emacs/admin/charsets/mapconv

#!/bin/sh

# Copyright (C) 2015-2024 Free Software Foundation, Inc.

# Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
#   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 <https://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 UNICODE2 YASUOKA
#   $4: awk script

## So that eg [A-F] as used by KANJI-DATABASE branch below works as expected.
## Otherwise with LANG=en_US.utf8, CNS-6.map was generated with a
## bogus entry.  By experiment, LC_COLLATE=C was not enough.
LC_ALL=C
export LC_ALL

BASE=`expr "$1" : '.*/\(.*\)' '|' "$1"` # basename
FILE="admin/charsets/mapfiles/$BASE"
BASE=`expr "$BASE" : '\(.*\)\.gz$' '|' "$BASE"` # remove any .gz suffix
AWK=${AWK:-awk}

case "$3" in
    GLIBC*)
	FILE="$BASE in localedata/charmaps of glibc";
	SOURCE="";;
    CZYBORRA)
	BASE="$BASE.gz";
	SOURCE="https://czyborra.com/charsets/${BASE}";;
    IANA)
	SOURCE="https://www.iana.org/assignments/charset-reg/${BASE}";;
    UNICODE)
	SOURCE="https://www.unicode.org/Public/MAPPINGS/VENDORS/ADOBE/${BASE}";;
    UNICODE2)
	SOURCE="https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/${BASE}";;
    YASUOKA)
	BASE="$BASE.Z";
	SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/ftp/CJKtable/${BASE}";;
    KANJI-DATABASE)
	# FIXME: This URL no longer works.
	SOURCE="http://kanji-database.cvs.sourceforge.net/viewvc/*checkout*/kanji-database/kanji-database/data/cns2ucsdkw.txt?revision=1.4";;
    *)
	printf 'Unknown file type: %s\n' "$3"
	exit 1;;
esac

if [ -n "$SOURCE" ] ; then
    echo "# Generated from $FILE which is a copy of";
    echo "# $SOURCE"
else
    echo "# Generated from $FILE"
fi


if [ -n "$4" ] ; then
    if [ -f "$4" ] ; then
	AWKPROG="$AWK -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
    gunzip -c $1 | sed -n -e "${2}p" \
	| sed -e 's,<U\([^>]*\)>[ 	]*/x\(..\).*,0x\2 0x\1,' \
	| sort | ${AWKPROG}
elif [ "$3" = "GLIBC-2" ] ; then
    # Source format is:
    #   <UYYYY>	/xXX/xZZ
    gunzip -c $1 | sed -n -e "${2}p" \
	| 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
    gunzip -c $1 | sed -n -e "${2}p" \
	| 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,' \
	| sort | ${AWKPROG}
elif [ "$3" = "CZYBORRA" ] ; then
    # Source format is:
    #   =XX	U+YYYY
    sed -n -e "${2}p" < $1 \
	| 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 [ "$3" = "UNICODE" ] ; then
    # Source format is:
    #   YYYY	XX
    # We perform reverse sort to prefer the first one in the
    # duplicated mappings (e.g. 0x20->U+0020, 0x20->U+00A0).
    sed -n -e "${2}p" < $1 \
	| sed -e 's/\([0-9A-F]*\)[^0-9A-F]*\([0-9A-F]*\).*/0x\2 0x\1/' \
	| sort -r
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 [ "$3" = "KANJI-DATABASE" ] ; then
    # Source format is:
    # C?-XXXX U+YYYYY .....
    sed -n -e "${2}p" < $1 \
	| sed -e 's/...\(....\) U+\([0-9A-F]*\).*/0x\1 0x\2/' \
	| sort | ${AWKPROG}
else
    printf 'Invalid arguments: %s\n' "$3"
    exit 1
fi