wmstats for Ruby

wmstats.rb

require 'benchmark'

filename = 'pagecounts-20141029-230000'
min_views = 500
prefix = 'en '
count = []

time = Benchmark.measure do
  File.open(filename).each_line do |line|
    next unless line.start_with? prefix
    
    parts = line.force_encoding("iso-8859-1").split(' ', 3)
    article, views = parts[1], parts[2].to_i
    
    count << [article, views] if views > min_views
  end

  count.sort! { |a,b| b[1] <=> a[1] }
end

puts "Query took #{time.total} seconds"

count[0..9].each { |item| puts "#{item[0]} (#{item[1]})" }