docsplit-paperclip-processor 0.1.2 → 0.2.0

data/CHANGELOG

@@ -0,0 +1,14 @@
+New in 0.2.0:
+
+API CHANGE: Rails.logger no longer called 
+Bug Fix: Was calling PaperclipError, now calls Paperclip::Error
+Test Coverage: Specs added for DocsplitProcessor, DocsplitPdf, DocsplitImage.
+Feature: Added docsplit as a dependency
+Feature: Added rspec as a development dependency
+
+New in 0.1.2:
+Feature: Using FileMagic to determine MIME type
+
+New in 0.1.1:
+Feature: Passing PDF on if PDF conversion is attempted on a PDF
+Feature: Added Docsplit.extract_image processor

data/docsplit-paperclip-processor.gemspec

@@ -16,6 +16,8 @@ Gem::Specification.new do |s|
 
   s.add_dependency "paperclip", "~> 2.4"
   s.add_dependency 'ruby-filemagic'
+  s.add_dependency 'docsplit'
+  s.add_development_dependency 'rspec'
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/lib/docsplit-paperclip-processor.rb

@@ -12,6 +12,10 @@ module Paperclip
       @attachment = attachment
       @basename   = File.basename(@file.path, '.*')
     end
+    
+    def src_path
+      File.expand_path(@src.path)
+    end
   end
 
   class DocsplitChaining < Processor
@@ -31,26 +35,24 @@ module Paperclip
   class DocsplitPdf < DocsplitProcessor
     def make
       begin
-        src_path = File.expand_path(@src.path)
         dst_dir = Dir.tmpdir
         dst_path = File.join(dst_dir, "#{@basename}.pdf")
 
-        if pdf_format?(src_path)
+        if pdf_format?
           dst_path = File.join(dst_dir, "_#{@basename}.pdf")
           FileUtils.copy_file(src_path, dst_path)
         else
           Docsplit.extract_pdf(src_path, :output => dst_dir)
         end
       rescue Exception => e
-        Rails.logger.error e.message
-        raise PaperclipError, "There was an error converting #{@basename} to pdf"
+        raise Paperclip::Error, "There was an error converting #{@basename} to pdf"
       end
       File.open(dst_path)
     end
 
-    def pdf_format?(file)
+    def pdf_format?
       file_magic = FileMagic.new
-      type = file_magic.file(file)
+      type = file_magic.file(src_path)
       file_magic.close
       type =~ /pdf/i
     end
@@ -59,17 +61,15 @@ module Paperclip
   class DocsplitImage < DocsplitProcessor
     def make
       begin
-        src_path = File.expand_path(@src.path)
         dst_path = Dir.tmpdir
         pages    = options[:pages] || [1]
         options  = @options.merge(:output => dst_path)
 
         Docsplit.extract_images(src_path, options)
       rescue Exception => e
-        Rails.logger.error e.message
-        raise PaperclipError, "There was an error extracting images from #{@basename}"
+        raise Paperclip::Error, "There was an error extracting images from #{@basename}"
       end
       File.open(File.join(dst_path, "#{@basename}_#{pages.first}.#{@options[:format]}"))
     end
   end
-end
+end

data/lib/docsplit-paperclip-processor/version.rb

@@ -1,7 +1,7 @@
 module Docsplit
   module Paperclip
     module Processor
-      VERSION = "0.1.2"
+      VERSION = "0.2.0"
     end
   end
 end

data/spec/docsplit-paperclip-processor_spec.rb

@@ -0,0 +1,21 @@
+require 'spec_helper'
+
+describe Paperclip::DocsplitProcessor do
+  it "has an accessible file attribute" do
+    d = Paperclip::DocsplitProcessor.new(File.open("./fixtures/word_xml.docx"))
+    d.src.path.should eq(File.open("./fixtures/word_xml.docx").path)
+  end
+  
+  it "has an accessible options hash attribute" do
+    options = {:option_1 => 1, :option_2 => 2}
+    d = Paperclip::DocsplitProcessor.new(File.open("./fixtures/word_xml.docx"), options)
+    d.options.should eq(options)
+  end
+  
+  it "has an accessible Paperclip::Attachment attribute" do
+    attachment = Paperclip::Attachment.new(nil, nil)
+    
+    d = Paperclip::DocsplitProcessor.new(File.open("./fixtures/word_xml.docx"), {}, attachment)
+    d.attachment.should eq(attachment)
+  end
+end

