rtesseract 2.0.1 → 2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6eae58279cf744227e79b7bbc9180f7aea852547
-  data.tar.gz: 3836aa96d24b7f1a0b957cf803553f547cc33544
+  metadata.gz: cb2f55f98e4b22827068fd2284a893788d72a751
+  data.tar.gz: f6b3ff2bfff6d4e250c75b239354485670b3d732
 SHA512:
-  metadata.gz: 0ef57359c7c7f43094a50838b6d29d28d7808c9cadd8f2b8514c613be030161f8d640c41ba3d403c00fb59fdf85ffcbc57795f6c65b8418ad348eb1a6c07e901
-  data.tar.gz: ff5f0f94c8039bd0b38b0c9ec2618b4c38b07b9707e28ff29a3bb943abc85d5afaa543dfba1ba2b9e565d056ea558eda9b7f6d222a6adb43614cd86c6e8fdcac
+  metadata.gz: ba2dcb1878a1c98013a6c4c0ad4a583a8b830faf01fede4df8b39a1d6e492ef79cc3610dee60ab856937e7ac7a3c7ae8789ae74fd32f80dbc910cd488a5f0651
+  data.tar.gz: aacbcfe446dd8050a6d45b78dab5d38468cb6110c4c6216c1877bfa2bbee08bdc6763e9b0c5c0ec7fe40aac8fc43a553da533b33449c60f40d21f6e6c8034faa

data/.rspec

@@ -1 +1,2 @@
 --color
+--order rand

data/.travis.yml

@@ -1,13 +1,13 @@
+sudo: required
+dist: trusty
 language: ruby
 addons:
   apt:
     packages:
     - tesseract-ocr
 
-sudo: false
 rvm:
-  - 1.9.3
-  - 2.0.0
-  - 2.1.5
-  - 2.2.2
-  - 2.3.0
+  - 2.1.10
+  - 2.2.6
+  - 2.3.3
+  - 2.4.0

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## v2.1.0
+
+#### Added
+
+* Support to generate searchable PDF
+
 ## v2.0.1
 
 #### Changed

data/Gemfile

@@ -7,8 +7,9 @@ group :development do
   gem 'rspec'
   gem 'rdoc'
   gem 'bundler'
-  gem 'jeweler', '~> 2.1.1'
+  gem 'jeweler'
   gem 'simplecov'
+  gem 'json'
   gem 'coveralls', require: false
 end
 

