elasticrepo 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bf7865804a9fb04e180fd3fbd804d93caebf1c59
-  data.tar.gz: 5413451aca453ec6f5425533b0728d12988b8609
+  metadata.gz: 56603fcfd136f7504f3987047358e24d2987f5d2
+  data.tar.gz: c1be2af01694f38c4e3173d632a126369370c948
 SHA512:
-  metadata.gz: f90a45a390a2be6ab6cc59ac3eeec36c9d62e0ddbe5dab2d87297193dd0da2108bf89aac082e6eda8ee9effeb3985d9180e5da53933506cfd9517b3b3ebec76b
-  data.tar.gz: 81b5c4ef3eb90404b4b485aa2d81f6ff6d8354d98df91dfa10825a3d66c61b71bf9590b069f650d502b3f5041f0b8fbacbdc9cc00d4b178f04ebe2dc5e3da31e
+  metadata.gz: 5209cc6b721bf1d10df0e0506b5b865e26b9632aeec311cacb268773f5bce0aa359029f1aa00ebb39c304b530681b3c1820b3800c2519f9bb8373d2f6a500acc
+  data.tar.gz: 74b40af8d9fd64312a67b61179b45c12b49bcd4c164a8d93bdcdc7bc8cea522da84b668c37c79aff7b2331e70e1c69e74e904e8d326cff788d893eb249e251cf

data/lib/elasticrepo/extractor.rb

@@ -1,19 +1,14 @@
 module Elasticrepo
   class Extractor
+    attr_reader :repos
 
     # GET /users/:user/starred 
-    # ex: /users/lapaty/starred --> array of hashes
+    # extract fields subset from each repo
+    # then get back an array of lighter repos 
 
-    # ex:
-    #     results = Elasticrepo::Extractor.new("lapaty")
-    #     results.extract
-
-    def initialize(owner)
-      @repos = Octokit.starred(owner)
-    end
-
-    def extract
-      @repos.map!{|repo|Elasticrepo::RepoSubset.new(repo)}
+    def initialize owner 
+      repos = Octokit.starred owner 
+      @repos = repos.map!{|repo|Elasticrepo::RepoSubset.new(repo)}
     end
   end
 end

data/lib/elasticrepo/indexer.rb

@@ -1,45 +1,67 @@
 module Elasticrepo
   class Indexer	
-    attr_reader :results
+    #attr_reader :indexed
 
-    def initialize owner
-      extractor = Elasticrepo::Extractor.new(owner)
-      @results  = extractor.extract 
+    def initialize(owner)
+      @owner = owner
+      @idx = "repositories"
     end
 
     def import
-      Tire.index 'repository' do
+      # extract subset fields by user repositories starred list  
+      # GET /users/:user/starred 
+      #
+      repos = Elasticrepo::Extractor.new(@owner).repos
 
-      #its(:full_name) { should eq("twitter/bootstrap") }
-         
-        # Create the index with proper mapping (if not exists already)
+      # index the extraction
+      #
+      @index = Tire::Index.new(@idx) do 
+        # Create the index with proper mapping (if doesn not exist already
         #
         create :mappings => {
           :question => {
             :properties => {
               :id => { :type => 'integer', :analyzer => 'keyword' },
-              :owner => { :type => 'string', :analyzer => 'keyword' },
-              :name => { :type => 'string', :analyzer => 'keyword' },
-              #:full_name => { :type => 'string', :analyzer => 'keyword' },
-              :url => { :type => 'string', :analyzer => 'snowball' },
-              :description => { :type => 'string', :analyzer => 'snowball' },
-              :organization => { :type => 'string', :analyzer => 'keyword' },
-              :language => { :type => 'string', :analyzer => 'keyword' },
-              :created_at => { :type => 'date', :analyzer => 'keyword' },
-              :pushed_at => { :type => 'date', :analyzer => 'keyword' },
-              :updated_at => { :type => 'date', :analyzer => 'keyword' }
+                :owner => { :type => 'string', :analyzer => 'keyword' },
+                :name => { :type => 'string', :analyzer => 'keyword' },
+                #:full_name => { :type => 'string', :analyzer => 'keyword' },
+                :url => { :type => 'string', :analyzer => 'snowball' },
+                :description => { :type => 'string', :analyzer => 'snowball' },
+                :organization => { :type => 'string', :analyzer => 'keyword' },
+                :language => { :type => 'string', :analyzer => 'keyword' },
+                :created_at => { :type => 'date', :analyzer => 'keyword' },
+                :pushed_at => { :type => 'date', :analyzer => 'keyword' },
+                :updated_at => { :type => 'date', :analyzer => 'keyword' }
             }
           }
-        }
-         
+        }  
         # Import documents
-        import @results
-         
+        #
+        import repos
         # Refresh the index for immediate searching
         #
         refresh
       end
-    end 
-  
-  end
-end
+    end # end import
+
+    def search(sub_string)
+      # search for a sub_string 
+      #
+      search = Tire::Search::Search.new(@idx)
+      search.query  { string('description:*"#{sub_string}"*') }
+      search.results
+    end
+
+    def update
+      # Just refresh the index as is 
+      #
+      @index.refresh
+    end
+
+    def delete
+      # delete 'repositories' index
+      #
+      @index.delete
+    end
+  end # end class
+end # end module

