universal_document_processor 1.0.2 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '06539a78d5cc253518f84b242dd7a8dcb71ce575614d7e8853bb9de70b031f75'
-  data.tar.gz: c58e957dfe6940c0cb16fb4c50f9ce0ee69aa7cf9a7587b2496a80da78bbdda8
+  metadata.gz: 8ec66decfe8626354f9fe05b757dbdc11921b21fa6b5dccfdb4d8ce5deba2c3f
+  data.tar.gz: 19c2802d337d0517ab91cfe71bdb2b051213e17f0e1a76605c5bce895429eed4
 SHA512:
-  metadata.gz: 81940e620b3dcff668493ae459e1287161ccbc56b8677acab3477913685d4f68580f0d4062ae0e777e83a000aa58a42619f3a96d0f19b2146e38fa2c3418587a
-  data.tar.gz: 61b98794dc95f0489a806d1dbb31b172f75570ac2fa140d0ff334347f58afdbfab370ffd72b003b948b7a4ec80656e6f29b196ca833e0b219b41316ebb729843
+  metadata.gz: f2cbb1944e533a4a75d6248dd6df279219e4a4c7b77dac3b0e4d474b5b4375203d188bff5d388af30716b3dc5487fcd293955c8504565c4a1b56d552a8484993
+  data.tar.gz: 2d95c2f173de302d14cdfda6d3357b5d7d9a5cf82cabc2e5622bdb8f6d7e60c56bab75eccf85a312045be5f8e66b743b4344420847192a3b0268cd4a70c5f414

data/Rakefile

@@ -1,12 +1,105 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
-require "rubocop/rake_task"
+require 'rake/testtask'
+require 'bundler/gem_tasks'
 
-RSpec::Core::RakeTask.new(:spec)
-RuboCop::RakeTask.new
+# Default task
+task default: :test
 
-desc "Run tests and linting"
-task default: %i[spec rubocop]
+# Test task
+Rake::TestTask.new(:test) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/test_*.rb']
+  t.verbose = true
+end
+
+# Individual test tasks
+Rake::TestTask.new(:test_core) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/test_universal_document_processor.rb']
+  t.verbose = true
+end
+
+Rake::TestTask.new(:test_ai) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/test_ai_agent.rb']
+  t.verbose = true
+end
+
+Rake::TestTask.new(:test_processors) do |t|
+  t.libs << 'test'
+  t.libs << 'lib'
+  t.test_files = FileList['test/test_processors.rb']
+  t.verbose = true
+end
+
+# Coverage task (if simplecov is available)
+desc "Run tests with coverage"
+task :coverage do
+  ENV['COVERAGE'] = 'true'
+  Rake::Task[:test].invoke
+end
+
+# Lint task (if rubocop is available)
+desc "Run RuboCop"
+task :lint do
+  begin
+    require 'rubocop/rake_task'
+    RuboCop::RakeTask.new
+  rescue LoadError
+    puts "RuboCop not available. Install it with: gem install rubocop"
+  end
+end
+
+# Documentation task
+desc "Generate documentation"
+task :doc do
+  system "yard doc"
+end
+
+# Clean task
+desc "Clean up generated files"
+task :clean do
+  FileUtils.rm_rf('coverage')
+  FileUtils.rm_rf('doc')
+  FileUtils.rm_rf('pkg')
+  FileUtils.rm_f('Gemfile.lock')
+end
+
+# Install dependencies
+desc "Install dependencies"
+task :install do
+  system "bundle install"
+end
+
+# Quality check task
+desc "Run all quality checks"
+task quality: [:test, :lint]
+
+# CI task
+desc "Run CI tasks"
+task ci: [:install, :test]
+
+# Development setup
+desc "Setup development environment"
+task :setup do
+  puts "Setting up development environment..."
+  Rake::Task[:install].invoke
+  puts "Development environment ready!"
+  puts ""
+  puts "Available tasks:"
+  puts "  rake test        - Run all tests"
+  puts "  rake test_core   - Run core functionality tests"
+  puts "  rake test_ai     - Run AI agent tests"
+  puts "  rake test_processors - Run processor tests"
+  puts "  rake coverage    - Run tests with coverage"
+  puts "  rake lint        - Run RuboCop linting"
+  puts "  rake doc         - Generate documentation"
+  puts "  rake clean       - Clean up generated files"
+  puts ""
+  puts "To run tests with AI features, set OPENAI_API_KEY environment variable"
+end
 
