tesseract-ocr 0.1.5 → 0.1.6

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1cb827519f64b7aba71ee22666e49e952a92ec41
+  data.tar.gz: 2687f882e6e704ebd53026b522e471d7aa57c914
+SHA512:
+  metadata.gz: 356b6ed6de748cfaf3dbb017346400a802e4a0c060759f29cc2ddb254448ab4584d655f4bc794ba198cbd43bda35d8cb802665ff2f74ae60ca1f305c89d59f88
+  data.tar.gz: 2340f05a490d53fb809a5bdcefed75a547674bbcc02b3200cf505335547e073f9fd2a2a04409e31de55865ae3afdc08d5121480246d06bce0432e4e4b17d794f

data/README.md

@@ -1,17 +1,25 @@
 ruby-tesseract - Ruby bindings and wrapper
 ==========================================
-This wrapper binds the TessBaseAPI object through ffi-inline (which means it will work on JRuby too)
-and then proceeds to wrap said API in a more ruby-esque Engine class.
+This wrapper binds the TessBaseAPI object through ffi-inline (which means it
+will work on JRuby too) and then proceeds to wrap said API in a more ruby-esque
+Engine class.
 
 Making it work
 --------------
-To make this library work you need tesseract-ocr and leptonica libraries and headers and a C++ compiler.
+To make this library work you need tesseract-ocr and leptonica libraries and
+headers and a C++ compiler.
 
 The gem is called `tesseract-ocr`.
 
+If you're on a distribution that separates the libraries from headers, remember
+to install the *-dev* package.
+
+On Debian you will need to `libleptonica-dev` and `libtesseract-dev`.
+
 Examples
 --------
-Following are some examples that show the functionalities provided by tesseract-ocr.
+Following are some examples that show the functionalities provided by
+tesseract-ocr.
 
 ### Basic functionality of tesseract
 
@@ -26,21 +34,21 @@ e = Tesseract::Engine.new {|e|
 e.text_for('test/first.png').strip # => 'ABC'
 ```
 
-You can pass to `#text_for` either a path, an IO object, a string containing the image or
-an object that responds to `#to_blob` (for example  Magick::Image), keep in mind that
-the format has to be supported by leptonica.
+You can pass to `#text_for` either a path, an IO object, a string containing
+the image or an object that responds to `#to_blob` (for example
+Magick::Image), keep in mind that the format has to be supported by leptonica.
 
 ### Accessing advanced features
 
-With advanced features you get access to blocks, paragraphs, lines, words and symbols.
+With advanced features you get access to blocks, paragraphs, lines, words and
+symbols.
 
-There are lot of way to access those levels, the methods are the following (replace level
-with one of the accessible features, so `each_level` can be `each_block` or `each_paragraph`
-etc.)
+Replace **level** in method names with either `block`, `paragraph`, `line`,
+`word` or `symbol`.
 
-The following kind of accessors need a block to be passed and they pass to the block each
-`Element` object. The Element object has various getters to access certain features, I'll
-talk about them later.
+The following kind of accessors need a block to be passed and they pass to the
+block each `Element` object. The Element object has various getters to access
+certain features, I'll talk about them later.
 
 The methods are:
 
@@ -48,9 +56,10 @@ The methods are:
 * `each_level_for`
 * `each_level_at`
 
-The following accessors instead return an `Array` of `Element`s with cached getters, the getters
-are cached beacause the values accessible in the `Element` are linked to the state of the internal
-API, and that state changes if you access something else.
+The following accessors instead return an `Array` of `Element`s with cached
+getters, the getters are cached beacause the values accessible in the `Element`
+are linked to the state of the internal API, and that state changes if you
+access something else.
 
 The methods are:
 
@@ -65,16 +74,19 @@ Each `Element` object has the following getters:
 * `bounding_box`, this will return the box where the element is confined into
 * `binary_image`, this will return the bichromatic image of the element
 * `image`, this will return the image of the element
-* `baseline`, this will return the line where the text is with a pair of coordinates
+* `baseline`, this will return the line where the text is with a pair of
+  coordinates
 * `orientation`, this will return the orientation of the element
 * `text`, this will return the text of the element
 * `confidence`, this will return the confidence of correctness for the element
 
 `Block` elements also have `type` accessors that specify the type of the block.
 
-`Word` elements also have `font_attributes`, `from_dictionary?` and `numeric?` getters.
+`Word` elements also have `font_attributes`, `from_dictionary?` and `numeric?`
+getters.
 
-`Symbol` elements also have `superscript?`, `subscript?` and `dropcap?` getters.
+`Symbol` elements also have `superscript?`, `subscript?` and `dropcap?`
+getters.
 
 Using the binary
 ----------------
@@ -97,3 +109,7 @@ ABC
 > tesseract.rb -c test/first.png 
 86
 ```
+
+License
+-------
+The license is BSD one clause.

data/bin/tesseract.rb

@@ -22,7 +22,7 @@ OptionParser.new do |o|
 	end
 
 	o.on '-p', '--psm MODE', 'page segmentation mode to use' do |value|
-		options[:psm] = value
+		options[:psm] = value.to_i
 	end
 
 	o.on '-u', '--unlv', 'output in UNLV format' do

data/lib/tesseract-ocr.rb

@@ -23,11 +23,11 @@
 #++
 
 module Tesseract
-	def prefix
+	def self.prefix
 		ENV['TESSDATA_PREFIX']
 	end
 
-	def prefix= (path)
+	def self.prefix=(path)
 		ENV['TESSDATA_PREFIX'] = path
 	end
 end

data/lib/tesseract/api.rb

@@ -155,12 +155,15 @@ class API
 
 	def get_text
 		pointer = C::BaseAPI.get_utf8_text(to_ffi)
-		result  = pointer.read_string
+
+		return if pointer.null?
+
+		result = pointer.read_string
 		result.force_encoding 'UTF-8'
 
 		result
 	ensure
-		C.free_array_of_char(pointer)
+		C.free_array_of_char(pointer) unless pointer.null?
 	end
 
 	def get_box (page = 0)

data/lib/tesseract/api/image.rb

@@ -25,7 +25,7 @@
 module Tesseract; class API
 
 class Image
-	def self.new (image)
+	def self.new (image, x = 0, y = 0)
 		image = if image.is_a?(String) && (File.exists?(File.expand_path(image)) rescue nil)
 			C::Leptonica.pix_read(File.expand_path(image))
 		elsif image.is_a?(String)
@@ -36,11 +36,13 @@ class Image
 			image = image.to_blob
 
 			C::Leptonica.pix_read_mem(image, image.bytesize)
+		else
+			image
 		end
 
 		raise ArgumentError, 'invalid image' if image.nil? || image.null?
 
-		super(image)
+		super(image, x, y)
 	end
 
 	attr_accessor :x, :y
@@ -68,10 +70,8 @@ class Image
 		size = FFI::MemoryPointer.new(:size_t)
 
 		C::Leptonica.pix_write_mem(to_ffi, data, size, C.for_enum(format))
-
 		result = data.typecast(:pointer).read_string(size.typecast(:size_t))
-
-		data.typecast(:pointer).free
+		C.free(data.typecast(:pointer))
 
 		result
 	end

data/lib/tesseract/api/iterator.rb

@@ -62,7 +62,7 @@ class Iterator
 	def get_image (level = :word, padding = 0)
 		image = C::Iterator.get_image(to_ffi, C.for_enum(level), padding)
 
-		Image.new(image.pix, image.x, image.y)
+		Image.new(image[:pix], image[:x], image[:y])
 	end
 
 	def baseline (level = :word)
@@ -75,12 +75,15 @@ class Iterator
 
 	def get_text (level = :word)
 		pointer = C::Iterator.get_utf8_text(to_ffi, C.for_enum(level))
-		result  = pointer.read_string
+		
+		return if pointer.null?
+
+		result = pointer.read_string
 		result.force_encoding 'UTF-8'
 
 		result
 	ensure
-		C.free_array_of_char(pointer)
+		C.free_array_of_char(pointer) unless pointer.null?
 	end
 
 	def confidence (level = :word)

data/lib/tesseract/c.rb

@@ -35,6 +35,12 @@ module C
 		cpp.include   'tesseract/strngs.h'
 		cpp.libraries 'tesseract'
 
+		cpp.function %{
+			void free (void* pointer) {
+				free(pointer);
+			}
+		}
+
 		cpp.function %{
 			void free_array_of_char (char* pointer) {
 				delete [] pointer;

data/lib/tesseract/c/leptonica.rb

@@ -48,7 +48,7 @@ module Leptonica
 		}, blocking: true
 
 		cpp.function %{
-			Pix* pix_read_fd (int fd) {
+			Pix* pix_read_stream (int fd) {
 				return pixReadStream(fdopen(fd, "rb"), 0);
 			}
 		}, blocking: true

data/lib/tesseract/version.rb

@@ -24,6 +24,6 @@
 
 module Tesseract
 	def self.version
-		'0.1.5'
+		'0.1.6'
 	end
 end

data/tesseract-ocr.gemspec

@@ -1,13 +1,14 @@
 Kernel.load 'lib/tesseract/version.rb'
 
 Gem::Specification.new {|s|
-	s.name         = 'tesseract-ocr'
-	s.version      = Tesseract.version
-	s.author       = 'meh.'
-	s.email        = 'meh@paranoici.org'
-	s.homepage     = 'http://github.com/meh/ruby-tesseract-ocr'
-	s.platform     = Gem::Platform::RUBY
-	s.summary      = 'A wrapper library to the tesseract-ocr API.'
+	s.name     = 'tesseract-ocr'
+	s.version  = Tesseract.version
+	s.author   = 'meh.'
+	s.email    = 'meh@schizofreni.co'
+	s.homepage = 'http://github.com/meh/ruby-tesseract-ocr'
+	s.platform = Gem::Platform::RUBY
+	s.summary  = 'A wrapper library to the tesseract-ocr API.'
+	s.license  = 'BSD'
 
 	s.files         = `git ls-files`.split("\n")
 	s.executables   = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }

metadata

@@ -1,82 +1,73 @@
 --- !ruby/object:Gem::Specification
 name: tesseract-ocr
 version: !ruby/object:Gem::Version
-  version: 0.1.5
-  prerelease: 
+  version: 0.1.6
 platform: ruby
 authors:
 - meh.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-29 00:00:00.000000000 Z
+date: 2014-02-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: call-me
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: iso-639
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: ffi-extra
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: ffi-inline
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 description: 
-email: meh@paranoici.org
+email: meh@schizofreni.co
 executables:
 - tesseract-train.rb
 - tesseract.rb
@@ -221,28 +212,28 @@ files:
 - test/test-european.jpg
 - test/test.png
 homepage: http://github.com/meh/ruby-tesseract-ocr
-licenses: []
+licenses:
+- BSD
+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: 1.8.23
+rubygems_version: 2.2.0
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A wrapper library to the tesseract-ocr API.
 test_files:
 - test/first.png
@@ -252,3 +243,4 @@ test_files:
 - test/tesseract_spec.rb
 - test/test-european.jpg
 - test/test.png
+has_rdoc: