universal_document_processor 1.0.2 → 1.0.5

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/document.rb

@@ -222,7 +222,11 @@ module UniversalDocumentProcessor
 
     def fallback_text_extraction
       begin
-        Yomu.new(@file_path).text
+        if defined?(Yomu)
+          Yomu.new(@file_path).text
+        else
+          "Unable to extract text: Yomu gem not available. Please install 'yomu' gem for universal text extraction: gem install yomu"
+        end
       rescue => e
         "Unable to extract text: #{e.message}"
       end

data/lib/universal_document_processor/processors/base_processor.rb

@@ -10,7 +10,11 @@ module UniversalDocumentProcessor
 
       def extract_text
         # Fallback to universal text extraction
-        Yomu.new(@file_path).text
+        if defined?(Yomu)
+          Yomu.new(@file_path).text
+        else
+          raise ProcessingError, "Universal text extraction requires the 'yomu' gem. Install it with: gem install yomu -v '~> 0.2'"
+        end
       rescue => e
         raise ProcessingError, "Failed to extract text: #{e.message}"
       end

data/lib/universal_document_processor/processors/pdf_processor.rb

@@ -2,14 +2,21 @@ 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")
           text.strip.empty? ? "No text content found in PDF" : text
         end
+      rescue => e
+        # Fallback to Yomu if pdf-reader fails
+        fallback_text_extraction(e)
       end
 
       def extract_metadata
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           reader = PDF::Reader.new(@file_path)
           info = reader.info || {}
@@ -32,6 +39,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_images
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           # Extract embedded images from PDF
           images = []
@@ -57,6 +66,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_tables
+        ensure_pdf_reader_available!
+        
         with_error_handling do
           # Basic table extraction from PDF text
           tables = []
@@ -87,6 +98,12 @@ 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
         []
@@ -100,6 +117,20 @@ module UniversalDocumentProcessor
       rescue
         []
       end
+
+      def fallback_text_extraction(original_error)
+        if defined?(Yomu)
+          begin
+            text = Yomu.new(@file_path).text
+            return text unless text.nil? || text.strip.empty?
+            "No text content found in PDF"
+          rescue => yomu_error
+            raise ProcessingError, "PDF text extraction failed. pdf-reader error: #{original_error.message}. Yomu fallback error: #{yomu_error.message}"
+          end
+        else
+          raise ProcessingError, "PDF text extraction failed: #{original_error.message}. Consider installing 'yomu' gem for fallback extraction: gem install yomu"
+        end
+      end
     end
   end
 end 

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 = "1.0.5"
 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 

data/test_ai_dependency.rb

@@ -0,0 +1,80 @@
+#!/usr/bin/env ruby
+
+# Add lib directory to load path
+$LOAD_PATH.unshift File.expand_path('lib', __dir__)
+
+# Load the gem
+require 'universal_document_processor'
+
+puts "Testing AI Dependency Handling"
+puts "=" * 50
+
+# Test 1: Check AI availability without API key
+puts "\n1. Testing AI availability without API key:"
+ai_available = UniversalDocumentProcessor.ai_available?
+puts "   AI Available: #{ai_available}"
+
+# Test 2: Create AI agent without API key
+puts "\n2. Creating AI agent without API key:"
+agent = UniversalDocumentProcessor.create_ai_agent
+puts "   Agent created: #{agent.class}"
+puts "   AI enabled: #{agent.ai_enabled}"
+puts "   AI available: #{agent.ai_available?}"
+
+# Test 3: Try to use AI methods without API key
+puts "\n3. Testing AI methods without API key:"
+
+# Create a sample text file
+require 'tempfile'
+sample_file = Tempfile.new(['test', '.txt'])
+sample_file.write("This is a test document for AI processing.")
+sample_file.close
+
+begin
+  result = UniversalDocumentProcessor.ai_analyze(sample_file.path)
+  puts "   ERROR: Should have raised an exception!"
+rescue UniversalDocumentProcessor::DependencyMissingError => e
+  puts "   ✓ Correctly raised DependencyMissingError: #{e.message}"
+rescue => e
+  puts "   ✗ Unexpected error: #{e.class} - #{e.message}"
+end
+
+# Test 4: Check available features
+puts "\n4. Available features:"
+features = UniversalDocumentProcessor.available_features
+puts "   Features: #{features.join(', ')}"
+puts "   AI processing included: #{features.include?(:ai_processing)}"
+
+# Test 5: Check optional dependencies
+puts "\n5. Optional dependencies:"
+optional_deps = UniversalDocumentProcessor.optional_dependencies
+puts "   Optional dependencies: #{optional_deps.keys.join(', ')}"
+
+missing_deps = UniversalDocumentProcessor.missing_dependencies
+puts "   Missing dependencies: #{missing_deps.join(', ')}"
+
+# Test 6: Installation instructions
+puts "\n6. Installation instructions:"
+instructions = UniversalDocumentProcessor.installation_instructions
+puts instructions
+
+# Test 7: Test with API key if provided
+if ENV['OPENAI_API_KEY'] && !ENV['OPENAI_API_KEY'].empty?
+  puts "\n7. Testing with API key:"
+  ai_available_with_key = UniversalDocumentProcessor.ai_available?
+  puts "   AI Available with key: #{ai_available_with_key}"
+  
+  agent_with_key = UniversalDocumentProcessor.create_ai_agent
+  puts "   Agent AI enabled: #{agent_with_key.ai_enabled}"
+else
+  puts "\n7. Skipping API key test (OPENAI_API_KEY not set)"
+end
+
+# Clean up
+sample_file.unlink
+
+puts "\n" + "=" * 50
+puts "AI Dependency Test Complete!"
+puts "✓ AI features are properly optional"
+puts "✓ Clear error messages when dependencies missing"
+puts "✓ Graceful degradation when features unavailable"