tesseract-ocr 0.1.1 → 0.1.2

data/bin/tesseract-train.rb

@@ -7,12 +7,8 @@ require 'shellwords'
 options = {}
 
 OptionParser.new do |o|
-	o.on '-b', '--box FILE...', Array, 'the box files to use' do |value|
-		options[:box] = value.map { |path| File.realpath(path) }
-	end
-
-	o.on '-i', '--image FILE...', Array, 'the image files to use' do |value|
-		options[:image] = value.map { |path| File.realpath(path) }
+	o.on '-d', '--data DATA...', Array, 'the data to use' do |value|
+		options[:data] = Hash[value.map { |e| e.split(?:).map { |p| File.realpath(p) } }]
 	end
 
 	o.on '-o', '--output FILE', 'the path where to output the traineddata' do |value|
@@ -32,12 +28,12 @@ Dir.chdir FileUtils.mkpath(File.join(Dir.tmpdir, rand.to_s)).first
 
 language = language.shellescape
 
-options[:box].each_with_index {|box, index|
+options[:data].each_with_index {|(box, image), index|
 	%x{
 		cp #{box.shellescape} #{language}.#{index}.box
-		cp #{options[:image][index].shellescape} #{language}.#{index}#{File.extname(options[:image][index]}
+		cp #{image.shellescape} #{language}.#{index}#{File.extname(image)}
 
-		tesseract #{language}#{File.extname(options[:image])} #{language} nobatch box.train.stderr
+		tesseract #{language}.#{index}#{File.extname(image)} #{language} nobatch box.train.stderr
 
 		unicharset_extractor #{language}.box
 
@@ -60,8 +56,10 @@ options[:box].each_with_index {|box, index|
 	mv #{language}.traineddata #{options[:output].shellescape}
 }
 
+=begin
 path = File.realpath(Dir.pwd)
 
 Dir.chdir '/'
 
 FileUtils.rm_rf path
+=end

data/bin/tesseract.rb

@@ -44,6 +44,14 @@ OptionParser.new do |o|
 	o.on '-w', '--whitelist LIST', 'whitelist the following chars' do |value|
 		options[:whitelist] = value
 	end
+
+	o.on '-s', '--scale VALUE', Float, 'scale the image before analyzing it' do |value|
+		options[:scale] = value
+	end
+
+	o.on '-r', '--resize VALUE', Float, 'resize the image before analyzing it' do |value|
+		options[:resize] = value
+	end
 end.parse!
 
 Tesseract::Engine.new(options[:path], options[:language], options[:mode]) {|engine|
@@ -53,11 +61,19 @@ Tesseract::Engine.new(options[:path], options[:language], options[:mode]) {|engi
 	engine.page_segmentation_mode = options[:psm] if options[:psm]
 	engine.load_config options[:config]           if options[:config]
 }.tap {|engine|
+	image = if options[:scale]
+		require 'RMagick'; Magick::Image.read(ARGV.first).first.scale(options[:scale])
+	elsif options[:resize]
+		require 'RMagick'; Magick::Image.read(ARGV.first).first.resize(options[:resize])
+	else
+		ARGV.first
+	end
+
 	if options[:unlv]
-		puts engine.text_for(ARGV.first).unlv.strip
+		puts engine.text_for(image).unlv.strip
 	elsif options[:confidence]
-		puts engine.text_for(ARGV.first).confidence
+		puts engine.text_for(image).confidence
 	else
-		puts engine.text_for(ARGV.first).strip
+		puts engine.text_for(image).strip
 	end
 }

data/examples/nerdz-captcha-breaker/break.rb

@@ -26,7 +26,7 @@ class Magick::Pixel
 	end
 end
 
-ENV['TESSDATA_PREFIX'] = './'
+Tesseract.prefix = './'
 
 Tesseract::Engine.new {|engine|
 	engine.language               = :lol

data/lib/tesseract-ocr.rb

@@ -22,5 +22,15 @@
 # or implied, of meh.
 #++
 
+module Tesseract
+	def prefix
+		ENV['TESSDATA_PREFIX']
+	end
+
+	def prefix= (path)
+		ENV['TESSDATA_PREFIX'] = path
+	end
+end
+
 require 'tesseract/api'
 require 'tesseract/engine'

data/lib/tesseract/version.rb

@@ -24,6 +24,6 @@
 
 module Tesseract
 	def self.version
-		'0.1.1'
+		'0.1.2'
 	end
 end

data/tesseract-ocr.gemspec

@@ -18,5 +18,5 @@ Gem::Specification.new {|s|
 	s.add_dependency 'iso-639'
 
 	s.add_dependency 'ffi-extra'
-	s.add_dependency 'ffi-inliner'
+	s.add_dependency 'ffi-inline'
 }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tesseract-ocr
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2011-12-07 00:00:00.000000000 Z
+date: 2012-02-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: call-me
-  requirement: &15076460 !ruby/object:Gem::Requirement
+  requirement: &19410320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *15076460
+  version_requirements: *19410320
 - !ruby/object:Gem::Dependency
   name: iso-639
-  requirement: &15075360 !ruby/object:Gem::Requirement
+  requirement: &19408960 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,10 +32,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *15075360
+  version_requirements: *19408960
 - !ruby/object:Gem::Dependency
   name: ffi-extra
-  requirement: &15074140 !ruby/object:Gem::Requirement
+  requirement: &19407840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -43,10 +43,10 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *15074140
+  version_requirements: *19407840
 - !ruby/object:Gem::Dependency
-  name: ffi-inliner
-  requirement: &15072700 !ruby/object:Gem::Requirement
+  name: ffi-inline
+  requirement: &19407000 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -54,7 +54,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *15072700
+  version_requirements: *19407000
 description: 
 email: meh@paranoici.org
 executables:
@@ -220,7 +220,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.10
+rubygems_version: 1.8.15
 signing_key: 
 specification_version: 3
 summary: A wrapper library to the tesseract-ocr API.