rtesseract 2.0.0 → 2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 695108fd1fe3b6bb921444dc8daadb248466dd13
-  data.tar.gz: d2e8b38f6a54c7ffd004863de72a9d880be9bdbc
+  metadata.gz: 6eae58279cf744227e79b7bbc9180f7aea852547
+  data.tar.gz: 3836aa96d24b7f1a0b957cf803553f547cc33544
 SHA512:
-  metadata.gz: c28af3ffb9d288fb580d22f68f99d3e159919284735ff6cf84a91ba8da636d4c771568019c0db4ae968bbad030cfc8e187100ca075b7904fb05eda5658ca8c0d
-  data.tar.gz: 3fdb3195471c7b0a3674c000d6ebafe4a7474cb6336911ff93e898233f872bb220b56b309be2e1148a19eb2abd1a764fa60ef09bfcfea66a103bdb35f836d8bd
+  metadata.gz: 0ef57359c7c7f43094a50838b6d29d28d7808c9cadd8f2b8514c613be030161f8d640c41ba3d403c00fb59fdf85ffcbc57795f6c65b8418ad348eb1a6c07e901
+  data.tar.gz: ff5f0f94c8039bd0b38b0c9ec2618b4c38b07b9707e28ff29a3bb943abc85d5afaa543dfba1ba2b9e565d056ea558eda9b7f6d222a6adb43614cd86c6e8fdcac

data/.travis.yml

@@ -3,6 +3,7 @@ addons:
   apt:
     packages:
     - tesseract-ocr
+
 sudo: false
 rvm:
   - 1.9.3

data/CHANGELOG.md

@@ -0,0 +1,22 @@
+## v2.0.1
+
+#### Changed
+
+* Refactoring of some small classes
+
+## v2.0.0
+
+#### Added
+
+* Support to options --tessdata-dir, --user-words and --user-patterns
+* Ruby 2.3.0 to travis tests.
+
+#### Changed
+
+* Refactoring of some classes
+* Crop options is a hash with x,y,w,h keys.
+* Areas of RTesseract::Mixed now changed :width to :w and :height to :h.
+
+#### Removed
+
+* Support to quick_magick gem.

data/Gemfile.lock

@@ -3,9 +3,8 @@ GEM
   specs:
     addressable (2.4.0)
     builder (3.2.2)
-    coveralls (0.8.10)
+    coveralls (0.8.13)
       json (~> 1.8)
-      rest-client (>= 1.6.8, < 2)
       simplecov (~> 0.11.0)
       term-ansicolor (~> 1.3)
       thor (~> 0.19.1)
@@ -14,8 +13,6 @@ GEM
       thread_safe (~> 0.3, >= 0.3.1)
     diff-lcs (1.2.5)
     docile (1.1.5)
-    domain_name (0.5.25)
-      unf (>= 0.0.5, < 1.0.0)
     faraday (0.9.2)
       multipart-post (>= 1.2, < 3)
     git (1.3.0)
@@ -28,8 +25,6 @@ GEM
       oauth2
     hashie (3.4.3)
     highline (1.7.8)
-    http-cookie (1.0.2)
-      domain_name (~> 0.5)
     jeweler (2.1.1)
       builder
       bundler (>= 1.0)
@@ -42,13 +37,11 @@ GEM
       semver
     json (1.8.3)
     jwt (1.5.1)
-    mime-types (2.99)
-    mini_magick (4.3.6)
+    mini_magick (4.5.1)
     mini_portile2 (2.0.0)
     multi_json (1.11.2)
     multi_xml (0.5.5)
     multipart-post (2.0.0)
-    netrc (0.11.0)
     nokogiri (1.6.7.2)
       mini_portile2 (~> 2.0.0.rc2)
     oauth2 (1.1.0)
@@ -61,26 +54,22 @@ GEM
     rake (11.1.2)
     rdoc (4.2.2)
       json (~> 1.4)
-    rest-client (1.8.0)
-      http-cookie (>= 1.0.2, < 2.0)
-      mime-types (>= 1.16, < 3.0)
-      netrc (~> 0.7)
     rmagick (2.15.4)
     rspec (3.4.0)
       rspec-core (~> 3.4.0)
       rspec-expectations (~> 3.4.0)
       rspec-mocks (~> 3.4.0)
-    rspec-core (3.4.1)
+    rspec-core (3.4.4)
       rspec-support (~> 3.4.0)
     rspec-expectations (3.4.0)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.4.0)
-    rspec-mocks (3.4.0)
+    rspec-mocks (3.4.1)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.4.0)
     rspec-support (3.4.1)
     semver (1.0.1)
-    simplecov (0.11.1)
+    simplecov (0.11.2)
       docile (~> 1.1.0)
       json (~> 1.8)
       simplecov-html (~> 0.10.0)
@@ -90,9 +79,6 @@ GEM
     thor (0.19.1)
     thread_safe (0.3.5)
     tins (1.6.0)
-    unf (0.1.4)
-      unf_ext
-    unf_ext (0.0.7.1)
 
