rtesseract 3.1.1 → 3.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8e5a1940f2ac4c4429afaedc85c0d958159466285ebdd1fd25bd9942ef152a36
-  data.tar.gz: 3971293ecf3ff95addc2f67560c9214d82bdd42d53a836c05fb3e343f7110741
+  metadata.gz: 120e26c05e889a9bbfa935c3d43bfcbd9432b7296aa9b144fc55fd3c43f6a6af
+  data.tar.gz: 147e882d0648febff070e7f422c79852be258f594ded86cbcde8b5677c49b354
 SHA512:
-  metadata.gz: 810b41ddbd021094f5d41d5fde2a59aff0deb3c1d343e319f04e47a86f048e4030294af277017a0d694c89b5dd262431e78ed673228784a924602a1b00871f27
-  data.tar.gz: 5122bb30c21077fbf8d9dfee754cdce7a57d99572b391ade83d1f904661888a237cf097ec5fbaee81af58015e99c7b5e7ea20b2f30b235af5e679edea443685e
+  metadata.gz: 9fc275b3afb190d731e0d12356867ea3a359177141fabe876a12b2df7391b65964b3086af63156bce8cc79d5e2a8f8c6c901b9ffeeef514ad7eb5482039858dd
+  data.tar.gz: fd6ab267bb3edfbd52afa54615ffad0e624c611270691b9e0e48cdf4ddbdbccd1565d0d52386ac664cc978fe23abf8aeb134a275f5629b2005f3464249c6455e

data/.deepsource.toml

@@ -0,0 +1,9 @@
+version = 1
+
+[[analyzers]]
+name = "shell"
+enabled = true
+
+[[analyzers]]
+name = "ruby"
+enabled = true

data/.github/FUNDING.yml

@@ -0,0 +1 @@
+github: dannnylo

data/.github/workflows/ci.yml

@@ -6,26 +6,32 @@ jobs:
     strategy:
       matrix:
         ruby:
-          - '2.5.x'
-          - '2.6.x'
-          - '2.7.x'
+          - '2.7.4'
+          - '3.2.0'
+        repository:
+          - 'ppa:alex-p/tesseract-ocr5'
+          - 'ppa:alex-p/tesseract-ocr-devel'
     steps:
       - uses: actions/checkout@v2
       - name: Install tesseract-ocr
         run: |
-          sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
+          sudo add-apt-repository ${{ matrix.repository }} -y
           sudo apt-get update -q
           sudo apt-get install tesseract-ocr tesseract-ocr-eng ghostscript -y
+          tesseract --version
       - name: Setup Ruby
-        uses: actions/setup-ruby@v1
+        uses: ruby/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby }}
       - name: Bundle
-        env:
-          MTSR_RAILS_VERSION: ${{ matrix.rails }}
         run: |
           gem uninstall -aIx bundler
           gem install bundler
           bundle install --jobs 4 --retry 3
       - name: Test
         run: bundle exec rake
+      - name: Coverage
+        env:
+          CODACY_PROJECT_TOKEN: ${{ secrets.CODACY_PROJECT_TOKEN }}
+        run: bash <(curl -Ls https://coverage.codacy.com/get.sh) report -l Ruby -r coverage/lcov/*
+

data/.rubocop.yml

@@ -1,3 +1,6 @@
+AllCops:
+  NewCops: enable
+  SuggestExtensions: false
 
 Layout/LineLength:
   Max: 150

data/CHANGELOG.md

@@ -1,3 +1,44 @@
+# 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
+
+* Added confidence for each word in box mode
+
+## v3.1.1
+
+#### Changed
+
+* Changed RTesseract::Command to receive a block when success run
+
+## v3.1.0
+
+#### Changed
+
+* Removed nokogi dependency.
+
+## v3.0.4
+
+#### Changed
+
+* Updated dependencies by security alerts.
+
+## v3.0.5
+
+#### Changed
+
+* Updated dependencies by security alerts.
+
+## v3.0.4
+
+#### Changed
+
+* Updated dependencies by security alerts.
+
 ## v3.0.3
 
 #### Changed

data/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

data/Gemfile.lock

@@ -1,55 +1,48 @@
 PATH
   remote: .
   specs:
-    rtesseract (3.1.1)
+    rtesseract (3.1.3)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    coveralls (0.8.23)
-      json (>= 1.8, < 3)
-      simplecov (~> 0.16.1)
-      term-ansicolor (~> 1.3)
-      thor (>= 0.19.4, < 2.0)
-      tins (~> 1.6)
-    diff-lcs (1.3)
-    docile (1.3.2)
-    json (2.3.0)
-    rake (13.0.1)
-    rspec (3.9.0)
-      rspec-core (~> 3.9.0)
-      rspec-expectations (~> 3.9.0)
-      rspec-mocks (~> 3.9.0)
-    rspec-core (3.9.1)
-      rspec-support (~> 3.9.1)
-    rspec-expectations (3.9.1)
+    diff-lcs (1.4.4)
+    docile (1.4.0)
+    rake (13.0.6)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-mocks (3.9.1)
+      rspec-support (~> 3.10.0)
+    rspec-mocks (3.10.2)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-support (3.9.2)
-    simplecov (0.16.1)
+      rspec-support (~> 3.10.0)
+    rspec-support (3.10.2)
+    simplecov (0.21.2)
       docile (~> 1.1)
-      json (>= 1.8, < 3)
-      simplecov-html (~> 0.10.0)
-    simplecov-html (0.10.2)
-    sync (0.5.0)
-    term-ansicolor (1.7.1)
-      tins (~> 1.0)
-    thor (1.0.1)
-    tins (1.24.1)
-      sync
+      simplecov-html (~> 0.11)
+      simplecov_json_formatter (~> 0.1)
+    simplecov-cobertura (1.4.2)
+      simplecov (~> 0.8)
+    simplecov-html (0.12.3)
+    simplecov-lcov (0.8.0)
+    simplecov_json_formatter (0.1.3)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
   bundler (~> 2)
-  coveralls
   rake
   rspec
   rtesseract!
+  simplecov
+  simplecov-cobertura
+  simplecov-lcov
 
 BUNDLED WITH
-   2.1.4
+   2.4.20

data/README.md

@@ -6,8 +6,11 @@
 <a href='https://github.com/dannnylo/rtesseract/workflows/CI/badge.svg'>
   <img src="https://github.com/dannnylo/rtesseract/workflows/CI/badge.svg" alt="Build Status" />
 </a>
-<a href='https://coveralls.io/r/dannnylo/rtesseract?branch=master'>
-    <img src="https://coveralls.io/repos/dannnylo/rtesseract/badge.png?branch=master" alt="Coverage Status" />
+<a href='https://app.codacy.com/project/badge/Grade/316a48934db8415d84d2f9a318b0f837'>
+  <img src="https://app.codacy.com/project/badge/Grade/316a48934db8415d84d2f9a318b0f837" alt="Coverage Status" />
+</a>
+<a href='https://app.codacy.com/project/badge/Coverage/316a48934db8415d84d2f9a318b0f837'>
+  <img src="https://app.codacy.com/project/badge/Coverage/316a48934db8415d84d2f9a318b0f837" alt="Coverage" />
 </a>
 <a href='https://codeclimate.com/github/dannnylo/rtesseract'>
     <img src="https://codeclimate.com/github/dannnylo/rtesseract.png" />
@@ -17,10 +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
@@ -100,20 +111,20 @@ This will preserve the image colors, pictures and structure in the generated pdf
   ```ruby
     RTesseract.new('test_words.png').to_box
     => [
-      {:word => 'If',  :x_start=>52, :y_start=>13, :x_end=>63, :y_end=>27},
-      {:word => 'you', :x_start=>69, :y_start=>17, :x_end=>100, :y_end=>31},
-      {:word => 'are', :x_start=>108, :y_start=>17, :x_end=>136, :y_end=>27},
-      {:word => 'a', :x_start=>143, :y_start=>17, :x_end=>151, :y_end=>27},
-      {:word => 'friend,', :x_start=>158, :y_start=>13, :x_end=>214, :y_end=>29},
-      {:word => 'you', :x_start=>51, :y_start=>39, :x_end=>82, :y_end=>53},
-      {:word => 'speak', :x_start=>90, :y_start=>35, :x_end=>140, :y_end=>53},
-      {:word => 'the', :x_start=>146, :y_start=>35, :x_end=>174, :y_end=>49},
-      {:word => 'password,', :x_start=>182, :y_start=>35, :x_end=>267, :y_end=>53},
-      {:word => 'and', :x_start=>51, :y_start=>57, :x_end=>81, :y_end=>71},
-      {:word => 'the', :x_start=>89, :y_start=>57, :x_end=>117, :y_end=>71},
-      {:word => 'doors', :x_start=>124, :y_start=>57, :x_end=>172, :y_end=>71},
-      {:word => 'will', :x_start=>180, :y_start=>57, :x_end=>208, :y_end=>71},
-      {:word => 'open.', :x_start=>216, :y_start=>61, :x_end=>263, :y_end=>75}
+      { :word => 'If', :confidence=>89, :x_start=>52, :y_start=>13, :x_end=>63, :y_end=>27},
+      { :word => 'you', :confidence=>96, :x_start=>69, :y_start=>17, :x_end=>100, :y_end=>31},
+      { :word => 'are', :confidence=>92, :x_start=>108, :y_start=>17, :x_end=>136, :y_end=>27},
+      { :word => 'a', :confidence=>92, :x_start=>133, :y_start=>8, :x_end=>147, :y_end=>35},
+      { :word => 'friend,', :confidence=>95, :x_start=>158, :y_start=>13, :x_end=>214, :y_end=>29},
+      { :word => 'you', :confidence=>96, :x_start=>51, :y_start=>39, :x_end=>82, :y_end=>53},
+      { :word => 'speak', :confidence=>96, :x_start=>90, :y_start=>35, :x_end=>140, :y_end=>53},
+      { :word => 'the', :confidence=>96, :x_start=>146, :y_start=>35, :x_end=>174, :y_end=>49},
+      { :word => 'password,', :confidence=>96, :x_start=>182, :y_start=>35, :x_end=>267, :y_end=>53},
+      { :word => 'and', :confidence=>96, :x_start=>51, :y_start=>57, :x_end=>81, :y_end=>71},
+      { :word => 'the', :confidence=>96, :x_start=>89, :y_start=>57, :x_end=>117, :y_end=>71},
+      { :word => 'doors', :confidence=>96, :x_start=>124, :y_start=>57, :x_end=>172, :y_end=>71},
+      { :word => 'will', :confidence=>96, :x_start=>180, :y_start=>57, :x_end=>208, :y_end=>71},
+      { :word => 'open.', :confidence=>96, :x_start=>216, :y_start=>61, :x_end=>263, :y_end=>75}
     ]
   ```
 

