ocr 0.2.0 → 0.3.0

data/README.md

@@ -5,12 +5,15 @@
   Recognize text and characters from image files using web services.
 
 ##Web services supported
+  - [WeOCR project](http://weocr.ocrgrid.org/)
   - [OCR Web Service](http://www.ocrwebservice.com/)([Online OCR](http://www.onlineocr.net/))
     * identify: Username and license code as password
     * languages: :brazilian, :byelorussian, :bulgarian, :catalan, :croatian, :czech, :danish, :dutch, :english, :estonian, :finnish, :french, :german, :greek, :hungarian, :indonesian, :italian, :latin, :latvian, :lithuanian, :moldavian, :polish, :portuguese, :romanian, :russian, :serbian, :slovakian, :slovenian, :spanish, :swedish, :turkish, :ukrainian
     * output formats: :doc, :pdf, :excel, :html, :txt, :rtf
   - [Free OCR online webservice](http://www.free-ocr.co.uk/)
     * identify: Username
+    * No tested for images more than 100x100px in size.
+    * Free service is limited to 100x100px images.
 
 #Installation
 ##From the command line
@@ -44,10 +47,27 @@ gem 'ocr'
   - Test error: error = ocr.error if ocr.error?
   - Results: text = ocr.text unless ocr.error?
 
+### WeOCR project
+  More info at [WeOCR project](http://weocr.ocrgrid.org/).
+
+  Extra properties outputencoding=NAME.
+
+```ruby
+  ocr = OCR.use :weocr
+
+  ocr.file= 'text_image.jpg'
+  ocr.format= :txt
+  ocr.outputencoding="utf-8"
+  ocr.recognize
+
+  puts "ERROR: #{ocr.error}" if ocr.error?
+  puts "RESULT: #{ocr.text}" unless ocr.error?
+```
+
 ### OCR Web Service
   More info at [OCR Web Service](http://www.ocrwebservice.com/).
 
-  Extra properties convert_to_bw=<BOOLEAN>, multi_page_doc=<BOOLEAN>.
+  Extra properties convert_to_bw=BOOLEAN, multi_page_doc=BOOLEAN.
 
 ```ruby
   ocr = OCR.use :onlineocr
@@ -63,7 +83,7 @@ gem 'ocr'
 ```
 
 ### Free OCR online webservice
-  More info at [Free OCR online webservice](http://www.free-ocr.co.uk/).
+  More info at [Free OCR online webservice](http://www.free-ocr.co.uk/). No tested for images larger than 100x100px. Free service is limited to 100x100px images.
 
 ```ruby
   ocr = OCR.use :free_ocr

data/lib/ocr.rb

@@ -1,6 +1,7 @@
 require File.expand_path('../ocr/factory', __FILE__)
 require File.expand_path('../ocr/ocr', __FILE__)
 require File.expand_path('../ocrs/dummy', __FILE__)
+require File.expand_path('../ocrs/weocr', __FILE__)
 require File.expand_path('../ocrs/onlineocr', __FILE__)
 require File.expand_path('../ocrs/free_ocr', __FILE__)
 

data/lib/ocr/version.rb

@@ -1,3 +1,3 @@
 module OCR
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

data/lib/ocrs/weocr.rb

@@ -0,0 +1,55 @@
+require 'net/http'
+require 'rexml/document'
+require 'nokogiri'
+
+module OCR
+  class Weocr < OCR::Ocr
+
+    attr_accessor :outputencoding, :servers, :servers_info, :server_cgi
+
+    def ocr_servers
+      @servers = []
+      @servers_info = {}
+      # Get OCR servers
+      url = 'http://weocr.ocrgrid.org/cgi-bin/weocr/search.cgi?lang=&fmt=xml'
+      xml_data = Net::HTTP.get(URI.parse(url))
+      doc = REXML::Document.new(xml_data)
+      doc.elements.each('weocrlist/server/url') do |ele|
+        @servers << ele.text
+      end
+
+      return unless @servers.count > 0
+
+      xml_data = Net::HTTP.get(URI.parse("#{@servers[0]}srvspec.xml"))
+      doc = REXML::Document.new(xml_data)
+      doc.elements.each('ocrserver/svinfo/cgi') do |ele|
+        @server_cgi = ele.text
+      end
+    end
+
+    private
+    def init
+      super()
+      self.outputencoding= 'utf-8'
+      self.server_cgi= false
+      self.ocr_servers
+    end
+
+    def ocr_recognize
+      raise Exception, 'No available OCR server' unless @server_cgi
+     res = `curl -F userfile=@#{@file} \
+     -F outputencoding="#{outputencoding}" \
+     -F outputformat="#{format.to_s}" \
+     #{@server_cgi} 2>/dev/null`
+
+      doc = Nokogiri::HTML.parse(res)
+      err = doc.search('h2').first
+      return false if have_error? err.content if err
+      set_text doc.search('pre').first.content
+    end
+
+    def have_error? response
+      return true && set_error(response) if response
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ocr
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-28 00:00:00.000000000Z
+date: 2012-03-02 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: savon
-  requirement: &20600860 !ruby/object:Gem::Requirement
+  requirement: &11878720 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,21 @@ dependencies:
         version: 0.9.9
   type: :runtime
   prerelease: false
-  version_requirements: *20600860
+  version_requirements: *11878720
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &11875660 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.5.0
+  type: :runtime
+  prerelease: false
+  version_requirements: *11875660
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &20588220 !ruby/object:Gem::Requirement
+  requirement: &11873900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -32,7 +43,7 @@ dependencies:
         version: 2.7.0
   type: :development
   prerelease: false
-  version_requirements: *20588220
+  version_requirements: *11873900
 description: Recognize text and characters from image files using web services.
 email:
 - mabarroso@mabarroso.com
@@ -42,6 +53,7 @@ extra_rdoc_files: []
 files:
 - lib/ocr.rb
 - lib/ocrs/free_ocr.rb
+- lib/ocrs/weocr.rb
 - lib/ocrs/onlineocr.rb
 - lib/ocrs/dummy.rb
 - lib/ocr/version.rb