ocr-file 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 6b558ce36c35e74b410f42928eae1a987485d1bbd64da77750574062bc05b91e
+  data.tar.gz: d906c620a02c5a2d139b3d89d05e9b3872ee6c929b4aa661b20f9033d8f3605f
+SHA512:
+  metadata.gz: 81049908609ba3d622be2b6f99dabeca2960a455fa3d56ee1fca4c177c2ee4365281421c1128ec3fa5476d068daa53b3d7f7600c5fd1c31fcb5834ca688f9747
+  data.tar.gz: 1a7dcd56a7196694371abf70633635545138bdc7bc0af2873fc5e7c22bdbfc97e9986ba1a18afc288b24e488caf999b644ec1f9d8889ce6e5efa6fcfe776c204

data/.gitignore

@@ -0,0 +1,56 @@
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+# Used by dotenv library to load environment variables.
+# .env
+
+# Ignore Byebug command history file.
+.byebug_history
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+#
+# vendor/Pods/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+# Used by RuboCop. Remote config files pulled in from inherit_from directive.
+# .rubocop-https?--*

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behaviour that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behaviour by participants include:
+
+* The use of sexualised language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behaviour and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behaviour.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviours that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behaviour may be
+reported by contacting the project team at contact@jasonchalom.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,5 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/TRex22/ocr-file" }
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,83 @@
+PATH
+  remote: .
+  specs:
+    ocr-file (0.0.1)
+      active_attr (~> 0.15.4)
+      console-style (~> 0.0.1)
+      hexapdf (~> 0.23.0)
+      mini_magick (~> 4.11.0)
+      rtesseract (~> 3.1.2)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    actionpack (7.0.3)
+      actionview (= 7.0.3)
+      activesupport (= 7.0.3)
+      rack (~> 2.0, >= 2.2.0)
+      rack-test (>= 0.6.3)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.2.0)
+    actionview (7.0.3)
+      activesupport (= 7.0.3)
+      builder (~> 3.1)
+      erubi (~> 1.4)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.1, >= 1.2.0)
+    active_attr (0.15.4)
+      actionpack (>= 3.0.2, < 7.1)
+      activemodel (>= 3.0.2, < 7.1)
+      activesupport (>= 3.0.2, < 7.1)
+    activemodel (7.0.3)
+      activesupport (= 7.0.3)
+    activesupport (7.0.3)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 1.6, < 2)
+      minitest (>= 5.1)
+      tzinfo (~> 2.0)
+    builder (3.2.4)
+    cmdparse (3.0.7)
+    coderay (1.1.3)
+    concurrent-ruby (1.1.10)
+    console-style (0.0.1)
+    crass (1.0.6)
+    erubi (1.10.0)
+    geom2d (0.3.1)
+    hexapdf (0.23.0)
+      cmdparse (~> 3.0, >= 3.0.3)
+      geom2d (~> 0.3)
+    i18n (1.10.0)
+      concurrent-ruby (~> 1.0)
+    loofah (2.18.0)
+      crass (~> 1.0.2)
+      nokogiri (>= 1.5.9)
+    method_source (1.0.0)
+    mini_magick (4.11.0)
+    minitest (5.16.0)
+    nokogiri (1.13.6-arm64-darwin)
+      racc (~> 1.4)
+    pry (0.14.1)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    racc (1.6.0)
+    rack (2.2.3.1)
+    rack-test (1.1.0)
+      rack (>= 1.0, < 3)
+    rails-dom-testing (2.0.3)
+      activesupport (>= 4.2.0)
+      nokogiri (>= 1.6)
+    rails-html-sanitizer (1.4.3)
+      loofah (~> 2.3)
+    rtesseract (3.1.2)
+    tzinfo (2.0.4)
+      concurrent-ruby (~> 1.0)
+
+PLATFORMS
+  arm64-darwin-20
+
+DEPENDENCIES
+  ocr-file!
+  pry (~> 0.14.1)
+
+BUNDLED WITH
+   2.3.5

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 Jason Chalom
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,121 @@
+#  OCR-File
+A tool to combine PDF tools, OCR tools and image processing into a
+single interface as both a CLI and a library.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ocr-file'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ocr-file
+
+### Other required dependencies
+You will need to install `tesseract` with your desired language on your system,
+`pdftoppm` needs to be available and also `image-magick`.
+
+## Usage
+```ruby
+  require 'ocr-file'
+
+  config = {
+    # Images from PDF
+    filetype: 'png',
+    quality: 100,
+    dpi: 300,
+    # Text to PDF
+    font: 'Helvetica',
+    font_size: 5, #8 # 12
+    text_x: 20,
+    text_y: 800,
+    minimum_word: 5,
+    # Cloud-Vision OCR
+    image_annotator: nil, # Needed for Cloud-Vision
+    type_of_ocr: OcrFile::OcrEngines::CloudVision::DOCUMENT_TEXT_DETECTION,
+    ocr_engine: 'tesseract', # 'cloud-vision'
+    # Image Pre-Processing
+    image_pre_preprocess: true,
+    effects: ['bw', 'norm'],
+    threshold: 0.25,
+    # PDF to Image Processing
+    optimise_pdf: true,
+    extract_pdf_images: true, # if false will screenshot each PDF page
+    temp_filename_prefix: 'image',
+    # Console Output
+    verbose: true,
+  }
+
+  doc = OcrFile::Document.new(
+    original_file_path: '/path-to-original-file/', # supports PDFs and images
+    save_file_path: '/folder-to-save-to/',
+    config: config # Not needed as defaults are used when not provided
+  )
+
+  doc.to_s # Returns text, removes temp files and wont save
+  doc.to_pdf # Saves a PDF (either searchable over the images or dumped text)
+  doc.to_text # Saves a text file with OCR text
+
+  # How to generate PDFs of images or text files:
+  original_file_path = 'file.txt' OR 'file.png'
+
+  doc = OcrFile::Document.new(
+    original_file_path: original_file_path, # supports PDFs and images
+    save_file_path: '/folder-to-save-to/',
+    config: config # Not needed as defaults are used when not provided
+  )
+
+  doc.to_pdf
+
+  # How to merge files into a single PDF:
+  filepaths = []
+  documents = file_paths.map { |path| OcrFile::ImageEngines::PdfEngine.open_pdf(path, password: '') }
+  merged_document = OcrFile::ImageEngines::PdfEngine.merge(documents)
+  OcrFile::ImageEngines::PdfEngine.save_pdf(merged_document, save_file_path, optimise: true)
+```
+
+### Notes / Tips
+Set `extract_pdf_images` to `false` for higher quality OCR. However this will consume more temporary space per PDF page and also be considerably slower.
+
+Image pre-processing is not yet implemented.
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+### TODOs
+- input validation
+- CLI
+- image processing
+- password
+- Base64 encoding
+- requirements checking (installed dependencies etc ...)
+- Tests
+- Configurable temp folder cleanup
+- Improve console output
+
+### Tests
+To run tests execute:
+
+    $ rake test
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/trex22/ocr-file. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the OCR-File: project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/trex22/ocr-file/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task :default => :test

data/bin/console

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "ocr-file"
+
+# 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.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+require "pry"
+Pry.start

data/bin/ocr-file

@@ -0,0 +1,5 @@
+#!/usr/bin/env ruby -wU
+
+require 'ocr-file'
+
+puts "Hello, world!"

