Created
July 8, 2010 18:46
-
-
Save kalbasit/468418 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/env ruby | |
require 'fileutils' | |
require 'digest/md5' | |
class DownloadArchiver | |
attr_reader :files | |
attr_reader :md5_to_files | |
def initialize(dir) | |
@base_dir = dir | |
_scan_for_files | |
_hash_files | |
end | |
def remove_duplicates | |
@md5_to_files.each_value do |v| | |
if v.size > 1 | |
for i in 1..v.size - 1 | |
@removed_files ||= Array.new | |
@removed_files << v[i] | |
FileUtils.rm v[i] | |
end | |
end | |
end | |
puts "#{@removed_files.size} has been removed" if @removed_files && @removed_files.size > 0 | |
@md5_to_files.clear | |
# Re-scan the folder | |
_scan_for_files | |
end | |
def archive | |
_archive_files_by_date | |
end | |
private | |
def _scan_for_files | |
@files = Array.new | |
@md5_to_files = Hash.new | |
Dir.glob(@base_dir + File::Separator + '*').each do |f| | |
if !File.directory? f | |
@files << f | |
end | |
end | |
end | |
def _hash_files | |
@files.each do |f| | |
digest = Digest::MD5.hexdigest(File.read f) | |
@md5_to_files[digest] ||= Array.new | |
@md5_to_files[digest] << f | |
end | |
end | |
def _archive_files_by_date | |
# Register today's date | |
today = Time.new() | |
@files.each do |f| | |
fh = File.new(f) | |
if !File.directory?(f) && (fh.mtime.year != today.year || fh.mtime.month != today.month) | |
f_year_path = @base_dir + File::Separator + fh.mtime.year.to_s | |
f_month_path = f_year_path + File::Separator + fh.mtime.month.to_s | |
FileUtils.mkdir f_year_path if !File::exists?(f_year_path) || !File.directory?(f_year_path) | |
FileUtils.mkdir f_month_path if !File::exists?(f_month_path) || !File.directory?(f_month_path) | |
FileUtils.mv(f, f_month_path + File::Separator + File.basename(f)) | |
end | |
end | |
end | |
end | |
# Register the base downloads path | |
downloads_path = ENV['HOME'] + '/Downloads' | |
da = DownloadArchiver.new(downloads_path) | |
da.remove_duplicates | |
da.archive |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment