1  #!/usr/bin/env python3
       2  # Copyright (C) 1998, 1999 Tom Tromey
       3  # Copyright (C) 2001 Red Hat Software
       4  #
       5  # SPDX-License-Identifier: GPL-2.0-or-later
       6  #
       7  # This program is free software; you can redistribute it and/or modify
       8  # it under the terms of the GNU General Public License as published by
       9  # the Free Software Foundation; either version 2, or (at your option)
      10  # any later version.
      11  #
      12  # This program is distributed in the hope that it will be useful,
      13  # but WITHOUT ANY WARRANTY; without even the implied warranty of
      14  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
      15  # GNU General Public License for more details.
      16  #
      17  # You should have received a copy of the GNU General Public License
      18  # along with this program; if not, see <http://www.gnu.org/licenses/>.
      19  
      20  """
      21  gen-casefold-txt.py - Generate test cases for casefolding from Unicode data.
      22  See http://www.unicode.org/Public/UNIDATA/UnicodeCharacterDatabase.html
      23  Usage:
      24      I consider the output of this program to be unrestricted.
      25      Use it as you will.
      26  """
      27  
      28  import sys
      29  import argparse
      30  
      31  
      32  def main(argv):
      33      parser = argparse.ArgumentParser(
      34          description="Generate test cases for casefolding from Unicode data"
      35      )
      36      parser.add_argument("UNICODE-VERSION")
      37      parser.add_argument("CaseFolding.txt")
      38      args = parser.parse_args(argv[1:])
      39      version = getattr(args, "UNICODE-VERSION")
      40      filename = getattr(args, "CaseFolding.txt")
      41  
      42      print(
      43          """\
      44  # Test cases generated from Unicode {} data
      45  # by gen-casefold-txt.py. Do not edit.
      46  #
      47  # Some special hand crafted tests
      48  #
      49  AaBbCc@@\taabbcc@@
      50  #
      51  # Now the automatic tests
      52  #""".format(
      53              version
      54          )
      55      )
      56  
      57      # Names of fields in the CaseFolding table
      58      CODE, STATUS, MAPPING = range(3)
      59  
      60      with open(filename, encoding="utf-8") as fileobj:
      61          for line in fileobj:
      62              # strip comments and skip empty lines
      63              line = line.split("#", 1)[0].strip()
      64              if not line:
      65                  continue
      66  
      67              fields = [f.strip() for f in line.split(";", 3)[:3]]
      68              if len(fields) != 3:
      69                  raise SystemExit(
      70                      "Entry for %s has wrong number of fields (%d)"
      71                      % (fields[CODE], len(fields))
      72                  )
      73  
      74              status = fields[STATUS]
      75              # skip simple and Turkic mappings
      76              if status in "ST":
      77                  continue
      78  
      79              code = chr(int(fields[CODE], 16))
      80              values = "".join([chr(int(v, 16)) for v in fields[MAPPING].split()])
      81              print("{}\t{}".format(code, values))
      82  
      83  
      84  if __name__ == "__main__":
      85      sys.exit(main(sys.argv))