rtesseract 1.2.6 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d411f0cb8348c4bd1d39d03edac5aa57023275f1
-  data.tar.gz: 5707dea49f6e560ae5785033cabbc489764acba8
+  metadata.gz: 68e5f82fed2132e93d4ba1f432d5beca598682e9
+  data.tar.gz: f51f2ba570d2b0fdbb6483a334843dfd6ce0f8be
 SHA512:
-  metadata.gz: 8ef2bc81e31136ae67a6280510d191633f9c0787726d1b8b697f46ae5a0201fa2248d1c51afb5f7e8f418f7d554a767d8a3c4edc212ed90498cb08005b347adf
-  data.tar.gz: ead5acd868fc9925e4d7de70e3d576eb02aa18dd69f653f38e06f021f7ebcc08596970894d43f835954a2efe974e2dd808a49ad2be1b531c5dbea0b962307107
+  metadata.gz: a6ff8c4f5bb5587f7bf8656876e9b83e0a252cf4a52d5e002c68867faddafdf5b46f2a7e2d65c70d5db583ea00321cddb126e542a5c6321e318b7083933c5bce
+  data.tar.gz: f5a9763a75e42c0d7fe40be660a6864af58463260153335be319ba1d1f5334579ff3a19edfc14c8c7476d202251fa7f172eb5b4bdae8ce79fd286a55f58617af

data/Gemfile

@@ -1,6 +1,8 @@
 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"

data/Gemfile.lock

@@ -1,18 +1,20 @@
 GEM
   remote: http://rubygems.org/
   specs:
-    addressable (2.3.7)
+    addressable (2.3.8)
     builder (3.2.2)
-    coveralls (0.7.10)
-      multi_json (~> 1.10)
+    coveralls (0.8.1)
+      json (~> 1.8)
       rest-client (>= 1.6.8, < 2)
-      simplecov (~> 0.9.1)
+      simplecov (~> 0.10.0)
       term-ansicolor (~> 1.3)
       thor (~> 0.19.1)
     descendants_tracker (0.0.4)
       thread_safe (~> 0.3, >= 0.3.1)
     diff-lcs (1.2.5)
     docile (1.1.5)
+    domain_name (0.5.24)
+      unf (>= 0.0.5, < 1.0.0)
     faraday (0.9.1)
       multipart-post (>= 1.2, < 3)
     git (1.2.9.1)
@@ -24,8 +26,10 @@ GEM
       multi_json (>= 1.7.5, < 2.0)
       nokogiri (~> 1.6.3)
       oauth2
-    hashie (3.4.0)
-    highline (1.7.1)
+    hashie (3.4.2)
+    highline (1.7.2)
+    http-cookie (1.0.2)
+      domain_name (~> 0.5)
     jeweler (2.0.1)
       builder
       bundler (>= 1.0)
@@ -35,15 +39,15 @@ GEM
       nokogiri (>= 1.5.10)
       rake
       rdoc
-    json (1.8.2)
-    jwt (1.2.1)
-    mime-types (2.4.3)
-    mini_magick (4.1.0)
+    json (1.8.3)
+    jwt (1.5.1)
+    mime-types (2.6.1)
+    mini_magick (4.2.7)
     mini_portile (0.6.2)
-    multi_json (1.10.1)
+    multi_json (1.11.1)
     multi_xml (0.5.5)
     multipart-post (2.0.0)
-    netrc (0.10.2)
+    netrc (0.10.3)
     nokogiri (1.6.6.2)
       mini_portile (~> 0.6.0)
     oauth2 (1.0.0)
@@ -53,37 +57,41 @@ GEM
       multi_xml (~> 0.5)
       rack (~> 1.2)
     quick_magick (0.8.0)
-    rack (1.6.0)
+    rack (1.6.4)
     rake (10.4.2)
     rdoc (4.2.0)
       json (~> 1.4)
-    rest-client (1.7.3)
+    rest-client (1.8.0)
+      http-cookie (>= 1.0.2, < 2.0)
       mime-types (>= 1.16, < 3.0)
       netrc (~> 0.7)
-    rmagick (2.13.4)
-    rspec (3.2.0)
-      rspec-core (~> 3.2.0)
-      rspec-expectations (~> 3.2.0)
-      rspec-mocks (~> 3.2.0)
-    rspec-core (3.2.1)
-      rspec-support (~> 3.2.0)
-    rspec-expectations (3.2.0)
+    rmagick (2.15.2)
+    rspec (3.3.0)
+      rspec-core (~> 3.3.0)
+      rspec-expectations (~> 3.3.0)
+      rspec-mocks (~> 3.3.0)
+    rspec-core (3.3.1)
+      rspec-support (~> 3.3.0)
+    rspec-expectations (3.3.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.2.0)
-    rspec-mocks (3.2.1)
+      rspec-support (~> 3.3.0)
+    rspec-mocks (3.3.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.2.0)
-    rspec-support (3.2.2)
-    simplecov (0.9.2)
+      rspec-support (~> 3.3.0)
+    rspec-support (3.3.0)
+    simplecov (0.10.0)
       docile (~> 1.1.0)
-      multi_json (~> 1.0)
-      simplecov-html (~> 0.9.0)
-    simplecov-html (0.9.0)
-    term-ansicolor (1.3.0)
+      json (~> 1.8)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.0)
+    term-ansicolor (1.3.2)
       tins (~> 1.0)
     thor (0.19.1)
-    thread_safe (0.3.4)
-    tins (1.3.4)
+    thread_safe (0.3.5)
+    tins (1.5.4)
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.1)
 
