admin/charsets/mapconv

   1 #!/bin/sh
   2 #
   3 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008
   4 #   National Institute of Advanced Industrial Science and Technology (AIST)
   5 #   Registration Number H13PRO009
   6 #
   7 # This file is part of GNU Emacs.
   8 #
   9 # GNU Emacs 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, or (at your option)
  12 # any later version.
  13 #
  14 # GNU Emacs 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 GNU Emacs; see the file COPYING.  If not, write to the
  21 # Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  22 # Boston, MA 02110-1301, USA.
  23
  24 # Comment:
  25 # Convert charset map of various format into this:
  26 #       0xXX 0xYYYY
  27 # where,
  28 #   XX is a code point of the charset in hexa-decimal,
  29 #   YYYY is the corresponding Unicode character code in hexa-decimal.
  30 # Arguments are:
  31 #   $1: source map file
  32 #   $2: address pattern for sed (optionally with substitution command)
  33 #   $3: format of source map file
  34 #       GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE YASUOKA MICROSOFT
  35 #   $4: awk script
  36
  37 BASE=`basename $1`
  38
  39 case "$3" in
  40     GLIBC*)
  41         SOURCE="glibc-2.3.2/localedata/charmaps/${BASE}";;
  42     CZYBORRA)
  43         SOURCE="http://czyborra.com/charsets/${BASE}";;
  44     IANA)
  45         SOURCE="http://www.iana.org/assignments/charset-reg/${BASE}";;
  46     UNICODE)
  47         SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
  48     UNICODE2)
  49         SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
  50     YASUOKA)
  51         SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/.../${BASE}";;
  52     MICROSOFT)
  53         SOURCE="http://www.microsoft.com/globaldev/reference/oem/${BASE}";;
  54     KANJI-DATABASE)
  55         SOURCE="data at http://sourceforge.net/cvs/?group_id=26261";;
  56     *)
  57         echo "Unknown file type: $3";
  58         exit 1;;
  59 esac
  60
  61 echo "# Generated from $SOURCE"
  62
  63 if [ -n "$4" ] ; then
  64     if [ -f "$4" ] ; then
  65         AWKPROG="gawk -f $4"
  66     else
  67         echo "Awk program does not exist: $4"
  68         exit 1
  69     fi
  70 else
  71     AWKPROG=cat
  72 fi
  73
  74 if [ "$3" == "GLIBC-1" ] ; then
  75     # Source format is:
  76     #   <UYYYY> /xXX
  77     sed -n -e "$2 p" < $1 \
  78         | sed -e 's,<U\([^>]*\)>[       ]*/x\(..\).*,0x\2 0x\1,' \
  79         | sort | ${AWKPROG}
  80 elif [ "$3" == "GLIBC-2" ] ; then
  81     # Source format is:
  82     #   <UYYYY> /xXX/xZZ
  83     sed -n -e "$2 p" < $1 \
  84         | sed -e 's,<U\([^>]*\)>[       ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
  85         | sort | ${AWKPROG}
  86 elif [ "$3" == "GLIBC-2-7" ] ; then
  87     # Source format is:
  88     #   <UYYYY> /xXX/xZZ
  89     # We must drop MSBs of XX and ZZ
  90     sed -n -e "$2 p" < $1 \
  91         | sed -e 's/xa/x2/g' -e 's/xb/x3/g' -e 's/xc/x4/g' \
  92               -e 's/xd/x5/g' -e 's/xe/x6/g' -e 's/xf/x7/g' \
  93               -e 's,<U\([^>]*\)>[       ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
  94         | tee temp \
  95         | sort | ${AWKPROG}
  96 elif [ "$3" == "CZYBORRA" ] ; then
  97     # Source format is:
  98     #   =XX     U+YYYY
  99     zcat $1 | sed -n -e "$2 p" \
 100         | sed -e 's/=\(..\)[^U]*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 101         | sort | ${AWKPROG}
 102 elif [ "$3" == "IANA" ] ; then
 103     # Source format is:
 104     #   0xXX    0xYYYY
 105     sed -n -e "$2 p" < $1 \
 106         | sed -e 's/\(0x[0-9A-Fa-f]*\)[^0]*\(0x[0-9A-Fa-f]*\).*/\1 \2/' \
 107         | sort | ${AWKPROG}
 108 elif [ "$3" == "UNICODE" ] ; then
 109     # Source format is:
 110     #   YYYY    XX
 111     sed -n -e "$2 p" < $1 \
 112         | sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
 113         | sort | ${AWKPROG}
 114 elif [ "$3" == "UNICODE2" ] ; then
 115     # Source format is:
 116     #   0xXXXX  0xYYYY  # ...
 117     sed -n -e "$2 p" < $1 \
 118         | sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \
 119         | ${AWKPROG} | sort -n -k 4,4
 120 elif [ "$3" == "YASUOKA" ] ; then
 121     # Source format is:
 122     # YYYY      0-XXXX (XXXX is a Kuten code)
 123     sed -n -e "$2 p" < $1 \
 124         | sed -e 's/\([0-9A-F]*\)[^0]*0-\([0-9]*\).*/0x\2 0x\1/' \
 125         | sort | ${AWKPROG}
 126 elif [ "$3" == "MICROSOFT" ] ; then
 127     # Source format is:
 128     # XX = U+YYYY
 129     sed -n -e "$2 p" < $1 \
 130         | sed -e 's/\([0-9A-F]*\).*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 131         | sort | ${AWKPROG}
 132 elif [ "$3" == "KANJI-DATABASE" ] ; then
 133     # Source format is:
 134     # C?-XXXX U+YYYYY .....
 135     sed -n -e "$2 p" < $1 \
 136         | sed -e 's/...\(....\) U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 137         | sort | ${AWKPROG}
 138 else
 139     echo "Invalid arguments"
 140     exit 1
 141 fi
 142
 143 # arch-tag: c33acb47-7eb6-4872-b871-15e1447e8f0e