rtesseract 1.3.0 → 1.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 68e5f82fed2132e93d4ba1f432d5beca598682e9
-  data.tar.gz: f51f2ba570d2b0fdbb6483a334843dfd6ce0f8be
+  metadata.gz: 3c5a4dc5260f5eee845925b59f89fa712466f2a6
+  data.tar.gz: 21b1ad6d79f1d1f82483c46c199eb4d6fd06120e
 SHA512:
-  metadata.gz: a6ff8c4f5bb5587f7bf8656876e9b83e0a252cf4a52d5e002c68867faddafdf5b46f2a7e2d65c70d5db583ea00321cddb126e542a5c6321e318b7083933c5bce
-  data.tar.gz: f5a9763a75e42c0d7fe40be660a6864af58463260153335be319ba1d1f5334579ff3a19edfc14c8c7476d202251fa7f172eb5b4bdae8ce79fd286a55f58617af
+  metadata.gz: 4a78a082daf437c8e7e20313973e93a7e04f2dec161c46d2bf7d37cce86718001d45b12995c12d63930f26ef93ab3c492e0413a6be64d30129ede2fa8f689276
+  data.tar.gz: b622c914be59d0f3fdfae141f5bdfdaadfb53fa22d03b4497cf20a1b12a689fef340e2446b67112565ca1d5510782dc3f3925614ee978e7ba2b9c2dc2d977e03

data/.travis.yml

@@ -1,8 +1,11 @@
 language: ruby
-before_script: "./.travis.sh"
+addons:
+  apt:
+    packages:
+    - tesseract-ocr
+sudo: false
 rvm:
   - 1.9.3
   - 2.0.0
-  - 2.1.0
-  - 2.2.0
-
+  - 2.1.5
+  - 2.2.2

data/Gemfile

@@ -1,20 +1,19 @@
-source "http://rubygems.org"
+source 'http://rubygems.org'
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 gem 'nokogiri'
 
 group :development do
-  gem "rspec"
-  gem "rdoc"
-  gem "bundler"
-  gem "jeweler", "~> 2.0.1"
-  gem "simplecov"
+  gem 'rspec'
+  gem 'rdoc'
+  gem 'bundler'
+  gem 'jeweler', '~> 2.0.1'
+  gem 'simplecov'
   gem 'coveralls', require: false
 end
 
 group :test do
-  gem "rmagick"
-  gem "mini_magick"
-  gem "quick_magick"
+  gem 'rmagick'
+  gem 'mini_magick'
+  gem 'quick_magick'
 end
-

data/README.rdoc

@@ -60,8 +60,8 @@ It's very simple to use rtesseract:
   mix_block.to_s
 
 === OPTIONS
-  
-Processors Options  (_Rmagick_ is default) 
+
+Processors Options  (_Rmagick_ is default)
 
   RTesseract.new("test.jpg", :processor => "mini_magick")
   RTesseract.new("test.jpg", :processor => "quick_magick")
@@ -70,7 +70,7 @@ Processors Options  (_Rmagick_ is default)
 
   RTesseract.new("test.jpg", :processor => "none")
 
-Language Options 
+Language Options
 
   RTesseract.new("test.jpg", :lang => "deu")
      * eng   - English
@@ -83,18 +83,37 @@ Language Options
      * spa   - Spanish
      * vie   - Vietnamese
   Note: Make sure you have installed the language to tesseract
-  
+
 Other Options
 
   RTesseract.new("test.jpg", options: :digits)  # Only digit recognition
-  
+
   OR
-  
+
   RTesseract.new("test.jpg", options: [:digits, :quiet])
-  
+
+=== BOUNDING BOX: TO GET WORDS WITH THEIR POSITIONS
+
+  RTesseract::Box.new('test_words.png').words
+  # => [
+  #   {:word => 'If',  :x_start=>52, :y_start=>13, :x_end=>63, :y_end=>27},
+  #   {:word => 'you', :x_start=>69, :y_start=>17, :x_end=>100, :y_end=>31},
+  #   {:word => 'are', :x_start=>108, :y_start=>17, :x_end=>136, :y_end=>27},
+  #   {:word => 'a', :x_start=>143, :y_start=>17, :x_end=>151, :y_end=>27},
+  #   {:word => 'friend,', :x_start=>158, :y_start=>13, :x_end=>214, :y_end=>29},
+  #   {:word => 'you', :x_start=>51, :y_start=>39, :x_end=>82, :y_end=>53},
+  #   {:word => 'speak', :x_start=>90, :y_start=>35, :x_end=>140, :y_end=>53},
+  #   {:word => 'the', :x_start=>146, :y_start=>35, :x_end=>174, :y_end=>49},
+  #   {:word => 'password,', :x_start=>182, :y_start=>35, :x_end=>267, :y_end=>53},
+  #   {:word => 'and', :x_start=>51, :y_start=>57, :x_end=>81, :y_end=>71},
+  #   {:word => 'the', :x_start=>89, :y_start=>57, :x_end=>117, :y_end=>71},
+  #   {:word => 'doors', :x_start=>124, :y_start=>57, :x_end=>172, :y_end=>71},
+  #   {:word => 'will', :x_start=>180, :y_start=>57, :x_end=>208, :y_end=>71},
+  #   {:word => 'open.', :x_start=>216, :y_start=>61, :x_end=>263, :y_end=>75}
+  # ]
 
 == Contributing to rtesseract
- 
+
 * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
 * Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
 * Fork the project.

data/Rakefile

@@ -6,7 +6,7 @@ begin
   Bundler.setup(:default, :development)
 rescue Bundler::BundlerError => e
   $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
+  $stderr.puts 'Run `bundle install` to install missing gems'
   exit e.status_code
 end
 require 'rake'
@@ -14,13 +14,13 @@ require 'rake'
 require 'jeweler'
 Jeweler::Tasks.new do |gem|
   # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
-  gem.name = "rtesseract"
-  gem.homepage = "http://github.com/dannnylo/rtesseract"
-  gem.license = "MIT"
-  gem.summary = %Q{Ruby library for working with the Tesseract OCR.}
-  gem.description = %Q{Ruby library for working with the Tesseract OCR.}
-  gem.email = "dannnylo@gmail.com"
-  gem.authors = ["Danilo Jeremias da Silva"]
+  gem.name = 'rtesseract'
+  gem.homepage = 'http://github.com/dannnylo/rtesseract'
+  gem.license = 'MIT'
+  gem.summary = 'Ruby library for working with the Tesseract OCR.'
+  gem.description = 'Ruby library for working with the Tesseract OCR.'
+  gem.email = 'dannnylo@gmail.com'
+  gem.authors = ['Danilo Jeremias da Silva']
   # dependencies defined in Gemfile
 end
 Jeweler::RubygemsDotOrgTasks.new
@@ -31,17 +31,17 @@ RSpec::Core::RakeTask.new(:spec) do |spec|
   spec.pattern = FileList['spec/**/*_spec.rb']
 end
 
-desc "Code coverage detail"
+desc 'Code coverage detail'
 task :simplecov do
-  ENV['COVERAGE'] = "true"
+  ENV['COVERAGE'] = 'true'
   Rake::Task['spec'].execute
 end
 