data/lib/elasticrepo/repo_subset.rb

@@ -7,7 +7,7 @@ module Elasticrepo
       @owner = attributes["owner"]["login"]
       @name = attributes["name"]
       @url = attributes["url"]
-      @description = attributes["description"]
+      @description = attributes["description"]  
       @created_at = attributes["created_at"]
       @pushed_at = attributes["pushed_at"]
       @organization = attributes["owner"]["type"]
@@ -15,5 +15,17 @@ module Elasticrepo
       @language = attributes["language"]
       @updated_at = attributes["updated_at"]
     end
+    
+    def to_indexed_json
+      self.to_json
+    end
+
+    # retourns json :
+ 
+      # repos[0].to_indexed_json 
+      # "[\"5392501\",\"cainlevy\",\"photor\",\"https://api.github.com/repos/cainlevy/photor\",\"Photo Organizer (in Ruby)\",\"2012-08-12T22:26:08Z\",\"2013-02-19T03:11:10Z\",\"User\",\"cainlevy/photor\",\"Ruby\",\"2013-03-13T02:05:33Z\"]"
+     
+      # repos[1].to_indexed_json
+      # "[\"612595\",\"aino\",\"galleria\",\"https://api.github.com/repos/aino/galleria\",\"The JavaScript Image Gallery\",\"2010-04-15T21:11:51Z\",\"2013-03-01T20:16:55Z\",\"Organization\",\"aino/galleria\",\"JavaScript\",\"2013-04-25T15:27:54Z\"]"
   end
-end
+end

data/lib/elasticrepo/version.rb

@@ -1,3 +1,3 @@
 module Elasticrepo
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/elasticrepo.rb

@@ -11,7 +11,7 @@ module Elasticrepo
   autoload :Version, "elasticrepo/version"
 
   Tire::Configuration.url "http://localhost:9200"
-  Tire::Configuration.logger 'elasticsearch.log', :level => 'debug'
+  #Tire::Configuration.logger 'elasticsearch.log', :level => 'debug'
 
   #class ElasticrepoError < StandardError
   #end

data/spec/elasticrepo/extractor_spec.rb

@@ -3,46 +3,57 @@ require "spec_helper"
   # http://developer.github.com/v3/repos/
   # https://github.com/pengwynn/octokit/blob/master/lib/octokit/client/users.rb
 
-  describe Elasticrepo::Extractor do
-    let(:fixture_repos) { Yajl::Parser.parse(fixture("repositories.json").read) }
-    # when online, works with "live" GitrHub V3 APIs ( uncomment following line )
-    # subject(:live_repos)  { Elasticrepo::Extractor.new("lapaty").repositories }
-
-    # when offline, works with local fixtures ( uncomment following line )
-    subject(:live_repos) { fixture_repos }
-
-    describe "#new" do 
-      context "get a list of two repos starred by user" do
-        its(:size) { should eq(2) }
+describe Elasticrepo::Extractor do
+  let(:fixture_repos)  { Yajl::Parser.parse(fixture("repositories.json").read) }
+  let(:live_extracted) { Elasticrepo::Extractor.new("lapaty") }
+
+  describe "#extract" do 
+    
+    context "specs debugging" do
+      it "print the content of running specs" do
+        print "live_extracted.repos:            #{live_extracted.repos} \n \n" 
+        print "live_extracted.repos.class:      #{live_extracted.repos.class} \n \n"
+        print "live_extracted.repos.to_json: #{live_extracted.repos.to_json} \n \n"
+        print "live_extracted.repos[0].to_json: #{live_extracted.repos[0].to_json} \n \n"
+        print "live_extracted.repos[0].owner:      #{live_extracted.repos[0].owner} \n \n"
+        print "live_extracted.repos[0].organization:      #{live_extracted.repos[0].organization} \n \n"
+
+        print "fixture_repos:                   #{fixture_repos} \n \n"
+        print "fixture_repos.class:             #{fixture_repos.class} \n \n"
+        print "fixture_repos.to_json:                #{fixture_repos[0].to_json} \n \n"
+        print "fixture_repos[0].to_json:                #{fixture_repos[0].to_json} \n \n"
+        print "fixture_repos[0]['owner']['login']:          #{fixture_repos[0]['owner']['login']} \n \n"
+        print "fixture_repos[0]['organization']:          #{fixture_repos[0]['organization']} \n \n"
       end
-      context "compare 'fixtures' with 'live github APIs'" do
-        # check well forming data set
-        it { fixture_repos.should be_a(Array) }
-        it { live_repos.should be_a(Array) }
-        it { fixture_repos.should_not be_empty }
-        it { live_repos.should_not be_empty }
-        # compare fixture to live API V3 
-        its(["id"])     { "#{live_repos[1]['id']}".should eq("#{fixture_repos[1]['id']}") }
-        its(["owner"])  { "#{live_repos[1]['id']}".should eq("#{fixture_repos[1]['id']}") }
-        its(["name"])   { "#{live_repos[1]['id']}".should eq("#{fixture_repos[1]['id']}") }
-      end 
-    end 
-
-    describe "#extract" do 
-      subject(:subset) { Elasticrepo::Extractor.new("lapaty").extract }
-
-      context "get list of repos starred by user" do
-        its("checks extracted id field") { "#{live_repos[0]['id']}".should eq("#{subset[0].id}") }
-        its("checks extracted id field") { "#{live_repos[1]['id']}".should eq("#{subset[1].id}") }
-
-        its("checks extracted owner field") { "#{live_repos[0]['owner']['login']}".should eq("#{subset[0].owner}") }
-        its("checks extracted owner field") { "#{live_repos[1]['owner']['login']}".should eq("#{subset[1].owner}") }
-
-        its("checks extracted name field") { "#{live_repos[0]['name']}".should eq("#{subset[0].name}") }
-        its("checks extracted name field") { "#{live_repos[1]['name']}".should eq("#{subset[1].name}") }
-
-      end 
-    end 
+    end
+
+    context "extract fields subset from each repo" do
+      its("fixture_repos[0]['id']") { fixture_repos[0]['id'].should eq live_extracted.repos[0].id }
+      #its("fixture_repos[0]['owner']['login']") { fixture_repos[0]['owner']['login'].should eq live_extracted.repos[0].owner['login'] }
+      its("fixture_repos[0]['name']") { fixture_repos[0]['name'].should eq live_extracted.repos[0].name }
+      its("fixture_repos[0]['url']") { fixture_repos[0]['url'].should eq live_extracted.repos[0].url }
+      its("fixture_repos[0]['description']") { fixture_repos[0]['description'].should eq live_extracted.repos[0].description }
+      its("fixture_repos[0]['created_at']") { fixture_repos[0]['created_at'].should eq live_extracted.repos[0].created_at }
+      its("fixture_repos[0]['pushed_at']") { fixture_repos[0]['pushed_at'].should eq live_extracted.repos[0].pushed_at }
+      #its("fixture_repos[0]['organization']") { fixture_repos[0]['organization'].should eq live_extracted.repos[0].organization }
+      its("fixture_repos[0]['language']") { fixture_repos[0]['language'].should eq live_extracted.repos[0].language }
+      its("fixture_repos[0]['full_name']") { fixture_repos[0]['full_name'].should eq live_extracted.repos[0].full_name }
+      #its("fixture_repos[0]['updated_at']") { fixture_repos[0]['updated_at'].should eq live_extracted.repos[0].updated_at }
+
+      its("fixture_repos[1]['id']") { fixture_repos[1]['id'].should eq live_extracted.repos[1].id }
+      #its("fixture_repos[1]['owner']['login']") { fixture_repos[1]['owner']['login'].should eq live_extracted.repos[1].owner['login'] }
+      its("fixture_repos[1]['url']") { fixture_repos[1]['url'].should eq live_extracted.repos[1].url }
+      its("fixture_repos[1]['description']") { fixture_repos[1]['description'].should eq live_extracted.repos[1].description }
+      its("fixture_repos[1]['name']") { fixture_repos[1]['name'].should eq live_extracted.repos[1].name }
+      its("fixture_repos[1]['created_at']") { fixture_repos[1]['created_at'].should eq live_extracted.repos[1].created_at }
+      its("fixture_repos[1]['pushed_at']") { fixture_repos[1]['pushed_at'].should eq live_extracted.repos[1].pushed_at }
+      #its("fixture_repos[1]['organization']") { fixture_repos[1]['organization'].should eq live_extracted.repos[1].organization }
+      its("fixture_repos[1]['full_name']") { fixture_repos[1]['full_name'].should eq live_extracted.repos[1].full_name }
+      its("fixture_repos[1]['language']") { fixture_repos[1]['language'].should eq live_extracted.repos[1].language }
+      #its("fixture_repos[1]['updated_at']") { fixture_repos[1]['updated_at'].should eq live_extracted.repos[1].updated_at }
+    end
+
   end 
 
