github_metadata 0.1.1 → 0.2.0

data/.gitignore

@@ -4,3 +4,4 @@ coverage
 rdoc
 *.gem
 .bundle
+Gemfile.lock

data/README.rdoc

@@ -11,6 +11,10 @@ The github_metadata gem is here to solve this. Currently it gives you, for any g
   * The count of pull requests
   * The list of contributors, with username and real name if available, and thereby also
     the count of contributors
+  * The default branch
+  * The most recent commits
+  * The average date for recent commits (to analyze project activity - hat tip to Ryan Bates for the
+    idea!)
     
 By the way: It goes very easy on the github servers in doing so, currently only performing 1 request 
 to fetch all of the information per instance.
@@ -36,6 +40,10 @@ Check out the full documentation to see all available methods.
   
   * Better (any?) error handling
   * Merge with my very own first_github_commit gem, which retrieves the very first commit to a repo
+
+== Compatible rubies
+
+Tested on MRI 1.8.7, 1.9.1, 1.9.2, and REE
   
 == Note on Patches/Pull Requests
 

data/github_metadata.gemspec

@@ -15,8 +15,12 @@ Gem::Specification.new do |s|
   s.rubyforge_project = "github_metadata"
   
   s.add_dependency 'nokogiri'
+  s.add_dependency 'feedzirra'
+  s.add_dependency 'i18n'
   s.add_development_dependency 'rspec', '>= 2.0.0'
-  s.add_development_dependency 'simplecov'
+  s.add_development_dependency 'simplecov', ">= 0.4.1"
+  s.add_development_dependency 'vcr'
+  s.add_development_dependency 'webmock'
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/lib/github_metadata/version.rb

@@ -1,3 +1,3 @@
 class GithubMetadata
-  VERSION = "0.1.1"
+  VERSION = "0.2.0"
 end

data/lib/github_metadata.rb

@@ -1,6 +1,8 @@
+# encoding: utf-8
 require 'rubygems'
 require 'open-uri'
 require 'nokogiri'
+require 'feedzirra'
 
 # A simple scraper that fetches data from github repos that is not
 # available via the API. See README for an introduction and overview.
@@ -17,6 +19,26 @@ class GithubMetadata
     end
   end
   
+  # Object representation of a commit, initialized
+  # from a github repo commit feed entry
+  class Commit
+    attr_reader :title, :message, :committed_at, :url, :author
+    
+    def initialize(atom_entry)
+      @atom_entry = atom_entry
+      @title = atom_entry.title
+      @message = atom_entry.content
+      @author = atom_entry.author
+      @committed_at = atom_entry.updated.kind_of?(Time) ? atom_entry.updated : Time.parse(atom_entry.updated)
+      @url = atom_entry.url
+    end
+    
+    private
+      def atom_entry
+        @atom_entry
+      end
+  end
+  
   def initialize(user, repo)
     @user, @repo = user, repo
   end
@@ -36,6 +58,18 @@ class GithubMetadata
     nil
   end
   
+  def github_url
+    "https://github.com/#{user}/#{repo}/"
+  end
+  
+  def contributors_url
+    File.join(github_url, 'contributors')
+  end
+  
+  def commits_feed_url
+    File.join(github_url, "commits/#{default_branch}.atom")
+  end
+  
   # Returns an array of GithubMetadata::Contributor instances, one for each
   # contributor listed on the contributors page of github
   def contributors
@@ -91,6 +125,25 @@ class GithubMetadata
     pull_request_link.text[/\d+/].to_i
   end
   
