synthra 0.1.0

data/scripts/fix_syntax_errors.rb

@@ -0,0 +1,108 @@
+#!/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)
+  original = content.dup
+  
+  # Fix common issues:
+  # 1. Missing 'end' for methods
+  # 2. Missing 'end' for classes
+  # 3. Bad indentation
+  
+  lines = content.lines
+  fixed = []
+  in_class = false
+  in_method = false
+  class_indent = 0
+  method_indent = 0
+  depth = 0
+  
+  lines.each_with_index do |line, idx|
+    stripped = line.strip
+    
+    # Track class start
+    if stripped =~ /^class\s+\w+\s*<\s*Base/
+      if in_class
+        # Close previous class
+        fixed << "    end\n"
+      end
+      in_class = true
+      class_indent = line[/\A */].size
+      fixed << line
+      depth = 1
+      next
+    end
+    
+    # Track method start
+    if stripped =~ /^\s*def\s+\w+/
+      in_method = true
+      method_indent = line[/\A */].size
+      fixed << line
+      depth += 1
+      next
+    end
+    
+    # Track 'end' statements
+    if stripped == 'end'
+      if depth > 0
+        depth -= 1
+        if depth == 0 && in_class
+          in_class = false
+          fixed << "    end\n"
+        else
+          fixed << line
+        end
+      else
+        fixed << line
+      end
+      next
+    end
+    
+    # Fix indentation for method bodies
+    if in_method && line.strip != '' && !line.strip.start_with?('#')
+      current_indent = line[/\A */].size
+      if current_indent < method_indent + 2
+        fixed << "      #{line.lstrip}"
+      else
+        fixed << line
+      end
+    else
+      fixed << line
+    end
+  end
+  
+  # Close any open classes
+  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")
+    puts "✅ Fixed #{File.basename(file_path)}"
+    true
+  else
+    puts "❌ Still has errors in #{File.basename(file_path)}:"
+    puts result.split("\n").first(3).join("\n")
+    false
+  end
+end
+
+# Fix all grouped files
+Dir.glob(File.join(BASE, '*/*.rb')).each do |file|
+  fix_file(file)
+end
+
+puts "\n✅ Fixed syntax errors in grouped files"

data/scripts/group_domain_types.rb

@@ -0,0 +1,112 @@
+#!/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 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"
+  
+  file_names.each do |file_name|
+    file_path = File.join(domain_dir, "#{file_name}.rb")
+    next unless File.exist?(file_path)
+    
+    content = File.read(file_path)
+    # Extract class definition (everything between class and end)
+    if content =~ /class\s+(\w+)\s*<\s*Base\s*\n(.*?)\n\s*end/m
+      class_name = $1
+      class_body = $2
+      merged_content += "\n    # #{class_name} type\n"
+      merged_content += "    class #{class_name} < Base\n"
+      merged_content += class_body.gsub(/^/, '      ') + "\n"
+      merged_content += "    end\n"
+    end
+  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} (#{file_names.size} types)"
+  
+  # Delete individual files
+  file_names.each do |file_name|
+    file_path = File.join(domain_dir, "#{file_name}.rb")
+    File.delete(file_path) if File.exist?(file_path)
+  end
+end
+
+puts "📁 Grouping types within domain folders...\n"
+
+total_files = 0
+DOMAIN_GROUPS.each do |domain, groups|
+  puts "\n📂 #{domain}/"
+  groups.each do |group_file, file_names|
+    merge_files(domain, group_file, file_names)
+    total_files += 1
+  end
+end
+
+puts "\n✅ Total grouped files: #{total_files}"
+puts "✅ Individual files removed, types grouped logically"
+

