contrib/unicode/gen_wcwidth.py

   1 #!/usr/bin/env python3
   2 #
   3 # Script to generate tables for cpp_wcwidth, leveraging glibc's utf8_gen.py.
   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 import sys
  22 import os
  23
  24 if len(sys.argv) != 2:
  25     print("usage: %s <unicode version>", file=sys.stderr)
  26     sys.exit(1)
  27 unicode_version = sys.argv[1]
  28
  29 # Parse a codepoint in the format output by glibc tools.
  30 def parse_ucn(s):
  31     if not (s.startswith("<U") and s.endswith(">")):
  32         raise ValueError
  33     return int(s[2:-1], base=16)
  34
  35 # Process a line of width output from utf_gen.py and update global array.
  36 widths = [1] * (1 + 0x10FFFF)
  37 def process_width(line):
  38     # Example lines:
  39     # <UA8FF>   0
  40     # <UA926>...<UA92D> 0
  41
  42     s = line.split()
  43     width = int(s[1])
  44     r = s[0].split("...")
  45     if len(r) == 1:
  46         begin = parse_ucn(r[0])
  47         end = begin + 1
  48     elif len(r) == 2:
  49         begin = parse_ucn(r[0])
  50         end = parse_ucn(r[1]) + 1
  51     else:
  52         raise ValueError
  53     widths[begin:end] = [width] * (end - begin)
  54
  55 # To keep things simple, we use glibc utf8_gen.py as-is.  It only outputs to a
  56 # file named UTF-8, which is not configurable.  Then we parse this into the form
  57 # we want it.
  58 os.system("from_glibc/utf8_gen.py --unicode_version %s" % unicode_version)
  59 processing = False
  60 for line in open("UTF-8", "r"):
  61     if processing:
  62         if line == "END WIDTH\n":
  63             processing = False
  64         else:
  65             try:
  66                 process_width(line)
  67             except (ValueError, IndexError):
  68                 print(e, "warning: ignored unexpected line: %s" % line,
  69                         file=sys.stderr, end="")
  70     elif line == "WIDTH\n":
  71         processing = True
  72
  73 # All bytes < 256 we treat as width 1.
  74 widths[0:255] = [1] * 255
  75
  76 # Condense the list to contiguous ranges.
  77 cur_range = [-1, 1]
  78 all_ranges = []
  79 for i, width in enumerate(widths):
  80     if width == cur_range[1]:
  81         cur_range[0] = i
  82     else:
  83         all_ranges.append(cur_range)
  84         cur_range = [i, width]
  85
  86 # Output the arrays for generated_cpp_wcwidth.h
  87 print("/*  Generated by contrib/unicode/gen_wcwidth.py,",
  88           "with the help of glibc's")
  89 print("    utf8_gen.py, using version %s" % unicode_version,
  90           "of the Unicode standard.  */")
  91 print("\nstatic const cppchar_t wcwidth_range_ends[] = {", end="")
  92 for i, r in enumerate(all_ranges):
  93     if i % 8:
  94         print(" ", end="")
  95     else:
  96         print("\n  ", end="")
  97     print("0x%x," % (r[0]), end="")
  98 print("\n};\n")
  99 print("static const unsigned char wcwidth_widths[] = {", end="")
 100 for i, r in enumerate(all_ranges):
 101     if i % 24:
 102         print(" ", end="")
 103     else:
 104         print("\n  ", end="")
 105     print("%d," % r[1], end="")
 106 print("\n};")