+  # Returns the default branch of the repo
+  def default_branch
+    document.at_css('.tabs .contextswitch code').text
+  end
+  
+  # Returns (at most) the last 20 commits (fetched from atom feed of the default_branch)
+  # as instances of GithubMetadata::Commit
+  def recent_commits
+    @recent_commits ||= commits_feed.entries.map {|e| GithubMetadata::Commit.new(e) }
+  end
+  
+  # Returns the average date of recent commits (by default all (max 20), can be modified
+  # by giving the optional argument)
+  def average_recent_committed_at(num=100)
+    commit_times = recent_commits[0..num].map {|c| c.committed_at.to_f }
+    average_time = commit_times.inject(0) {|s, i| s + i} / commit_times.length
+    Time.at(average_time)
+  end
+  
   private
   
     def document
@@ -99,8 +152,8 @@ class GithubMetadata
       raise GithubMetadata::RepoNotFound, err.to_s
     end
     
-    def contributors_url
-      "https://github.com/#{user}/#{repo}/contributors"
+    def commits_feed
+      @commits_feed ||= Feedzirra::Feed.fetch_and_parse(commits_feed_url)
     end
     
     def load_contributors

data/spec/github_metadata_spec.rb

@@ -8,83 +8,29 @@ describe GithubMetadata do
     end
     subject { @metadata }
 
-    describe '#user' do
-      specify do
-        subject.user.should == 'aslakhellesoy'
-      end
-    end
-    
-    describe '#repo' do
-      specify do
-        subject.repo.should == 'cucumber'
-      end
-    end
-    
-    specify do
-      subject.should have_wiki
-    end
-    
-    describe '#wiki_pages' do
-      specify do
-        expected = @raw.match(/Wiki \((\d+)\)/)[1].to_i
-        expected.should be > 50
-        subject.wiki_pages.should == expected
-      end
-    end
-    
-    specify do
-      subject.should_not have_issues
-    end
-    
-    describe '#issues' do
-      specify do
-        subject.issues.should == nil
-      end
-    end
+    its(:user) { should == 'aslakhellesoy' }
+    its(:repo) { should == 'cucumber' }
+  
+    specify { should have_wiki }
+    its(:wiki_pages) { should == @raw.match(/Wiki \((\d+)\)/)[1].to_i }
     
-    describe '#pull_requests' do
-      specify do
-        expected = @raw.match(/Pull Requests \((\d+)\)/)[1].to_i
-        subject.pull_requests.should == expected
-      end
-    end
+    specify { should_not have_issues }
+    its(:issues) { should be_nil }
     
-    describe '#contributors' do
-      specify do
-        expected = @raw.match(/(\d+) contributors/)[1].to_i
-        subject.contributors.length.should == expected
-      end
-    end
+    its(:pull_requests) { should == @raw.match(/Pull Requests \((\d+)\)/)[1].to_i }
     
-    describe '#contributor_usernames' do
-      specify do
-        subject.contributor_usernames.should include('aslakhellesoy')
-      end
-    end
+    its("contributors.length") { should == @raw.match(/(\d+) contributors/)[1].to_i}
+    its(:contributor_usernames) { should include('aslakhellesoy') }
+    its(:contributor_realnames) { should include('Iain Hecker', 'Elliot Crosby-McCullough', 'David Chelimsky') }
+    its("contributor_realnames.length") { should < @metadata.contributor_usernames.length } 
     
-    describe '#contributor_realnames' do
-      specify do
-        subject.contributor_realnames.should include('Iain Hecker', 'Elliot Crosby-McCullough', 'Aslak Hellesøy')
-      end
+    its("contributor_names.length") { should == @metadata.contributors.count }
+    its(:contributor_names) { should include('Iain Hecker', 'Elliot Crosby-McCullough', 'David Chelimsky') }
+    its(:contributor_names) { should include('marocchino') }
       
-      specify do
-        subject.contributor_realnames.length.should < subject.contributor_usernames.length
-      end
-    end
+    its(:default_branch) { should == 'master' }
     
