admin/charsets/mapconv

   1 #!/bin/sh
   2
   3 # Copyright (C) 2015 Free Software Foundation, Inc.
   4
   5 # Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   6 #   National Institute of Advanced Industrial Science and Technology (AIST)
   7 #   Registration Number H13PRO009
   8
   9 # This file is part of GNU Emacs.
  10
  11 # GNU Emacs is free software: you can redistribute it and/or modify
  12 # it under the terms of the GNU General Public License as published by
  13 # the Free Software Foundation, either version 3 of the License, or
  14 # (at your option) any later version.
  15
  16 # GNU Emacs is distributed in the hope that it will be useful,
  17 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  18 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  19 # GNU General Public License for more details.
  20
  21 # You should have received a copy of the GNU General Public License
  22 # along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  23
  24 # Commentary:
  25
  26 # Convert charset map of various format into this:
  27 #       0xXX 0xYYYY
  28 # where,
  29 #   XX is a code point of the charset in hexa-decimal,
  30 #   YYYY is the corresponding Unicode character code in hexa-decimal.
  31 # Arguments are:
  32 #   $1: source map file
  33 #   $2: address pattern for sed (optionally with substitution command)
  34 #   $3: format of source map file
  35 #       GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE UNICODE2 YASUOKA
  36 #   $4: awk script
  37
  38 ## So that eg [A-F] as used by KANJI-DATABASE branch below works as expected.
  39 ## Otherwise with LANG=en_US.utf8, CNS-6.map was generated with a
  40 ## bogus entry.  By experiment, LC_COLLATE=C was not enough.
  41 export LC_ALL=C
  42
  43 BASE=`expr "$1" : '.*/\(.*\)' '|' "$1"` # basename
  44 FILE="admin/charsets/mapfiles/$BASE"
  45 BASE=`expr "$BASE" : '\(.*\)\.gz$' '|' "$BASE"` # remove any .gz suffix
  46 AWK=${AWK:-awk}
  47
  48 case "$3" in
  49     GLIBC*)
  50         FILE="$BASE in localedata/charmaps of glibc";
  51         SOURCE="";;
  52     CZYBORRA)
  53         BASE="$BASE.gz";
  54         SOURCE="http://czyborra.com/charsets/${BASE}";;
  55     IANA)
  56         SOURCE="http://www.iana.org/assignments/charset-reg/${BASE}";;
  57     UNICODE)
  58         SOURCE="http://www.unicode.org/Public/MAPPINGS/VENDORS/ADOBE/${BASE}";;
  59     UNICODE2)
  60         SOURCE="http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/${BASE}";;
  61     YASUOKA)
  62         BASE="$BASE.Z";
  63         SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/ftp/CJKtable/${BASE}";;
  64     KANJI-DATABASE)
  65         SOURCE="http://kanji-database.cvs.sourceforge.net/viewvc/*checkout*/kanji-database/kanji-database/data/cns2ucsdkw.txt?revision=1.4";;
  66     *)
  67         printf 'Unknown file type: %s\n' "$3"
  68         exit 1;;
  69 esac
  70
  71 if [ -n "$SOURCE" ] ; then
  72     echo "# Generated from $FILE which is a copy of";
  73     echo "# $SOURCE"
  74 else
  75     echo "# Generated from $FILE"
  76 fi
  77
  78
  79 if [ -n "$4" ] ; then
  80     if [ -f "$4" ] ; then
  81         AWKPROG="$AWK -f $4"
  82     else
  83         echo "Awk program does not exist: $4"
  84         exit 1
  85     fi
  86 else
  87     AWKPROG=cat
  88 fi
  89
  90 if [ "$3" = "GLIBC-1" ] ; then
  91     # Source format is:
  92     #   <UYYYY> /xXX
  93     gunzip -c $1 | sed -n -e "${2}p" \
  94         | sed -e 's,<U\([^>]*\)>[       ]*/x\(..\).*,0x\2 0x\1,' \
  95         | sort | ${AWKPROG}
  96 elif [ "$3" = "GLIBC-2" ] ; then
  97     # Source format is:
  98     #   <UYYYY> /xXX/xZZ
  99     gunzip -c $1 | sed -n -e "${2}p" \
 100         | sed -e 's,<U\([^>]*\)>[       ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
 101         | sort | ${AWKPROG}
 102 elif [ "$3" = "GLIBC-2-7" ] ; then
 103     # Source format is:
 104     #   <UYYYY> /xXX/xZZ
 105     # We must drop MSBs of XX and ZZ
 106     gunzip -c $1 | sed -n -e "${2}p" \
 107         | sed -e 's/xa/x2/g' -e 's/xb/x3/g' -e 's/xc/x4/g' \
 108               -e 's/xd/x5/g' -e 's/xe/x6/g' -e 's/xf/x7/g' \
 109               -e 's,<U\([^>]*\)>[       ]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
 110         | sort | ${AWKPROG}
 111 elif [ "$3" = "CZYBORRA" ] ; then
 112     # Source format is:
 113     #   =XX     U+YYYY
 114     sed -n -e "${2}p" < $1 \
 115         | sed -e 's/=\(..\)[^U]*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 116         | sort | ${AWKPROG}
 117 elif [ "$3" = "IANA" ] ; then
 118     # Source format is:
 119     #   0xXX    0xYYYY
 120     sed -n -e "${2}p" < $1 \
 121         | sed -e 's/\(0x[0-9A-Fa-f]*\)[^0]*\(0x[0-9A-Fa-f]*\).*/\1 \2/' \
 122         | sort | ${AWKPROG}
 123 elif [ "$3" = "UNICODE" ] ; then
 124     # Source format is:
 125     #   YYYY    XX
 126     # We perform reverse sort to prefer the first one in the
 127     # duplicated mappings (e.g. 0x20->U+0020, 0x20->U+00A0).
 128     sed -n -e "${2}p" < $1 \
 129         | sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
 130         | sort -r
 131 elif [ "$3" = "UNICODE2" ] ; then
 132     # Source format is:
 133     #   0xXXXX  0xYYYY  # ...
 134     sed -n -e "${2}p" < $1 \
 135         | sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \
 136         | ${AWKPROG} | sort -n -k 4,4
 137 elif [ "$3" = "YASUOKA" ] ; then
 138     # Source format is:
 139     # YYYY      0-XXXX (XXXX is a Kuten code)
 140     sed -n -e "${2}p" < $1 \
 141         | sed -e 's/\([0-9A-F]*\)[^0]*0-\([0-9]*\).*/0x\2 0x\1/' \
 142         | sort | ${AWKPROG}
 143 elif [ "$3" = "KANJI-DATABASE" ] ; then
 144     # Source format is:
 145     # C?-XXXX U+YYYYY .....
 146     sed -n -e "${2}p" < $1 \
 147         | sed -e 's/...\(....\) U+\([0-9A-F]*\).*/0x\1 0x\2/' \
 148         | sort | ${AWKPROG}
 149 else
 150     printf 'Invalid arguments: %s\n' "$3"
 151     exit 1
 152 fi