data/spec/docsplit_image_spec.rb

@@ -0,0 +1,55 @@
+require 'spec_helper'
+
+describe Paperclip::DocsplitImage do
+  def pdf_jpg_images
+    Dir.entries(Dir.tmpdir).reject{ |x| !(x =~ /twopage_\d.jpg/) }
+  end
+  
+  context "with a valid pdf file attachment" do
+    before(:all) do
+      pdf_jpg_images.each do |tempfile|
+        File.delete(File.join(Dir.tmpdir, tempfile))
+      end
+      
+      @file = File.open("./fixtures/twopage.pdf")
+      @processor = Paperclip::DocsplitImage.new(@file, {:format => :jpg, :size => "50x50"})
+      @output = @processor.make
+    end
+    
+    after(:all) do
+      @file.close
+    end
+    
+    it "#make generates an image for each page of the document" do
+      pdf_jpg_images.count.should eq(2)
+    end
+  
+    it "#make generates images at the specified resolution" do
+      cmd = %Q[identify -format "%wx%h" "#{@output.path}"]
+      `#{cmd}`.chomp.should eq("39x50")
+    end
+  
+    it "#make generates images in the specified format" do
+      pdf_jpg_images.each do |output_file|
+        FileMagic.new.file(File.join(Dir.tmpdir, output_file)).should =~ /jpeg/i
+      end
+    end
+  
+    it "#make returns the image of the first page" do
+      File.basename(@output).should eq('twopage_1.jpg')
+    end
+  end
+  
+  context "when processing fails" do
+    it "#make raises an error if the processing was unsuccessful" do
+      @file = File.open("./fixtures/twopage.pdf")
+      Dir.stub!(:tmpdir).and_return(:raise)
+    
+      lambda {
+        Paperclip::DocsplitImage.new(@file, {:format => :jpg}).make
+      }.should raise_error(Paperclip::Error)
+    
+      @file.close
+    end
+  end
+end

data/spec/docsplit_pdf_spec.rb

@@ -0,0 +1,61 @@
+require 'spec_helper'
+
+describe Paperclip::DocsplitPdf do
+  def make_output
+    Paperclip::DocsplitPdf.new(@file).make
+  end
+
+  context "with a Microsoft Word .docx file" do
+    before(:all) do
+      @file = File.open("./fixtures/word_xml.docx")
+      @output = make_output
+    end
+
+    after(:all) do
+      @file.close
+    end
+
+    describe "produces a file with a .pdf extension" do
+      it "names the converted document with a .pdf extension" do
+        File.extname(@output.path).should eq(".pdf")
+      end
+
+      it "produces PDF-format file" do
+        FileMagic.new.file(@output.path).should =~ /pdf/i
+      end
+    end
+  end
+  
+  it "passes the document on if it is already a PDF" do
+    @file = File.open("./fixtures/portable_document_format.pdf")
+
+    lambda {
+      FileMagic.new.file(make_output.path).should =~ /pdf/i
+    }.should_not raise_error
+    
+    @file.close
+  end
+
+  it "raises an error if PDF conversion was unsuccessful" do
+    @file = File.open("./fixtures/test.bin")
+    Dir.stub!(:tmpdir).and_return(:raise)
+    
+    lambda {
+      make_output
+    }.should raise_error(Paperclip::Error)
+    
+    @file.close
+  end
+
+  describe "#pdf_format?" do
+    it "identifies a PDF document as a PDF" do
+      processor = Paperclip::DocsplitPdf.new(File.open("./fixtures/portable_document_format.pdf"))
+      processor.pdf_format?.should be_true
+    end
+
+    it "identifies a non-PDF document as not a PDF" do
+      processor = Paperclip::DocsplitPdf.new(File.open("./fixtures/word_xml.docx"))
+      processor.pdf_format?.should be_false
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,7 @@
+require "paperclip"
+require "filemagic"
+require "docsplit"
+require "docsplit-paperclip-processor"
+
+require 'rspec'
+require 'rspec/autorun'

metadata

@@ -1,100 +1,132 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: docsplit-paperclip-processor
-version: !ruby/object:Gem::Version 
-  hash: 31
+version: !ruby/object:Gem::Version
+  version: 0.2.0
   prerelease: 
-  segments: 
-  - 0
-  - 1
-  - 2
-  version: 0.1.2
 platform: ruby
-authors: 
+authors:
 - Tien Le
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2012-05-08 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2012-07-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: paperclip
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        hash: 11
-        segments: 
-        - 2
-        - 4
-        version: "2.4"
+      - !ruby/object:Gem::Version
+        version: '2.4'
   type: :runtime
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.4'
+- !ruby/object:Gem::Dependency
   name: ruby-filemagic
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  version_requirements: !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 3
-        segments: 
-        - 0
-        version: "0"
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: docsplit
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   type: :runtime
-  version_requirements: *id002
-description: This gem is simple Paperclip processor which uses Docsplit to convert uploaded files to pdf, or extract information/thumbnails from them
-email: 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This gem is simple Paperclip processor which uses Docsplit to convert
+  uploaded files to pdf, or extract information/thumbnails from them
+email:
 - tienlx@gmail.com
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - .gitignore
+- CHANGELOG
 - Gemfile
 - README.md
 - Rakefile
 - docsplit-paperclip-processor.gemspec
+- fixtures/not_a_docx.docx
+- fixtures/portable_document_format.pdf
+- fixtures/test.bin
+- fixtures/twopage.pdf
+- fixtures/word_xml.docx
 - lib/docsplit-paperclip-processor.rb
 - lib/docsplit-paperclip-processor/version.rb
+- spec/docsplit-paperclip-processor_spec.rb
+- spec/docsplit_image_spec.rb
+- spec/docsplit_pdf_spec.rb
+- spec/spec_helper.rb
 homepage: https://github.com/tienle/docsplit-paperclip-processor
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: docsplit-paperclip-processor
-rubygems_version: 1.8.6
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: A Paperclip processor for Docsplit
-test_files: []
-
+test_files:
+- spec/docsplit-paperclip-processor_spec.rb
+- spec/docsplit_image_spec.rb
+- spec/docsplit_pdf_spec.rb
+- spec/spec_helper.rb
+has_rdoc: