rhocr 0.1 → 0.1.1

data/Manifest

@@ -1,7 +1,6 @@
 Manifest
 README
 Rakefile
-TODO.txt
 data/Seite_Die_Gartenlaube_242.html
 data/Seite_Tagebuch_H_C_Lang_08.html
 data/Seite_Tagebuch_H_C_Lang_08.jpg

data/Rakefile

@@ -2,8 +2,8 @@ require 'rubygems'
 require 'rake'
 require 'echoe'
 
-Echoe.new('rhocr', '0.1') do |p|
-  p.description    = "Manipulate and use OCR data encode in HOCR"
+Echoe.new('rhocr', '0.1.1') do |p|
+  p.description    = "Manipulate and use OCR data encoded in hOCR-Format see: http://code.google.com/p/hocr-tools/"
   p.url            = "http://github.com/daandi/rhocr"
   p.author         = "Andreas Neumann"
   p.email          = "andreas@neumann.biz"

data/data/test.html

@@ -14,7 +14,8 @@
 
 <p class='ocr_par' title='bbox 79 109 1119 189' style='font-size:8pt;font-family:"Arial";font-style:normal'><span class='ocr_line' title='bbox 79 109 1119 145'><span class='ocrx_word' title='bbox 79 109 294 144'>Athenobius,</span> <span class='ocrx_word' title='bbox 334 112 398 139'>Der</span> <span class='ocrx_word' title='bbox 417 115 476 139'>von</span> <span class='ocrx_word' title='bbox 494 112 545 139'>der</span> <span class='ocrx_word' title='bbox 565 112 687 140'>Göttin</span> <span class='ocrx_word' title='bbox 707 112 857 140'>Minerva</span> <span class='ocrx_word' title='bbox 876 112 954 145'>lebt,</span> <span class='ocrx_word' title='bbox 974 112 1043 140'>oder:</span> <span class='ocrx_word' title='bbox 1062 112 1119 140'>Mi»</span><br></span><span class='ocr_line' title='bbox 108 155 300 189'><span class='ocrx_word' title='bbox 108 159 183 182'>nerva</span> <span class='ocrx_word' title='bbox 201 155 300 189'>Bogen.</span></span></p>
 
-<p class='ocr_par' title='bbox 74 196 1117 316' style='font-size:8pt;font-family:"Arial";font-style:normal'><span class='ocr_line' title='bbox 160 196 1117 232'><span class='ocrx_word' title='bbox 160 198 214 225'>Des</span> <span class='ocrx_word' title='bbox 242 197 340 230'>Königs</span> <span class='ocrx_word' title='bbox 367 196 503 230'>Antiochus</span> <span class='ocrx_word' title='bbox 531 197 626 230'>Freund</span> <span class='ocrx_word' title='bbox 655 197 713 225'>oder</span> <span class='ocrx_word' title='bbox 739 196 858 232'>geheimer</span> <span class='ocrx_word' title='bbox 885 196 963 230'>Nath.</span> <span class='ocrx_word' title='bbox 994 199 1005 224'>l</span> <span class='ocrx_word' title='bbox 1033 197 1117 226'>Mack.</span><br></span><span class='ocr_line' title='bbox 109 241 206 274'><span class='ocrx_word' title='bbox 109 241 147 274'>15,</span> <span class='ocrx_word' title='bbox 166 242 206 267'>28.</span><br></span><span class='ocr_line' title='bbox 74 281 1116 316'><span class='ocrx_word' title='bbox 74 281 205 315'>Athlai.</span> <span class='ocrx_word' title='bbox 242 284 310 310'>Dee</span> <span class='ocrx_word' title='bbox 337 282 417 315'>Herr</span> <span class='ocrx_word' title='bbox 440 281 598 315'>zerreißet</span> <span class='ocrx_word' title='bbox 625 282 681 310'>oder</span> <span class='ocrx_word' title='bbox 706 282 864 316'>zerbricht.</span> <span class='ocrx_word' title='bbox 898 282 975 310'>Einer</span> <span class='ocrx_word' title='bbox 999 286 1050 310'>von</span> <span class='ocrx_word' title='bbox 1069 282 1116 310'>den</span></span></p>
+<p class='ocr_par' title='bbox 74 196 1117 316' style='font-size:8pt;font-family:"Arial";font-style:normal'><span class='ocr_line' title='bbox 160 196 1117 232'>
+	<span class='ocrx_word' title='bbox 160 198 214 225'>Des</span> <span class='ocrx_word' title='bbox 242 197 340 230'>Königs</span> <span class='ocrx_word' title='bbox 367 196 503 230'>Antiochus</span> <span class='ocrx_word' title='bbox 531 197 626 230'>Freund</span> <span class='ocrx_word' title='bbox 655 197 713 225'>oder</span> <span class='ocrx_word' title='bbox 739 196 858 232'>geheimer</span> <span class='ocrx_word' title='bbox 885 196 963 230'>Nath.</span> <span class='ocrx_word' title='bbox 994 199 1005 224'>l</span> <span class='ocrx_word' title='bbox 1033 197 1117 226'>Mack.</span><br></span><span class='ocr_line' title='bbox 109 241 206 274'><span class='ocrx_word' title='bbox 109 241 147 274'>15,</span> <span class='ocrx_word' title='bbox 166 242 206 267'>28.</span><br></span><span class='ocr_line' title='bbox 74 281 1116 316'><span class='ocrx_word' title='bbox 74 281 205 315'>Athlai.</span> <span class='ocrx_word' title='bbox 242 284 310 310'>Dee</span> <span class='ocrx_word' title='bbox 337 282 417 315'>Herr</span> <span class='ocrx_word' title='bbox 440 281 598 315'>zerreißet</span> <span class='ocrx_word' title='bbox 625 282 681 310'>oder</span> <span class='ocrx_word' title='bbox 706 282 864 316'>zerbricht.</span> <span class='ocrx_word' title='bbox 898 282 975 310'>Einer</span> <span class='ocrx_word' title='bbox 999 286 1050 310'>von</span> <span class='ocrx_word' title='bbox 1069 282 1116 310'>den</span></span></p>
 
 <p class='ocr_par' title='bbox 74 324 1114 401' style='font-size:8pt;font-family:"Arial";font-style:normal'><span class='ocr_line' title='bbox 107 324 594 357'><span class='ocrx_word' title='bbox 107 325 281 357'>Nachlommen</span> <span class='ocrx_word' title='bbox 300 324 392 352'>Bebai.</span> <span class='ocrx_word' title='bbox 410 324 472 356'>Esra</span> <span class='ocrx_word' title='bbox 496 327 533 355'>10,</span> <span class='ocrx_word' title='bbox 553 326 594 351'>28.</span><br></span><span class='ocr_line' title='bbox 74 366 1114 401'><span class='ocrx_word' title='bbox 74 366 189 400'>Athni.</span> <span class='ocrx_word' title='bbox 217 368 296 395'>Eine</span> <span class='ocrx_word' title='bbox 315 367 450 401'>Trübsal</span> <span class='ocrx_word' title='bbox 469 372 528 394'>von</span> <span class='ocrx_word' title='bbox 548 366 638 394'>Gott.</span> <span class='ocrx_word' title='bbox 673 366 722 394'>Ein</span> <span class='ocrx_word' title='bbox 742 366 819 400'>Sohn</span> <span class='ocrx_word' title='bbox 838 366 954 400'>Semaja.</span> <span class='ocrx_word' title='bbox 986 369 998 394'>1</span> <span class='ocrx_word' title='bbox 1018 368 1114 400'>Chron.</span></span></p>
 

data/lib/hocr_box.rb

@@ -46,6 +46,14 @@ class HOCRBox
         other.left_distance_to(self)
     end
     
+    def top_distance_to(other)
+        @top - other.bottom
+    end
+    
+    def bottom_distance_to(other)
+        other.top_distance_to(self)
+    end
+    
     def to_s
         coordinates_to_s
     end

data/lib/ocr_element.rb

@@ -105,7 +105,7 @@ class OCRWord < OCRElement
     end
     
     def to_s
-        "#{text}[#{@features}]"
+        "#{text}:#{coordinates}->#{@features}"
     end
     
     def to_image_html

data/rhocr.gemspec

@@ -2,21 +2,21 @@
 
 Gem::Specification.new do |s|
   s.name = %q{rhocr}
-  s.version = "0.1"
+  s.version = "0.1.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
   s.authors = [%q{Andreas Neumann}]
-  s.date = %q{2011-09-08}
-  s.description = %q{Manipulate and use OCR data encode in HOCR}
+  s.date = %q{2011-09-30}
+  s.description = %q{Manipulate and use OCR data encoded in hOCR-Format see: http://code.google.com/p/hocr-tools/}
   s.email = %q{andreas@neumann.biz}
-  s.extra_rdoc_files = [%q{README}, %q{TODO.txt}, %q{lib/hocr_box.rb}, %q{lib/ocr_document.rb}, %q{lib/ocr_element.rb}, %q{lib/ocr_page.rb}, %q{lib/rhocr.rb}]
-  s.files = [%q{Manifest}, %q{README}, %q{Rakefile}, %q{TODO.txt}, %q{data/Seite_Die_Gartenlaube_242.html}, %q{data/Seite_Tagebuch_H_C_Lang_08.html}, %q{data/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{data/test.html}, %q{data/test.png}, %q{example/example_server.rb}, %q{example/public/OCRTest.css}, %q{example/public/OCRTest.html}, %q{example/public/OCRTest_marker.js}, %q{example/public/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{example/public/img/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{lib/hocr_box.rb}, %q{lib/ocr_document.rb}, %q{lib/ocr_element.rb}, %q{lib/ocr_page.rb}, %q{lib/rhocr.rb}, %q{rhocr.gemspec}, %q{spec/hocr_box_spec.rb}, %q{spec/ocr_document_spec.rb}, %q{spec/ocr_element_spec.rb}, %q{spec/ocr_page_spec.rb}, %q{spec/rhocr_spec.rb}, %q{test.html}]
+  s.extra_rdoc_files = [%q{README}, %q{lib/hocr_box.rb}, %q{lib/ocr_document.rb}, %q{lib/ocr_element.rb}, %q{lib/ocr_page.rb}, %q{lib/rhocr.rb}]
+  s.files = [%q{Manifest}, %q{README}, %q{Rakefile}, %q{data/Seite_Die_Gartenlaube_242.html}, %q{data/Seite_Tagebuch_H_C_Lang_08.html}, %q{data/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{data/test.html}, %q{data/test.png}, %q{example/example_server.rb}, %q{example/public/OCRTest.css}, %q{example/public/OCRTest.html}, %q{example/public/OCRTest_marker.js}, %q{example/public/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{example/public/img/Seite_Tagebuch_H_C_Lang_08.jpg}, %q{lib/hocr_box.rb}, %q{lib/ocr_document.rb}, %q{lib/ocr_element.rb}, %q{lib/ocr_page.rb}, %q{lib/rhocr.rb}, %q{rhocr.gemspec}, %q{spec/hocr_box_spec.rb}, %q{spec/ocr_document_spec.rb}, %q{spec/ocr_element_spec.rb}, %q{spec/ocr_page_spec.rb}, %q{spec/rhocr_spec.rb}, %q{test.html}]
   s.homepage = %q{http://github.com/daandi/rhocr}
   s.rdoc_options = [%q{--line-numbers}, %q{--inline-source}, %q{--title}, %q{Rhocr}, %q{--main}, %q{README}]
   s.require_paths = [%q{lib}]
   s.rubyforge_project = %q{rhocr}
   s.rubygems_version = %q{1.8.6}
-  s.summary = %q{Manipulate and use OCR data encode in HOCR}
+  s.summary = %q{Manipulate and use OCR data encoded in hOCR-Format see: http://code.google.com/p/hocr-tools/}
 
   if s.respond_to? :specification_version then
     s.specification_version = 3

data/spec/hocr_box_spec.rb

@@ -90,5 +90,17 @@ describe HOCRBox do
         end
     end
     
+    describe '#top_distance_to(element)' do
+        it 'box should be 2px below of element' do
+             HOCRBox.new(109,241,206,274).top_distance_to(HOCRBox.new(160,196,1117,232)).should == 9
+        end
+    end
+    
+    describe '#bottom_distance_to(element)' do
+        it 'box should be 2px above of element' do
+            HOCRBox.new(160,196,1117,232).bottom_distance_to(HOCRBox.new(109,241,206,274)).should == 9
+        end
+    end
+    
     
 end

data/spec/ocr_element_spec.rb

@@ -81,6 +81,11 @@ describe OCRElement do
       it 'special #to_html method' do
          @ocr_element.lines[0].words[5].to_html.should == "<span class='ocrx_word'>Minerva</span>"
       end
+      it 'special #to_s method' do
+         @ocr_element.lines[0].words[5].to_s.should == "Minerva:[707, 112, 857, 140]->[]"
+         @ocr_element.lines[0].words[5].features << :a_test << :additional
+         @ocr_element.lines[0].words[5].to_s.should == "Minerva:[707, 112, 857, 140]->[:a_test, :additional]"
+      end
   end
   
  end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rhocr
 version: !ruby/object:Gem::Version
-  version: '0.1'
+  version: 0.1.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-09-08 00:00:00.000000000Z
+date: 2011-09-30 00:00:00.000000000Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70276550001820 !ruby/object:Gem::Requirement
+  requirement: &70233340332980 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,14 +21,13 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70276550001820
-description: Manipulate and use OCR data encode in HOCR
+  version_requirements: *70233340332980
+description: ! 'Manipulate and use OCR data encoded in hOCR-Format see: http://code.google.com/p/hocr-tools/'
 email: andreas@neumann.biz
 executables: []
 extensions: []
 extra_rdoc_files:
 - README
-- TODO.txt
 - lib/hocr_box.rb
 - lib/ocr_document.rb
 - lib/ocr_element.rb
@@ -38,7 +37,6 @@ files:
 - Manifest
 - README
 - Rakefile
-- TODO.txt
 - data/Seite_Die_Gartenlaube_242.html
 - data/Seite_Tagebuch_H_C_Lang_08.html
 - data/Seite_Tagebuch_H_C_Lang_08.jpg
@@ -91,5 +89,5 @@ rubyforge_project: rhocr
 rubygems_version: 1.8.6
 signing_key: 
 specification_version: 3
-summary: Manipulate and use OCR data encode in HOCR
+summary: ! 'Manipulate and use OCR data encoded in hOCR-Format see: http://code.google.com/p/hocr-tools/'
 test_files: []

data/TODO.txt

@@ -1,42 +0,0 @@
-1. Implementiert
-	* HOCR einlesen
-	* Auf HOCR-Elemente zugreifen
-	* Als Text ausgeben
-	* Als formatiertes HTML ausgeben (Stylesheet fehlt)
-	* Auf Grafik ausgeben (nur ohne Nesting)
-	
-	* Erste Tests um Elemente mit Features zu versehen
-
-2. geplant
-	* ABBYY-XML
-	* Algorithmen um Elemente mit Features zu versehen
-	* logische Strukturen markieren
-
-3. Probleme
-	* Testdaten, Stabi liefert schlecht Grafiken
-	* Geschwindigkeit
-	* Algorithmen, wie integrieren? Sollte modular sein
-	* Feste Ordnung wird zur Zeit voraussgesetz
-
-4. Bisheriges Vorgehen
-	=> HOCR einlesen, parsen
-	=> OCRElemente nach bestimmten Kriterien mit Features versehen
-	=> Anhand von Features logische Strukturen ermitteln
-	
-	
-	
-5. geplante Schritte
-	* OCRs in ABBYY-XML von Dokumenten in Antrag anfertigen
-	* Tests in Ruby-Version
-	* weitere Algorithmen um Features zu finden
-	
-	* Scala/Java - Version
-	* Uli/Thorsten XML integrieren
-	* GUI
-
-6. 	Idee: 
-		=> Nutzer wählt Bereiche in GUI aus und benennt sie.
-		=> Features der gewählten Bereiche werden ermittelt.
-		=> Anhand der Features werden aus dem gesamten Dokument die logischen Strukturen extrahiert
-		=> Feedbackschleife in GUI mit 
-			Grafik+Marker|Text als HTML mit Marker|