rubocop 0.93.1 → 1.79.2

data/lib/rubocop/cop/naming/inclusive_language.rb

@@ -0,0 +1,297 @@
+# frozen_string_literal: true
+
+module RuboCop
+  module Cop
+    module Naming
+      # Recommends the use of inclusive language instead of problematic terms.
+      # The cop can check the following locations for offenses:
+      #
+      # - identifiers
+      # - constants
+      # - variables
+      # - strings
+      # - symbols
+      # - comments
+      # - file paths
+      #
+      # Each of these locations can be individually enabled/disabled via configuration,
+      # for example CheckIdentifiers = true/false.
+      #
+      # Flagged terms are configurable for the cop. For each flagged term an optional
+      # Regex can be specified to identify offenses. Suggestions for replacing a flagged term can
+      # be configured and will be displayed as part of the offense message.
+      # An AllowedRegex can be specified for a flagged term to exempt allowed uses of the term.
+      # `WholeWord: true` can be set on a flagged term to indicate the cop should only match when
+      # a term matches the whole word (partial matches will not be offenses).
+      #
+      # The cop supports autocorrection when there is only one suggestion. When there are multiple
+      # suggestions, the best suggestion cannot be identified and will not be autocorrected.
+      #
+      # @example FlaggedTerms: { whitelist: { Suggestions: ['allowlist'] } }
+      #   # Suggest replacing identifier whitelist with allowlist
+      #
+      #   # bad
+      #   whitelist_users = %w(user1 user1)
+      #
+      #   # good
+      #   allowlist_users = %w(user1 user2)
+      #
+      # @example FlaggedTerms: { master: { Suggestions: ['main', 'primary', 'leader'] } }
+      #   # Suggest replacing master in an instance variable name with main, primary, or leader
+      #
+      #   # bad
+      #   @master_node = 'node1.example.com'
+      #
+      #   # good
+      #   @primary_node = 'node1.example.com'
+      #
+      # @example FlaggedTerms: { whitelist: { Regex: !ruby/regexp '/white[-_\s]?list' } }
+      #   # Identify problematic terms using a Regexp
+      #
+      #   # bad
+      #   white_list = %w(user1 user2)
+      #
+      #   # good
+      #   allow_list = %w(user1 user2)
+      #
+      # @example FlaggedTerms: { master: { AllowedRegex: 'master\'?s degree' } }
+      #   # Specify allowed uses of the flagged term as a string or regexp.
+      #
+      #   # bad
+      #   # They had a masters
+      #
+      #   # good
+      #   # They had a master's degree
+      #
+      # @example FlaggedTerms: { slave: { WholeWord: true } }
+      #   # Specify that only terms that are full matches will be flagged.
+      #
+      #   # bad
+      #   Slave
+      #
+      #   # good (won't be flagged despite containing `slave`)
+      #   TeslaVehicle
+      class InclusiveLanguage < Base
+        include RangeHelp
+        extend AutoCorrector
+
+        EMPTY_ARRAY = [].freeze
+        MSG = "Consider replacing '%<term>s'%<suffix>s."
+        MSG_FOR_FILE_PATH = "Consider replacing '%<term>s' in file path%<suffix>s."
+
+        WordLocation = Struct.new(:word, :position)
+
+        def initialize(config = nil, options = nil)
+          super
+          @flagged_term_hash = {}
+          @flagged_terms_regex = nil
+          @allowed_regex = nil
+          @check_token = preprocess_check_config
+          preprocess_flagged_terms
+        end
+
+        def on_new_investigation
+          investigate_filepath if cop_config['CheckFilepaths']
+          investigate_tokens
+        end
+
+        private
+
+        def investigate_tokens
+          processed_source.tokens.each do |token|
+            next unless check_token?(token.type)
+
+            word_locations = scan_for_words(token.text)
+            next if word_locations.empty?
+
+            add_offenses_for_token(token, word_locations)
+          end
+        end
+
+        def add_offenses_for_token(token, word_locations)
+          word_locations.each do |word_location|
+            word = word_location.word
+            range = offense_range(token, word)
+
+            add_offense(range, message: create_message(word)) do |corrector|
+              suggestions = find_flagged_term(word)['Suggestions']
+
+              if (preferred_term = preferred_sole_term(suggestions))
+                corrector.replace(range, preferred_term)
+              end
+            end
+          end
+        end
+
+        def check_token?(type)
+          !!@check_token[type]
+        end
+
+        def preprocess_check_config # rubocop:disable Metrics/AbcSize
+          {
+            tIDENTIFIER: cop_config['CheckIdentifiers'],
+            tCONSTANT: cop_config['CheckConstants'],
+            tIVAR: cop_config['CheckVariables'],
+            tCVAR: cop_config['CheckVariables'],
+            tGVAR: cop_config['CheckVariables'],
+            tSYMBOL: cop_config['CheckSymbols'],
+            tSTRING: cop_config['CheckStrings'],
+            tSTRING_CONTENT: cop_config['CheckStrings'],
+            tCOMMENT: cop_config['CheckComments']
+          }.freeze
+        end
+
+        def preprocess_flagged_terms
+          allowed_strings = []
+          flagged_term_strings = []
+          cop_config['FlaggedTerms'].each do |term, term_definition|
+            next if term_definition.nil?
+
+            allowed_strings.concat(process_allowed_regex(term_definition['AllowedRegex']))
+            regex_string = ensure_regex_string(extract_regexp(term, term_definition))
+            flagged_term_strings << regex_string
+
+            add_to_flagged_term_hash(regex_string, term, term_definition)
+          end
+
+          set_regexes(flagged_term_strings, allowed_strings)
+        end
+
+        def preferred_sole_term(suggestions)
+          case suggestions
+          when Array
+            suggestions.one? && preferred_sole_term(suggestions.first)
+          when String
+            suggestions
+          end
+        end
+
+        def extract_regexp(term, term_definition)
+          return term_definition['Regex'] if term_definition['Regex']
+          return /(?:\b|(?<=[\W_]))#{term}(?:\b|(?=[\W_]))/ if term_definition['WholeWord']
+
+          term
+        end
+
+        def add_to_flagged_term_hash(regex_string, term, term_definition)
+          @flagged_term_hash[Regexp.new(regex_string, Regexp::IGNORECASE)] =
+            term_definition.merge('Term' => term,
+                                  'SuggestionString' =>
+                                    preprocess_suggestions(term_definition['Suggestions']))
+        end
+
+        def set_regexes(flagged_term_strings, allowed_strings)
+          @flagged_terms_regex = array_to_ignorecase_regex(flagged_term_strings)
+          @allowed_regex = array_to_ignorecase_regex(allowed_strings) unless allowed_strings.empty?
+        end
+
+        def process_allowed_regex(allowed)
+          return EMPTY_ARRAY if allowed.nil?
+
+          Array(allowed).map do |allowed_term|
