Created
December 15, 2009 16:49
-
-
Save samaaron/257079 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/ruby -wKU | |
require 'benchmark' | |
class WordCounter | |
def initialize(directory) | |
files_to_count = Dir["#{ARGV[0]}/**"].reject{|name| File.directory?(name)} | |
@counts = Hash.new(0) | |
count_words_in_files(files_to_count) | |
end | |
def output_alphabetical(outfile) ; output(outfile, sorted_alphabetically) ; end | |
def output_decreasing(outfile) ; output(outfile, sorted_by_count) ; end | |
def output(outfile, counts=@counts) | |
File.open(outfile, 'w') do |out| | |
counts.each { |pair| out << "#{pair[0]}\t#{pair[1]}\n" } | |
end | |
end | |
private | |
def sorted_alphabetically ; sort(0) ; end | |
def sorted_by_count ; sort(1) ; end | |
def count_words_in_files(filenames) | |
filenames.each do |name| | |
File.open(name, 'r').read.scan(/\w+/) { |word| @counts[word.downcase] += 1 } | |
end | |
end | |
def sort(sort_by_index) | |
@counts.sort { |a, b| b[sort_by_index] <=> a[sort_by_index] } | |
end | |
end | |
Benchmark.bm do |benchmark| | |
benchmark.report("alphabetical:") do | |
counter = WordCounter.new(ARGV[0]) | |
counter.output_alphabetical("counts-alphabetical-ruby") | |
end | |
benchmark.report("decreasing: ") do | |
counter = WordCounter.new(ARGV[0]) | |
counter.output_decreasing("counts-descreasing-ruby") | |
end | |
benchmark.report("total: ") do | |
counter = WordCounter.new(ARGV[0]) | |
counter.output_alphabetical("counts-alphabetical-ruby") | |
counter.output_decreasing("counts-descreasing-ruby") | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment