rtesseract 0.0.6 → 0.0.7

data/README.rdoc

@@ -24,6 +24,26 @@ It's very simple to use rtesseract:
   image.source = "new_image.png"
   image.to_s
 
+=== CONVERT PARTS OF IMAGE TO STRING
+
+  mix_block = RTesseract::Mixed.new("test.jpg") do |image|
+    image.area(28,  19, 25, 25)
+    image.area(180, 22, 20, 28)
+    image.area(218, 22, 24, 28)
+    image.area(248, 24, 22, 22)
+  end
+  mix_block.to_s
+
+  OR
+
+  mix_block = RTesseract::Mixed.new("test.jpg",{:areas => [
+    {:x => 28,  :y=>19, :width=>25, :height=>25 },
+    {:x => 180,  :y=>22, :width=>20, :height=>28},
+    {:x => 218,  :y=>22, :width=>24, :height=>28},
+    {:x => 248,  :y=>24, :width=>22, :height=>22}
+  ]})
+  mix_block.to_s
+
 == Note on Patches/Pull Requests
 
 * Fork the project.

data/Rakefile

@@ -5,13 +5,15 @@ begin
   require 'jeweler'
   Jeweler::Tasks.new do |gem|
     gem.name = "rtesseract"
-    gem.version = '0.0.6'
+    gem.version = '0.0.7'
     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.homepage = "http://github.com/dannnylo/rtesseract"
     gem.authors = ["Danilo Jeremias da Silva"]
+    gem.add_development_dependency "jeweler", ">=1.4.0"
     gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+
     gem.add_runtime_dependency "rmagick", '>= 2.10.1'
   end
   Jeweler::GemcutterTasks.new

data/lib/rtesseract/errors.rb

@@ -1,4 +1,6 @@
 class RTesseract
   class ConversionError < StandardError ;end
+  class ImageNotSelectedError < StandardError ;end
+  class TempFilesNotRemovedError < StandardError ;end
 end
 

data/lib/rtesseract/mixed.rb

@@ -40,7 +40,7 @@ class RTesseract
         convert
         @value
       else
-        raise "Select a image file."
+        raise RTesseract::ImageNotSelectedError
       end
     end
 

data/lib/rtesseract.rb

@@ -6,15 +6,19 @@ require "rtesseract/errors"
 require "rtesseract/mixed"
 
 class RTesseract
-  VERSION = '0.0.6'
+  VERSION = '0.0.7'
   attr_accessor :options
   attr_writer   :lang
+  attr_writer   :psm
 
   def initialize(src="", options={})
     @uid = options.delete(:uid) || nil
     @source  = Pathname.new src
     @command = options.delete(:command) || "tesseract"
     @lang    = options.delete(:lang) || options.delete("lang") || ""
+    @psm    = options.delete(:psm) || options.delete("psm") || nil
+    @clear_console_output = options.delete(:clear_console_output)
+    @clear_console_output = true if @clear_console_output.nil?
     @options = options
     @value   = ""
     @x,@y,@w,@h = []
@@ -55,8 +59,8 @@ class RTesseract
       end
     end
     true
-    rescue
-      raise "Error on remove file."
+  rescue
+    raise RTesseract::TempFilesNotRemovedError
   end
 
   def generate_uid
@@ -77,15 +81,28 @@ class RTesseract
   ## * vie   - Vietnamese
   ## Note: Make sure you have installed the language to tesseract
   def lang
-    language = "#{@lang}".strip
-    {"eng" => ["eng","en","en-us","english"], "deu" => ["deu"], "deu-f" => ["deu-f"] , "fra" => ["fra"], "ita" => ["ita","it"] , "nld" => ["nld"] , "por" => ["por","pt","pt-br","portuguese"] , "spa" => ["spa"] , "vie" => ["vie"]}.each do |value,names|
-      return " -l #{value} " if names.include? language.downcase
+    language = "#{@lang}".strip.downcase
+    { #Aliases to languages names
+      "eng" => ["en","en-us","english"],
+      "ita" => ["it"],
+      "por" => ["pt","pt-br","portuguese"],
+      "spa" => ["sp"]
+    }.each do |value,names|
+      return " -l #{value} " if names.include? language
     end
+    return " -l #{language} " if language.size > 0
     ""
   rescue
     ""
   end
 
+  #Page Segment Mode
+  def psm
+    @psm.nil? ? "" : " -psm #{@psm} "
+  rescue
+    ""
+  end
+
   def config
     @options ||= {}
     @options.collect{|k,v| "#{k} #{v}" }.join("\n")
@@ -98,17 +115,23 @@ class RTesseract
     conf.path
   end
 
+  #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
+  end
+
   #Convert image to string
   def convert
     generate_uid
     tmp_file  = Pathname.new(Dir::tmpdir).join("#{@uid}_#{@source.basename}")
     tmp_image = image_to_tiff
-    `#{@command} #{tmp_image} #{tmp_file.to_s} #{lang} #{config_file}`
+    `#{@command} #{tmp_image} #{tmp_file.to_s} #{lang} #{psm} #{config_file} #{clear_console_output}`
     @value = File.read("#{tmp_file.to_s}.txt").to_s
     @uid = nil
     remove_file([tmp_image,"#{tmp_file.to_s}.txt"])
   rescue
-    raise "Error on conversion."
+    raise RTesseract::ConversionError
   end
 
   #Output value
@@ -118,7 +141,7 @@ class RTesseract
       convert
       @value
     else
-      raise "Select a image file."
+      raise RTesseract::ImageNotSelectedError
     end
   end
 

data/rtesseract.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{rtesseract}
-  s.version = "0.0.6"
+  s.version = "0.0.7"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Danilo Jeremias da Silva"]
-  s.date = %q{2011-03-02}
+  s.date = %q{2011-03-16}
   s.description = %q{Ruby library for working with the Tesseract OCR.}
   s.email = %q{dannnylo@gmail.com}
   s.extra_rdoc_files = [
@@ -49,13 +49,16 @@ Gem::Specification.new do |s|
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<jeweler>, [">= 1.4.0"])
       s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 0"])
       s.add_runtime_dependency(%q<rmagick>, [">= 2.10.1"])
     else
+      s.add_dependency(%q<jeweler>, [">= 1.4.0"])
       s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
       s.add_dependency(%q<rmagick>, [">= 2.10.1"])
     end
   else
+    s.add_dependency(%q<jeweler>, [">= 1.4.0"])
     s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
     s.add_dependency(%q<rmagick>, [">= 2.10.1"])
   end

data/test/test_mixed.rb

@@ -16,12 +16,20 @@ class TestMixed < Test::Unit::TestCase
 
     should "translate parts of the image to text" do
       mix_block = RTesseract::Mixed.new(@image_tiff) do |image|
-       image.area(28,  19, 25, 25) #position of 4
-       image.area(180, 22, 20, 28) # position of 3
-       image.area(218, 22, 24, 28) # position of z
-       image.area(248, 24, 22, 22) # position of z
+        image.area(28,  19, 25, 25) #position of 4
+        image.area(180, 22, 20, 28) # position of 3
+        image.area(218, 22, 24, 28) # position of z
+        image.area(248, 24, 22, 22) # position of z
       end
       assert_equal mix_block.to_s_without_spaces , "43ZZ"
+
+      mix_block = RTesseract::Mixed.new(@image_tiff,{:areas => [
+        {:x => 28,  :y=>19, :width=>25, :height=>25 }, #position of 4
+        {:x => 180,  :y=>22, :width=>20, :height=>28}, # position of 3
+        {:x => 218,  :y=>22, :width=>24, :height=>28}, # position of z
+        {:x => 248,  :y=>24, :width=>22, :height=>22}  # position of z
+      ]})
+      assert_equal mix_block.to_s_without_spaces , "43ZZ"
     end
   end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rtesseract
 version: !ruby/object:Gem::Version 
-  hash: 19
+  hash: 17
   prerelease: 
   segments: 
   - 0
   - 0
-  - 6
-  version: 0.0.6
+  - 7
+  version: 0.0.7
 platform: ruby
 authors: 
 - Danilo Jeremias da Silva
@@ -15,13 +15,29 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-03-02 00:00:00 -03:00
+date: 2011-03-16 00:00:00 -03:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: thoughtbot-shoulda
+  name: jeweler
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 7
+        segments: 
+        - 1
+        - 4
+        - 0
+        version: 1.4.0
+  type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: thoughtbot-shoulda
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -31,11 +47,11 @@ dependencies:
         - 0
         version: "0"
   type: :development
-  version_requirements: *id001
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: rmagick
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -47,7 +63,7 @@ dependencies:
         - 1
         version: 2.10.1
   type: :runtime
-  version_requirements: *id002
+  version_requirements: *id003
 description: Ruby library for working with the Tesseract OCR.
 email: dannnylo@gmail.com
 executables: []