-task :default => :spec
+task default: :spec
 
 require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+  version = File.exist?('VERSION') ? File.read('VERSION') : ''
 
   rdoc.rdoc_dir = 'rdoc'
   rdoc.title = "rtesseract #{version}"

data/VERSION

@@ -1 +1 @@
-1.3.0
+1.3.1

data/lib/processors/none.rb

@@ -10,7 +10,7 @@ module NoneProcessor
 
   def self.image_to_tif(source, _x = nil, _y = nil, _w = nil, _h = nil)
     tmp_file = Tempfile.new(['', '.tif'])
-    tmp_file.write(self.read_with_processor(source))
+    tmp_file.write(read_with_processor(source))
     tmp_file
   end
 
@@ -21,6 +21,6 @@ module NoneProcessor
     File.read(path)
   end
 
-  def self.image?(object)
+  def self.image?(*)
   end
 end

data/lib/processors/rmagick.rb

@@ -2,11 +2,11 @@
 # Add to rtesseract a image manipulation with RMagick
 module RMagickProcessor
   def self.setup
-    begin
-      require 'rmagick'
-    rescue
-      require 'RMagick'
-    end
+    require 'rmagick'
+  rescue LoadError
+    # :nocov:
+    require 'RMagick'
+    # :nocov:
   end
 
   def self.a_name?(name)
@@ -18,7 +18,10 @@ module RMagickProcessor
     cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
     cat.crop!(x, y, w, h) unless [x, y, w, h].compact == []
     cat.alpha Magick::DeactivateAlphaChannel
-    cat.write(tmp_file.path.to_s) { self.compression = Magick::NoCompression }
+    cat.write(tmp_file.path.to_s) {
+      # self.depth = 16
+      self.compression = Magick::NoCompression
+    }
     tmp_file
   end
 

data/lib/rtesseract.rb

@@ -1,6 +1,7 @@
 # encoding: UTF-8
 require 'pathname'
 require 'tempfile'
+require 'utils'
 
 require 'rtesseract/errors'
 require 'rtesseract/mixed'
@@ -17,10 +18,11 @@ require 'processors/none.rb'
 class RTesseract
   attr_accessor :image_object
   attr_accessor :options
+  attr_accessor :options_cmd
   attr_writer :lang
   attr_writer :psm
   attr_reader :processor
-  attr_accessor :options_cmd
+  attr_reader :source
 
   OPTIONS = %w(command lang psm processor debug clear_console_output options)
   # Aliases to languages names
@@ -32,8 +34,8 @@ class RTesseract
   }
 
   def initialize(src = '', options = {})
-    @options = command_line_options(options)
-    @value, @x, @y, @w, @h = ['']
+    command_line_options(options)
+    @value, @x, @y, @w, @h = [nil]
     @processor = RTesseract.choose_processor!(@processor)
     @source = @processor.image?(src) ? src : Pathname.new(src)
     initialize_hook
@@ -42,24 +44,17 @@ class RTesseract
   def initialize_hook
   end
 
-  def fetch_option(options, name, default)
-    options.fetch(name.to_s, options.fetch(name, default))
-  end
-
   def command_line_options(options)
-    @command = fetch_option(options, :command, default_command)
-    @lang = fetch_option(options, :lang, '')
-    @psm = fetch_option(options, :psm, nil)
-    @processor = fetch_option(options, :processor, 'rmagick')
-    @debug = fetch_option(options, :debug, false)
-    @options_cmd = fetch_option(options, :options, [])
+    @options = options
+    @command = @options.option(:command, default_command)
+    @lang = @options.option(:lang, '')
+    @psm = @options.option(:psm, nil)
+    @processor = @options.option(:processor, 'rmagick')
+    @debug = @options.option(:debug, false)
+    @options_cmd = @options.option(:options, [])
     @options_cmd = [@options_cmd] unless @options_cmd.is_a?(Array)
-
     # Disable clear console if debug mode
-    @clear_console_output = @debug ? false : fetch_option(options, :clear_console_output, true)
-
-    options.delete_if { |k, v| OPTIONS.include?(k.to_s) }
-    options
+    @clear_console_output = @debug ? false : options.option(:clear_console_output, true)
   end
 
   def default_command
@@ -68,32 +63,30 @@ class RTesseract
     'tesseract'
   end
 
-  def self.read(src = nil, options = {}, &block)
+  def self.read(src = nil, options = {})
     fail RTesseract::ImageNotSelectedError if src.nil?
-    processor = RTesseract.choose_processor!(options.delete(:processor) || options.delete('processor'))
+    processor = RTesseract.choose_processor!(options.option(:processor, nil))
     image = processor.read_with_processor(src.to_s)
-
     yield(image)
-    object = RTesseract.new('', options)
-    object.from_blob(image.to_blob)
+    object = RTesseract.new('', options).from_blob(image.to_blob)
     object
   end
 
-  def read(&block)
+  def read
     image = @processor.read_with_processor(@source.to_s)
     new_image = yield(image)
-    self.from_blob(new_image.to_blob, File.extname(@source.to_s))
+    from_blob(new_image.to_blob, File.extname(@source.to_s))
     self
   end
 
   def source=(src)
-    @value = ''
+    @value = nil
     @source = @processor.image?(src) ? src : Pathname.new(src)
   end
 
   # Crop image to convert
   def crop!(x, y, width, height)
-    @value = ''
+    @value = nil
     @x, @y, @w, @h = x.to_i, y.to_i, width.to_i, height.to_i
     self
   end
@@ -110,7 +103,7 @@ class RTesseract
     end
     true
   rescue => error
-    raise RTesseract::TempFilesNotRemovedError.new(:error => error, :files => files)
+    raise RTesseract::TempFilesNotRemovedError.new(error: error, files: files)
   end
 
   # Select the language
@@ -201,26 +194,27 @@ class RTesseract
     convert_text
     remove_file([@image, text_file_with_ext])
   rescue => error
-    raise RTesseract::ConversionError.new(error)
+    raise RTesseract::ConversionError.new(error), error, caller
   end
 
   # Read image from memory blob
   def from_blob(blob, ext = '')
-    blob_file = Tempfile.new(['blob', ext], :encoding => 'ascii-8bit')
-    blob_file.binmode
-    blob_file.write(blob)
+    blob_file = Tempfile.new(['blob', ext], encoding: 'ascii-8bit')
+    blob_file.binmode.write(blob)
     blob_file.rewind
     blob_file.flush
     self.source = blob_file.path
     convert
     remove_file([blob_file])
+    self
   rescue => error
-    raise RTesseract::ConversionError.new(error)
+    raise RTesseract::ConversionError.new(error), error, caller
   end
 
   # Output value
   def to_s
-    return @value if @value != ''
+    return @value if @value != nil
+
     if @processor.image?(@source) || @source.file?
       convert
       @value
@@ -249,4 +243,3 @@ class RTesseract
     processor
   end
 end
-

data/lib/rtesseract/box.rb

@@ -23,15 +23,13 @@ class RTesseract
     end
 
     def parse_file
-      Nokogiri::HTML(File.read(text_file_with_ext)).css('span.ocrx_word, span.ocr_word')
+      html = Nokogiri::HTML(File.read(text_file_with_ext))
+      html.css('span.ocrx_word, span.ocr_word')
     end
 
     def convert_text
       text_objects =  []
-      parse_file.each do |word|
-        attributes = word.attributes['title'].value.to_s.gsub(';', '').split(' ')
-        text_objects << { :word => word.text, :x_start => attributes[1].to_i, :y_start => attributes[2].to_i , :x_end => attributes[3].to_i, :y_end => attributes[4].to_i }
-      end
+      parse_file.each { |word| text_objects << BoxParser.new(word).to_h }
       @value = text_objects
     end
 