 desc "Build the gem"
 task :build do
@@ -23,14 +116,4 @@ desc "Install the gem locally"
 task :install do
   system "gem build universal_document_processor.gemspec"
   system "gem install universal_document_processor-*.gem"
-end
-
-desc "Clean build artifacts"
-task :clean do
-  system "rm -f *.gem"
-end
-
-desc "Generate documentation"
-task :doc do
-  system "yard doc"
 end 

data/lib/universal_document_processor/ai_agent.rb

@@ -4,7 +4,7 @@ require 'uri'
 
 module UniversalDocumentProcessor
   class AIAgent
-    attr_reader :api_key, :model, :base_url, :conversation_history
+    attr_reader :api_key, :model, :base_url, :conversation_history, :ai_enabled
 
     def initialize(options = {})
       @api_key = options[:api_key] || ENV['OPENAI_API_KEY']
@@ -13,12 +13,15 @@ module UniversalDocumentProcessor
       @conversation_history = []
       @max_history = options[:max_history] || 10
       @temperature = options[:temperature] || 0.7
+      @ai_enabled = false
       
       validate_configuration
     end
 
     # Main document analysis with AI
     def analyze_document(document_result, query = nil)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       if query
@@ -63,6 +66,8 @@ Please provide:
 
     # Ask specific questions about a document
     def ask_document_question(document_result, question)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       prompt = build_question_prompt(context, question)
@@ -74,6 +79,8 @@ Please provide:
 
     # Summarize document content
     def summarize_document(document_result, length: :medium)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       length_instruction = case length
@@ -92,6 +99,8 @@ Please provide:
 
     # Extract key information from document
     def extract_key_information(document_result, categories = nil)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       categories ||= ['key_facts', 'important_dates', 'names', 'locations', 'numbers']
       
@@ -104,6 +113,8 @@ Please provide:
 
     # Translate document content
     def translate_document(document_result, target_language)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       prompt = build_translation_prompt(context, target_language)
@@ -115,6 +126,8 @@ Please provide:
 
     # Generate document insights and recommendations
     def generate_insights(document_result)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       prompt = build_insights_prompt(context)
@@ -126,6 +139,8 @@ Please provide:
 
     # Compare multiple documents
     def compare_documents(document_results, comparison_type = :content)
+      ensure_ai_available!
+      
       contexts = document_results.map { |doc| build_document_context(doc) }
       
       prompt = build_comparison_prompt(contexts, comparison_type)
@@ -137,6 +152,8 @@ Please provide:
 
     # Classify document type and purpose
     def classify_document(document_result)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       prompt = build_classification_prompt(context)
@@ -148,6 +165,8 @@ Please provide:
 
     # Generate action items from document
     def extract_action_items(document_result)
+      ensure_ai_available!
+      
       context = build_document_context(document_result)
       
       prompt = build_action_items_prompt(context)
@@ -159,6 +178,8 @@ Please provide:
 
     # Chat about the document
     def chat(message, document_result = nil)
+      ensure_ai_available!
+      
       if document_result
         context = build_document_context(document_result)
         prompt = build_chat_prompt(context, message)
@@ -180,6 +201,10 @@ Please provide:
     def conversation_summary
       return "No conversation history" if @conversation_history.empty?
       
+      unless @ai_enabled
+        return "AI features are disabled. Cannot generate conversation summary."
+      end
+      
       history_text = @conversation_history.map do |entry|
         "Q: #{entry[:question]}\nA: #{entry[:answer]}"
       end.join("\n\n")
@@ -188,11 +213,27 @@ Please provide:
       call_openai_api(prompt)
     end
 
