pdf_ocr 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 32727eeb24656d1fce7cb43f2f5192f29cfda53192ef161cfae047f2871f6bff
+  data.tar.gz: 558586ded2489faf79ce7f36ee1ab6df267d9dc30d67e6ba554be61bde959e19
+SHA512:
+  metadata.gz: c02b99bb1e652fe8c26ad80ed8dc4652c8eab5cc9a8bb4699b656080066772f811ee66ced0faa584f9a526322620c9e628f3a47c194f54b900706f968274c4dc
+  data.tar.gz: 9d7fea0ffe63fb2c10825d906831fb70dce2f1ab3d3d0c02c814dbd499c81fa906f23bc27e794d5ed3670b381c86b9da1b6f1abc091392684f5c17f97be000b4

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/Gemfile

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in ocr.gemspec
+gemspec
+
+gem "rake", "~> 13.0"
+gem "rspec"
+gem "pdf-reader"
+gem "mini_magick"
+gem "byebug"
+gem "rtesseract"

data/Gemfile.lock

@@ -0,0 +1,63 @@
+PATH
+  remote: .
+  specs:
+    pdf_ocr (0.1.0)
+      mini_magick
+      pdf-reader
+      rtesseract
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    Ascii85 (2.0.1)
+    afm (0.2.2)
+    bigdecimal (3.3.1)
+    byebug (12.0.0)
+    diff-lcs (1.6.2)
+    hashery (2.1.2)
+    mini_magick (4.13.2)
+    mini_portile2 (2.8.9)
+    nokogiri (1.18.10)
+      mini_portile2 (~> 2.8.2)
+      racc (~> 1.4)
+    pdf-reader (2.15.0)
+      Ascii85 (>= 1.0, < 3.0, != 2.0.0)
+      afm (>= 0.2.1, < 2)
+      hashery (~> 2.0)
+      ruby-rc4
+      ttfunk
+    racc (1.8.1)
+    rake (13.3.0)
+    rspec (3.13.1)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.5)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.6)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.6)
+    rtesseract (2.2.0)
+      nokogiri
+    ruby-rc4 (0.1.5)
+    ttfunk (1.8.0)
+      bigdecimal (~> 3.1)
+
+PLATFORMS
+  x86_64-linux
+
+DEPENDENCIES
+  byebug
+  mini_magick
+  pdf-reader
+  pdf_ocr!
+  rake (~> 13.0)
+  rspec
+  rtesseract
+
+BUNDLED WITH
+   2.4.12

data/README.md

@@ -0,0 +1,138 @@
+# OCR
+
+A lightweight Ruby gem for extracting text from PDFs, including scanned PDFs using OCR.
+
+This gem supports:
+
+- PDFs with readable text
+- Scanned PDFs using Tesseract OCR
+- File objects, file paths, StringIO, and Rails/ActiveStorage uploads
+- Fully Rails-independent
+
+---
+
+## 🚀 Features
+
+- Detect if PDF is scanned or text-based
+- Extract text from normal PDFs using `PDF::Reader`
+- Extract text from scanned PDFs using `RTesseract` and `MiniMagick`
+- Automatic cleanup of temporary images
+
+---
+
+## 💻 Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ocr', git: 'https://github.com/your_username/ocr.git'
+```
+
+Or install directly:
+```ruby
+gem install ocr
+```
+
+## Dependencies
+- PDF::Reader
+
+- RTesseract
+
+- MiniMagick
+
+- Tesseract OCR (system-level executable)
+
+- pdftoppm from Poppler utils (for converting PDF pages to images)
+
+## ⚙️ Usage
+```ruby
+require 'ocr'
+require 'stringio'
+
+# From a File object
+file = File.open("path/to/document.pdf")
+result = Ocr::DataExtractor.new(file).call
+puts result["raw_text"] if result["success"]
+
+# From a file path string
+result = Ocr::DataExtractor.new("path/to/document.pdf").call
+
+# From a StringIO object (in-memory PDF)
+pdf_data = StringIO.new(File.read("path/to/document.pdf"))
+result = Ocr::DataExtractor.new(pdf_data).call
+```
+
+## Example Result
+```ruby
+{
+  "success" => true,
+  "raw_text" => "Extracted text content from PDF ..."
+}
+```
+- If OCR fails for a scanned PDF:
+```ruby
+{
+  "success" => false,
+  "message" => "Unable to extract text using OCR"
+}
+```
+## 🔧 Notes
+1. Ensure Tesseract OCR is installed on your system:
+```
+# Ubuntu/Debian
+sudo apt install tesseract-ocr
+
+# MacOS (with Homebrew)
+brew install tesseract
+```
+2. Ensure pdftoppm is installed (for PDF-to-image conversion):
+```
+# Ubuntu/Debian
+sudo apt install poppler-utils
+
+# MacOS (with Homebrew)
+brew install poppler
+```
+3. This gem does not require Rails, but it will work with Rails ActiveStorage objects that respond to .open.
+
+## 🧪 Running Tests
+```
+bundle install
+bundle exec rspec
+```
+
+- PDFs with selectable text
+
+- Scanned PDFs
+
+- Malformed PDFs (fallback to OCR)
+
+## 📝 Contributing
+
+- Fork the repository
+
+- Create your feature branch (git checkout -b your-feature)
+
+- Commit your changes (git commit -am 'Add new feature')
+
+- Push to the branch (git push origin your-feature)
+
+- Open a Pull Request
+
+## 📝 License
+
+MIT License © RaviShankarSinghal
+
+
+---
+
+This version includes:
+
+- Version and build badges (replace with your repo info)  
+- Clear installation instructions  
+- Usage examples for File, path, and StringIO  
+- System dependencies  
+- Test instructions  
+- Contributing guidelines  
+
+---

