contrib/unicode/gen-combining-chars.py

   1 #!/usr/bin/env python3
   2 #
   3 # Script to generate libcpp/combining-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_combining_char(code_point) -> bool:
  25     return unicodedata.combining(chr(code_point)) != 0
  26
  27 class Range:
  28     def __init__(self, start, end, value):
  29         self.start = start
  30         self.end = end
  31         self.value = value
  32
  33     def __repr__(self):
  34         return f'Range({self.start:x}, {self.end:x}, {self.value})'
  35
  36 def make_ranges(value_callback):
  37     ranges = []
  38     for code_point in range(0x10FFFF):
  39         value = is_combining_char(code_point)
  40         if 0:
  41             print(f'{code_point=:x} {value=}')
  42         if ranges and ranges[-1].value == value:
  43             # Extend current range
  44             ranges[-1].end = code_point
  45         else:
  46             # Start a new range
  47             ranges.append(Range(code_point, code_point, value))
  48     return ranges
  49
  50 ranges = make_ranges(is_combining_char)
  51 if 0:
  52     pprint(ranges)
  53
  54 print(f"/* Generated by contrib/unicode/gen-combining-chars.py")
  55 print(f"   using version {unicodedata.unidata_version}"
  56       " of the Unicode standard.  */")
  57 print("\nstatic const cppchar_t combining_range_ends[] = {", end="")
  58 for i, r in enumerate(ranges):
  59     if i % 8:
  60         print(" ", end="")
  61     else:
  62         print("\n  ", end="")
  63     print("0x%x," % r.end, end="")
  64 print("\n};\n")
  65 print("static const bool is_combining[] = {", end="")
  66 for i, r in enumerate(ranges):
  67     if i % 24:
  68         print(" ", end="")
  69     else:
  70         print("\n  ", end="")
  71     if r.value:
  72         print("1,", end="")
  73     else:
  74         print("0,", end="")
  75 print("\n};")