Add Rubocop rule to catch arrays of size > 300. Also fix a bunch of .rubocop_todo.yml (#2256)

* Add no-huge-arrays rule to fail on array or set literals over 300

* fix constant lookup in dynamically defined class

---------

Co-authored-by: jneen <[email protected]>

Author: jneen

.rubocop.yml

@@ -2,6 +2,7 @@ inherit_from: .rubocop_todo.yml
 
 require:
   - ./lib/rubocop/cop/rouge/no_building_alternation_pattern_in_regexp.rb
+  - ./lib/rubocop/cop/rouge/no_huge_collections.rb
 
 plugins:
   - rubocop-performance
@@ -18,6 +19,9 @@ AllCops:
     - "lib/rouge/lexers/**/builtins.rb"
   NewCops: enable
 
+Rouge:
+  Enabled: true
+
 Style:
   Enabled: false
 
@@ -76,12 +80,41 @@ Lint/IneffectiveAccessModifier:
 Lint/AmbiguousOperatorPrecedence:
   Enabled: false
 
+# this just is plain broken, disabling
+Lint/OutOfRangeRegexpRef:
+  Enabled: false
+
+# there are actual reasons to do this
+Lint/MissingSuper:
+  Enabled: false
+
+# sometimes the arguments are deprecated you guys
+Lint/ToEnumArguments:
+  Enabled: false
+
+# sometimes we deal with very gnarly strings, this is not useful
+Lint/NestedPercentLiteral:
+  Enabled: false
+
+# usually not actionable
+Lint/DuplicateBranch:
+  Enabled: false
+
 Naming/BlockForwarding:
   Enabled: false
 
 Naming/PredicateMethod:
   Enabled: false
 
+Naming/MethodParameterName:
+  Enabled: false
+
+Naming/HeredocDelimiterNaming:
+  Enabled: false
+
+Naming/VariableNumber:
+  Enabled: false
+
 Performance/RegexpMatch:
   Enabled: false
 

.rubocop_todo.yml

@@ -1,115 +1,23 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config --exclude-limit 50`
-# on 2026-02-27 15:13:26 UTC using RuboCop version 1.85.0.
+# on 2026-03-20 18:54:21 UTC using RuboCop version 1.84.2.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 8
-# Configuration parameters: AllowedMethods.
-# AllowedMethods: enums
-Lint/ConstantDefinitionInBlock:
-  Exclude:
-    - 'spec/formatters/html_spec.rb'
-    - 'spec/lexer_spec.rb'
-    - 'spec/theme_spec.rb'
-
-# Offense count: 38
-# Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
-Lint/DuplicateBranch:
-  Exclude:
-    - 'lib/rouge/cli.rb'
-    - 'lib/rouge/lexers/apache.rb'
-    - 'lib/rouge/lexers/apex.rb'
-    - 'lib/rouge/lexers/batchfile.rb'
-    - 'lib/rouge/lexers/brightscript.rb'
-    - 'lib/rouge/lexers/common_lisp.rb'
-    - 'lib/rouge/lexers/coq.rb'
-    - 'lib/rouge/lexers/css.rb'
-    - 'lib/rouge/lexers/cython.rb'
-    - 'lib/rouge/lexers/ecl.rb'
-    - 'lib/rouge/lexers/idlang.rb'
-    - 'lib/rouge/lexers/llvm.rb'
-    - 'lib/rouge/lexers/php.rb'
-    - 'lib/rouge/lexers/python.rb'
-    - 'lib/rouge/lexers/robot_framework.rb'
-    - 'lib/rouge/lexers/ruby.rb'
-    - 'lib/rouge/lexers/sas.rb'
-    - 'lib/rouge/lexers/sqf.rb'
-    - 'lib/rouge/lexers/stan.rb'
-    - 'lib/rouge/lexers/varnish.rb'
-    - 'lib/rouge/lexers/viml.rb'
-    - 'lib/rouge/lexers/yang.rb'
-
-# Offense count: 3
+# Offense count: 1
 # Configuration parameters: AllowComments, AllowEmptyLambdas.
 Lint/EmptyBlock:
   Exclude:
     - 'lib/rouge/lexers/nix.rb'
-    - 'spec/lexers/terraform_spec.rb'
-
-# Offense count: 27
-# Configuration parameters: AllowedParentClasses.
-Lint/MissingSuper:
-  Exclude:
-    - 'lib/rouge/cli.rb'
-    - 'lib/rouge/formatters/html_inline.rb'
-    - 'lib/rouge/formatters/html_legacy.rb'
-    - 'lib/rouge/formatters/html_line_highlighter.rb'
-    - 'lib/rouge/formatters/html_line_table.rb'
-    - 'lib/rouge/formatters/html_linewise.rb'
-    - 'lib/rouge/formatters/html_pygments.rb'
-    - 'lib/rouge/formatters/html_table.rb'
-    - 'lib/rouge/formatters/null.rb'
-    - 'lib/rouge/formatters/terminal256.rb'
-    - 'lib/rouge/formatters/tex.rb'
-    - 'lib/rouge/guesser.rb'
-    - 'lib/rouge/guessers/disambiguation.rb'
-    - 'lib/rouge/guessers/filename.rb'
-    - 'lib/rouge/guessers/glob_mapping.rb'
-    - 'lib/rouge/guessers/mimetype.rb'
-    - 'lib/rouge/guessers/modeline.rb'
-    - 'lib/rouge/guessers/source.rb'
-    - 'lib/rouge/regex_lexer.rb'
-    - 'lib/rouge/theme.rb'
-    - 'lib/rouge/util.rb'
 
