gdb/ada-unicode.py

   1 #!/usr/bin/env python3
   2
   3 # Generate Unicode case-folding table for Ada.
   4
   5 # Copyright (C) 2022 Free Software Foundation, Inc.
   6
   7 # This file is part of GDB.
   8
   9 # This program is free software; you can redistribute it and/or modify
  10 # it under the terms of the GNU General Public License as published by
  11 # the Free Software Foundation; either version 3 of the License, or
  12 # (at your option) any later version.
  13
  14 # This program is distributed in the hope that it will be useful,
  15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  17 # GNU General Public License for more details.
  18
  19 # You should have received a copy of the GNU General Public License
  20 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  21
  22 # This generates the ada-casefold.h header.
  23 # Usage:
  24 #   python ada-unicode.py
  25
  26 import gdbcopyright
  27
  28 # The start of the current range of case-conversions we are
  29 # processing.  If RANGE_START is None, then we're outside of a range.
  30 range_start = None
  31 # End of the current range.
  32 range_end = None
  33 # The delta between RANGE_START and the upper-case variant of that
  34 # character.
  35 upper_delta = None
  36 # The delta between RANGE_START and the lower-case variant of that
  37 # character.
  38 lower_delta = None
  39
  40 # All the ranges found and completed so far.
  41 # Each entry is a tuple of the form (START, END, UPPER_DELTA, LOWER_DELTA).
  42 all_ranges = []
  43
  44
  45 def finish_range():
  46     global range_start
  47     global range_end
  48     global upper_delta
  49     global lower_delta
  50     if range_start is not None:
  51         all_ranges.append((range_start, range_end, upper_delta, lower_delta))
  52         range_start = None
  53         range_end = None
  54         upper_delta = None
  55         lower_delta = None
  56
  57
  58 def process_codepoint(val):
  59     global range_start
  60     global range_end
  61     global upper_delta
  62     global lower_delta
  63     c = chr(val)
  64     low = c.lower()
  65     up = c.upper()
  66     # U+00DF ("LATIN SMALL LETTER SHARP S", aka eszsett) traditionally
  67     # upper-cases to the two-character string "SS" (the capital form
  68     # is a relatively recent addition -- 2017).  Our simple scheme
  69     # can't handle this, so we skip it.  Also, because our approach
  70     # just represents runs of characters with identical folding
  71     # deltas, this change must terminate the current run.
  72     if (c == low and c == up) or len(low) != 1 or len(up) != 1:
  73         finish_range()
  74         return
  75     updelta = ord(up) - val
  76     lowdelta = ord(low) - val
  77     if range_start is not None and (updelta != upper_delta or lowdelta != lower_delta):
  78         finish_range()
  79     if range_start is None:
  80         range_start = val
  81         upper_delta = updelta
  82         lower_delta = lowdelta
  83     range_end = val
  84
  85
  86 for c in range(0, 0x10FFFF):
  87     process_codepoint(c)
  88
  89 with open("ada-casefold.h", "w") as f:
  90     print(
  91         gdbcopyright.copyright("ada-unicode.py", "UTF-32 case-folding for GDB"),
  92         file=f,
  93     )
  94     for r in all_ranges:
  95         print(f"   {{{r[0]}, {r[1]}, {r[2]}, {r[3]}}},", file=f)