comparison admin/charsets/mapconv @ 103578:63a1307441f9

For the UNICODE format files, do reverse sort and don't compact the map. This is to prefer the first one in the duplicated mappings (e.g. 0x20->U+0020, 0x20->U+00A0).

103577:520b069d6504

#   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
#   $4: awk script

FILE="admin/charsets/$1"
BASE=`basename $1 .gz`

	| 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
    zcat $1 | sed -n -e "$2 p" \
	| 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	# ...
    zcat $1 | sed -n -e "$2 p" \
	| sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \

103578:63a1307441f9

#   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

FILE="admin/charsets/$1"
BASE=`basename $1 .gz`

	| 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).
    zcat $1 | sed -n -e "$2 p" \
	| 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	# ...
    zcat $1 | sed -n -e "$2 p" \
	| sed -e 's/\([0-9A-Fx]*\)[^0]*\([0-9A-Fx]*\).*/\1 \2/' \