contrib/unicode/gen-printable-chars.py

   1 #!/usr/bin/env python3
   2 #
   3 # Script to generate libcpp/printable-chars.inc
   4 #
   5 # This file is part of GCC.
   6 #
   7 # GCC is free software; you can redistribute it and/or modify it under
   8 # the terms of the GNU General Public License as published by the Free
   9 # Software Foundation; either version 3, or (at your option) any later
  10 # version.
  11 #
  12 # GCC is distributed in the hope that it will be useful, but WITHOUT ANY
  13 # WARRANTY; without even the implied warranty of MERCHANTABILITY or
  14 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  15 # for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with GCC; see the file COPYING3.  If not see
  19 # <http://www.gnu.org/licenses/>.
  20
  21 from pprint import pprint
  22 import unicodedata
  23
  24 def is_printable_char(code_point) -> bool:
  25     category = unicodedata.category(chr(code_point))
  26     # "Cc" is "control" and "Cf" is "format"
  27     return category[0] != 'C'
  28
  29 class Range:
  30     def __init__(self, start, end, value):
  31         self.start = start
  32         self.end = end
  33         self.value = value
  34
  35     def __repr__(self):
  36         return f'Range({self.start:x}, {self.end:x}, {self.value})'
  37
  38 def make_ranges(value_callback):
  39     ranges = []
  40     for code_point in range(0x10FFFF):
  41         value = is_printable_char(code_point)
  42         if 0:
  43             print(f'{code_point=:x} {value=}')
  44         if ranges and ranges[-1].value == value:
  45             # Extend current range
  46             ranges[-1].end = code_point
  47         else:
  48             # Start a new range
  49             ranges.append(Range(code_point, code_point, value))
  50     return ranges
  51
  52 ranges = make_ranges(is_printable_char)
  53 if 0:
  54     pprint(ranges)
  55
  56 print(f"/* Generated by contrib/unicode/gen-printable-chars.py")
  57 print(f"   using version {unicodedata.unidata_version}"
  58       " of the Unicode standard.  */")
  59 print("\nstatic const cppchar_t printable_range_ends[] = {", end="")
  60 for i, r in enumerate(ranges):
  61     if i % 8:
  62         print(" ", end="")
  63     else:
  64         print("\n  ", end="")
  65     print("0x%x," % r.end, end="")
  66 print("\n};\n")
  67 print("static const bool is_printable[] = {", end="")
  68 for i, r in enumerate(ranges):
  69     if i % 24:
  70         print(" ", end="")
  71     else:
  72         print("\n  ", end="")
  73     if r.value:
  74         print("1,", end="")
  75     else:
  76         print("0,", end="")
  77 print("\n};")