contrib/unicode/utf8-dump.py

   1 #!/usr/bin/env python3
   2 #
   3 # Script to dump a UTF-8 file as a list of numbered lines (mimicking GCC's
   4 # diagnostic output format), interleaved with lines per character showing
   5 # the Unicode codepoints, the UTF-8 encoding bytes, the name of the
   6 # character, and, where printable, the characters themselves.
   7 # The lines are printed in logical order, which may help the reader to grok
   8 # the relationship between visual and logical ordering in bi-di files.
   9 #
  10 # SPDX-License-Identifier: MIT
  11 #
  12 # Copyright (C) 2021 David Malcolm <dmalcolm@redhat.com>.
  13 #
  14 # Permission is hereby granted, free of charge, to any person obtaining a
  15 # copy of this software and associated documentation files (the "Software"),
  16 # to deal in the Software without restriction, including without limitation
  17 # the rights to use, copy, modify, merge, publish, distribute, sublicense,
  18 # and/or sell copies of the Software, and to permit persons to whom the
  19 # Software is furnished to do so, subject to the following conditions:
  20 #
  21 # The above copyright notice and this permission notice shall be included
  22 # in all copies or substantial portions of the Software.
  23 #
  24 # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
  25 # OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  26 # MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
  27 # IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
  28 # CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT
  29 # OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE
  30 # OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  31
  32 import sys
  33 import unicodedata
  34
  35
  36 def get_name(ch):
  37     try:
  38         return unicodedata.name(ch)
  39     except ValueError:
  40         if ch == '\n':
  41             return 'LINE FEED (LF)'
  42         return '(unknown)'
  43
  44
  45 def get_printable(ch):
  46     cat = unicodedata.category(ch)
  47     if cat == 'Cc':
  48         return '(control character)'
  49     elif cat == 'Cf':
  50         return '(format control)'
  51     elif cat[0] == 'Z':
  52         return '(separator)'
  53     return ch
  54
  55
  56 def dump_file(f_in):
  57     line_num = 1
  58     for line in f_in:
  59         print('%4i | %s' % (line_num, line.rstrip()))
  60         for ch in line:
  61             utf8_desc = '%15s' % (' '.join(['0x%02x' % b
  62                                             for b in ch.encode('utf-8')]))
  63             print('%4s |   U+%04X %s %40s %s'
  64                   % ('', ord(ch), utf8_desc, get_name(ch), get_printable(ch)))
  65         line_num += 1
  66
  67
  68 with open(sys.argv[1], mode='r') as f_in:
  69     dump_file(f_in)