+            next if allowed_term.is_a?(String) && allowed_term.strip.empty?
+
+            ensure_regex_string(allowed_term)
+          end
+        end
+
+        def ensure_regex_string(regex)
+          regex.is_a?(Regexp) ? regex.source : regex
+        end
+
+        def array_to_ignorecase_regex(strings)
+          Regexp.new(strings.join('|'), Regexp::IGNORECASE)
+        end
+
+        def investigate_filepath
+          word_locations = scan_for_words(processed_source.file_path)
+
+          case word_locations.length
+          when 0
+            return
+          when 1
+            message = create_single_word_message_for_file(word_locations.first.word)
+          else
+            words = word_locations.map(&:word)
+            message = create_multiple_word_message_for_file(words)
+          end
+
+          add_global_offense(message)
+        end
+
+        def create_single_word_message_for_file(word)
+          create_message(word, MSG_FOR_FILE_PATH)
+        end
+
+        def create_multiple_word_message_for_file(words)
+          format(MSG_FOR_FILE_PATH, term: words.join("', '"), suffix: ' with other terms')
+        end
+
+        def scan_for_words(input)
+          masked_input = mask_input(input)
+          return EMPTY_ARRAY unless masked_input.match?(@flagged_terms_regex)
+
+          masked_input.enum_for(:scan, @flagged_terms_regex).map do
+            match = Regexp.last_match
+            WordLocation.new(match.to_s, match.offset(0).first)
+          end
+        end
+
+        def mask_input(str)
+          safe_str = if str.valid_encoding?
+                       str
+                     else
+                       str.encode('UTF-8', invalid: :replace, undef: :replace)
+                     end
+
+          return safe_str if @allowed_regex.nil?
+
+          safe_str.gsub(@allowed_regex) { |match| '*' * match.size }
+        end
+
+        def create_message(word, message = MSG)
+          flagged_term = find_flagged_term(word)
+          suggestions = flagged_term['SuggestionString']
+          suggestions = ' with another term' if suggestions.blank?
+
+          format(message, term: word, suffix: suggestions)
+        end
+
+        def find_flagged_term(word)
+          _regexp, flagged_term = @flagged_term_hash.find do |key, _term|
+            key.match?(word)
+          end
+          flagged_term
+        end
+
+        def preprocess_suggestions(suggestions)
+          return '' if suggestions.nil? ||
+                       (suggestions.is_a?(String) && suggestions.strip.empty?) || suggestions.empty?
+
+          format_suggestions(suggestions)
+        end
+
+        def format_suggestions(suggestions)
+          quoted_suggestions = Array(suggestions).map { |word| "'#{word}'" }
+          suggestion_str = case quoted_suggestions.size
+                           when 1
+                             quoted_suggestions.first
+                           when 2
+                             quoted_suggestions.join(' or ')
+                           else
+                             last_quoted = quoted_suggestions.pop
+                             quoted_suggestions << "or #{last_quoted}"
+                             quoted_suggestions.join(', ')
+                           end
+          " with #{suggestion_str}"
+        end
+
+        def offense_range(token, word)
+          start_position = token.pos.begin_pos + token.pos.source.index(word)
+
+          range_between(start_position, start_position + word.length)
+        end
+      end
+    end
+  end
+end

