ocrsdk 0.1.0 → 0.1.1

data/.gitignore

@@ -2,4 +2,6 @@
 .sublime-project
 .sublime-project.sublime-workspace
 coverage.data
-Gemfile.lock
+Gemfile.lock
+coverage
+*.gem

data/README.md

@@ -1,2 +1,81 @@
 OCRSDK [![Build Status](https://secure.travis-ci.org/andrusha/ocrsdk.png?branch=master)](http://travis-ci.org/andrusha/ocrsdk) [![Dependency Status](https://gemnasium.com/andrusha/ocrsdk.png)](http://gemnasium.com/andrusha/ocrsdk) [![Code Climate](https://codeclimate.com/badge.png)](https://codeclimate.com/github/andrusha/ocrsdk)
-======
+======
+
+An Abbyy's [OCRSDK](http://ocrsdk.com) API wrapper in Ruby.
+
+Terminology
+-----------
+
+Abbyy uses terms "Image" and "Document" in a way that might be confusing at first, so let's get it straight from the beginning:
+
+* Image - is a single input _file_ which result in a single output, it might be _multi-page_ pdf document as well as jpeg image.
+* Document - is a collection of files which result in a single output, e.g. a collection of scanned pages in tiff format.
+
+Installation
+------------
+
+```bash
+gem install ocrsdk
+```
+
+Configuration
+-------------
+
+```ruby
+OCRSDK.setup do |config|
+  config.application_id = '99bottlesofbeer'
+  config.password = '98bottlesofbeer'
+end
+```
+
+Usage
+-----
+
+There are two basic workflows - synchornous and asynchronous. The first one is simpler, but since recognition may take a significant amount of time and you may want to utilize the same thread (or give response to the user, that processing is started) while document is processed there is also an asynchronous version of each function.
+
+### Simple
+
+```ruby
+image = OCRSDK::Image.new '~/why_cats_paint.pdf'
+
+# sync
+image.as_text_sync([:english]) # => "because they can"
+image.as_pdf_sync([:english], '~/why_cats_paint_ocred.pdf') # # => 31337 (bytes written)
+
+# async
+promise = image.as_text([:english])
+puts "Your document would be ready in #{promise.estimate_completion}"
+promise.wait.result # byte-string, you might need to .force_encoding("utf-8") => "because they can"
+```
+
+### Advanced
+
+```ruby
+# have the same methods as Image + a few format-specific
+pdf = OCRSDK::PDF.new '~/why_cats_paint.pdf'
+unless pdf.recognizeable?
+  return puts "Your document is already recognized"
+end
+
+promise = pdf.as_pdf([:english]) # pdf with images as pdf recognized
+puts "Your document would be ready in #{promise.estimate_completion}"
+
+while promise.processing?
+  begin
+    promise.update
+    sleep 5
+  rescue OCRSDK::NotEnoughCredits
+    return puts "You need to purchase more credits for your account"
+  end
+end
+
+if promise.completed?
+  File.open('~/why_cats_paint_ocred.pdf', 'wb+') {|f| f.write promise.result }
+else
+  puts "Processing failed"
+end
+```
+
+Copyright
+=========
+Copytright © 2012 Andrey Korzhuev. See LICENSE for details.

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/lib/ocrsdk/abstract_entity.rb

@@ -1,9 +1,6 @@
 class OCRSDK::AbstractEntity
-  def initialize(application_id=nil, password=nil)
-    @application_id = application_id || '' # Rails.configuration.ocrsdk.application_id
-    @password       = password       || '' # Rails.configuration.ocrsdk.password
-
-    @url = prepare_url @application_id, @password
+  def initialize
+    @url = prepare_url OCRSDK.config.application_id, OCRSDK.config.password
   end
 
 private

data/lib/ocrsdk/image.rb

@@ -3,15 +3,15 @@ class OCRSDK::Image < OCRSDK::AbstractEntity
   include OCRSDK::Verifiers::Format
   include OCRSDK::Verifiers::Profile
 
-  def initialize(image_path, application_id=nil, password=nil)
-    super(application_id, password)
+  def initialize(image_path)
+    super()
     @image_path = image_path
   end
 
   def as_text(languages)
     xml_string = api_process_image @image_path, languages, :txt, :text_extraction
 
