# -*- coding: utf-8 -*-
import openpyxl, sys
from openpyxl.utils import get_column_letter
sys.stdout.reconfigure(encoding='utf-8')
new=openpyxl.load_workbook('_충청남도_서천군_NEW.xlsx').active
old=openpyxl.load_workbook('충청남도_서천군_backup_탭전개전.xlsx').active
print('=== hyperlink mismatches ===')
for r in range(3,new.max_row+1):
    c=new.cell(r,11); L=new.cell(r,12).value
    if L in ('페이지','게시판','사이트') and c.hyperlink:
        if isinstance(c.value,str) and c.value.strip()!=c.hyperlink.target.strip():
            print(f'  R{r} L={L} val={c.value[:45]} tgt={c.hyperlink.target[:45]}')
# L type counts old vs new
from collections import Counter
def lc(ws):
    return Counter(ws.cell(r,12).value for r in range(3,ws.max_row+1) if ws.cell(r,12).value)
print('OLD L counts:', dict(lc(old)))
print('NEW L counts:', dict(lc(new)))
# 분야별이행기준 group size
for r in range(3,new.max_row+1):
    if new.cell(r,6).value=='분야별이행기준':
        cnt=0
        for k in range(r, r+40):
            if new.cell(k,6).value and k>r and new.cell(k,6).value!='분야별이행기준': break
            if new.cell(k,7).value or new.cell(k,6).value=='분야별이행기준': cnt+=1
        print(f'분야별이행기준 @R{r}, first G={new.cell(r,7).value}, last few:')
        for k in range(r, r+28):
            g=new.cell(k,7).value; f=new.cell(k,6).value
            if f and f!='분야별이행기준' and k>r: break
        # show merge
        fm=[str(m) for m in new.merged_cells.ranges if m.min_col==6 and m.min_row==r]
        print('   F-merge:', fm)
        break
# site row preserved?
print('=== site rows sample (new) ===')
sc=0
for r in range(3,new.max_row+1):
    if new.cell(r,12).value=='사이트':
        sc+=1
        if sc<=3:
            print(f'  R{r} F={new.cell(r,6).value} M={new.cell(r,13).value} N={new.cell(r,14).value} link={new.cell(r,11).hyperlink.target[:40] if new.cell(r,11).hyperlink else None}')
print('site count new:', sc)
# verify total D/E merge integrity: every data row covered by a D value (merge-top or own)
missingD=0
dranges=[m for m in new.merged_cells.ranges if m.min_col==4]
covered=set()
for m in dranges:
    for rr in range(m.min_row,m.max_row+1): covered.add(rr)
for r in range(3,new.max_row+1):
    if new.cell(r,4).value is None and r not in covered:
        missingD+=1
print('rows with no D coverage:', missingD)