anjlab-tesseract 0.1.1

data/lib/tesseract.rb

@@ -0,0 +1,11 @@
+path = File.join(File.dirname(__FILE__), 'tesseract')
+['dependency_checker', 'file_handler', 'process'].each do |f|
+  require File.expand_path(File.join(path, f))
+end
+require 'pathname'
+require 'digest/md5'
+require 'shellwords'
+
+module Tesseract
+
+end

data/lib/tesseract/dependency_checker.rb

@@ -0,0 +1,40 @@
+module Tesseract
+  class DependencyChecker
+    #putting these here so its easyer to test
+    IMAGE_MAGICK_ERROR = "ImageMagick \"convert\" command not found! Make sure ImageMagick is installed and in the system path"
+    TESSERACT_ERROR = "\"tesseract\" command not found! Make sure tesseract is installed and in the system path"
+    OS_ERROR = "Only Unix Based enviroments are supported Mac, Linux, etc."
+
+    def self.check!
+      check_os!
+      check_for_tesseract!
+      check_for_imagemagick!
+      true
+    end
+
+    private
+    #for easy mocking
+    def self.run_cmd(cmd)
+      `#{cmd}`
+    end
+
+    def self.check_os!
+      case ::RUBY_PLATFORM
+        when /darwin/
+          return true
+        when /linux/, /unix/
+          return true
+      end
+      raise Exception, OS_ERROR
+    end
+
+    def self.check_for_imagemagick!
+      raise Exception, IMAGE_MAGICK_ERROR if run_cmd('which convert').empty?
+    end
+
+    def self.check_for_tesseract!
+      raise Exception, TESSERACT_ERROR if run_cmd('which tesseract').empty?
+    end
+
+  end
+end

data/lib/tesseract/file_handler.rb

@@ -0,0 +1,17 @@
+require 'pathname'
+require 'tempfile'
+module Tesseract
+  class FileHandler
+    @tempfiles = []
+    def self.create_temp_file(filename)
+      file = Pathname.new(Dir::tmpdir).join(filename)
+      @tempfiles << file
+      return file
+    end
+    def self.cleanup!
+      @tempfiles.each do |file|
+        File.unlink(file.to_s) if File.exists?(file.to_s)
+      end
+    end
+  end
+end

data/lib/tesseract/process.rb

@@ -0,0 +1,127 @@
+require 'shellwords'
+module Tesseract
+  class Process
+
+    attr_reader :image
+
+    CONVERT_COMMAND = 'convert'
+    TESSERACT_COMMAND = 'tesseract'
+    # Initialize a Tesseract translation process
+    # image_name is the file to translate
+    # options can be of the following:
+    # * tesseract_options Hash of options for tesseract
+    # * convert_options Array of options for convert
+    # * lang Image input language (eng, fra, etc. )
+    # * convert_command Convert binary name/path
+    # * tesseract_command Tesseract binary name/path
+    # * check_deps Boolean value. If true, verifies dependencies. Defaults to false
+    def initialize(image_name, options = {})
+      defaults = {
+        :tesseract_options => {},
+        :convert_options => {:input => [], :output => []},
+        :lang => :eng,
+        :convert_command => CONVERT_COMMAND,
+        :tesseract_command => TESSERACT_COMMAND,
+        :check_deps => false
+      }
+      @out = nil
+      @image = Pathname.new(image_name)
+      @hash = Digest::MD5.hexdigest("#{@image}-#{Time.now}")
+
+      merge_options! defaults, options
+      DependencyChecker.check! if @options[:check_deps]
+    end
+
+    def merge_options!(defaults, options)
+      @options = {}
+
+      if options.has_key? :tesseract_options
+        @options[:tesseract_options] = defaults[:tesseract_options].merge!(options[:tesseract_options]) if options.has_key? :tesseract_options
+      end
+
+
+      if options.has_key? :convert_options
+        @options[:convert_options] = defaults[:convert_options]
+        defaults[:convert_options].each do |k,v|
+          next unless options[:convert_options].has_key? k
+          @options[:convert_options][k] = v | options[:convert_options][k]
+        end
+        options.delete :convert_options
+      end
+
+      [:tesseract_options, :convert_options].each do |k|
+        options.delete(k) if options.has_key? k
+      end
+      @options = defaults.merge options
+    end
+
+    def lang=(lang)
+      @options[:lang]
+    end
+    def lang
+      @options[:lang]
+    end
+    def to_s
+      @out ||= process!
+    end
+
+    # Process the image into text.
+    def process!
+      temp_image = to_tiff
+      begin
+        text = tesseract_translation(temp_image)
+      rescue IOError
+        raise
+      ensure
+        FileHandler.cleanup!
+      end
+      text.gsub(/^\//, '')
+    end
+
+    # Generates the convert command.
+    def generate_convert_command(temp_file)
+      cmd = [@options[:convert_command]]
+      input_opt = @options[:convert_options][:input]
+      output_opt = @options[:convert_options][:output]
+
+      cmd += input_opt unless input_opt.empty?
+      cmd << Shellwords.shellescape(@image.to_s)
+      cmd += output_opt unless output_opt.empty?
+      cmd << temp_file.to_s
+      cmd.join(" ")
+    end
+
+    # Converts the source image to a tiff file.
+    def to_tiff
+      temp_file = FileHandler.create_temp_file("#{@hash}.tif")
+      executed = system generate_convert_command(temp_file)
+      raise RuntimeError, "`#{@options[:convert_command]}` could not be executed." if executed.nil?
+      temp_file
+    end
+
+    # Translate a tiff file into text
+    def tesseract_translation(image_file)
+      temp_text_file = FileHandler.create_temp_file(@hash.to_s)
+      config_file = write_configs
+      txt_file = "#{temp_text_file}.txt"
+      executed = system [@options[:tesseract_command], image_file.to_s, temp_text_file.to_s, "-l #{@options[:lang]}", config_file, "&> /dev/null"].join(' ')
+      raise RuntimeError, "`#{@options[:tesseract_command]}` could not be executed." if (executed.nil? || executed == false)
+      # wait until file (amazon cloud bug)
+      until File.exist?(txt_file)
+        sleep 1
+      end
+      out = File.read(txt_file)
+      File.unlink txt_file
+      out
+    end
+    # Writes Tesseract configuration for the current source file
+    def write_configs
+      return '' if @options[:tesseract_options].empty?
+      path = FileHandler.create_temp_file("#{@hash}.config")
+      File.open(path, "w+") do |f|
+        @options[:tesseract_options].each { |k,v| f << "#{k} #{v}\n" }
+      end
+      path
+    end
+  end
+end

data/lib/tesseract/version.rb

@@ -0,0 +1,3 @@
+module Tesseract
+  VERSION = '0.1.1'
+end

metadata

@@ -0,0 +1,62 @@
+--- !ruby/object:Gem::Specification
+name: anjlab-tesseract
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+  prerelease: 
+platform: ruby
+authors:
+- Scott Davis
+- Martin Samson
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-04-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: &70257151089280 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: *70257151089280
+description: Ruby wrapper for google tesseract
+email: jetviper21@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/tesseract.rb
+- lib/tesseract/process.rb
+- lib/tesseract/file_handler.rb
+- lib/tesseract/dependency_checker.rb
+- lib/tesseract/version.rb
+homepage: http://github.com/scottdavis/ruby-tesseract
+licenses: []
+post_install_message: 
+rdoc_options:
+- --charset=UTF-8
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.8.6
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 1.3.6
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.15
+signing_key: 
+specification_version: 3
+summary: Ruby wrapper for google tesseract
+test_files: []