 PLATFORMS
   ruby
@@ -109,4 +95,4 @@ DEPENDENCIES
   simplecov
 
 BUNDLED WITH
-   1.10.6
+   1.11.2

data/VERSION

@@ -1 +1 @@
-2.0.0
+2.0.1

data/lib/processors/mini_magick.rb

@@ -1,32 +1,43 @@
 # encoding: UTF-8
-# Add to rtesseract a image manipulation with MiniMagick
-module MiniMagickProcessor
-  def self.setup
-    require 'mini_magick'
-  end
+# RTesseract class
+class RTesseract
+  # Processor Module
+  module Processor
+    # Add to rtesseract a image manipulation with MiniMagick
+    module MiniMagickProcessor
+      # Setup Processor
+      def self.setup
+        require 'mini_magick'
+      end
 
-  def self.a_name?(name)
-    %w(mini_magick MiniMagickProcessor).include?(name.to_s)
-  end
+      # Check if is this Processor
+      def self.a_name?(name)
+        %w(mini_magick MiniMagickProcessor).include?(name.to_s)
+      end
 
-  def self.image_to_tif(source, _points = {})
-    tmp_file = Tempfile.new(['', '.tif'])
-    cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
-    cat.format('tif') do |c|
-      c.compress 'None'
-      c.alpha 'off'
-    end
-    cat.crop("#{_points[:w]}x#{_points[:h]}+#{_points[:x]}+#{_points[:y]}") if _points.is_a?(Hash) && _points.values.compact != []
-    cat.alpha 'off'
-    cat.write tmp_file.path.to_s
-    tmp_file
-  end
+      # Convert Image to Tiff
+      def self.image_to_tif(source, points = {})
+        tmp_file = Tempfile.new(['', '.tif'])
+        cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
+        cat.format('tif') do |c|
+          c.compress 'None'
+          c.alpha 'off'
+        end
+        cat.crop("#{points[:w]}x#{points[:h]}+#{points[:x]}+#{points[:y]}") if points.is_a?(Hash) && points.values.compact != []
+        cat.alpha 'off'
+        cat.write tmp_file.path.to_s
+        tmp_file
+      end
 
-  def self.read_with_processor(path)
-    MiniMagick::Image.open(path.to_s)
-  end
+      # Cast instance of image
+      def self.read_with_processor(path)
+        MiniMagick::Image.open(path.to_s)
+      end
 
-  def self.image?(object)
-    object.class == MiniMagick::Image
+      # Check if is a MiniMagick image
+      def self.image?(object)
+        object.class == MiniMagick::Image
+      end
+    end
   end
-end
+end

data/lib/processors/none.rb

@@ -1,26 +1,34 @@
 # encoding: UTF-8
-# Add to rtesseract a image without manipulation
-module NoneProcessor
-  def self.setup
-  end
-
-  def self.a_name?(name)
-    %w(none NoneProcessor).include?(name.to_s)
-  end
+# RTesseract class
+class RTesseract
+  # Processor Module
+  module Processor
+    # Add to rtesseract a image without manipulation
+    module NoneProcessor
+      # Setup Processor
+      def self.setup
+      end
 
