rtesseract 3.0.2 → 3.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: aa205feaeb6a538fbe70f6482e2ac8cd99c709b40f977d69addb38689045d9a9
-  data.tar.gz: 9216bd8d9aae244e8e6dd527e050a0281f940a8aeebfcfa3f7d696c1c830a1b1
+  metadata.gz: 8eb694ea4b37475f756451795c145b8ba9618a0e5e94b0774a90301bb1aa97a2
+  data.tar.gz: fe725c774fc39720ff830e47e4580f7335def9ece76f67fad77fe9722f415d6c
 SHA512:
-  metadata.gz: 47df8a451610fbbae458851a626fb48a97ecb77a7eb32c24fcc29cb38465e4ac0d170f447cf557ade0ff8776bfee7fe5e102cb1bb32a2eacfbbc6eaf38a89a7d
-  data.tar.gz: 0540a33932743072a560a99ba5a0224ffd855df6dd8890fb2072582cc12af94f62c1aa6d2bf5b193e56bcf9e308f1daef85cd438da04aaffd9d083ba750d1c0a
+  metadata.gz: f40f8b53fc3c63e4968d9b1adab5153771730897fd681e354afea79f2007c28c4216dc61cad0d218dc7d76814360ae9169a0ffb8999ab6c8d15ef51ad712ec07
+  data.tar.gz: e2dfbf63b972c6e678d4bb79ec00064a958c9607f76cffe197bc26f555dff35bd7b0e1c263e376ede9598e2f429a344abb4b8d39b0e47ede6d1c09a32e6c44a4

data/.rubocop.yml

@@ -0,0 +1,8 @@
+Documentation:
+  Enabled: false
+
+Metrics/LineLength:
+  Max: 150
+
+Metrics/BlockLength:
+  Max: 50

data/CHANGELOG.md

@@ -1,3 +1,15 @@
+## v3.0.3
+
+#### Changed
+
+* Fix some problems with commanders gem
+
+## v3.0.0
+
+#### Changed
+
+* Refactoring all gem to working with tesseract version 4  or above
+
 ## v2.1.0
 
 #### Added

data/Gemfile

@@ -1,6 +1,6 @@
-source "https://rubygems.org"
+source 'https://rubygems.org'
 
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in rtesseract.gemspec
 gemspec

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    rtesseract (3.0.2)
+    rtesseract (3.0.3)
       nokogiri
 
 GEM
@@ -17,7 +17,7 @@ GEM
     docile (1.3.1)
     json (2.1.0)
     mini_portile2 (2.4.0)
-    nokogiri (1.9.1)
+    nokogiri (1.10.1)
       mini_portile2 (~> 2.4.0)
     rake (10.5.0)
     rspec (3.8.0)

data/Rakefile

@@ -1,6 +1,6 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 
-task :default => :spec
+task default: :spec

data/bin/console

@@ -1,7 +1,7 @@
 #!/usr/bin/env ruby
 
-require "bundler/setup"
-require "rtesseract"
+require 'bundler/setup'
+require 'rtesseract'
 
 # You can add fixtures and/or initialization code here to make experimenting
 # with your gem easier. You can also use a different console, if you like.
@@ -10,5 +10,5 @@ require "rtesseract"
 # require "pry"
 # Pry.start
 
-require "irb"
+require 'irb'
 IRB.start(__FILE__)

data/lib/rtesseract.rb

@@ -1,11 +1,11 @@
-require "rtesseract/check"
-require "rtesseract/configuration"
-require "rtesseract/command"
-require "rtesseract/base"
-require "rtesseract/text"
-require "rtesseract/pdf"
-require "rtesseract/box"
-require "rtesseract/tsv"
+require 'rtesseract/check'
+require 'rtesseract/configuration'
+require 'rtesseract/command'
+require 'rtesseract/base'
+require 'rtesseract/text'
+require 'rtesseract/pdf'
+require 'rtesseract/box'
+require 'rtesseract/tsv'
 
 class RTesseract
   class Error < StandardError; end
@@ -15,10 +15,11 @@ class RTesseract
   def initialize(src = '', options = {})
     @source = src
     @config = RTesseract.config.merge(options)
+    @errors = []
   end
 
   def to_box
-    Box.run(@source, config)
+    Box.run(@source, @errors, config)
   end
 
   def words
@@ -26,20 +27,22 @@ class RTesseract
   end
 
   def to_pdf
-    Pdf.run(@source, config)
+    Pdf.run(@source, @errors, config)
   end
 
   def to_tsv
-    Tsv.run(@source, config)
+    Tsv.run(@source, @errors, config)
   end
 
