#!/bin/ksh
# match2 -- Produce report from log files
#
# Usage: match2 keyId_value output_file log_file...

Usage="Usage: %s keyId_value output_file log_file...
    Output records are created for every unique input record with field 14
    that is \"keyId=keyId_value\".  The output records contain fields 2,
    5, and 14 from the selected input records.  If input field 5 is
    \"none11111\", \"none11111\" will be replaced by the contents of field 5
    in any other record in the log files that has the same value in
    field 12 as field 12 in the selected input record that does not have
    \"none11111\" in field 5.  Output records will be sorted by performing
    a numeric sort on the first output field.  The sorted output will be
    written to the file named by \"output_file\" (or to standard output
    if \"output_file\" is \"-\".\n"

base="$(basename "$0")"
if [ $# -lt 3 ]
then    printf "$Usage" "$base" >&2
        exit 1
fi
matchId_value="$1"
if [ X"$2" = "X-" ]
then    cmd="sort -n -u"
else    cmd="sort -n -u -o \"$2\""
fi
# Shift away the keyId_value and output_file operands that have already
# been saved.  This leaves just the log_file operands in "$@".
shift 2
awk -v base="$base" -v cmd="$cmd" -v link="linkId=$matchId_value" 'BEGIN {
        # Indicates exit code to use if not 0
        ec = ""
        # Set output field separator to a comma.
        OFS = ","
        # Value in field 5 indicating the the correct value is unknown.
        unknown = "none11111"
}
$14 == link {
        # Gather data for an output record for this keyId...
        # o1[x] and o2[x] are output fields 1 and 2; output field 3 is
        # a constant (link), so it does not need to be preserved from
        # each line.  nm[x] contains the "id=" fields needed to find a
        # matching record for records that did not have a valid field 5
        # when the log entry was created...
        o1[NR] = $2
        if($5 == unknown) nm[NR] = $12
        else    o2[NR] = $5
        next
}
$5 != unknown  && ( $10 == "page" || $10 == "clk" ) {
        # Save a field 5 value for the id specified by field 12...
        id[$12] = $5
}
END {   # Fill in the missing o2[x] output fields...
        for (i in nm) if((o2[i] = id[nm[i]]) == "") {
                # Set o2[x] to the unknown value if no matching field
                # was found, and set the final exit code to indicate
                # that at least one entry had no match.
                o2[i] = unknown
                printf("%s: No valid field 5 found for %s\n", base, nm[i])
                ec = 2
        }
        # Write and sort the completed output records.
        for (i in o1) {
                print o1[i],o2[i],link | cmd
        }
        exit ec
}' "$@" >&2
exit

chmod +x match2

match2 1ddoic output_file abc-2012-10-01_000*