-    describe '#contributor_names' do
-      specify do
-        subject.contributor_names.count.should == subject.contributors.count
-      end
-      
-      specify do
-        subject.contributor_names.should include('Iain Hecker', 'Elliot Crosby-McCullough', 'Aslak Hellesøy')
-      end
-      
-      specify do
-        subject.contributor_names.should include('marocchino')
-      end
-    end
+    its(:commits_feed_url) { should == 'https://github.com/aslakhellesoy/cucumber/commits/master.atom' }
   end
   
   context "initialized with colszowka/simplecov" do
@@ -94,76 +40,55 @@ describe GithubMetadata do
     end
     subject { @metadata }
 
-    describe '#user' do
-      specify do
-        subject.user.should == 'colszowka'
-      end
-    end
+    its(:user) { should == 'colszowka' }
+    its(:repo) { should == 'simplecov' }
     
-    describe '#repo' do
-      specify do
-        subject.repo.should == 'simplecov'
-      end
-    end
+    it { should_not have_wiki }
+    its(:wiki_pages) { should be_nil }
 
-    specify do
-      subject.should_not have_wiki
-    end
+    it { should have_issues }
+    its(:issues) { should == @raw.match(/Issues \((\d+)\)/)[1].to_i }
     
-    describe '#wiki_pages' do
-      specify do
-        subject.wiki_pages.should be nil
-      end
-    end
+    its(:pull_requests) { should == 0 }
     
-    specify do
-      subject.should have_issues
-    end
-
-    describe '#issues' do
-      specify do
-        expected = @raw.match(/Issues \((\d+)\)/)[1].to_i
-        subject.issues.should == expected
-      end
-    end
+    its("contributors.length") { should == @raw.match(/(\d+) contributors/)[1].to_i}
+    its(:contributors) { should be_all {|c| c.instance_of?(GithubMetadata::Contributor)} }
     
-    describe '#pull_requests' do
-      specify do
-        subject.pull_requests.should be 0
-      end
-    end
+    its(:contributor_usernames) { should include('colszowka') }
+    its(:contributor_realnames) { should include('Christoph Olszowka') }
+    its("contributor_names.count") { should == @metadata.contributors.count }
+    its(:contributor_names) { should include('Christoph Olszowka') }
+    
+    its(:default_branch) { should == 'master' }
     
-    describe '#contributors' do
-      specify do
-        expected = @raw.match(/(\d+) contributors/)[1].to_i
-        subject.contributors.length.should be expected
+    its(:commits_feed_url) { should == 'https://github.com/colszowka/simplecov/commits/master.atom' }
+    
+    context "recent_commits" do
+      before(:all) do
+        VCR.use_cassette('simplecov') do
+          @metadata.recent_commits
+        end
       end
+      subject { @metadata.recent_commits }
+
+      it { should have(20).items }
       
-      it 'should be all instance of Contributor' do
-        subject.contributors.should be_all {|c| c.instance_of?(GithubMetadata::Contributor)}
-      end
-    end
-    
-    describe '#contributor_usernames' do
-      specify do
-        subject.contributor_usernames.should include('colszowka')
+      context ".first" do
+        subject { @metadata.recent_commits.first }
+        
+        it { should be_a(GithubMetadata::Commit)}
+        its(:title) { should == 'Require simplecov-html ~> 0.4.3' }
+        its(:author) { should == 'Christoph Olszowka' }
+        its(:url) { should == 'https://github.com/colszowka/simplecov/commit/5ec4ca01255135234fe5b771ec3dd743a2b4ea1a' }
+        its("committed_at.utc") { should == Time.mktime(2011, 2, 25, 16, 26, 16).utc }
       end
     end
     
-    describe '#contributor_realnames' do
-      specify do
-        subject.contributor_realnames.should include('Christoph Olszowka')
-      end
+    it("should return last commit date for average_recent_committed_at(1)") do 
+      subject.average_recent_committed_at(1).should == Time.mktime(2011, 2, 25, 16, 25, 44).utc
     end
     
