admin/charsets/eucjp-ms.awk

   1 # eucjp-ms.awk -- Generate a translation table for eucJP-ms.
   2 # Copyright (C) 2004
   3 #   National Institute of Advanced Industrial Science and Technology (AIST)
   4 #   Registration Number H13PRO009
   5 #
   6 # This file is part of GNU Emacs.
   7 #
   8 # GNU Emacs is free software; you can redistribute it and/or modify
   9 # it under the terms of the GNU General Public License as published by
  10 # the Free Software Foundation; either version 2, or (at your option)
  11 # any later version.
  12 #
  13 # GNU Emacs is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16 # GNU General Public License for more details.
  17 #
  18 # You should have received a copy of the GNU General Public License
  19 # along with GNU Emacs; see the file COPYING.  If not, write to the
  20 # Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  21 # Boston, MA 02111-1307, USA.
  22
  23 # Comment:
  24
  25 # eucJP-ms is one of eucJP-open encoding defined at this page:
  26 #  http://www.opengroup.or.jp/jvc/cde/appendix.html
  27
  28 BEGIN {
  29   print ";;; eucjp-ms.el -- translation table for eucJP-ms. -*- no-byte-compile: t -*-";
  30   print ";;; Automatically genrated from eucJP-13th.txt, eucJP-udc.txt, eucJP-ibmext.txt";
  31   print "(let ((map";
  32   printf "       '(;JISEXT<->UNICODE";
  33
  34   tohex["A"] = 10;
  35   tohex["B"] = 11;
  36   tohex["C"] = 12;
  37   tohex["D"] = 13;
  38   tohex["E"] = 14;
  39   tohex["F"] = 15;
  40 }
  41
  42 function decode_hex(str) {
  43   n = 0;
  44   len = length(str);
  45   for (i = 1; i <= len; i++)
  46     {
  47       c = substr(str, i, 1);
  48       if (c >= "0" && c <= "9")
  49         n = n * 16 + (c - "0");
  50       else
  51         n = n * 16 + tohex[c];
  52     }
  53   return n;
  54 }
  55
  56 /0x8F/ {
  57   code = decode_hex(substr($1, 5, 4));
  58   code -= 32896;                # code -= 0x8080
  59   printf "\n     (#x%04x #x%s)", code, substr($2, 3, 4);
  60   next;
  61 }
  62
  63 /0x[A-F]/ {
  64   code = decode_hex(substr($1, 3, 4));
  65   code -= 32896;                # code -= 0x8080
  66   printf "\n     (#x%04x . #x%s)", code, substr($2, 3, 4);
  67 }
  68
  69 END {
  70   print ")))";
  71   print "  (mapc #'(lambda (x)";
  72   print "           (if (integerp (cdr x))";
  73   print "               (setcar x (decode-char 'japanese-jisx0208 (car x)))";
  74   print "             (setcar x (decode-char 'japanese-jisx0212 (car x)))";
  75   print "             (setcdr x (cadr x))))";
  76   print "       map)";
  77   print "  (define-translation-table 'eucjp-ms-decode map)";
  78   print "  (mapc #'(lambda (x)";
  79   print "           (let ((tmp (car x)))";
  80   print "             (setcar x (cdr x)) (setcdr x tmp)))";
  81   print "       map)";
  82   print "  (define-translation-table 'eucjp-ms-encode map))";
  83 }
  84
  85 # arch-tag: d9cc7af7-2d6e-48cd-8eed-a6d25226de7c