woods 1.5.0 → 1.6.0

data/lib/woods/extractors/factory_extractor.rb

@@ -35,9 +35,7 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of factory units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].flat_map { |file| extract_factory_file(file) }
-        end
+        find_files_in_directories(@directories).flat_map { |file| extract_factory_file(file) }
       end
 
       # Extract factory definitions from a single factory file.
@@ -282,7 +280,7 @@ module Woods
           deps << { type: :factory, target: assoc, via: :factory_association }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/graphql_extractor.rb

@@ -770,7 +770,7 @@ module Woods
           deps << { type: :graphql_resolver, target: resolver, via: :field_resolver }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
 
       # ──────────────────────────────────────────────────────────────────────

data/lib/woods/extractors/i18n_extractor.rb

@@ -2,6 +2,8 @@
 
 require 'yaml'
 
+require_relative 'shared_utility_methods'
+
 module Woods
   module Extractors
     # I18nExtractor handles internationalization locale file extraction.
@@ -16,6 +18,8 @@ module Woods
     #   en = units.find { |u| u.identifier == "en.yml" }
     #
     class I18nExtractor
+      include SharedUtilityMethods
+
       # Directories to scan for locale files
       I18N_DIRECTORIES = %w[
         config/locales
@@ -30,10 +34,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of i18n units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.yml')].filter_map do |file|
-            extract_i18n_file(file)
-          end
+        find_files_in_directories(@directories, '**/*.yml').filter_map do |file|
+          extract_i18n_file(file)
         end
       end
 

data/lib/woods/extractors/job_extractor.rb

@@ -46,11 +46,9 @@ module Woods
         units = []
 
         # File-based discovery (catches everything)
-        @directories.each do |dir|
-          Dir[dir.join('**/*.rb')].each do |file|
-            unit = extract_job_file(file)
-            units << unit if unit
-          end
+        find_files_in_directories(@directories).each do |file|
+          unit = extract_job_file(file)
+          units << unit if unit
         end
 
         # Also try class-based discovery for ActiveJob
@@ -356,7 +354,7 @@ module Woods
 
         deps << { type: :infrastructure, target: :redis, via: :code_reference } if source.match?(/Redis\.current|REDIS/)
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
 
       # Scan source for job class enqueue calls and return the list of enqueued job names.

data/lib/woods/extractors/lib_extractor.rb

@@ -211,7 +211,7 @@ module Woods
       # @return [Array<Hash>] Dependency hashes with :type, :target, :via
       def extract_dependencies(source)
         deps = scan_common_dependencies(source)
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/mailer_extractor.rb

@@ -243,7 +243,7 @@ module Woods
           deps << { type: :route, target: route, via: :url_helper }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
 
       # ──────────────────────────────────────────────────────────────────────

data/lib/woods/extractors/manager_extractor.rb

@@ -40,10 +40,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of manager units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].filter_map do |file|
-            extract_manager_file(file)
-          end
+        find_files_in_directories(@directories).filter_map do |file|
+          extract_manager_file(file)
         end
       end
 
@@ -181,7 +179,7 @@ module Woods
 
         deps.concat(scan_common_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/migration_extractor.rb

@@ -462,7 +462,7 @@ module Woods
         # Scan data migration code for common dependencies
         deps.concat(scan_common_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/model_extractor.rb

@@ -501,7 +501,7 @@ module Woods
               options: v.options.except(:if, :unless, :on),
               conditions: format_validation_conditions(v)
             }
-            entry[:implicit_belongs_to] = true if implicit_belongs_to_validator?(v)
+            entry[:implicit_belongs_to] = true if implicit_belongs_to_validator?(model, v)
             entry
           end
         end
@@ -654,7 +654,7 @@ module Woods
           end
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
 