-    OCRSDK::Promise.from_response xml_string, @application_id, @password
+    OCRSDK::Promise.from_response xml_string
   end
 
   def as_text_sync(languages, wait_interval=OCRSDK::DEFAULT_POLL_TIME)
@@ -21,7 +21,7 @@ class OCRSDK::Image < OCRSDK::AbstractEntity
   def as_pdf(languages)
     xml_string = api_process_image @image_path, languages, :pdf, :document_conversion
 
-    OCRSDK::Promise.from_response xml_string, @application_id, @password
+    OCRSDK::Promise.from_response xml_string
   end
 
   def as_pdf_sync(languages, out_path=nil, wait_interval=OCRSDK::DEFAULT_POLL_TIME)

data/lib/ocrsdk/promise.rb

@@ -3,12 +3,12 @@ class OCRSDK::Promise < OCRSDK::AbstractEntity
 
   attr_reader :task_id, :status, :result_url, :estimate_processing_time
 
-  def self.from_response(xml_string, application_id=nil, password=nil)
-    OCRSDK::Promise.new(nil, application_id, password).parse_response xml_string
+  def self.from_response(xml_string)
+    OCRSDK::Promise.new(nil).parse_response xml_string
   end
 
-  def initialize(task_id, application_id=nil, password=nil)
-    super(application_id, password)
+  def initialize(task_id)
+    super()
     @task_id = task_id
   end
 

data/lib/ocrsdk/verifiers/format.rb

@@ -1,11 +1,11 @@
 module OCRSDK::Verifiers::Format
   # http://ocrsdk.com/documentation/specifications/image-formats/
   INPUT_FORMATS = [:bmp, :dcx, :pcx, :png, :jp2, :jpc, :jpg, :jpeg, :jfif, :pdf, 
-    :tif, :tiff, :gif, :djvu, :djv, :jb2]
+    :tif, :tiff, :gif, :djvu, :djv, :jb2].freeze
 
   # http://ocrsdk.com/documentation/apireference/processImage/
   OUTPUT_FORMATS = [:txt, :rtf, :docx, :xlsx, :pptx, :pdf_searchable, 
-    :pdf_text_and_images, :xml, :alto]
+    :pdf_text_and_images, :xml, :alto].freeze
 
   def format_to_s(format)
     format.to_s.camelize(:lower)

data/lib/ocrsdk/verifiers/language.rb

@@ -15,7 +15,7 @@ module OCRSDK::Verifiers::Language
     :portuguese_standard, :provencal, :quechua, :romanian, :romanian_moldavia, :romany, 
     :rundi, :russian, :samoan, :selkup, :serbian_cyrillic, :shona, :sioux, :slovenian, 
     :somali, :spanish, :sunda, :tabassaran, :tagalog, :tahitian, :tajik, :tatar, :tinpo, 
-    :tun, :turkish, :uighur_cyrillic, :ukrainian, :uzbek_cyrillic, :visayan]
+    :tun, :turkish, :uighur_cyrillic, :ukrainian, :uzbek_cyrillic, :visayan].freeze
 
   def language_to_s(language)
     language.to_s.camelize

data/lib/ocrsdk/verifiers/profile.rb

@@ -1,7 +1,7 @@
 module OCRSDK::Verifiers::Profile
   # http://ocrsdk.com/documentation/specifications/processing-profiles/
   PROFILES = [:document_conversion, :document_archiving, :text_extraction,
-    :field_level_recognition, :barcode_recognition]
+    :field_level_recognition, :barcode_recognition].freeze
 
   def profile_to_s(profile)
     profile.to_s.camelize(:lower)

data/lib/ocrsdk/verifiers/status.rb

@@ -1,7 +1,7 @@
 module OCRSDK::Verifiers::Status
   # http://ocrsdk.com/documentation/specifications/task-statuses/
   STATUSES = [:submitted, :queued, :in_progress, :completed, 
-    :processing_failed, :deleted, :not_enough_credits]
+    :processing_failed, :deleted, :not_enough_credits].freeze
 
   def status_to_s(status)
     status.to_s.camelize

data/lib/ocrsdk.rb

@@ -5,11 +5,18 @@ require 'pdf-reader'
 require 'rest-client'
 require 'active_support/inflector'
 require 'active_support/time'
+require 'active_support/configurable'
 
