checksummer 0.1.2 → 0.1.4

data/README.rdoc

@@ -1,6 +1,58 @@
 = checksummer
+checksummer replaces all files in a given directory with symlinks to files named and hashed by MD5 checksum of each file.
 
-Description goes here.
+= Usage
+
+  checksummer <directory_to_checksum> <directory_to_write_data> [OPTIONS]
+  
+  Options:
+    --sleep TIME     Sleep for TIME milliseconds after each symlink operation (for fair IO)
+
+= Example
+
+  checksummer /music /data
+
+== Jay-Z - The Blueprint 3
+ source                                                                                                destination
+ /music/jay-z/the_blueprint_3/01-what_we_talkin_about.mp3                                        =>    /data/3/6/a/5/36a5642b1613bf5589cb479332bddca6
+ /music/jay-z/the_blueprint_3/02-thank_you.mp3                                                   =>    /data/5/1/e/8/51e896f5544b9372edbdf7ec853892a1
+ /music/jay-z/the_blueprint_3/03-doa.mp3                                                         =>    /data/1/e/7/a/1e7aa593020b60e6b45d0178e49d0413 (duplicate)
+ /music/jay-z/the_blueprint_3/04-run_this_town.mp3                                               =>    /data/1/f/4/5/1f454817ee460e28ede71b5e5ee902bd (duplicate)
+ /music/jay-z/the_blueprint_3/05-empire_state_of_mind.mp3                                        =>    /data/4/9/d/3/49d39143e0c42e4c2b852f604938c0d0 (duplicate)
+ /music/jay-z/the_blueprint_3/06-real_as_it_gets.mp3                                             =>    /data/9/8/8/d/988d10054f0eceb5def18bbb2c453557
+ /music/jay-z/the_blueprint_3/07-on_to_the_next_one.mp3                                          =>    /data/e/f/8/0/ef80c8b3560b5e1c15c919f354d226f8
+ /music/jay-z/the_blueprint_3/08-off_that.mp3                                                    =>    /data/3/6/a/8/36a8152e0d98ccd6a375a8ab489cd4a1
+ /music/jay-z/the_blueprint_3/09-a_star_is_born.mp3                                              =>    /data/4/f/0/f/4f0f8253196a98fb54bed89a3768fb8b
+ /music/jay-z/the_blueprint_3/10-venus_vs_mars.mp3                                               =>    /data/3/6/1/c/361cba2aaa0d42bc376187a49448fa45
+ /music/jay-z/the_blueprint_3/11-already_home.mp3                                                =>    /data/d/4/a/7/d4a7756791dbd6df6514c84262b9bb18
+ /music/jay-z/the_blueprint_3/12-hate.mp3                                                        =>    /data/4/a/6/d/4a6d2a9d04778ead9b04d7f45be1e6bd
+ /music/jay-z/the_blueprint_3/13-reminder.mp3                                                    =>    /data/c/e/7/4/ce74f6184af8acc3af232df9b9335a76
+ /music/jay-z/the_blueprint_3/14-so_ambitious.mp3                                                =>    /data/0/d/6/1/0d6140d1a1c681b1f9f5eba7dee523e9
+ /music/jay-z/the_blueprint_3/15-young_forever.mp3                                               =>    /data/f/0/2/1/f0212f638eea55b9d5815515d40e9787
+                                                                                                       
+== Jay-Z - The Hits Collection Volume One                                                              
+  source                                                                                                destination
+ /music/jay-z/the_hits_collection_volume_one/01-public_service_announcement_(interlude).mp3      =>    /data/a/c/1/a/ac1a8c0df8971e732f034a2c6efa6fc1
+ /music/jay-z/the_hits_collection_volume_one/02-run_this_town.mp3                                =>    /data/1/f/4/5/1f454817ee460e28ede71b5e5ee902bd (duplicate)
+ /music/jay-z/the_hits_collection_volume_one/03-03_bonnie_&_clyde.mp3                            =>    /data/d/9/6/5/d9659ed413e0be456c35521639953724
+ /music/jay-z/the_hits_collection_volume_one/04-encore.mp3                                       =>    /data/c/7/c/e/c7ce40508cb1cacf56cbd671bd1adfb8
+ /music/jay-z/the_hits_collection_volume_one/05-i_just_wanna_love_u_(give_it_2_me).mp3           =>    /data/e/1/9/f/e19fa1483b208e75792b30d8562aaed0
+ /music/jay-z/the_hits_collection_volume_one/06-izzo_(hova).mp3                                  =>    /data/1/a/a/a/1aaabf78c9d8e30745b3fc8b2e87e285
+ /music/jay-z/the_hits_collection_volume_one/07-doa_(death_of_auto-tune).mp3                     =>    /data/1/e/7/a/1e7aa593020b60e6b45d0178e49d0413 (duplicate)
+ /music/jay-z/the_hits_collection_volume_one/08-99_problems.mp3                                  =>    /data/7/6/b/6/76b689ae2f65bc44340a4bc2831cd559
+ /music/jay-z/the_hits_collection_volume_one/09-empire_state_of_mind.mp3                         =>    /data/4/9/d/3/49d39143e0c42e4c2b852f604938c0d0 (duplicate)
+ /music/jay-z/the_hits_collection_volume_one/10-dirt_off_your_shoulder.mp3                       =>    /data/3/2/c/5/32c5218d1a460a6257ab6b7aad23add9
+ /music/jay-z/the_hits_collection_volume_one/11-hard_knock_life_(ghetto_anthem).mp3              =>    /data/3/5/9/9/3599648c6dfba16787a0f27b2593c624
+ /music/jay-z/the_hits_collection_volume_one/12-show_me_what_you_got.mp3                         =>    /data/1/a/3/8/1a38f265b1e40d5fc7e1c1814eecc887
+ /music/jay-z/the_hits_collection_volume_one/13-roc_boys_(and_the_winner_is).mp3                 =>    /data/f/8/7/5/f875b6de8e2f7fd5366a209a1ec225c2
+ /music/jay-z/the_hits_collection_volume_one/14-big_pimpin.mp3                                   =>    /data/e/9/e/b/e9ebaa49726d7ac990c4eb57fc8eee59
+
+= Advantages
+
+* Save space: dulicate files are replaced with symlinks to one file
+* Partition data uniformly on multiple disks:
+  /data/[0-8] could be symlinked to e.g. /dev/disk1
+  /data/[9-f] could be symlinked to e.g. /dev/disk2
 
 == Contributing to checksummer
  

data/Rakefile

@@ -13,7 +13,7 @@ require 'jeweler'
 Jeweler::Tasks.new do |gem|
   # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
   gem.name = "checksummer"
-  gem.homepage = "http://github.com/tobstarr/checksummer"
+  gem.homepage = "http://github.com/dynport/checksummer"
   gem.license = "MIT"
   gem.summary = %Q{Replace files with links to md5 files}
   gem.description = %Q{Replace files with links to md5 files}

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.1.4

data/checksummer.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{checksummer}
-  s.version = "0.1.2"
+  s.version = "0.1.4"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Tobias Schwab"]
-  s.date = %q{2011-01-26}
+  s.date = %q{2011-01-29}
   s.default_executable = %q{checksummer}
   s.description = %q{Replace files with links to md5 files}
   s.email = %q{tobias.schwab@dynport.de}
@@ -37,7 +37,7 @@ Gem::Specification.new do |s|
     "spec/checksummer_spec.rb",
     "spec/spec_helper.rb"
   ]
-  s.homepage = %q{http://github.com/tobstarr/checksummer}
+  s.homepage = %q{http://github.com/dynport/checksummer}
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
   s.rubygems_version = %q{1.3.7}

data/lib/checksummer_file.rb

@@ -46,7 +46,9 @@ class ChecksummerFile
       else
         :symlinked
       end
+      mtime = File.mtime(path)
       FileUtils.ln_sf(new_path, path)
+      FileUtils.touch(path, :mtime => mtime)
       status
     else
       :was_symlink

data/spec/checksummer_file_spec.rb

@@ -36,14 +36,17 @@ describe ChecksummerFile do
   
   describe "#checksum_to!" do
     let(:file) { ChecksummerFile.new(:path => "/some/text.csv") }
+    let(:time) { Time.local(2010, 9, 10, 11, 12, 13) }
     let(:md5) { "fde8dad8ea43640b00cdd1e92e532ca9" }
     
     before(:each) do
       FileUtils.stub!(:cp).and_return true
       FileUtils.stub!(:mkdir_p)
+      FileUtils.stub!(:touch)
       FileUtils.stub(:ln_sf).and_return true
       File.stub!(:exists?).and_return false
       File.stub(:symlink?).and_return false
+      File.stub!(:mtime).and_return time
       file.stub!(:md5).and_return md5
     end
     