data/scripts/group_domain_types_fixed.rb

@@ -0,0 +1,150 @@
+#!/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_class_content(file_path)
+  return nil unless File.exist?(file_path)
+  
+  content = File.read(file_path)
+  # Extract everything from class definition to matching end
+  if content =~ /class\s+(\w+)\s*<\s*Base\s*\n(.*?)\n\s*end\s*$/m
+    class_name = $1
+    class_body = $2
+    
+    # Clean up the class body - remove module wrapper if present
+    class_body = class_body.gsub(/^\s*module\s+FakeDataDSL\s*\n\s*module\s+Types\s*\n/, '')
+    class_body = class_body.gsub(/\n\s*end\s*\n\s*end\s*$/, '')
+    
+    # Extract YARD comments if present
+    yard_comment = ''
+    if content =~ /(#{Regexp.escape("    #")}.*?\n)(?=\s*class\s+#{class_name})/m
+      yard_comment = $1
+    end
+    
+    { name: class_name, body: class_body, comment: yard_comment }
+  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"
+  
+  file_names.each do |file_name|
+    file_path = File.join(domain_dir, "#{file_name}.rb")
+    class_info = extract_class_content(file_path)
+    next unless class_info
+    
+    # Add class with proper indentation
+    merged_content += "\n"
+    merged_content += class_info[:comment] if class_info[:comment] && !class_info[:comment].empty?
+    merged_content += "    class #{class_info[:name]} < Base\n"
+    # Indent class body by 6 spaces (2 for module + 2 for class + 2 for method)
+    class_body_lines = class_info[:body].lines
+    class_body_lines.each do |line|
+      if line.strip.empty?
+        merged_content += "\n"
+      else
+        # Preserve relative indentation, but ensure minimum 6 spaces
+        current_indent = line[/\A */].size
+        if current_indent >= 4
+          merged_content += "      #{line.lstrip}\n"
+        else
+          merged_content += "      #{line}\n"
+        end
+      end
+    end
+    merged_content += "    end\n"
+  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} (#{file_names.size} types)"
+  
+  # Delete individual files
+  file_names.each do |file_name|
+    file_path = File.join(domain_dir, "#{file_name}.rb")
+    File.delete(file_path) if File.exist?(file_path)
+  end
+end
+
+# First, restore individual files from grouped files if they exist
+# (in case we need to re-run)
+puts "📁 Grouping types within domain folders...\n"
+
+total_files = 0
+DOMAIN_GROUPS.each do |domain, groups|
+  puts "\n📂 #{domain}/"
+  groups.each do |group_file, file_names|
+    merge_files(domain, group_file, file_names)
+    total_files += 1
+  end
+end
+
+puts "\n✅ Total grouped files: #{total_files}"
+puts "✅ Individual files removed, types grouped logically"
+

data/scripts/merge_domains_to_one_file.rb

@@ -0,0 +1,68 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Get all domain folders
+domains = Dir.glob(File.join(BASE, '*')).select { |f| File.directory?(f) && File.basename(f) != 'types' }.map { |f| File.basename(f) }
+
+domains.each do |domain|
+  domain_dir = File.join(BASE, domain)
+  next unless Dir.exist?(domain_dir)
+  
+  puts "📂 Merging #{domain}/ into #{domain}.rb"
+  
+  merged = "# frozen_string_literal: true\n\nmodule FakeDataDSL\n  module Types\n"
+  
+  # Read all .rb files in domain, sorted
+  files = Dir.glob(File.join(domain_dir, '*.rb')).sort
+  class_count = 0
+  
+  files.each do |file|
+    content = File.read(file)
+    
+    # Extract each class definition
+    content.scan(/class\s+(\w+)\s*<\s*Base\s*\n(.*?)(?=\n\s*class\s+\w+\s*<\s*Base|\n\s*end\s*$|\Z)/m) do |class_name, class_body|
+      merged += "\n    # #{class_name} type\n"
+      merged += "    class #{class_name} < Base\n"
+      
+      # Fix indentation - ensure methods are indented by 6 spaces
+      class_body.lines.each do |line|
+        if line.strip.empty?
+          merged += "\n"
+        else
+          # Remove leading whitespace and add proper indent
+          stripped = line.lstrip
+          # Skip module/end lines
+          next if stripped =~ /^(module|end)\s*$/
+          merged += "      #{stripped}\n"
+        end
+      end
+      
+      merged += "    end\n"
+      class_count += 1
+    end
+  end
+  
+  merged += "  end\nend\n"
+  
+  # Write merged file to types root
+  output = File.join(BASE, "#{domain}.rb")
+  File.write(output, merged)
+  
+  # Verify syntax
+  result = `ruby -c "#{output}" 2>&1`
+  if result.include?("Syntax OK")
+    # Delete domain folder
+    FileUtils.rm_rf(domain_dir)
+    puts "  ✅ Created #{domain}.rb (#{class_count} classes from #{files.size} files)"
+  else
+    puts "  ❌ Syntax error in #{domain}.rb:"
+    puts result
+  end
+end
+
+puts "\n✅ All domains merged into single files!"
+puts "📊 Final count: #{Dir.glob(File.join(BASE, '*.rb')).count} files in types/"

data/scripts/move_existing_types.rb

@@ -0,0 +1,130 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'fileutils'
+
+BASE = File.join(__dir__, '..', 'lib', 'fake_data_dsl', 'types')
+
+# Map existing individual files to domain folders
+MAPPINGS = {
+  # Address & Location
+  'address.rb' => 'address_location',
+  'city.rb' => 'address_location',
+  'state.rb' => 'address_location',
+  'country.rb' => 'address_location',
+  'country_code.rb' => 'address_location',
+  'postal_code.rb' => 'address_location',
+  'latitude.rb' => 'address_location',
+  'longitude.rb' => 'address_location',
+  'timezone.rb' => 'address_location',
+  
+  # Finance & Banking
+  'money.rb' => 'finance_banking',
+  'currency.rb' => 'finance_banking',
+  'credit_card.rb' => 'finance_banking',
+  'bank_name.rb' => 'finance_banking',
+  'account_number.rb' => 'finance_banking',
+  'iban.rb' => 'finance_banking',
+  'transaction_amount.rb' => 'finance_banking',
+  
+  # Personal & Names
+  'name.rb' => 'personal_names',
+  'first_name.rb' => 'personal_names',
+  'last_name.rb' => 'personal_names',
+  'full_name.rb' => 'personal_names',
+  'username.rb' => 'personal_names',
+  'age.rb' => 'personal_names',
+  'gender.rb' => 'personal_names',
+  'national_id.rb' => 'personal_names',
+  
+  # Technology & Internet
+  'email.rb' => 'technology_internet',
+  'phone.rb' => 'technology_internet',
+  'url.rb' => 'technology_internet',
+  'domain.rb' => 'technology_internet',
+  'user_agent.rb' => 'technology_internet',
+  'ip.rb' => 'technology_internet',
+  'mac_address.rb' => 'technology_internet',
+  
+  # Commerce & Products
+  'product_name.rb' => 'commerce_products',
+  'product_category.rb' => 'commerce_products',
+  'sku.rb' => 'commerce_products',
+  'discount.rb' => 'commerce_products',
+  'tax_rate.rb' => 'commerce_products',
+  'company_name.rb' => 'commerce_products',
+  'job_title.rb' => 'commerce_products',
+  
+  # Health & Medical
+  'blood_type.rb' => 'health_medical',
+  'bmi.rb' => 'health_medical',
+  'heart_rate.rb' => 'health_medical',
+  'medical_code.rb' => 'health_medical',
+  
+  # Travel
+  'airline.rb' => 'travel',
+  'airport_code.rb' => 'travel',
+  'flight_number.rb' => 'travel',
+  'seat_number.rb' => 'travel',
+  
+  # Date & Time
+  'date_type.rb' => 'date_time',
+  'datetime_type.rb' => 'date_time',
+  'time_type.rb' => 'date_time',
+  'timestamp.rb' => 'date_time',
+  'past_date.rb' => 'date_time',
+  'future_date.rb' => 'date_time',
+  'date_between.rb' => 'date_time',
+  'now.rb' => 'date_time',
+  
+  # Crypto
+  'bitcoin_address.rb' => 'crypto',
+  'ethereum_address.rb' => 'crypto',
+  'private_key.rb' => 'crypto',
+  'hash_type.rb' => 'crypto',
+  
+  # Core (keep in root)
+  'base.rb' => nil,
+  'registry.rb' => nil,
+  'text.rb' => nil,
+  'number.rb' => nil,
+  'boolean.rb' => nil,
+  'enum.rb' => nil,
+  'array_type.rb' => nil,
+  'object_type.rb' => nil,
+  'custom.rb' => nil,
+  'reference.rb' => nil,
+  'formula.rb' => nil,
+  'template.rb' => nil,
+  'regex.rb' => nil,
+  'sequence.rb' => nil,
+  'default_value.rb' => nil,
+  'character_sequence.rb' => nil,
+  'digit_sequence.rb' => nil,
+  'id_sequence.rb' => nil,
+  'uuid.rb' => nil,
+  'ulid.rb' => nil,
+  'json_array.rb' => nil,
+  'naughty_string.rb' => nil,
+  'repeating_element.rb' => nil,
+  'scenario.rb' => nil
+}
+
+moved = 0
+MAPPINGS.each do |file, domain|
+  source = File.join(BASE, file)
+  next unless File.exist?(source)
+  
+  if domain
+    target_dir = File.join(BASE, domain)
+    target = File.join(target_dir, file)
+    FileUtils.mkdir_p(target_dir)
+    FileUtils.mv(source, target)
+    puts "✅ Moved #{file} -> #{domain}/#{file}"
+    moved += 1
+  else
+    puts "⏭️  Keeping #{file} in root (core type)"
+  end
+end
+
+puts "\n✅ Moved #{moved} files to domain folders"