'))
sites = [s for s in dd.SITES if s[2] not in EXCLUDE and (not only or s[2] in only)]
print(f'대상 기관: {len(sites)}개 (공주·계룡 제외) 모드={mode}\n')
print(f'{"기관":<8}{"현재":>6}{"합친그룹":>7}{"제거행":>6}{"→남음":>7}{"부착합침":>7}')
print('-' * 55)
grand_g = grand_r = grand_h = 0
attach_detail = []
for prov, idx, name in sites:
xp = dd.xpath(prov, idx, name)
if not os.path.exists(xp):
print(f'{name:<8} 엑셀 없음'); continue
wb = openpyxl.load_workbook(xp); ws = wb.active
rows = dd.load_flat(ws)
out, groups, held = collapse(rows)
removed = len(rows) - len(out)
grand_g += len(groups); grand_r += removed; grand_h += len(held)
print(f'{name:<8}{len(rows):>6}{len(groups):>7}{removed:>6}{len(out):>7}{len(held):>7}')
for h in held:
attach_detail.append((name, h['E'], h['F'], h['O']))
if mode == 'run' and groups:
bak = xp.replace('.xlsx', '_backup_collapse전.xlsx')
shutil.copy(xp, bak)
dd.write_back(ws, out)
try:
wb.save(xp)
except PermissionError:
wb.save(xp.replace('.xlsx', '_LP.xlsx')); print(f' !! {name} 잠김→_LP')
print('-' * 55)
print(f'합계: 합친그룹 {grand_g} / 제거행 {grand_r} / 부착합침 {grand_h} ({mode})')
if attach_detail:
print(f'\n=== 부착 유형 합쳐진 그룹 {len(attach_detail)}개 (O 결과 확인용) ===')
for nm, E, F, O in attach_detail:
print(f' [{nm}] {E} > {F} → O={O}')
if __name__ == '__main__':
main()