digest_extensions 0.0.3 → 0.1.0

data/.rspec

@@ -1 +1,2 @@
+--format doc
 --color

data/Gemfile

@@ -7,7 +7,7 @@ source "http://rubygems.org"
 # Include everything needed to run rake, tests, features, etc.
 group :development do
   gem "rspec", "~> 2.6.0"
-  gem "bundler", "~> 1.0.0"
+  gem "bundler", "~> 1.0"
   gem "jeweler", "~> 1.6.4"
   gem "rake-compiler", "~> 0.7.9"
 #  gem "rcov", ">= 0"

data/README.rdoc

@@ -1,9 +1,46 @@
 = digest_extensions
 
-Description goes here.
+Extension to the Digest module of the ruby standard library to support marshalling 
+
+With this gem you can accumulatively compute the digest of a byte
+sequence over several executions by storing the marshalled digest
+object in a database:
+
+    class FakeDatabase
+      attr_accessor :value
+    end
+    @db = FakeDatabase.new
+
+    def update_digest(part)
+      marshalled_digest = Marshal::load(@db.value) # Fetch the last digest from database
+      marshalled_digest << part # Compute digest incrementally
+      @db.value = Marshal::dump(marshalled_digest) # Store updated digest in database
+    end
+
+    ## parts_array is provided; for example as a series of files
+    ## generated with the command split on a larger file.
+    @db.value = Marshal::dump(Digest::MD5.new) #An initial value
+    parts_array.each do |part|
+      # Assume this method is invoked in a new process each time, and
+      # the only thing they share is the database (faked in the example with @db)
+      update_digest(part)
+    end
+    Marshal::load(@db.value).hexdigest.should == Digest::MD5.hexdigest(parts_array.inject("", :+))
+
+The plan is to have this feature to be included in the ruby standard library.
+
+== Known issues
+
+Currently the marshalled values are specific to the underlying native
+library used to compute the digest values. That means that if you are
+using a ruby that is compiled with linkage to OpenSSL as the
+underlying md5 library, then the marshalled values (in the database)
+cannot be used with a ruby version compiled with linkage to rubys
+native md5 implementation. So take care of that when you consider
+upgrading your ruby version.
 
 == Contributing to digest_extensions
- 
+
 * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
 * Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
 * Fork the project
@@ -14,6 +51,6 @@ Description goes here.
 
 == Copyright
 
-Copyright (c) 2011 Jarl Friis. See LICENSE.txt for
+Copyright (c) 2011-2012 Jarl Friis. See LICENSE.txt for
 further details.
 

data/VERSION

@@ -1 +1 @@
-0.0.3
+0.1.0

data/digest_extensions.gemspec

@@ -4,14 +4,14 @@
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
-  s.name = %q{digest_extensions}
-  s.version = "0.0.2"
+  s.name = "digest_extensions"
+  s.version = "0.1.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Jarl Friis"]
-  s.date = %q{2011-10-11}
-  s.description = %q{With marshalling of digest objects, it is possible to compute the digests over several executions by storing the marshalled object on file or database, this is handy for computing digests for large files that comes in parts.}
-  s.email = %q{jarl@softace.dk}
+  s.date = "2012-08-05"
+  s.description = "With marshalling of digest objects, it is possible to compute the digests over several executions by storing the marshalled object on file or database, this is handy for computing digests for large files that comes in parts."
+  s.email = "jarl@softace.dk"
   s.extensions = ["ext/digest_extensions/extconf.rb"]
   s.extra_rdoc_files = [
     "LICENSE.txt",
@@ -21,7 +21,6 @@ Gem::Specification.new do |s|
     ".document",
     ".rspec",
     "Gemfile",
-    "Gemfile.lock",
     "LICENSE.txt",
     "README.rdoc",
     "Rakefile",
@@ -34,30 +33,29 @@ Gem::Specification.new do |s|
     "spec/digest_extensions_spec.rb",
     "spec/spec_helper.rb"
   ]
-  s.homepage = %q{http://github.com/jarl-dk/digest_extensions}
+  s.homepage = "http://github.com/jarl-dk/digest_extensions"
   s.licenses = ["GPL"]
   s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.7}
-  s.summary = %q{Extensions to the Digest module of the ruby standard library to support marshalling}
+  s.rubygems_version = "1.8.24"
+  s.summary = "Extensions to the Digest module of the ruby standard library to support marshalling"
 
   if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_development_dependency(%q<rspec>, ["~> 2.6.0"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_development_dependency(%q<bundler>, ["~> 1.0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
       s.add_development_dependency(%q<rake-compiler>, ["~> 0.7.9"])
     else
       s.add_dependency(%q<rspec>, ["~> 2.6.0"])
-      s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+      s.add_dependency(%q<bundler>, ["~> 1.0"])
       s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
       s.add_dependency(%q<rake-compiler>, ["~> 0.7.9"])
     end
   else
     s.add_dependency(%q<rspec>, ["~> 2.6.0"])
-    s.add_dependency(%q<bundler>, ["~> 1.0.0"])
+    s.add_dependency(%q<bundler>, ["~> 1.0"])
     s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
     s.add_dependency(%q<rake-compiler>, ["~> 0.7.9"])
   end

data/spec/digest_extensions_spec.rb

@@ -4,29 +4,42 @@ require 'digest/md5'
 
 describe Digest::MD5 do
   describe "#marshal_dump" do
+    it "can marshal md5 sum for empty object  " do
+      digest = Digest::MD5.new
+      digest.marshal_dump
+    end
+
     it "returns a byte sequence that is larger than 176" do
       ## 88 bytes is minum state information for MD5
       digest = Digest::MD5.new
       digest.marshal_dump.should have_at_least(176).bytes.to_a
     end
 