data/lib/rubocop/cop/naming/memoized_instance_variable_name.rb

@@ -3,8 +3,10 @@
 module RuboCop
   module Cop
     module Naming
-      # This cop checks for memoized methods whose instance variable name
-      # does not match the method name.
+      # Checks for memoized methods whose instance variable name
+      # does not match the method name. Applies to both regular methods
+      # (defined with `def`) and dynamic methods (defined with
+      # `define_method` or `define_singleton_method`).
       #
       # This cop can be configured with the EnforcedStyleForLeadingUnderscores
       # directive. It can be configured to allow for memoized instance variables
@@ -12,6 +14,12 @@ module RuboCop
       # convention that is used to implicitly indicate that an ivar should not
       # be set or referenced outside of the memoization method.
       #
+      # @safety
+      #   This cop relies on the pattern `@instance_var ||= ...`,
+      #   but this is sometimes used for other purposes than memoization
+      #   so this cop is considered unsafe. Also, its autocorrection is unsafe
+      #   because it may conflict with instance variable names already in use.
+      #
       # @example EnforcedStyleForLeadingUnderscores: disallowed (default)
       #   # bad
       #   # Method foo is memoized using an instance variable that is
@@ -20,6 +28,11 @@ module RuboCop
       #     @something ||= calculate_expensive_thing
       #   end
       #
+      #   def foo
+      #     return @something if defined?(@something)
+      #     @something = calculate_expensive_thing
+      #   end
+      #
       #   # good
       #   def _foo
       #     @foo ||= calculate_expensive_thing
@@ -43,6 +56,17 @@ module RuboCop
       #     @foo ||= calculate_expensive_thing(helper_variable)
       #   end
       #
+      #   # good
+      #   define_method(:foo) do
+      #     @foo ||= calculate_expensive_thing
+      #   end
+      #
+      #   # good
+      #   define_method(:foo) do
+      #     return @foo if defined?(@foo)
+      #     @foo = calculate_expensive_thing
+      #   end
+      #
       # @example EnforcedStyleForLeadingUnderscores: required
       #   # bad
       #   def foo
@@ -54,6 +78,11 @@ module RuboCop
       #     @foo ||= calculate_expensive_thing
       #   end
       #
+      #   def foo
+      #     return @foo if defined?(@foo)
+      #     @foo = calculate_expensive_thing
+      #   end
+      #
       #   # good
       #   def foo
       #     @_foo ||= calculate_expensive_thing
@@ -64,6 +93,22 @@ module RuboCop
       #     @_foo ||= calculate_expensive_thing
       #   end
       #
+      #   def foo
+      #     return @_foo if defined?(@_foo)
+      #     @_foo = calculate_expensive_thing
+      #   end
+      #
+      #   # good
+      #   define_method(:foo) do
+      #     @_foo ||= calculate_expensive_thing
+      #   end
+      #
+      #   # good
+      #   define_method(:foo) do
+      #     return @_foo if defined?(@_foo)
+      #     @_foo = calculate_expensive_thing
+      #   end
+      #
       # @example EnforcedStyleForLeadingUnderscores :optional
       #   # bad
       #   def foo
@@ -84,40 +129,109 @@ module RuboCop
       #   def _foo
       #     @_foo ||= calculate_expensive_thing
       #   end
+      #
+      #   # good
+      #   def foo
+      #     return @_foo if defined?(@_foo)
+      #     @_foo = calculate_expensive_thing
+      #   end
+      #
+      #   # good
+      #   define_method(:foo) do
+      #     @foo ||= calculate_expensive_thing
+      #   end
+      #
+      #   # good
+      #   define_method(:foo) do
+      #     @_foo ||= calculate_expensive_thing
+      #   end
       class MemoizedInstanceVariableName < Base
+        extend AutoCorrector
+
         include ConfigurableEnforcedStyle
 
         MSG = 'Memoized variable `%<var>s` does not match ' \
-          'method name `%<method>s`. Use `@%<suggested_var>s` instead.'
+              'method name `%<method>s`. Use `@%<suggested_var>s` instead.'
         UNDERSCORE_REQUIRED = 'Memoized variable `%<var>s` does not start ' \
-          'with `_`. Use `@%<suggested_var>s` instead.'
-
-        def self.node_pattern
-          memo_assign = '(or_asgn $(ivasgn _) _)'
-          memoized_at_end_of_method = "(begin ... #{memo_assign})"
-          instance_method =
-            "(def $_ _ {#{memo_assign} #{memoized_at_end_of_method}})"
-          class_method =
-            "(defs self $_ _ {#{memo_assign} #{memoized_at_end_of_method}})"
-          "{#{instance_method} #{class_method}}"
-        end
+                              'with `_`. Use `@%<suggested_var>s` instead.'
+        DYNAMIC_DEFINE_METHODS = %i[define_method define_singleton_method].to_set.freeze
+        INITIALIZE_METHODS = %i[initialize initialize_clone initialize_copy initialize_dup].freeze
+
+        # @!method method_definition?(node)
+        def_node_matcher :method_definition?, <<~PATTERN
+          ${
+            (block (send _ %DYNAMIC_DEFINE_METHODS ({sym str} $_)) ...)
+            (def $_ ...)
+            (defs _ $_ ...)
+          }
+        PATTERN
+
+        # rubocop:disable Metrics/AbcSize
+        # rubocop:disable Metrics/MethodLength
+        def on_or_asgn(node)
+          lhs = node.lhs
+          return unless lhs.ivasgn_type?
+
+          method_node, method_name = find_definition(node)
+          return unless method_node
 
-        private_class_method :node_pattern
-        def_node_matcher :memoized?, node_pattern
+          body = method_node.body
+          return unless body == node || body.children.last == node
 
-        def on_def(node)
-          (method_name, ivar_assign) = memoized?(node)
-          return if matches?(method_name, ivar_assign)
+          return if matches?(method_name, lhs)
 
+          suggested_var = suggested_var(method_name)
           msg = format(
-            message(ivar_assign.children.first.to_s),
-            var: ivar_assign.children.first.to_s,
-            suggested_var: suggested_var(method_name),
+            message(lhs.name),
+            var: lhs.name,
+            suggested_var: suggested_var,
             method: method_name
           )
-          add_offense(ivar_assign.source_range, message: msg)
+          add_offense(lhs, message: msg) do |corrector|
+            corrector.replace(lhs.loc.name, "@#{suggested_var}")
+          end
         end
-        alias on_defs on_def
+        # rubocop:enable Metrics/MethodLength
+        # rubocop:enable Metrics/AbcSize
+
+        # @!method defined_memoized?(node, ivar)
+        def_node_matcher :defined_memoized?, <<~PATTERN
+          (begin
+            (if (defined $(ivar %1)) (return $(ivar %1)) nil?)
+            ...
+            $(ivasgn %1 _))
+        PATTERN
+
+        # rubocop:disable Metrics/AbcSize, Metrics/MethodLength
+        def on_defined?(node)
+          arg = node.first_argument
+          return false unless arg.ivar_type?
+
+          method_node, method_name = find_definition(node)
+          return false unless method_node
+
+          defined_memoized?(method_node.body, arg.name) do |defined_ivar, return_ivar, ivar_assign|
+            return false if matches?(method_name, ivar_assign)
+
+            suggested_var = suggested_var(method_name)
+            msg = format(
+              message(arg.name),
+              var: arg.name,
+              suggested_var: suggested_var,
+              method: method_name
+            )
+            add_offense(defined_ivar, message: msg) do |corrector|
+              corrector.replace(defined_ivar, "@#{suggested_var}")
+            end
+            add_offense(return_ivar, message: msg) do |corrector|
+              corrector.replace(return_ivar, "@#{suggested_var}")
+            end
+            add_offense(ivar_assign.loc.name, message: msg) do |corrector|
+              corrector.replace(ivar_assign.loc.name, "@#{suggested_var}")
+            end
+          end
+        end
+        # rubocop:enable Metrics/AbcSize, Metrics/MethodLength
 
         private
 
@@ -125,12 +239,22 @@ module RuboCop
           'EnforcedStyleForLeadingUnderscores'
         end
 
+        def find_definition(node)
+          # Methods can be defined in a `def` or `defs`,
+          # or dynamically via a `block` node.
+          node.each_ancestor(:any_def, :block).each do |ancestor|
+            method_node, method_name = method_definition?(ancestor)
+            return [method_node, method_name] if method_node
+          end
+
+          nil
+        end
+
         def matches?(method_name, ivar_assign)
-          return true if ivar_assign.nil? || method_name == :initialize
+          return true if ivar_assign.nil? || INITIALIZE_METHODS.include?(method_name)
 
-          method_name = method_name.to_s.delete('!?')
-          variable = ivar_assign.children.first
-          variable_name = variable.to_s.sub('@', '')
+          method_name = method_name.to_s.delete('!?=')
+          variable_name = ivar_assign.name.to_s.sub('@', '')
 
           variable_name_candidates(method_name).include?(variable_name)
         end
@@ -138,20 +262,19 @@ module RuboCop
         def message(variable)
           variable_name = variable.to_s.sub('@', '')
 
-          return UNDERSCORE_REQUIRED if style == :required &&
-                                        !variable_name.start_with?('_')
+          return UNDERSCORE_REQUIRED if style == :required && !variable_name.start_with?('_')
 
           MSG
         end
 
         def suggested_var(method_name)
-          suggestion = method_name.to_s.delete('!?')
+          suggestion = method_name.to_s.delete('!?=')
 
           style == :required ? "_#{suggestion}" : suggestion
         end
 
         def variable_name_candidates(method_name)
-          no_underscore = method_name.sub(/\A_/, '')
+          no_underscore = method_name.delete_prefix('_')
           with_underscore = "_#{method_name}"
           case style
           when :required