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/ocr-file/cli.rb

@@ -0,0 +1,5 @@
+module OcrFile
+  module Cli
+
+  end
+end

data/lib/ocr-file/document.rb

@@ -0,0 +1,195 @@
+module OcrFile
+  class Document
+    ACCEPTED_IMAGE_TYPES = ['png', 'jpeg', 'jpg', 'tiff', 'bmp']
+    PAGE_BREAK = "\n\r\n" # TODO: Make configurable
+    DEFAULT_CONFIG = {
+      # Images from PDF
+      filetype: 'png',
+      quality: 100,
+      dpi: 300,
+      # Text to PDF
+      font: 'Helvetica',
+      font_size: 5, #8 # 12
+      text_x: 20,
+      text_y: 800,
+      minimum_word: 5,
+      # Cloud-Vision OCR
+      image_annotator: nil, # Needed for Cloud-Vision
+      type_of_ocr: OcrFile::OcrEngines::CloudVision::DOCUMENT_TEXT_DETECTION,
+      ocr_engine: 'tesseract', # 'cloud-vision'
+      # Image Pre-Processing
+      image_pre_preprocess: true,
+      effects: ['bw', 'norm'],
+      threshold: 0.25,
+      # PDF to Image Processing
+      optimise_pdf: true,
+      extract_pdf_images: true, # if false will screenshot each PDF page
+      temp_filename_prefix: 'image',
+      # Console Output
+      verbose: true,
+    }
+
+    attr_reader :original_file_path,
+      :filename,
+      :save_file_path,
+      :final_save_file,
+      :config,
+      :ocr_engine
+
+    # save_file_path will also generate a tmp path for tmp files. Expected folder path
+    # TODO: Add in more input validation
+    def initialize(original_file_path:, save_file_path:, config: DEFAULT_CONFIG)
+      @original_file_path = original_file_path
+      @filename = original_file_path.split('/').last.split('.').first
+
+      date = Time.now.to_s.split(' ').first
+
+      @save_file_path = save_file_path
+      @final_save_file = "#{@save_file_path}/#{@filename}-#{date}-#{Time.now.to_i}"
+
+      @config = config
+      @ocr_engine = find_ocr_engine(config[:ocr_engine])
+    end
+
+    def pdf?
+      @original_file_path.include?('.pdf')
+    end
+
+    def image?
+      return false if pdf?
+      ACCEPTED_IMAGE_TYPES.any? { |type| @original_file_path.include?(".#{type}")}
+    end
+
+    # Treat anything which isnt a PDF or image as text
+    def text?
+      !pdf? && !image?
+    end
+
+    def to_pdf
+      if pdf?
+        create_temp_folder
+        image_paths = extract_image_paths_from_pdf(@original_file_path)
+
+        pdfs_to_merge = []
+
+        image_paths.each do |image_path|
+          pdfs_to_merge << @ocr_engine.ocr_to_pdf(image_path, options: @config)
+        end
+
+        merged_pdf = OcrFile::ImageEngines::PdfEngine.merge(pdfs_to_merge)
+
+        OcrFile::ImageEngines::PdfEngine
+          .save_pdf(merged_pdf, "#{@final_save_file}.pdf", optimise: @config[:optimise_pdf])
+
+        close
+      elsif text?
+        text = ::OcrFile::FileHelpers.open_text_file(@original_file_path)
+        pdf_file = OcrFile::ImageEngines::PdfEngine.pdf_from_text(text, @config)
+
+        OcrFile::ImageEngines::PdfEngine
+          .save_pdf(pdf_file, "#{@final_save_file}.pdf", optimise: @config[:optimise_pdf])
+      else # is an image
+        ocr_image_to_pdf
+      end
+    end
+
+    def to_text
+      if pdf?
+        create_temp_folder
+        image_paths = extract_image_paths_from_pdf(@original_file_path)
+
+        image_paths.each do |image_path|
+          text = @ocr_engine.ocr_to_text(image_path, options: @config)
+          ::OcrFile::FileHelpers.append_file("#{@final_save_file}.txt", "#{text}#{PAGE_BREAK}")
+        end
+
+        close
+      elsif text?
+        ::OcrFile::FileHelpers.open_text_file(@original_file_path)
+      else # is an image
+        ocr_image_to_text(save: true)
+      end
+    end
+
+    def to_s
+      if pdf?
+        create_temp_folder
+        image_paths = extract_image_paths_from_pdf(@original_file_path)
+
+        text = ''
+
+        image_paths.each do |image_path|
+          text = "#{text}#{PAGE_BREAK}#{@ocr_engine.ocr_to_text(image_path, options: @config)}"
+        end
+
+        close
+        text
+      elsif text?
+        ::OcrFile::FileHelpers.open_text_file(@original_file_path)
+      else # is an image
+        ocr_image_to_text(save: false)
+      end
+    end
+
+    def close
+      ::OcrFile::FileHelpers.clear_folder(@temp_folder_path)
+    end
+
+    private
+
+    def extract_image_paths_from_pdf(file_path)
+      document = OcrFile::ImageEngines::PdfEngine.open_pdf(file_path, password: '')
+
+      if @config[:extract_pdf_images]
+        OcrFile::ImageEngines::PdfEngine
+          .extract_images(document, @temp_folder_path, verbose: @config[:verbose])
+      else # Generate screenshots of each image
+        OcrFile::ImageEngines::Pdftoppm.images_from_pdf(
+          file_path,
+          @temp_folder_path,
+          filename: @config[:temp_filename_prefix],
+          filetype: @config[:filetype],
+          quality: @config[:quality],
+          dpi: @config[:dpi],
+          verbose: @config[:verbose]
+        )
+      end
+    end
+
+    def create_temp_folder
+      # TODO: Make this a bit more robust
+      @temp_folder_path = "#{save_file_path}/temp/".gsub(' ', '\ ')
+      ::OcrFile::FileHelpers.make_directory(@temp_folder_path)
+    end
+
+    def ocr_image_to_pdf
+      pdf_document = @ocr_engine.ocr_to_pdf(@original_file_path, options: @config)
+      OcrFile::ImageEngines::PdfEngine
+        .save_pdf(pdf_document, "#{@final_save_file}.pdf", optimise: @config[:optimise_pdf])
+    end
+
+    def ocr_image_to_text(save: true)
+      text = @ocr_engine.ocr_to_text(@original_file_path, options: @config)
+
+      if save
+        ::OcrFile::FileHelpers.append_file("#{@final_save_file}.txt", text)
+      else
+        text
+      end
+    end
+
+    def find_ocr_engine(engine_id)
+      ocr_engine_constants
+        .map { |c| ocr_module(c) }
+        .find { |selected_module| selected_module.id == engine_id }
+    end
+
+    def ocr_module(constant)
+      OcrFile::OcrEngines.const_get(constant)
+    end
+
+    def ocr_engine_constants
+      OcrFile::OcrEngines.constants
+    end
+  end
+end

