motion-ocr 0.0.1 → 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a274f9c83916a0294a98708646178a2a6ca2964d
+  data.tar.gz: 029fbbfd7614ba1d36f8dc2fcf7ec3c90f55f21a
+SHA512:
+  metadata.gz: fb68853812fcef42a7d352676e32da6526c03dd3a25729c33df4c5c95877e9dcd3cb378b3357080e21cc6e6bb3cf59309a34a7ee25f88d4100c844b15cd0b581
+  data.tar.gz: d70e53de63da7bee37206ddf18d93698e5e05c275835292163c209a2a11ad41a07ad6bdfdb6b49631cf908d5d48476f5806bd99bc540d447c3615f9e9674a63a

data/README.md

@@ -10,13 +10,28 @@ First, install the gem:
 
 Then, reference it in your RubyMotion project Rakefile:
 
+    # -*- coding: utf-8 -*-
+    $:.unshift("/Library/RubyMotion/lib")
+    require 'motion/project/template/ios'
+
     require 'motion-ocr'
 
 And that's it. Build your project and MotionOCR will be ready for action.
 
 ### Use
 
-    ocr             = MotionOCR.new
+    ocr             = Motion::OCR.new
     image_with_text = UIImage.imageNamed('phototest.gif').CGImage
 
     ocr.scan(image_with_text) # returns a String containing the detected text in the image
+
+### Options
+
+You use your own Tesseract language file
+(available at https://code.google.com/p/tesseract-ocr/downloads/list).
+
+Put the language file (e.g., `spa.traineddata`) into your app's
+`ressources/tessdata` directory.
+Then pass the language to MotionOCR:
+
+    ocr = Motion::OCR.new language: 'spa'

data/Rakefile

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 require "bundler/gem_tasks"
 $:.unshift("/Library/RubyMotion/lib")
-require 'motion/project'
+require 'motion/project/template/ios'
 
 Bundler.setup
 Bundler.require
@@ -14,4 +14,3 @@ Motion::Project::App.setup do |app|
   app.deployment_target = '5.0'
 
 end
-

data/lib/motion-ocr/ocr.rb

@@ -0,0 +1,19 @@
+module Motion
+  class OCR
+    def initialize(options={})
+      options[:language] ||= "eng"
+      @motion_ocr = MotionOCR.alloc.initWithOptions stringify(options)
+    end
+
+    def scan(image)
+      @motion_ocr.scan image
+    end
+
+    private
+
+    def stringify(hash)
+      stringified = hash.flatten.map(&:to_s)
+      Hash[*stringified]
+    end
+  end
+end

data/lib/motion-ocr/version.rb

@@ -1,3 +1,3 @@
 module MotionOCR
-  VERSION = "0.0.1"
+  VERSION = "0.1.0"
 end

data/spec/motion_ocr_spec.rb

@@ -1,13 +1,45 @@
-describe MotionOCR do
+# encoding: UTF-8
 
-  before do
-    @ocr = MotionOCR.new
-  end
+describe Motion::OCR do
 
   it "can detect the text in the sample image" do
-    image_with_text = UIImage.imageWithContentsOfFile(File.expand_path('../support/phototest.gif', __FILE__)).CGImage
+    ocr = Motion::OCR.new
+
+    ocr.scan(image 'phototest').should == <<-EOF.gsub(/^\W\W+/, '')
+      This is a lot of 12 point text to test the
+      ocr code and see if it works on all types
+      of file format.
+      The quick brown dog jumped over the
+      lazy fox. The quick brown dog jumped
+      over the lazy fox. The quick brown dog
+      jumped over the lazy fox. The quick
+      brown dog jumped over the lazy fox.
+
+    EOF
+  end
+
+  it "accepts the language as parameter" do
+    install_language :deu
+    ocr = Motion::OCR.new language: "deu"
+
+    ocr.scan(image 'phototest_german').should == <<-EOF.gsub(/^\W\W+/, '')
+      Weit hinten, hinter den Wortbergen,
+      fern der Länder Vokalien und Konsonantien
+      leben die Blindtexte.
+      Abgeschieden wohnen sie in Buchstabhausen
+      an der Küste des Semantik,
+      eines großen Sprachozeans.
+      Ein kleines Bächlein namens Duden
+      fließt durch ihren Ort
+      und versorgt sie mit den nötigen Regelialien.
+
+    EOF
+  end
 
-    @ocr.scan(image_with_text).should == <<-EOF.gsub(/^      /, '')
+  it "still works with the old constructor" do
+    ocr = MotionOCR.new
+
+    ocr.scan(image 'phototest').should == <<-EOF.gsub(/^\W\W+/, '')
       This is a lot of 12 point text to test the
       ocr code and see if it works on all types
       of file format.
@@ -20,4 +52,18 @@ describe MotionOCR do
     EOF
   end
 
+  def image(image_name)
+    UIImage.imageWithContentsOfFile(file("#{image_name}.gif")).CGImage
+  end
+
+  def file(file_name)
+    File.expand_path("../support/#{file_name}", __FILE__)
+  end
+
+  def install_language(language)
+    documentPaths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, true)
+    targetPath = "#{documentPaths.first}/tessdata/#{language}.traineddata"
+    fileManager = NSFileManager.defaultManager
+    fileManager.copyItemAtPath file("#{language}.traineddata"), toPath: targetPath, error: nil
+  end
 end

data/vendor/MotionOCR/MotionOCR/MotionOCR.h

@@ -18,5 +18,6 @@ namespace tesseract {
     uint32_t *pixels;
 }
 
+- (id)initWithOptions:(NSDictionary*)options;
 - (NSString *)scan:(id)image;
 @end

data/vendor/MotionOCR/MotionOCR/MotionOCR.mm

@@ -16,32 +16,36 @@
 @implementation MotionOCR
 
 - (id)init {
-    self = [super init];
-
-    if (self) {
-        // Set up the tessdata path. This is included in the application bundle
-        // but is copied to the Documents directory on the first run.
-        NSArray *documentPaths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES);
-        NSString *documentPath = ([documentPaths count] > 0) ? [documentPaths objectAtIndex:0] : nil;
-
-        NSString *dataPath = [documentPath stringByAppendingPathComponent:@"tessdata"];
-        NSFileManager *fileManager = [NSFileManager defaultManager];
-        // If the expected store doesn't exist, copy the default store.
-        if (![fileManager fileExistsAtPath:dataPath]) {
-            // get the path to the app bundle (with the tessdata dir)
-            NSString *bundlePath = [[NSBundle mainBundle] bundlePath];
-            NSString *tessdataPath = [bundlePath stringByAppendingPathComponent:@"tessdata"];
-            if (tessdataPath) {
-                [fileManager copyItemAtPath:tessdataPath toPath:dataPath error:NULL];
-            }
-        }
-
-        setenv("TESSDATA_PREFIX", [[documentPath stringByAppendingString:@"/"] UTF8String], 1);
-
-        tesseract = new tesseract::TessBaseAPI();
-        tesseract->Init([dataPath cStringUsingEncoding:NSUTF8StringEncoding], "eng");
-    }
-    return self;
+  return [self initWithOptions:@{}];
+}
+
+- (id)initWithOptions:(NSDictionary*)options {
+  self = [super init];
+
+  if (self) {
+      // Set up the tessdata path. This is included in the application bundle
+      // but is copied to the Documents directory on the first run.
+      NSArray *documentPaths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES);
+      NSString *documentPath = ([documentPaths count] > 0) ? [documentPaths objectAtIndex:0] : nil;
+
+      NSString *dataPath = [documentPath stringByAppendingPathComponent:@"tessdata"];
+      NSFileManager *fileManager = [NSFileManager defaultManager];
+      // If the expected store doesn't exist, copy the default store.
+      if (![fileManager fileExistsAtPath:dataPath]) {
+          // get the path to the app bundle (with the tessdata dir)
+          NSString *bundlePath = [[NSBundle mainBundle] bundlePath];
+          NSString *tessdataPath = [bundlePath stringByAppendingPathComponent:@"tessdata"];
+          if (tessdataPath) {
+              [fileManager copyItemAtPath:tessdataPath toPath:dataPath error:NULL];
+          }
+      }
+
+      setenv("TESSDATA_PREFIX", [[documentPath stringByAppendingString:@"/"] UTF8String], 1);
+
+      tesseract = new tesseract::TessBaseAPI();
+      tesseract->Init([dataPath cStringUsingEncoding:NSUTF8StringEncoding], [options[@"language"] UTF8String]);
+  }
+  return self;
 }
 
 - (void)dealloc {

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: motion-ocr
 version: !ruby/object:Gem::Version
-  version: 0.0.1
-  prerelease: 
+  version: 0.1.0
 platform: ruby
 authors:
 - Fernando Espinosa Jiménez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-01-05 00:00:00.000000000 Z
+date: 2014-10-09 00:00:00.000000000 Z
 dependencies: []
 description: Allows to perform text detection inside images in an easy way.
 email:
@@ -18,7 +17,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - Gemfile.lock
 - LICENSE
@@ -26,12 +25,15 @@ files:
 - Rakefile
 - app/app_delegate.rb
 - lib/motion-ocr.rb
+- lib/motion-ocr/ocr.rb
 - lib/motion-ocr/version.rb
 - motion-ocr.gemspec
 - resources/tessdata/configs/nodict
 - resources/tessdata/eng.traineddata
 - spec/motion_ocr_spec.rb
+- spec/support/deu.traineddata
 - spec/support/phototest.gif
+- spec/support/phototest_german.gif
 - vendor/MotionOCR/MotionOCR.bridgesupport
 - vendor/MotionOCR/MotionOCR.xcodeproj/project.pbxproj
 - vendor/MotionOCR/MotionOCR.xcodeproj/project.xcworkspace/contents.xcworkspacedata
@@ -86,28 +88,29 @@ files:
 - vendor/MotionOCR/MotionOCR/build_dependencies/dependencies/lib/libtesseract_all.a
 homepage: https://github.com/ferdev/motion-ocr
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A RubyMotion wrapper for the OCR engine, Tesseract
 test_files:
 - spec/motion_ocr_spec.rb
+- spec/support/deu.traineddata
 - spec/support/phototest.gif
+- spec/support/phototest_german.gif