-    describe '#contributor_names' do
-      specify do
-        subject.contributor_names.count.should be subject.contributors.count
-      end
-      specify do
-        subject.contributor_names.should include('Christoph Olszowka')
-      end
-    end
+    its("average_recent_committed_at.to_i") { should == Time.mktime(2011, 2, 11, 1, 49, 14).to_i }
   end
 
   context "initialized with an invalid repo path" do
@@ -179,7 +104,13 @@ describe GithubMetadata do
   
   describe "fetch with invalid repo path" do
     it "should return nil and swallow the 404" do
-      GithubMetadata.fetch('colszowka', 'anotherfunkyrepo').should be nil
+      GithubMetadata.fetch('colszowka', 'anotherfunkyrepo').should be_nil
+    end
+  end
+  
+  describe "fetch with valid repo path" do
+    it "should be a GithubMetadata instance" do
+      GithubMetadata.fetch('colszowka', 'simplecov').should be_a(GithubMetadata)
     end
   end
 

data/spec/spec_helper.rb

@@ -7,3 +7,12 @@ require 'github_metadata'
 RSpec.configure do |config|
   # some (optional) config here
 end
+
+require 'vcr'
+
+VCR.config do |c|
+  c.allow_http_connections_when_no_cassette = true
+  c.default_cassette_options = { :record => :new_episodes }
+  c.cassette_library_dir = 'fixtures/vcr_cassettes'
+  c.stub_with :webmock # or :fakeweb
+end

metadata

@@ -1,12 +1,8 @@
 --- !ruby/object:Gem::Specification 
 name: github_metadata
 version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 1
-  - 1
-  version: 0.1.1
+  prerelease: 
+  version: 0.2.0
 platform: ruby
 authors: 
 - Christoph Olszowka
@@ -14,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-04 00:00:00 +01:00
+date: 2011-03-11 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,39 +21,75 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
-  name: rspec
+  name: feedzirra
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 2
-        - 0
-        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: i18n
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: rspec
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
         version: 2.0.0
   type: :development
-  version_requirements: *id002
+  version_requirements: *id004
 - !ruby/object:Gem::Dependency 
   name: simplecov
   prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.4.1
+  type: :development
+  version_requirements: *id005
+- !ruby/object:Gem::Dependency 
+  name: vcr
+  prerelease: false
+  requirement: &id006 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :development
-  version_requirements: *id003
+  version_requirements: *id006
+- !ruby/object:Gem::Dependency 
+  name: webmock
+  prerelease: false
+  requirement: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :development
+  version_requirements: *id007
 description: Extracts additional information like amount of committers, issues and wiki pages from Github repos
 email: 
 - christoph at olszowka de
@@ -71,7 +103,6 @@ files:
 - .gitignore
 - .rspec
 - Gemfile
-- Gemfile.lock
 - LICENSE
 - README.rdoc
 - Rakefile
@@ -94,21 +125,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 requirements: []
 
 rubyforge_project: github_metadata
-rubygems_version: 1.3.7
+rubygems_version: 1.5.3
 signing_key: 
 specification_version: 3
 summary: Extracts additional information from Github repos that isn't available via API

data/Gemfile.lock

@@ -1,31 +0,0 @@
-PATH
-  remote: .
-  specs:
-    github_metadata (0.1.0)
-      nokogiri
-
-GEM
-  remote: http://rubygems.org/
-  specs:
-    diff-lcs (1.1.2)
-    nokogiri (1.4.4)
-    rspec (2.4.0)
-      rspec-core (~> 2.4.0)
-      rspec-expectations (~> 2.4.0)
-      rspec-mocks (~> 2.4.0)
-    rspec-core (2.4.0)
-    rspec-expectations (2.4.0)
-      diff-lcs (~> 1.1.2)
-    rspec-mocks (2.4.0)
-    simplecov (0.3.7)
-      simplecov-html (>= 0.3.7)
-    simplecov-html (0.3.9)
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  github_metadata!
-  nokogiri
-  rspec (>= 2.0.0)
-  simplecov