1 #!/usr/bin/python
   2 # -*- coding: UTF-8 -*-
   3 
   4 TestString = "ä ö ü ß Ä Ö Ü"
   5 print TestString
   6 print TestString.encode("String_Escape"
ERROR: EOF in multi-line statement

   1 def testcodec( txt, destination="utf_8" ):
   2     "Testet blind alle Codecs mit encode und decode"
   3 
   4     codecs = ['ascii', 'big5', 'big5hkscs', 'cp037', 'cp424', 'cp437', 'cp500',
   5         'cp737', 'cp775', 'cp850', 'cp852', 'cp855', 'cp856', 'cp857', 'cp860',
   6         'cp861', 'cp862', 'cp863', 'cp864', 'cp865', 'cp866', 'cp869', 'cp874',
   7         'cp875', 'cp932', 'cp949', 'cp950', 'cp1006', 'cp1026', 'cp1140', 'cp1250',
   8         'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255', 'cp1256', 'cp1257', 'cp1258',
   9         'euc_jp', 'euc_jis_2004', 'euc_jisx0213', 'euc_kr', 'gb2312', 'gbk', 'gb18030',
  10         'hz', 'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004',
  11         'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr', 'latin_1', 'iso8859_2',
  12         'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6', 'iso8859_7', 'iso8859_8',
  13         'iso8859_9', 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15', 'johab',
  14         'koi8_r', 'koi8_u', 'mac_cyrillic', 'mac_greek', 'mac_iceland', 'mac_latin2',
  15         'mac_roman', 'mac_turkish', 'ptcp154', 'shift_jis', 'shift_jis_2004',
  16         'shift_jisx0213', 'utf_16', 'utf_16_be', 'utf_16_le', 'utf_7', 'utf_8',
  17         'idna', 'mbcs', 'palmos',
  18         'raw_unicode_escape', 'rot_13', 'string_escape',
  19         'undefined', 'unicode_escape', 'unicode_internal'
  20     ]
  21     #~ codecs += [
  22         #~ 'base64_codec',
  23         #~ 'bz2_codec',
  24         #~ 'hex_codec',
  25         #~ 'punycode',
  26         #~ 'quopri_codec',
  27         #~ 'zlib_codec',
  28         #~ 'uu_codec'
  29     #~ ]
  30     for codec in codecs:
  31         try:
  32             print txt.decode( codec ).encode( destination ), " - codec:", codec
  33         except:
  34             pass
  35     print "-"*80
  36 
  37 testcodec( "Ein ue...: ü" )
  38 testcodec( "latin-1..: \xfc" )
  39 testcodec( "UTF8.....: \xc3\xbc" )