RubyGems - rhocr - Versions diffs - 0.0.3 → 0.1 - Mend

rhocr 0.0.3 → 0.1

Files changed (28) hide show

data/Manifest +15 -6
data/Rakefile +3 -3
data/TODO.txt +42 -0
data/data/Seite_Die_Gartenlaube_242.html +42 -0
data/data/Seite_Tagebuch_H_C_Lang_08.jpg +0 -0
data/data/test.html +71 -0
data/data/test.png +0 -0
data/example/example_server.rb +2 -2
data/example/public/Seite_Tagebuch_H_C_Lang_08.jpg +0 -0
data/lib/hocr_box.rb +67 -0
data/lib/ocr_document.rb +50 -0
data/lib/ocr_element.rb +149 -0
data/lib/ocr_page.rb +80 -25
data/lib/rhocr.rb +30 -1
data/rhocr.gemspec +12 -9
data/spec/hocr_box_spec.rb +94 -0
data/spec/ocr_document_spec.rb +80 -0
data/spec/ocr_element_spec.rb +86 -0
data/spec/ocr_page_spec.rb +116 -0
data/spec/rhocr_spec.rb +34 -0
data/test.html +1 -0
metadata +52 -39
data/example/public/img/Seite_Tagebuch_H_C_Lang_05.jpg +0 -0
data/lib/ocr_box.rb +0 -43
data/lib/ocrx_word.rb +0 -23
data/rspec/ocr_box_spec.rb +0 -48
data/rspec/ocr_page_spec.rb +0 -17
data/rspec/ocrx_word_spec.rb +0 -32

data/test.html ADDED Viewed

@@ -0,0 +1 @@

+ <div class='ocr_page' style='position:absolute; top:0px; left:0px; height:1326px; width:1326px;;background-image: url(data/test.png); width:1326px; height:1326>px ;'>Athenobius—Aulon.29Athenobius,DervonderGöttinMinervalebt,oder:Mi»nervaBogen.DesKönigsAntiochusFreundodergeheimerNath.lMack.15,28.Athlai.DeeHerrzerreißetoderzerbricht.EinervondenNachlommenBebai.Esra10,28.Athni.EineTrübsalvonGott.EinSohnSemaja.1Chron.27.7.Athniel.GottesTrübsal,d.i.eineTrübsal,vonGottzugesügt.EinSohnKenas,desBrudersKaleb;gewannKiriathSepher,unddamitAchsa.dieTochterseinesBettersKaleb.Nicht,1.12.13.Atroth-Sophan,dieKroneoderDecke,oderBedeckungdes'Hügels.EineStadtderRubenitenimKönigreichSthon.4Mos.32,35.AtrothAddar:DieKroneAddar(desSohnesBenjamin).DieseStadtgehörtedenBenjaminitern,lagindenGrenzenIudatmdEphraim.Atroth.Beth-Ioab,d.i.dieKronedesHausesIoab.EineStadtinIuda,wodieNachlommenSalmagewohnthaben.1Chron.2,54.Attalia.EineStadtinPamphilienod.Libyen,vonAttalaPhila.delphoerbaut.Ap.Gesch.14,25.AttalusEinKöniginMysien,welchesunterPhrygiengehörte;,genanntvonAttale,welchesbeidenPhrygiernKropfoderGurgelgeheißenhabensoll.,WareinKönigderPergamenerundPhrvgier.lMack.15,22.Ava.IstbeidenaltenGriechenAiaod.Aea,dieHauptstadtinCol»chide,woAetasregierte.ColchisheißtheutigesTagesMengrelicn,diemeistenEinwohnersindChristen.VonhierwurdendieLeutevonSalmanasscrnachSamariagesührt,wosienochihreGötterNibehasundTharthacanbeteten.2Kön.l7,24.31.Aven.Götze,Eitelleit.SowirdBethelgenannt.Hos.10,8.wegenderGötzen,diedaselbstvondenIsraelitenverehrtwurden.MitdemganzenNamen:Beth»Aven,dasGötzenhaus,oder,damandemEitelnnachwandelt.Hos.4,15.Augustus.Würdigverehrtundangebetetzuwerden.DiesenNamengabdasromischeVolldemKaiserOctavian,undalleromischenKaiserhabendiesenNamenbeibehalten,daßsie«au,-per2ußr>«ti,d.i,allzeitMehrerdesReichsgeheißenhaben.Avith.Haufe.EineStadtinIdumäa.1Mos.36,35.Aulon.Ausgehöhlt.DasgroßeThal,worindieberühmtenStädteVethsanoderScythopolis,Tlberias,Iericho,dastodteMeer</div>

metadata CHANGED Viewed

@@ -1,82 +1,95 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification
 name: rhocr
-version: !ruby/object:Gem::Version
+version: !ruby/object:Gem::Version
+  version: '0.1'
   prerelease:
-  version: 0.0.3
 platform: ruby
-authors:
+authors:
 - Andreas Neumann
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2011-07-03 00:00:00 +02:00
-default_executable:
-dependencies: []
+date: 2011-09-08 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: &70276550001820 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *70276550001820
 description: Manipulate and use OCR data encode in HOCR
-email: info @nospam@ an-it.com
+email: andreas@neumann.biz
 executables: []
 extensions: []
-extra_rdoc_files:
+extra_rdoc_files:
 - README
-- lib/ocr_box.rb
+- TODO.txt
+- lib/hocr_box.rb
+- lib/ocr_document.rb
+- lib/ocr_element.rb
 - lib/ocr_page.rb
-- lib/ocrx_word.rb
 - lib/rhocr.rb
-files:
+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
+- data/test.html
+- data/test.png
 - example/example_server.rb
 - example/public/OCRTest.css
 - example/public/OCRTest.html
 - example/public/OCRTest_marker.js
-- example/public/img/Seite_Tagebuch_H_C_Lang_05.jpg
+- example/public/Seite_Tagebuch_H_C_Lang_08.jpg
 - example/public/img/Seite_Tagebuch_H_C_Lang_08.jpg
-- lib/ocr_box.rb
+- lib/hocr_box.rb
+- lib/ocr_document.rb
+- lib/ocr_element.rb
 - lib/ocr_page.rb
-- lib/ocrx_word.rb
 - lib/rhocr.rb
 - rhocr.gemspec
-- rspec/ocr_box_spec.rb
-- rspec/ocr_page_spec.rb
-- rspec/ocrx_word_spec.rb
-has_rdoc: true
+- spec/hocr_box_spec.rb
+- spec/ocr_document_spec.rb
+- spec/ocr_element_spec.rb
+- spec/ocr_page_spec.rb
+- spec/rhocr_spec.rb
+- test.html
 homepage: http://github.com/daandi/rhocr
 licenses: []
 post_install_message:
-rdoc_options:
+rdoc_options:
 - --line-numbers
 - --inline-source
 - --title
 - Rhocr
 - --main
 - README
-require_paths:
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements:
-  - - ">="
-    - !ruby/object:Gem::Version
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements:
-  - - ">="
-    - !ruby/object:Gem::Version
-      version: "1.2"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '1.2'
 requirements: []
 rubyforge_project: rhocr
-rubygems_version: 1.6.2
+rubygems_version: 1.8.6
 signing_key:
 specification_version: 3
 summary: Manipulate and use OCR data encode in HOCR
 test_files: []

data/example/public/img/Seite_Tagebuch_H_C_Lang_05.jpg DELETED Viewed

Binary file

data/lib/ocr_box.rb DELETED Viewed

@@ -1,43 +0,0 @@
-#coding: utf-8
-class OCRBox
-    attr_reader :x1, :y1, :x2, :y2
-    def initialize(x1, y1 , x2, y2)
-        @x1 = x1
-        @y1 = y1
-        @x2 = x2
-        @y2 = y2
-    end
-    def encloses?(element)
-        @x1 <= element.x1 and
-        @x2 >= element.x2 and
-        @y1 <= element.y1 and
-        @y2 >= element.y2
-    end
-    def enclosed_by?(element)
-        return element.encloses? self
-    end
-    def to_s
-        "tl->(x:#{@x1} y:#{@y1})/br->:(x:#{@x2} y:#{@y2})"
-    end
-    def to_css_style
-        top     = @y1
-        left    = @x1
-        height  = @y2 - @y1
-        width   = @x2 - @x1
-        "position:absolute; top:#{top}px; left:#{left}px; height:#{height}px; width:#{width}px;"
-    end
-    def to_json
-    end
-end

data/lib/ocrx_word.rb DELETED Viewed

@@ -1,23 +0,0 @@
-#coding: utf-8
-require 'cgi'
-require_relative 'ocr_box'
-class OCRXWord < OCRBox
-    attr_reader :text
-    def initialize(x1,y1,x2,y2,word)
-        super(x1.to_i, y1.to_i, x2.to_i, y2.to_i)
-        @text = word
-    end
-    def to_html(css_class = 'ocrx_word')
-        "<span style='#{ to_css_style }' class='#{css_class}'><span class='word'>" + CGI::escapeHTML(@text) +"</span></span>"
-    end
-    def to_s
-        "#{@text}\t#{super}"
-    end
-end

data/rspec/ocr_box_spec.rb DELETED Viewed

@@ -1,48 +0,0 @@
-#coding: utf-8
-require_relative '../lib/ocr_box'
-describe OCRBox do
-    before(:each) do
-        @box ||=  OCRBox.new(1,2,20,8)
-    end
-    describe "#to_s" do
-        it "prints a human readable Box-Version with coordinates upper_left(x,y) bottom_right(x,y)" do
-            @box.to_s.should == "tl->(x:1 y:2)/br->:(x:20 y:8)"
-        end
-    end
-    describe '#encloses?(element)' do
-        it "tests wather given OCRBox is enclosed by the current OCRBox" do
-            @box.encloses?( OCRBox.new(0,3,19,7) ).should be_false
-            @box.encloses?( OCRBox.new(2,3,19,7) ).should be_true
-        end
-        it "encloses also itself" do
-            @box.encloses?( @box ).should be_true
-        end
-    end
-    describe '#to_css_style' do
-        it 'should create css-style attributes' do
-            @box.to_css_style.should == 'position:absolute; top:2px; left:1px; height:6px; width:19px;'
-        end
-    end
-    describe '#enclosed_by?(element)' do
-        it 'should be enclosed by Boxes bigger than itself' do
-            @box.enclosed_by?( OCRBox.new(0,1,21,9) ).should be_true
-        end
-        it 'should not be enclosed by Boxes smaller than itself' do
-            @box.enclosed_by?( OCRBox.new(2,3,19,7) ).should be_false
-        end
-        it 'should be enclosed by Boxes of the same size' do
-            @box.enclosed_by?( @box ).should be_true
-        end
-    end
-end

data/rspec/ocr_page_spec.rb DELETED Viewed

@@ -1,17 +0,0 @@
-#coding: utf-8
-require_relative '../lib/ocr_page'
-describe OCRPage do
-  before(:each) do
-      @ocr_page ||= OCRPage.new('../data/Seite_Tagebuch_H_C_Lang_08.html')
-  end
-  describe '' do
-      it '' do
-          p @ocr_page.enclosed_words( OCRBox.new(500,1703,1200,1800) )
-      end
-  end
-end

data/rspec/ocrx_word_spec.rb DELETED Viewed

@@ -1,32 +0,0 @@
-#coding: utf-8
-require_relative '../lib/ocrx_word'
-describe OCRXWord do
-  before(:each) do
-      @ocrx_word = OCRXWord.new(10,15,20,20,'WORT')
-  end
-  describe '#to_s' do
-      it 'should print the coordinates of the box and the textual information' do
-        p @ocrx_word
-        @ocrx_word.to_s.should == "WORT\ttl->(x:10 y:15)/br->:(x:20 y:20)"
-      end
-  end
-  describe '#to_html(css_class)' do
-      it 'should create an span elment to overlay an image on an html-page' do
-        @ocrx_word.to_html.should == "<span style='position:absolute; top:15px; left:10px; height:5px; width:10px;' class='ocrx_word'><span class='word'>WORT</span></span>"
-      end
-      it 'no css_class_class given should default to ocrx_word' do
-          @ocrx_word.to_html.should =~ /class='ocrx_word'/
-      end
-      it 'css_class given should be part of genearted html' do
-          @ocrx_word.to_html('rosebud').should =~ /class='rosebud'/
-      end
-  end
-end