isrc 1.0.2 → 1.0.3

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    NjRhOTMyZWJiMzZiNjg5YzVjYTNjNTgzYzk5MTZjMjEyOGM4Njc3Mg==
-  data.tar.gz: !binary |-
-    ZmRiYTg5YWQzYTg4OWIzNzU5NDI3YTU5YmQ3OTA5MWVmZWZlMDRkNg==
+SHA1:
+  metadata.gz: bd97834b5c09da196ffc4e68c34b6be56cc63ed7
+  data.tar.gz: 0159b3fe894a23048a316f50818e3dc83b6fdc97
 SHA512:
-  metadata.gz: !binary |-
-    NTk2NDcwMjBlYzIxMmRiM2FjODY0MzNmNGJkODBjZGExYzY3MzJhNjNlNTUx
-    OGRlMWU3ZTE5MjM3OWNhNWY0ODJlNDYwNWMyOTU4MTNmNmViMjRkZTRhYTQ2
-    OTIwMTc2YWRiMDJhZjE1NzI0MDU2MTk1OWJmYzhiODNmODMzNTc=
-  data.tar.gz: !binary |-
-    YTZiMmFmMDkxNTQ5OWVlNGE0NGJlNmE5ZjUzMzlkNzJlMzRiNTJlYTk4MjM1
-    MWNhYzIxYTc5NTFjZGZlNmJhYzg3NWJkNjE5Y2E2NTkwMDUxMmFlNGYzYmYx
-    NDc3OGI1N2NjYmUxYTI0MTdjZDA0NDhlOTBlZTAzYmUwMzBjMzU=
+  metadata.gz: da759b2fdeb7f8e97e593002ca9ab2c3aa2f9cfff4f12b68614e1c6a4384c499dc7df87458a8862856dbef0ba8791ef55a0a6b92825fd2a095700e5cbd1184cd
+  data.tar.gz: a1c1f55955dbcacca8d21f4c0adadfe179395a478370f3522dfa1e284dba66712b0104d62f0fa31a006e723be055d841a93a53dad5111760d3bc2c1cd583f49a

data/lib/isrc.rb

@@ -9,86 +9,57 @@ module ISRC
   PPLUK_SESSION_GRAB_URL = 'http://repsearch.ppluk.com/ARSWeb/appmanager/ARS/main'
   PPLUK_AJAX_SEARCH_URL = 'http://repsearch.ppluk.com/ARSWeb/block/send-receive-updates'
 
+  def self.configure(&block)
+    ISRC::Configuration.instance_eval(&block)
+  end
+
   class PPLUK
     def retrieve(opts)
-      # default options
-      opts = { :title_size => 2 }.merge(opts)
+      # NOTE the online search is a bit funky: adding more to the search make the results worse
+      # trying out a three word limit
 
-      agent = Mechanize.new
-      agent.log = Logger.new "mech.log"
-      agent.user_agent_alias = 'Mac Safari'
+      pieces = self.extract_song_peices(opts[:title])
 
-      isrc_session_init = agent.get PPLUK_SESSION_GRAB_URL
-      view_state = self.extract_view_state(isrc_session_init.body)
-      ice_session, ice_session_count = self.extract_ice_session(isrc_session_init.body)
+      # try the first two pieces at first
 
-      # add the ice_sessions cookie
-      ice_cookie = Mechanize::Cookie.new('ice.sessions', "#{ice_session}##{ice_session_count}")
-      ice_cookie.path = "/"
-      ice_cookie.domain = "repsearch.ppluk.com"
-      agent.cookie_jar.add!(ice_cookie)
+      # if the song is only one word, submit request with on processing
+      if pieces[:all].size == 1
+        @matches = self.request(opts)
+      elsif pieces[:all].size > 1
+        # let's try increasing the number of pieces, starting from 2
+        pieces_count = 1
 
-      # NOTE the online search is a bit funky: adding more to the search make the results worse
-      # trying out a three word limit
+        begin
+          pieces_count += 1
 
-      title_pieces = extract_song_peices(opts[:title])
-      shortened_title = title_pieces.slice(0, [opts[:title_size], title_pieces.size].min).join(' ')
-
-      # puts "Title: #{shortened_title}\nArtist: #{opts[:artist]}"
-
-      begin
-        isrc_search = agent.post PPLUK_AJAX_SEARCH_URL, {
-          'ice.submit.partial' => 'false',
-          # 'ice.event.target' => 'T400335881332330323192:ars_form:search_button',
-          # 'ice.event.captured' => 'T400335881332330323192:ars_form:search_button',
-          # 'ice.event.type' => 'onclick',
-          # 'ice.event.alt' => 'false',
-          # 'ice.event.ctrl' => 'false',
-          # 'ice.event.shift' => 'false',
-          # 'ice.event.meta' => 'false',
-          # 'ice.event.x' => '47',
-          # 'ice.event.y' => '65',
-          # 'ice.event.left' => 'false',
-          # 'ice.event.right' => 'false',
-          'T5000782701386267377497:ars_form:search_button' => 'Search',
-          'T5000782701386267377497:ars_form:isrc_code' => '',
-          'T5000782701386267377497:ars_form:rec_title_idx' => '',
-          'T5000782701386267377497:ars_form:rec_title' => shortened_title,
-          'T5000782701386267377497:ars_form:rec_band_artist_idx' => '',
-          'T5000782701386267377497:ars_form:rec_band_artist' => opts[:artist],
-          'javax.faces.RenderKitId' => 'ICEfacesRenderKit',
-          'javax.faces.ViewState' => view_state,
-          'icefacesCssUpdates' => '',
-          'T5000782701386267377497:ars_form' => '',
-          'ice.session' => ice_session,
-          'ice.view' => view_state,
-          'ice.focus' => '',
-
-          # the rand is 19 characters long in the browser's HTTP requests
-          'rand' => sprintf('%1.17f', rand)
-        }
-      rescue Mechanize::ResponseCodeError => e
-        agent.log.error "Error submitting AJAX request: #{e.page.body}"
-      end
+          shortened_title = pieces[:all].slice(0, pieces_count).join(' ')
 
-      # creates an array representation of the table:
-      #   artist, title, isrc, rights holder, released, time
-      isrc_html = Nokogiri::HTML(isrc_search.body)
-      @matches = isrc_html.css("table[id='T5000782701386267377497:ars_form:searchResultsTable'] tbody tr").map do |m|
-        columns = m.css('td')
+          @matches = self.request({
+            title: shortened_title,
+            artist: opts[:artist]
+          })
+        end while @matches.empty? && pieces[:all].size > pieces_count + 1
 
-        # if there is no ISRC don't bother looking
-        next if columns[2] == 'Not Supplied'
+        # given 'Surrender [Original Mix]' the above algorithm will submit the entire title
+        # if that didn't work, strip out all meta elements and try greatest to least number of song pieces
 
-        # zero length music wont be used
-        next if columns[-1] == '0:00sec'
+        # TODO we shouldn't allow one letter or two letter title requests
+        # TODO remove stop words
+        # TODO detect when meta == title pieces
 
-        columns.map &:text
-      end
+        pieces_count = pieces[:title].size
+
+        while @matches.empty? && pieces_count > 0
+          shortened_title = pieces[:title].slice(0, pieces_count).join(' ')
+
+          @matches = self.request({
+            title: shortened_title,
+            artist: opts[:artist]
+          })
+
+          pieces_count -= 1
+        end
 
-      # if the shortened title did not work, try making it longer
-      if @matches.empty? && opts[:title_size] < title_pieces.size
-        self.retrieve(opts.merge({:title_size => opts[:title_size] + 1}))
       end
     end
 