-  def self.image_to_tif(source, _points = {})
-    tmp_file = Tempfile.new(['', '.tif'])
-    tmp_file.write(read_with_processor(source))
-    tmp_file
-  end
+      # Check if is this Processor
+      def self.a_name?(name)
+        %w(none NoneProcessor).include?(name.to_s)
+      end
 
-  def self.need_crop?(*)
-  end
+      # Convert Image to Tiff
+      def self.image_to_tif(source, _points = {})
+        tmp_file = Tempfile.new(['', '.tif'])
+        tmp_file.write(read_with_processor(source))
+        tmp_file
+      end
 
-  def self.read_with_processor(path)
-    File.read(path)
-  end
+      # Cast instance of image
+      def self.read_with_processor(path)
+        File.read(path)
+      end
 
-  def self.image?(*)
+      # Check if is a image
+      def self.image?(*)
+      end
+    end
   end
 end

data/lib/processors/rmagick.rb

@@ -1,35 +1,46 @@
 # encoding: UTF-8
-# Add to rtesseract a image manipulation with RMagick
-module RMagickProcessor
-  def self.setup
-    require 'rmagick'
-  rescue LoadError
-    # :nocov:
-    require 'RMagick'
-    # :nocov:
-  end
+# RTesseract class
+class RTesseract
+  # Processor Module
+  module Processor
+    # Add to rtesseract a image manipulation with RMagick
+    module RMagickProcessor
+      # Setup Processor
+      def self.setup
+        require 'rmagick'
+      rescue LoadError
+        # :nocov:
+        require 'RMagick'
+        # :nocov:
+      end
 
-  def self.a_name?(name)
-    %w(rmagick RMagickProcessor).include?(name.to_s)
-  end
+      # Check if is this Processor
+      def self.a_name?(name)
+        %w(rmagick RMagickProcessor).include?(name.to_s)
+      end
 
-  def self.image_to_tif(source, _points = {})
-    tmp_file = Tempfile.new(['', '.tif'])
-    cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
-    cat.crop!(_points[:x], _points[:y], _points[:w], _points[:h]) if _points.is_a?(Hash) && _points.values.compact != []
-    cat.alpha Magick::DeactivateAlphaChannel
-    cat.write(tmp_file.path.to_s) do
-      # self.depth = 16
-      self.compression = Magick::NoCompression
-    end
-    tmp_file
-  end
+      # Convert Image to Tiff
+      def self.image_to_tif(source, points = {})
+        tmp_file = Tempfile.new(['', '.tif'])
+        cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
+        cat.crop!(points[:x], points[:y], points[:w], points[:h]) if points.is_a?(Hash) && points.values.compact != []
+        cat.alpha Magick::DeactivateAlphaChannel
+        cat.write(tmp_file.path.to_s) do
+          # self.depth = 16
+          self.compression = Magick::NoCompression
+        end
+        tmp_file
+      end
 
-  def self.read_with_processor(path)
-    Magick::Image.read(path.to_s).first
-  end
+      # Cast instance of image
+      def self.read_with_processor(path)
+        Magick::Image.read(path.to_s).first
+      end
 
-  def self.image?(object)
-    object.class == Magick::Image
+      # Check if is a RMagick image
+      def self.image?(object)
+        object.class == Magick::Image
+      end
+    end
   end
 end

data/lib/rtesseract.rb

@@ -1,18 +1,10 @@
 # encoding: UTF-8
 require 'pathname'
 require 'tempfile'
-require 'utils'
 
+require 'rtesseract/utils'
 require 'rtesseract/configuration'
 require 'rtesseract/errors'
-require 'rtesseract/mixed'
-require 'rtesseract/box'
-require 'rtesseract/box_char'
-
-# Processors
-require 'processors/rmagick.rb'
-require 'processors/mini_magick.rb'
-require 'processors/none.rb'
 
 # Ruby wrapper for Tesseract OCR
 class RTesseract
@@ -23,58 +15,30 @@ class RTesseract
   def initialize(src = '', options = {})
     self.configuration = RTesseract.local_config(options)
     @options = options || {}
-    @value, @points = [nil, {}]
-    @processor = RTesseract.choose_processor!(self.configuration.processor)
+    @value = nil
+    @points = {}
+    @processor = RTesseract::Processor.choose_processor!(configuration.processor)
     @source = @processor.image?(src) ? src : Pathname.new(src)
     initialize_hook
   end
 
+  # Hook to end of initialize method
   def initialize_hook
   end
 
-  def self.read(src = nil, options = {})
-    fail RTesseract::ImageNotSelectedError if src.nil?
-    processor = RTesseract.choose_processor!(options.option(:processor, nil))
-    image = processor.read_with_processor(src.to_s)
-    yield(image)
-    object = RTesseract.new('', options).from_blob(image.to_blob)
-    object
-  end
-
-  def read
-    image = @processor.read_with_processor(@source.to_s)
-    new_image = yield(image)
-    from_blob(new_image.to_blob, File.extname(@source.to_s))
-    self
-  end
-
+  # Define the source
   def source=(src)
     @value = nil
     @source = @processor.image?(src) ? src : Pathname.new(src)
   end
 
   # Crop image to convert
-  def crop!(_points = {})
+  def crop!(points = {})
     @value = nil
-    @points = _points
+    @points = points
     self
   end
 
-  # Remove files
-  def remove_file(files = [])
-    files.each do |file|
-      if file.is_a?(Tempfile)
-        file.close
-        file.unlink
-      else
-        File.unlink(file)
-      end
-    end
-    true
-  rescue => error
-    raise RTesseract::TempFilesNotRemovedError.new(error: error, files: files)
-  end
-
   # Select the language
   # ===Languages
   ## * eng   - English
@@ -88,58 +52,56 @@ class RTesseract
   ## * vie   - Vietnamese
   ## Note: Make sure you have installed the language to tesseract
   def lang
-    language = "#{self.configuration.lang}".strip.downcase
-    LANGUAGES.each do |value, names|
-      return " -l #{value} " if names.include? language
-    end
-    return " -l #{language} " if language.size > 0
+    language = (configuration.lang || 'eng').to_s.strip.downcase
+    " -l #{LANGUAGES[language] || language} "
+  rescue
     ''
+  end
+
+  # Convert option to command
+  def option_to_string(prefix, value = nil)
+    (value.nil? ? '' : " #{prefix} #{value} ")
   rescue
     ''
   end
 
   # Page Segment Mode
   def psm
-    (self.configuration.psm.nil? ? '' : " -psm #{self.configuration.psm} ")
-  rescue
-    ''
+    option_to_string('-psm', configuration.psm)
   end
 
   # Tessdata Dir
   def tessdata_dir
-    (self.configuration.tessdata_dir.nil? ? '' : " --tessdata-dir #{self.configuration.tessdata_dir} ")
-  rescue
-    ''
+    option_to_string('--tessdata-dir', configuration.tessdata_dir)
   end
 
   # User Words
   def user_words
-    (self.configuration.user_words.nil? ? '' : " --user-words #{self.configuration.user_words} ")
-  rescue
-    ''
+    option_to_string('--user-words', configuration.user_words)
   end
 
   # User Patterns
   def user_patterns
-    (self.configuration.user_patterns.nil? ? '' : " --user-patterns #{self.configuration.user_patterns} ")
-  rescue
-    ''
+    option_to_string('--user-patterns', configuration.user_patterns)
   end
 
   # Options on line
   def options_cmd
-    self.configuration.options_cmd
+    configuration.options_cmd
   end
 
+  # Hook to before config
   def config_hook
   end
 
+  # Convert configurations
   def config
     @options ||= {}
     config_hook
     @options.map { |k, v| "#{k} #{v}" }.join("\n")
   end
 
+  # Write config to file
   def config_file
     config_hook
     return '' if @options == {}
@@ -151,34 +113,41 @@ class RTesseract
 
   # TODO: Clear console for MacOS or Windows
   def clear_console_output
-    return '' if self.configuration.debug
+    return '' if configuration.debug
     return '2>/dev/null' if File.exist?('/dev/null') # Linux console clear
   end
 
+  # Get image
   def image
     (@image = @processor.image_to_tif(@source, @points)).path
   end
 
+  # Extension of file
   def file_ext
     '.txt'
   end
 
+  # Rand file path
   def text_file
     @text_file = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
   end
 
+  # Full path of file with extension
   def text_file_with_ext(ext = nil)
     [@text_file, ext || file_ext].join('')
   end
 
+  # Run command
   def convert_command
-    `#{self.configuration.command} "#{image}" "#{text_file}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{self.configuration.options_cmd.join(' ')}`
+    `#{configuration.command} "#{image}" "#{text_file}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{configuration.options_cmd.join(' ')}`
   end
 
+  # Read result file
   def convert_text
     @value = File.read(text_file_with_ext).to_s
   end
 
+  # Hook to convert
   def after_convert_hook
   end
 
@@ -187,21 +156,7 @@ class RTesseract
     convert_command
     after_convert_hook
     convert_text
-    remove_file([@image, text_file_with_ext])
-  rescue => 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.write(blob)
-    blob_file.rewind
-    blob_file.flush
-    self.source = blob_file.path
-    convert
-    remove_file([blob_file])
-    self
+    RTesseract::Utils.remove_files([@image, text_file_with_ext])
   rescue => error
     raise RTesseract::ConversionError.new(error), error, caller
   end
@@ -220,19 +175,17 @@ class RTesseract
 
   # Remove spaces and break-lines
   def to_s_without_spaces
-    to_s.gsub(' ', '').gsub("\n", '').gsub("\r", '')
-  end
-
-  def self.choose_processor!(processor)
-    processor =
-    if MiniMagickProcessor.a_name?(processor.to_s)
-      MiniMagickProcessor
-    elsif NoneProcessor.a_name?(processor.to_s)
-      NoneProcessor
-    else
-      RMagickProcessor
-    end
-    processor.setup
-    processor
+    to_s.delete(' ').delete("\n").delete("\r")
   end
 end
+
+require 'rtesseract/mixed'
+require 'rtesseract/box'
+require 'rtesseract/box_char'
+require 'rtesseract/blob'
+require 'rtesseract/processor'
+
+# Processors
+require 'processors/rmagick.rb'
+require 'processors/mini_magick.rb'
+require 'processors/none.rb'

data/lib/rtesseract/blob.rb

@@ -0,0 +1,34 @@
+# Blob methods
+class RTesseract
+  # Read image from memory blob
+  def self.read(src = nil, options = {})
+    fail RTesseract::ImageNotSelectedError if src.nil?
+    processor = RTesseract::Processor.choose_processor!(options.option(:processor, nil))
+    image = processor.read_with_processor(src.to_s)
+    yield(image)
+    object = RTesseract.new('', options).from_blob(image.to_blob)
+    object
+  end
+
+  # Read image from memory blob
+  def read
+    image = @processor.read_with_processor(@source.to_s)
+    new_image = yield(image)
+    from_blob(new_image.to_blob, File.extname(@source.to_s))
+    self
+  end
+
+  # Read image from memory blob
+  def from_blob(blob, ext = '')
+    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
+    RTesseract::Utils.remove_files([blob_file])
+    self
+  rescue => error
+    raise RTesseract::ConversionError.new(error), error, caller
+  end
+end

data/lib/rtesseract/box.rb

@@ -2,37 +2,45 @@
 require 'nokogiri'
 require 'fileutils'
 
+# RTesseract
 class RTesseract
   # Class to read char positions from an image
   class Box < RTesseract
+    # Setting value as blank array
     def initialize_hook
-      @value, @points = [[], {}]
+      @value = []
     end
 
+    # Aditional options to config file
     def config_hook
       @options['tessedit_create_hocr'] = 1 # Split Words configuration
     end
 
+    # Words converted
     def words
       convert if @value == []
       @value
     end
 
+    # Extension of file
     def file_ext
       '.hocr'
     end
 
+    # Read the result file
     def parse_file
       html = Nokogiri::HTML(File.read(text_file_with_ext))
       html.css('span.ocrx_word, span.ocr_word')
     end
 
+    # Return words to value
     def convert_text
       text_objects =  []
       parse_file.each { |word| text_objects << BoxParser.new(word).to_h }
       @value = text_objects
     end
 
+    # Move file html to hocr
     def after_convert_hook
       FileUtils.mv(text_file_with_ext('.html'), text_file_with_ext) rescue nil
     end
@@ -56,6 +64,7 @@ class RTesseract
         @attributes = title.gsub(';', '').split(' ')
       end
 
+      # Hash of word and position
       def to_h
         {
           word: @word.text,

data/lib/rtesseract/box_char.rb

@@ -1,4 +1,5 @@
 # encoding: UTF-8
+# RTesseract
 class RTesseract
   # Class to read char positions from an image
   class BoxChar < Box
@@ -8,10 +9,12 @@ class RTesseract
 
     alias_method :characters, :words
 
+    # Extension of file
     def file_ext
       '.box'
     end
 
+    # Read the result file
     def parse_file
       File.read(text_file_with_ext).to_s
     end

data/lib/rtesseract/configuration.rb

@@ -1,12 +1,16 @@
-# Configuration
+# RTesseract
 class RTesseract
   # Aliases to languages names
   LANGUAGES = {
-    'eng' => %w(en en-us english),
-    'ita' => %w(it),
-    'por' => %w(pt pt-br portuguese),
-    'spa' => %w(sp)
-  }
+    'en' => 'eng',
+    'en-us' => 'eng',
+    'english' => 'eng',
+    'pt' => 'por',
+    'pt-br' => 'por',
+    'portuguese' => 'por',
+    'it' => 'ita',
+    'sp' => 'spa'
+  }.freeze
 
   # Configuration class
   class Configuration
@@ -16,16 +20,19 @@ class RTesseract
       @processor = 'rmagick'
     end
 
+    # Global configuration
     def parent
       @parent ||= RTesseract.configuration || RTesseract::Configuration.new
     end
 
+    # Set value of option
     def option(options, name, default = nil)
       self.instance_variable_set("@#{name}", options.option(name, parent.send(name)) || default)
     end
 
+    # Return the values of options
     def load_options(options, names = [])
-      names.each{ |name| option(options, name, nil) }
+      names.each { |name| option(options, name, nil) }
     end
   end
 
@@ -38,6 +45,7 @@ class RTesseract
     yield(configuration)
   end
 
+  # Default command
   def self.default_command
     TesseractBin::Executables[:tesseract] || 'tesseract'
   rescue
@@ -49,7 +57,7 @@ class RTesseract
     RTesseract::Configuration.new.tap do |config|
       config.command = config.option(options, :command, RTesseract.default_command)
       config.processor = config.option(options, :processor, 'rmagick')
-      config.load_options(options, [ :lang, :psm, :tessdata_dir, :user_words, :user_patterns ])
+      config.load_options(options, [:lang, :psm, :tessdata_dir, :user_words, :user_patterns])
       config.debug = config.option(options, :debug, false)
       config.options_cmd = [options.option(:options, nil)].flatten.compact
     end

data/lib/rtesseract/errors.rb

@@ -1,3 +1,4 @@
+# RTesseract
 class RTesseract
   # Class of error with storage of normal errors
   class ErrorWithMemory < StandardError

data/lib/rtesseract/mixed.rb

@@ -1,4 +1,5 @@
 # encoding: UTF-8
+# RTesseract
 class RTesseract
   # Class to read an image from specified areas
   class Mixed
@@ -12,11 +13,13 @@ class RTesseract
       yield self if block_given?
     end
 
-    def area(_points)
+    # Add areas
+    def area(points)
       @value = ''
-      @areas << _points # { x: x,  y: y, width: width, height: height }
+      @areas << points
     end
 
+    # Clear areas
     def clear_areas
       @areas = []
     end
@@ -25,7 +28,7 @@ class RTesseract
     def convert
       @value = []
       @areas.each_with_object(RTesseract.new(@source.to_s, @options.dup)) do |area, image|
-        image.crop!(area) # area[:x], area[:y], area[:width], area[:height])
+        image.crop!(area)
         @value << image.to_s
       end
     rescue => error
@@ -45,7 +48,7 @@ class RTesseract
 
     # Remove spaces and break-lines
     def to_s_without_spaces
-      to_s.gsub(' ', '').gsub("\n", '').gsub("\r", '')
+      to_s.delete(' ').delete("\n").delete("\r")
     end
   end
 end

data/lib/rtesseract/processor.rb

@@ -0,0 +1,19 @@
+# RTesseract
+class RTesseract
+  # Processor managment
+  module Processor
+    # Return the processor
+    def self.choose_processor!(processor)
+      processor =
+      if RTesseract::Processor::MiniMagickProcessor.a_name?(processor.to_s)
+        MiniMagickProcessor
+      elsif RTesseract::Processor::NoneProcessor.a_name?(processor.to_s)
+        NoneProcessor
+      else
+        RMagickProcessor
+      end
+      processor.setup
+      processor
+    end
+  end
+end

data/lib/rtesseract/utils.rb

@@ -0,0 +1,34 @@
+# RTesseract
+class RTesseract
+  # Some utils methods
+  module Utils
+    # Remove files or Tempfile
+    def self.remove_files(files = [])
+      files.each do |file|
+        self.remove_file(file)
+      end
+      true
+    rescue => error
+      raise RTesseract::TempFilesNotRemovedError.new(error: error, files: files)
+    end
+
+    # Remove file or Tempfile
+    def self.remove_file(file)
+      if file.is_a?(Tempfile)
+        file.close
+        file.unlink
+      else
+        File.unlink(file)
+      end
+      true
+    end
+  end
+end
+
+# Hash
+class Hash
+  # return the value and remove from 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 2.0.0 ruby lib
+# stub: rtesseract 2.0.1 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "rtesseract"
-  s.version = "2.0.0"
+  s.version = "2.0.1"
 
   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 = "2016-04-19"
+  s.date = "2016-05-17"
   s.description = "Ruby library for working with the Tesseract OCR."
   s.email = "dannnylo@gmail.com"
   s.extra_rdoc_files = [
@@ -22,6 +22,7 @@ Gem::Specification.new do |s|
     ".document",
     ".rspec",
     ".travis.yml",
+    "CHANGELOG.md",
     "Gemfile",
     "Gemfile.lock",
     "LICENSE.txt",
@@ -32,13 +33,16 @@ Gem::Specification.new do |s|
     "lib/processors/none.rb",
     "lib/processors/rmagick.rb",
     "lib/rtesseract.rb",
+    "lib/rtesseract/blob.rb",
     "lib/rtesseract/box.rb",
     "lib/rtesseract/box_char.rb",
     "lib/rtesseract/configuration.rb",
     "lib/rtesseract/errors.rb",
     "lib/rtesseract/mixed.rb",
-    "lib/utils.rb",
+    "lib/rtesseract/processor.rb",
+    "lib/rtesseract/utils.rb",
     "rtesseract.gemspec",
+    "spec/configs/eng.user-words.txt",
     "spec/images/README.pdf",
     "spec/images/blank.tif",
     "spec/images/mixed.tif",

data/spec/configs/eng.user-words.txt

@@ -0,0 +1,13 @@
+you
+are
+a
+friend
+you
+speak
+the
+password
+and
+the
+doors
+will
+open

data/spec/rtesseract_box_char_spec.rb

@@ -6,17 +6,7 @@ describe 'Rtesseract::BoxChar' do
     @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
-    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 }])
-
-    expect(RTesseract::BoxChar.new(@words_image).characters).to eql([
+    @values = [
       { 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 },
@@ -72,7 +62,18 @@ describe 'Rtesseract::BoxChar' do
       { 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: '.', x_start: 261, y_start: 47, x_end: 263, y_end: 49 }]
+  end
+
+  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 }])
+
+    expect(RTesseract::BoxChar.new(@words_image).characters).to eql(@values)
 
     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)

data/spec/rtesseract_spec.rb

@@ -81,6 +81,7 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif, lang: 'eng').to_s_without_spaces).to eql('43XF')
 
     expect(RTesseract.new(@image_tif, lang: 'eng').lang).to eql(' -l eng ')
+    expect(RTesseract.new(@image_tif, lang: 'it').lang).to eql(' -l ita ')
 
