unicode.py

   1 #!/usr/bin/python
   2
   3 # Cycript - Optimizing JavaScript Compiler/Runtime
   4 # Copyright (C) 2009-2015  Jay Freeman (saurik)
   5
   6 # GNU Affero General Public License, Version 3 {{{
   7 #
   8 # This program is free software: you can redistribute it and/or modify
   9 # it under the terms of the GNU Affero General Public License as published by
  10 # the Free Software Foundation, either version 3 of the License, or
  11 # (at your option) any later version.
  12 #
  13 # This program is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 # GNU Affero General Public License for more details.
  17 #
  18 # You should have received a copy of the GNU Affero General Public License
  19 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  20 # }}}
  21
  22 import sys
  23
  24 trees = [dict(), dict(), dict(), dict()]
  25
  26 for line in sys.stdin:
  27     line = line[0:14]
  28     line = line.rstrip(' \n')
  29     line = line.split('..')
  30     if len(line) == 1:
  31         line.append(line[0])
  32     line = [int(end, 16) for end in line]
  33     for point in range(line[0], line[1] + 1):
  34         # http://stackoverflow.com/questions/7105874/
  35         point = "\\U%08x" % point
  36         point = point.decode('unicode-escape')
  37         point = point.encode('utf-8')
  38         point = list(point)
  39         tree = trees[len(point) - 1]
  40         for unit in point:
  41             unit = ord(unit)
  42             tree = tree.setdefault(unit, dict())
  43
  44 items = []
  45
  46 def build(index, tree, units):
  47     if index == 0:
  48         keys = tree.keys()
  49     else:
  50         keys = []
  51         for unit, tree in tree.iteritems():
  52             if build(index - 1, tree, units + [unit]):
  53                 keys.append(unit)
  54
  55     if len(keys) == 0:
  56         return False
  57     if len(keys) == 0xc0 - 0x80:
  58         return True
  59
  60     item = ''
  61     for unit in units:
  62         item += '\\x%02x' % unit
  63     item += '['
  64
  65     first = -1
  66     last = -1
  67
  68     assert len(keys) != 0
  69     for unit in keys + [-1]:
  70         if unit != -1:
  71             if first == -1:
  72                 first = unit
  73                 last = unit
  74                 continue
  75             if unit == last + 1:
  76                 last = unit
  77                 continue
  78
  79         item += '\\x%02x' % first
  80         if first != last:
  81             if last != first + 1:
  82                 item += '-'
  83             item += '\\x%02x' % last
  84
  85         first = unit
  86         last = unit
  87
  88     item += ']'
  89
  90     for i in range(0, index):
  91         item += '[\\x80-\\xbf]'
  92
  93     items.append(item)
  94     return False
  95
  96 for index, tree in enumerate(trees):
  97     build(index, tree, [])
  98
  99 name = sys.argv[1]
 100 parts = []
 101 part = []
 102 length = 0
 103 index = 0
 104 for item in items:
 105     part += [item]
 106     length += len(item) + 1
 107     if length > 1000:
 108         indexed = name + '_' + str(index)
 109         index += 1
 110         print indexed, '|'.join(part)
 111         parts += ['{' + indexed + '}']
 112         part = []
 113         length = 0
 114 parts += part
 115 print name, '|'.join(parts)