docsplit-paperclip-processor 0.2.0 → 0.2.2

data/.rspec

@@ -0,0 +1 @@
+--color --order random -f d

data/CHANGELOG

@@ -1,5 +1,11 @@
-New in 0.2.0:
+New in 0.2.2:
+Feature: Added ability to save extracted text back to an ActiveRecord model's field
+Documentation: Updated docs for extracting text and listed dependencies
+
+New in 0.2.1:
+Feature: Added Paperclip::DocsplitText for text extraction
 
+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.

data/Gemfile

@@ -1,4 +1,3 @@
 source "http://rubygems.org"
 
-gemspec
-gem "docsplit"
+gemspec

data/README.md

@@ -7,6 +7,7 @@ These include the Microsoft Office formats: doc, docx, ppt, xls and so on, as we
 
 * [Paperclip][0]
 * [Docsplit][1]
+* [FileMagic][2]
 
 ## Installation ##
 
@@ -40,7 +41,25 @@ Use it as you would any other Paperclip processor. For example, in your model:
 
 which will convert your document into pdf.
 
-### Extract information (text, metadata) and thumbnail ###
+### Extract text ###
+
+WARNING: This feature is in alpha.
+
+    class Document < ActiveRecord::Base
+
+      has_attached_file :file,
+                        :styles => {
+                          :text => {
+                            :processors => [:docsplit_text],
+                            :full_text_column => :file_full_text
+                          }
+                        }
+
+    end
+
+will extract the text from the file uploaded, and desposit the full text of the file into the column 'file_full_text'.
+
+### Extract metadata and thumbnail ###
 
 Will be include in the next releases.
 

data/docsplit-paperclip-processor.gemspec

@@ -14,10 +14,16 @@ Gem::Specification.new do |s|
 
   s.rubyforge_project = "docsplit-paperclip-processor"
 
-  s.add_dependency "paperclip", "~> 2.4"
+  s.add_dependency "paperclip", "~> 3.1"
   s.add_dependency 'ruby-filemagic'
   s.add_dependency 'docsplit'
+  s.add_development_dependency 'bundler', ">= 1.1.4"
   s.add_development_dependency 'rspec'
+  s.add_development_dependency 'activerecord'
+  s.add_development_dependency 'sqlite3'
+
+  # Runtime dependencies
+  s.add_runtime_dependency "paperclip"
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/lib/docsplit-paperclip-processor.rb

@@ -1,3 +1,4 @@
+require "docsplit"
 require "paperclip"
 require "filemagic"
 
@@ -17,59 +18,8 @@ module Paperclip
       File.expand_path(@src.path)
     end
   end
+end
 
-  class DocsplitChaining < Processor
-    attr_accessor :options, :attachment
-
-    def initialize(file, options = {}, attachment = nil)
-      super
-      @options    = options
-      @attachment = attachment
-    end
-
-    def make
-      attachment.to_file(options[:from_style] || :original)
-    end
-  end
-
-  class DocsplitPdf < DocsplitProcessor
-    def make
-      begin
-        dst_dir = Dir.tmpdir
-        dst_path = File.join(dst_dir, "#{@basename}.pdf")
-
-        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
-        raise Paperclip::Error, "There was an error converting #{@basename} to pdf"
-      end
-      File.open(dst_path)
-    end
-
-    def pdf_format?
-      file_magic = FileMagic.new
-      type = file_magic.file(src_path)
-      file_magic.close
-      type =~ /pdf/i
-    end
-  end
-
-  class DocsplitImage < DocsplitProcessor
-    def make
-      begin
-        dst_path = Dir.tmpdir
-        pages    = options[:pages] || [1]
-        options  = @options.merge(:output => dst_path)
-
-        Docsplit.extract_images(src_path, options)
-      rescue Exception => e
-        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
+require 'processors/docsplit_image'
+require 'processors/docsplit_pdf'
+require 'processors/docsplit_text'