       # Enrich callback metadata with side-effect analysis.
@@ -922,17 +922,30 @@ module Woods
         conditions
       end
 
-      # Detect Rails-generated implicit belongs_to presence validators
+      # Detect Rails-generated implicit belongs_to presence validators.
       #
+      # `belongs_to` (with belongs_to_required_by_default, Rails 5+)
+      # registers an ActiveRecord PresenceValidator on the association
+      # attribute. Reflection offers no declaration provenance — the
+      # validator class and its #validate source_location are identical for
+      # an explicit `validates :assoc, presence: true` — so this flags any
+      # AR presence validator whose attributes are all belongs_to
+      # association names. (The previous source_location heuristic matched
+      # EVERY AR presence validator, since PresenceValidator#validate is
+      # always defined in the gem, never under Rails.root.)
+      #
+      # @param model [Class] The ActiveRecord model class
       # @param validator [ActiveModel::Validator]
       # @return [Boolean]
-      def implicit_belongs_to_validator?(validator)
-        if defined?(ActiveRecord::Validations::PresenceValidator) && !validator.is_a?(ActiveRecord::Validations::PresenceValidator)
-          return false
-        end
+      def implicit_belongs_to_validator?(model, validator)
+        return false unless defined?(ActiveRecord::Validations::PresenceValidator)
+        return false unless validator.is_a?(ActiveRecord::Validations::PresenceValidator)
+
+        belongs_to_names = model.reflect_on_all_associations(:belongs_to).map { |r| r.name.to_sym }
+        return false if belongs_to_names.empty?
 
-        loc = validator.class.instance_method(:validate).source_location&.first
-        loc && !loc.start_with?(Rails.root.to_s)
+        attributes = validator.respond_to?(:attributes) ? Array(validator.attributes) : []
+        attributes.any? && attributes.all? { |a| belongs_to_names.include?(a.to_sym) }
       rescue StandardError
         false
       end
@@ -975,7 +988,10 @@ module Woods
 
       def callback_count(model)
         %i[validation save create update destroy commit rollback].sum do |type|
-          model.send("_#{type}_callbacks").size
+          # CallbackChain includes Enumerable but defines no #size on any
+          # supported Rails version — #size raises and the rescue would
+          # zero the count. #count is the only correct API here.
+          model.send("_#{type}_callbacks").count
         rescue StandardError
           0
         end

data/lib/woods/extractors/phlex_extractor.rb

@@ -254,7 +254,7 @@ module Woods
         deps.concat(scan_navigation_dependencies(source))
         deps.concat(scan_form_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/policy_extractor.rb

@@ -43,10 +43,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of policy units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].filter_map do |file|
-            extract_policy_file(file)
-          end
+        find_files_in_directories(@directories).filter_map do |file|
+          extract_policy_file(file)
         end
       end
 
@@ -184,7 +182,7 @@ module Woods
         deps.concat(scan_service_dependencies(source))
         deps.concat(scan_job_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/poro_extractor.rb

@@ -222,7 +222,7 @@ module Woods
       # @return [Array<Hash>] Dependency hashes with :type, :target, :via
       def extract_dependencies(source)
         deps = scan_common_dependencies(source)
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/pundit_extractor.rb

@@ -38,10 +38,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of Pundit policy units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].filter_map do |file|
-            extract_pundit_file(file)
-          end
+        find_files_in_directories(@directories).filter_map do |file|
+          extract_pundit_file(file)
         end
       end
 
@@ -216,7 +214,7 @@ module Woods
         deps.concat(scan_model_dependencies(source))
         deps.concat(scan_service_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/rake_task_extractor.rb

@@ -34,9 +34,7 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of rake task units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rake')].flat_map { |file| extract_rake_file(file) }
-        end
+        find_files_in_directories(@directories, '**/*.rake').flat_map { |file| extract_rake_file(file) }
       end
 
       # Extract rake tasks from a single .rake file.
@@ -336,7 +334,7 @@ module Woods
           deps << { type: :rake_task, target: dep, via: :task_dependency }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/serializer_extractor.rb

@@ -52,11 +52,9 @@ module Woods
         units = []
 
         # File-based discovery (catches everything in known directories)
-        @directories.each do |dir|
-          Dir[dir.join('**/*.rb')].each do |file|
-            unit = extract_serializer_file(file)
-            units << unit if unit
-          end
+        find_files_in_directories(@directories).each do |file|
+          unit = extract_serializer_file(file)
+          units << unit if unit
         end
 
         # Class-based discovery for loaded gems
@@ -332,7 +330,7 @@ module Woods
 
         deps.concat(scan_service_dependencies(source))
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/service_extractor.rb

@@ -44,10 +44,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of service units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].filter_map do |file|
-            extract_service_file(file)
-          end
+        find_files_in_directories(@directories).filter_map do |file|
+          extract_service_file(file)
         end
       end
 
@@ -210,7 +208,7 @@ module Woods
           deps << { type: :infrastructure, target: :redis, via: :code_reference }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/shared_dependency_scanner.rb

@@ -23,7 +23,7 @@ module Woods
     #     def extract_dependencies(source)
     #       deps = scan_common_dependencies(source)
     #       deps << { type: :custom, target: "Bar", via: :special }
-    #       deps.uniq { |d| [d[:type], d[:target]] }
+    #       consolidate_dependencies(deps)
     #     end
     #   end
     #
@@ -45,22 +45,27 @@ module Woods
       # @param via [Symbol] Relationship label (default: :code_reference)
       # @return [Array<Hash>] Dependency hashes with :type, :target, :via
       def scan_model_dependencies(source, via: :code_reference)
+        # Strip `#` line comments before scanning so references inside
+        # YARD docstrings / TODO comments don't generate ghost edges.
+        # Applied to ALL passes — a commented `Library::Book` should not
+        # produce an edge through the full-name pass. Stripping is
+        # string-literal-aware: a `#` inside a `"..."`/`'...'` literal is
+        # NOT a comment, so a line like `link_to "Tag #ruby", Article.recent`
+        # keeps its `Article` reference (a plain `#...` regex would have
+        # eaten the rest of the line and dropped the edge). String
+        # interpolation (`"Book: #{Library::Book.new}"`) is preserved for the
+        # same reason — the `#{...}` lives inside the literal.
+        scannable = strip_ruby_line_comments(source)
+
         targets = Set.new
-        source.scan(ModelNameCache.model_names_regex).each { |m| targets << m }
-        extract_constantize_targets(source).each { |t| targets << t }
+        scannable.scan(ModelNameCache.model_names_regex).each { |m| targets << m }
+        extract_constantize_targets(scannable).each { |t| targets << t }
 
         # Short-name + constantize resolution are additive passes guarded
         # by `respond_to?` so partial test doubles that only stub
         # `model_names_regex` still work. Real extraction runs always
         # have the full API.
         if ModelNameCache.respond_to?(:short_names_regex) && ModelNameCache.respond_to?(:resolve_short_name)
-          # Strip `#` line comments before scanning so references inside
-          # YARD docstrings / TODO comments don't generate ghost edges.
-          # The negative lookahead `(?!\{)` keeps Ruby's `#{...}` string
-          # interpolation intact — stripping blindly would eat every model
-          # reference inside `"Book: #{Library::Book.new}"` etc., which
-          # is a common ERB/Phlex/string pattern.
-          scannable = source.gsub(/#(?!\{)[^\n]*/, '')
           scannable.scan(ModelNameCache.short_names_regex).each do |short|
             resolved = ModelNameCache.resolve_short_name(short)
             targets << resolved if resolved
@@ -70,6 +75,58 @@ module Woods
         targets.map { |model_name| { type: :model, target: model_name, via: via } }
       end
 
