bruteforce mojibake decoder

try.py

# as of python 3.9
all_encodings = ['ascii', 'big5', 'big5hkscs', 'cp037', 'cp273', 'cp424', 'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850', 'cp852', 'cp855', 'cp856', 'cp857', 'cp858', 'cp860', 'cp861', 'cp862', 'cp863', 'cp864', 'cp865', 'cp866', 'cp869', 'cp874', 'cp875', 'cp932', 'cp949', 'cp950', 'cp1006', 'cp1026', 'cp1125', 'cp1140', 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', 'cp1256', 'cp1257', 'cp1258', 'euc_jp', 'euc_jis_2004', 'euc_jisx0213', 'euc_kr', 'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr', 'latin_1', 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6', 'iso8859_7', 'iso8859_8', 'iso8859_9', 'iso8859_10', 'iso8859_11', 'iso8859_13', 'iso8859_14', 'iso8859_15', 'iso8859_16', 'johab', 'koi8_r', 'koi8_t', 'koi8_u', 'kz1048', 'mac_cyrillic', 'mac_greek', 'mac_iceland', 'mac_latin2', 'mac_roman', 'mac_turkish', 'ptcp154', 'shift_jis', 'shift_jis_2004', 'shift_jisx0213', 'utf_32', 'utf_32_be', 'utf_32_le', 'utf_16', 'utf_16_be', 'utf_16_le', 'utf_7', 'utf_8', 'utf_8_sig']

start = 'åÊ'

def insert(d, k, set_elem):
  if k in d:
    d[k].add(set_elem)
  else:
    d[k] = {set_elem}

stage1_encodings = dict()
stage2_encodings = dict()
stage3_encodings = dict()
stage4_encodings = set()

for encoding1 in all_encodings:
  try:
    stage1 = start.encode(encoding1)
  except:
    continue
  insert(stage1_encodings, stage1, encoding1)

  for encoding2 in all_encodings:
    try:
      stage2 = stage1.decode(encoding2)
    except:
      continue
    insert(stage2_encodings, (stage1, stage2), encoding2)

    for encoding3 in all_encodings:
      try:
        stage3 = stage2.encode(encoding3)
      except:
        continue
      insert(stage3_encodings, (stage2, stage3), encoding3)

      try:
        stage4 = stage3.decode('utf-8')
      except:
        continue
      if len(stage4) != 1:
        continue
      stage4_encodings.add((stage3, stage4))

for stage3, result in stage4_encodings:
  print(f"{result!r}")
  print(f"|- UTF-8")
  print(f" |- {stage3!r}")
  for stage2_3, encoding3 in stage3_encodings.items():
    if stage2_3[1] == stage3:
      stage2 = stage2_3[0]
      print(f"  |- {', '.join(encoding3)}")
      print(f"   |- {stage2!r}")
      for stage1_2, encoding2 in stage2_encodings.items():
        if stage1_2[1] == stage2:
          stage1 = stage1_2[0]
          print(f"    |- {', '.join(encoding2)}")
          print(f"     |- {stage1!r}")
          encoding1 = stage1_encodings[stage1]
          print(f"      |- {', '.join(encoding1)}")
          print(f"       |- {start!r}")