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

@@ -1,7 +1,7 @@
 module Docsplit
   module Paperclip
     module Processor
-      VERSION = "0.2.0"
+      VERSION = "0.2.2"
     end
   end
 end

data/lib/processors/docsplit_image.rb

@@ -0,0 +1,21 @@
+module Paperclip
+  class DocsplitImage < DocsplitProcessor
+    def make
+      begin
+        @dst_path = Dir.tmpdir
+        @pages    = @options[:pages] || [1]
+        @options  = @options.merge(:output => @dst_path)
+
+        Docsplit.extract_images(src_path, @options)
+      rescue Exception => e
+        raise Paperclip::Error, "There was an error extracting images from #{@basename}"
+      end
+      
+      destination_file
+    end
+
+    def destination_file
+      File.open(File.join(@dst_path, "#{@basename}_#{@pages.first}.#{@options[:format]}"))
+    end
+  end
+end

data/lib/processors/docsplit_pdf.rb

@@ -0,0 +1,27 @@
+module Paperclip
+ class DocsplitPdf < DocsplitProcessor
+    def make
+      begin
+        dst_dir = Dir.tmpdir
+        dst_path = File.join(dst_dir, "#{@basename}.pdf")
+
+        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
+        raise Paperclip::Error, "There was an error converting #{@basename} to pdf"
+      end
+      File.open(dst_path)
+    end
+
+    def pdf_format?
+      file_magic = FileMagic.new
+      type = file_magic.file(src_path)
+      file_magic.close
+      type =~ /pdf/i
+    end
+  end
+end

data/lib/processors/docsplit_text.rb

@@ -0,0 +1,42 @@
+module Paperclip
+  class DocsplitText < DocsplitProcessor
+    def make
+      begin
+        @dst_path = Dir.tmpdir
+        @pages    = @options[:pages] || [1]
+        @options  = @options.merge(:output => @dst_path)
+
+        Docsplit.extract_text(src_path, @options)
+      rescue Exception => e
+        raise Paperclip::Error, "There was an error extracting text from #{@basename}"
+      end
+
+      if @options[:full_text_column]
+        # Bypassing callbacks to save full text. See Paperclip issue #671:
+        # https://github.com/thoughtbot/paperclip/issues/671
+        ar_model = @attachment.instance
+        ar_model[@options[:full_text_column]] = full_text
+        ar_model.run_callbacks(:save) { false }
+
+        # This would be the preferred method of saving this text.
+        # @attachment.instance.update_attribute(@options[:full_text_column], full_text)
+      end
+
+      destination_file
+    end
+
+    def destination_file
+      File.open(File.join(@dst_path, "#{@basename}.txt"))
+    end
+
+    def full_text
+      full_text = String.new
+
+      destination_file.each do |line|
+        full_text += line
+      end
+
+      full_text
+    end
+  end
+end

data/spec/docsplit_extract_text_spec.rb

@@ -0,0 +1,65 @@
+require 'spec_helper'
+
+describe Paperclip::DocsplitText do
+  before(:all) do
+    @file = File.open("./fixtures/word_xml.docx")
+  end
+
+  after(:all) do
+    @file.close
+  end
+
+  context "with no options supplied" do
+    before(:all) do
+      @options = {}
+      @processor = Paperclip::DocsplitText.new(@file, @options)
+    end
+
+    it "#make sends the correct commands to Docsplit" do
+      Docsplit.should_receive(:extract_text).with(File.expand_path(@file.path), @options.merge(:output => Dir.tmpdir))
+  
+      @processor.make
+    end
+    
+    it "#make returns the text tempfile created by Docsplit" do
+      result = @processor.make
+
+      text = String.new
+      result.each do |line|
+        text += line
+      end
+
+      text.should eq("This is a test document.\n\n\f")
+    end
+  end
+
+  context "with a destination column for extracted text" do
+    before(:all) do
+      @options = {:full_text_column => :document_full_text}
+      @doc = Document.new()
+    end
+
+    after(:all) do
+      FileUtils.rm_rf("./spec/tmp", secure: true)
+    end
+
+    it "#make stores the full text in the specified field" do
+      @doc.original = @file
+      @doc.save!
+
+      @doc.reload
+
+      @doc.original_full_text.should eq("This is a test document.\n\n\f")
+    end
+  end
+
+  context "when processing fails" do
+    it "#make raises an error if the processing was unsuccessful" do
+      Dir.stub!(:tmpdir).and_return(:raise)
+    
+      lambda {
+        Paperclip::DocsplitText.new(@file, {}).make
+      }.should raise_error(Paperclip::Error)
+    end
+  end
+end

data/spec/docsplit_image_spec.rb

@@ -1,55 +1,47 @@
 require 'spec_helper'
 
 describe Paperclip::DocsplitImage do
-  def pdf_jpg_images
-    Dir.entries(Dir.tmpdir).reject{ |x| !(x =~ /twopage_\d.jpg/) }
+  def delete_temp_images
+    Dir.entries(Dir.tmpdir).reject{ |x| !(x =~ /twopage_\d.jpg/) }.each do |tempfile|
+      File.delete(File.join(Dir.tmpdir, tempfile))
+    end
+  end
+
+  before(:all) do
+    delete_temp_images
+    @file = File.open("./fixtures/twopage.pdf")
+  end
+
+  after(:all) do
+    delete_temp_images
+    @file.close
   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
+      @options = {:format => :jpg, :size => "50x50"}
+      @processor = Paperclip::DocsplitImage.new(@file, @options)
     end
     