data/Rakefile

@@ -0,0 +1,4 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+task default: %i[]

data/lib/ocr/data_extractor.rb

@@ -0,0 +1,122 @@
+require "mini_magick"
+require "pdf/reader"
+require "rtesseract"
+require "securerandom"
+require "shellwords"
+require "tmpdir"
+
+module Ocr
+  class DataExtractor
+    def initialize(document)
+      @document = document
+    end
+
+    def call
+      ocr_data(@document)
+    end
+
+    private
+
+    def ocr_data(document)
+      extracted_text = ""
+      is_scanned = false
+
+      file = get_file_from(document)
+      reader = if file.respond_to?(:path)
+                PDF::Reader.new(file.path)
+              else
+                PDF::Reader.new(file)
+              end
+
+      reader.pages.each do |page|
+        page_text = safe_page_text(page)
+        extracted_text << " " << page_text
+
+        if page_text.strip.empty? || mostly_junk?(page_text)
+          is_scanned = true
+          break
+        end
+      end
+
+      if is_scanned || scanned_pdf?(extracted_text)
+        scanned_pdf_ocr(file)
+      else
+        { "success" => true, "raw_text" => extracted_text.strip }
+      end
+    rescue PDF::Reader::MalformedPDFError, PDF::Reader::UnsupportedFeatureError => e
+      log_warning "PDF parsing failed: #{e.message}"
+      scanned_pdf_ocr(file)
+    end
+
+    def get_file_from(document)
+      return document.tap(&:open) if document.respond_to?(:open)
+      return document if document.is_a?(File)
+      return document if document.respond_to?(:read)
+      return File.open(document) if document.is_a?(String)
+
+      raise ArgumentError, "Unsupported document type: #{document.class}"
+    end
+
+    def safe_page_text(page)
+      page.text.to_s.encode("UTF-8", invalid: :replace, undef: :replace, replace: "")
+    rescue
+      ""
+    end
+
+    def scanned_pdf?(text)
+      return true if text.empty?
+      junk_ratio = text.count("^A-Za-z0-9\s").to_f / text.size
+      junk_ratio > 0.5 || text.size < 100
+    end
+
+    def mostly_junk?(text)
+      return true if text.empty?
+      text.scan(/[A-Za-z]/).count < (text.size * 0.2)
+    end
+
+    def scanned_pdf_ocr(file)
+      images = []
+      full_text = ""
+
+      images = if file.respond_to?(:path)
+                convert_pdf_to_images(file.path)
+              else
+                convert_pdf_to_images(file)
+              end
+      full_text += images.map { |img| extract_text(img) }.join(" ")
+
+      unless full_text.strip.empty?
+        { "success" => true, "raw_text" => full_text.strip }
+      else
+        { "success" => false, "message" => "Unable to extract text using OCR" }
+      end
+    ensure
+      cleanup(images)
+    end
+
+    def convert_pdf_to_images(pdf_path)
+      output_prefix = File.join(Dir.tmpdir, "ocr_page_#{SecureRandom.hex(4)}")
+      system("pdftoppm -png -r 300 #{Shellwords.escape(pdf_path)} #{Shellwords.escape(output_prefix)}")
+      Dir["#{output_prefix}-*.png"]
+    end
+
+    def extract_text(image_path)
+      RTesseract.new(image_path, lang: "eng", processor: "mini_magick").to_s
+    rescue => e
+      log_warning "OCR failed on #{image_path}: #{e.message}"
+      ""
+    end
+
+    def cleanup(images)
+      images&.each { |img| File.delete(img) if File.exist?(img) }
+    end
+
+    def log_warning(message)
+      if defined?(Rails)
+        Rails.logger.warn(message)
+      else
+        warn(message)
+      end
+    end
+  end
+end