data/lib/ocr-file/file_helpers.rb

@@ -0,0 +1,40 @@
+module OcrFile
+  module FileHelpers
+    extend self
+
+    def merge_pdfs(file_paths, save_file_path)
+      documents = file_paths.map { |path| OcrFile::ImageEngines::PdfEngine.open_pdf(path) }
+      merged_document = OcrFile::ImageEngines::PdfEngine.merge(documents)
+      save_pdf(merged_document, save_file_path, optimise: true)
+    end
+
+    # Beware this is dangerous!
+    def clear_folder(path)
+      return unless path.include?('/temp') # Small hacky safeguard
+      `rm -rf #{path}` # Cleanup
+    end
+
+    def make_directory(path)
+      `mkdir -p #{path}`
+    end
+
+    def open_json(path)
+      JSON.parse(File.read(path))
+    end
+
+    def append_file(path, text)
+      File.open(path, 'a') { |file| file.write(text) }
+    end
+
+    def open_text_file(path)
+      File.read(path)
+    end
+
+    def fetch_temp_image_paths(save_path, temp_filename, filetype)
+      filenames = `ls #{save_path} | grep .#{filetype}`.split("\n")
+      filenames.map do |filename|
+        "#{save_path}/#{filename}"
+      end
+    end
+  end
+end

data/lib/ocr-file/image_engines/image_magick.rb

@@ -0,0 +1,14 @@
+module OcrFile
+  module ImageEngines
+    module ImageMagick
+      extend self
+
+      # TODO:
+      # B/W
+      # Contrast
+      # Image Norm
+      # Threshold
+      # Conversion of image types
+    end
+  end
+end

data/lib/ocr-file/image_engines/pdf_engine.rb

@@ -0,0 +1,75 @@
+module OcrFile
+  module ImageEngines
+    module PdfEngine
+      extend self
+
+      PAGE_BREAK = "\n\r\n"
+
+      DEFAULT_PAGE_OPTIONS = {
+        font: 'Helvetica',
+        font_size: 5, #8 # 12
+        text_x: 20,
+        text_y: 800,
+        minimum_word: 5,
+      }
+
+      def pdf_from_text(text, options = DEFAULT_PAGE_OPTIONS)
+        document = ::HexaPDF::Document.new
+
+        text
+          .split(PAGE_BREAK)
+          .reject { |line| line.size < options[:minimum_word] }
+          .each { |page_text| document = add_page(document, page_text, options) }
+
+        document
+      end
+
+      def add_page(document, text, options)
+        canvas = document.pages.add.canvas
+        canvas.font(options[:font], size: options[:font_size])
+        canvas.text(text, at: [options[:text_x], options[:text_y]])
+
+        document
+      end
+
+      def save_pdf(document, save_file_path, optimise: true)
+        document.write(save_file_path, optimize: true)
+      end
+
+      def open_pdf(file, password: '')
+        ::HexaPDF::Document.open(file, decryption_opts: { password: password })
+      end
+
+      def extract_images(document, save_path, verbose: false)
+        image_paths = []
+
+        ::HexaPDF::CLI::Images.new.send(:each_image, document) do |image, index, pindex, (_x_ppi, _y_ppi)|
+          puts "Processing page: #{pindex} ..."
+          info = image.info
+
+          if info.writable
+            image_filename = "#{index}.#{image.info.extension}"
+            image_path = "#{save_path}/#{image_filename}"
+            image.write(image_path)
+
+            image_paths << image_path
+          elsif command_parser.verbosity_warning?
+            puts style("Warning (image #{index}, page #{pindex}): PDF image format not supported for writing", RED)
+          end
+        end
+
+        image_paths
+      end
+
+      def merge(documents)
+        target = ::HexaPDF::Document.new
+
+        documents.each do |document|
+          document.pages.each { |page| target.pages << target.import(page) }
+        end
+
+        target
+      end
+    end
+  end
+end

