Merge pull request #91 from dannnylo/release

New Release

.github/workflows/ci.yml

@@ -7,9 +7,9 @@ jobs:
       matrix:
         ruby:
           - '2.7.4'
-          - '3.0.0'
+          - '3.2.0'
         repository:
-          - 'ppa:alex-p/tesseract-ocr'
+          - 'ppa:alex-p/tesseract-ocr5'
           - 'ppa:alex-p/tesseract-ocr-devel'
     steps:
       - uses: actions/checkout@v2

.rubocop.yml

@@ -1,5 +1,6 @@
 AllCops:
   NewCops: enable
+  SuggestExtensions: false
 
 Layout/LineLength:
   Max: 150

CHANGELOG.md

@@ -1,4 +1,8 @@
 # Changes
+## v3.1.3
+
+* Fixed a configuration error that wouldn't allow you to do different kinds of calls on the same object, for example calling .to_box and then .to_s would result in unexpected behavior.
+
 ## v3.1.2
 
 #### Added

Gemfile

@@ -6,3 +6,13 @@ git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
 
 # Specify your gem's dependencies in rtesseract.gemspec
 gemspec
+
+group :development, :test do
+  gem 'bundler', '~> 2'
+  gem 'rake'
+  gem 'rspec'
+
+  gem 'simplecov'
+  gem 'simplecov-cobertura'
+  gem 'simplecov-lcov'
+end

Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    rtesseract (3.1.2)
+    rtesseract (3.1.3)
 
 GEM
   remote: https://rubygems.org/
@@ -45,4 +45,4 @@ DEPENDENCIES
   simplecov-lcov
 
 BUNDLED WITH
-   2.2.22
+   2.4.20

README.md

@@ -20,10 +20,18 @@ Ruby library for working with the Tesseract OCR.
 
 ## Installation
 
-Check if tesseract ocr programs is installed:
+Check if tesseract ocr programs are installed:
 
     $ tesseract --version
 
+If not, you can install them with a command like:
+
+    $ apt install tesseract-ocr
+
+or
+
+    $ brew install tesseract
+
 Add this line to your application's Gemfile:
 
 ```ruby

lib/rtesseract.rb

@@ -21,24 +21,24 @@ def initialize(src = '', options = {})
   end
 
   def to_box
-    Box.run(@source, @errors, config)
+    Box.run(@source, @errors, @config)
   end
 
   def words
     to_box.map { |word| word[:word] }
   end
 
   def to_pdf
-    Pdf.run(@source, @errors, config)
+    Pdf.run(@source, @errors, @config)
   end
 
   def to_tsv
-    Tsv.run(@source, @errors, config)
+    Tsv.run(@source, @errors, @config)
   end
 
   # Output value
   def to_s
-    Text.run(@source, @errors, config)
+    Text.run(@source, @errors, @config)
   end
 
   # Remove spaces and break-lines

lib/rtesseract/box.rb

@@ -6,7 +6,7 @@ module Box
 
     class << self
       def run(source, errors, options)
-        options.tessedit_create_hocr = 1
+        options = options.merge({ tessedit_create_hocr: 1 })
 
         RTesseract::Command.new(source, temp_file_path, errors, options).run do |output_path|
           parse(File.read("#{output_path}.hocr"))

lib/rtesseract/pdf.rb

@@ -5,7 +5,7 @@ module Pdf
     extend Base
 
     def self.run(source, errors, options)
-      options.tessedit_create_pdf = 1
+      options = options.merge({ tessedit_create_pdf: 1 })
 
       RTesseract::Command.new(source, temp_file_path, errors, options).run do |output_path|
         File.open("#{output_path}.pdf", 'r')

lib/rtesseract/text.rb

@@ -5,7 +5,9 @@
 class RTesseract
   module Text
     def self.run(source, errors, options)
-      RTesseract::Command.new(source, 'stdout', errors, options).run
+      text = RTesseract::Command.new(source, 'stdout', errors, options).run
+      text = text.gsub("\f", '') if text.is_a?(String)
+      text
     end
   end
 end

lib/rtesseract/tsv.rb

@@ -5,7 +5,7 @@ module Tsv
     extend Base
 
     def self.run(source, errors, options)
-      options.tessedit_create_tsv = 1
+      options = options.merge({ tessedit_create_tsv: 1 })
 
       RTesseract::Command.new(
         source,

lib/rtesseract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class RTesseract
-  VERSION = '3.1.2'
+  VERSION = '3.1.3'
 end

rtesseract.gemspec

@@ -20,16 +20,10 @@ Gem::Specification.new do |spec|
   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.required_ruby_version = '>= 2.5'
+  spec.required_ruby_version = '>= 2.7'
   spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
-  spec.add_development_dependency 'bundler', '~> 2'
-  spec.add_development_dependency 'rake'
-  spec.add_development_dependency 'rspec'
-
-  spec.add_development_dependency 'simplecov'
-  spec.add_development_dependency 'simplecov-cobertura'
-  spec.add_development_dependency 'simplecov-lcov'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 end

spec/rtesseract/text_spec.rb

@@ -32,6 +32,6 @@
   end
 
   it 'tests output text' do
-    expect(RTesseract.new(words_image).to_s).to eql("If you are a friend,\nyou speak the password,\nand the doors will open.\n\f")
+    expect(RTesseract.new(words_image).to_s).to eql("If you are a friend,\nyou speak the password,\nand the doors will open.\n")
   end
 end

spec/rtesseract_spec.rb

@@ -4,6 +4,7 @@
   let(:path) { Pathname.new(__dir__) }
   let(:image_path) { path.join('resources', 'test.tif').to_s }
   let(:pdf_path) { path.join('resources', 'test.tif').to_s }
+  let(:words_image) { path.join('resources', 'test_words.png').to_s }
 
   it 'returns the tesseract version' do
     expect(described_class.tesseract_version).to be > 3.05
@@ -78,4 +79,25 @@
       end
     end
   end
+
+  it 'runs multiple types' do
+    tesseract = RTesseract.new(words_image)
+    # Check that none of the other options affects the config, making text error out.
+    box = tesseract.to_box
+    pdf = tesseract.to_pdf
+    tsv = tesseract.to_tsv
+
+    result = tesseract.to_s
+    expect(result).to eql("If you are a friend,\nyou speak the password,\nand the doors will open.\n")
+    expect(box).to be_a(Array)
+
+    expect(pdf).to be_a(File)
+    expect(File.extname(pdf.path)).to eq('.pdf')
+
+    expect(tsv).to be_a(File)
+    expect(File.extname(tsv.path)).to eq('.tsv')
+
+    pdf.close
+    tsv.close
+  end
 end