@@ -132,9 +103,20 @@ module ISRC
 
     protected
       def extract_song_peices(title)
-        title_pieces = title.split(/(\([^)]+\)|\[[^\]]+\])/).reject { |s| s.strip.empty? }
-        title_pieces[0] = title_pieces[0].split(' ')
-        title_pieces.flatten
+        # this splits a song title into peices:
+        #   * 'bracket' peice (meta)
+        #   * 'parenthesis' peice (meta)
+        #   * song words (title)
+
+        all_pieces = title.split(/(\([^)]+\)|\[[^\]]+\])/).reject { |s| s.strip.empty? }
+        title_pieces = all_pieces.shift.split(' ')
+        meta_pieces = all_pieces
+
+        {
+          all: [title_pieces, meta_pieces].flatten,
+          meta: meta_pieces,
+          title: title_pieces
+        }
       end
 
       def extract_view_state(body)
@@ -151,5 +133,76 @@ module ISRC
         minutes.to_i * 60 + seconds.to_i
       end
 
+      def request(opts = {})
+        puts "Title: #{opts[:title]}\nArtist: #{opts[:artist]}"
+
+        agent = Mechanize.new
+        # TODO log path needs to be configurable
+        agent.log = Logger.new "mech.log"
+        agent.user_agent_alias = 'Mac Safari'
+
+        # grab the main page HTML to pull session vars to make the AJAX request
+        isrc_session_init = agent.get(PPLUK_SESSION_GRAB_URL)
+        view_state = self.extract_view_state(isrc_session_init.body)
+        ice_session, ice_session_count = self.extract_ice_session(isrc_session_init.body)
+
+        # add the ice_sessions cookie for the AJAX search request
+        ice_cookie = Mechanize::Cookie.new('ice.sessions', "#{ice_session}##{ice_session_count}")
+        ice_cookie.path = "/"
+        ice_cookie.domain = "repsearch.ppluk.com"
+        agent.cookie_jar.add!(ice_cookie)
+
+        begin
+          isrc_search = agent.post PPLUK_AJAX_SEARCH_URL, {
+            'ice.submit.partial' => 'false',
+            # 'ice.event.target' => 'T400335881332330323192:ars_form:search_button',
+            # 'ice.event.captured' => 'T400335881332330323192:ars_form:search_button',
+            # 'ice.event.type' => 'onclick',
+            # 'ice.event.alt' => 'false',
+            # 'ice.event.ctrl' => 'false',
+            # 'ice.event.shift' => 'false',
+            # 'ice.event.meta' => 'false',
+            # 'ice.event.x' => '47',
+            # 'ice.event.y' => '65',
+            # 'ice.event.left' => 'false',
+            # 'ice.event.right' => 'false',
+            'T5000782701386267377497:ars_form:search_button' => 'Search',
+            'T5000782701386267377497:ars_form:isrc_code' => '',
+            'T5000782701386267377497:ars_form:rec_title_idx' => '',
+            'T5000782701386267377497:ars_form:rec_title' => opts[:title],
+            'T5000782701386267377497:ars_form:rec_band_artist_idx' => '',
+            'T5000782701386267377497:ars_form:rec_band_artist' => opts[:artist],
+            'javax.faces.RenderKitId' => 'ICEfacesRenderKit',
+            'javax.faces.ViewState' => view_state,
+            'icefacesCssUpdates' => '',
+            'T5000782701386267377497:ars_form' => '',
+            'ice.session' => ice_session,
+            'ice.view' => view_state,
+            'ice.focus' => '',
+
+            # the rand is 19 characters long in the browser's HTTP requests
+            'rand' => sprintf('%1.17f', rand)
+          }
+        rescue Mechanize::ResponseCodeError => e
+          agent.log.error "Error submitting AJAX request: #{e.page.body}"
+        end
+
+        # creates an array representation of the table:
+        #   artist, title, isrc, rights holder, released, time
+
+        isrc_table = Nokogiri::HTML(isrc_search.body).css("table[id='T5000782701386267377497:ars_form:searchResultsTable'] tbody tr")
+        isrc_table.map do |m|
+          columns = m.css('td')
+
+          # if there is no ISRC don't bother looking
+          next if columns[2] == 'Not Supplied'
+
+          # zero length music wont be used
+          next if columns[-1] == '0:00sec'
+
+          columns.map &:text
+        end
+      end
+
   end
 end