     # Invalid lang object
     expect(RTesseract.new(@image_tif, lang: MakeStringError.new).lang).to eql('')
@@ -98,6 +99,7 @@ describe 'Rtesseract' do
     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')
+    expect(RTesseract.new(@image_tif, tessedit_char_whitelist: "ABCDEF12345").to_s_without_spaces).to eql('43F')
   end
 
   it ' crop image' do
@@ -121,14 +123,14 @@ describe 'Rtesseract' do
 
   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)
-    expect(MiniMagickProcessor.a_name?('teste')).to eql(false)
-    expect(MiniMagickProcessor.a_name?('mini_magick')).to eql(true)
-    expect(MiniMagickProcessor.a_name?('MiniMagickProcessor')).to eql(true)
-    expect(NoneProcessor.a_name?('none')).to eql(true)
-    expect(NoneProcessor.a_name?('NoneProcessor')).to eql(true)
+    expect(RTesseract::Processor::RMagickProcessor.a_name?('teste')).to eql(false)
+    expect(RTesseract::Processor::RMagickProcessor.a_name?('rmagick')).to eql(true)
+    expect(RTesseract::Processor::RMagickProcessor.a_name?('RMagickProcessor')).to eql(true)
+    expect(RTesseract::Processor::MiniMagickProcessor.a_name?('teste')).to eql(false)
+    expect(RTesseract::Processor::MiniMagickProcessor.a_name?('mini_magick')).to eql(true)
+    expect(RTesseract::Processor::MiniMagickProcessor.a_name?('MiniMagickProcessor')).to eql(true)
+    expect(RTesseract::Processor::NoneProcessor.a_name?('none')).to eql(true)
+    expect(RTesseract::Processor::NoneProcessor.a_name?('NoneProcessor')).to eql(true)
   end
 
   it ' change image in a block' do
@@ -172,10 +174,9 @@ describe 'Rtesseract' do
   end
 
   it 'remove a file' do
-    rtesseract = RTesseract.new('.')
-    rtesseract.remove_file(Tempfile.new('config'))
+    RTesseract::Utils.remove_files(Tempfile.new('config'))
 
-    expect { rtesseract.remove_file(Pathname.new(Dir.tmpdir).join('test_not_exists')) }.to raise_error(RTesseract::TempFilesNotRemovedError)
+    expect { RTesseract::Utils.remove_files(Pathname.new(Dir.tmpdir).join('test_not_exists')) }.to raise_error(RTesseract::TempFilesNotRemovedError)
   end
 
   it ' support  default config processors' do
@@ -201,7 +202,6 @@ describe 'Rtesseract' do
     RTesseract.configure { |config| config.psm = 7 }
     expect(RTesseract.new(@image_tif).psm).to eql(' -psm 7 ')
 
-
     RTesseract.configure { |config| config.tessdata_dir = '/tmp/test' }
     expect(RTesseract.new(@image_tif).tessdata_dir).to eql(' --tessdata-dir /tmp/test ')
 
@@ -220,5 +220,7 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif, tessdata_dir: MakeStringError.new).tessdata_dir).to eql('')
     expect(RTesseract.new(@image_tif, user_words: MakeStringError.new).user_words).to eql('')
     expect(RTesseract.new(@image_tif, user_patterns: MakeStringError.new).user_patterns).to eql('')
+
+    # expect(RTesseract.new(@path.join('images', 'test_words.png').to_s, psm: 3, user_words: @path.join('configs', 'eng.user-words.txt').to_s).to_s).to eql("If you are a friend,\nyou speak the password,\nand the doors will open.\n\n")
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.0.1
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-19 00:00:00.000000000 Z
+date: 2016-05-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -119,6 +119,7 @@ files:
 - ".document"
 - ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -129,13 +130,16 @@ files:
 - lib/processors/none.rb
 - lib/processors/rmagick.rb
 - lib/rtesseract.rb
+- lib/rtesseract/blob.rb
 - lib/rtesseract/box.rb
 - lib/rtesseract/box_char.rb
 - lib/rtesseract/configuration.rb
 - lib/rtesseract/errors.rb
 - lib/rtesseract/mixed.rb
-- lib/utils.rb
+- lib/rtesseract/processor.rb
+- lib/rtesseract/utils.rb
 - rtesseract.gemspec
+- spec/configs/eng.user-words.txt
 - spec/images/README.pdf
 - spec/images/blank.tif
 - spec/images/mixed.tif

data/lib/utils.rb

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