+      # Remove `#` line comments from Ruby source without touching `#`
+      # characters that sit inside single- or double-quoted string literals.
+      #
+      # A naive `gsub(/#.*/, '')` truncates lines like
+      # `redirect "/posts#comments"; Post.touch` at the in-string `#`,
+      # silently dropping the `Post` reference. This scanner walks each line
+      # tracking quote state so only a genuine (unquoted) `#` starts a
+      # comment. Escapes (`\"`, `\'`) inside literals are honored. Heredocs,
+      # `%`-literals, and character literals whose char is a quote (`?'`,
+      # `?"`) are not modeled — these are rare in the constant-bearing code
+      # this scans, and mis-reading one only risks a spurious edge (a comment
+      # left unstripped) or a missed edge, never a crash or a dropped-but-real
+      # reference outside those constructs.
+      #
+      # @param source [String] Ruby source code
+      # @return [String] source with unquoted `#` comments removed
+      def strip_ruby_line_comments(source)
+        source.each_line.map { |line| strip_line_comment(line) }.join
+      end
+
+      # Strip a trailing `#` comment from a single line, ignoring `#` inside
+      # string literals. Preserves the line's trailing newline.
+      #
+      # @param line [String]
+      # @return [String]
+      def strip_line_comment(line)
+        in_single = false
+        in_double = false
+        i = 0
+        len = line.length
+        while i < len
+          ch = line[i]
+          if (in_single || in_double) && ch == '\\'
+            i += 2 # skip escaped char inside a literal
+            next
+          elsif in_single
+            in_single = false if ch == "'"
+          elsif in_double
+            in_double = false if ch == '"'
+          elsif ch == "'"
+            in_single = true
+          elsif ch == '"'
+            in_double = true
+          elsif ch == '#'
+            trailing = line[i..].end_with?("\n") ? "\n" : ''
+            return line[0...i] + trailing
+          end
+          i += 1
+        end
+        line
+      end
+
       # Extract string-literal arguments passed to `.constantize` or
       # `const_get(...)`. Matches both `"Library::Book".constantize`
       # and `Object.const_get("Library::Book")` / `const_get("...")`.
@@ -137,12 +194,27 @@ module Woods
       # @param source [String] Ruby source code to scan
       # @return [Array<Hash>] Deduplicated dependency hashes
       def scan_common_dependencies(source)
-        deps = []
-        deps.concat(scan_model_dependencies(source))
-        deps.concat(scan_service_dependencies(source))
-        deps.concat(scan_job_dependencies(source))
-        deps.concat(scan_mailer_dependencies(source))
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(
+          scan_model_dependencies(source),
+          scan_service_dependencies(source),
+          scan_job_dependencies(source),
+          scan_mailer_dependencies(source)
+        )
+      end
+
+      # Merge dependency arrays and deduplicate by +[type, target]+.
+      #
+      # Centralizes the `deps.uniq { |d| [d[:type], d[:target]] }` chain
+      # duplicated at the end of most extractors' +extract_dependencies+
+      # methods. Arrays are flattened one level and nils removed; the first
+      # occurrence of each +[type, target]+ pair wins, so the first +:via+
+      # label recorded is preserved — identical to the inline chains this
+      # replaces.
+      #
+      # @param dependency_arrays [Array<Array<Hash>>] One or more dependency arrays
+      # @return [Array<Hash>] Flattened, nil-free, deduplicated dependency hashes
+      def consolidate_dependencies(*dependency_arrays)
+        dependency_arrays.flatten(1).compact.uniq { |d| [d[:type], d[:target]] }
       end
 
       # Match _path/_url route helpers anywhere in source.

data/lib/woods/extractors/shared_utility_methods.rb

@@ -20,6 +20,20 @@ module Woods
     #   end
     #
     module SharedUtilityMethods
+      # Glob files matching a pattern across a list of directories.
+      #
+      # Centralizes the `Dir[dir.join('**/*.rb')]` loop duplicated across
+      # the directory-scanning extractors. Directories are globbed in order
+      # and the per-directory results concatenated, matching the original
+      # per-directory iteration semantics.
+      #
+      # @param directories [Array<Pathname>] Directories to glob
+      # @param pattern [String] Glob pattern relative to each directory
+      # @return [Array<String>] Matching file paths
+      def find_files_in_directories(directories, pattern = '**/*.rb')
+        directories.flat_map { |dir| Dir[dir.join(pattern).to_s] }
+      end
+
       # Check whether a path points to application source (under app_root, but
       # not inside vendor/ or node_modules/ directories).
       #

data/lib/woods/extractors/state_machine_extractor.rb

@@ -36,9 +36,7 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of state machine units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].flat_map { |file| extract_model_file(file) }
-        end
+        find_files_in_directories(@directories).flat_map { |file| extract_model_file(file) }
       end
 
