tesseract 0.0.1

data/Gemfile

@@ -0,0 +1,3 @@
+source 'http://rubygems.org'
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,15 @@
+PATH
+  remote: .
+  specs:
+    tesseract (0.0.1)
+
+GEM
+  remote: http://rubygems.org/
+  specs:
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (>= 1.0.0)
+  tesseract!

data/Rakefile

@@ -0,0 +1,9 @@
+require 'rake'
+require 'rake/testtask'
+require 'rake/rdoctask'
+Rake::TestTask.new do |t|
+  t.libs << "tesseract"
+  t.libs << "test"
+  t.test_files = FileList['test/*_test.rb']
+  t.verbose = true
+end

data/Readme.md

@@ -0,0 +1,22 @@
+# Ruby Tesseract
+
+This is a library for using the tesseract OCR in ruby applications
+
+## Dependcies
+
+1. [Terreract](http://code.google.com/p/tesseract-ocr/)
+2. [ImageMagick](http://www.imagemagick.org/script/index.php) - Note the command line program `convert` needs to be accessible to ruby
+3. *nix based operating system
+
+##Usage
+
+*Please Note the default language is english*
+
+    tess = Tesseract::Process.new("photo.jpg")
+    tess.to_s
+    
+Config options are also supported
+
+    tess = Tesseract::Process.new("photo.jpg", {:lang => 'some language', :chop_enable => 0})
+    tess.to_s
+    

data/tesseract.gemspec

@@ -0,0 +1,20 @@
+Gem::Specification.new do |s|
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+
+  s.name = %q{tesseract}
+  s.version = '0.0.1'
+  s.platform  = Gem::Platform::RUBY
+
+  s.authors = ["Scott Davis"]
+  s.description = %q{Ruby wrapper for google tesseract}
+  s.summary = %q{Ruby wrapper for google tesseract}
+  s.email = %q{jetviper21@gmail.com}
+  s.date = Date.today.to_s
+  s.files        = `git ls-files`.split("\n")
+  s.executables  = `git ls-files`.split("\n").map{|f| f =~ /^bin\/(.*)/ ? $1 : nil}.compact
+  s.require_path = 'tesseract'
+  s.homepage = %q{http://github.com/jetviper21/ruby-tesseract}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.required_rubygems_version = ">= 1.3.6"
+  s.add_development_dependency "bundler", ">= 1.0.0"
+end

data/tesseract.rb

@@ -0,0 +1,54 @@
+Dir["tesseract/*.rb"].each { |file| require file }
+require 'pathname'
+require 'digest/md5'
+module Tesseract
+  class Process
+    attr_reader :image
+    attr_accessor :lang
+    CONVERT_COMMAND = 'convert'
+    TESSERACT_COMMAND = 'tesseract'
+  
+    def initialize(image_name, options = {})
+      DependencyChecker.check!
+      @image = Pathname.new(image_name)
+      @hash = Digest::MD5.hexdigest("#{@image}-#{Time.now}")
+      @lang = options[:lang].nil? ? 'eng' : options.delete(:lang)
+      @options = options
+    end
+  
+    def to_s
+      @out ||= process!
+    end
+  
+    def process!
+      temp_image = to_tiff
+      text = tesseract_translation(temp_image)
+      FileHandler.cleanup!
+      text.gsub(/^\//, '')
+    end
+  
+    def to_tiff
+      temp_file = FileHandler.create_temp_file("#{@hash}.tif")
+      system [CONVERT_COMMAND, image, temp_file].join(" ")
+      temp_file
+    end
+  
+    def tesseract_translation(image_file)
+      temp_text_file = FileHandler.create_temp_file("#{@hash}")
+      config_file = write_configs
+      system [TESSERACT_COMMAND, image_file, temp_text_file, "-l #{@lang}", config_file, "&> /dev/null"].join(" ")
+      File.read("#{temp_text_file}.txt")
+    end
+    
+    def write_configs
+      return '' if @options.empty?
+      path = FileHandler.create_temp_file("#{@hash}.config")
+      File.open(path, "w+") do |f|
+        @options.each { |k,v| f << "#{k} #{v}\n" }
+      end
+      path
+    end
+    
+  end
+  
+end

data/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/tesseract/file_handler.rb

@@ -0,0 +1,20 @@
+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/test/tesseract_test.rb

@@ -0,0 +1,82 @@
+require 'test/unit'
+require 'test/unit/assertions'
+require 'rubygems'
+require 'shoulda'
+require 'test_helper'
+require 'mocha'
+require '../tesseract/tesseract'
+
+class TesseractTest < Test::Unit::TestCase
+  TEST_FILE = File.join(File.dirname(__FILE__), 'photo.jpeg')
+  context "dependency os check fails windows" do
+    setup do
+      @old_val = RUBY_PLATFORM
+      silence_stream(STDERR) { Object.const_set("RUBY_PLATFORM", 'windows') }
+    end
+    should "throw exception" do
+      assert_raises Exception, Tesseract::DependencyChecker::OS_ERROR do
+        Tesseract::Process.new(TEST_FILE)
+      end
+    end
+    teardown do
+      silence_stream(STDERR) { Object.const_set("RUBY_PLATFORM", @old_val) }
+    end
+  end
+  
+  context "dependency imagemagic fails" do
+    setup do
+      Tesseract::DependencyChecker.expects(:run_cmd).with("which tesseract").returns('foo').once
+      Tesseract::DependencyChecker.expects(:run_cmd).with("which convert").returns('').once
+    end
+    should "throw exception" do
+      assert_raises Exception, Tesseract::DependencyChecker::IMAGE_MAGICK_ERROR do
+        Tesseract::Process.new(TEST_FILE)
+      end
+    end
+  end
+  
+  context "dependency tesseract fails" do
+    setup do
+      Tesseract::DependencyChecker.expects(:run_cmd).with("which tesseract").returns('').once
+    end
+    should "throw exception" do
+      assert_raises Exception, Tesseract::DependencyChecker::TESSERACT_ERROR do
+        Tesseract::Process.new(TEST_FILE)
+      end
+    end
+  end
+  
+  context "tesseract" do
+    setup do
+      @tess = Tesseract::Process.new(TEST_FILE)
+    end
+    should "return text" do
+      assert !@tess.to_s.empty?
+    end
+    should "hanve lang of eng" do
+      assert_equal 'eng', @tess.lang
+    end
+  end
+  
+  context "tesseract diff lang" do
+    setup do
+      @tess = Tesseract::Process.new(TEST_FILE, {:lang => 'butts'})
+    end
+    should "have lang of butts" do
+      assert_equal 'butts', @tess.lang
+    end
+  end
+  
+  context "tesseract configs" do
+    setup do
+      @tess = Tesseract::Process.new(TEST_FILE, {:chop_enable=>0})
+    end
+    should "return text" do
+      assert !@tess.to_s.empty?
+    end
+    should "hanve lang of eng" do
+      assert_equal 'eng', @tess.lang
+    end
+  end
+  
+end

data/test/test_helper.rb

@@ -0,0 +1,10 @@
+class Test::Unit::TestCase
+  def silence_stream(stream)
+    old_stream = stream.dup
+    stream.reopen('/dev/null')
+    stream.sync = true
+    yield
+  ensure
+    stream.reopen(old_stream)
+  end
+end

metadata

@@ -0,0 +1,94 @@
+--- !ruby/object:Gem::Specification 
+name: tesseract
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Scott Davis
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-02-22 00:00:00 -05:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: bundler
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 1
+        - 0
+        - 0
+        version: 1.0.0
+  type: :development
+  version_requirements: *id001
+description: Ruby wrapper for google tesseract
+email: jetviper21@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- Gemfile
+- Gemfile.lock
+- Rakefile
+- Readme.md
+- tesseract.gemspec
+- tesseract.rb
+- tesseract/dependency_checker.rb
+- tesseract/file_handler.rb
+- test/photo.jpeg
+- test/tesseract_test.rb
+- test/test_helper.rb
+has_rdoc: true
+homepage: http://github.com/jetviper21/ruby-tesseract
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- tesseract
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 23
+      segments: 
+      - 1
+      - 3
+      - 6
+      version: 1.3.6
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.4.2
+signing_key: 
+specification_version: 3
+summary: Ruby wrapper for google tesseract
+test_files: []
+