-    it "returns a byte sequence that is accepted by marshal_load" do
-      Digest::MD5.new.marshal_load(Digest::MD5.new.marshal_dump)
-    end
-  end
-  it "can marshal md5 sum for empty object  " do
-    digest = Digest::MD5.new
-    digest.marshal_load(Digest::MD5.new.marshal_dump)
-    digest.hexdigest.should == Digest::MD5.new.hexdigest
   end
-  it "can marshal md5 sum objects " do
-    byte_sequence = rand(256).chr("binary") * 100000
-    hex_digest = Digest::MD5.hexdigest(byte_sequence)
-    d = Digest::MD5.new
-    d << byte_sequence
-    md = d.marshal_dump
-    Digest::MD5.new.tap{|h|h.marshal_load(md)}.hexdigest.should == hex_digest
+
+  describe "#marshal_load" do
+    context "with a marshalled digest of empty byte sequence" do
+      digest = Digest::MD5.new
+      marshalled_digest = digest.marshal_dump
+
+      it "can load to the correct digest" do
+        Digest::MD5.new.tap{|h|h.marshal_load(marshalled_digest)}.hexdigest.should == digest.hexdigest
+      end
+    end
+
+    context "with marshalled digest of a random byte sequence" do
+      size = 10000
+      byte_sequence = (0...size).map{|i| rand(256)}.pack('c*')
+      digest = Digest::MD5.new
+      digest << byte_sequence
+      marshalled_digest = digest.marshal_dump
+      
+      it "can load to the correct digest " do
+        Digest::MD5.new.tap{|h|h.marshal_load(marshalled_digest)}.hexdigest.should == digest.hexdigest
+      end
+    end
   end
+
   it "can continue on partial digestions " do
     size = 10000
     byte_sequence = (0...size).map{|i| rand(256)}.pack('c*')
@@ -39,4 +52,35 @@ describe Digest::MD5 do
     continue << byte_sequence[split+1..-1]
     continue.hexdigest.should == hex_digest
   end
+
+  context "with an array of parts" do
+    size = 1000000
+    byte_sequence = (0...size).map{|i| rand(256)}.pack('c*')
+    parts = 100 + rand(900)
+    max_size = size/parts #Integer
+    parts_array = (0..parts).map{|p| byte_sequence[(p*max_size)...((p+1)*max_size)]}
+    
+    it "can be used to take a series of parts and compute the digest of the concatenation" do
+      class FakeDatabase
+        attr_accessor :value
+      end
+      @db = FakeDatabase.new
+
+      def update_digest(part)
+        marshalled_digest = Marshal::load(@db.value) # Fetch the last digest from database
+        marshalled_digest << part # Compute digest incrementally
+        @db.value = Marshal::dump(marshalled_digest) # Store updated digest in database
+      end
+
+      ## parts_array is provided; for example as a series of files
+      ## generated with the command split on a larger file.
+      @db.value = Marshal::dump(Digest::MD5.new) #An initial value
+      parts_array.each do |part|
+        # Assume this method is invoked in a new process each time, and
+        # the only thing they share is the database (faked in the example with @db)
+        update_digest(part)
+      end
+      Marshal::load(@db.value).hexdigest.should == Digest::MD5.hexdigest(parts_array.inject("", :+))
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: digest_extensions
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-10-12 00:00:00.000000000Z
+date: 2012-08-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &26019580 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -21,21 +21,31 @@ dependencies:
         version: 2.6.0
   type: :development
   prerelease: false
-  version_requirements: *26019580
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 2.6.0
 - !ruby/object:Gem::Dependency
   name: bundler
-  requirement: &26018820 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '1.0'
   type: :development
   prerelease: false
-  version_requirements: *26018820
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &26017280 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -43,10 +53,15 @@ dependencies:
         version: 1.6.4
   type: :development
   prerelease: false
-  version_requirements: *26017280
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.6.4
 - !ruby/object:Gem::Dependency
   name: rake-compiler
-  requirement: &26008460 !ruby/object:Gem::Requirement
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -54,7 +69,12 @@ dependencies:
         version: 0.7.9
   type: :development
   prerelease: false
-  version_requirements: *26008460
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.7.9
 description: With marshalling of digest objects, it is possible to compute the digests
   over several executions by storing the marshalled object on file or database, this
   is handy for computing digests for large files that comes in parts.
@@ -69,7 +89,6 @@ files:
 - .document
 - .rspec
 - Gemfile
-- Gemfile.lock
 - LICENSE.txt
 - README.rdoc
 - Rakefile
@@ -96,7 +115,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -1639069279099423950
+      hash: 42947112275077556
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -105,7 +124,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.6
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Extensions to the Digest module of the ruby standard library to support marshalling

data/Gemfile.lock

@@ -1,29 +0,0 @@
-GEM
-  remote: http://rubygems.org/
-  specs:
-    diff-lcs (1.1.2)
-    git (1.2.5)
-    jeweler (1.6.4)
-      bundler (~> 1.0)
-      git (>= 1.2.5)
-      rake
-    rake (0.9.2)
-    rake-compiler (0.7.9)
-      rake
-    rspec (2.6.0)
-      rspec-core (~> 2.6.0)
-      rspec-expectations (~> 2.6.0)
-      rspec-mocks (~> 2.6.0)
-    rspec-core (2.6.4)
-    rspec-expectations (2.6.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.6.0)
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  bundler (~> 1.0.0)
-  jeweler (~> 1.6.4)
-  rake-compiler (~> 0.7.9)
-  rspec (~> 2.6.0)