@@ -49,5 +47,24 @@ class RTesseract
         fail RTesseract::ImageNotSelectedError.new(@source)
       end
     end
+
+    # Parse word data from html.
+    class BoxParser
+      def initialize(word_html)
+        @word = word_html
+        title = @word.attributes['title'].value.to_s
+        @attributes = title.gsub(';', '').split(' ')
+      end
+
+      def to_h
+        {
+          word: @word.text,
+          x_start: @attributes[1].to_i,
+          y_start: @attributes[2].to_i,
+          x_end: @attributes[3].to_i,
+          y_end: @attributes[4].to_i
+        }
+      end
+    end
   end
 end

data/lib/rtesseract/box_char.rb

@@ -19,8 +19,8 @@ class RTesseract
     def convert_text
       text_objects = []
       parse_file.each_line do |line|
-        char, x_start, y_start, x_end, y_end, word = line.split(' ')
-        text_objects << { :char => char, :x_start => x_start.to_i, :y_start => y_start.to_i , :x_end => x_end.to_i, :y_end => y_end.to_i }
+        char, x_start, y_start, x_end, y_end, _word = line.split(' ')
+        text_objects << { char: char, x_start: x_start.to_i, y_start: y_start.to_i, x_end: x_end.to_i, y_end: y_end.to_i }
       end
       @value = text_objects
     end

data/lib/rtesseract/mixed.rb

@@ -14,7 +14,7 @@ class RTesseract
 
     def area(x, y, width, height)
       @value = ''
-      @areas << { :x => x,  :y => y, :width => width, :height => height }
+      @areas << { x: x,  y: y, width: width, height: height }
     end
 
     def clear_areas
@@ -29,7 +29,7 @@ class RTesseract
         @value << image.to_s
       end
     rescue => error
-      raise RTesseract::ConversionError.new(error)
+      raise RTesseract::ConversionError.new(error), error, caller
     end
 
     # Output value

data/lib/utils.rb

@@ -0,0 +1,5 @@
+class Hash
+  def option(attr_name, default)
+    delete(attr_name.to_s) || delete(attr_name) || default
+  end
+end

data/rtesseract.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: rtesseract 1.3.0 ruby lib
+# stub: rtesseract 1.3.1 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "rtesseract"
-  s.version = "1.3.0"
+  s.version = "1.3.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Danilo Jeremias da Silva"]
-  s.date = "2015-06-23"
+  s.date = "2015-10-07"
   s.description = "Ruby library for working with the Tesseract OCR."
   s.email = "dannnylo@gmail.com"
   s.extra_rdoc_files = [
@@ -21,7 +21,6 @@ Gem::Specification.new do |s|
   s.files = [
     ".document",
     ".rspec",
-    ".travis.sh",
     ".travis.yml",
     "Gemfile",
     "Gemfile.lock",
@@ -38,7 +37,10 @@ Gem::Specification.new do |s|
     "lib/rtesseract/box_char.rb",
     "lib/rtesseract/errors.rb",
     "lib/rtesseract/mixed.rb",
+    "lib/utils.rb",
     "rtesseract.gemspec",
+    "spec/images/README.pdf",
+    "spec/images/blank.tif",
     "spec/images/mixed.tif",
     "spec/images/orientation_reverse.png",
     "spec/images/test with spaces.tif",
@@ -56,7 +58,7 @@ Gem::Specification.new do |s|
   ]
   s.homepage = "http://github.com/dannnylo/rtesseract"
   s.licenses = ["MIT"]
-  s.rubygems_version = "2.2.2"
+  s.rubygems_version = "2.4.3"
   s.summary = "Ruby library for working with the Tesseract OCR."
 
   if s.respond_to? :specification_version then

data/spec/rtesseract_box_char_spec.rb

@@ -1,82 +1,82 @@
 # encoding: UTF-8
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
-describe "Rtesseract::BoxChar" do
+describe 'Rtesseract::BoxChar' do
   before do
-    @path = Pathname.new(__FILE__.gsub('rtesseract_box_char_spec.rb','')).expand_path
+    @path = Pathname.new(__FILE__.gsub('rtesseract_box_char_spec.rb', '')).expand_path
     @image_tiff = @path.join('images', 'test.tif').to_s
     @words_image = @path.join('images', 'test_words.png').to_s
   end
 
-
-  it "bounding box by char" do
+  it 'bounding box by char' do
     expect(RTesseract::BoxChar.new(@image_tiff).characters.is_a?(Array)).to eql(true)
     expect(RTesseract::BoxChar.new(@image_tiff).characters).to eql([
-      {:char=>"4", :x_start=>145, :y_start=>14, :x_end=>159, :y_end=>33},
-      {:char=>"3", :x_start=>184, :y_start=>14, :x_end=>196, :y_end=>33},
-      {:char=>"X", :x_start=>222, :y_start=>14, :x_end=>238, :y_end=>32},
-      {:char=>"F", :x_start=>260, :y_start=>14, :x_end=>273, :y_end=>32}]
-    )
+      { char: '4', x_start: 145, y_start: 14, x_end: 159, y_end: 33 },
+      { char: '3', x_start: 184, y_start: 14, x_end: 196, y_end: 33 },
+      { char: 'X', x_start: 222, y_start: 14, x_end: 238, y_end: 32 },
+      { char: 'F', x_start: 260, y_start: 14, x_end: 273, y_end: 32 }])
+
     expect(RTesseract::BoxChar.new(@words_image).characters).to eql([
-      {:char => 'I', :x_start=>52, :y_start=>91, :x_end=>54, :y_end=>104},
-      {:char => 'f', :x_start=>56, :y_start=>91, :x_end=>63, :y_end=>105},
-      {:char => 'y', :x_start=>69, :y_start=>87, :x_end=>79, :y_end=>101},
-      {:char => 'o', :x_start=>80, :y_start=>91, :x_end=>90, :y_end=>101},
-      {:char => 'u', :x_start=>92, :y_start=>91, :x_end=>100, :y_end=>101},
-      {:char => 'a', :x_start=>108, :y_start=>91, :x_end=>116, :y_end=>101},
-      {:char => 'r', :x_start=>119, :y_start=>91, :x_end=>125, :y_end=>101},
-      {:char => 'e', :x_start=>126, :y_start=>91, :x_end=>136, :y_end=>101},
-      {:char => 'a', :x_start=>143, :y_start=>91, :x_end=>151, :y_end=>101},
-      {:char => 'f', :x_start=>158, :y_start=>91, :x_end=>165, :y_end=>105},
-      {:char => 'r', :x_start=>166, :y_start=>91, :x_end=>172, :y_end=>101},
-      {:char => 'i', :x_start=>174, :y_start=>91, :x_end=>176, :y_end=>105},
-      {:char => 'e', :x_start=>178, :y_start=>91, :x_end=>188, :y_end=>101},
-      {:char => 'n', :x_start=>190, :y_start=>91, :x_end=>198, :y_end=>101},
-      {:char => 'd', :x_start=>200, :y_start=>91, :x_end=>209, :y_end=>105},
-      {:char => ',', :x_start=>211, :y_start=>89, :x_end=>214, :y_end=>93},
-      {:char => 'y', :x_start=>51, :y_start=>65, :x_end=>61, :y_end=>79},
-      {:char => 'o', :x_start=>62, :y_start=>69, :x_end=>72, :y_end=>79},
-      {:char => 'u', :x_start=>74, :y_start=>69, :x_end=>82, :y_end=>79},
-      {:char => 's', :x_start=>90, :y_start=>69, :x_end=>97, :y_end=>79},
-      {:char => 'p', :x_start=>99, :y_start=>65, :x_end=>108, :y_end=>79},
-      {:char => 'e', :x_start=>109, :y_start=>69, :x_end=>119, :y_end=>79},
-      {:char => 'a', :x_start=>120, :y_start=>69, :x_end=>128, :y_end=>79},
-      {:char => 'k', :x_start=>131, :y_start=>69, :x_end=>140, :y_end=>83},
-      {:char => 't', :x_start=>146, :y_start=>69, :x_end=>152, :y_end=>82},
-      {:char => 'h', :x_start=>154, :y_start=>69, :x_end=>162, :y_end=>83},
-      {:char => 'e', :x_start=>164, :y_start=>69, :x_end=>174, :y_end=>79},
-      {:char => 'p', :x_start=>182, :y_start=>65, :x_end=>191, :y_end=>79},
-      {:char => 'a', :x_start=>192, :y_start=>69, :x_end=>200, :y_end=>79},
-      {:char => 's', :x_start=>202, :y_start=>69, :x_end=>209, :y_end=>79},
-      {:char => 's', :x_start=>210, :y_start=>69, :x_end=>217, :y_end=>79},
-      {:char => 'w', :x_start=>219, :y_start=>69, :x_end=>232, :y_end=>79},
-      {:char => 'o', :x_start=>234, :y_start=>69, :x_end=>244, :y_end=>79},
-      {:char => 'r', :x_start=>246, :y_start=>69, :x_end=>252, :y_end=>79},
-      {:char => 'd', :x_start=>253, :y_start=>69, :x_end=>262, :y_end=>83},
-      {:char => ',', :x_start=>264, :y_start=>67, :x_end=>267, :y_end=>71},
-      {:char => 'a', :x_start=>51, :y_start=>47, :x_end=>59, :y_end=>57},
-      {:char => 'n', :x_start=>62, :y_start=>47, :x_end=>70, :y_end=>57},
-      {:char => 'd', :x_start=>72, :y_start=>47, :x_end=>81, :y_end=>61},
-      {:char => 't', :x_start=>89, :y_start=>47, :x_end=>95, :y_end=>60},
-      {:char => 'h', :x_start=>97, :y_start=>47, :x_end=>105, :y_end=>61},
-      {:char => 'e', :x_start=>107, :y_start=>47, :x_end=>117, :y_end=>57},
-      {:char => 'd', :x_start=>124, :y_start=>47, :x_end=>133, :y_end=>61},
-      {:char => 'o', :x_start=>135, :y_start=>47, :x_end=>145, :y_end=>57},
-      {:char => 'o', :x_start=>146, :y_start=>47, :x_end=>156, :y_end=>57},
-      {:char => 'r', :x_start=>158, :y_start=>47, :x_end=>164, :y_end=>57},
-      {:char => 's', :x_start=>165, :y_start=>47, :x_end=>172, :y_end=>57},
-      {:char => 'w', :x_start=>180, :y_start=>47, :x_end=>193, :y_end=>57},
-      {:char => 'i', :x_start=>196, :y_start=>47, :x_end=>198, :y_end=>61},
-      {:char => 'l', :x_start=>201, :y_start=>47, :x_end=>203, :y_end=>61},
-      {:char => 'l', :x_start=>206, :y_start=>47, :x_end=>208, :y_end=>61},
-      {:char => 'o', :x_start=>216, :y_start=>47, :x_end=>226, :y_end=>57},
-      {:char => 'p', :x_start=>228, :y_start=>43, :x_end=>237, :y_end=>57},
-      {:char => 'e', :x_start=>238, :y_start=>47, :x_end=>248, :y_end=>57},
-      {:char => 'n', :x_start=>250, :y_start=>47, :x_end=>258, :y_end=>57},
-      {:char => '.', :x_start=>261, :y_start=>47, :x_end=>263, :y_end=>49}]
-    )
+      { char: 'I', x_start: 52, y_start: 91, x_end: 54, y_end: 104 },
+      { char: 'f', x_start: 56, y_start: 91, x_end: 63, y_end: 105 },
+      { char: 'y', x_start: 69, y_start: 87, x_end: 79, y_end: 101 },
+      { char: 'o', x_start: 80, y_start: 91, x_end: 90, y_end: 101 },
+      { char: 'u', x_start: 92, y_start: 91, x_end: 100, y_end: 101 },
+      { char: 'a', x_start: 108, y_start: 91, x_end: 116, y_end: 101 },
+      { char: 'r', x_start: 119, y_start: 91, x_end: 125, y_end: 101 },
+      { char: 'e', x_start: 126, y_start: 91, x_end: 136, y_end: 101 },
+      { char: 'a', x_start: 143, y_start: 91, x_end: 151, y_end: 101 },
+      { char: 'f', x_start: 158, y_start: 91, x_end: 165, y_end: 105 },
+      { char: 'r', x_start: 166, y_start: 91, x_end: 172, y_end: 101 },
+      { char: 'i', x_start: 174, y_start: 91, x_end: 176, y_end: 105 },
+      { char: 'e', x_start: 178, y_start: 91, x_end: 188, y_end: 101 },
+      { char: 'n', x_start: 190, y_start: 91, x_end: 198, y_end: 101 },
+      { char: 'd', x_start: 200, y_start: 91, x_end: 209, y_end: 105 },
+      { char: ',', x_start: 211, y_start: 89, x_end: 214, y_end: 93 },
+      { char: 'y', x_start: 51, y_start: 65, x_end: 61, y_end: 79 },
+      { char: 'o', x_start: 62, y_start: 69, x_end: 72, y_end: 79 },
+      { char: 'u', x_start: 74, y_start: 69, x_end: 82, y_end: 79 },
+      { char: 's', x_start: 90, y_start: 69, x_end: 97, y_end: 79 },
+      { char: 'p', x_start: 99, y_start: 65, x_end: 108, y_end: 79 },
+      { char: 'e', x_start: 109, y_start: 69, x_end: 119, y_end: 79 },
+      { char: 'a', x_start: 120, y_start: 69, x_end: 128, y_end: 79 },
+      { char: 'k', x_start: 131, y_start: 69, x_end: 140, y_end: 83 },
+      { char: 't', x_start: 146, y_start: 69, x_end: 152, y_end: 82 },
+      { char: 'h', x_start: 154, y_start: 69, x_end: 162, y_end: 83 },
+      { char: 'e', x_start: 164, y_start: 69, x_end: 174, y_end: 79 },
+      { char: 'p', x_start: 182, y_start: 65, x_end: 191, y_end: 79 },
+      { char: 'a', x_start: 192, y_start: 69, x_end: 200, y_end: 79 },
+      { char: 's', x_start: 202, y_start: 69, x_end: 209, y_end: 79 },
+      { char: 's', x_start: 210, y_start: 69, x_end: 217, y_end: 79 },
+      { char: 'w', x_start: 219, y_start: 69, x_end: 232, y_end: 79 },
+      { char: 'o', x_start: 234, y_start: 69, x_end: 244, y_end: 79 },
+      { char: 'r', x_start: 246, y_start: 69, x_end: 252, y_end: 79 },
+      { char: 'd', x_start: 253, y_start: 69, x_end: 262, y_end: 83 },
+      { char: ',', x_start: 264, y_start: 67, x_end: 267, y_end: 71 },
+      { char: 'a', x_start: 51, y_start: 47, x_end: 59, y_end: 57 },
+      { char: 'n', x_start: 62, y_start: 47, x_end: 70, y_end: 57 },
+      { char: 'd', x_start: 72, y_start: 47, x_end: 81, y_end: 61 },
+      { char: 't', x_start: 89, y_start: 47, x_end: 95, y_end: 60 },
+      { char: 'h', x_start: 97, y_start: 47, x_end: 105, y_end: 61 },
+      { char: 'e', x_start: 107, y_start: 47, x_end: 117, y_end: 57 },
+      { char: 'd', x_start: 124, y_start: 47, x_end: 133, y_end: 61 },
+      { char: 'o', x_start: 135, y_start: 47, x_end: 145, y_end: 57 },
+      { char: 'o', x_start: 146, y_start: 47, x_end: 156, y_end: 57 },
+      { char: 'r', x_start: 158, y_start: 47, x_end: 164, y_end: 57 },
+      { char: 's', x_start: 165, y_start: 47, x_end: 172, y_end: 57 },
+      { char: 'w', x_start: 180, y_start: 47, x_end: 193, y_end: 57 },
+      { char: 'i', x_start: 196, y_start: 47, x_end: 198, y_end: 61 },
+      { char: 'l', x_start: 201, y_start: 47, x_end: 203, y_end: 61 },
+      { char: 'l', x_start: 206, y_start: 47, x_end: 208, y_end: 61 },
+      { char: 'o', x_start: 216, y_start: 47, x_end: 226, y_end: 57 },
+      { char: 'p', x_start: 228, y_start: 43, x_end: 237, y_end: 57 },
+      { char: 'e', x_start: 238, y_start: 47, x_end: 248, y_end: 57 },
+      { char: 'n', x_start: 250, y_start: 47, x_end: 258, y_end: 57 },
+      { char: '.', x_start: 261, y_start: 47, x_end: 263, y_end: 49 }])
+
+    expect { RTesseract::BoxChar.new(@image_tiff, command: 'tesseract_error').to_s }.to raise_error(RTesseract::ConversionError)
+    expect { RTesseract::BoxChar.new(@image_tiff + '_not_exist').to_s }.to raise_error(RTesseract::ImageNotSelectedError)
 