data/lib/ocr-file/image_engines/pdftoppm.rb

@@ -0,0 +1,27 @@
+module OcrFile
+  module ImageEngines
+    module Pdftoppm
+      extend self
+
+      # TODO: other options
+      # https://www.xpdfreader.com/pdftoppm-man.html
+      # password
+      # −mono Generate a monochrome PBM file (instead of an RGB PPM file).
+      # −gray Generate a grayscale PGM file (instead of an RGB PPM file).
+      # −cmyk Generate a CMYK PAM file (instead of an RGB PPM file).
+      def images_from_pdf(pdf_path, save_path, filename: 'image', filetype: 'png', quality: 100, dpi: 300, verbose: true)
+        print 'Generating screenshots of each PDF page ... '
+
+        if filetype == 'jpg'
+          `pdftoppm -jpeg -jpegopt quality=#{quality} -r #{dpi} #{pdf_path} #{save_path}/#{filename}`
+        else
+          `pdftoppm -#{filetype} -r #{dpi} #{pdf_path} #{save_path}/#{filename}`
+        end
+
+        puts 'Complete!'
+
+        OcrFile::FileHelpers.fetch_temp_image_paths(save_path, filename, filetype)
+      end
+    end
+  end
+end

data/lib/ocr-file/ocr_engines/cloud_vision.rb

@@ -0,0 +1,59 @@
+module OcrFile
+  module OcrEngines
+    module CloudVision
+      extend self
+
+      DEFAULT_LANGUAGE = 'en'
+
+      # Available Types: https://github.com/googleapis/google-cloud-ruby/blob/master/google-cloud-vision/lib/google/cloud/vision/v1/image_annotator_pb.rb
+      TEXT_DETECTION = 'TEXT_DETECTION' # Used for low-quality images
+      DOCUMENT_TEXT_DETECTION = 'DOCUMENT_TEXT_DETECTION' # Used for dense text documents
+
+      def id
+        'cloud-vision'
+      end
+
+      def ocr_to_text(file_path, options: { type_of_ocr: '', image_annotator: nil })
+        type_of_ocr = options[:type_of_ocr]
+        image_annotator = options[:image_annotator]
+
+        response = detect_text(type_of_ocr, file_path, image_annotator)
+        extract_text(response)
+      end
+
+      def ocr_to_pdf(file_path, options: { type_of_ocr: '', image_annotator: nil })
+        text = ocr_to_text(file_path, options: { type_of_ocr: '', image_annotator: nil })
+        OcrFile::ImageEngines::PdfEngine.pdf_from_text(text, options)
+      end
+
+      private
+
+      def detect_text(type_of_ocr, image_path, image_annotator)
+        if type_of_ocr == 'DOCUMENT_TEXT_DETECTION'
+          image_annotator.document_text_detection(image: image_path)
+        else
+          image_annotator.text_detection(image: image_path)
+        end
+      end
+
+      def extract_text(response)
+        raw_text = ''
+        foreign_text = ''
+
+        response.responses.each do |section|
+          section.text_annotations.each do |annotation|
+            raw_text << annotation.description
+
+            if annotation.locale && annotation.locale != DEFAULT_LANGUAGE
+              foreign_text << annotation.description
+            end
+          end
+        end
+
+        raw_text = raw_text.split("\n")
+        raw_text.pop # Remove the last line
+        raw_text.join("\n")
+      end
+    end
+  end
+end