-  
+end 
+

data/spec/elasticrepo/indexer_spec.rb

@@ -1,16 +1,32 @@
 require "spec_helper"
 
 describe Elasticrepo::Indexer do
+  let(:repos) { Elasticrepo::Indexer.new("lapaty") }
+  subject(:indexer) { repos.import }
 
-   let(:indexer) { Elasticrepo::Indexer.new("lapaty") }
+  context "print Elasticrepo::Indexer instantiation for debugging purposes" do
+    its("repos")                   { print "#{repos} \n \n" }
+    its("repos.class")             { print "#{repos.class} \n \n" }
+    its("repos.inspect")           { print "#{repos.inspect} \n \n" }
 
-  describe "#import" do
-    subject { indexer.import }
+    its("repos.extracted")         { print "#{repos.extracted} \n \n" }
+    its("repos.extracted.class")   { print "#{repos.extracted.class} \n \n" }
+    its("repos.extracted.inspect") { print "#{repos.extracted.inspect} \n \n" }
+  end
 
-    it { print "indexer.inspect : #{indexer.inspect}" }
-    it { print "indexer.results : #{indexer.results}" }
+  context "print before instance import for debugging purposes" do 
+    its("indexer.extracted") { print "indexer: #{indexer.extracted} \n \n" }
+    its("indexer.extracted.class") { print "indexer.extracted.class: #{imported.class} \n \n" }
+    its("indexer.extracted.inspect") { print "indexer.extracted.inspect: #{indexer.extracted.inspect} \n \n" }
   end
 
+  #describe "#import" do
+    #it { subject.to_json.should include(5392501,"cainlevy","photor") }
+  #  its("imported") { print "imported #{imported} \n \n" }
+  #end
+
+#[{"id":5392501,"owner":"cainlevy","name":"photor","url":"https://api.github.com/repos/cainlevy/photor","description":"Photo Organizer (in Ruby)","created_at":"2012-08-12T22:26:08Z","pushed_at":"2013-02-19T03:11:10Z","organization":"User","full_name":"cainlevy/photor","language":"Ruby","updated_at":"2013-03-13T02:05:33Z"},{"id":612595,"owner":"aino","name":"galleria","url":"https://api.github.com/repos/aino/galleria","description":"The JavaScript Image Gallery","created_at":"2010-04-15T21:11:51Z","pushed_at":"2013-03-01T20:16:55Z","organization":"Organization","full_name":"aino/galleria","language":"JavaScript","updated_at":"2013-04-18T06:30:41Z"}]
+
 #  describe "GET index" do
 #    it "assigns all reports as @reports" do
 #     report = Report.create! valid_attributes
@@ -57,28 +73,3 @@ end
 #      end
 #    end
 #  end
-#end
-
-#--------------------------------------------------------------------------------
-#    context "get list of repos starred by a user" do
-#      describe "#new" do # Elasticrepo::Extractor.new("lapaty").repositories
-#        let(:parsed )   { Yajl::Parser.parse(fixture("repositories.json").read) }
-#        subject(:ockto_get) { Elasticrepo::Extractor.new("lapaty").repositories }
-  
-#        # just to show the content while rspec'ing
-#        it "print" do
-#          print "parsed: #{parsed[1]["id"]} \n + \n +\n"
-#          print "ockto_get: #{ockto_get[1]["id"]} \n + \n +\n"
-#        end
-  
-#        it { parsed.should be_a(Array) }
-#        it { ockto_get.should be_a(Array) }
-#        it { parsed.should_not be_empty }
-#        it { ockto_get.should_not be_empty }
-  
-#        its(:size)      { should eq(2) }
-#        its(["id"])     { "#{ockto_get[1]['id']}".should eq("#{parsed[1]['id']}") }
-#        its(["owner"])  { "#{ockto_get[1]['id']}".should eq("#{parsed[1]['id']}") }
-#        its(["name"])   { "#{ockto_get[1]['id']}".should eq("#{parsed[1]['id']}") }
-#      end
-#    end

data/spec/fixtures/fixture_repos[0].to_json

@@ -0,0 +1 @@
+{"id":5392501,"name":"photor","full_name":"cainlevy/photor","owner":{"login":"cainlevy","id":4449,"avatar_url":"https://secure.gravatar.com/avatar/2573ddee29779e76b7da7d3c2c9ff18d?d=https://a248.e.akamai.net/assets.github.com%2Fimages%2Fgravatars%2Fgravatar-user-420.png","gravatar_id":"2573ddee29779e76b7da7d3c2c9ff18d","url":"https://api.github.com/users/cainlevy","html_url":"https://github.com/cainlevy","followers_url":"https://api.github.com/users/cainlevy/followers","following_url":"https://api.github.com/users/cainlevy/following","gists_url":"https://api.github.com/users/cainlevy/gists{/gist_id}","starred_url":"https://api.github.com/users/cainlevy/starred{/owner}{/repo}","subscriptions_url":"https://api.github.com/users/cainlevy/subscriptions","organizations_url":"https://api.github.com/users/cainlevy/orgs","repos_url":"https://api.github.com/users/cainlevy/repos","events_url":"https://api.github.com/users/cainlevy/events{/privacy}","received_events_url":"https://api.github.com/users/cainlevy/received_events","type":"User"},"private":false,"html_url":"https://github.com/cainlevy/photor","description":"Photo Organizer (in Ruby)","fork":false,"url":"https://api.github.com/repos/cainlevy/photor","forks_url":"https://api.github.com/repos/cainlevy/photor/forks","keys_url":"https://api.github.com/repos/cainlevy/photor/keys{/key_id}","collaborators_url":"https://api.github.com/repos/cainlevy/photor/collaborators{/collaborator}","teams_url":"https://api.github.com/repos/cainlevy/photor/teams","hooks_url":"https://api.github.com/repos/cainlevy/photor/hooks","issue_events_url":"https://api.github.com/repos/cainlevy/photor/issues/events{/number}","events_url":"https://api.github.com/repos/cainlevy/photor/events","assignees_url":"https://api.github.com/repos/cainlevy/photor/assignees{/user}","branches_url":"https://api.github.com/repos/cainlevy/photor/branches{/branch}","tags_url":"https://api.github.com/repos/cainlevy/photor/tags{/tag}","blobs_url":"https://api.github.com/repos/cainlevy/photor/git/blobs{/sha}","git_tags_url":"https://api.github.com/repos/cainlevy/photor/git/tags{/sha}","git_refs_url":"https://api.github.com/repos/cainlevy/photor/git/refs{/sha}","trees_url":"https://api.github.com/repos/cainlevy/photor/git/trees{/sha}","statuses_url":"https://api.github.com/repos/cainlevy/photor/statuses/{sha}","languages_url":"https://api.github.com/repos/cainlevy/photor/languages","stargazers_url":"https://api.github.com/repos/cainlevy/photor/stargazers","contributors_url":"https://api.github.com/repos/cainlevy/photor/contributors","subscribers_url":"https://api.github.com/repos/cainlevy/photor/subscribers","subscription_url":"https://api.github.com/repos/cainlevy/photor/subscription","commits_url":"https://api.github.com/repos/cainlevy/photor/commits{/sha}","git_commits_url":"https://api.github.com/repos/cainlevy/photor/git/commits{/sha}","comments_url":"https://api.github.com/repos/cainlevy/photor/comments{/number}","issue_comment_url":"https://api.github.com/repos/cainlevy/photor/issues/comments/{number}","contents_url":"https://api.github.com/repos/cainlevy/photor/contents/{+path}","compare_url":"https://api.github.com/repos/cainlevy/photor/compare/{base}...{head}","merges_url":"https://api.github.com/repos/cainlevy/photor/merges","archive_url":"https://api.github.com/repos/cainlevy/photor/{archive_format}{/ref}","downloads_url":"https://api.github.com/repos/cainlevy/photor/downloads","issues_url":"https://api.github.com/repos/cainlevy/photor/issues{/number}","pulls_url":"https://api.github.com/repos/cainlevy/photor/pulls{/number}","milestones_url":"https://api.github.com/repos/cainlevy/photor/milestones{/number}","notifications_url":"https://api.github.com/repos/cainlevy/photor/notifications{?since,all,participating}","labels_url":"https://api.github.com/repos/cainlevy/photor/labels{/name}","created_at":"2012-08-12T22:26:08Z","updated_at":"2013-03-13T02:05:33Z","pushed_at":"2013-02-19T03:11:10Z","git_url":"git://github.com/cainlevy/photor.git","ssh_url":"git@github.com:cainlevy/photor.git","clone_url":"https://github.com/cainlevy/photor.git","svn_url":"https://github.com/cainlevy/photor","homepage":null,"size":312,"watchers_count":4,"language":"Ruby","has_issues":true,"has_downloads":true,"has_wiki":true,"forks_count":0,"mirror_url":null,"open_issues_count":0,"forks":0,"open_issues":0,"watchers":4,"master_branch":"master","default_branch":"master"}