-    expect{RTesseract::BoxChar.new(@image_tiff, {:command => "tesseract_error"}).to_s }.to raise_error(RTesseract::ConversionError)
-    expect{RTesseract::BoxChar.new(@image_tiff + "_not_exist").to_s }.to raise_error(RTesseract::ImageNotSelectedError)
+    #expect(RTesseract::BoxChar.new(@path.join('images', 'blank.tif').to_s, options: :digits).characters).to eql([])
   end
 end

data/spec/rtesseract_box_spec.rb

@@ -1,36 +1,37 @@
 # encoding: UTF-8
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
-describe "Rtesseract::Box" do
+describe 'Rtesseract::Box' do
   before do
-    @path = Pathname.new(__FILE__.gsub("rtesseract_box_spec.rb","")).expand_path
-    @image_tiff = @path.join("images","test.tif").to_s
-    @words_image = @path.join("images","test_words.png").to_s
+    @path = Pathname.new(__FILE__.gsub('rtesseract_box_spec.rb', '')).expand_path
+    @image_tiff = @path.join('images', 'test.tif').to_s
+    @words_image = @path.join('images', 'test_words.png').to_s
   end
 
-
-  it "bounding box" do
+  it 'bounding box' do
     expect(RTesseract.new(@words_image).to_s).to eql("If you are a friend,\nyou speak the password,\nand the doors will open.\n\n")
     expect(RTesseract::Box.new(@words_image).words).to eql([
-      {:word => 'If',  :x_start=>52, :y_start=>13, :x_end=>63, :y_end=>27},
-      {:word => 'you', :x_start=>69, :y_start=>17, :x_end=>100, :y_end=>31},
-      {:word => 'are', :x_start=>108, :y_start=>17, :x_end=>136, :y_end=>27},
-      {:word => 'a', :x_start=>143, :y_start=>17, :x_end=>151, :y_end=>27},
-      {:word => 'friend,', :x_start=>158, :y_start=>13, :x_end=>214, :y_end=>29},
-      {:word => 'you', :x_start=>51, :y_start=>39, :x_end=>82, :y_end=>53},
-      {:word => 'speak', :x_start=>90, :y_start=>35, :x_end=>140, :y_end=>53},
-      {:word => 'the', :x_start=>146, :y_start=>35, :x_end=>174, :y_end=>49},
-      {:word => 'password,', :x_start=>182, :y_start=>35, :x_end=>267, :y_end=>53},
-      {:word => 'and', :x_start=>51, :y_start=>57, :x_end=>81, :y_end=>71},
-      {:word => 'the', :x_start=>89, :y_start=>57, :x_end=>117, :y_end=>71},
-      {:word => 'doors', :x_start=>124, :y_start=>57, :x_end=>172, :y_end=>71},
-      {:word => 'will', :x_start=>180, :y_start=>57, :x_end=>208, :y_end=>71},
-      {:word => 'open.', :x_start=>216, :y_start=>61, :x_end=>263, :y_end=>75}
+      { word: 'If',  x_start: 52, y_start: 13, x_end: 63, y_end: 27 },
+      { word: 'you', x_start: 69, y_start: 17, x_end: 100, y_end: 31 },
+      { word: 'are', x_start: 108, y_start: 17, x_end: 136, y_end: 27 },
+      { word: 'a', x_start: 143, y_start: 17, x_end: 151, y_end: 27 },
+      { word: 'friend,', x_start: 158, y_start: 13, x_end: 214, y_end: 29 },
+      { word: 'you', x_start: 51, y_start: 39, x_end: 82, y_end: 53 },
+      { word: 'speak', x_start: 90, y_start: 35, x_end: 140, y_end: 53 },
+      { word: 'the', x_start: 146, y_start: 35, x_end: 174, y_end: 49 },
+      { word: 'password,', x_start: 182, y_start: 35, x_end: 267, y_end: 53 },
+      { word: 'and', x_start: 51, y_start: 57, x_end: 81, y_end: 71 },
+      { word: 'the', x_start: 89, y_start: 57, x_end: 117, y_end: 71 },
+      { word: 'doors', x_start: 124, y_start: 57, x_end: 172, y_end: 71 },
+      { word: 'will', x_start: 180, y_start: 57, x_end: 208, y_end: 71 },
+      { word: 'open.', x_start: 216, y_start: 61, x_end: 263, y_end: 75 }
     ])
 
     expect(RTesseract::Box.new(@image_tiff).words.is_a?(Array)).to eql(true)
-    expect(RTesseract::Box.new(@words_image).to_s).to eql("If you are a friend, you speak the password, and the doors will open.")
-    expect{RTesseract::Box.new(@image_tiff, {:command => "tesseract_error"}).to_s }.to raise_error(RTesseract::ConversionError)
-    expect{RTesseract::Box.new(@image_tiff + "_not_exist").to_s }.to raise_error(RTesseract::ImageNotSelectedError)
+    expect(RTesseract::Box.new(@words_image).to_s).to eql('If you are a friend, you speak the password, and the doors will open.')
+    expect { RTesseract::Box.new(@image_tiff, command: 'tesseract_error').to_s }.to raise_error(RTesseract::ConversionError)
+    expect { RTesseract::Box.new(@image_tiff + '_not_exist').to_s }.to raise_error(RTesseract::ImageNotSelectedError)
+
+    #expect(RTesseract::Box.new(@path.join('images', 'blank.tif').to_s, options: :digits).words).to eql([])
   end
 end

data/spec/rtesseract_mixed_spec.rb

@@ -1,46 +1,49 @@
 # encoding: UTF-8
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 
-describe "Rtesseract::Mixed" do
+describe 'Rtesseract::Mixed' do
   before do
-    @path = Pathname.new(__FILE__.gsub("rtesseract_mixed_spec.rb","")).expand_path
-    @image_tif = @path.join("images","mixed.tif").to_s
-    @image2_tif = @path.join("images","mixed2.tif").to_s
+    @path = Pathname.new(__FILE__.gsub('rtesseract_mixed_spec.rb', '')).expand_path
+    @image_tif = @path.join('images', 'mixed.tif').to_s
+    @image2_tif = @path.join('images', 'mixed2.tif').to_s
   end
 