data/lib/ocr/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Ocr
+  VERSION = "0.1.0"
+end

data/lib/ocr.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+require_relative "ocr/version"
+require_relative "ocr/data_extractor"
+
+module Ocr
+  class Error < StandardError; end
+  # Your code goes here...
+end

data/ocr.gemspec

@@ -0,0 +1,46 @@
+# frozen_string_literal: true
+
+require_relative "lib/ocr/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "pdf_ocr"
+  spec.version       = Ocr::VERSION
+  spec.authors       = ["Ravi Shankar Singhal"]
+  spec.email         = ["ravi.singhal2308@gmail.com"]
+
+  spec.summary       = "A lightweight Ruby gem for extracting text from images using OCR."
+  spec.description   = "OCR is a Ruby gem that allows you to easily extract text from image files (JPG, PNG, PDF) using Tesseract OCR engine. It provides a simple, intuitive interface for integrating OCR capabilities into your Ruby or Rails applications."
+  spec.homepage      = "https://github.com/RaviShankarSinghal/ocr_gem"
+  spec.license       = "MIT"
+
+  spec.required_ruby_version = ">= 2.6.0"
+
+  spec.metadata = {
+    "homepage_uri"   => spec.homepage,
+    "source_code_uri" => "https://github.com/RaviShankarSinghal/ocr_gem",
+    "changelog_uri"   => "https://github.com/RaviShankarSinghal/ocr_gem/blob/main/CHANGELOG.md",
+    "documentation_uri" => "https://rubydoc.info/gems/ocr"
+  }
+
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (File.expand_path(f) == __FILE__) ||
+        f.start_with?(*%w[bin/ test/ spec/ features/ .git .circleci appveyor])
+    end
+  end
+
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  # Common dependencies for OCR-based Ruby gems
+  # Runtime dependencies
+  spec.add_runtime_dependency "pdf-reader"
+  spec.add_runtime_dependency "mini_magick"
+  spec.add_runtime_dependency "rtesseract"
+
+  # Development dependencies
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "byebug"
+
+end

data/sig/ocr.rbs

@@ -0,0 +1,4 @@
+module Ocr
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,129 @@
+--- !ruby/object:Gem::Specification
+name: pdf_ocr
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Ravi Shankar Singhal
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2025-10-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mini_magick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rtesseract
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  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'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  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'
+description: OCR is a Ruby gem that allows you to easily extract text from image files
+  (JPG, PNG, PDF) using Tesseract OCR engine. It provides a simple, intuitive interface
+  for integrating OCR capabilities into your Ruby or Rails applications.
+email:
+- ravi.singhal2308@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- lib/ocr.rb
+- lib/ocr/data_extractor.rb
+- lib/ocr/version.rb
+- ocr.gemspec
+- sig/ocr.rbs
+homepage: https://github.com/RaviShankarSinghal/ocr_gem
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/RaviShankarSinghal/ocr_gem
+  source_code_uri: https://github.com/RaviShankarSinghal/ocr_gem
+  changelog_uri: https://github.com/RaviShankarSinghal/ocr_gem/blob/main/CHANGELOG.md
+  documentation_uri: https://rubydoc.info/gems/ocr
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.6.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.7
+signing_key:
+specification_version: 4
+summary: A lightweight Ruby gem for extracting text from images using OCR.
+test_files: []