+    # Check if AI features are available
+    def ai_available?
+      @ai_enabled
+    end
+
     private
 
     def validate_configuration
-      raise ArgumentError, "OpenAI API key is required" unless @api_key
-      raise ArgumentError, "OpenAI API key cannot be empty" if @api_key.empty?
+      if @api_key && !@api_key.empty?
+        @ai_enabled = true
+      else
+        @ai_enabled = false
+        warn "Warning: OpenAI API key not provided. AI features will be disabled. Set OPENAI_API_KEY environment variable or pass api_key option to enable AI features."
+      end
+    end
+
+    # Ensure AI is available before making API calls
+    def ensure_ai_available!
+      unless @ai_enabled
+        raise DependencyMissingError, "AI features are not available. Please provide an OpenAI API key to use AI functionality."
+      end
     end
 
     def build_document_context(document_result)

data/lib/universal_document_processor/processors/pdf_processor.rb

@@ -2,6 +2,8 @@ module UniversalDocumentProcessor
   module Processors
     class PdfProcessor < BaseProcessor
       def extract_text
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           reader = PDF::Reader.new(@file_path)
           text = reader.pages.map(&:text).join("\n")
@@ -10,6 +12,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_metadata
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           reader = PDF::Reader.new(@file_path)
           info = reader.info || {}
@@ -32,6 +36,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_images
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           # Extract embedded images from PDF
           images = []
@@ -57,6 +63,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_tables
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           # Basic table extraction from PDF text
           tables = []
@@ -87,6 +95,12 @@ module UniversalDocumentProcessor
 
       private
 
+      def ensure_pdf_reader_available!
+        unless defined?(PDF::Reader)
+          raise DependencyMissingError, "PDF processing requires the 'pdf-reader' gem. Install it with: gem install pdf-reader -v '~> 2.0'"
+        end
+      end
+
       def extract_form_fields(reader)
         # Extract PDF form fields if present
         []

data/lib/universal_document_processor/processors/word_processor.rb

@@ -30,6 +30,7 @@ module UniversalDocumentProcessor
       def extract_images
         with_error_handling do
           return [] unless @file_path.end_with?('.docx')
+          ensure_docx_available!
           
           images = []
           doc = Docx::Document.open(@file_path)
@@ -53,6 +54,7 @@ module UniversalDocumentProcessor
       def extract_tables
         with_error_handling do
           return [] unless @file_path.end_with?('.docx')
+          ensure_docx_available!
           
           tables = []
           doc = Docx::Document.open(@file_path)
@@ -88,7 +90,15 @@ module UniversalDocumentProcessor
 
       private
 
+      def ensure_docx_available!
+        unless defined?(Docx)
+          raise DependencyMissingError, "DOCX processing requires the 'docx' gem. Install it with: gem install docx -v '~> 0.8'"
+        end
+      end
+
       def extract_docx_text
+        ensure_docx_available!
+        
         doc = Docx::Document.open(@file_path)
         text_content = []
         
@@ -109,6 +119,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_docx_metadata
+        ensure_docx_available!
+        
         doc = Docx::Document.open(@file_path)
         core_properties = doc.core_properties
         

data/lib/universal_document_processor/version.rb

@@ -1,3 +1,3 @@
 module UniversalDocumentProcessor
-  VERSION = "1.0.2"
+  VERSION = "1.0.3"
 end 

data/lib/universal_document_processor.rb

@@ -122,48 +122,72 @@ module UniversalDocumentProcessor
   def self.ai_analyze(file_path, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.analyze_document(document_result, options[:query])
   end
 
   def self.ai_summarize(file_path, length: :medium, options: {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.summarize_document(document_result, length: length)
   end
 
   def self.ai_extract_info(file_path, categories = nil, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.extract_key_information(document_result, categories)
   end
 
   def self.ai_translate(file_path, target_language, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.translate_document(document_result, target_language)
   end
 
   def self.ai_classify(file_path, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.classify_document(document_result)
   end
 
   def self.ai_insights(file_path, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.generate_insights(document_result)
   end
 
   def self.ai_action_items(file_path, options = {})
     document_result = process(file_path, options)
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.extract_action_items(document_result)
   end
 
   def self.ai_compare(file_paths, comparison_type = :content, options = {})
     document_results = file_paths.map { |path| process(path, options) }
     ai_agent = AIAgent.new(options)
+    unless ai_agent.ai_available?
+      raise DependencyMissingError, "AI features require an OpenAI API key. Set OPENAI_API_KEY environment variable or pass api_key in options."
+    end
     ai_agent.compare_documents(document_results, comparison_type)
   end
 