-  it "should be instantiable" do
+  it 'should be instantiable' do
     expect(RTesseract::Mixed.new.class).to eql(RTesseract::Mixed)
     expect(RTesseract::Mixed.new(@image_tif).class).to eql(RTesseract::Mixed)
   end
 
-  it "should translate parts of the image to text" do
-    mix_block = RTesseract::Mixed.new(@image_tif,{:psm=>7}) do |image|
-      image.area(28,  19, 25, 25) #position of 4
+  it 'should translate parts of the image to text' do
+    mix_block = RTesseract::Mixed.new(@image_tif, psm: 7) do |image|
+      image.area(28,  19, 25, 25) # position of 4
       image.area(180, 22, 20, 28) # position of 3
-      image.area(218, 22, 24, 28) # position of z
-      image.area(248, 24, 22, 22) # position of z
+      image.area(218, 22, 24, 28) # position of F
+      image.area(248, 24, 22, 22) # position of F
     end
-    expect(mix_block.to_s_without_spaces).to eql("43FF")
+    expect(mix_block.to_s_without_spaces).to eql('43FF')
     mix_block.clear_areas
     expect(mix_block.areas).to eql([])
 
-    mix_block = RTesseract::Mixed.new(@image_tif,{:areas => [
-      {:x => 28,  :y=>19, :width=>25, :height=>25 }, #position of 4
-      {:x => 180,  :y=>22, :width=>20, :height=>28}, # position of 3
-      {:x => 218,  :y=>22, :width=>24, :height=>28}, # position of z
-      {:x => 248,  :y=>24, :width=>22, :height=>22}  # position of z
-    ],:psm=>7})
-    expect(mix_block.to_s_without_spaces).to eql("43FF")
+    @areas = []
+    @areas << { x: 28, y: 19, width: 25, height: 25 } # position of 4
+    @areas << { x: 180, y: 22, width: 20, height: 28 } # position of 3
+    @areas << { x: 218, y: 22, width: 24, height: 28 } # position of f
+    @areas << { x: 248, y: 24, width: 22, height: 22 }  # position of f
+
+    mix_block = RTesseract::Mixed.new(@image_tif, areas: @areas, psm: 7)
+    expect(mix_block.to_s_without_spaces).to eql('43FF')
+
+    mix_block = RTesseract::Mixed.new(@path.join('images', 'blank.tif').to_s, areas: @areas, psm: 7)
+    expect(mix_block.to_s_without_spaces).to eql('')
   end
 
-  it " get a error" do
-    mix_block = RTesseract::Mixed.new(@path.join("images","test_not_exists.png").to_s,{:areas => [{:x => 28,  :y=>19, :width=>25, :height=>25 }
-    ],:psm=>7})
-    expect{ mix_block.to_s_without_spaces }.to raise_error(RTesseract::ImageNotSelectedError)
+  it ' get a error' do
+    @areas = [{ x: 28, y: 19, width: 25, height: 25 }]
 
+    mix_block = RTesseract::Mixed.new(@path.join('images', 'test_not_exists.png').to_s, areas: @areas, psm: 7)
+    expect { mix_block.to_s_without_spaces }.to raise_error(RTesseract::ImageNotSelectedError)
 
-    mix_block = RTesseract::Mixed.new(@image_tif,{:areas => [{:x => 28,  :y=>19, :width=>25, :height=>25 }
-    ],:psm=>7, :command => "tesseract_error"})
-    expect{ mix_block.to_s }.to raise_error(RTesseract::ConversionError)
+    mix_block = RTesseract::Mixed.new(@image_tif, areas: @areas, psm: 7, command: 'tesseract_error')
+    expect { mix_block.to_s }.to raise_error(RTesseract::ConversionError)
   end
 end

data/spec/rtesseract_spec.rb

@@ -1,121 +1,130 @@
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 # encoding: UTF-8
 require 'pathname'
+
+# Class to rise error
 class MakeStringError
   def to_s
-    raise "error"
+    fail 'error'
   end
 end
 
-describe "Rtesseract" do
+describe 'Rtesseract' do
   before do
-    @path = Pathname.new(__FILE__.gsub("rtesseract_spec.rb","")).expand_path
-    @image_tif = @path.join("images","test.tif").to_s
+    @path = Pathname.new(__FILE__.gsub('rtesseract_spec.rb', '')).expand_path
+    @image_tif = @path.join('images', 'test.tif').to_s
   end
 
-  it " be instantiable" do
+  it ' be instantiable' do
     expect(RTesseract.new.class).to eql(RTesseract)
-    expect(RTesseract.new("").class).to eql(RTesseract)
+    expect(RTesseract.new('').class).to eql(RTesseract)
     expect(RTesseract.new(@image_tif).class).to eql(RTesseract)
   end
 
-  it " translate image to text" do
-    expect(RTesseract.new(@image_tif).to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@image_tif, {:processor => 'mini_magick'}).to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@path.join("images","test1.tif").to_s).to_s_without_spaces).to eql("V2V4")
-    expect(RTesseract.new(@path.join("images","test with spaces.tif").to_s).to_s_without_spaces).to eql("V2V4")
+  it ' translate image to text' do
+    expect(RTesseract.new(@image_tif).to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@image_tif, processor: 'mini_magick').to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@path.join('images', 'test1.tif').to_s).to_s_without_spaces).to eql('V2V4')
+    expect(RTesseract.new(@path.join('images', 'test with spaces.tif').to_s).to_s_without_spaces).to eql('V2V4')
+  end
 
+  it ' translate images .png, .jpg, .bmp' do
+    expect(RTesseract.new(@path.join('images', 'test.png').to_s).to_s_without_spaces).to eql('HW9W')
+    expect(RTesseract.new(@path.join('images', 'test.jpg').to_s).to_s_without_spaces).to eql('3R8F')
+    expect(RTesseract.new(@path.join('images', 'test.bmp').to_s).to_s_without_spaces).to eql('FLA6')
   end
 
-  it " translate images .png, .jpg, .bmp" do
-    expect(RTesseract.new(@path.join("images","test.png").to_s).to_s_without_spaces).to eql("HW9W")
-    expect(RTesseract.new(@path.join("images","test.jpg").to_s).to_s_without_spaces).to eql("3R8F")
-    expect(RTesseract.new(@path.join("images","test.bmp").to_s).to_s_without_spaces).to eql("FLA6")
+  it ' should not error with depth > 32' do
+    #expect(RTesseract.new(@path.join('images', 'README.pdf').to_s, debug: true).to_s_without_spaces).to eql('')
   end
 
-  it " support  diferent processors" do
-    #Rmagick
-    expect(RTesseract.new(@image_tif).to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@image_tif, :processor => 'rmagick').to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@path.join("images","test.png").to_s, :processor => 'rmagick').to_s_without_spaces).to eql("HW9W")
+  it ' support  diferent processors' do
+    # Rmagick
+    expect(RTesseract.new(@image_tif).to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@image_tif, processor: 'rmagick').to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@path.join('images', 'test.png').to_s, processor: 'rmagick').to_s_without_spaces).to eql('HW9W')
 
