unicode_chars

   1 #!/usr/bin/env python3
   2 # The MIT License (MIT)
   3 #
   4 # Copyright (c) 2011-2015 Ismaël Bouya http://www.normalesup.org/~bouya/
   5 #
   6 # Permission is hereby granted, free of charge, to any person obtaining a copy
   7 # of this software and associated documentation files (the "Software"), to deal
   8 # in the Software without restriction, including without limitation the rights
   9 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  10 # copies of the Software, and to permit persons to whom the Software is
  11 # furnished to do so, subject to the following conditions:
  12 #
  13 # The above copyright notice and this permission notice shall be included in
  14 # all copies or substantial portions of the Software.
  15 #
  16 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  17 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  18 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  19 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  20 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  21 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  22 # THE SOFTWARE.
  23
  24 import sys
  25 import unicodedata
  26
  27 string = sys.stdin.readline().strip()
  28 for char in string:
  29   print("U+%04x" % ord(char), end="")
  30   if (ord(char) < 31):
  31     print()
  32   else:
  33     print(" " + char + " ", end="")
  34     try:
  35       print(unicodedata.name(char), "["+unicodedata.category(char)+"]")
  36       decomposition = unicodedata.decomposition(char).split(" ")
  37       if len(decomposition) > 1:
  38         for subchar in decomposition:
  39           try:
  40             unicode_char = chr(int(subchar, 16))
  41             print("           U+%s" % subchar, unicodedata.name(unicode_char))
  42           except ValueError:
  43             print("           " + subchar)
  44     except:
  45       pass