bookshark 1.0.0.alpha.3 → 1.0.0.alpha.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d1a505294880b3816fc6382b9d48035d0e780e85
-  data.tar.gz: 5cc5432c462fea9ab4781bf91bfa9cef9ffa2e2d
+  metadata.gz: 818b101a82314fcff676b111f3e407821a9f0dc5
+  data.tar.gz: 12dd9368013a7911b4ce8c3f799db90e42c80671
 SHA512:
-  metadata.gz: aeee746c931f9171c58c1594145cdaa91d89fda5de4671a4e9a5cf92b3e3d09bffaea863b555326b2224594b901b3859ffff8eacc0a078acd600fc9fee005a7c
-  data.tar.gz: f6f5061c6a636e4eb558508000cb572fd2cd34a59802146a45f6f9bea89f6fa30e14e13a1de54e49a067bae8217b6b9685bc6d124a0d1ac31c3fbb800ea738ab
+  metadata.gz: b937fcae31844c3742ff6ad00ef91e27a24fe2d8f67c2319fbafeab5db16e1fdc382e26fb37a9d1409ba446fefe8c4407b9cc3d7d95038da6533e09aac2a8900
+  data.tar.gz: 70932725282459f1b6c161517630c5a8edd364efca16d4f2e41b1170ebba721368b9fef14eab7d9fa710c2ebd2e099374d76f53ee15c40b9df0dfa99799eab0e

data/lib/bookshark/extractors/author_extractor.rb

@@ -43,7 +43,12 @@ module Biblionet
 
         # puts JSON.pretty_generate(author_hash)
 
-        return @author = author_hash
+        if author_hash[:lastname].nil? and author_hash[:firstname].nil?
+          return nil
+        else
+          return @author = author_hash
+        end
+
       end
 
       def split_name(fullname)
@@ -81,7 +86,7 @@ module Biblionet
         if (content_re.match(document)).nil?
           puts document
         end
-        content = content_re.match(document)[0]
+        content = content_re.match(document)[0] unless (content_re.match(document)).nil?
 
         @nodeset = Nokogiri::HTML(content)        
       end  

data/lib/bookshark/extractors/book_extractor.rb

@@ -9,12 +9,12 @@ module Biblionet
 
       def initialize(uri=nil)
         super(uri)        
-        extract_book unless uri.nil?        
+        extract_book unless uri.nil? or @page.nil?        
       end
 
       def load_and_extract_book(uri=nil)
         load_page(uri)
-        extract_book unless uri.nil?
+        extract_book unless uri.nil? or @page.nil?
       end      
 
       # Converts the parsed contributors string to hash. 
@@ -116,6 +116,10 @@ module Biblionet
                
         page = BookDataExtractor.new(book_page)
 
+        # End extraction if BookDataExtractor couldnt create a nodeset
+        return nil if page.nodeset.nil?
+
+
         book_hash = Hash.new      
 
         begin                
@@ -200,9 +204,14 @@ module Biblionet
         if (content_re.match(document)).nil?
           puts document
         end
-        content = content_re.match(document)[0]
-
-        @nodeset = Nokogiri::HTML(content)        
+        content = content_re.match(document)[0] unless (content_re.match(document)).nil?
+        
+        # If content is nil, there is something wrong with the html, so return nil
+        if content.nil?
+          @nodeset = nil
+        else
+          @nodeset = Nokogiri::HTML(content) 
+        end        
       end
 
       def image

data/lib/bookshark/extractors/category_extractor.rb

@@ -8,7 +8,7 @@ module Biblionet
 
       def initialize(uri=nil)
         super(uri)        
-        extract_categories unless uri.nil?        
+        extract_categories unless uri.nil? or @page.nil?         
       end
 
       def extract_categories(category_page=@page)
@@ -43,15 +43,18 @@ module Biblionet
           category_hash = {biblionet_id => category.clone}
         end.reduce({}, :update) unless @page.nil?               
 
-        @categories[:current] = (@categories[@biblionet_id.to_s].clone)
-        @categories[:current][:b_id] = @biblionet_id
-        
-        return @categories  
+        if present?(@categories)
+          @categories[:current] = (@categories[@biblionet_id.to_s].clone)
+          @categories[:current][:b_id] = @biblionet_id
+          return @categories
+        else
+          return nil
+        end                
       end
 
       def extract_categories_from(uri=nil)
         load_page(uri)
-        extract_categories unless uri.nil?
+        extract_categories unless uri.nil? or @page.nil? 
       end
 
 

data/lib/bookshark/extractors/publisher_extractor.rb

@@ -21,6 +21,8 @@ module Biblionet
         puts "Extracting publisher: #{biblionet_id}"
         page = PublisherDataExtractor.new(publisher_page)
         
+        return nil if page.nodeset.nil?
+                
         headquarters                    = page.headquarters
         bookstores                      = page.bookstores
         bookstores['Έδρα']              = headquarters 
@@ -46,9 +48,14 @@ module Biblionet
         if (content_re.match(document)).nil?
           puts document
         end
-        content = content_re.match(document)[0]
-
-        @nodeset = Nokogiri::HTML(content)        
+        content = content_re.match(document)[0] unless (content_re.match(document)).nil?
+
+        # If content is nil, there is something wrong with the html, so return nil
+        if content.nil?
+          @nodeset = nil
+        else
+          @nodeset = Nokogiri::HTML(content)
+        end                 
       end  
 
       def name

data/lib/bookshark/version.rb

@@ -1,3 +1,3 @@
 module Bookshark
-  VERSION = "1.0.0.alpha.3"
+  VERSION = "1.0.0.alpha.5"
 end

data/spec/bookshark_spec.rb

@@ -9,13 +9,37 @@ describe Bookshark::Extractor do
   let(:eager_book_184923) { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/eager_book_184923.json", File.dirname(__FILE__))).read)) }
   let(:search_01)         { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/search_01.json"        , File.dirname(__FILE__))).read)) }
   let(:search_ids_01)     { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/search_ids_01.json"    , File.dirname(__FILE__))).read)) }
+  let(:empty_book)        { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/empty_book.json"       , File.dirname(__FILE__))).read)) }
+  let(:empty_author)      { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/empty_author.json"     , File.dirname(__FILE__))).read)) }
+  let(:empty_publisher)   { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/empty_publisher.json"  , File.dirname(__FILE__))).read)) }
+  let(:empty_category)    { JSON.pretty_generate(JSON.parse(open(File.expand_path("test_data/empty_category.json"   , File.dirname(__FILE__))).read)) }
 
 
   describe '#author' do
     context 'from remote html source' do
-      it 'reads html from the web and extracts author data' do
-        expect(subject.author(id: 13219)).to eq author_13219
+      context 'when the author exists' do
+        it 'reads html from the web based on given id and extracts author data' do
+          expect(subject.author(id: 13219)).to eq author_13219
+        end
+        it 'reads html from the web based on given uri and extracts author data' do
+          expect(subject.author(uri: "http://biblionet.gr/author/13219")).to eq author_13219
+        end        
       end
+      context 'when the author doesnt exist' do
+        it 'returns an empty array' do
+          expect(subject.author(id: 0)).to eq empty_author
+        end  
+      end  
+      context 'when no options are set' do
+        it 'returns an empty array' do
+          expect(subject.author).to eq empty_author
+        end  
+      end 
+      context 'when a the given uri is wrong' do
+        it 'returns an empty array' do
+          expect(subject.author(uri: "http://google.com")).to eq empty_author
+        end  
+      end           
     end
 
     context 'from local storage' do
@@ -28,41 +52,114 @@ describe Bookshark::Extractor do
 
   describe '#publisher' do
     context 'extract from remote html source' do
-      it 'reads html from the web and extracts publisher data' do
-        expect(subject.publisher(id: 20)).to eq publisher_20
+      context 'when the publisher exists' do
+        it 'reads html from the web based on given id and extracts publisher data' do
+          expect(subject.publisher(id: 20)).to eq publisher_20
+        end
+        it 'reads html from the web based on given uri and extracts publisher data' do
+          expect(subject.publisher(uri: "http://biblionet.gr/com/20")).to eq publisher_20
+        end        
       end
+      context 'when the publisher doesnt exist' do
+        it 'returns an empty array' do
+          expect(subject.publisher(id: 0)).to eq empty_publisher
+        end  
+      end  
+      context 'when no options are set' do
+        it 'returns an empty array' do
+          expect(subject.publisher).to eq empty_publisher
+        end  
+      end  
+      context 'when a the given uri is wrong' do
+        it 'returns an empty array' do
+          expect(subject.publisher(uri: "http://google.com")).to eq empty_publisher
+        end  
+      end             
     end    
   end
 
   describe '#category' do
     context 'extract from remote html source' do
-      it 'reads html from the web and extracts category data' do
-        expect(subject.category(id: 1041)).to eq category_1041
+      context 'when the category exists' do
+        it 'reads html from the web based on given id and extracts category data' do
+          expect(subject.category(id: 1041)).to eq category_1041
+        end
+        it 'reads html from the web based on given uri and extracts category data' do
+          expect(subject.category(uri: "http://biblionet.gr/index/1041")).to eq category_1041
+        end
       end
+      context 'when the category doesnt exist' do
+        it 'returns an empty array' do
+          expect(subject.category(id: 0)).to eq empty_category
+        end  
+      end  
+      context 'when no options are set' do
+        it 'returns an empty array' do
+          expect(subject.category).to eq empty_category
+        end  
+      end  
+      context 'when a the given uri is wrong' do
+        it 'returns an empty array' do
+          expect(subject.category(uri: "http://google.com")).to eq empty_category
+        end  
+      end                            
     end 
   end
 