-    #MiniMagick
-    expect(RTesseract.new(@image_tif, :processor => 'mini_magick').to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@path.join("images","test.png").to_s, :processor => 'mini_magick').to_s_without_spaces).to eql("HW9W")
+    # MiniMagick
+    expect(RTesseract.new(@image_tif, processor: 'mini_magick').to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@path.join('images', 'test.png').to_s, processor: 'mini_magick').to_s_without_spaces).to eql('HW9W')
 
-    #QuickMagick
-    expect(RTesseract.new(@image_tif, :processor => 'quick_magick').to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@path.join("images","test.png").to_s, :processor => 'quick_magick').to_s_without_spaces).to eql("HW9W")
+    # QuickMagick
+    expect(RTesseract.new(@image_tif, processor: 'quick_magick').to_s_without_spaces).to eql('43XF')
+    expect(RTesseract.new(@path.join('images', 'test.png').to_s, processor: 'quick_magick').to_s_without_spaces).to eql('HW9W')
 
-    #NoneMagick
-    expect(RTesseract.new(@image_tif, :processor => 'none').to_s_without_spaces).to eql("43XF")
+    # NoneMagick
+    expect(RTesseract.new(@image_tif, processor: 'none').to_s_without_spaces).to eql('43XF')
   end
 
-  it " change the image" do
+  it ' change the image' do
     image = RTesseract.new(@image_tif)
-    expect(image.to_s_without_spaces).to eql("43XF")
-    image.source = @path.join("images","test1.tif").to_s
-    expect(image.to_s_without_spaces).to eql("V2V4")
+    expect(image.to_s_without_spaces).to eql('43XF')
+    image.source = @path.join('images', 'test1.tif').to_s
+    expect(image.to_s_without_spaces).to eql('V2V4')
   end
 
-  it " select the language" do
-    #English
-    expect(RTesseract.new(@image_tif,{:lang=>"eng"}).lang).to eql(" -l eng ")
-    expect(RTesseract.new(@image_tif,{:lang=>"en"}).lang).to eql(" -l eng ")
-    expect(RTesseract.new(@image_tif,{:lang=>"en-US"}).lang).to eql(" -l eng ")
-    expect(RTesseract.new(@image_tif,{:lang=>"english"}).lang).to eql(" -l eng ")
+  it ' returns the source' do
+    image = RTesseract.new(@image_tif)
+    expect(image.source).to eql(Pathname.new(@image_tif))
+  end
 
-    #Portuguese
-    expect(RTesseract.new(@image_tif,{:lang=>"por"}).lang).to eql(" -l por ")
-    expect(RTesseract.new(@image_tif,{:lang=>"pt-BR"}).lang).to eql(" -l por ")
-    expect(RTesseract.new(@image_tif,{:lang=>"pt-br"}).lang).to eql(" -l por ")
-    expect(RTesseract.new(@image_tif,{:lang=>"pt"}).lang).to eql(" -l por ")
-    expect(RTesseract.new(@image_tif,{:lang=>"portuguese"}).lang).to eql(" -l por ")
+  it ' select the language' do
+    # English
+    expect(RTesseract.new(@image_tif, lang: 'eng').lang).to eql(' -l eng ')
+    expect(RTesseract.new(@image_tif, lang: 'en').lang).to eql(' -l eng ')
+    expect(RTesseract.new(@image_tif, lang: 'en-US').lang).to eql(' -l eng ')
+    expect(RTesseract.new(@image_tif, lang: 'english').lang).to eql(' -l eng ')
 
-    expect(RTesseract.new(@image_tif,{:lang=>"eng"}).to_s_without_spaces).to eql("43XF")
-    #RTesseract.new(@image_tif,{:lang=>"por"}).to_s_without_spaces).to eql("43XF")
-    expect(RTesseract.new(@image_tif,{:lang=>"eng"}).lang).to eql(" -l eng ")
+    # Portuguese
+    expect(RTesseract.new(@image_tif, lang: 'por').lang).to eql(' -l por ')
+    expect(RTesseract.new(@image_tif, lang: 'pt-BR').lang).to eql(' -l por ')
+    expect(RTesseract.new(@image_tif, lang: 'pt-br').lang).to eql(' -l por ')
+    expect(RTesseract.new(@image_tif, lang: 'pt').lang).to eql(' -l por ')
+    expect(RTesseract.new(@image_tif, lang: 'portuguese').lang).to eql(' -l por ')
 
-    #Inválid lang object
-    expect(RTesseract.new(@image_tif,{:lang=>MakeStringError.new}).lang).to eql("")
-  end
+    expect(RTesseract.new(@image_tif, lang: 'eng').to_s_without_spaces).to eql('43XF')
 
-  it " select options" do
-     expect(RTesseract.new(@image_tif).options_cmd).to eql([])
-     expect(RTesseract.new(@image_tif, options: 'digits').options_cmd).to eql(['digits'])
-     expect(RTesseract.new(@image_tif, options: :digits).options_cmd).to eql([:digits])
-     expect(RTesseract.new(@image_tif, options: [:digits, :quiet]).options_cmd).to eql([:digits, :quiet])
+    expect(RTesseract.new(@image_tif, lang: 'eng').lang).to eql(' -l eng ')
+
+    # Invalid lang object
+    expect(RTesseract.new(@image_tif, lang: MakeStringError.new).lang).to eql('')
   end
 
-  it " be configurable" do
-     expect(RTesseract.new(@image_tif,{:chop_enable=>0,:enable_assoc=>0,:display_text=>0}).config).to eql("chop_enable 0\nenable_assoc 0\ndisplay_text 0")
-     expect(RTesseract.new(@image_tif,{:chop_enable=>0}).config).to eql("chop_enable 0")
-     expect(RTesseract.new(@image_tif,{:chop_enable=>0,:enable_assoc=>0}).config).to eql("chop_enable 0\nenable_assoc 0")
-     expect(RTesseract.new(@image_tif,{:chop_enable=>0}).to_s_without_spaces).to eql("43XF")
+  it ' select options' do
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+    expect(RTesseract.new(@image_tif, options: 'digits').options_cmd).to eql(['digits'])
+    expect(RTesseract.new(@image_tif, options: :digits).options_cmd).to eql([:digits])
+    expect(RTesseract.new(@image_tif, options: [:digits, :quiet]).options_cmd).to eql([:digits, :quiet])
   end
 
-  it " crop image" do
-     expect(RTesseract.new(@image_tif,{:psm=>7}).crop!(140,10,36,40).to_s_without_spaces).to eql("4")
-     expect(RTesseract.new(@image_tif,{:psm=>7}).crop!(180,10,36,40).to_s_without_spaces).to eql("3")
-     expect(RTesseract.new(@image_tif,{:psm=>7}).crop!(216,10,20,40).to_s_without_spaces).to eql("X")
-     expect(RTesseract.new(@image_tif,{:psm=>7}).crop!(240,10,30,40).to_s_without_spaces).to eql("F")
+  it ' be configurable' do
+    expect(RTesseract.new(@image_tif, chop_enable: 0, enable_assoc: 0, display_text: 0).config).to eql("chop_enable 0\nenable_assoc 0\ndisplay_text 0")
+    expect(RTesseract.new(@image_tif, chop_enable: 0).config).to eql('chop_enable 0')
+    expect(RTesseract.new(@image_tif, chop_enable: 0, enable_assoc: 0).config).to eql("chop_enable 0\nenable_assoc 0")
+    expect(RTesseract.new(@image_tif, chop_enable: 0).to_s_without_spaces).to eql('43XF')
   end
 
+  it ' crop image' do
+    expect(RTesseract.new(@image_tif, psm: 7).crop!(140, 10, 36, 40).to_s_without_spaces).to eql('4')
+    expect(RTesseract.new(@image_tif, psm: 7).crop!(180, 10, 36, 40).to_s_without_spaces).to eql('3')
+    expect(RTesseract.new(@image_tif, psm: 7).crop!(216, 10, 20, 40).to_s_without_spaces).to eql('X')
+    expect(RTesseract.new(@image_tif, psm: 7).crop!(240, 10, 30, 40).to_s_without_spaces).to eql('F')
+  end
 
-  it " read image from blob" do
-    image = Magick::Image.read(@path.join("images","test.png").to_s).first
-    blob = image.quantize(256,Magick::GRAYColorspace).to_blob
+  it ' read image from blob' do
+    image = Magick::Image.read(@path.join('images', 'test.png').to_s).first
+    blob = image.quantize(256, Magick::GRAYColorspace).to_blob
 
-    test = RTesseract.new("", {:psm => 7})
+    test = RTesseract.new('', psm: 7)
     test.from_blob(blob)
-    expect(test.to_s_without_spaces).to eql("HW9W")
+    expect(test.to_s_without_spaces).to eql('HW9W')
 
-    test = RTesseract.new("", {:psm => 7})
-    expect{test.from_blob('') }.to raise_error(RTesseract::ConversionError)
+    test = RTesseract.new('', psm: 7)
+    expect { test.from_blob('') }.to raise_error(RTesseract::ConversionError)
   end
 
-  it " use a instance" do
-    expect(RTesseract.new(Magick::Image.read(@image_tif.to_s).first).to_s_without_spaces).to eql("43XF")
+  it ' use a instance' do
+    expect(RTesseract.new(Magick::Image.read(@image_tif.to_s).first).to_s_without_spaces).to eql('43XF')
     expect(RMagickProcessor.a_name?('teste')).to eql(false)
     expect(RMagickProcessor.a_name?('rmagick')).to eql(true)
     expect(RMagickProcessor.a_name?('RMagickProcessor')).to eql(true)
@@ -129,46 +138,50 @@ describe "Rtesseract" do
     expect(NoneProcessor.a_name?('NoneProcessor')).to eql(true)
   end
 
-  it " change image in a block" do
-    test = RTesseract.read(@path.join("images","test.png").to_s){}
+  it ' change image in a block' do
+    test = RTesseract.read(@path.join('images', 'test.png').to_s) {}
     expect(test.class).to eql(RTesseract)
 
     test = RTesseract.new(@image_tif)
     test.read do |image|
       image = image.quantize(256, Magick::GRAYColorspace)
     end
-    expect(test.to_s_without_spaces).to eql("43XF")
+    expect(test.to_s_without_spaces).to eql('43XF')
+
+    test = RTesseract.new(@path.join('images', 'blank.tif').to_s)
+    test.read do |image|
+      image
+    end
+    expect(test.to_s_without_spaces).to eql('')
 
-    test = RTesseract.read(@path.join("images","test.png").to_s) do |image|
-      #image = image.white_threshold(245)
-      #image = image.quantize(256,Magick::GRAYColorspace)
+    test = RTesseract.read(@path.join('images', 'test.png').to_s) do |image|
       image.rotate(90)
     end
-    expect(test.to_s_without_spaces).to eql("HW9W")
+    expect(test.to_s_without_spaces).to eql('HW9W')
 
-    test = RTesseract.read(@path.join("images","test.jpg").to_s,{:lang=>'en'}) do |image|
+    test = RTesseract.read(@path.join('images', 'test.jpg').to_s, lang: 'en') do |image|
       image = image.white_threshold(245).quantize(256, Magick::GRAYColorspace)
     end
-    expect(test.to_s_without_spaces).to eql("3R8F")
+    expect(test.to_s_without_spaces).to eql('3R8F')
 
-    test = RTesseract.read(@path.join("images","test.jpg").to_s,{:lang=>'en', :processor => 'mini_magick'}) do |image|
-      image.gravity "south"
+    test = RTesseract.read(@path.join('images', 'test.jpg').to_s, lang: 'en', processor: 'mini_magick') do |image|
+      image.gravity 'south'
     end
-    expect(test.to_s_without_spaces).to eql("3R8F")
+    expect(test.to_s_without_spaces).to eql('3R8F')
   end
 
-  it " get a error" do
-    expect{ RTesseract.new(@path.join("images","test.jpg").to_s, {:command => "tesseract_error"}).to_s }.to raise_error(RTesseract::ConversionError)
-    expect{ RTesseract.new(@path.join("images","test_not_exists.png").to_s).to_s }.to raise_error(RTesseract::ImageNotSelectedError)
+  it ' get a error' do
+    expect { RTesseract.new(@path.join('images', 'test.jpg').to_s, command: 'tesseract_error').to_s }.to raise_error(RTesseract::ConversionError)
+    expect { RTesseract.new(@path.join('images', 'test_not_exists.png').to_s).to_s }.to raise_error(RTesseract::ImageNotSelectedError)
 
-    #Inválid psm object
-    expect(RTesseract.new(@image_tif,{:psm=>MakeStringError.new}).psm).to eql("")
+    # Invalid psm object
+    expect(RTesseract.new(@image_tif, psm:  MakeStringError.new).psm).to eql('')
   end
 
-  it "remove a file" do
+  it 'remove a file' do
     rtesseract = RTesseract.new('.')
     rtesseract.remove_file(Tempfile.new('config'))
 
-    expect{ rtesseract.remove_file(Pathname.new(Dir.tmpdir).join("test_not_exists")) }.to raise_error(RTesseract::TempFilesNotRemovedError)
+    expect { rtesseract.remove_file(Pathname.new(Dir.tmpdir).join('test_not_exists')) }.to raise_error(RTesseract::TempFilesNotRemovedError)
   end
 end

data/spec/spec_helper.rb

@@ -3,17 +3,16 @@ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))
 require 'rspec'
 require 'coveralls'
-require "simplecov"
+require 'simplecov'
 SimpleCov.start do
-  add_filter "/spec/"
+  add_filter '/spec/'
 end
 Coveralls.wear!
 
 require 'rtesseract'
 # Requires supporting files with custom matchers and macros, etc,
 # in ./support/ and its subdirectories.
-Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each {|f| require f}
-
-RSpec.configure do |config|
+Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each { |f| require f }
 
+RSpec.configure do # |config|
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.3.1
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-23 00:00:00.000000000 Z
+date: 2015-10-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -118,7 +118,6 @@ extra_rdoc_files:
 files:
 - ".document"
 - ".rspec"
-- ".travis.sh"
 - ".travis.yml"
 - Gemfile
 - Gemfile.lock
@@ -135,7 +134,10 @@ files:
 - lib/rtesseract/box_char.rb
 - lib/rtesseract/errors.rb
 - lib/rtesseract/mixed.rb
+- lib/utils.rb
 - rtesseract.gemspec
+- spec/images/README.pdf
+- spec/images/blank.tif
 - spec/images/mixed.tif
 - spec/images/orientation_reverse.png
 - spec/images/test with spaces.tif
@@ -170,7 +172,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.

data/.travis.sh

@@ -1,2 +0,0 @@
-#!/bin/sh
-sudo apt-get install tesseract-ocr tesseract-ocr-por