emacs/admin/charsets/mapconv

#!/bin/sh

# Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008
#   National Institute of Advanced Industrial Science and Technology (AIST)
#   Registration Number H13PRO009

# This file is part of GNU Emacs.

# GNU Emacs is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# GNU Emacs is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.

# Commentary:

# Convert charset map of various format into this:
#	0xXX 0xYYYY
# where,
#   XX is a code point of the charset in hexa-decimal,
#   YYYY is the corresponding Unicode character code in hexa-decimal.
# Arguments are:
#   $1: source map file
#   $2: address pattern for sed (optionally with substitution command)
#   $3: format of source map file
#	GLIBC-1 GLIBC-2 GLIBC-2-7 CZYBORRA IANA UNICODE YASUOKA MICROSOFT
#   $4: awk script

BASE=`basename $1`

case "$3" in
    GLIBC*)
	SOURCE="glibc-2.3.2/localedata/charmaps/${BASE}";;
    CZYBORRA)
	SOURCE="http://czyborra.com/charsets/${BASE}";;
    IANA)
	SOURCE="http://www.iana.org/assignments/charset-reg/${BASE}";;
    UNICODE)
	SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
    UNICODE2)
	SOURCE="http://www.unicode.org/Public/MAPPINGS/.../${BASE}";;
    YASUOKA)
	SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/.../${BASE}";;
    MICROSOFT)
	SOURCE="http://www.microsoft.com/globaldev/reference/oem/${BASE}";;
    KANJI-DATABASE)
	SOURCE="data at http://sourceforge.net/cvs/?group_id=26261";;
    *)
	echo "Unknown file type: $3";
	exit 1;;
esac

echo "# Generated from $SOURCE"

if [ -n "$4" ] ; then
    if [ -f "$4" ] ; then
	AWKPROG="gawk -f $4"
    else
	echo "Awk program does not exist: $4"
	exit 1
    fi
else
    AWKPROG=cat
fi

if [ "$3" == "GLIBC-1" ] ; then
    # Source format is:
    #   <UYYYY>	/xXX
    sed -n -e "$2 p" < $1 \
	| sed -e 's,<U\([^>]*\)>[ 	]*/x\(..\).*,0x\2 0x\1,' \
	| sort | ${AWKPROG}
elif [ "$3" == "GLIBC-2" ] ; then
    # Source format is:
    #   <UYYYY>	/xXX/xZZ
    sed -n -e "$2 p" < $1 \
	| sed -e 's,<U\([^>]*\)>[ 	]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
	| sort | ${AWKPROG}
elif [ "$3" == "GLIBC-2-7" ] ; then
    # Source format is:
    #   <UYYYY>	/xXX/xZZ
    # We must drop MSBs of XX and ZZ
    sed -n -e "$2 p" < $1 \
	| sed -e 's/xa/x2/g' -e 's/xb/x3/g' -e 's/xc/x4/g' \
	      -e 's/xd/x5/g' -e 's/xe/x6/g' -e 's/xf/x7/g' \
	      -e 's,<U\([^>]*\)>[ 	]*/x\(..\)/x\(..\).*,0x\2\3 0x\1,' \
	| tee temp \
	| sort | ${AWKPROG}
elif [ "$3" == "CZYBORRA" ] ; then
    # Source format is:
    #   =XX	U+YYYY
    zcat $1 | sed -n -e "$2 p" \
	| sed -e 's/=\(..\)[^U]*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
	| sort | ${AWKPROG}
elif [ "$3" == "IANA" ] ; then
    # Source format is:
    #   0xXX	0xYYYY
    sed -n -e "$2 p" < $1 \
	| sed -e 's/\(0x[0-9A-Fa-f]*\)[^0]*\(0x[0-9A-Fa-f]*\).*/\1 \2/' \
	| sort | ${AWKPROG}
elif [ "$3" == "UNICODE" ] ; then
    # Source format is:
    #   YYYY	XX
    sed -n -e "$2 p" < $1 \
	| sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
	| sort | ${AWKPROG}
elif [ "$3" == "UNICODE2" ] ; then
    # Source format is:
    #   0xXXXX	0xYYYY	# ...
    sed -n -e "$2 p" < $1 \
	| sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \
	| ${AWKPROG} | sort -n -k 4,4
elif [ "$3" == "YASUOKA" ] ; then
    # Source format is:
    # YYYY	0-XXXX (XXXX is a Kuten code)
    sed -n -e "$2 p" < $1 \
	| sed -e 's/\([0-9A-F]*\)[^0]*0-\([0-9]*\).*/0x\2 0x\1/' \
	| sort | ${AWKPROG}
elif [ "$3" == "MICROSOFT" ] ; then
    # Source format is:
    # XX = U+YYYY
    sed -n -e "$2 p" < $1 \
	| sed -e 's/\([0-9A-F]*\).*U+\([0-9A-F]*\).*/0x\1 0x\2/' \
	| sort | ${AWKPROG}
elif [ "$3" == "KANJI-DATABASE" ] ; then
    # Source format is:
    # C?-XXXX U+YYYYY .....
    sed -n -e "$2 p" < $1 \
	| sed -e 's/...\(....\) U+\([0-9A-F]*\).*/0x\1 0x\2/' \
	| sort | ${AWKPROG}
else
    echo "Invalid arguments"
    exit 1
fi

# arch-tag: c33acb47-7eb6-4872-b871-15e1447e8f0e