@@ -82,6 +85,11 @@ describe ChecksummerFile do
       it "returns :copied when copied" do
         file.checksum_to!("/tmp/data").should == :copied
       end
+      
+      it "changes the mtime of the symlink to the mtime of the original file" do
+        FileUtils.should_receive(:touch).with("/some/text.csv", :mtime => time)
+        file.checksum_to!("/tmp/data")
+      end
     end
     
     describe "with the file being checksummed already" do
@@ -107,6 +115,11 @@ describe ChecksummerFile do
       it "returns :symlinked" do
         file.checksum_to!("/tmp/data").should == :symlinked
       end
+      
+      it "changes the mtime of the symlink to the mtime of the original file" do
+        FileUtils.should_receive(:touch).with("/some/text.csv", :mtime => time)
+        file.checksum_to!("/tmp/data")
+      end
     end
     
     describe "with the file being a symlink" do
@@ -132,6 +145,11 @@ describe ChecksummerFile do
       it "returns :exists" do
         file.checksum_to!("/tmp/data").should == :was_symlink
       end
+      
+      it "changes the mtime of the symlink to the mtime of the original file" do
+        FileUtils.should_not_receive(:touch)
+        file.checksum_to!("/tmp/data")
+      end
     end
   end
   

data/spec/checksummer_spec.rb

@@ -151,29 +151,39 @@ describe "Checksummer" do
   describe "#integration" do
     let(:root) { File.expand_path("tmp", File.dirname(__FILE__)) }
     
+    def time_for_index(index)
+      Time.local(2010, 11, 12, 13, 14, index)
+    end
+    
     before(:each) do
       FileUtils.rm_rf(root)
       FileUtils.mkdir_p("#{root}/source")
       FileUtils.mkdir_p("#{root}/data")
       FileUtils.mkdir_p("#{root}/data/a/b/c/d/abcdefg")
       1.upto(3).each do |i|
-        File.open("#{root}/source/file#{i}.txt", "w") { |f| f.puts "file #{i}" }
+        path = "#{root}/source/file#{i}.txt"
+        File.open(path, "w") { |f| f.puts "file #{i}" }
+        FileUtils.touch("#{root}/source/file#{i}.txt", :mtime => time_for_index(i))
       end
       FileUtils.ln_sf("#{root}/data/a/b/c/d/abcdefg", "#{root}/source/file4.txt")
+      FileUtils.touch("#{root}/data/a/b/c/d/abcdefg", :mtime => time_for_index(4))
     end
     
     it "checksums all files" do
       cs = Checksummer.new("#{root}/data")
       cs.checksum_directory("#{root}/source")
-      { "4/3/4/9/4349cfeff8e2eb74dffc369bb5fd084e" => "file2.txt", "9/c/3/8/9c38e8324dbf031557c89d53a39f0b26" => "file3.txt", 
-        "e/2/4/3/e243bb39c844b3543a7726576c869caf" => "file1.txt", "a/b/c/d/abcdefg" => "file4.txt"
-      }.each do |data_file, original_file|
+      { "4/3/4/9/4349cfeff8e2eb74dffc369bb5fd084e" => ["file2.txt", time_for_index(2)], 
+        "9/c/3/8/9c38e8324dbf031557c89d53a39f0b26" => ["file3.txt", time_for_index(3)], 
+        "e/2/4/3/e243bb39c844b3543a7726576c869caf" => ["file1.txt", time_for_index(1)], 
+        "a/b/c/d/abcdefg" => ["file4.txt", time_for_index(4)]
+      }.each do |data_file, (original_file, mtime)|
         original = Pathname.new("#{root}/source/#{original_file}")
         data = Pathname.new("#{root}/data/#{data_file}")
         File.should be_exists(original.to_s)
         File.should be_exists(data.to_s)
         original.realpath.to_s.should match(/\//)
         original.realpath.should == data
+        File.mtime(original).should == mtime
       end
     end
   end

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 1
-  - 2
-  version: 0.1.2
+  - 4
+  version: 0.1.4
 platform: ruby
 authors: 
 - Tobias Schwab
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-26 00:00:00 +01:00
+date: 2011-01-29 00:00:00 +01:00
 default_executable: checksummer
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -142,7 +142,7 @@ files:
 - spec/checksummer_spec.rb
 - spec/spec_helper.rb
 has_rdoc: true
-homepage: http://github.com/tobstarr/checksummer
+homepage: http://github.com/dynport/checksummer
 licenses: 
 - MIT
 post_install_message: 
@@ -155,7 +155,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: -3983138821397024121
+      hash: 3104515524890018189
       segments: 
       - 0
       version: "0"