 PLATFORMS
   ruby
@@ -93,6 +101,7 @@ DEPENDENCIES
   coveralls
   jeweler (~> 2.0.1)
   mini_magick
+  nokogiri
   quick_magick
   rdoc
   rmagick

data/VERSION

@@ -1 +1 @@
-1.2.6
+1.3.0

data/lib/processors/mini_magick.rb

@@ -12,10 +12,10 @@ module MiniMagickProcessor
   def self.image_to_tif(source, x = nil, y = nil, w = nil, h = nil)
     tmp_file = Tempfile.new(['', '.tif'])
     cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
-    cat.format('tif') { |c|
+    cat.format('tif') do |c|
       c.compress 'None'
-      c.alpha 'off' 
-    }
+      c.alpha 'off'
+    end
     cat.crop("#{w}x#{h}+#{x}+#{y}") unless [x, y, w, h].compact == []
     cat.alpha 'off'
     cat.write tmp_file.path.to_s

data/lib/processors/none.rb

@@ -8,13 +8,13 @@ module NoneProcessor
     %w(none NoneProcessor).include?(name.to_s)
   end
 
-  def self.image_to_tif(source, x = nil, y = nil, w = nil, h = nil)
+  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
   end
 
-  def self.need_crop?(x = nil, y = nil, w = nil, h = nil)
+  def self.need_crop?(*)
   end
 
   def self.read_with_processor(path)

data/lib/processors/quick_magick.rb

@@ -14,8 +14,8 @@ module QuickMagickProcessor
     cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
     cat.compress = 'None'
     cat.format = 'tif'
-    cat.alpha = "off"
-    cat.crop("#{w}x#{h}+#{x}+#{y}") if need_crop?( x, y, w, h)
+    cat.alpha = 'off'
+    cat.crop("#{w}x#{h}+#{x}+#{y}") if need_crop?(x, y, w, h)
     cat.write tmp_file.path.to_s
     tmp_file
   end

data/lib/processors/rmagick.rb

@@ -2,7 +2,11 @@
 # Add to rtesseract a image manipulation with RMagick
 module RMagickProcessor
   def self.setup
-    require 'RMagick'
+    begin
+      require 'rmagick'
+    rescue
+      require 'RMagick'
+    end
   end
 
   def self.a_name?(name)

data/lib/rtesseract.rb

@@ -4,6 +4,8 @@ require 'tempfile'
 
 require 'rtesseract/errors'
 require 'rtesseract/mixed'
+require 'rtesseract/box'
+require 'rtesseract/box_char'
 
 # Processors
 require 'processors/rmagick.rb'
@@ -13,14 +15,15 @@ require 'processors/none.rb'
 
 # Ruby wrapper for Tesseract OCR
 class RTesseract
+  attr_accessor :image_object
   attr_accessor :options
-  attr_writer   :lang
-  attr_writer   :psm
-  attr_reader   :processor
+  attr_writer :lang
+  attr_writer :psm
+  attr_reader :processor
   attr_accessor :options_cmd
 
   OPTIONS = %w(command lang psm processor debug clear_console_output options)
-   # Aliases to languages names
+  # Aliases to languages names
   LANGUAGES = {
     'eng' => %w(en en-us english),
     'ita' => %w(it),
@@ -33,6 +36,10 @@ class RTesseract
     @value, @x, @y, @w, @h = ['']
     @processor = RTesseract.choose_processor!(@processor)
     @source = @processor.image?(src) ? src : Pathname.new(src)
+    initialize_hook
+  end
+
+  def initialize_hook
   end
 
   def fetch_option(options, name, default)
@@ -40,13 +47,13 @@ class RTesseract
   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)
+    @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_cmd = [@options_cmd] unless @options_cmd.kind_of?(Array)
+    @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)
@@ -66,12 +73,19 @@ class RTesseract
     processor = RTesseract.choose_processor!(options.delete(:processor) || options.delete('processor'))
     image = processor.read_with_processor(src.to_s)
 
-    yield image
+    yield(image)
     object = RTesseract.new('', options)
     object.from_blob(image.to_blob)
     object
   end
 
+  def read(&block)
+    image = @processor.read_with_processor(@source.to_s)
+    new_image = yield(image)
+    self.from_blob(new_image.to_blob, File.extname(@source.to_s))
+    self
+  end
+
   def source=(src)
     @value = ''
     @source = @processor.image?(src) ? src : Pathname.new(src)
@@ -129,12 +143,17 @@ class RTesseract
     ''
   end
 
+  def config_hook
+  end
+
   def config
     @options ||= {}
+    config_hook
     @options.map { |k, v| "#{k} #{v}" }.join("\n")
   end
 
   def config_file
+    config_hook
     return '' if @options == {}
     conf = Tempfile.new('config')
     conf.write(config)
@@ -142,7 +161,7 @@ class RTesseract
     conf.path
   end
 
-  #TODO: Clear console for MacOS or Windows
+  # TODO: Clear console for MacOS or Windows
   def clear_console_output
     return '' unless @clear_console_output
     return '2>/dev/null' if File.exist?('/dev/null') # Linux console clear
@@ -152,22 +171,42 @@ class RTesseract
     (@image = @processor.image_to_tif(@source, @x, @y, @w, @h)).path
   end
 
+  def file_ext
+    '.txt'
+  end
+
   def text_file
-    @text_file = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}.txt").to_s
+    @text_file = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
+  end
+
+  def text_file_with_ext(ext = nil)
+    [@text_file, ext || file_ext].join('')
+  end
+
+  def convert_command
+    `#{@command} "#{image}" "#{text_file}" #{lang} #{psm} #{config_file} #{clear_console_output} #{@options_cmd.join(' ')}`
+  end
+
+  def convert_text
+    @value = File.read(text_file_with_ext).to_s
+  end
+
+  def after_convert_hook
   end
 
   # Convert image to string
   def convert
-    `#{@command} "#{image}" "#{text_file.gsub('.txt', '')}" #{lang} #{psm} #{config_file} #{clear_console_output} #{@options_cmd.join(' ')}`
-    @value = File.read(@text_file).to_s
-    remove_file([@image, @text_file])
+    convert_command
+    after_convert_hook
+    convert_text
+    remove_file([@image, text_file_with_ext])
   rescue => error
     raise RTesseract::ConversionError.new(error)
   end
 
   # Read image from memory blob
-  def from_blob(blob)
-    blob_file = Tempfile.new('blob', :encoding => 'ascii-8bit')
+  def from_blob(blob, ext = '')
+    blob_file = Tempfile.new(['blob', ext], :encoding => 'ascii-8bit')
     blob_file.binmode
     blob_file.write(blob)
     blob_file.rewind
@@ -196,15 +235,16 @@ class RTesseract
   end
 
   def self.choose_processor!(processor)
-    processor =  if MiniMagickProcessor.a_name?(processor.to_s)
-                    MiniMagickProcessor
-                  elsif QuickMagickProcessor.a_name?(processor.to_s)
-                    QuickMagickProcessor
-                  elsif NoneProcessor.a_name?(processor.to_s)
-                    NoneProcessor
-                  else
-                    RMagickProcessor
-                  end
+    processor =
+    if MiniMagickProcessor.a_name?(processor.to_s)
+      MiniMagickProcessor
+    elsif QuickMagickProcessor.a_name?(processor.to_s)
+      QuickMagickProcessor
+    elsif NoneProcessor.a_name?(processor.to_s)
+      NoneProcessor
+    else
+      RMagickProcessor
+    end
     processor.setup
     processor
   end

data/lib/rtesseract/box.rb

@@ -0,0 +1,53 @@
+# encoding: UTF-8
+require 'nokogiri'
+require 'fileutils'
+
+class RTesseract
+  # Class to read char positions from an image
+  class Box < RTesseract
+    def initialize_hook
+      @value, @x, @y, @w, @h = [[]]
+    end
+
+    def config_hook
+      @options['tessedit_create_hocr'] = 1 # Split Words configuration
+    end
+
+    def words
+      convert if @value == []
+      @value
+    end
+
+    def file_ext
+      '.hocr'
+    end
+
+    def parse_file
+      Nokogiri::HTML(File.read(text_file_with_ext)).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
+      @value = text_objects
+    end
+
+    def after_convert_hook
+      FileUtils.mv(text_file_with_ext('.html'), text_file_with_ext) rescue nil
+    end
+
+    # Output value
+    def to_s
+      return @value.map { |word| word[:word] } if @value != []
+      if @processor.image?(@source) || @source.file?
+        convert
+        @value.map { |word| word[:word] }.join(' ')
+      else
+        fail RTesseract::ImageNotSelectedError.new(@source)
+      end
+    end
+  end
+end

data/lib/rtesseract/box_char.rb

@@ -0,0 +1,28 @@
+# encoding: UTF-8
+class RTesseract
+  # Class to read char positions from an image
+  class BoxChar < Box
+    def config_hook
+      @options['tessedit_create_boxfile'] = 1 # Split chars
+    end
+
+    alias_method :characters, :words
+
+    def file_ext
+      '.box'
+    end
+
+    def parse_file
+      File.read(text_file_with_ext).to_s
+    end
+
+    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 }
+      end
+      @value = text_objects
+    end
+  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 1.2.6 ruby lib
+# stub: rtesseract 1.3.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "rtesseract"
-  s.version = "1.2.6"
+  s.version = "1.3.0"
 
   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 = "2015-03-13"
+  s.date = "2015-06-23"
   s.description = "Ruby library for working with the Tesseract OCR."
   s.email = "dannnylo@gmail.com"
   s.extra_rdoc_files = [
@@ -34,29 +34,36 @@ Gem::Specification.new do |s|
     "lib/processors/quick_magick.rb",
     "lib/processors/rmagick.rb",
     "lib/rtesseract.rb",
+    "lib/rtesseract/box.rb",
+    "lib/rtesseract/box_char.rb",
     "lib/rtesseract/errors.rb",
     "lib/rtesseract/mixed.rb",
     "rtesseract.gemspec",
     "spec/images/mixed.tif",
+    "spec/images/orientation_reverse.png",
     "spec/images/test with spaces.tif",
     "spec/images/test.bmp",
     "spec/images/test.jpg",
     "spec/images/test.png",
     "spec/images/test.tif",
     "spec/images/test1.tif",
+    "spec/images/test_words.png",
+    "spec/rtesseract_box_char_spec.rb",
+    "spec/rtesseract_box_spec.rb",
     "spec/rtesseract_mixed_spec.rb",
     "spec/rtesseract_spec.rb",
     "spec/spec_helper.rb"
   ]
   s.homepage = "http://github.com/dannnylo/rtesseract"
   s.licenses = ["MIT"]
-  s.rubygems_version = "2.2.1"
+  s.rubygems_version = "2.2.2"
   s.summary = "Ruby library for working with the Tesseract OCR."
 
   if s.respond_to? :specification_version then
     s.specification_version = 4
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
       s.add_development_dependency(%q<rspec>, [">= 0"])
       s.add_development_dependency(%q<rdoc>, [">= 0"])
       s.add_development_dependency(%q<bundler>, [">= 0"])
@@ -64,6 +71,7 @@ Gem::Specification.new do |s|
       s.add_development_dependency(%q<simplecov>, [">= 0"])
       s.add_development_dependency(%q<coveralls>, [">= 0"])
     else
+      s.add_dependency(%q<nokogiri>, [">= 0"])
       s.add_dependency(%q<rspec>, [">= 0"])
       s.add_dependency(%q<rdoc>, [">= 0"])
       s.add_dependency(%q<bundler>, [">= 0"])
@@ -72,6 +80,7 @@ Gem::Specification.new do |s|
       s.add_dependency(%q<coveralls>, [">= 0"])
     end
   else
+    s.add_dependency(%q<nokogiri>, [">= 0"])
     s.add_dependency(%q<rspec>, [">= 0"])
     s.add_dependency(%q<rdoc>, [">= 0"])
     s.add_dependency(%q<bundler>, [">= 0"])

data/spec/rtesseract_box_char_spec.rb

@@ -0,0 +1,82 @@
+# encoding: UTF-8
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "Rtesseract::BoxChar" do
+  before 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([
+      {: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)
+  end
+end

data/spec/rtesseract_box_spec.rb

@@ -0,0 +1,36 @@
+# encoding: UTF-8
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+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
+  end
+
+
+  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}
+    ])
+
+    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)
+  end
+end

data/spec/rtesseract_mixed_spec.rb

@@ -9,8 +9,8 @@ describe "Rtesseract::Mixed" do
   end
 
   it "should be instantiable" do
-    RTesseract::Mixed.new.class.should eql(RTesseract::Mixed)
-    RTesseract::Mixed.new(@image_tif).class.should eql(RTesseract::Mixed)
+    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
@@ -20,9 +20,9 @@ describe "Rtesseract::Mixed" do
       image.area(218, 22, 24, 28) # position of z
       image.area(248, 24, 22, 22) # position of z
     end
-    mix_block.to_s_without_spaces.should eql("43FF")
+    expect(mix_block.to_s_without_spaces).to eql("43FF")
     mix_block.clear_areas
-    mix_block.areas.should == []
+    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
@@ -30,7 +30,7 @@ describe "Rtesseract::Mixed" do
       {:x => 218,  :y=>22, :width=>24, :height=>28}, # position of z
       {:x => 248,  :y=>24, :width=>22, :height=>22}  # position of z
     ],:psm=>7})
-    mix_block.to_s_without_spaces.should eql("43FF")
+    expect(mix_block.to_s_without_spaces).to eql("43FF")
   end
 
