rtesseract 2.2.0 → 3.0.0

data/Rakefile

@@ -1,50 +1,6 @@
-# encoding: utf-8
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
 
-require 'rubygems'
-require 'bundler'
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts 'Run `bundle install` to install missing gems'
-  exit e.status_code
-end
-require 'rake'
+RSpec::Core::RakeTask.new(:spec)
 
-require 'jeweler'
-Jeweler::Tasks.new do |gem|
-  # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
-  gem.name = 'rtesseract'
-  gem.homepage = 'http://github.com/dannnylo/rtesseract'
-  gem.license = 'MIT'
-  gem.summary = 'Ruby library for working with the Tesseract OCR.'
-  gem.description = 'Ruby library for working with the Tesseract OCR.'
-  gem.email = 'dannnylo@gmail.com'
-  gem.authors = ['Danilo Jeremias da Silva']
-  # dependencies defined in Gemfile
-end
-Jeweler::RubygemsDotOrgTasks.new
-
-require 'rspec/core'
-require 'rspec/core/rake_task'
-RSpec::Core::RakeTask.new(:spec) do |spec|
-  spec.pattern = FileList['spec/**/*_spec.rb']
-end
-
-desc 'Code coverage detail'
-task :simplecov do
-  ENV['COVERAGE'] = 'true'
-  Rake::Task['spec'].execute
-end
-
-task default: :spec
-
-require 'rdoc/task'
-Rake::RDocTask.new do |rdoc|
-  version = File.exist?('VERSION') ? File.read('VERSION') : ''
-
-  rdoc.rdoc_dir = 'rdoc'
-  rdoc.title = "rtesseract #{version}"
-  rdoc.rdoc_files.include('README*')
-  rdoc.rdoc_files.include('lib/**/*.rb')
-end
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "rtesseract"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/rtesseract.rb

@@ -1,244 +1,46 @@
-# encoding: UTF-8
-require 'pathname'
-require 'tempfile'
+require "rtesseract/check"
+require "rtesseract/configuration"
+require "rtesseract/command"
+require "rtesseract/text"
+require "rtesseract/pdf"
+require "rtesseract/box"
+require "rtesseract/tsv"
 
-require 'rtesseract/utils'
-require 'rtesseract/configuration'
-require 'rtesseract/errors'
-
-# Ruby wrapper for Tesseract OCR
 class RTesseract
-  attr_accessor :configuration
-  attr_reader :processor
-  attr_reader :source
-
-  def initialize(src = '', options = {})
-    self.configuration = RTesseract.local_config(options)
-    @options = options || {}
-    @points = {}
-    @processor = RTesseract::Processor.choose_processor!(configuration.processor)
-    self.source = src
-    initialize_hook
-  end
-
-  # Hook to end of initialize method
-  def initialize_hook
-  end
-
-  # Define the source
-  def source=(src)
-    @value = nil
-    @pdf_path = nil
-    @source = @processor.image?(src) ? src : Pathname.new(src)
-  end
-
-  # Crop image to convert
-  def crop!(points = {})
-    @value = nil
-    @points = points
-    self
-  end
-
-  # Select the language
-  # ===Languages
-  ## * eng   - English
-  ## * deu   - German
-  ## * deu-f - German fraktur
-  ## * fra   - French
-  ## * ita   - Italian
-  ## * nld   - Dutch
-  ## * por   - Portuguese
-  ## * spa   - Spanish
-  ## * vie   - Vietnamese
-  ## Note: Make sure you have installed the language to tesseract
-  def lang
-    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
-    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)
-  end
-
-  # User Words
-  def user_words
-    option_to_string('--user-words', configuration.user_words)
-  end
-
-  # User Patterns
-  def user_patterns
-    option_to_string('--user-patterns', configuration.user_patterns)
-  end
-
-  # Options on line
-  def 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
+  class Error < StandardError; end
 
-  # Write config to file
-  def config_file
-    config_hook
-    return '' if @options == {}
-    conf = Tempfile.new('config')
-    conf.write(config)
-    conf.flush
-    conf.path
-  end
-
-  # TODO: Clear console for MacOS or Windows
-  def clear_console_output
-    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
-
-  # Detect version number
-  def tesseract_version
-    RTesseract::Utils.version_number
-  end
-
-
-  # Rand file path
-  def file_dest
-    @file_dest = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
-  end
-
-  # 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}" "#{file_dest}" #{lang} #{oem} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{options_cmd.join(' ')}`
-  end
+  check_version!
 
-  # Is pdf output?
-  def pdf?
-    options_cmd.include? 'pdf'
-  end
+  attr_reader :config, :source
 
-  # Read result file
-  def convert_text
-    @value = File.read(file_with_ext).to_s
+  def initialize(src = '', options = {})
+    @source = src
+    @config = RTesseract.config.merge(options)
   end
 
-  # Store pdf result path
-  def convert_pdf
-    @pdf_path = file_with_ext('.pdf')
+  def to_box
+    Box.run(@source, config)
   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
+  def words
+    to_box.map { |word| word[:word] }
   end
 
-  # Hook to convert
-  def after_convert_hook
+  def to_pdf
+    Pdf.run(@source, config)
   end
 
-  # Convert image to string
-  def convert
-    convert_command
-    after_convert_hook
-    convert_result
-  rescue => error
-    raise RTesseract::ConversionError.new(error), error, caller
+  def to_tsv
+    Tsv.run(@source, config)
   end
 
   # Output value
   def to_s
-    return @value if @value
-
-    if @processor.image?(@source) || @source.file?
-      convert
-      @value
-    else
-      fail RTesseract::ImageNotSelectedError.new(@source)
-    end
+    Text.run(@source, config)
   end
 
   # Remove spaces and break-lines
   def to_s_without_spaces
     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'
-require 'rtesseract/processor'
-
-# Processors
-require 'processors/rmagick.rb'
-require 'processors/mini_magick.rb'
-require 'processors/none.rb'

data/lib/rtesseract/box.rb

@@ -1,73 +1,28 @@
-# encoding: UTF-8
 require 'nokogiri'
-require 'fileutils'
+require 'tmpdir'
 
-# RTesseract
 class RTesseract
-  # Class to read char positions from an image
-  class Box < RTesseract
-    # Setting value as blank array
-    def initialize_hook
-      @value = []
+  module Box
+    def self.temp_dir
+      @file_path = Pathname.new(Dir.tmpdir)
     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(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
+    def self.run(source, options)
+      name = "rtesseract_#{SecureRandom.uuid}"
+      options.tessedit_create_hocr = 1
 
-    # Move file html to hocr
-    def after_convert_hook
-      FileUtils.mv(file_with_ext('.html'), file_with_ext) rescue nil
-    end
+      RTesseract::Command.new(source, temp_dir.join(name).to_s, options).run
 
-    # 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
+      parse(temp_dir.join("#{name}.hocr").read)
     end
 
-    # Parse word data from html.
-    class BoxParser
-      def initialize(word_html)
-        @word = word_html
-        title = @word.attributes['title'].value.to_s
-        @attributes = title.gsub(';', '').split(' ')
-      end
+    def self.parse(content)
+      html = Nokogiri::HTML(content)
+      html.css('span.ocrx_word, span.ocr_word').map do |word|
+        @attributes = word.attributes['title'].value.to_s.gsub(';', '').split(' ')
 
-      # Hash of word and position
-      def to_h
         {
-          word: @word.text,
+          word: word.text,
           x_start: @attributes[1].to_i,
           y_start: @attributes[2].to_i,
           x_end: @attributes[3].to_i,
@@ -76,4 +31,4 @@ class RTesseract
       end
     end
   end
-end
+end

data/lib/rtesseract/check.rb

@@ -0,0 +1,14 @@
+
+class RTesseract
+  class << self
+    def tesseract_version
+      Open3.capture2e(RTesseract.config.command, "--version").first.to_s.match(/\d+.\d+/)[0].to_f
+    rescue Errno::ENOENT
+      0
+    end
+
+    def check_version!
+      raise RTesseract::Error.new('Tesseract OCR 3.5 or later not installed') if RTesseract.tesseract_version < 3.05
+    end
+  end
+end