python黑魔法之编码转换

source -> unicode -> dest

codecs.register_error(name, error_handler)

def cjk_error(e):
  if not isinstance(e, UnicodeDecodeError):
    raise TypeError("don't know how to handle %r" % exc) 
  if exc.end + 1 > len(exc.object): 
    raise TypeError('unknown codec ,the object too short!') 
  ch1 = ord(exc.object[exc.start:exc.end]) 
  newpos = exc.end + 1 
  ch2 = ord(exc.object[exc.start + 1:newpos]) 
  sk = exc.object[exc.start:newpos] 
  if 0x81<=ch1<=0xFE and (0x40<=ch2<=0x7E or 0x7E<=ch2<=0xFE): # GBK 
    return (unicode(sk,'cp936'), newpos) 
  if 0x81<=ch1<=0xFE and (0x40<=ch2<=0x7E or 0xA1<=ch2<=0xFE): # BIG5 
    return (unicode(sk,'big5'), newpos) 
  raise TypeError('unknown codec !') 
codecs.register_error("cjk_replace", cjk_replace) 

a = "你"              # utf8编码：'\xe4\xbd\xa0'
c = unicode(a[:2],'gbk')  # 正常返回
c = unicode(a, 'gbk')    # UnicodeDecodeError 。错误发生在第三个字节

import codec

def cjk_replace(e):
  if not isinstance(e, UnicodeDecodeError):
    raise TypeError("invalid exception type %s" e)

  src = e.encoding
  if src in ('gbk','gb18030', 'big5'):
    beg = e.start - 2
    if beg >= 0:
      try:
        return unicode(e.object[beg:e.end], 'utf8'), e.end + 1
      except:
        pass

  if exc.end + 1 > len(exc.object):
    raise TypeError('unknown codec ,the object too short!')
  ch1 = ord(exc.object[exc.start:exc.end])
  newpos = exc.end + 1
  ch2 = ord(exc.object[exc.start + 1:newpos])
  sk = exc.object[exc.start:newpos]

  if src != 'gbk' and 0x81<=ch1<=0xFE and (0x40<=ch2<=0x7E or 0x7E<=ch2<=0xFE): # GBK
    return (unicode(sk,'cp936'), newpos)
  if src != 'big5' and 0x81<=ch1<=0xFE and (0x40<=ch2<=0x7E or 0xA1<=ch2<=0xFE): # BIG5
    return (unicode(sk,'big5'), newpos)
  raise TypeError('unknown codec !')

codecs.register_error("cjk_replace", cjk_replace)