universal_document_processor 1.0.1 → 1.0.3

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

@@ -5,8 +5,11 @@ module UniversalDocumentProcessor
         with_error_handling do
           if @file_path.end_with?('.docx')
             extract_docx_text
+          elsif @file_path.end_with?('.doc')
+            # Built-in .doc file processing
+            fallback_text_extraction
           else
-            # Fallback for .doc files
+            # Handle other Word formats
             fallback_text_extraction
           end
         end
@@ -16,6 +19,8 @@ module UniversalDocumentProcessor
         with_error_handling do
           if @file_path.end_with?('.docx')
             extract_docx_metadata
+          elsif @file_path.end_with?('.doc')
+            extract_doc_metadata
           else
             super
           end
@@ -25,6 +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)
@@ -48,6 +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)
@@ -73,12 +80,25 @@ module UniversalDocumentProcessor
       end
 
       def supported_operations
-        super + [:extract_images, :extract_tables, :extract_styles, :extract_comments]
+        if @file_path.end_with?('.docx')
+          super + [:extract_images, :extract_tables, :extract_styles, :extract_comments]
+        else
+          # .doc files support basic text and metadata extraction
+          super + [:extract_basic_formatting]
+        end
       end
 
       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 = []
         
@@ -99,6 +119,8 @@ module UniversalDocumentProcessor
       end
 
       def extract_docx_metadata
+        ensure_docx_available!
+        
         doc = Docx::Document.open(@file_path)
         core_properties = doc.core_properties
         
@@ -126,12 +148,80 @@ module UniversalDocumentProcessor
         0
       end
 
+      def extract_doc_metadata
+        # Extract basic metadata from .doc files
+        file_stats = File.stat(@file_path)
+        extracted_text = extract_doc_text_builtin
+        
+        super.merge({
+          format: 'Microsoft Word Document (.doc)',
+          word_count: count_words(extracted_text),
+          character_count: extracted_text.length,
+          created_at: file_stats.ctime,
+          modified_at: file_stats.mtime,
+          file_size: file_stats.size,
+          extraction_method: 'Built-in binary parsing'
+        })
+      rescue => e
+        super.merge({
+          format: 'Microsoft Word Document (.doc)',
+          extraction_error: e.message
+        })
+      end
+
       def fallback_text_extraction
-        # Use Yomu for .doc files or as fallback
-        Yomu.new(@file_path).text
+        # Built-in .doc file text extraction
+        extract_doc_text_builtin
       rescue => e
         "Unable to extract text from Word document: #{e.message}"
       end
+
+      def extract_doc_text_builtin
+        # Read .doc file as binary and extract readable text
+        content = File.binread(@file_path)
+        
+        # .doc files store text in a specific format - extract readable ASCII text
+        # This is a simplified extraction that works for basic .doc files
+        text_content = []
+        
+        # Look for text patterns in the binary data
+        # .doc files often have text stored with null bytes between characters
+        content.force_encoding('ASCII-8BIT').scan(/[\x20-\x7E\x0A\x0D]{4,}/) do |match|
+          # Clean up the extracted text
+          cleaned_text = match.gsub(/[\x00-\x1F\x7F-\xFF]/n, ' ').strip
+          text_content << cleaned_text if cleaned_text.length > 3
+        end
+        
+        # Try alternative extraction method if first method yields little text
+        if text_content.join(' ').length < 50
+          text_content = extract_doc_alternative_method(content)
+        end
+        
+        result = text_content.join("\n").strip
+        result.empty? ? "Text extracted from .doc file (content may be limited due to complex formatting)" : result
+      end
+
+      def extract_doc_alternative_method(content)
+        # Alternative method: look for Word document text patterns
+        text_parts = []
+        
+        # .doc files often have text in UTF-16 or with specific markers
+        # Try to find readable text segments
+        content.force_encoding('UTF-16LE').encode('UTF-8', invalid: :replace, undef: :replace).scan(/[[:print:]]{5,}/m) do |match|
+          cleaned = match.strip
+          text_parts << cleaned if cleaned.length > 4 && !cleaned.match?(/^[\x00-\x1F]*$/)
+        end
+        
+        # If UTF-16 doesn't work, try scanning for ASCII patterns
+        if text_parts.empty?
+          content.force_encoding('ASCII-8BIT').scan(/[a-zA-Z0-9\s\.\,\!\?\;\:]{10,}/n) do |match|
+            cleaned = match.strip
+            text_parts << cleaned if cleaned.length > 9
+          end
+        end
+        
+        text_parts.uniq
+      end
     end
   end
 end 

data/lib/universal_document_processor/utils/file_detector.rb

@@ -15,6 +15,7 @@ module UniversalDocumentProcessor
         'htm' => 'text/html',
         'xml' => 'application/xml',
         'csv' => 'text/csv',
+        'tsv' => 'text/tab-separated-values',
         'json' => 'application/json',
         'jpg' => 'image/jpeg',
         'jpeg' => 'image/jpeg',

data/lib/universal_document_processor/version.rb

@@ -1,3 +1,3 @@
 module UniversalDocumentProcessor
-  VERSION = "1.0.1"
+  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: 1.0.1
+  version: 1.0.3
 platform: ruby
 authors:
 - Vikas Patil
@@ -66,19 +66,47 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.3'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: rexml
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: '3.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        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
@@ -135,6 +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,
@@ -145,9 +187,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- AI_USAGE_GUIDE.md
 - CHANGELOG.md
-- GEM_RELEASE_GUIDE.md
 - Gemfile
 - LICENSE
 - README.md
@@ -178,6 +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