rtesseract 0.0.9 → 0.0.10

data/README.rdoc

@@ -24,6 +24,14 @@ It's very simple to use rtesseract:
   image.source = "new_image.png"
   image.to_s
 
+=== TRANSFORM THE IMAGE
+
+  image = RTesseract.read("my_image.jpg") do |img|
+    img = img.white_threshold(245)
+    img = img.quantize(256,Magick::GRAYColorspace)
+  end
+  image.to_s
+
 === CONVERT PARTS OF IMAGE TO STRING
 
   mix_block = RTesseract::Mixed.new("test.jpg") do |image|
@@ -58,4 +66,3 @@ It's very simple to use rtesseract:
 == Copyright
 
 Copyright (c) 2010 Danilo Jeremias da Silva. See LICENSE for details.
-

data/Rakefile

@@ -5,7 +5,7 @@ begin
   require 'jeweler'
   Jeweler::Tasks.new do |gem|
     gem.name = "rtesseract"
-    gem.version = '0.0.9'
+    gem.version = '0.0.10'
     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"
@@ -54,4 +54,3 @@ Rake::RDocTask.new do |rdoc|
   rdoc.rdoc_files.include('README*')
   rdoc.rdoc_files.include('lib/**/*.rb')
 end
-

data/lib/processors/mini_magick.rb

@@ -9,4 +9,14 @@ module MiniMagickProcessor
     cat.write tmp_file.to_s
     return tmp_file
   end
-end
+
+  def image_from_blob(blob)
+    generate_uid
+    tmp_file = Pathname.new(Dir::tmpdir).join("#{@uid}_#{@source.basename}.tif").to_s
+    cat = MiniMagick::Image.read(blob)
+    cat.format("tif")
+    cat.crop("#{@w}x#{@h}+#{@x}+#{@y}") unless [@x, @y, @w, @h].compact == []
+    cat.write tmp_file.to_s
+    return tmp_file
+  end
+end

data/lib/processors/rmagick.rb

@@ -8,4 +8,13 @@ module RMagickProcessor
     cat.write tmp_file.to_s
     return tmp_file
   end
+
+  def image_from_blob(blob)
+    generate_uid
+    tmp_file = Pathname.new(Dir::tmpdir).join("#{@uid}_#{@source.basename}.tif").to_s
+    cat = Magick::Image.from_blob(blob).first
+    cat.crop!(@x, @y, @w, @h) unless [@x, @y, @w, @h].compact == []
+    cat.write tmp_file.to_s
+    return tmp_file
+  end
 end

data/lib/rtesseract.rb

@@ -5,7 +5,7 @@ require "rtesseract/errors"
 require "rtesseract/mixed"
 
 class RTesseract
-  VERSION = '0.0.9'
+  VERSION = '0.0.10'
   attr_accessor :options
   attr_writer   :lang
   attr_writer   :psm
@@ -26,6 +26,15 @@ class RTesseract
     choose_processor!
   end
 
+  def self.read(src = nil, options = {}, &block)
+    raise RTesseract::ImageNotSelectedError if src == nil
+    image = Magick::Image.read(src.to_s).first
+    yield image
+    object = RTesseract.new("", options)
+    object.from_blob(image.to_blob)
+    object
+  end
+
   def source= src
     @value = ""
     @source = Pathname.new src
@@ -127,6 +136,19 @@ class RTesseract
     raise RTesseract::ConversionError
   end
 
+  #Read image from memory blob
+  def from_blob(blob)
+    generate_uid
+    tmp_file  = Pathname.new(Dir::tmpdir).join("#{@uid}_#{@source.basename}")
+    tmp_image = image_from_blob(blob)
+    `#{@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 RTesseract::ConversionError
+  end
+
   #Output value
   def to_s
     return @value if @value != ""
@@ -154,4 +176,3 @@ class RTesseract
     end
   end
 end
-

data/rtesseract.gemspec

@@ -4,14 +4,14 @@
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
-  s.name = %q{rtesseract}
-  s.version = "0.0.9"
+  s.name = "rtesseract"
+  s.version = "0.0.10"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = [%q{Danilo Jeremias da Silva}]
-  s.date = %q{2011-12-01}
-  s.description = %q{Ruby library for working with the Tesseract OCR.}
-  s.email = %q{dannnylo@gmail.com}
+  s.authors = ["Danilo Jeremias da Silva"]
+  s.date = "2012-01-13"
+  s.description = "Ruby library for working with the Tesseract OCR."
+  s.email = "dannnylo@gmail.com"
   s.extra_rdoc_files = [
     "LICENSE",
     "README.rdoc"
@@ -37,10 +37,10 @@ Gem::Specification.new do |s|
     "test/test_mixed.rb",
     "test/test_rtesseract.rb"
   ]
-  s.homepage = %q{http://github.com/dannnylo/rtesseract}
-  s.require_paths = [%q{lib}]
-  s.rubygems_version = %q{1.8.3}
-  s.summary = %q{Ruby library for working with the Tesseract OCR.}
+  s.homepage = "http://github.com/dannnylo/rtesseract"
+  s.require_paths = ["lib"]
+  s.rubygems_version = "1.8.11"
+  s.summary = "Ruby library for working with the Tesseract OCR."
 
   if s.respond_to? :specification_version then
     s.specification_version = 3

data/test/test_rtesseract.rb

@@ -77,6 +77,27 @@ class TestRtesseract < Test::Unit::TestCase
       reg.convert
       assert_not_equal value , reg.generate_uid
     end
+
+    should "read image from blob" do
+      image = Magick::Image.read(@path.join("images","test.png").to_s).first
+      blob = image.white_threshold(245).quantize(256,Magick::GRAYColorspace).to_blob
+
+      test = RTesseract.new
+      test.from_blob(blob)
+      assert_equal test.to_s_without_spaces , "HW9W"
+    end
+
+    should "change image in a block" do
+      test = RTesseract.read(@path.join("images","test.png").to_s) do |image|
+        image = image.white_threshold(245)
+        image = image.quantize(256,Magick::GRAYColorspace)
+      end
+      assert_equal test.to_s_without_spaces , "HW9W"
+
+      test = RTesseract.read(@path.join("images","test.jpg").to_s,{:lang=>'en'}) do |image|
+        image = image.white_threshold(245).quantize(256,Magick::GRAYColorspace)
+      end
+      assert_equal test.to_s_without_spaces , "3R8Z"
+    end
   end
 end
-

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: rtesseract
 version: !ruby/object:Gem::Version 
-  hash: 13
+  hash: 11
   prerelease: 
   segments: 
   - 0
   - 0
-  - 9
-  version: 0.0.9
+  - 10
+  version: 0.0.10
 platform: ruby
 authors: 
 - Danilo Jeremias da Silva
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-12-01 00:00:00 Z
+date: 2012-01-13 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: jeweler
@@ -121,7 +121,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.8.3
+rubygems_version: 1.8.11
 signing_key: 
 specification_version: 3
 summary: Ruby library for working with the Tesseract OCR.