-    after(:all) do
-      @file.close
+    it "#make sends the correct commands to Docsplit" do
+      @processor.stub!(:destination_file)
+      Docsplit.should_receive(:extract_images).with(File.expand_path(@file.path), @options.merge(:output => Dir.tmpdir))
+
+      @processor.make
     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')
+      @processor.make.path.should eq(File.open(Dir.tmpdir + '/twopage_1.jpg').path)
     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/schema.rb

@@ -0,0 +1,10 @@
+ActiveRecord::Schema.define :version => 0 do
+  create_table "documents", :force => true do |t|
+    t.string :owner
+    t.string :original_file_name
+    t.string :original_content_type
+    t.integer :original_updated_at
+    t.integer :original_file_size
+    t.text :original_full_text
+  end
+end

data/spec/spec_helper.rb

@@ -1,7 +1,33 @@
-require "paperclip"
-require "filemagic"
-require "docsplit"
-require "docsplit-paperclip-processor"
+require 'paperclip'
+require 'paperclip/railtie'
+require 'filemagic'
+require 'docsplit'
+require 'docsplit-paperclip-processor'
 
 require 'rspec'
-require 'rspec/autorun'
+require 'rspec/autorun'
+
+# Prepare activerecord
+require "active_record"
+
+# Connect to sqlite
+ActiveRecord::Base.establish_connection(
+  "adapter" => "sqlite3",
+  "database" => ":memory:"
+)
+
+ActiveRecord::Base.logger = Logger.new(nil)
+load(File.join(File.dirname(__FILE__), 'schema.rb'))
+
+Paperclip::Railtie.insert
+
+class Document < ActiveRecord::Base
+	has_attached_file :original,
+		:storage => :filesystem,
+    	:path => "./spec/tmp/:id.:extension",
+    	:url => "/spec/tmp/:id.:extension",
+    	:styles => {
+    		:text => {:full_text_column => :original_full_text}
+    	},
+    	:processors => [:docsplit_text]
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: docsplit-paperclip-processor
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-14 00:00:00.000000000 Z
+date: 2012-08-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: paperclip
@@ -18,7 +18,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.4'
+        version: '3.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -26,7 +26,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.4'
+        version: '3.1'
 - !ruby/object:Gem::Dependency
   name: ruby-filemagic
   requirement: !ruby/object:Gem::Requirement
@@ -59,6 +59,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.1.4
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -75,6 +91,54 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: activerecord
+  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'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  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'
+- !ruby/object:Gem::Dependency
+  name: paperclip
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  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:
@@ -84,6 +148,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - .gitignore
+- .rspec
 - CHANGELOG
 - Gemfile
 - README.md
@@ -96,9 +161,14 @@ files:
 - fixtures/word_xml.docx
 - lib/docsplit-paperclip-processor.rb
 - lib/docsplit-paperclip-processor/version.rb
+- lib/processors/docsplit_image.rb
+- lib/processors/docsplit_pdf.rb
+- lib/processors/docsplit_text.rb
 - spec/docsplit-paperclip-processor_spec.rb
+- spec/docsplit_extract_text_spec.rb
 - spec/docsplit_image_spec.rb
 - spec/docsplit_pdf_spec.rb
+- spec/schema.rb
 - spec/spec_helper.rb
 homepage: https://github.com/tienle/docsplit-paperclip-processor
 licenses: []
@@ -126,7 +196,8 @@ specification_version: 3
 summary: A Paperclip processor for Docsplit
 test_files:
 - spec/docsplit-paperclip-processor_spec.rb
+- spec/docsplit_extract_text_spec.rb
 - spec/docsplit_image_spec.rb
 - spec/docsplit_pdf_spec.rb
+- spec/schema.rb
 - spec/spec_helper.rb
-has_rdoc: