synthra 0.1.0

data/scripts/batch_fix_all.rb

@@ -0,0 +1,96 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Read each broken file, extract classes, and rewrite properly
+Dir.glob(File.join(BASE, '*/*.rb')).sort.each do |file_path|
+  next if File.basename(file_path) == 'national_id.rb' # Already fixed
+  
+  content = File.read(file_path)
+  
+  # Extract all class definitions with their bodies
+  classes = []
+  content.scan(/class\s+(\w+)\s*<\s*Base\s*\n(.*?)(?=\n\s*class\s+\w+\s*<\s*Base|\n\s*end\s*$|\Z)/m) do |class_name, class_body|
+    classes << { name: class_name, body: class_body }
+  end
+  
+  # If no classes found, try a different pattern
+  if classes.empty?
+    # Try to find classes by looking for "class Name < Base" patterns
+    lines = content.lines
+    current_class = nil
+    class_lines = []
+    in_class = false
+    
+    lines.each do |line|
+      if line =~ /class\s+(\w+)\s*<\s*Base/
+        if current_class
+          classes << { name: current_class, body: class_lines.join }
+        end
+        current_class = $1
+        class_lines = []
+        in_class = true
+      elsif in_class
+        if line.strip == 'end' && class_lines.count { |l| l.strip == 'end' } >= 1
+          # End of class
+          classes << { name: current_class, body: class_lines.join }
+          current_class = nil
+          in_class = false
+          class_lines = []
+        else
+          class_lines << line
+        end
+      end
+    end
+    
+    if current_class && !class_lines.empty?
+      classes << { name: current_class, body: class_lines.join }
+    end
+  end
+  
+  # Rebuild file
+  if !classes.empty?
+    rebuilt = "# frozen_string_literal: true\n\nmodule FakeDataDSL\n  module Types\n"
+    
+    classes.each do |cls|
+      rebuilt += "\n    # #{cls[:name]} type\n"
+      rebuilt += "    class #{cls[:name]} < Base\n"
+      
+      # Fix indentation of class body
+      cls[:body].lines.each do |line|
+        if line.strip.empty?
+          rebuilt += "\n"
+        elsif line.strip.start_with?('#')
+          rebuilt += "      #{line.lstrip}\n"
+        else
+          # Ensure proper indentation (6 spaces for method body)
+          current_indent = line[/\A */].size
+          if current_indent < 6 && line.strip != 'end'
+            rebuilt += "      #{line.lstrip}\n"
+          else
+            rebuilt += line
+          end
+        end
+      end
+      
+      rebuilt += "    end\n"
+    end
+    
+    rebuilt += "  end\nend\n"
+    
+    File.write(file_path, rebuilt)
+    
+    # Verify
+    result = `ruby -c "#{file_path}" 2>&1`
+    if result.include?("Syntax OK")
+      puts "  ✅ #{File.basename(File.dirname(file_path))}/#{File.basename(file_path)}"
+    else
+      puts "  ❌ #{File.basename(File.dirname(file_path))}/#{File.basename(file_path)}"
+    end
+  end
+end
+
+puts "✅ Batch fix complete"

data/scripts/delete_old_files.rb

@@ -0,0 +1,32 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Delete old grouped files
+old_files = %w[
+  address_location_types.rb
+  finance_banking_types.rb
+  technology_internet_types.rb
+  commerce_product_types.rb
+  media_entertainment_types.rb
+  personal_names_types.rb
+  text_content_types.rb
+  datetime.rb
+  hash.rb
+  time.rb
+]
+
+deleted = 0
+old_files.each do |file|
+  path = File.join(BASE, file)
+  if File.exist?(path)
+    File.delete(path)
+    puts "✅ Deleted #{file}"
+    deleted += 1
+  end
+end
+
+puts "\n✅ Deleted #{deleted} old files"

data/scripts/fix_all_grouped_files.rb

@@ -0,0 +1,137 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+def fix_grouped_file(file_path)
+  content = File.read(file_path)
+  lines = content.lines
+  fixed = []
+  in_class = false
+  in_method = false
+  class_name = nil
+  method_name = nil
+  depth = 0
+  class_indent = 0
+  
+  i = 0
+  while i < lines.length
+    line = lines[i]
+    stripped = line.strip
+    indent = line[/\A */].size
+    
+    # Class definition
+    if stripped =~ /^class\s+(\w+)\s*<\s*Base/
+      if in_class
+        # Close previous class
+        fixed << "    end\n"
+      end
+      class_name = $1
+      in_class = true
+      in_method = false
+      class_indent = indent
+      fixed << "    class #{class_name} < Base\n"
+      depth = 1
+      i += 1
+      next
+    end
+    
+    # Method definition
+    if stripped =~ /^\s*def\s+(\w+)/
+      method_name = $1
+      in_method = true
+      # Ensure proper indentation (6 spaces for method in class)
+      fixed << "      #{stripped}\n"
+      depth += 1
+      i += 1
+      next
+    end
+    
+    # 'end' statement
+    if stripped == 'end'
+      if depth > 0
+        depth -= 1
+        if depth == 0 && in_class
+          in_class = false
+          in_method = false
+          fixed << "    end\n"
+        else
+          # Method or block end
+          fixed << "      end\n"
+        end
+      else
+        fixed << line
+      end
+      i += 1
+      next
+    end
+    
+    # Regular line - fix indentation
+    if in_class
+      if stripped.empty?
+        fixed << "\n"
+      elsif stripped.start_with?('#')
+        # Comments - preserve relative indentation but ensure minimum
+        if indent >= class_indent
+          fixed << "      #{stripped}\n"
+        else
+          fixed << "      #{line.lstrip}\n"
+        end
+      else
+        # Code - ensure 6 space indent (2 for module + 2 for class + 2 for method)
+        if indent < 6 && !stripped.start_with?('#')
+          fixed << "      #{line.lstrip}\n"
+        else
+          fixed << line
+        end
+      end
+    else
+      fixed << line
+    end
+    
+    i += 1
+  end
+  
+  # Close any open class
+  if in_class
+    fixed << "    end\n"
+  end
+  
+  # Ensure module ends
+  if fixed.join !~ /\n\s*end\s*\n\s*end\s*$/
+    fixed << "  end\nend\n"
+  end
+  
+  File.write(file_path, fixed.join)
+  
+  # Verify syntax
+  result = `ruby -c "#{file_path}" 2>&1`
+  if result.include?("Syntax OK")
+    true
+  else
+    puts "  ❌ #{File.basename(file_path)}: #{result.split("\n").first}"
+    false
+  end
+end
+
+puts "🔧 Fixing syntax errors in grouped files...\n"
+
+fixed_count = 0
+error_count = 0
+
+Dir.glob(File.join(BASE, '*/*.rb')).sort.each do |file|
+  domain = File.basename(File.dirname(file))
+  filename = File.basename(file)
+  
+  if fix_grouped_file(file)
+    puts "  ✅ #{domain}/#{filename}"
+    fixed_count += 1
+  else
+    error_count += 1
+  end
+end
+
+puts "\n✅ Fixed: #{fixed_count} files"
+puts "❌ Errors: #{error_count} files" if error_count > 0

data/scripts/fix_all_indentation.rb

@@ -0,0 +1,48 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Fix indentation in all domain folder files
+Dir.glob(File.join(BASE, '*/*.rb')).each do |file|
+  content = File.read(file)
+  original = content.dup
+  
+  # Check if class definition is not properly indented
+  if content =~ /^class\s+\w+\s*<\s*Base/ || content =~ /^\s{0,3}class\s+\w+\s*<\s*Base/
+    lines = content.lines
+    fixed = []
+    in_class = false
+    class_indent = 4  # 4 spaces for class in module
+    
+    lines.each_with_index do |line, idx|
+      # Module/end lines
+      if line =~ /^module\s+FakeDataDSL/ || line =~ /^module\s+Types/
+        fixed << line
+      elsif line =~ /^end\s*$/ && !in_class && idx > 0 && lines[idx-1] !~ /^\s+end/
+        fixed << line
+      # Class definition
+      elsif line =~ /^\s*class\s+(\w+)\s*<\s*Base/
+        fixed << "    class #{$1} < Base\n"
+        in_class = true
+      # End of class
+      elsif line =~ /^\s*end\s*$/ && in_class
+        fixed << "    end\n"
+        in_class = false
+      # Inside class - indent by 6 spaces (2 for module + 2 for class + 2 for method)
+      elsif in_class
+        # Remove leading whitespace and add proper indent
+        fixed << "      #{line.lstrip}"
+      else
+        fixed << line
+      end
+    end
+    
+    File.write(file, fixed.join)
+    puts "✅ Fixed #{File.basename(File.dirname(file))}/#{File.basename(file)}"
+  end
+end
+
+puts "✅ Fixed indentation in all domain folder files"

data/scripts/fix_all_syntax.rb

@@ -0,0 +1,124 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+def fix_file(file_path)
+  content = File.read(file_path)
+  lines = content.lines
+  fixed = []
+  
+  in_class = false
+  class_name = nil
+  class_start_idx = nil
+  depth = 0
+  
+  i = 0
+  while i < lines.length
+    line = lines[i]
+    stripped = line.strip
+    
+    # Class definition
+    if stripped =~ /^class\s+(\w+)\s*<\s*Base/
+      if in_class
+        # Close previous class
+        fixed << "    end\n"
+      end
+      class_name = $1
+      in_class = true
+      class_start_idx = i
+      fixed << "    class #{class_name} < Base\n"
+      depth = 1
+      i += 1
+      next
+    end
+    
+    # Method definition
+    if stripped =~ /^\s*def\s+(\w+)/
+      fixed << "      #{stripped}\n"
+      depth += 1
+      i += 1
+      next
+    end
+    
+    # 'end' statement
+    if stripped == 'end'
+      if depth > 1
+        depth -= 1
+        fixed << "      end\n"
+      elsif depth == 1 && in_class
+        depth = 0
+        in_class = false
+        fixed << "    end\n"
+      else
+        fixed << line
+      end
+      i += 1
+      next
+    end
+    
+    # Regular line
+    if in_class
+      if stripped.empty?
+        fixed << "\n"
+      elsif stripped.start_with?('#')
+        fixed << "      #{stripped}\n"
+      else
+        # Code line - ensure proper indentation
+        current_indent = line[/\A */].size
+        if current_indent < 6
+          fixed << "      #{line.lstrip}\n"
+        else
+          fixed << line
+        end
+      end
+    else
+      fixed << line
+    end
+    
+    i += 1
+  end
+  
+  # Close any open class
+  if in_class
+    fixed << "    end\n"
+  end
+  
+  # Ensure module ends
+  if fixed.join !~ /\n\s*end\s*\n\s*end\s*$/
+    fixed << "  end\nend\n"
+  end
+  
+  File.write(file_path, fixed.join)
+  
+  # Verify syntax
+  result = `ruby -c "#{file_path}" 2>&1`
+  if result.include?("Syntax OK")
+    true
+  else
+    puts "  ❌ #{File.basename(file_path)}: #{result.split("\n").first(2).join(' ')}"
+    false
+  end
+end
+
+puts "🔧 Fixing all grouped files...\n"
+
+fixed = 0
+errors = 0
+
+Dir.glob(File.join(BASE, '*/*.rb')).sort.each do |file|
+  domain = File.basename(File.dirname(file))
+  filename = File.basename(file)
+  
+  if fix_file(file)
+    puts "  ✅ #{domain}/#{filename}"
+    fixed += 1
+  else
+    errors += 1
+  end
+end
+
+puts "\n✅ Fixed: #{fixed} files"
+puts "❌ Errors: #{errors} files" if errors > 0

data/scripts/fix_grouped_files.rb

@@ -0,0 +1,184 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Group types within each domain into logical files
+DOMAIN_GROUPS = {
+  'address_location' => {
+    'addresses.rb' => %w[address address_line_2 street_name street_number street_suffix],
+    'locations.rb' => %w[city state country country_code postal_code latitude longitude timezone],
+    'airports.rb' => %w[airport_name airport_continent airport_country_code airport_elevation airport_gps_code airport_latitude airport_longitude airport_municipality airport_region_code],
+    'banks_hospitals.rb' => %w[bank_city bank_country_code bank_street_address bank_state hospital_city hospital_postal_code hospital_state hospital_street_address]
+  },
+  'finance_banking' => {
+    'identifiers.rb' => %w[ssn ein national_id nhs_number medicare_beneficiary_id duns_number],
+    'banking.rb' => %w[money currency credit_card bank_name account_number iban bank_routing_number bank_swift_bic bank_lei bank_riad_code transaction_amount],
+    'credit_cards.rb' => %w[credit_card_type]
+  },
+  'personal_names' => {
+    'names.rb' => %w[name first_name last_name full_name first_name_female first_name_male first_name_european],
+    'identifiers.rb' => %w[username age gender gender_abbrev gender_binary gender_facebook],
+    'titles_suffixes.rb' => %w[title suffix],
+    'chinese.rb' => %w[family_name_chinese given_name_chinese]
+  },
+  'technology_internet' => {
+    'communication.rb' => %w[email phone url domain user_agent],
+    'networking.rb' => %w[ip mac_address ip_v4_cidr ip_v6_cidr],
+    'apps.rb' => %w[app_bundle_id app_name app_version],
+    'devices.rb' => %w[mobile_device_brand mobile_device_model mobile_device_os mobile_device_release_date],
+    'formats.rb' => %w[language language_code mime_type top_level_domain base64_image_url dummy_image_url mongodb_object_id]
+  },
+  'commerce_products' => {
+    'products.rb' => %w[product_name product_category product_description product_price product_subcategory product_grocery sku],
+    'companies.rb' => %w[company_name job_title],
+    'commerce.rb' => %w[discount tax_rate shirt_size],
+    'construction.rb' => %w[construction_heavy_equipment construction_material construction_role construction_standard_cost_code construction_subcontract_category construction_trade]
+  },
+  'text_content' => {
+    'text_generation.rb' => %w[paragraphs sentences words],
+    'business.rb' => %w[buzzword catch_phrase slogan fake_company_name],
+    'colors.rb' => %w[color hex_color short_hex_color],
+    'security.rb' => %w[password password_hash md5 sha1 sha256 encrypt],
+    'misc.rb' => %w[avatar file_name frequency linked_in_skill nato_phonetic row_number sql_expression university blank race department_corporate department_retail]
+  },
+  'health_medical' => {
+    'medical.rb' => %w[blood_type bmi heart_rate medical_code]
+  },
+  'travel' => {
+    'travel.rb' => %w[airline airport_code flight_number seat_number]
+  },
+  'date_time' => {
+    'dates.rb' => %w[date_type datetime_type time_type timestamp now past_date future_date date_between]
+  },
+  'crypto' => {
+    'crypto.rb' => %w[bitcoin_address ethereum_address private_key hash_type]
+  },
+  'media_entertainment' => {
+    'media.rb' => %w[movie_genres movie_title]
+  }
+}
+
+def extract_complete_class(file_path)
+  return nil unless File.exist?(file_path)
+  
+  content = File.read(file_path)
+  
+  # Find class definition
+  if content =~ /class\s+(\w+)\s*<\s*Base/
+    class_name = $1
+    class_start = content.index(/class\s+#{class_name}\s*<\s*Base/)
+    
+    # Find matching end by tracking indentation
+    lines = content.lines
+    start_line_idx = content[0..class_start].lines.count - 1
+    class_indent = lines[start_line_idx][/\A */].size
+    
+    depth = 1
+    end_line_idx = start_line_idx + 1
+    
+    while end_line_idx < lines.length && depth > 0
+      line = lines[end_line_idx]
+      line_indent = line[/\A */].size
+      
+      if line =~ /^\s*class\s+\w+\s*<\s*Base/
+        depth += 1
+      elsif line =~ /^\s*end\s*$/ && line_indent <= class_indent
+        depth -= 1
+        break if depth == 0
+      end
+      end_line_idx += 1
+    end
+    
+    if depth == 0
+      class_content = lines[start_line_idx..end_line_idx].join
+      # Remove leading module wrapper if present
+      class_content = class_content.gsub(/^\s*module\s+FakeDataDSL\s*\n\s*module\s+Types\s*\n/, '')
+      class_content = class_content.gsub(/\n\s*end\s*\n\s*end\s*$/, '')
+      { name: class_name, content: class_content }
+    else
+      nil
+    end
+  else
+    nil
+  end
+end
+
+def merge_files(domain, group_name, file_names)
+  domain_dir = File.join(BASE, domain)
+  return unless Dir.exist?(domain_dir)
+  
+  merged_content = "# frozen_string_literal: true\n\nmodule FakeDataDSL\n  module Types\n"
+  
+  found_count = 0
+  file_names.each do |file_name|
+    # Try both snake_case variations
+    file_paths = [
+      File.join(domain_dir, "#{file_name}.rb"),
+      File.join(domain_dir, "#{file_name.gsub('_', '')}.rb")
+    ]
+    
+    class_info = nil
+    file_paths.each do |path|
+      if File.exist?(path)
+        class_info = extract_complete_class(path)
+        break if class_info
+      end
+    end
+    
+    next unless class_info
+    
+    # Add class with proper formatting
+    merged_content += "\n"
+    # Extract and add class definition, fixing indentation
+    class_lines = class_info[:content].lines
+    class_lines.each do |line|
+      if line.strip.empty?
+        merged_content += "\n"
+      else
+        # Ensure proper indentation (6 spaces for class body)
+        current_indent = line[/\A */].size
+        if line =~ /^\s*class\s+\w+\s*<\s*Base/
+          merged_content += "    #{line.lstrip}"
+        elsif line =~ /^\s*end\s*$/ && current_indent <= 4
+          merged_content += "    end\n"
+        else
+          # Preserve relative indentation but ensure minimum
+          if current_indent >= 4
+            merged_content += "      #{line.lstrip}\n"
+          else
+            merged_content += "      #{line}\n"
+          end
+        end
+      end
+    end
+    found_count += 1
+  end
+  
+  merged_content += "  end\nend\n"
+  
+  output_path = File.join(domain_dir, group_name)
+  File.write(output_path, merged_content)
+  puts "  ✅ Created #{domain}/#{group_name} (#{found_count}/#{file_names.size} types)"
+  
+  found_count
+end
+
+puts "📁 Fixing grouped files...\n"
+
+total_files = 0
+total_types = 0
+DOMAIN_GROUPS.each do |domain, groups|
+  puts "\n📂 #{domain}/"
+  groups.each do |group_file, file_names|
+    count = merge_files(domain, group_file, file_names)
+    total_files += 1
+    total_types += count if count
+  end
+end
+
+puts "\n✅ Total grouped files: #{total_files}"
+puts "✅ Total types grouped: #{total_types}"
+