data/lib/rtesseract/box.rb

@@ -6,7 +6,7 @@ class RTesseract
 
     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"))
@@ -20,16 +20,17 @@ class RTesseract
       def parse_line(line)
         return unless line.match?(/oc(rx|r)_word/)
 
-        word = line.match(/(?<=>)(.*?)(?=<)/).to_s
+        word = line.to_s.scan(/>(.*)</).flatten.first.to_s
 
         return if word.strip == ''
 
-        word_info(word, parse_position(line))
+        word_info(word, parse_position(line), parse_confidence(line))
       end
 
-      def word_info(word, positions)
+      def word_info(word, positions, confidence)
         {
           word: word,
+          confidence: confidence[-1].to_i,
           x_start: positions[1].to_i,
           y_start: positions[2].to_i,
           x_end: positions[3].to_i,
@@ -38,7 +39,11 @@ class RTesseract
       end
 
       def parse_position(line)
-        line.match(/(?<=title)(.*?)(?=;)/).to_s.split(' ')
+        line.match(/(?<=title)(.*?)(?=;)/).to_s.split
+      end
+
+      def parse_confidence(line)
+        line.match(/(?<=;)(.*?)(?=')/).to_s.split
       end
     end
   end

data/lib/rtesseract/pdf.rb

@@ -5,7 +5,7 @@ class RTesseract
     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')

data/lib/rtesseract/text.rb

@@ -5,7 +5,9 @@ require 'open3'
 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

data/lib/rtesseract/tsv.rb

@@ -5,9 +5,14 @@ class RTesseract
     extend Base
 
     def self.run(source, errors, options)
-      options.tessedit_create_tsv = 1
+      options = options.merge({ tessedit_create_tsv: 1 })
 
-      RTesseract::Command.new(source, temp_file_path, errors, options).run do |output_path|
+      RTesseract::Command.new(
+        source,
+        temp_file_path,
+        errors,
+        options
+      ).run do |output_path|
         File.open("#{output_path}.tsv", 'r')
       end
     end

data/lib/rtesseract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class RTesseract
-  VERSION = '3.1.1'
+  VERSION = '3.1.3'
 end

data/lib/rtesseract.rb

@@ -12,7 +12,7 @@ require 'rtesseract/tsv'
 class RTesseract
   class Error < StandardError; end
 
-  attr_reader :config, :source
+  attr_reader :config, :source, :errors
 
   def initialize(src = '', options = {})
     @source = src
@@ -21,7 +21,7 @@ class RTesseract
   end
 
   def to_box
-    Box.run(@source, @errors, config)
+    Box.run(@source, @errors, @config)
   end
 
   def words
@@ -29,22 +29,20 @@ class RTesseract
   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
   def to_s_without_spaces
     to_s.gsub(/\s/, '')
   end
-
-  attr_reader :errors
 end

data/rtesseract.gemspec

@@ -20,12 +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 = '>= 2.7'
   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 'coveralls'
-  spec.add_development_dependency 'rake'
-  spec.add_development_dependency 'rspec'
+  spec.metadata['rubygems_mfa_required'] = 'true'
 end

metadata

@@ -1,71 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 3.1.1
+  version: 3.1.3
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-04-24 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2'
-- !ruby/object:Gem::Dependency
-  name: coveralls
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+date: 2023-10-04 00:00:00.000000000 Z
+dependencies: []
 description: Ruby library for working with the Tesseract OCR.
 email:
 - dannnylo@gmail.com
@@ -73,7 +17,9 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".deepsource.toml"
 - ".document"
+- ".github/FUNDING.yml"
 - ".github/workflows/ci.yml"
 - ".gitignore"
 - ".hound.yml"
@@ -102,7 +48,8 @@ files:
 homepage: http://github.com/dannnylo/rtesseract
 licenses:
 - MIT
-metadata: {}
+metadata:
+  rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
 require_paths:
@@ -111,14 +58,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: '2.7'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.8
+rubygems_version: 3.4.10
 signing_key: 
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.