data/lib/ocr-file/ocr_engines/tesseract.rb

@@ -0,0 +1,22 @@
+module OcrFile
+  module OcrEngines
+    module Tesseract
+      extend self
+
+      def id
+        'tesseract'
+      end
+
+      def ocr_to_text(file_path, options: {})
+        image = ::RTesseract.new(file_path)
+        image.to_s # Getting the value
+      end
+
+      def ocr_to_pdf(file_path, options: {})
+        image = ::RTesseract.new(file_path)
+        raw_output = image.to_pdf  # Getting open file of pdf
+        OcrFile::ImageEngines::PdfEngine.open_pdf(raw_output, password: '')
+      end
+    end
+  end
+end

data/lib/ocr-file/version.rb

@@ -0,0 +1,3 @@
+module OcrFile
+  VERSION = "0.0.1"
+end

data/lib/ocr-file.rb

@@ -0,0 +1,19 @@
+require 'hexapdf'
+require 'hexapdf/cli/images'
+require 'rtesseract'
+require 'mini_magick'
+
+require 'ocr-file/version'
+
+require 'ocr-file/image_engines/pdf_engine'
+require 'ocr-file/image_engines/image_magick'
+require 'ocr-file/image_engines/pdftoppm'
+require 'ocr-file/ocr_engines/tesseract'
+require 'ocr-file/ocr_engines/cloud_vision'
+require 'ocr-file/file_helpers'
+require 'ocr-file/document'
+require 'ocr-file/cli'
+
+module OcrFile
+  class Error < StandardError; end
+end

data/ocr-file.gemspec

@@ -0,0 +1,38 @@
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "ocr-file/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "ocr-file"
+  spec.version       = OcrFile::VERSION
+  spec.authors       = ["trex22"]
+  spec.email         = ["contact@jasonchalom.com"]
+
+  spec.summary       = "A tool to combine PDF tools, OCR tools and image processing into a single interface as both a CLI and a library."
+  spec.description   = "A tool to combine PDF tools, OCR tools and image processing into a single interface as both a CLI and a library."
+  spec.homepage      = "https://github.com/TRex22/ocr-file"
+
+  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
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+
+  spec.bindir        = "bin"
+  spec.executables   = ["ocr-file"] #spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  # Dependencies
+  spec.add_dependency "console-style", "~> 0.0.1"
+
+  spec.add_dependency "active_attr", "~> 0.15.4"
+  spec.add_dependency "hexapdf", "~> 0.23.0"
+  spec.add_dependency "rtesseract", "~> 3.1.2"
+  spec.add_dependency "mini_magick", "~> 4.11.0"
+
+  # Development Dependencies
+  spec.add_development_dependency "pry", "~> 0.14.1"
+end

metadata

@@ -0,0 +1,151 @@
+--- !ruby/object:Gem::Specification
+name: ocr-file
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- trex22
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-06-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: console-style
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.1
+- !ruby/object:Gem::Dependency
+  name: active_attr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.15.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.15.4
+- !ruby/object:Gem::Dependency
+  name: hexapdf
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.23.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.23.0
+- !ruby/object:Gem::Dependency
+  name: rtesseract
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.1.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 3.1.2
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.11.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.11.0
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.1
+description: A tool to combine PDF tools, OCR tools and image processing into a single
+  interface as both a CLI and a library.
+email:
+- contact@jasonchalom.com
+executables:
+- ocr-file
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- bin/console
+- bin/ocr-file
+- bin/setup
+- lib/ocr-file.rb
+- lib/ocr-file/cli.rb
+- lib/ocr-file/document.rb
+- lib/ocr-file/file_helpers.rb
+- lib/ocr-file/image_engines/image_magick.rb
+- lib/ocr-file/image_engines/pdf_engine.rb
+- lib/ocr-file/image_engines/pdftoppm.rb
+- lib/ocr-file/ocr_engines/cloud_vision.rb
+- lib/ocr-file/ocr_engines/tesseract.rb
+- lib/ocr-file/version.rb
+- ocr-file.gemspec
+homepage: https://github.com/TRex22/ocr-file
+licenses:
+- MIT
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.4
+signing_key:
+specification_version: 4
+summary: A tool to combine PDF tools, OCR tools and image processing into a single
+  interface as both a CLI and a library.
+test_files: []