canon 0.2.9 → 0.2.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a13457a67f3e2ab91e00cec19684c502605ab807bdd87eb1120e77d190a99c2e
-  data.tar.gz: 35c0c873340e12c63048adf2222fda2f8c2ae3972337dcc212b26d391191ac35
+  metadata.gz: 8fcacddf719d0cb69472bc55b2a23d724c938fdf76f995eb77be962aeda42182
+  data.tar.gz: 3a1d14c811209e8353c7539d12c2f7a4d23d44c1e6742b6f48a8d94f65282bd5
 SHA512:
-  metadata.gz: 8db915564eebd4ca4dfadd65358f721aa70bca318c22dc1c02eff5e3527cf646ea19722b760072851f358b3fabefd12fc5f6dfc216bce146423c7091f3bf7eac
-  data.tar.gz: f92e7491d781c8762483335558ede985a1653bcfb88613858115aa87e50bb326f95b0b76b845c54154e657fb9f25b3d1f348bf8e9baa926ea1c6bfbbd77d6ca6
+  metadata.gz: f4685b05d13d6cedad780751a8011a722511a9a5623a3a3fa14ce548b95d036c8fd36cabb10d8793ede0a97cf5a1e72d8f53729022c90c8b316c510dc133983e
+  data.tar.gz: 5201625d93a1ed9c2efb929905c1d14f4a292e914604149f8e5902a61d1ea6059b987c8875b073ec71340adb1833a33bbce450f58006f29736a37d810f326d6d

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
-# `rubocop --auto-gen-config`
-# on 2026-05-24 10:34:05 UTC using RuboCop version 1.86.0.
+# `rubocop --auto-gen-config --no-auto-gen-timestamp`
+# using RuboCop version 1.86.0.
 # 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
@@ -11,7 +11,7 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'canon.gemspec'
 
-# Offense count: 1358
+# Offense count: 1357
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
@@ -62,7 +62,7 @@ Lint/UselessConstantScoping:
   Exclude:
     - 'lib/canon/diff_formatter/theme.rb'
 
-# Offense count: 313
+# Offense count: 316
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Enabled: false
@@ -83,7 +83,7 @@ Metrics/BlockNesting:
 Metrics/CyclomaticComplexity:
   Enabled: false
 
-# Offense count: 523
+# Offense count: 527
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 146
@@ -107,6 +107,14 @@ Naming/MethodParameterName:
     - 'lib/canon/comparison/xml_comparator/attribute_comparator.rb'
     - 'lib/canon/xml/namespace_handler.rb'
 
+# Offense count: 1
+# Configuration parameters: Mode, AllowedMethods, AllowedPatterns, AllowBangMethods, WaywardPredicates.
+# AllowedMethods: call
+# WaywardPredicates: infinite?, nonzero?
+Naming/PredicateMethod:
+  Exclude:
+    - 'spec/canon/comparison/xml_attribute_diff_spec.rb'
+
 # Offense count: 6
 # Configuration parameters: EnforcedStyle, CheckMethodNames, CheckSymbols, AllowedIdentifiers, AllowedPatterns.
 # SupportedStyles: snake_case, normalcase, non_integer
@@ -132,7 +140,7 @@ Performance/CollectionLiteralInLoop:
 RSpec/ContextWording:
   Enabled: false
 
-# Offense count: 47
+# Offense count: 48
 # Configuration parameters: IgnoredMetadata.
 RSpec/DescribeClass:
   Enabled: false
@@ -143,7 +151,7 @@ RSpec/DescribeMethod:
     - 'spec/canon/comparison/multiple_differences_spec.rb'
     - 'spec/canon/diff_formatter/character_map_customization_spec.rb'
 
-# Offense count: 874
+# Offense count: 893
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 44
@@ -195,7 +203,7 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/canon/comparison/match_options_spec.rb'
 
-# Offense count: 736
+# Offense count: 749
 RSpec/MultipleExpectations:
   Max: 15
 
@@ -248,7 +256,7 @@ RSpec/SpecFilePathFormat:
     - 'spec/canon/yaml/formatter_spec.rb'
     - 'spec/xml_c14n_spec.rb'
 
-# Offense count: 72
+# Offense count: 18
 # Configuration parameters: IgnoreNameless, IgnoreSymbolicNames.
 RSpec/VerifiedDoubles:
   Exclude:
@@ -274,12 +282,13 @@ Style/HashLikeCase:
     - 'lib/canon/diff/diff_block_builder.rb'
     - 'lib/canon/xml/character_encoder.rb'
 
-# Offense count: 4
+# Offense count: 6
 # This cop supports unsafe autocorrection (--autocorrect-all).
 Style/IdenticalConditionalBranches:
   Exclude:
     - 'lib/canon/diff_formatter/by_object/base_formatter.rb'
     - 'lib/canon/diff_formatter/legend.rb'
+    - 'lib/canon/xml/whitespace_normalizer.rb'
 