data/Gemfile.lock

@@ -2,83 +2,87 @@ GEM
   remote: http://rubygems.org/
   specs:
     addressable (2.4.0)
-    builder (3.2.2)
-    coveralls (0.8.13)
-      json (~> 1.8)
-      simplecov (~> 0.11.0)
-      term-ansicolor (~> 1.3)
-      thor (~> 0.19.1)
-      tins (~> 1.6.0)
+    builder (3.2.3)
+    coveralls (0.7.2)
+      multi_json (~> 1.3)
+      rest-client (= 1.6.7)
+      simplecov (>= 0.7)
+      term-ansicolor (= 1.2.2)
+      thor (= 0.18.1)
     descendants_tracker (0.0.4)
       thread_safe (~> 0.3, >= 0.3.1)
-    diff-lcs (1.2.5)
+    diff-lcs (1.3)
     docile (1.1.5)
     faraday (0.9.2)
       multipart-post (>= 1.2, < 3)
     git (1.3.0)
-    github_api (0.13.1)
+    github_api (0.16.0)
       addressable (~> 2.4.0)
       descendants_tracker (~> 0.0.4)
       faraday (~> 0.8, < 0.10)
       hashie (>= 3.4)
-      multi_json (>= 1.7.5, < 2.0)
-      oauth2
-    hashie (3.4.3)
-    highline (1.7.8)
-    jeweler (2.1.1)
+      mime-types (>= 1.16, < 3.0)
+      oauth2 (~> 1.0)
+    hashie (3.5.7)
+    highline (1.7.10)
+    jeweler (2.3.7)
       builder
-      bundler (>= 1.0)
+      bundler (>= 1)
       git (>= 1.2.5)
-      github_api
+      github_api (~> 0.16.0)
       highline (>= 1.6.15)
       nokogiri (>= 1.5.10)
+      psych (~> 2.2)
       rake
       rdoc
-      semver
-    json (1.8.3)
-    jwt (1.5.1)
-    mini_magick (4.5.1)
-    mini_portile2 (2.0.0)
-    multi_json (1.11.2)
-    multi_xml (0.5.5)
+      semver2
+    json (2.1.0)
+    jwt (1.5.6)
+    mime-types (2.99.3)
+    mini_magick (4.8.0)
+    mini_portile2 (2.3.0)
+    multi_json (1.12.2)
+    multi_xml (0.6.0)
     multipart-post (2.0.0)
-    nokogiri (1.6.7.2)
-      mini_portile2 (~> 2.0.0.rc2)
-    oauth2 (1.1.0)
-      faraday (>= 0.8, < 0.10)
-      jwt (~> 1.0, < 1.5.2)
+    nokogiri (1.8.1)
+      mini_portile2 (~> 2.3.0)
+    oauth2 (1.4.0)
+      faraday (>= 0.8, < 0.13)
+      jwt (~> 1.0)
       multi_json (~> 1.3)
       multi_xml (~> 0.5)
       rack (>= 1.2, < 3)
-    rack (1.6.4)
-    rake (11.1.2)
-    rdoc (4.2.2)
-      json (~> 1.4)
-    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 (3.4.4)
-      rspec-support (~> 3.4.0)
-    rspec-expectations (3.4.0)
+    psych (2.2.4)
+    rack (2.0.3)
+    rake (12.3.0)
+    rdoc (6.0.1)
+    rest-client (1.6.7)
+      mime-types (>= 1.16)
+    rmagick (2.16.0)
+    rspec (3.7.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.4.0)
-    rspec-mocks (3.4.1)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.4.0)
-    rspec-support (3.4.1)
-    semver (1.0.1)
-    simplecov (0.11.2)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.0)
+    semver2 (3.4.2)
+    simplecov (0.15.1)
       docile (~> 1.1.0)
-      json (~> 1.8)
+      json (>= 1.8, < 3)
       simplecov-html (~> 0.10.0)
-    simplecov-html (0.10.0)
-    term-ansicolor (1.3.2)
-      tins (~> 1.0)
-    thor (0.19.1)
-    thread_safe (0.3.5)
-    tins (1.6.0)
+    simplecov-html (0.10.2)
+    term-ansicolor (1.2.2)
+      tins (~> 0.8)
+    thor (0.18.1)
+    thread_safe (0.3.6)
+    tins (0.13.2)
 
 PLATFORMS
   ruby
@@ -86,7 +90,8 @@ PLATFORMS
 DEPENDENCIES
   bundler
   coveralls
-  jeweler (~> 2.1.1)
+  jeweler
+  json
   mini_magick
   nokogiri
   rdoc
@@ -95,4 +100,4 @@ DEPENDENCIES
   simplecov
 
 BUNDLED WITH
-   1.11.2
+   1.16.1

data/README.rdoc

@@ -16,6 +16,8 @@ To work properly rtesseract are needed:
 
 Atention: Version 1.0.0 works fine with Ruby 2.0 and tesseract 3.0 and lower versions of rtesseract works fine with Ruby 1.8 and tesseract 2.0.4.
 
+PDF support requires a newer version of tesseract, specifically V.3.03 or above.
+
 == EXAMPLE USAGE
 
 It's very simple to use rtesseract:
@@ -23,7 +25,19 @@ It's very simple to use rtesseract:
 === CONVERT IMAGE TO STRING
 
   image = RTesseract.new("my_image.jpg")
-  image.to_s #Getting the value
+  image.to_s # Getting the value
+
+=== CONVERT IMAGE TO SEARCHABLE PDF
+
+  image = RTesseract.new("my_image.jpg")
+  image.to_pdf  # Getting the pdf path
+  image.to_s    # Still can get the value only.
+  # ...
+  # some stuff
+  # ...
+  image.clean   # to delete file once finished
+
+This will preserve the image colors, pictures and structure in the generated pdf.
 
 === CHANGE THE IMAGE
 
@@ -89,6 +103,7 @@ Language Options
      * por   - Portuguese
      * spa   - Spanish
      * vie   - Vietnamese
+     * or any other supported by tesseract.
   Note: Make sure you have installed the language to tesseract
 
 Other Options

data/VERSION

@@ -1 +1 @@
-2.0.1
+2.2.0

data/lib/processors/mini_magick.rb

@@ -21,10 +21,10 @@ class RTesseract
         cat = source.is_a?(Pathname) ? read_with_processor(source.to_s) : source
         cat.format('tif') do |c|
           c.compress 'None'
-          c.alpha 'off'
+          c.alpha 'off' if MiniMagick.cli != :graphicsmagick
         end
         cat.crop("#{points[:w]}x#{points[:h]}+#{points[:x]}+#{points[:y]}") if points.is_a?(Hash) && points.values.compact != []
-        cat.alpha 'off'
+        cat.alpha 'off' if MiniMagick.cli != :graphicsmagick
         cat.write tmp_file.path.to_s
         tmp_file
       end
@@ -40,4 +40,4 @@ class RTesseract
       end
     end
   end
-end
+end

data/lib/rtesseract/blob.rb

@@ -3,7 +3,7 @@ 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))
+    processor = RTesseract::Processor.choose_processor!(options[:processor])
     image = processor.read_with_processor(src.to_s)
     yield(image)
     object = RTesseract.new('', options).from_blob(image.to_blob)
@@ -31,4 +31,4 @@ class RTesseract
   rescue => error
     raise RTesseract::ConversionError.new(error), error, caller
   end
-end
+end

data/lib/rtesseract/box.rb

@@ -29,7 +29,7 @@ class RTesseract
 
     # Read the result file
     def parse_file
-      html = Nokogiri::HTML(File.read(text_file_with_ext))
+      html = Nokogiri::HTML(File.read(file_with_ext))
       html.css('span.ocrx_word, span.ocr_word')
     end
 
@@ -42,7 +42,7 @@ class RTesseract
 
     # Move file html to hocr
     def after_convert_hook
-      FileUtils.mv(text_file_with_ext('.html'), text_file_with_ext) rescue nil
+      FileUtils.mv(file_with_ext('.html'), file_with_ext) rescue nil
     end
 
     # Output value

data/lib/rtesseract/box_char.rb

@@ -16,7 +16,7 @@ class RTesseract
 
     # Read the result file
     def parse_file
-      File.read(text_file_with_ext).to_s
+      File.read(file_with_ext).to_s
     end
 
     def convert_text

data/lib/rtesseract/configuration.rb

@@ -14,7 +14,7 @@ class RTesseract
 
   # Configuration class
   class Configuration
-    attr_accessor :processor, :lang, :psm, :tessdata_dir, :user_words, :user_patterns, :command, :debug, :options_cmd
+    attr_accessor :processor, :lang, :psm, :oem, :tessdata_dir, :user_words, :user_patterns, :command, :debug, :options_cmd
 
     def initialize
       @processor = 'rmagick'
@@ -43,6 +43,15 @@ class RTesseract
   def self.configure
     self.configuration ||= Configuration.new
     yield(configuration)
+    self.clear_pdf_option
+  end
+
+  # Clear pdf option
+  def self.clear_pdf_option
+    if self.configuration.options_cmd
+      self.configuration.options_cmd.delete('pdf')
+      self.configuration.options_cmd.delete(:pdf)
+    end
   end
 
   # Default command
@@ -57,9 +66,10 @@ 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, :oem, :tessdata_dir, :user_words, :user_patterns])
       config.debug = config.option(options, :debug, false)
-      config.options_cmd = [options.option(:options, nil)].flatten.compact
+      pdf_opts = lambda { |o| o == 'pdf' || o == :pdf }
+      config.options_cmd = [options.option(:options, nil)].delete_if(&pdf_opts).flatten.compact
     end
   end
-end
+end

data/lib/rtesseract/errors.rb

@@ -12,4 +12,10 @@ class RTesseract
   class ConversionError < ErrorWithMemory; end
   class ImageNotSelectedError < ErrorWithMemory; end
   class TempFilesNotRemovedError < ErrorWithMemory; end
+  
+  class TesseractVersionError < StandardError 
+    def initialize 
+      super "Tesseract version is unknown or below 3.03 which is required for pdf output."
+    end
+  end
 end

data/lib/rtesseract/utils.rb

@@ -1,3 +1,5 @@
+require 'open3'
+
 # RTesseract
 class RTesseract
   # Some utils methods
@@ -22,6 +24,14 @@ class RTesseract
       end
       true
     end
+
+    # Extract tesseract version number
+    def self.version_number
+      output, st = Open3.capture2e(RTesseract.default_command, "--version")
+
+      version = output.split("\n")[0].split(" ")[1].split('.')[0, 2].join('.')
+      Float(version) rescue nil
+    end
   end
 end
 
@@ -31,4 +41,4 @@ class Hash
   def option(attr_name, default)
     delete(attr_name.to_s) || delete(attr_name) || default
   end
-end
+end

data/lib/rtesseract/uzn.rb

@@ -0,0 +1,47 @@
+# encoding: UTF-8
+# RTesseract
+class RTesseract
+  # Alternative approach to Mixed when you want to read from specific areas.
+  # Requires `-psm 4` which means the text must be "a single column of text of variable sizes".
+  class Uzn < RTesseract
+    attr_reader :areas
+    DEFAULT_ALPHABET = 'Text/Latin'
+
+    def initialize(src = '', options = {})
+      @areas = options.delete(:areas) || []
+      @alphabet = options.delete(:alphabet) || DEFAULT_ALPHABET
+      super(src, options.merge(psm: 4))
+      yield self if block_given?
+    end
+
+    # Add areas
+    def area(points)
+      areas << points
+    end
+
+    def convert_command
+      @image = image
+      write_uzn_file
+      `#{configuration.command} "#{@image}" "#{file_dest}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{options_cmd.join(' ')}`
+    end
+
+    def after_convert_hook
+      RTesseract::Utils.remove_files([@uzn_file])
+    end
+
+    private
+
+    def write_uzn_file
+      folder = File.dirname(@image)
+      basename = File.basename(@image, '.tif')
+      @uzn_file = File.new("#{folder}/#{basename}.uzn", File::CREAT|File::TRUNC|File::RDWR)
+
+      areas.each do |points|
+        s = "#{points[:x]} #{points[:y]} #{points[:w]} #{points[:h]} #{@alphabet}\n"
+        @uzn_file.write(s)
+        @uzn_file.flush
+      end
+    end
+
+  end
+end

data/lib/rtesseract.rb

@@ -15,10 +15,9 @@ class RTesseract
   def initialize(src = '', options = {})
     self.configuration = RTesseract.local_config(options)
     @options = options || {}
-    @value = nil
     @points = {}
     @processor = RTesseract::Processor.choose_processor!(configuration.processor)
-    @source = @processor.image?(src) ? src : Pathname.new(src)
+    self.source = src
     initialize_hook
   end
 
@@ -29,6 +28,7 @@ class RTesseract
   # Define the source
   def source=(src)
     @value = nil
+    @pdf_path = nil
     @source = @processor.image?(src) ? src : Pathname.new(src)
   end
 
@@ -70,6 +70,11 @@ class RTesseract
     option_to_string('-psm', configuration.psm)
   end
 
+  # Engine Mode
+  def oem
+    option_to_string '--oem', configuration.oem
+  end
+
   # Tessdata Dir
   def tessdata_dir
     option_to_string('--tessdata-dir', configuration.tessdata_dir)
@@ -127,24 +132,50 @@ class RTesseract
     '.txt'
   end
 
+  # Detect version number
+  def tesseract_version
+    RTesseract::Utils.version_number
+  end
+
+
   # Rand file path
-  def text_file
-    @text_file = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
+  def file_dest
+    @file_dest = 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('')
+  # Full path of file with txt extension
+  def file_with_ext(ext = nil)
+    [@file_dest, ext || file_ext].join('')
   end
 