data/lib/isrc/version.rb

@@ -1,3 +1,3 @@
 module ISRC
-  VERSION = "1.0.2"
+  VERSION = "1.0.3"
 end

data/spec/isrc_spec.rb

@@ -29,6 +29,16 @@ describe ISRC do
       # however, the length delta is huge
     end
 
+    it "handles results with brackets" do
+      isrc.retrieve artist: 'Curiosity Killed The Cat', title: 'Down to Earth'
+      isrc.match(time:'03:54')[:isrc].should == 'GBF088600037'
+    end
+
+    it 'handles a mixed version of a song when there is not a mixed version listed' do
+      isrc.retrieve artist:'Kings of Leon', title: 'Use Somebody (Chew Fu Festival Fix)'
+      isrc.match(time:'5:37')[:isrc].should == 'USRC10800301'
+    end
+
     it "handles edge cases that don't make sense" do
       isrc.retrieve artist:'Toni Braxton', title:'Youre Making me High'
       isrc.match(time:'4:12')[:isrc].should == 'USLF29600183'
@@ -49,17 +59,22 @@ describe ISRC do
   end
 
   context "song title processing" do
-    it "should handle bracket mixes" do
-      pieces = isrc.send(:extract_song_peices, "Surrender [Original Mix]")
-      pieces.size.should == 2
-      pieces.last.should == "[Original Mix]"
+    context 'of brackets' do
+      it "should parse them correctly with a one word song" do
+        pieces = isrc.send(:extract_song_peices, "Surrender [Original Mix]")
+        pieces[:all].size.should == 2
+        pieces[:all].last.should == "[Original Mix]"
+        pieces[:meta].size.should == 1
+      end
     end
 
     context 'of parenthesis' do
       it "should count parenthesis as a single song peice" do
         pieces = isrc.send(:extract_song_peices, "Want Me (Like Water) (New Vocal Mix No 1)")
-        pieces.size.should == 4
-        pieces.last.should == '(New Vocal Mix No 1)'
+        pieces[:all].size.should == 4
+        pieces[:all].last.should == '(New Vocal Mix No 1)'
+        pieces[:meta].size.should == 2
+        pieces[:title].size.should == 2
       end
 
       it "should handle a single word song with parenthesis" do
@@ -70,13 +85,16 @@ describe ISRC do
         isrc.retrieve artist:'Frank Sinatra', title: 'Chicago (Digitally Remastered)'
         isrc.match(time:'2:14')[:isrc].should == 'USCA20300966'
         # or USCA29800388; they are basically the same
+
+        # Bagatelle in A minor, WoO 59 -`Für Elise` by Bella Davidovich...
       end
     end
 
     it "should handle a standard multi-word title" do
       pieces = isrc.send(:extract_song_peices, "Take Your Time")
-      pieces.size.should == 3
-      pieces.last.should == "Time"
+      pieces[:all].size.should == 3
+      pieces[:title].size.should == 3
+      pieces[:title].last.should == "Time"
     end
 
   end

metadata

@@ -1,83 +1,83 @@
 --- !ruby/object:Gem::Specification
 name: isrc
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.3
 platform: ruby
 authors:
 - Michael Bianco
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-27 00:00:00.000000000 Z
+date: 2014-03-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: mechanize
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: guard
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: Pull ISRC codes from PPLK UK's database
@@ -87,8 +87,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
-- .rspec
+- ".gitignore"
+- ".rspec"
 - Gemfile
 - Guardfile
 - LICENSE
@@ -110,17 +110,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.1.11
+rubygems_version: 2.2.0
 signing_key: 
 specification_version: 4
 summary: Pull ISRC codes from PPLK UK's database