Strips out and reformats an NPG access log file

process_log

# First reformat in to CSV and remove duff fields
cat npgj2ee1.nature.com_nature_access.log.2011-03-11 | awk -F"( \"| -)" '{ if ($1 ~ /^Timestamp /) {next;}; printf "%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s\n", $1, $2, $4, $5, $6, $7, $9, $10, $11, $12, $13, $14 }' | sed -e 's/"//g' > sample.log


# Now process sensitive fields
require 'csv'
require 'digest/md5'

output_string = CSV.generate do |output|
  CSV.foreach(ARGV.first) do |row|
    output << row.map do |field|
      if !field.nil? && field.strip =~ /^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$/
        Digest::MD5.hexdigest(field)
      else
        field
      end
    end
  end
end

STDOUT.write output_string