iconvdata/tst-table-charmap.sh

   1 #!/bin/sh
   2 # Copyright (C) 2000-2021 Free Software Foundation, Inc.
   3 # This file is part of the GNU C Library.
   4 # Contributed by Bruno Haible <haible@clisp.cons.org>, 2000.
   5 #
   6
   7 # The GNU C Library is free software; you can redistribute it and/or
   8 # modify it under the terms of the GNU Lesser General Public
   9 # License as published by the Free Software Foundation; either
  10 # version 2.1 of the License, or (at your option) any later version.
  11
  12 # The GNU C Library 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 GNU
  15 # Lesser General Public License for more details.
  16
  17 # You should have received a copy of the GNU Lesser General Public
  18 # License along with the GNU C Library; if not, see
  19 # <https://www.gnu.org/licenses/>.
  20
  21 # Converts a glibc format charmap to a simple format .table file.
  22
  23 LC_ALL=C
  24 export LC_ALL
  25
  26 case "$1" in
  27   POSIX )
  28     # Old POSIX/DKUUG borrowed format
  29     grep '^<.*>.*/x[0-9A-Fa-f]*[        ]*<U....>.*$' | grep -v 'not a real character' | sed -e 's,^<.*>[       ]*\([/x0-9A-Fa-f]*\)[   ]*<U\(....\)>.*$,\1     0x\2,' | tr abcdef ABCDEF | sed -e 's,/x\([0-9A-F][0-9A-F]\),\1,g' | sed -e 's,^,0x,' | sort | uniq | grep -v '^0x00    0x\([1-9A-F]...\|.[1-9A-F]..\|..[1-9A-F].\|...[1-9A-F]\)'
  30     ;;
  31   *)
  32     # New Unicode based format
  33     sed -e 's,^%IRREVERSIBLE%,,' | grep '^<U[0-9A-F][0-9A-F][0-9A-F][0-9A-F][0-9A-F]*>[         ]*/x' | grep -v 'not a real character' | sed -e 's,<U\(....\)>[         ]*\([/x0-9A-Fa-f]*\).*$,\2      0x\1,' -e 's,<U0*\([1-9A-F][0-9A-F][0-9A-F][0-9A-F][0-9A-F][0-9A-F]*\)>[        ]*\([/x0-9A-Fa-f]*\).*$,\2      0x\1,' | tr abcdef ABCDEF | sed -e 's,/x\([0-9A-F][0-9A-F]\),\1,g' | sed -e 's,^,0x,' | sort | uniq | grep -v '^0x00    0x\([1-9A-F]...\|.[1-9A-F]..\|..[1-9A-F].\|...[1-9A-F]\)'
  34     ;;
  35 esac