act_as_page_extractor 0.6.3 → 0.7.0

data/spec/act_as_page_extractor_spec.rb

@@ -4,42 +4,79 @@ require 'act_as_page_extractor'
 describe ActAsPageExtractor do
   context 'correct extraction' do
     [
-      'test-doc-3-pages.docx',
-      'test-doc-3-pages.doc',
-      'test-doc-3-pages.pdf',
-      'test-doc-3-pages.rtf',
-      'test-doc-3-pages.odt',
-      'test-doc-3-pages.html',
-      'test-doc-3-pages.txt',
-      'test-doc-3-pages.docx.zip',
-      'test-doc-3-pages.docx.rar',
-      'test-doc-3-pages.docx.7z'
+      'Oscar_Wilde_The_Happy_Prince_en.docx',
+      'Oscar_Wilde_The_Happy_Prince_en.doc',
+      'Oscar_Wilde_The_Happy_Prince_en.pdf',
+      'Oscar_Wilde_The_Happy_Prince_en.rtf',
+      'Oscar_Wilde_The_Happy_Prince_en.odt',
+      'Oscar_Wilde_The_Happy_Prince_en.html',
+      'Oscar_Wilde_The_Happy_Prince_en.txt',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.zip',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.rar',
+      'Oscar_Wilde_The_Happy_Prince_en.docx.7z'
     ].each do |document|
-      it "extraction valid document #{document}" do
+      it "extracts valid document #{document}" do
         book = Book.new({doc_path: document})
         allow(Book).to receive_message_chain('where') { [book] }
         ActAsPageExtractor.start_extraction
         expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:extracted]
-        expect(ExtractedPage.array.count).to eq 3
-        expect(ExtractedPage.array[0][:page]).to match /require \'act_as_page_extractor\/modules\/interface\'/
+        expect(ExtractedPage.array.count).to eq 4
+        expect(ExtractedPage.array[0][:page]).to match /on a tall column, stood the statue of the Happy Prince/
         unless document.match /pdf/
           expect(book.pdf_path).to match /pdf/
           expect(book.remove_files.count).to eq 1
+          expect(book.pages_extraction_errors).to be_empty
         end
         expect(ActAsPageExtractor.statistics).to include(supported_documents:  1)
       end
     end
   end
 
-  context 'incorrect extraction' do
-    [
-      'test-doc-3-pages.wrong',
-    ].each do |document|
-      it "extraction invalid document #{document}" do
-        book = Book.new({doc_path: document})
-        allow(Book).to receive_message_chain('where') { [book] }
+  describe 'errors processing' do
+    let(:book) { Book.new({doc_path: document}) }
+
+    before do
+      allow(Book).to receive_message_chain('where') { [book] }
+    end
+
+    context 'when invalid doctype' do
+      let(:document) { 'Oscar_Wilde_The_Happy_Prince_en.wrong' }
+
+      it "logs invalid doctype" do
+        ActAsPageExtractor.start_extraction
+        expect(book.page_extraction_state).to eq 'error_doctype'
+        expect(book.pages_extraction_errors).to match('error_doctype')
+      end
+    end
+
+    context 'with extraction timeout' do
+      let(:error_msg) { 'execution expired' }
+      let(:document) { 'Oscar_Wilde_The_Happy_Prince_en.docx' }
+
+      before do
+        allow(Docsplit).to receive(:extract_pdf).and_raise(Timeout::Error.new(error_msg))
+      end
+
+      it "logs timeout error" do
+        ActAsPageExtractor.start_extraction
+        expect(book.page_extraction_state).to eq 'error_extraction'
+        expect(book.pages_extraction_errors).to match(error_msg)
+      end
+    end
+
+    context 'when Docsplit returns failure' do
+      let(:error_msg) { 'Unknown Docsplit error' }
+      let(:document) { 'Oscar_Wilde_The_Happy_Prince_en.docx' }
+
+      before do
+        allow(Docsplit).to receive(:extract_pdf).and_raise(Timeout::Error.new(error_msg))
+        allow(Docsplit).to receive(:extract_text).and_raise(Timeout::Error.new(error_msg))
+      end
+
+      it "logs Docsplit error" do
         ActAsPageExtractor.start_extraction
-        expect(book.page_extraction_state).to eq ActAsPageExtractor::EXTRACTING_STATES[:'error.extraction']
+        expect(book.page_extraction_state).to eq 'error_extraction'
+        expect(book.pages_extraction_errors).to match(error_msg)
       end
     end
   end

data/spec/spec_helper.rb

@@ -3,7 +3,7 @@ unless ENV['SKIP_COVERAGE']
   SimpleCov.start 'rails' do
     add_filter 'vendor'
   end
-  SimpleCov.minimum_coverage 100
+  SimpleCov.minimum_coverage 98
 end
 
 require 'rspec'

data/spec/support/models.rb

@@ -14,7 +14,8 @@ class Book
                 :page_extraction_state,
                 :page_extraction_pages,
                 :page_extraction_doctype,
-                :page_extraction_filesize
+                :page_extraction_filesize,
+                :pages_extraction_errors
 
   def self.before_create &block
     yield
@@ -35,6 +36,7 @@ class Book
     filename:          :filename, # CarrierWave class with 'filename.url' method
     document_id:       :document_id,
     additional_fields: [:category_id, :user_id],
+    root_folder:       Dir.pwd.to_s,
     file_storage:      "#{Dir.pwd}/test/",
     pdf_storage:       "#{Dir.pwd}/test/uploads/extracted/pdf"
   }
@@ -44,6 +46,7 @@ class Book
     @id = @category_id = @user_id = nil
     @page_extraction_state = @page_extraction_pages = nil
     @page_extraction_doctype = @page_extraction_filesize = nil
+    @pages_extraction_errors = ''
     ExtractedPage.cleanup
   end
 
@@ -62,7 +65,13 @@ class Book
 
   def update params
     params.each do |key, value|
-      instance_eval("self.#{key} = #{value.class == String ? '\'' + value + '\'': value }")
+      if value.nil?
+        instance_eval("self.#{key} = nil")
+      elsif value.class == String
+        instance_eval("self.#{key} = \"#{value}\"")
+      else
+        instance_eval("self.#{key} = #{value}")
+      end
     end
   end
 end