rtesseract 3.1.2 → 3.1.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 87f85a70ab24a03a719e7726d95debeb469d822c447acc39a8adc1579c43e6d1
-  data.tar.gz: a18cd83cd4632ed5adc096f9384659f0e47a4ba33e2f8a76e804cf8140e8798b
+  metadata.gz: 0a6663ca2e040b7f9ea75dba9efd078c4d4e8e9ddd51f5e6891049328fc39492
+  data.tar.gz: 0f0cb1ccfbaf0fde1a04da091f55ee536992504f2fcf698ab56fbd354292b2a3
 SHA512:
-  metadata.gz: 4f6b37e1645d5f82c759e5feea081cfcf5384e2ad91423d2d04030a89ef007eb9469ecf398ba4cd2364bf2baeea4bad885866c4c41b19fa4da2c078b79cef4a6
-  data.tar.gz: bea642e1d7d2576dbdaeeb68ff730627104894d914a405a4ec2a37b8c65755f2f9c33a5091e16eaced51162725b6ea62f647b764ec838eefe3bfe4f58f461986
+  metadata.gz: e5a661e73977518acc17627a850d1cdc22df44af6ed4118b974af8b9a487cab1bf487583cf3a196c4b23b3a708d1fed9521ecbd5aa1e0d5d0284bdc671739fe3
+  data.tar.gz: b575ccd5b3fe076d0565857a558ca454b0e919e1b421ca071b6eaa8636b20ffed8f899280d666ba2735f0cf73e72552535944aa55f72a8c985116008f7059457

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 +6,31 @@ jobs:
     strategy:
       matrix:
         ruby:
-          - '2.5.x'
-          - '2.6.x'
-          - '2.7.x'
+          - '3.2.0'
+          - '3.4.2'
+        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 +1,12 @@
+# Changes
+
+## v3.1.4
+# Changed
+* Temporary hocr file is deleted after the file is processed.
+
+## 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

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 (3.1.2)
+    rtesseract (3.1.4)
 
 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 +20,21 @@ 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
+
+or for Heroku 22 to add the buildpack https://github.com/pathwaysmedical/heroku-buildpack-tesseract
+
+
 Add this line to your application's Gemfile:
 
 ```ruby

data/lib/rtesseract/base.rb

@@ -9,5 +9,9 @@ class RTesseract
     def temp_file_path
       Pathname.new(Dir.tmpdir).join("rtesseract_#{SecureRandom.uuid}").to_s
     end
+
+    def remove_tmp_file(absolute_file_path)
+      File.delete(absolute_file_path) if File.file?(absolute_file_path)
+    end
   end
 end

data/lib/rtesseract/box.rb

@@ -6,10 +6,13 @@ 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"))
+          filename = "#{output_path}.hocr"
+          content = File.read(filename)
+          remove_tmp_file(filename)
+          parse(content)
         end
       end
 
@@ -20,7 +23,7 @@ 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 == ''
 
@@ -39,11 +42,11 @@ 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(' ')
+        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 = '3.1.2'
+  VERSION = '3.1.4'
 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 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rtesseract
 version: !ruby/object:Gem::Version
-  version: 3.1.2
+  version: 3.1.4
 platform: ruby
 authors:
 - Danilo Jeremias da Silva
-autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-08-23 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: 2025-04-30 00:00:00.000000000 Z
+dependencies: []
 description: Ruby library for working with the Tesseract OCR.
 email:
 - dannnylo@gmail.com
@@ -73,7 +16,9 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".deepsource.toml"
 - ".document"
+- ".github/FUNDING.yml"
 - ".github/workflows/ci.yml"
 - ".gitignore"
 - ".hound.yml"
@@ -102,8 +47,8 @@ files:
 homepage: http://github.com/dannnylo/rtesseract
 licenses:
 - MIT
-metadata: {}
-post_install_message: 
+metadata:
+  rubygems_mfa_required: 'true'
 rdoc_options: []
 require_paths:
 - lib
@@ -111,15 +56,14 @@ 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: 3.1.2
-signing_key: 
+rubygems_version: 3.6.3
 specification_version: 4
 summary: Ruby library for working with the Tesseract OCR.
 test_files: []