   # Output value
   def to_s
-    Text.run(@source, config)
+    Text.run(@source, @errors, config)
   end
 
   # Remove spaces and break-lines
   def to_s_without_spaces
     to_s.gsub(/\s/, '')
   end
+
+  attr_reader :errors
 end

data/lib/rtesseract/base.rb

@@ -1,5 +1,6 @@
 require 'tmpdir'
 require 'securerandom'
+require 'pathname'
 
 class RTesseract
   module Base
@@ -9,4 +10,4 @@ class RTesseract
       Pathname.new(Dir.tmpdir).join("#{@rand_file}#{ext}").to_s
     end
   end
-end
+end

data/lib/rtesseract/box.rb

@@ -4,10 +4,10 @@ class RTesseract
   module Box
     extend RTesseract::Base
 
-    def self.run(source, options)
+    def self.run(source, errors, options)
       options.tessedit_create_hocr = 1
 
-      RTesseract::Command.new(source, temp_file, options).run
+      RTesseract::Command.new(source, temp_file, errors, options).run
 
       parse(File.read(temp_file('.hocr')))
     end
@@ -15,16 +15,19 @@ class RTesseract
     def self.parse(content)
       html = Nokogiri::HTML(content)
       html.css('span.ocrx_word, span.ocr_word').map do |word|
-        @attributes = word.attributes['title'].value.to_s.gsub(';', '').split(' ')
-
-        {
-          word: word.text,
-          x_start: @attributes[1].to_i,
-          y_start: @attributes[2].to_i,
-          x_end: @attributes[3].to_i,
-          y_end: @attributes[4].to_i
-        }
+        attributes = word.attributes['title'].value.to_s.delete(';').split(' ')
+        word_info(word, attributes)
       end
     end
+
+    def self.word_info(word, data)
+      {
+        word: word.text,
+        x_start: data[1].to_i,
+        y_start: data[2].to_i,
+        x_end: data[3].to_i,
+        y_end: data[4].to_i
+      }
+    end
   end
-end
+end

data/lib/rtesseract/check.rb

@@ -1,14 +1,13 @@
-
 class RTesseract
   class << self
     def tesseract_version
-      Open3.capture2e(RTesseract.config.command, "--version").first.to_s.match(/\d+.\d+/)[0].to_f
+      Open3.capture2e(RTesseract.config.command, '--version').first.to_s.match(/\d+.\d+/)[0].to_f
     rescue Errno::ENOENT
       0
     end
 
     def check_version!
-      raise RTesseract::Error.new('Tesseract OCR 3.5 or later not installed') if RTesseract.tesseract_version < 3.05
+      raise RTesseract::Error, 'Tesseract OCR 3.5 or later not installed' if RTesseract.tesseract_version < 3.05
     end
   end
-end
+end

data/lib/rtesseract/command.rb

@@ -1,14 +1,15 @@
 class RTesseract
   class Command
-    FIXED = [:command, :psm, :oem, :lang, :tessdata_dir, :user_words, :user_patterns, :config_file]
+    FIXED = %i[command psm oem lang tessdata_dir user_words user_patterns config_file].freeze
 
     attr_reader :options
 
-    def initialize(source, output, options)
+    def initialize(source, output, errors, options)
       @source = source
       @output = output
       @options = options
-      @full_command = [ options.command, @source, @output]
+      @errors = errors
+      @full_command = [options.command, @source, @output]
     end
 
     def full_command
@@ -41,11 +42,13 @@ class RTesseract
     end
 
     def run
-      output, status = Open3.capture2e(*full_command.flatten)
+      output, error, status = Open3.capture3(*full_command.flatten)
+
+      @errors.push(error)
 
       return output if status.success?
 
-      raise RTesseract::Error.new(output)
+      raise RTesseract::Error, error
     end
   end
-end
+end

data/lib/rtesseract/configuration.rb

@@ -3,16 +3,20 @@ require 'ostruct'
 class RTesseract
   class Configuration < OpenStruct
     def merge(options)
-      RTesseract::Configuration.new(self.to_h.merge(options))
+      RTesseract::Configuration.new(to_h.merge(options))
+    end
+
+    def command
+      @table[:command]
     end
   end
 
   class << self
     def config
       @config ||= RTesseract::Configuration.new(
-                    command: 'tesseract',
-                    debug_file: '/dev/null'
-                  )
+        command: 'tesseract',
+        debug_file: '/dev/null'
+      )
     end
 
     def configure

data/lib/rtesseract/pdf.rb

@@ -2,12 +2,12 @@ class RTesseract
   module Pdf
     extend Base
 
-    def self.run(source, options)
+    def self.run(source, errors, options)
       options.tessedit_create_pdf = 1
 
-      RTesseract::Command.new(source, temp_file, options).run
+      RTesseract::Command.new(source, temp_file, errors, options).run
 
       File.open(temp_file('.pdf'), 'r')
     end
   end
-end
+end

data/lib/rtesseract/text.rb

@@ -2,8 +2,8 @@ require 'open3'
 
 class RTesseract
   module Text
-    def self.run(source, options)
-      RTesseract::Command.new(source, 'stdout', options).run
+    def self.run(source, errors, options)
+      RTesseract::Command.new(source, 'stdout', errors, options).run
     end
   end
-end
+end

data/lib/rtesseract/tsv.rb

@@ -2,12 +2,12 @@ class RTesseract
   module Tsv
     extend Base
 
-    def self.run(source, options)
+    def self.run(source, errors, options)
       options.tessedit_create_tsv = 1
 
-      RTesseract::Command.new(source, temp_file, options).run
+      RTesseract::Command.new(source, temp_file, errors, options).run
 
       File.open(temp_file('.tsv'), 'r')
     end
   end
-end
+end

data/lib/rtesseract/version.rb

@@ -1,3 +1,3 @@
 class RTesseract
-  VERSION = '3.0.2'.freeze
+  VERSION = '3.0.3'.freeze
 end

data/rtesseract.gemspec

@@ -1,33 +1,32 @@
-
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path('lib', __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require "rtesseract/version"
+require 'rtesseract/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "rtesseract"
+  spec.name          = 'rtesseract'
   spec.version       = RTesseract::VERSION
-  spec.authors       = ["Danilo Jeremias da Silva"]
-  spec.email         = ["dannnylo@gmail.com"]
+  spec.authors       = ['Danilo Jeremias da Silva']
+  spec.email         = ['dannnylo@gmail.com']
 
-  spec.summary       = "Ruby library for working with the Tesseract OCR.".freeze
-  spec.description   = "Ruby library for working with the Tesseract OCR.".freeze
-  spec.homepage      = "http://github.com/dannnylo/rtesseract".freeze
-  spec.license       = "MIT"
+  spec.summary       = 'Ruby library for working with the Tesseract OCR.'.freeze
+  spec.description   = 'Ruby library for working with the Tesseract OCR.'.freeze
+  spec.homepage      = 'http://github.com/dannnylo/rtesseract'.freeze
+  spec.license       = 'MIT'
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
-  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+  spec.files         = Dir.chdir(File.expand_path(__dir__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
-  spec.bindir        = "exe"
+  spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
-  spec.require_paths = ["lib"]
+  spec.require_paths = ['lib']
 
-  spec.add_development_dependency "bundler", "~> 1.17"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rspec", "~> 3.0"
-  spec.add_development_dependency "simplecov"
-  spec.add_development_dependency "coveralls"
+  spec.add_development_dependency 'bundler', '~> 1.17'
+  spec.add_development_dependency 'coveralls'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'simplecov'
 
-  spec.add_dependency "nokogiri"
+  spec.add_dependency 'nokogiri'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 3.0.2
+  version: 3.0.3
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-01-04 00:00:00.000000000 Z
+date: 2019-03-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -25,49 +25,49 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.17'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: coveralls
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '10.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '10.0'
 - !ruby/object:Gem::Dependency
-  name: simplecov
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: coveralls
+  name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -104,6 +104,7 @@ files:
 - ".document"
 - ".gitignore"
 - ".rspec"
+- ".rubocop.yml"
 - ".travis.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
@@ -145,7 +146,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 2.7.8
 signing_key: 
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.