gistfile1.txt

#!/usr/bin/env python3.11

import re
import pandas as pd

flags = re.MULTILINE|re.UNICODE|re.IGNORECASE|re.DOTALL

def strip_dot(s):
  return ''.join(s.split('.'))

def norm(s):
  if isinstance(s, str):
    ss = s
  elif isinstance(s, (float, int)):
    ss = str(s)
  else:
    ss = ''

  if ss == 'nan':
    ss = ''

  return strip_dot(' '.join(ss.strip().splitlines())
                  .replace('first', '1') .replace('second', '2')
                  .replace('third', '3') .replace('forth', '4') .replace('fifth', '5')
                  .replace('sixth', '6') .replace('seventh', '7'))

re_u_or_p = re.compile(r'([U|P|P.|U.])[\w|\s]?([0-9])', flags)
re_plan = re.compile(r'(plan)[\s|.]?([0-9])', flags)
re_pu = re.compile(r'(pu)[\w|\s]?([0-9])', flags)
re_xetg = re.compile(r'([0-9])[\s|.].[etg|etg.|et.|etasje]', flags)
re_etgx = re.compile(r'etg[\s|.]?([0-9])', flags)
re_floorx = re.compile(r'flo[o]?r[\s|.]?([0-9])', flags)
re_xfloor = re.compile(r'([0-9])[\s|.]flo[o]?r', flags)

def check_UP(s):
  res = re_u_or_p.findall(s)
  if res:
    return res
  return None

  #  if res and res.group(1):
  #    print(s, res)
  #    return res.group(1)+res.group(2)
  #  return None

def check_plan(s):
  res = re_plan.match(s)
  if res:
    return ['P'+res.group(2)]
  return None

def check_PU(s):
  res = re_pu.match(s)
  if res:
    return ['U'+res.group(2)]
  return None

def check_xetg(s):
  res = re_xetg.match(s)
  if res:
    return ['P'+res.group(1)]
  return None

def check_etgx(s):
  res = re_etgx.match(s)
  if res:
    return ['P'+res.group(1)]
  return None

def tx(r):
  s = norm(r)

  for fx in [ check_PU, check_UP, check_plan, check_etgx, check_xetg]:
    v = fx(s)
    if v is not None:
      return v
  return None

numbers = set('1234567')
warnsym = set('-,')

def tx_mark(r):
  s = norm(r)
  letters = set(s)
  cn = letters.intersection(numbers)
  sn = letters.intersection(warnsym)

  return 'x' if (cn and sn) else ''

def row_itr(df):
  for _, row in df.iterrows():
    new_raw =  tx(row['raw'])
    if new_raw:
      l = list(new_raw)
      n = len(l)
      for s in l:
        tmp = row.copy()
        if isinstance(s, str):
          tmp['raw3'] = s.upper()
          tmp['hrs3'] = row['hrs']

        elif isinstance(s, tuple):
          tmp['raw3'] = f'{s[0]}{s[1]}'.upper()
          tmp['hrs3'] = row['hrs']/n
          tmp['split'] = 's' if len(l)>1 else ''
        yield tmp
    else:
      x = row.copy()
      x['hrs3'] = row['hrs']
      yield x

def main():
  #  fn = "dat3.xlsx"
  fn = "dat-4.xlsx"
  #  fn = "dat-ex.xlsx"
  df = pd.read_excel(fn)
  ins = df.shape

  initial_sum = df['hrs'].sum()
  print(initial_sum)

  #  print(df)
  df2 = pd.DataFrame(list(row_itr(df)))

  final_sum = df2['hrs3'].sum()
  print(final_sum)

  for _, row in df.iterrows():
    print( row['raw'],' | ', norm(row['raw3']))

  print('fn: ', fn , ' in:', ins, 'out:', df2.shape)
  df2.to_excel(f'out-{fn}')


if __name__ == '__main__':
  main()