Deduplicate a sorted CSV file, adding a rowcount column

count_lines.rb

def clean_line some_text
    # Takes a comma delimited string, returns an array of fields with leading
    # and trailing whitespace stripped out.
    some_text.gsub(/\"|\n/, "").split(',').each { |x| x.strip! }
end

def spit_line counter, some_line
    # Takes a counter and an array of strings, prints them in counter,strings
    # CSV format.
    print "#{counter}"
    some_line.each { |x| print ",#{x}"}
    print "\n"
    STDOUT.flush
end

# init
counter     = 1
last_line   = clean_line ARGF.readline

ARGF.each do |this_line|
    this_line = clean_line this_line

    if this_line == last_line
        counter   = counter + 1
    else
        spit_line counter, last_line

        counter   = 1
        last_line = this_line
    end
end

# wrap up
spit_line counter, last_line