comparison admin/charsets/mapconv @ 89815:59bbae51ad73

Add code for handling KANJI-DATABASE format.

89814:bd285ab281c3

	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

    # 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

89815:59bbae51ad73

	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

    # 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