   describe '#book' do
     context 'extract from remote html source' do
-      it 'reads html from the web and extracts book data' do
-        expect(subject.book(id: 103788)).to eq book_103788
-      end
-
-      it 'reads html from the web and eager extracts all book and reference data' do
-        expect(subject.book(id: 184923, eager: true)).to eq eager_book_184923
+      context 'when book exists' do
+        it 'reads html from the web based on given id and extracts book data' do
+          expect(subject.book(id: 103788)).to eq book_103788
+        end
+
+        it 'reads html from the web based on given uri and extracts book data' do
+          expect(subject.book(uri: "http://biblionet.gr/book/103788")).to eq book_103788
+        end        
+
+        it 'reads html from the web and eager extracts all book and reference data' do
+          expect(subject.book(id: 184923, eager: true)).to eq eager_book_184923
+        end
       end
+      context 'when the book doesnt exist' do
+        it 'returns an empty array' do
+          expect(subject.book(id: 0)).to eq empty_book
+        end  
+      end  
+      context 'when no options are set' do
+        it 'returns an empty array' do
+          expect(subject.book).to eq empty_book
+        end  
+      end  
+      context 'when a the given uri is wrong' do
+        it 'returns an empty array' do
+          expect(subject.book(uri: "http://google.com")).to eq empty_book
+        end  
+      end            
     end
   end 
 
   describe '#search' do
-    context 'extract from remote html source' do
-      it 'builds a search url and extracts book ids from search page' do
-        expect(subject.search(title: 'σημεια και τερατα', results_type: 'ids')).to eq search_ids_01
+    context 'search and extract from remote html source' do
+      context 'when books are found' do
+        it 'builds a search url and extracts book ids from search page' do
+          expect(subject.search(title: 'σημεια και τερατα', results_type: 'ids')).to eq search_ids_01
+        end
+
+        it 'builds a search url and extracts book data from search page' do
+          expect(subject.search(title: 'σημεια και τερατα', results_type: 'metadata')).to eq search_01
+        end  
       end
-
-      it 'builds a search url and extracts book data from search page' do
-        expect(subject.search(title: 'σημεια και τερατα', results_type: 'metadata')).to eq search_01
-      end      
+      context 'when no books are found' do  
+        it 'returns an empty array' do
+          expect(subject.search(isbn: 'some-invalid-isbn')).to eq empty_book
+        end  
+      end  
+      context 'when no options are set' do
+        it 'returns an empty array' do
+          expect(subject.search).to eq empty_book
+        end  
+      end         
     end 
   end
  

data/spec/test_data/empty_author.json

@@ -0,0 +1,5 @@
+{
+  "author": [
+
+  ]
+}

data/spec/test_data/empty_book.json

@@ -0,0 +1,5 @@
+{
+  "book": [
+
+  ]
+}

data/spec/test_data/empty_category.json

@@ -0,0 +1,5 @@
+{
+  "category": [
+
+  ]
+}

data/spec/test_data/empty_publisher.json

@@ -0,0 +1,5 @@
+{
+  "publisher": [
+
+  ]
+}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: bookshark
 version: !ruby/object:Gem::Version
-  version: 1.0.0.alpha.3
+  version: 1.0.0.alpha.5
 platform: ruby
 authors:
 - Dimitris Klisiaris
@@ -149,6 +149,10 @@ files:
 - spec/test_data/book_103788.json
 - spec/test_data/category_1041.json
 - spec/test_data/eager_book_184923.json
+- spec/test_data/empty_author.json
+- spec/test_data/empty_book.json
+- spec/test_data/empty_category.json
+- spec/test_data/empty_publisher.json
 - spec/test_data/publisher_20.json
 - spec/test_data/search_01.json
 - spec/test_data/search_ids_01.json
@@ -186,6 +190,10 @@ test_files:
 - spec/test_data/book_103788.json
 - spec/test_data/category_1041.json
 - spec/test_data/eager_book_184923.json
+- spec/test_data/empty_author.json
+- spec/test_data/empty_book.json
+- spec/test_data/empty_category.json
+- spec/test_data/empty_publisher.json
 - spec/test_data/publisher_20.json
 - spec/test_data/search_01.json
 - spec/test_data/search_ids_01.json