Shell Programming and Scripting

match='match($0, / ABC\+[0-9]+\+/)'

awk '{'"$match"'; print substr($0, RSTART+RLENGTH)}' file |
while IFS= read -r line; do
        printf '%s' "$line" | od -An -tx1 | paste -s - |
            sed 's/[[:blank:]]//g; s/../\\x&/g'
done > hextemp

awk '{'"
        $match"'
        pre=substr($0, 1, RSTART+RLENGTH-1)
        nbytes=substr($0, RSTART+5, RLENGTH-6)
        post=substr($0, RSTART+RLENGTH+nbytes)
        getline hexstr < hextemp
        hexstr=substr(hexstr, 1, 4*nbytes)
        printf "%s%s%s%s", pre, hexstr, post, ORS
}' hextemp=hextemp file

#!/bin/ksh
### Functions:
# Usage: hexit bytes
# Convert the string ("bytes") into printable hexadecimal escape sequences
# corresponding to the values of the bytes in the string.  This function will
# not work correctly if a null byte appears in the string other than as the
# string terminator.  It will correctly handle newline characters in the bytes
# operand.
hexit() {
        printf "%s" "$1" | od -An -tx1 | while read x
        do      set -- $x
                while [ $# -gt 0 ]
                do      printf '\\x%s' "$1"
                        shift
                done
        done
}

### Main program:
# Usage: hexstring string...
# This utility will process each string operand (which must be of the form:
#       <front><hex-head><hex-bytes><tail>
# where <front> is any sequence of zero or more printable characters not
#               containing any substring that matches the format specified for
#               <hex-head>.
#       <hex-head> is composed of three parts in sequence:
#               <hex-head-start><count><hex-head-end>
#       where   <hex-head-start> is the characters "ABC+",
#               <count> is one or more characters from the current locale's
#                       digit character class) that will be interpreted as a
#                       decimal digit string specifying the number of bytes
#                       included in <hex-bytes> (see below), and
#               <hex-head-end> is a "+" character.
#       <hex-data> is string of <count> bytes.  These bytes can contain any
#               value except the null byte as long as no substring of these
#               bytes constitute a string that can be interpreted as a valid
#               <hex-head> string either by itself or when combined with the
#               following <tail>.
#       <tail>  is zero or more printable characters not containing any
#               substring that matches the format specifeid above for
#               <hex-head>.
# When processing is complete, a string will be written to stdout containging
# <front> (unchanged), <hex-head> (unchanged), <hex-data> (converted to the
# four character hexadecimal escape sequence representing each byte in the
# <hex-data>), and <tail> (unchanged).
#
# Example: (Assuming this script is invoked by a recent ksh running on a system
# with the ASCII codeset underlying the current locale):
#       hexstring $'start ABC+5+a\tb\nc+end'
# would produce the following output:
#       start ABC+5+\x61\x09\x62\x0a\x63+end
ec=0    # Exit code (0 unless an error is detected)
while [ $# -gt 0 ]
do
        # Extract the <count> field.
        count=$(expr "$1" : ".*ABC+\([0-9]\{1,\}\)+")
        if [ "$count" == "" ]
        then
                printf "%s: \"ABC+<digits>+\" not found in \"%s\"\n" \
                        $(basename "$0") "$1"
                shift
                ec=1
                continue
        fi
        # Calculate the offset to the start of <hex-bytes>.
        off=$(expr "$1" : ".*ABC+[0-9]\{1,\}+")
        # Print <front> and <hex-head>
        printf "%s" "${1:0:off}"
        # Print <hex-bytes> as hexadecimal escape sequences.
        hexit "${1:off:count}"
        # And, print <tail>
        printf "%s\n" "${1:off + count}"
        shift
done
exit $ec