Merge pull request #51 from Erol/general-document-reader-using-yomu

Add a general document reader class using Yomu

Gemfile

@@ -4,10 +4,11 @@ gemspec
 
 gem 'birch'
 gem 'schiphol'
+gem 'yomu'
 
 group :test do
   gem 'rspec'
   gem 'rake'
   gem 'terminal-table'
   gem 'simplecov'
-end
+end

lib/treat/workers/formatters/readers/autoselect.rb

@@ -3,7 +3,7 @@ class Treat::Workers::Formatters::Readers::Autoselect
   ExtensionRegexp = /^.*?\.([a-zA-Z0-9]{2,5})$/
   ImageExtensions = ['gif', 'jpg', 'jpeg', 'png']
   DefaultOptions = {
-    :default_to => 'txt'
+    :default_to => 'document'
   }
 
   # Choose a reader to use.

lib/treat/workers/formatters/readers/document.rb

@@ -0,0 +1,17 @@
+require 'yomu'
+
+# This class is a wrapper for Yomu.
+# Yomu is a library for extracting text and metadata from files and documents
+# using the Apache Tika content analysis toolkit.
+class Treat::Workers::Formatters::Readers::Document
+  # Extract the readable text from any document.
+  #
+  # Options: none.
+  def self.read(document, options = {})
+    yomu = Yomu.new(document.file)
+
+    document.value = yomu.text
+    document.set :format, yomu.mimetype.extensions.first
+    document
+  end
+end

spec/entities/document.rb

@@ -9,10 +9,10 @@ module Treat::Specs::Entities
           it "opens the file and reads its " +
           "content into a document" do
             f = Treat.paths.spec +
-            'workers/examples/english/mathematicians/leibniz.txt'
+            'workers/examples/english/mathematicians/pythagoras.docx'
             d = Treat::Entities::Document.build(f)
             d.should be_an_instance_of Treat::Entities::Document
-            d.to_s.index('Gottfried Leibniz').should_not eql nil
+            d.to_s.index('Pythagoras of Samos').should_not eql nil
           end
         end
 

treat.gemspec

@@ -25,6 +25,7 @@ Gem::Specification.new do |s|
   # Runtime dependencies
   s.add_runtime_dependency 'schiphol'
   s.add_runtime_dependency 'birch'
+  s.add_runtime_dependency 'yomu'
 
   # Development dependencies
   s.add_development_dependency 'rspec'
@@ -36,4 +37,4 @@ Gem::Specification.new do |s|
   To complete the installation, run `require treat` in an IRB 
   terminal, followed by `Treat::Core::Installer.install`. }
 
-end
+end