curate_tumblr 1.0.3

data/lib/curate_tumblr/utilities/utilities_format.rb

@@ -0,0 +1,91 @@
+module CurateTumblr
+
+  def self.get_format_ar_tumblrs_urls( ar_tumblrs_urls )
+    raise "ar_tumblrs_urls is a #{ar_tumblrs_urls.class} instead of Array" if !ar_tumblrs_urls.is_a? Array
+    ar_new_tumblrs_urls = []
+    ar_tumblrs_urls.each do |tumblr|
+      format_tumblr_url!( tumblr )
+      ar_new_tumblrs_urls << tumblr
+    end
+    ar_new_tumblrs_urls
+  end    
+
+  def self.get_format_tumblr_urls( tumblr_urls )
+    if tumblr_urls.is_a? Set
+      new_tumblr_urls = Set.new
+    else
+      new_tumblr_urls = []
+    end
+    tumblr_urls.each do |url|
+      new_url = url.dup
+      format_tumblr_url!( new_url )
+      new_tumblr_urls << new_url
+    end
+    new_tumblr_urls
+  end
+
+  def self.get_format_urls( urls )
+    if urls.is_a? Set
+      new_urls = Set.new
+    else
+      new_urls = []
+    end
+    urls.each do |url|
+      new_url = url.dup
+      format_url!( new_url )
+      new_urls << new_url
+    end
+    new_urls
+  end
+
+  def self.format_url!( url )
+    url.gsub!("target=\"_blank\"", "")
+    url.gsub!("href=\"", "")
+    url.gsub!("http://", "")
+    url.gsub!("https://", "")
+    url.gsub!("http%3A%2F%2F", "")
+    url.gsub!("\"", "")
+    url.gsub!('"', "")
+    url.chomp!
+    url.chomp!( " " )
+    url.lstrip!
+  end 
+  
+  def self.get_format_ar_urls( ar_urls )
+    raise "ar_urls is a #{ar_urls.class} instead of Array" if !ar_urls.is_a? Array
+    ar_new_urls = []
+    ar_urls.each do |url|        
+      format_url!( url )
+      ar_new_urls << url
+    end
+    ar_new_urls
+  end       
+
+  def self.get_format_ar_tumblr_urls( ar_urls )
+    raise "ar_urls is a #{ar_urls.class} instead of Array" if !ar_urls.is_a? Array
+    ar_new_urls = []
+    ar_urls.each do |url|        
+      format_tumblr_url!( url )
+      ar_new_urls << url
+    end
+    ar_new_urls
+  end 
+
+  def self.format_tumblr_url!( tumblr_url )
+    format_url!( tumblr_url )
+    tumblr_url.gsub!("tumblr.com/", "tumblr.com")
+    tumblr_url.gsub!("class=\"tumblr_blog\"", "")
+    tumblr_url.gsub!("tumblr_blog href=", "")
+    tumblr_url.gsub!("tumblr_blog", "")
+    tumblr_url.gsub!("post", "")
+    tumblr_url.gsub!("www.", "")
+  end     
+
+  def self.format_post_id( post_id )
+    post_id.gsub('/', '').chomp.strip  
+  end
+  
+  def self.format_post_reblog_key( key )
+    key.gsub('/', '').gsub('?', '').chomp.strip  
+  end          
+end    

data/lib/curate_tumblr/utilities/utilities_validate.rb

@@ -0,0 +1,54 @@
+module CurateTumblr
+  def self.hash_multiple_posts_valid?( hash_posts )
+    return false if hash_posts.nil? 
+    return false if !hash_posts.is_a? Hash
+    return false if !hash_posts.has_key?( 'posts' )
+    return false if !hash_posts['posts'].is_a? Array
+    true
+  end
+  
+  def self.hash_post_valid?( hash_post )
+    return false if !hash_post
+    return false if !hash_post.is_a?( Hash )
+    return false if !hash_post.has_key?( 'blog_name' )
+    return false if !hash_post.has_key?( 'id' )
+    true
+  end
+
+  def self.hash_id_valid?( hash_id )
+    return false if !hash_id.is_a? Hash
+    return false if !hash_id.has_key?( 'id' )    
+    return false if !post_id_valid?( hash_id['id'] )    
+    true
+  end
+    
+  def self.hash_url_valid?( hash_url )
+    return false if !hash_url.is_a? Hash
+    return false if !hash_url.has_key?( :tumblr_url )    
+    return false if !hash_url.has_key?( :post_id )
+    return false if !post_id_valid?( hash_url[:post_id] )    
+    true    
+  end    
+
+  def self.check_paths_ar_photos( ar_photos )
+    ar_photos.each do |path|
+      raise "path #{path} doesn't exist" if !File.exist?( path )
+    end
+  end   
+
+  def self.post_id_valid?( post_id )
+    return false if post_id.nil?
+    return false if !post_id
+    return false if post_id.is_a?( String ) && post_id.empty?
+    return false if post_id.is_a?( Integer ) && post_id.to_s.empty?
+    true
+  end
+
+  def self.reblog_key_valid?( reblog_key )
+    return false if reblog_key.nil?
+    return false if !reblog_key
+    return false if !reblog_key.is_a? String
+    return false if reblog_key.empty?
+    true
+  end    
+end    

data/lib/curate_tumblr/values.rb

@@ -0,0 +1,22 @@
+module CurateTumblr
+  STATE_PUBLISHED = "published"
+  STATE_DRAFT = "draft"
+  STATE_QUEUE = "queue"
+  STATE_PRIVATE = "private"
+
+  CLIENT_STATUS_OK = 200
+  CLIENT_STATUS_BAD_REQUEST = 400
+  CLIENT_STATUS_NOT_FOUND = 404
+  CLIENT_STATUS_RATE_LIMIT = 429
+  COUNT_ALERT_IF_TOO_MUCH_BAD_REQUESTS = 5 
+
+  DISPLAY_SLEEP_BEFORE = "("
+  DISPLAY_SLEEP_AFTER = ")"
+  DISPLAY_TUMBLR_POST = "+"
+  DISPLAY_TUMBLR_REBLOG = ">"
+  DISPLAY_TUMBLR_DELETE = "-"
+  DISPLAY_TUMBLR_FOLLOW = ":"
+  DISPLAY_TUMBLR_GETPOSTS = "?"
+
+  SANDBOX_POST_ID = 1 # for testing without sending to tumblr
+end

data/spec/curate_tumblr/curator_spec.rb

@@ -0,0 +1,36 @@
+require 'spec_helper'
+
+describe CurateTumblr::Curator do 
+
+  describe "config" do
+    it "get hash" do
+      oauth_consumer_key = RandomWord.nouns.next
+      oauth_consumer_secret = RandomWord.nouns.next
+      oauth_token = RandomWord.nouns.next
+      oauth_token_secret = RandomWord.nouns.next
+      infos_name = RandomWord.nouns.next
+      hash_config = {}
+        hash_config.merge!( CurateTumblr::Tumblr::Client::get_client_config_hash( oauth_consumer_key, oauth_consumer_secret, oauth_token, oauth_token_secret ) )
+        hash_config.merge!( CurateTumblr::Tumblr::Infos::get_infos_config_hash )
+      expect { CurateTumblr::Curator.check_config_hash( hash_config ) }.to_not raise_error
+    end
+
+    it "empty" do
+      expect { CurateTumblr::Curator.check_config_hash( { 
+        CurateTumblr::Tumblr::Client::HASH_CONFIG_CLIENT => {},
+        CurateTumblr::Tumblr::Infos::HASH_CONFIG_INFOS => {},
+      } ) }.to raise_error
+    end
+
+    it "get document yaml" do
+      string_yaml = CurateTumblr::Curator.get_string_yaml_from_config( get_random_config_hash )
+      string_yaml.should be_true
+      string_yaml.empty?.should_not be_true
+      documents = YAML::load_documents( string_yaml )
+      documents.is_a?( Array ).should be_true
+      documents.count.should eq( 1 )
+      hash_config = documents.first
+      expect { CurateTumblr::Curator.check_config_hash( hash_config ) }.to_not raise_error
+    end
+  end
+end  

data/spec/curate_tumblr/publish/follow_spec.rb

@@ -0,0 +1,183 @@
+require 'spec_helper'
+
+describe CurateTumblr::Publish::Follow do 
+  include_context "shared targets"
+  include_context "shared links"
+  include_context "shared tags"
+  include_context "shared caption post"
+  let(:curator) { FactoryGirl.build( :curator ) }
+
+  describe "to follow after" do
+  	it "should follow all links in caption when no source" do
+      ar_links = curator.send( :add_tofollow_tumblr_links_from_caption, caption )
+      ar_links.count.should eq( ar_links_caption_tumblrs.count )
+      ar_links_caption_tumblrs.each { |link| ar_links.include?( link ).should be_true }
+      curator.all_tofollow_urls.count.should eq( ar_links_caption_tumblrs.count )
+    end
+
+    it "should follow links in caption but not the source" do
+      ar_links = curator.send( :add_tofollow_tumblr_links_from_caption, caption, source )
+      ar_links_caption_tumblrs.each { |link| ar_links.include?( link ).should be_true }
+      ar_links.count.should eq( ar_links_caption_tumblrs.count )
+      curator.all_tofollow_urls.count.should eq( ar_links_caption_tumblrs.count - 1 )
+    end   
+
+    it "direct extract tumblr links in curation" do
+      curator.all_tofollow_urls.count.should eq( 0 )
+      curator.reblog_and_extract( link_follow )
+
+      curator.count_rebloged.should eq( 1 )
+      curator.all_tofollow_urls.count.should eq( count_caption_links_to_follow + 1 )
+    end
+
+    it "check tofollow tumblrs are not post urls" do
+      ar_tofollow = get_random_ar_tumblrs( 4 )
+      ar_tofollow.each do |link|
+        CurateTumblr::Tumblr::ExtractLinks.simple_tumblr_url?( link ).should eq( true )
+        CurateTumblr::Tumblr::ExtractLinks.tumblr_url?( link ).should eq( true )
+        CurateTumblr::Tumblr::ExtractLinks.tumblr_post_url?( link ).should eq( false )
+      end
+    end
+
+    it "add tofollow tumblrs" do
+    	ar_tofollow = get_random_ar_tumblrs( 4 )
+    	ar_tofollow.each do |link|
+    		curator.reblog_and_extract( link )
+    	end
+    	curator.all_tofollow_urls.count.should eq( ar_tofollow.count )
+    	ar_tofollow.each { |link| curator.all_tofollow_urls.include?( link ).should be_true }
+    end
+
+    it "add tofollow from post tumblrs" do
+    	ar_tofollow = [ "likeafieldmouse.tumblr.com", "mother-natureson.tumblr.com", "fuck-mefood.tumblr.com", "unpopuler.tumblr.com" ]
+    	ar_tumblrs_posts = [ "http://likeafieldmouse.tumblr.com/post/56880391419/adrian-velazco", "http://likeafieldmouse.tumblr.com/post/56878573508/nicolai-howalt-boxers-before-and-after-the", "http://mother-natureson.tumblr.com/post/56880589244/unpopuler-my-blog-will-make-you-smile"]
+    	ar_tumblrs_posts.each do |post|
+    		curator.reblog_and_extract( post )
+    	end
+    	curator.all_tofollow_urls.count.should eq( ar_tofollow.count )
+    	ar_tofollow.each { |link| curator.all_tofollow_urls.include?( link ).should be_true }
+    end    
+  end
+
+  describe "add follow links to file" do
+    it "puts links in file" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      
+      count_follow = curator.count_followed
+      urls_tofollow = [ "tofollow1.tumblr.com", "tofollow2.tumblr.com", "tofollow3.tumblr.com"]
+      
+      urls_tofollow.each { |url| curator.add_tofollow_url( url ) }
+      curator.add_tofollow_tofile 
+      
+      File.exists?( curator.get_filename_tofollow ).should eq( true )
+      all_tofollow_urls = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      all_tofollow_urls.count.should eq( urls_tofollow.count )
+      urls_tofollow.each { |link| all_tofollow_urls.include?( link + "\n" ).should be_true }
+    end
+
+    it "keep links already in file" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      
+      urls_tofollow = [ "tofollow1.tumblr.com", "tofollow2.tumblr.com", "tofollow3.tumblr.com"]
+      urls_infile = [ "already1.tumblr.com", "already2.tumblr.com" ]
+
+      File.open( curator.get_filename_tofollow, "w+" ) { |file| file.puts( urls_infile ) }
+      CurateTumblr.get_ar_from_file( curator.get_filename_tofollow ).count.should eq( urls_infile.count )
+
+      urls_tofollow.each { |url| curator.add_tofollow_url( url ) }
+      curator.add_tofollow_tofile 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( urls_infile.count + urls_tofollow.count )
+      urls_infile.each { |link| ar_tofollow.include?( link + "\n" ).should be_true }
+      urls_tofollow.each { |link| ar_tofollow.include?( link + "\n" ).should be_true }
+      curator.all_tofollow_urls.count.should eq( 0 )
+    end        
+
+    it "dont put link in file if already exists" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      
+      urls_tofollow = [ "tofollow1.tumblr.com", "tofollow2.tumblr.com", "tofollow3.tumblr.com"]
+      url_tonotfollow = "tofollow2.tumblr.com"
+
+      File.open( curator.get_filename_tofollow, "w+" ) { |file| file.puts( url_tonotfollow ) }
+      CurateTumblr.get_ar_from_file( curator.get_filename_tofollow ).count.should eq( 1 )
+
+      urls_tofollow.each { |url| curator.add_tofollow_url( url ) }
+      curator.add_tofollow_tofile 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( urls_tofollow.count )
+      urls_tofollow.each { |link| ar_tofollow.include?( link + "\n" ).should be_true }
+    end  
+  end
+
+	describe "follow" do  
+		it "url" do
+			curator.count_followed.should eq( 0 )
+			curator.follow_url( "photonotdead.tumblr.com" )
+			curator.count_followed.should eq( 1 )
+		end
+  end
+
+  describe "from file" do
+    it "put direct tofollow in file" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      File.open( curator.get_filename_tofollow, 'w' ) { }
+
+      ar_links = curator.send( :add_tofollow_tumblr_links_from_caption, caption )
+      curator.add_tofollow_tofile 
+      ar_links.count.should eq( ar_links_caption_tumblrs.count ) 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( ar_links_caption_tumblrs.count )
+      ar_links_caption_tumblrs.each { |link| ar_tofollow.include?( link + "\n" ).should be_true  }
+    end   
+
+    it "follow from a caption true post1" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      File.open( curator.get_filename_tofollow, 'w' ) { }
+
+      ar_links_caption = ["afleshfesten.tumblr.com"]
+      hash_post = curator.get_hash_post( "creve-coeur.tumblr.com", 49454185206 )
+      CurateTumblr.hash_post_valid?( hash_post ).should be_true
+      curator.extract_links_caption_from_post( hash_post ).should be_true
+      curator.add_tofollow_tofile 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( ar_links_caption.count )
+      ar_links_caption.each { |link| ar_tofollow.include?( link + "\n" ).should be_true  }
+    end
+
+    it "follow from a caption true post2" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      File.open( curator.get_filename_tofollow, 'w' ) { }
+
+      ar_links_caption = [ "photonotdead.tumblr.com", "classy-as-fcuk.tumblr.com", "crystvllized.tumblr.com", "worldofadvice.tumblr.com" ]
+
+      hash_post = curator.get_hash_post( "photonotdead.tumblr.com", 55108093006 )
+      CurateTumblr.hash_post_valid?( hash_post ).should be_true
+      curator.extract_links_caption_from_post( hash_post ).should be_true
+      curator.add_tofollow_tofile 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( ar_links_caption.count )
+      ar_links_caption.each { |link| ar_tofollow.include?( link + "\n" ).should be_true  }
+    end
+
+    it "follow from a caption true post3" do
+      File.delete( curator.get_filename_tofollow ) if File.exists?( curator.get_filename_tofollow )
+      File.open( curator.get_filename_tofollow, 'w' ) { }
+        
+      ar_links_caption = [ "we-melancholy-dreams.tumblr.com", "palejizz.tumblr.com", "sinnerer.tumblr.com" ]
+      hash_post = curator.get_hash_post( "melancholicbeautyofsadness.tumblr.com", 55115100145 )
+      CurateTumblr.hash_post_valid?( hash_post ).should be_true
+      curator.extract_links_caption_from_post( hash_post ).should be_true
+      curator.add_tofollow_tofile 
+
+      ar_tofollow = CurateTumblr.get_ar_from_file( curator.get_filename_tofollow )
+      ar_tofollow.count.should eq( ar_links_caption.count )
+      ar_links_caption.each { |link| ar_tofollow.include?( link + "\n" ).should be_true  }
+    end
+	end
+end  

data/spec/curate_tumblr/publish/post_spec.rb

@@ -0,0 +1,45 @@
+require 'spec_helper'
+
+describe CurateTumblr::Publish::Post do 
+  include_context "shared targets"
+  let(:curator) { FactoryGirl.build( :curator ) }
+
+  describe "get infos post" do
+    it "hash post from tumblr and id post" do
+      hash_post = curator.get_hash_post( target_tumblr, target_post_id )      
+      hash_post.should_not be_nil
+      hash_post.should_not be_false
+      hash_post.is_a?( Hash ).should be_true
+      CurateTumblr.hash_post_valid?( hash_post ).should be_true
+      hash_post["blog_name"].should eq( target_name )
+      hash_post["id"].to_s.should eq( target_post_id )
+    end
+
+    it "extract hash url from post url" do
+      hash_url = CurateTumblr.get_hash_url_from_post_url( target_post_url )
+      hash_url.should be_true
+      hash_url[:tumblr_url].should eq( target_tumblr )
+      hash_url[:post_id].should eq( target_post_id )
+    end
+
+    it "no hash url from bad post url" do
+      hash_url = CurateTumblr.get_hash_url_from_post_url( bad_target_post_url )
+      hash_url.should be_false
+    end
+  end
+
+  describe "post" do
+    it "text" do
+      curator.post_in_published
+      curator.count_posted.should eq( 0 )
+      curator.all_published_id.count.should eq( curator.count_posted )
+
+      id = curator.post_text( get_post_title, get_post_text )
+      id.should_not be_nil
+      id.should be_true
+      id.is_a?( Integer ).should be_true    
+      curator.count_posted.should eq( 1 )
+      curator.all_published_id.count.should eq( curator.count_posted )
+    end
+  end  
+end