   # Run command
   def convert_command
-    `#{configuration.command} "#{image}" "#{text_file}" #{lang} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{configuration.options_cmd.join(' ')}`
+    `#{configuration.command} "#{image}" "#{file_dest}" #{lang} #{oem} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{options_cmd.join(' ')}`
+  end
+
+  # Is pdf output?
+  def pdf?
+    options_cmd.include? 'pdf'
   end
 
   # Read result file
   def convert_text
-    @value = File.read(text_file_with_ext).to_s
+    @value = File.read(file_with_ext).to_s
+  end
+
+  # Store pdf result path
+  def convert_pdf
+    @pdf_path = file_with_ext('.pdf')
+  end
+
+  # Convert result to proper type
+  def convert_result
+    if pdf?
+      convert_pdf
+    else
+      convert_text
+      RTesseract::Utils.remove_files([@image, file_with_ext])
+    end
   end
 
   # Hook to convert
@@ -155,15 +186,14 @@ class RTesseract
   def convert
     convert_command
     after_convert_hook
-    convert_text
-    RTesseract::Utils.remove_files([@image, text_file_with_ext])
+    convert_result
   rescue => error
     raise RTesseract::ConversionError.new(error), error, caller
   end
 
   # Output value
   def to_s
-    return @value if @value != nil
+    return @value if @value
 
     if @processor.image?(@source) || @source.file?
       convert
@@ -175,11 +205,34 @@ class RTesseract
 
   # Remove spaces and break-lines
   def to_s_without_spaces
-    to_s.delete(' ').delete("\n").delete("\r")
+    to_s.gsub(/\s/, '')
   end
+
+  # Output pdf path
+  def to_pdf
+    return @pdf_path if @pdf_path
+
+    fail TesseractVersionError.new if tesseract_version.nil? || tesseract_version < 3.03
+
+    if @processor.image?(@source) || @source.file?
+      options_cmd << 'pdf'
+      convert
+      options_cmd.delete('pdf')
+      @pdf_path
+    else
+      fail RTesseract::ImageNotSelectedError.new(@source)
+    end
+  end
+
+  # Destroy pdf file
+  def clean
+    RTesseract::Utils.remove_files([@pdf_path])
+  end
+
 end
 
 require 'rtesseract/mixed'
+require 'rtesseract/uzn'
 require 'rtesseract/box'
 require 'rtesseract/box_char'
 require 'rtesseract/blob'

data/rtesseract.gemspec

@@ -2,18 +2,18 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: rtesseract 2.0.1 ruby lib
+# stub: rtesseract 2.2.0 ruby lib
 
 Gem::Specification.new do |s|
-  s.name = "rtesseract"
-  s.version = "2.0.1"
+  s.name = "rtesseract".freeze
+  s.version = "2.2.0"
 
-  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 = "2016-05-17"
-  s.description = "Ruby library for working with the Tesseract OCR."
-  s.email = "dannnylo@gmail.com"
+  s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
+  s.require_paths = ["lib".freeze]
+  s.authors = ["Danilo Jeremias da Silva".freeze]
+  s.date = "2018-01-05"
+  s.description = "Ruby library for working with the Tesseract OCR.".freeze
+  s.email = "dannnylo@gmail.com".freeze
   s.extra_rdoc_files = [
     "LICENSE.txt",
     "README.rdoc"
@@ -41,6 +41,7 @@ Gem::Specification.new do |s|
     "lib/rtesseract/mixed.rb",
     "lib/rtesseract/processor.rb",
     "lib/rtesseract/utils.rb",
+    "lib/rtesseract/uzn.rb",
     "rtesseract.gemspec",
     "spec/configs/eng.user-words.txt",
     "spec/images/README.pdf",
@@ -48,6 +49,7 @@ Gem::Specification.new do |s|
     "spec/images/mixed.tif",
     "spec/images/orientation_reverse.png",
     "spec/images/test with spaces.tif",
+    "spec/images/test-pdf.png",
     "spec/images/test.bmp",
     "spec/images/test.jpg",
     "spec/images/test.png",
@@ -58,41 +60,45 @@ Gem::Specification.new do |s|
     "spec/rtesseract_box_spec.rb",
     "spec/rtesseract_mixed_spec.rb",
     "spec/rtesseract_spec.rb",
+    "spec/rtesseract_uzn_spec.rb",
     "spec/spec_helper.rb"
   ]
-  s.homepage = "http://github.com/dannnylo/rtesseract"
-  s.licenses = ["MIT"]
-  s.rubygems_version = "2.4.8"
-  s.summary = "Ruby library for working with the Tesseract OCR."
+  s.homepage = "http://github.com/dannnylo/rtesseract".freeze
+  s.licenses = ["MIT".freeze]
+  s.rubygems_version = "2.6.14".freeze
+  s.summary = "Ruby library for working with the Tesseract OCR.".freeze
 
   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"])
-      s.add_development_dependency(%q<jeweler>, ["~> 2.1.1"])
-      s.add_development_dependency(%q<simplecov>, [">= 0"])
-      s.add_development_dependency(%q<coveralls>, [">= 0"])
+      s.add_runtime_dependency(%q<nokogiri>.freeze, [">= 0"])
+      s.add_development_dependency(%q<rspec>.freeze, [">= 0"])
+      s.add_development_dependency(%q<rdoc>.freeze, [">= 0"])
+      s.add_development_dependency(%q<bundler>.freeze, [">= 0"])
+      s.add_development_dependency(%q<jeweler>.freeze, [">= 0"])
+      s.add_development_dependency(%q<simplecov>.freeze, [">= 0"])
+      s.add_development_dependency(%q<json>.freeze, [">= 0"])
+      s.add_development_dependency(%q<coveralls>.freeze, [">= 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"])
-      s.add_dependency(%q<jeweler>, ["~> 2.1.1"])
-      s.add_dependency(%q<simplecov>, [">= 0"])
-      s.add_dependency(%q<coveralls>, [">= 0"])
+      s.add_dependency(%q<nokogiri>.freeze, [">= 0"])
+      s.add_dependency(%q<rspec>.freeze, [">= 0"])
+      s.add_dependency(%q<rdoc>.freeze, [">= 0"])
+      s.add_dependency(%q<bundler>.freeze, [">= 0"])
+      s.add_dependency(%q<jeweler>.freeze, [">= 0"])
+      s.add_dependency(%q<simplecov>.freeze, [">= 0"])
+      s.add_dependency(%q<json>.freeze, [">= 0"])
+      s.add_dependency(%q<coveralls>.freeze, [">= 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"])
-    s.add_dependency(%q<jeweler>, ["~> 2.1.1"])
-    s.add_dependency(%q<simplecov>, [">= 0"])
-    s.add_dependency(%q<coveralls>, [">= 0"])
+    s.add_dependency(%q<nokogiri>.freeze, [">= 0"])
+    s.add_dependency(%q<rspec>.freeze, [">= 0"])
+    s.add_dependency(%q<rdoc>.freeze, [">= 0"])
+    s.add_dependency(%q<bundler>.freeze, [">= 0"])
+    s.add_dependency(%q<jeweler>.freeze, [">= 0"])
+    s.add_dependency(%q<simplecov>.freeze, [">= 0"])
+    s.add_dependency(%q<json>.freeze, [">= 0"])
+    s.add_dependency(%q<coveralls>.freeze, [">= 0"])
   end
 end
 

data/spec/rtesseract_spec.rb

@@ -1,6 +1,7 @@
 require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
 # encoding: UTF-8
 require 'pathname'
+RTesseract::Processor::RMagickProcessor.setup
 
 # Class to rise error
 class MakeStringError
@@ -13,6 +14,7 @@ describe 'Rtesseract' do
   before do
     @path = Pathname.new(__FILE__.gsub('rtesseract_spec.rb', '')).expand_path
     @image_tif = @path.join('images', 'test.tif').to_s
+    @image_for_pdf = @path.join('images', 'test-pdf.png').to_s
   end
 
   it ' be instantiable' do
@@ -94,12 +96,43 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif, options: [:digits, :quiet]).options_cmd).to eql([:digits, :quiet])
   end
 
+  it ' support pdf output mode' do
+    # Internal test. Consider 'pdf' option only when #to_pdf is called.
+    expect(RTesseract.new(@image_tif, options: 'pdf').options_cmd).to eql([])
+    expect(RTesseract.new(@image_for_pdf, options: :pdf).options_cmd).to eql([])
+
+    pdf_ocr = RTesseract.new(@image_for_pdf)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(true)
+    expect(File.extname(pdf_ocr.to_pdf)).to eql('.pdf')
+    # Comment next line and go to tmp dir to see generated pdf.
+    expect(pdf_ocr.clean).to eq(true)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(false)
+
+    # Still have original functionality (i.e. #to_s, #to_s_without_spaces).
+    pdf_ocr = RTesseract.new(@image_tif)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(true)
+    expect(File.extname(pdf_ocr.to_pdf)).to eql('.pdf')
+    expect(pdf_ocr.to_s_without_spaces).to eql('43XF')
+    expect(pdf_ocr.clean).to eq(true)
+    expect(File.exists?(pdf_ocr.to_pdf)).to eql(false)
+  end
+
+  it ' warn when tesseract cannot give pdf' do
+    rtesseract = RTesseract.new(@image_for_pdf)
+
+    allow(rtesseract).to receive(:tesseract_version).and_return(3.02)
+    expect { rtesseract.to_pdf }.to raise_error(RTesseract::TesseractVersionError)
+
+    allow(rtesseract).to receive(:tesseract_version).and_return(3.03)
+    expect { rtesseract.to_pdf }.not_to raise_error
+  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')
-    expect(RTesseract.new(@image_tif, tessedit_char_whitelist: "ABCDEF12345").to_s_without_spaces).to eql('43F')
+    expect(RTesseract.new(@image_tif, tessedit_char_whitelist: 'ABCDEF12345').to_s_without_spaces).to eql('43F')
   end
 
   it ' crop image' do
@@ -165,6 +198,13 @@ describe 'Rtesseract' do
     expect(test.to_s_without_spaces).to eql('3R8F')
   end
 
+  it 'does not raise on read with image_magick processor' do
+    expect {
+      instance = RTesseract.read(@image_tif, processor: 'mini_magick') {}
+      expect(instance.processor.a_name?('mini_magick')).to be_truthy
+    }.not_to raise_error
+  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)
@@ -179,7 +219,11 @@ describe 'Rtesseract' do
     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
+  it ' get a numeric value for tesseract version' do
+    expect(RTesseract::Utils.version_number).to be_a Float
+  end
+
+  it ' support default config processors' do
     # Rmagick
     RTesseract.configure { |config| config.processor = 'rmagick' }
     expect(RTesseract.new(@image_tif).processor.a_name?('rmagick')).to eql(true)
@@ -212,6 +256,18 @@ describe 'Rtesseract' do
     expect(RTesseract.new(@image_tif).user_patterns).to eql(' --user-patterns /tmp/test ')
   end
 
+  it ' configure pdf has no effect and kept in-house' do
+    # So it does not interfere with #to_s outputting.
+    RTesseract.configure { |config| config.options_cmd =  ['pdf'] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+
+    RTesseract.configure { |config| config.options_cmd = [:pdf] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+
+    RTesseract.configure { |config| config.options_cmd = [:pdf, 'pdf'] }
+    expect(RTesseract.new(@image_tif).options_cmd).to eql([])
+  end
+
   it ' support new configs' do
     expect(RTesseract.new(@image_tif, tessdata_dir: '/tmp/test').tessdata_dir).to eql(' --tessdata-dir /tmp/test ')
     expect(RTesseract.new(@image_tif, user_words: '/tmp/test').user_words).to eql(' --user-words /tmp/test ')