 # http://ocrsdk.com/documentation/apireference/
 module OCRSDK
+  include ActiveSupport::Configurable
+
   DEFAULT_POLL_TIME = 3
   SERVICE_URL = 'cloud.ocrsdk.com'
+
+  def self.setup
+    yield config
+  end
 end
 
 require 'ocrsdk/errors'

data/spec/abstract_entity_spec.rb

@@ -0,0 +1,19 @@
+# -*- encoding : utf-8 -*-
+require 'spec_helper'
+
+describe OCRSDK::AbstractEntity do
+  before do
+    OCRSDK.setup do |config|
+      config.application_id = 'meow'
+      config.password = 'purr'
+    end
+  end
+
+  it "should initialize and prepare url" do
+    OCRSDK::AbstractEntity.new.instance_eval { @url }.to_s.should_not be_empty
+  end
+
+  it "should prepare url correctly" do
+    OCRSDK::AbstractEntity.new.instance_eval { prepare_url 'meow!', "'pew'" }.to_s.should == "http://meow%21:%27pew%27@cloud.ocrsdk.com"
+  end
+end

data/spec/ocrsdk/image_spec.rb

@@ -2,6 +2,13 @@
 require 'spec_helper'
 
 describe OCRSDK::Image do
+  before do
+    OCRSDK.setup do |config|
+      config.application_id = 'app_id'
+      config.password = 'pass'
+    end    
+  end
+
   describe ".as_text" do
     subject { OCRSDK::Image.new 'image.jpg' }
     before { mock_ocrsdk }
@@ -46,7 +53,7 @@ describe OCRSDK::Image do
   end
 
   describe ".api_process_image" do
-    subject { OCRSDK::Image.new 'image.jpg', 'app_id', 'pass' }
+    subject { OCRSDK::Image.new 'image.jpg' }
 
     it "should raise UnsupportedLanguage on unsupported language" do
       expect {

data/spec/ocrsdk/pdf_spec.rb

@@ -2,6 +2,13 @@
 require 'spec_helper'
 
 describe OCRSDK::PDF do
+  before do
+    OCRSDK.setup do |config|
+      config.application_id = 'meow'
+      config.password = 'purr'
+    end    
+  end
+  
   describe ".recognizeable?" do
     it "should return false for a document with text only" do
       OCRSDK::PDF.new(TestFiles.lorem_pdf).recognizeable?.should be_false

data/spec/ocrsdk/promise_spec.rb

@@ -2,6 +2,12 @@
 require 'spec_helper'
 
 describe OCRSDK::Promise do
+  before do
+    OCRSDK.setup do |config|
+      config.application_id = 'app_id'
+      config.password = 'pass'
+    end
+  end
 
   describe ".parse_response" do
     context "correct response" do
@@ -57,7 +63,7 @@ describe OCRSDK::Promise do
   end
 
   describe ".api_update_status" do
-    subject { OCRSDK::Promise.new 'test', 'app_id', 'pass' }
+    subject { OCRSDK::Promise.new 'test' }
 
     it "should make an api call with correct url" do
       RestClient.stub(:get) do |url| 

data/spec/ocrsdk_spec.rb

@@ -5,4 +5,14 @@ describe OCRSDK do
   it "should have service url" do 
     OCRSDK::SERVICE_URL.length.should > 0
   end
+
+  it "should be configurable" do
+    OCRSDK.setup do |config|
+      config.application_id = 'meow'
+      config.password = 'purr'
+    end
+
+    OCRSDK.config.application_id.should == 'meow'
+    OCRSDK.config.password.should == 'purr'
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ocrsdk
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-30 00:00:00.000000000 Z
+date: 2012-12-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
@@ -154,23 +154,6 @@ files:
 - README.md
 - Rakefile
 - VERSION
-- coverage/index.css
-- coverage/index.html
-- coverage/jquery.js
-- coverage/jquery.tablesorter.js
-- coverage/lib/ocrsdk.rb.html
-- coverage/lib/ocrsdk/abstract_entity.rb.html
-- coverage/lib/ocrsdk/document.rb.html
-- coverage/lib/ocrsdk/errors.rb.html
-- coverage/lib/ocrsdk/image.rb.html
-- coverage/lib/ocrsdk/pdf.rb.html
-- coverage/lib/ocrsdk/promise.rb.html
-- coverage/lib/ocrsdk/verifiers.rb.html
-- coverage/lib/ocrsdk/verifiers/format.rb.html
-- coverage/lib/ocrsdk/verifiers/language.rb.html
-- coverage/lib/ocrsdk/verifiers/profile.rb.html
-- coverage/lib/ocrsdk/verifiers/status.rb.html
-- coverage/report.css
 - lib/ocrsdk.rb
 - lib/ocrsdk/abstract_entity.rb
 - lib/ocrsdk/document.rb
@@ -184,6 +167,7 @@ files:
 - lib/ocrsdk/verifiers/profile.rb
 - lib/ocrsdk/verifiers/status.rb
 - ocrsdk.gemspec
+- spec/abstract_entity_spec.rb
 - spec/fixtures/files/lorem.complex.pdf
 - spec/fixtures/files/lorem.pdf
 - spec/fixtures/files/malformed.pdf
@@ -228,6 +212,7 @@ signing_key:
 specification_version: 3
 summary: Abbyy's OCR (ocrsdk.com) API wrapper in Ruby.
 test_files:
+- spec/abstract_entity_spec.rb
 - spec/fixtures/files/lorem.complex.pdf
 - spec/fixtures/files/lorem.pdf
 - spec/fixtures/files/malformed.pdf