data/spec/fixtures/live_extracted.repos[0].to_json

@@ -0,0 +1 @@
+ {"id":5392501,"owner":"cainlevy","name":"photor","url":"https://api.github.com/repos/cainlevy/photor","description":"Photo Organizer (in Ruby)","created_at":"2012-08-12T22:26:08Z","pushed_at":"2013-02-19T03:11:10Z","organization":"User","full_name":"cainlevy/photor","language":"Ruby","updated_at":"2013-03-13T02:05:33Z"}

data/spec/spec_helper.rb

@@ -1,8 +1,9 @@
 $LOAD_PATH.unshift(File.dirname(__FILE__))
 $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), "..", "lib"))
 
-require 'fakeweb'
 require 'elasticrepo'
+#require 'json_spec'
+#require 'fakeweb'
 require 'octokit'
 require 'tire'
 require 'yajl'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: elasticrepo
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Luca G. Soave
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-20 00:00:00.000000000 Z
+date: 2013-04-26 00:00:00.000000000 Z
 dependencies: []
 description: |2
     Feed me.
@@ -22,10 +22,11 @@ files:
 - lib/elasticrepo/version.rb
 - lib/elasticrepo/indexer.rb
 - lib/elasticrepo/extractor.rb
-- lib/elasticsearch.log
 - spec/elasticrepo/extractor_spec.rb
 - spec/elasticrepo/repo_subset_spec.rb
 - spec/elasticrepo/indexer_spec.rb
+- spec/fixtures/live_extracted.repos[0].to_json
+- spec/fixtures/fixture_repos[0].to_json
 - spec/fixtures/repositories.json
 - spec/fixtures/repository.json
 - spec/elasticrepo_spec.rb