data/spec/rtesseract_uzn_spec.rb

@@ -0,0 +1,56 @@
+# encoding: UTF-8
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe 'Rtesseract::Uzn' do
+  before do
+    @path = Pathname.new(__FILE__.gsub('rtesseract_uzn_spec.rb', '')).expand_path
+    @image_tif = @path.join('images', 'mixed.tif').to_s
+  end
+
+  it 'should be instantiable' do
+    expect(RTesseract::Uzn.new.class).to eql(RTesseract::Uzn)
+    expect(RTesseract::Uzn.new(@image_tif).class).to eql(RTesseract::Uzn)
+  end
+
+  it 'should translate parts of the image to text from a block' do
+    uzn_block = RTesseract::Uzn.new(@image_tif) do |image|
+      image.area(x: 28, y: 19, w: 25, h: 25) # position of 4
+      image.area(x: 180, y: 22, w: 20, h: 28) # position of 3
+      image.area(x: 218, y: 22, w: 24, h: 28) # position of F
+      image.area(x: 248, y: 24, w: 22, h: 22) # position of F
+    end
+
+    expect(uzn_block.to_s_without_spaces).to eql('43FF')
+  end
+
+  it 'should translate parts of the image to text from initializer options' do
+    @areas = []
+    @areas << { x: 28, y: 19, w: 25, h: 25 } # position of 4
+    @areas << { x: 180, y: 22, w: 20, h: 28 } # position of 3
+    @areas << { x: 218, y: 22, w: 24, h: 28 } # position of f
+    @areas << { x: 248, y: 24, w: 22, h: 22 }  # position of f
+
+    uzn_block = RTesseract::Uzn.new(@image_tif, areas: @areas)
+    expect(uzn_block.to_s_without_spaces).to eql('43FF')
+  end
+
+  it 'should handle a blank image' do
+    @areas = []
+    @areas << { x: 28, y: 19, w: 25, h: 25 } # position of 4
+    @areas << { x: 180, y: 22, w: 20, h: 28 } # position of 3
+    @areas << { x: 218, y: 22, w: 24, h: 28 } # position of f
+    @areas << { x: 248, y: 24, w: 22, h: 22 }  # position of f
+    uzn_block = RTesseract::Uzn.new(@path.join('images', 'blank.tif').to_s, areas: @areas)
+    expect(uzn_block.to_s_without_spaces).to eql('')
+  end
+
+  it ' get a error' do
+    @areas = [{ x: 28, y: 19, w: 25, h: 25 }]
+
+    uzn_block = RTesseract::Uzn.new(@path.join('images', 'test_not_exists.png').to_s, areas: @areas, psm: 7)
+    expect { uzn_block.to_s_without_spaces }.to raise_error(RTesseract::ImageNotSelectedError)
+
+    uzn_block = RTesseract::Uzn.new(@image_tif, areas: @areas, psm: 7, command: 'tesseract_error')
+    expect { uzn_block.to_s }.to raise_error(RTesseract::ConversionError)
+  end
+end

data/spec/spec_helper.rb

@@ -14,5 +14,8 @@ require 'rtesseract'
 # in ./support/ and its subdirectories.
 Dir["#{File.dirname(__FILE__)}/support/**/*.rb"].each { |f| require f }
 
-RSpec.configure do # |config|
+RSpec.configure do |config|
+  config.after(:each) do
+    RTesseract.configuration = RTesseract::Configuration.new
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 2.2.0
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-05-17 00:00:00.000000000 Z
+date: 2018-01-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -70,16 +70,16 @@ dependencies:
   name: jeweler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.1.1
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.1.1
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: simplecov
   requirement: !ruby/object:Gem::Requirement
@@ -94,6 +94,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: coveralls
   requirement: !ruby/object:Gem::Requirement
@@ -138,6 +152,7 @@ files:
 - lib/rtesseract/mixed.rb
 - lib/rtesseract/processor.rb
 - lib/rtesseract/utils.rb
+- lib/rtesseract/uzn.rb
 - rtesseract.gemspec
 - spec/configs/eng.user-words.txt
 - spec/images/README.pdf
@@ -145,6 +160,7 @@ files:
 - spec/images/mixed.tif
 - spec/images/orientation_reverse.png
 - spec/images/test with spaces.tif
+- spec/images/test-pdf.png
 - spec/images/test.bmp
 - spec/images/test.jpg
 - spec/images/test.png
@@ -155,6 +171,7 @@ files:
 - spec/rtesseract_box_spec.rb
 - spec/rtesseract_mixed_spec.rb
 - spec/rtesseract_spec.rb
+- spec/rtesseract_uzn_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/dannnylo/rtesseract
 licenses:
@@ -176,7 +193,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.8
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.