data/coverage/index.css

@@ -1,56 +0,0 @@
-.near {
-  background-color: #E0DEDB;
-  color: black;
-}
-
-.near a {
-  color: black;
-}
-
-.near a:visited {
-  color: black;
-}
-
-.miss {
-  font-weight: normal;
-}
-
-a {
-  color: black;
-}
-
-a:visited {
-  color: black;
-}
-
-.header {
-  cursor:pointer;
-}
-
-th.header:hover {
-  background-color:#666;
-}
-
-.headerSortUp:after {
-  content: "\25BC";
-/*  margin-left: 1em;*/
-}
-
-.headerSortDown:after {
-  content: "\25B2";
-  
-/*  margin-left: 1em;*/
-}
-
-#filters {
-  padding-bottom: 20px;
-  font-size: 16px;
-}
-
-#big_total {
-  float: right;
-  border: 3px solid #999;
-  padding: 10px;
-  font-size: 24px;
-  font-weight: bold;
-}

data/coverage/index.html

@@ -1,244 +0,0 @@
-<html>
-  <head>
-    <title>Coverage Report</title>
-    <link href="report.css?0.9295655220139563" media="screen" rel="stylesheet" type="text/css" />
-    <link href="index.css?0.1185955988799996" media="screen" rel="stylesheet" type="text/css" />
-    <script src="jquery.js?0.8317918045278826"></script>
-    <script src="jquery.tablesorter.js?0.4377297609330264"></script>
-    <script>
-      $(function() {
-        
-        function filterByPercent() {
-          var p = $('#filter_by_percent').val();
-          if (p == 0 ) {
-            $('#main tbody tr').show();
-          } else if (p == 10) {
-            $('#main tbody tr.row').show();
-            $('#main tbody tr.10').hide();
-          } else if (p == 100) {
-            $('#main tbody tr.row').hide();
-            $('#main tbody tr.10').show();
-          } else {
-            $('#main tbody tr.row').hide();
-            var x = 0;
-            while (x < p) {
-              $('#main tbody tr.' + x).show();
-              x++;
-            }
-          }
-        }
-        
-        function filterByName(name) {
-          $('#main tbody tr:visible').each(function() {
-            if ($(this).attr('id').indexOf(name) != -1) {
-              $(this).show();
-            } else {
-              $(this).hide();
-            }
-          });
-        }
-        
-        $('#filter_by_percent').change(function(e) {
-          filterByPercent();
-          filterByName($('#filter_by_name').val());
-        });
-      
-        $('#filter_by_name').keyup(function(e) {
-          filterByPercent();
-          filterByName($(this).val());
-        });
-        
-        $("#main").tablesorter(); 
-      });
-    </script>
-  </head>
-  <body>
-    <div id='big_total' class='miss'>99.44%</div>
-    
-    <h1>Coverage Report</h1>
-    
-    <div id='filters'>
-      Filter:
-      <input type='text' id='filter_by_name'>
-      
-      Code Coverage Threshold:
-      <select id='filter_by_percent'>
-        <option value='0'>Show All</option>
-        <option value='1'><= 10% Coverage</option>
-        <option value='2'><= 20% Coverage</option>
-        <option value='3'><= 30% Coverage</option>
-        <option value='4'><= 40% Coverage</option>
-        <option value='5'><= 50% Coverage</option>
-        <option value='6'><= 60% Coverage</option>
-        <option value='7'><= 70% Coverage</option>
-        <option value='8'><= 80% Coverage</option>
-        <option value='9'><= 90% Coverage</option>
-        <option value='10'>< 100% Coverage</option>
-        <option value='100'>= 100% Coverage</option>
-      </select>
-    </div>
-
-    <table cellpadding='0' cellspacing='1'>
-      <tr>
-        <th>Legend</th>
-      </tr>
-      <tr>
-        
-        <td class='hit'>This file was tested 100%!</td>
-      </tr>
-      <tr>
-        <td class='near'>This file was tested >90%!</td>
-      </tr>
-      <tr>
-        <td class='miss'>This file was not tested nearly enough!</td>