       # Extract state machine definitions from a single model file.
@@ -391,7 +389,7 @@ module Woods
         deps = [{ type: :model, target: class_name, via: :state_machine }]
         deps.concat(scan_service_dependencies(source, via: :state_machine_callback))
         deps.concat(scan_job_dependencies(source, via: :state_machine_callback))
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/validator_extractor.rb

@@ -41,10 +41,8 @@ module Woods
       #
       # @return [Array<ExtractedUnit>] List of validator units
       def extract_all
-        @directories.flat_map do |dir|
-          Dir[dir.join('**/*.rb')].filter_map do |file|
-            extract_validator_file(file)
-          end
+        find_files_in_directories(@directories).filter_map do |file|
+          extract_validator_file(file)
         end
       end
 
@@ -204,7 +202,7 @@ module Woods
           deps << { type: :validator, target: validator, via: :code_reference }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/extractors/view_component_extractor.rb

@@ -315,7 +315,7 @@ module Woods
           deps << { type: :route, target: route, via: :url_helper }
         end
 
-        deps.uniq { |d| [d[:type], d[:target]] }
+        consolidate_dependencies(deps)
       end
     end
   end

data/lib/woods/filename_utils.rb

@@ -8,12 +8,41 @@ module Woods
   # Used by Extractor (writing) and IndexValidator (reading) to ensure
   # filename generation is consistent across both sides.
   module FilenameUtils
+    # Normalize a single identifier segment for use in a filename: replace
+    # `::` with `__` and every other non-`[a-zA-Z0-9_-]` character with `_`.
+    # This is the one character transform shared by {#safe_filename},
+    # {#collision_safe_filename}, and the precomputed-flow reader/writer
+    # (via {.flow_filename}) so the sides of each filename contract cannot
+    # drift. Also usable as a module method (`FilenameUtils.safe_segment`)
+    # for callers that don't mix the module in.
+    #
+    # @param identifier [String]
+    # @return [String]
+    def self.safe_segment(identifier)
+      identifier.to_s.gsub('::', '__').gsub(/[^a-zA-Z0-9_-]/, '_')
+    end
+
+    # Filename for a precomputed request-flow document, combining the
+    # controller identifier and action name — each normalized via
+    # {.safe_segment}. Used by both {Woods::FlowPrecomputer} (writing) and the
+    # MCP server's `trace_flow` (reading) so a name containing an
+    # out-of-charset character is written and looked up under the SAME file
+    # (the writer previously left the action raw while the reader allow-listed
+    # it, so such flows were written under one name and never found).
+    #
+    # @param controller_id [String] e.g. "Admin::UsersController"
+    # @param action [String] e.g. "index"
+    # @return [String] e.g. "Admin__UsersController_index.json"
+    def self.flow_filename(controller_id, action)
+      "#{safe_segment(controller_id)}_#{safe_segment(action)}.json"
+    end
+
     # Convert an identifier to a safe filename (legacy format).
     #
     # @param identifier [String] The unit identifier (e.g., "Admin::UsersController")
     # @return [String] A filesystem-safe filename (e.g., "Admin__UsersController.json")
     def safe_filename(identifier)
-      "#{identifier.gsub('::', '__').gsub(/[^a-zA-Z0-9_-]/, '_')}.json"
+      "#{FilenameUtils.safe_segment(identifier)}.json"
     end
 
     # Convert an identifier to a collision-safe filename (current format).
@@ -24,7 +53,7 @@ module Woods
     # @param identifier [String] The unit identifier
     # @return [String] Collision-safe filename (e.g., "Admin__UsersController_a1b2c3d4.json")
     def collision_safe_filename(identifier)
-      base = identifier.gsub('::', '__').gsub(/[^a-zA-Z0-9_-]/, '_')
+      base = FilenameUtils.safe_segment(identifier)
       digest = Digest::SHA256.hexdigest(identifier)[0, 8]
       "#{base}_#{digest}.json"
     end