data/spec/curate_tumblr/publish/reblog_spec.rb

@@ -0,0 +1,118 @@
+require 'spec_helper'
+
+describe CurateTumblr::Publish::Reblog do 
+  include_context "shared targets"
+  include_context "shared links"
+  include_context "shared tags"
+  let(:curator) { FactoryGirl.build( :curator ) }
+
+  describe "reblog link" do
+    let(:tumblr_url) { "youknow-thisistheend.tumblr.com" }
+    let(:post_url) {  "http://youknow-thisistheend.tumblr.com/post/54773810226/facebook-auf-we-heart-it" }
+    let(:post_reblog_url) {  "http://www.tumblr.com/reblog/54773810226/HXKbdnPG?redirect_to=http%3A%2F%2Fterryrichardson.tumblr.com%2Fpost%2F221532252&source=iframe" }
+    let(:post_id) {  "54773810226" }
+    let(:post_reblog_key) {  "HXKbdnPG" }
+
+    context "direct reblog url" do
+      it "hash post from reblog url" do
+        post_reblog_id = CurateTumblr::Tumblr::ExtractLinks.get_post_id_from_reblog_url( post_reblog_url )
+        post_reblog_id.should eq( post_id )
+        
+        hash_post = curator.get_hash_post( tumblr_url, post_id )
+        CurateTumblr.hash_post_valid?( hash_post ).should be_true
+        hash_post["id"].to_s.should eq( post_reblog_id )
+    
+        reblog_key1 = CurateTumblr.get_reblog_key_from_hash_post( hash_post )   
+        reblog_key1.should eq( post_reblog_key )
+        
+        reblog_key2 = CurateTumblr::Tumblr::ExtractLinks.get_reblog_key_from_reblog_url( post_reblog_url )      
+        reblog_key2.should eq( post_reblog_key )
+        
+        curator.send( :reblog_post_key, post_reblog_id, reblog_key2 ).should be_true  
+      end
+
+      it "get post id 1" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_post_id_from_reblog_url( target_reblog_url )
+        id.should eq ( target_reblog_id )
+      end
+
+      it "get reblog key 1" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_reblog_key_from_reblog_url( target_reblog_url )
+        id.should eq ( target_reblog_key )
+      end
+      
+      it "reblog  1" do
+        count = curator.count_rebloged
+        id = curator.reblog_and_extract( target_reblog_url )
+        id.should_not be_nil
+        id.should be_true
+        id.is_a?( Integer ).should be_true              
+        curator.count_rebloged.should eq( count+1 )
+        curator.all_published_id.count.should eq( curator.count_rebloged )
+      end
+
+      it "get post id 2" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_post_id_from_reblog_url( target_reblog_url2 )
+        id.should eq ( target_reblog_id2 )
+      end
+          
+      it "get reblog key 2" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_reblog_key_from_reblog_url( target_reblog_url2 )
+        id.should eq ( target_reblog_key2 )
+      end
+              
+      it "reblog 2" do
+        count = curator.count_rebloged
+        id = curator.reblog_and_extract( target_reblog_url2 )    
+        id.should_not be_nil
+        id.should be_true
+        id.is_a?( Integer ).should be_true              
+        curator.count_rebloged.should eq( count+1 )
+        curator.all_published_id.count.should eq( curator.count_rebloged )
+      end
+     
+      it "get post id 3" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_post_id_from_reblog_url( target_reblog_url3 )
+        id.should eq ( target_reblog_id3 )
+      end
+    
+      it "get reblog key 3" do
+        id = CurateTumblr::Tumblr::ExtractLinks.get_reblog_key_from_reblog_url( target_reblog_url3 )
+        id.should eq ( target_reblog_key3 )
+      end
+          
+      it "reblog 3" do
+        count = curator.count_rebloged
+        id = curator.reblog_and_extract( target_reblog_url3 )    
+        id.should_not be_nil
+        id.should be_true
+        id.is_a?( Integer ).should be_true              
+        curator.count_rebloged.should eq( count+1 )    
+        curator.all_published_id.count.should eq( curator.count_rebloged )
+      end
+  end
+
+
+  context "from url link" do
+    it "get url source from post" do
+      url_tumblr = "marseraki.tumblr.com"
+      id_post = "55357197864"
+      url_source = "http://d-rogue.tumblr.com"
+      hash_post = curator.get_hash_post( url_tumblr, id_post )
+      hash_post.should be_true
+      CurateTumblr.get_source_from_hash_post( hash_post ).should eq( url_source )
+    end
+
+    it "get url link from post" do
+      url_tumblr = "marseraki.tumblr.com"
+      id_post = "55357197864"
+      url_link = "http://cutbeneathourhands.tumblr.com/"
+      hash_post = curator.get_hash_post( url_tumblr, id_post )
+      hash_post.should be_true
+      CurateTumblr.get_link_url_from_hash_post( hash_post ).should eq( url_link )
+    end  
+  end
+
+
+  end  
+end