 # Offense count: 4
-Lint/NestedPercentLiteral:
-  Exclude:
-    - 'lib/rouge/lexers/hylang.rb'
-    - 'lib/rouge/lexers/janet.rb'
-    - 'lib/rouge/lexers/powershell.rb'
-    - 'spec/lexers/j_spec.rb'
-
-# Offense count: 1
-Lint/OutOfRangeRegexpRef:
-  Exclude:
-    - 'lib/rouge/tex_theme_renderer.rb'
-
-# Offense count: 1
-Lint/ToEnumArguments:
-  Exclude:
-    - 'lib/rouge/lexer.rb'
-
-# Offense count: 43
 Naming/ConstantName:
   Exclude:
     - 'lib/rouge/lexers/eiffel.rb'
-    - 'lib/rouge/themes/gruvbox.rb'
-
-# Offense count: 8
-# Configuration parameters: ForbiddenDelimiters.
-# ForbiddenDelimiters: (?i-mx:(^|\s)(EO[A-Z]{1}|END)(\s|$))
-Naming/HeredocDelimiterNaming:
-  Exclude:
-    - 'lib/rouge/tex_theme_renderer.rb'
-    - 'spec/lexers/mason_spec.rb'
-    - 'spec/lexers/matlab_spec.rb'
-    - 'spec/lexers/swift_spec.rb'
 
-# Offense count: 8
+# Offense count: 5
 # This cop supports unsafe autocorrection (--autocorrect-all).
 # Configuration parameters: EnforcedStyleForLeadingUnderscores.
 # SupportedStylesForLeadingUnderscores: disallowed, required, optional
@@ -120,7 +28,6 @@ Naming/MemoizedInstanceVariableName:
     - 'lib/rouge/lexers/hack.rb'
     - 'lib/rouge/lexers/python.rb'
     - 'lib/rouge/lexers/verilog.rb'
-    - 'lib/rouge/lexers/yang.rb'
 
 # Offense count: 16
 # Configuration parameters: EnforcedStyle, AllowedPatterns, ForbiddenIdentifiers, ForbiddenPatterns.
@@ -131,35 +38,6 @@ Naming/MethodName:
     - 'lib/rouge/lexers/igorpro.rb'
     - 'lib/rouge/lexers/xpath.rb'
 
-# Offense count: 68
-# Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.
-# AllowedNames: as, at, by, cc, db, id, if, in, io, ip, of, on, os, pp, to
-Naming/MethodParameterName:
-  Exclude:
-    - 'lib/rouge.rb'
-    - 'lib/rouge/cli.rb'
-    - 'lib/rouge/formatter.rb'
-    - 'lib/rouge/formatters/html.rb'
-    - 'lib/rouge/formatters/html_legacy.rb'
-    - 'lib/rouge/formatters/html_line_table.rb'
-    - 'lib/rouge/formatters/html_linewise.rb'
-    - 'lib/rouge/formatters/html_pygments.rb'
-    - 'lib/rouge/formatters/html_table.rb'
-    - 'lib/rouge/formatters/null.rb'
-    - 'lib/rouge/formatters/terminal256.rb'
-    - 'lib/rouge/formatters/tex.rb'
-    - 'lib/rouge/guessers/disambiguation.rb'
-    - 'lib/rouge/lexer.rb'
-    - 'lib/rouge/lexers/coq.rb'
-    - 'lib/rouge/lexers/escape.rb'
-    - 'lib/rouge/lexers/plain_text.rb'
-    - 'lib/rouge/regex_lexer.rb'
-    - 'lib/rouge/tex_theme_renderer.rb'
-    - 'lib/rouge/theme.rb'
-    - 'lib/rouge/token.rb'
-    - 'lib/rouge/util.rb'
-    - 'spec/support/lexing.rb'
-
 # Offense count: 40
 # Configuration parameters: EnforcedStyle, AllowedIdentifiers, AllowedPatterns, ForbiddenIdentifiers, ForbiddenPatterns.
 # SupportedStyles: snake_case, camelCase
@@ -172,15 +50,6 @@ Naming/VariableName:
     - 'lib/rouge/lexers/kotlin.rb'
     - 'lib/rouge/lexers/xpath.rb'
 
-# Offense count: 5
-# Configuration parameters: EnforcedStyle, CheckMethodNames, CheckSymbols, AllowedIdentifiers, AllowedPatterns.
-# SupportedStyles: snake_case, normalcase, non_integer
-# AllowedIdentifiers: TLS1_1, TLS1_2, capture3, iso8601, rfc1123_date, rfc822, rfc2822, rfc3339, x86_64
-Naming/VariableNumber:
-  Exclude:
-    - 'lib/rouge/lexers/c.rb'
-    - 'lib/rouge/themes/gruvbox.rb'
-
 # Offense count: 2
 # This cop supports unsafe autocorrection (--autocorrect-all).
 Performance/StringInclude:
@@ -230,3 +99,24 @@ Rouge/NoBuildingAlternationPatternInRegexp:
     - 'lib/rouge/lexers/vala.rb'
     - 'lib/rouge/lexers/wollok.rb'
     - 'lib/rouge/lexers/xojo.rb'
+
+# Offense count: 20
+Rouge/NoHugeCollections:
+  Exclude:
+    - 'lib/rouge/lexers/abap.rb'
+    - 'lib/rouge/lexers/apple_script.rb'
+    - 'lib/rouge/lexers/cobol.rb'
+    - 'lib/rouge/lexers/common_lisp.rb'
+    - 'lib/rouge/lexers/css.rb'
+    - 'lib/rouge/lexers/datastudio.rb'
+    - 'lib/rouge/lexers/freefem.rb'
+    - 'lib/rouge/lexers/hql.rb'
+    - 'lib/rouge/lexers/idlang.rb'
+    - 'lib/rouge/lexers/igorpro.rb'
+    - 'lib/rouge/lexers/janet.rb'
+    - 'lib/rouge/lexers/openedge.rb'
+    - 'lib/rouge/lexers/plsql.rb'
+    - 'lib/rouge/lexers/racket.rb'
+    - 'lib/rouge/lexers/sas.rb'
+    - 'lib/rouge/lexers/sql.rb'
+    - 'lib/rouge/lexers/stata.rb'

lib/rouge/cli.rb

@@ -514,9 +514,7 @@ def run
       out = []
       argv.each do |arg|
         case arg
-        when /^(--\w+)=(.*)$/
-          out << $1 << $2
-        when /^(-\w)(.+)$/
+        when /^(--\w+)=(.*)$/, /^(-\w)(.+)$/
           out << $1 << $2
         else
           out << arg

lib/rouge/lexers/apache.rb

@@ -17,15 +17,11 @@ class Apache < RegexLexer
       end
 
       def name_for_token(token, tktype)
-        if SECTIONS.include? token
-          tktype
-        elsif DIRECTIVES.include? token
-          tktype
-        elsif VALUES.include? token
-          tktype
-        else
-          Text
-        end
+        return tktype if SECTIONS.include?(token)
+        return tktype if DIRECTIVES.include?(token)
+        return tktype if VALUES.include?(token)
+
+        Text
       end
 
       state :whitespace do

lib/rouge/lexers/viml.rb

@@ -49,11 +49,11 @@ class VimL < RegexLexer
 
           if KEYWORDS[:command].include? name
             token Keyword
-          elsif KEYWORDS[:function].include? name
-            token Name::Builtin
-          elsif KEYWORDS[:option].include? name
-            token Name::Builtin
-          elsif KEYWORDS[:auto].include? name
+          elsif (
+            KEYWORDS[:function].include?(name) ||
+            KEYWORDS[:option].include?(name) ||
+            KEYWORDS[:auto].include?(name)
+          )
             token Name::Builtin
           else
             token Text