view admin/charsets/mapconv @ 89665:9010cefe8d29

(enum iso_code_class_type): Delete ISO_carriage_return. (CODING_GET_INFO): Delete argument eol_type. Callers changed. (decode_coding_utf_8): Don't do eol converion. (detect_coding_utf_16): Check coding->src_chars, not coding->src_bytes. Add heuristics for those that have no signature. (decode_coding_emacs_mule): Don't do eol converion. (decode_coding_iso_2022): Likewise. (decode_coding_sjis): Likewise. (decode_coding_big5): Likewise. (decode_coding_charset): Likewise. (adjust_coding_eol_type): Return a new coding system. (detect_coding): Don't detect eol. Fix for utf-16 detection. (decode_eol): In case of CRLF->LF conversion, use del_range_2 on each change. (decode_coding): Pay attention to undo_list. Do eol convesion for all types of coding-systems (if necessary). (Vcode_conversion_work_buf_list): Delete it. (Vcode_conversion_reused_workbuf): Renamed from Vcode_conversion_reused_work_buf. (Vcode_conversion_workbuf_name): New variable. (reused_workbuf_in_use): New variable. (make_conversion_work_buffer): Delete the arg DEPTH. (code_conversion_restore): Argument changed to cons. (code_conversion_save): Delete the argument BUFFER. Callers changed. (detect_coding_system): New argument src_chars. Callers changed. Fix for utf-16 detection. (init_coding_once): Don't use ISO_carriage_return. (syms_of_coding): Initialized Vcode_conversion_workbuf_name and reused_workbuf_in_use.

#!/bin/sh
#
# Copyright (C) 2003
#   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 2, 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; see the file COPYING.  If not, write to the
# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
# Boston, MA 02111-1307, USA.

# Comment:
# 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=`echo $1 | sed 's/.*\(glibc.*$\)/\1/'`;;
    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/.../${BASE}";;
    YASUOKA)
	SOURCE="http://kanji.zinbun.kyoto-u.ac.jp/~yasuoka/.../${BASE}";;
    MICROSOFT)
	SOURCE="http://www.microsoft.com/globaldev/reference/oem/${BASE}";;
    *)
	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" == "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}
else
    echo "Invalid arguments"
    exit 1
fi