@@ -171,6 +195,12 @@ module UniversalDocumentProcessor
     AIAgent.new(options)
   end
 
+  # Check if AI features are available
+  def self.ai_available?(options = {})
+    ai_agent = AIAgent.new(options)
+    ai_agent.ai_available?
+  end
+
   # Convert document to different format
   def self.convert(file_path_or_io, target_format, options = {})
     Document.new(file_path_or_io, options).convert_to(target_format)
@@ -207,9 +237,54 @@ module UniversalDocumentProcessor
     end
   end
 
+  # Get list of optional dependencies
+  def self.optional_dependencies
+    {
+      'pdf-reader' => '~> 2.0',      # PDF text extraction
+      'prawn' => '~> 2.4',           # PDF generation
+      'docx' => '~> 0.8',            # Word document processing
+      'roo' => '~> 2.8',             # Excel/Spreadsheet processing
+      'mini_magick' => '~> 4.11',    # Image processing
+      'yomu' => '~> 0.2'             # Universal text extraction fallback
+    }
+  end
+
+  # Check which optional dependencies are missing
+  def self.missing_dependencies
+    missing = []
+    missing << 'pdf-reader' unless dependency_available?(:pdf_reader)
+    missing << 'prawn' unless dependency_available?(:prawn)
+    missing << 'docx' unless dependency_available?(:docx)
+    missing << 'roo' unless dependency_available?(:roo)
+    missing << 'mini_magick' unless dependency_available?(:mini_magick)
+    missing << 'yomu' unless dependency_available?(:yomu)
+    missing
+  end
+
+  # Generate installation instructions for missing dependencies
+  def self.installation_instructions
+    missing = missing_dependencies
+    return "All optional dependencies are installed!" if missing.empty?
+
+    instructions = ["To enable additional features, install these optional gems:"]
+    missing.each do |gem_name|
+      version = optional_dependencies[gem_name]
+      instructions << "  gem install #{gem_name} -v '#{version}'"
+    end
+    
+    instructions << ""
+    instructions << "Or add to your Gemfile:"
+    missing.each do |gem_name|
+      version = optional_dependencies[gem_name]
+      instructions << "  gem '#{gem_name}', '#{version}'"
+    end
+    
+    instructions.join("\n")
+  end
+
   # Get list of available features based on installed dependencies
   def self.available_features
-    features = [:text_processing, :html_processing, :xml_processing, :csv_processing, :json_processing, :archive_processing]
+    features = [:text_processing, :html_processing, :xml_processing, :csv_processing, :json_processing, :archive_processing, :tsv_processing]
     
     features << :pdf_processing if dependency_available?(:pdf_reader)
     features << :word_processing if dependency_available?(:docx)
@@ -218,6 +293,14 @@ module UniversalDocumentProcessor
     features << :universal_text_extraction if dependency_available?(:yomu)
     features << :pdf_generation if dependency_available?(:prawn)
     
+    # Check AI availability without creating circular dependency
+    begin
+      ai_agent = AIAgent.new
+      features << :ai_processing if ai_agent.ai_enabled
+    rescue
+      # AI not available
+    end
+    
     features
   end
 end 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: universal_document_processor
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.3
 platform: ruby
 authors:
 - Vikas Patil
@@ -80,19 +80,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3.2'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '5.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '5.0'
+- !ruby/object:Gem::Dependency
+  name: minitest-reporters
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -149,6 +163,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.22'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.22'
 description: A comprehensive Ruby gem that handles document processing, text extraction,
   and AI-powered analysis for PDF, Word, Excel, PowerPoint, images, archives, and
   more with a unified API. Includes agentic AI features for document analysis, summarization,
@@ -190,6 +218,8 @@ metadata:
   documentation_uri: https://github.com/vpatil160/universal_document_processor/blob/main/README.md
   funding_uri: https://github.com/sponsors/vpatil160
   rubygems_mfa_required: 'true'
+  optional_dependencies: pdf-reader ~> 2.0, prawn ~> 2.4, docx ~> 0.8, roo ~> 2.8,
+    mini_magick ~> 4.11, yomu ~> 0.2
 rdoc_options: []
 require_paths:
 - lib