-      </tr>
-    </table>
-    
-    <div>&nbsp;</div>
-
-    <table cellpadding="0" cellspacing='1' id='main'>
-      <thead>
-        <tr class='header'>
-          <th>File</th>
-          <th>Lines</th>
-          <th>Lines Of Code</th>
-          <th>Untested Lines of Code</th>
-          <th>Tested %</th>
-        </tr>
-      </thead>
-      
-      <tbody>
-        
-          <tr class='row hit 10' id='lib/ocrsdk.rb'>
-            <td>
-              <a href="lib/ocrsdk.rb.html">lib/ocrsdk.rb</a>
-            </td>
-            <td>23</td>
-            <td>23</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/abstract_entity.rb'>
-            <td>
-              <a href="lib/ocrsdk/abstract_entity.rb.html">lib/ocrsdk/abstract_entity.rb</a>
-            </td>
-            <td>14</td>
-            <td>8</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/document.rb'>
-            <td>
-              <a href="lib/ocrsdk/document.rb.html">lib/ocrsdk/document.rb</a>
-            </td>
-            <td>8</td>
-            <td>3</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/errors.rb'>
-            <td>
-              <a href="lib/ocrsdk/errors.rb.html">lib/ocrsdk/errors.rb</a>
-            </td>
-            <td>13</td>
-            <td>10</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/image.rb'>
-            <td>
-              <a href="lib/ocrsdk/image.rb.html">lib/ocrsdk/image.rb</a>
-            </td>
-            <td>56</td>
-            <td>29</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/pdf.rb'>
-            <td>
-              <a href="lib/ocrsdk/pdf.rb.html">lib/ocrsdk/pdf.rb</a>
-            </td>
-            <td>27</td>
-            <td>12</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/promise.rb'>
-            <td>
-              <a href="lib/ocrsdk/promise.rb.html">lib/ocrsdk/promise.rb</a>
-            </td>
-            <td>87</td>
-            <td>47</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row miss 8' id='lib/ocrsdk/verifiers.rb'>
-            <td>
-              <a href="lib/ocrsdk/verifiers.rb.html">lib/ocrsdk/verifiers.rb</a>
-            </td>
-            <td>17</td>
-            <td>7</td>
-            <td>1</td>
-            <td>85.7%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/verifiers/format.rb'>
-            <td>
-              <a href="lib/ocrsdk/verifiers/format.rb.html">lib/ocrsdk/verifiers/format.rb</a>
-            </td>
-            <td>26</td>
-            <td>11</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/verifiers/language.rb'>
-            <td>
-              <a href="lib/ocrsdk/verifiers/language.rb.html">lib/ocrsdk/verifiers/language.rb</a>
-            </td>
-            <td>43</td>
-            <td>14</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/verifiers/profile.rb'>
-            <td>
-              <a href="lib/ocrsdk/verifiers/profile.rb.html">lib/ocrsdk/verifiers/profile.rb</a>
-            </td>
-            <td>15</td>
-            <td>7</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-          <tr class='row hit 10' id='lib/ocrsdk/verifiers/status.rb'>
-            <td>
-              <a href="lib/ocrsdk/verifiers/status.rb.html">lib/ocrsdk/verifiers/status.rb</a>
-            </td>
-            <td>19</td>
-            <td>9</td>
-            <td>0</td>
-            <td>100.0%</td>
-          </tr>
-        
-      </tbody>
-      
-      <tr class='header'>
-        <th>Total</th>
-        <th>348</th>
-        <th>180</th>
-        <th>1</th>
-        <th>99.44%</th>
-      </tr>
-    </table>
-    <p>Generated on: 2012-12-01 01:40:30 +0400</p>
-  </body>
-</html>