   it " get a error" do

data/spec/rtesseract_spec.rb

@@ -14,70 +14,70 @@ describe "Rtesseract" do
   end
 
   it " be instantiable" do
-    RTesseract.new.class.should eql(RTesseract)
-    RTesseract.new("").class.should eql(RTesseract)
-    RTesseract.new(@image_tif).class.should 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
-    RTesseract.new(@image_tif).to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@image_tif, {:processor => 'mini_magick'}).to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@path.join("images","test1.tif").to_s).to_s_without_spaces.should eql("V2V4")
-    RTesseract.new(@path.join("images","test with spaces.tif").to_s).to_s_without_spaces.should eql("V2V4")
+    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
-    RTesseract.new(@path.join("images","test.png").to_s).to_s_without_spaces.should eql("HW9W")
-    RTesseract.new(@path.join("images","test.jpg").to_s).to_s_without_spaces.should eql("3R8F")
-    RTesseract.new(@path.join("images","test.bmp").to_s).to_s_without_spaces.should eql("FLA6")
+    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 " support  diferent processors" do
     #Rmagick
-    RTesseract.new(@image_tif).to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@image_tif, :processor => 'rmagick').to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@path.join("images","test.png").to_s, :processor => 'rmagick').to_s_without_spaces.should eql("HW9W")
+    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
-    RTesseract.new(@image_tif, :processor => 'mini_magick').to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@path.join("images","test.png").to_s, :processor => 'mini_magick').to_s_without_spaces.should eql("HW9W")
+    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
-    RTesseract.new(@image_tif, :processor => 'quick_magick').to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@path.join("images","test.png").to_s, :processor => 'quick_magick').to_s_without_spaces.should eql("HW9W")
+    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
-    RTesseract.new(@image_tif, :processor => 'none').to_s_without_spaces.should eql("43XF")
+    expect(RTesseract.new(@image_tif, :processor => 'none').to_s_without_spaces).to eql("43XF")
   end
 
   it " change the image" do
     image = RTesseract.new(@image_tif)
-    image.to_s_without_spaces.should eql("43XF")
+    expect(image.to_s_without_spaces).to eql("43XF")
     image.source = @path.join("images","test1.tif").to_s
-    image.to_s_without_spaces.should eql("V2V4")
+    expect(image.to_s_without_spaces).to eql("V2V4")
   end
 
   it " select the language" do
     #English
-     RTesseract.new(@image_tif,{:lang=>"eng"}).lang.should eql(" -l eng ")
-     RTesseract.new(@image_tif,{:lang=>"en"}).lang.should eql(" -l eng ")
-     RTesseract.new(@image_tif,{:lang=>"en-US"}).lang.should eql(" -l eng ")
-     RTesseract.new(@image_tif,{:lang=>"english"}).lang.should eql(" -l eng ")
+    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 ")
 
     #Portuguese
-    RTesseract.new(@image_tif,{:lang=>"por"}).lang.should eql(" -l por ")
-    RTesseract.new(@image_tif,{:lang=>"pt-BR"}).lang.should eql(" -l por ")
-    RTesseract.new(@image_tif,{:lang=>"pt-br"}).lang.should eql(" -l por ")
-    RTesseract.new(@image_tif,{:lang=>"pt"}).lang.should eql(" -l por ")
-    RTesseract.new(@image_tif,{:lang=>"portuguese"}).lang.should eql(" -l por ")
+    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 ")
 
-    RTesseract.new(@image_tif,{:lang=>"eng"}).to_s_without_spaces.should eql("43XF")
-    #RTesseract.new(@image_tif,{:lang=>"por"}).to_s_without_spaces.should eql("43XF")
-    RTesseract.new(@image_tif,{:lang=>"eng"}).lang.should 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 ")
 
     #Inválid lang object
-    RTesseract.new(@image_tif,{:lang=>MakeStringError.new}).lang.should eql("")
+    expect(RTesseract.new(@image_tif,{:lang=>MakeStringError.new}).lang).to eql("")
   end
 
   it " select options" do
@@ -88,17 +88,17 @@ describe "Rtesseract" do
   end
 
   it " be configurable" do
-     RTesseract.new(@image_tif,{:chop_enable=>0,:enable_assoc=>0,:display_text=>0}).config.should eql("chop_enable 0\nenable_assoc 0\ndisplay_text 0")
-     RTesseract.new(@image_tif,{:chop_enable=>0}).config.should eql("chop_enable 0")
-     RTesseract.new(@image_tif,{:chop_enable=>0,:enable_assoc=>0}).config.should eql("chop_enable 0\nenable_assoc 0")
-     RTesseract.new(@image_tif,{:chop_enable=>0}).to_s_without_spaces.should eql("43XF")
+     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
-     RTesseract.new(@image_tif,{:psm=>7}).crop!(140,10,36,40).to_s_without_spaces.should eql("4")
-     RTesseract.new(@image_tif,{:psm=>7}).crop!(180,10,36,40).to_s_without_spaces.should eql("3")
-     RTesseract.new(@image_tif,{:psm=>7}).crop!(216,10,20,40).to_s_without_spaces.should eql("X")
-     RTesseract.new(@image_tif,{:psm=>7}).crop!(240,10,30,40).to_s_without_spaces.should eql("F")
+     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
 
 
@@ -108,47 +108,53 @@ describe "Rtesseract" do
 
     test = RTesseract.new("", {:psm => 7})
     test.from_blob(blob)
-    test.to_s_without_spaces.should 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)
   end
 
   it " use a instance" do
-    RTesseract.new(Magick::Image.read(@image_tif.to_s).first).to_s_without_spaces.should eql("43XF")
-    RMagickProcessor.a_name?('teste').should == false
-    RMagickProcessor.a_name?('rmagick').should == true
-    RMagickProcessor.a_name?('RMagickProcessor').should == true
-
-    MiniMagickProcessor.a_name?('teste').should == false
-    MiniMagickProcessor.a_name?('mini_magick').should == true
-    MiniMagickProcessor.a_name?('MiniMagickProcessor').should == true
-
-    QuickMagickProcessor.a_name?('teste').should == false
-    QuickMagickProcessor.a_name?('quick_magick').should == true
-    QuickMagickProcessor.a_name?('QuickMagickProcessor').should == true
-
-    NoneProcessor.a_name?('none').should == true
-    NoneProcessor.a_name?('NoneProcessor').should == true
+    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(QuickMagickProcessor.a_name?('teste')).to eql(false)
+    expect(QuickMagickProcessor.a_name?('quick_magick')).to eql(true)
+    expect(QuickMagickProcessor.a_name?('QuickMagickProcessor')).to eql(true)
+    expect(NoneProcessor.a_name?('none')).to eql(true)
+    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){}
+    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")
+
     test = RTesseract.read(@path.join("images","test.png").to_s) do |image|
-      image = image.white_threshold(245)
-      image = image.quantize(256,Magick::GRAYColorspace)
+      #image = image.white_threshold(245)
+      #image = image.quantize(256,Magick::GRAYColorspace)
+      image.rotate(90)
     end
-    test.to_s_without_spaces.should 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|
       image = image.white_threshold(245).quantize(256, Magick::GRAYColorspace)
     end
-    test.to_s_without_spaces.should 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.white_threshold(245)
       image.gravity "south"
     end
-    test.to_s_without_spaces.should eql("3R8F")
+    expect(test.to_s_without_spaces).to eql("3R8F")
   end
 
   it " get a error" do
@@ -156,7 +162,7 @@ describe "Rtesseract" do
     expect{ RTesseract.new(@path.join("images","test_not_exists.png").to_s).to_s }.to raise_error(RTesseract::ImageNotSelectedError)
 
     #Inválid psm object
-    RTesseract.new(@image_tif,{:psm=>MakeStringError.new}).psm.should eql("")
+    expect(RTesseract.new(@image_tif,{:psm=>MakeStringError.new}).psm).to eql("")
   end
 
   it "remove a file" do

metadata

@@ -1,15 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 1.2.6
+  version: 1.3.0
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-13 00:00:00.000000000 Z
+date: 2015-06-23 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -117,16 +131,22 @@ files:
 - lib/processors/quick_magick.rb
 - lib/processors/rmagick.rb
 - lib/rtesseract.rb
+- lib/rtesseract/box.rb
+- lib/rtesseract/box_char.rb
 - lib/rtesseract/errors.rb
 - lib/rtesseract/mixed.rb
 - rtesseract.gemspec
 - spec/images/mixed.tif
+- spec/images/orientation_reverse.png
 - spec/images/test with spaces.tif
 - spec/images/test.bmp
 - spec/images/test.jpg
 - spec/images/test.png
 - spec/images/test.tif
 - spec/images/test1.tif
+- spec/images/test_words.png
+- spec/rtesseract_box_char_spec.rb
+- spec/rtesseract_box_spec.rb
 - spec/rtesseract_mixed_spec.rb
 - spec/rtesseract_spec.rb
 - spec/spec_helper.rb
@@ -150,7 +170,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.1
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.