 # Offense count: 1
 # Configuration parameters: AllowedMethods.

data/Rakefile

@@ -7,6 +7,26 @@ RSpec::Core::RakeTask.new(:spec)
 
 begin
   require "opal/rspec/rake_task"
+
+  # Configure Opal load paths at load time (same pattern as moxml)
+  if defined?(Opal)
+    Opal.append_path File.expand_path("lib", __dir__)
+
+    # moxml gem
+    begin
+      moxml_spec = Gem::Specification.find_by_name("moxml")
+      moxml_lib = moxml_spec.full_require_paths.first
+      Opal.append_path moxml_lib
+      moxml_compat = File.expand_path("compat/opal", moxml_lib)
+      Opal.append_path moxml_compat if File.directory?(moxml_compat)
+    rescue Gem::MissingSpecError
+      # moxml not installed
+    end
+
+    # REXML: bundled gem since Ruby 3.4
+    rexml_lib = $LOAD_PATH.find { |p| File.exist?(File.join(p, "rexml", "document.rb")) }
+    Opal.append_path rexml_lib if rexml_lib
+  end
 rescue LoadError
   # Opal not available or incompatible with current Ruby version
 end
@@ -20,9 +40,9 @@ Dir.glob("lib/tasks/**/*.rake").each { |r| load r }
 namespace :spec do
   if defined?(Opal::RSpec::RakeTask)
     desc "Run Opal (JavaScript) tests"
-    Opal::RSpec::RakeTask.new(:opal) do |server, runner|
-      server.append_path "lib"
+    Opal::RSpec::RakeTask.new(:opal) do |_server, runner|
       runner.default_path = "spec"
+      runner.requires = %w[rexml_compat rexml/document rexml/xpath moxml/adapter/rexml spec_helper]
       runner.pattern = "spec/canon/opal_xml_smoke_spec.rb"
     end
   end

data/lib/canon/cache.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require "digest"
+require "digest" unless RUBY_ENGINE == "opal"
 
 module Canon
   # Cache for expensive operations during document comparison
@@ -73,50 +73,39 @@ module Canon
       end
 
       # Generate cache key for document parsing
-      #
-      # @param content [String] Document content
-      # @param format [Symbol] Document format
-      # @param preprocessing [Symbol] Preprocessing option
-      # @return [String] Cache key
       def key_for_document(content, format, preprocessing)
-        digest = Digest::SHA256.hexdigest(content)
-        "doc:#{format}:#{preprocessing}:#{digest[0..16]}"
+        "doc:#{format}:#{preprocessing}:#{content_hash(content)}"
       end
 
       # Generate cache key for format detection
-      #
-      # @param content [String] Document content
-      # @return [String] Cache key
       def key_for_format_detection(content)
-        # Use first 100 chars for quick key, plus length
-        # Force to binary to avoid encoding compatibility issues
         preview = content[0..100].b
-        digest = Digest::SHA256.hexdigest(preview + content.length.to_s)
-        "fmt:#{digest[0..16]}"
+        "fmt:#{content_hash(preview + content.length.to_s)}"
       end
 
       # Generate cache key for XML canonicalization
-      #
-      # @param content [String] XML content
-      # @param with_comments [Boolean] Whether to include comments
-      # @return [String] Cache key
       def key_for_c14n(content, with_comments)
-        digest = Digest::SHA256.hexdigest(content)
-        "c14n:#{with_comments}:#{digest[0..16]}"
+        "c14n:#{with_comments}:#{content_hash(content)}"
       end
 
       # Generate cache key for preprocessing
-      #
-      # @param content [String] Original content
-      # @param preprocessing [Symbol] Preprocessing type
-      # @return [String] Cache key
       def key_for_preprocessing(content, preprocessing)
-        digest = Digest::SHA256.hexdigest(content)
-        "pre:#{preprocessing}:#{digest[0..16]}"
+        "pre:#{preprocessing}:#{content_hash(content)}"
       end
 
       private
 
+      # Generate a hash string for cache keys
+      def content_hash(content)
+        if defined?(Digest::SHA256)
+          Digest::SHA256.hexdigest(content)[0..16]
+        else
+          # Opal fallback: simple string hash
+          h = content.each_char.reduce(0) { |acc, c| ((acc * 31) + c.ord) & 0xFFFFFFFF }
+          h.to_s(16).rjust(8, "0")
+        end
+      end
+
       # Get or create cache for a category
       #
       # @param category [Symbol] Cache category

data/lib/canon/comparison/html_comparator.rb

@@ -558,6 +558,8 @@ module Canon
           end
         end
 
+        public :detect_html_version
+
         # Detect HTML version from node
         #
         # @param node [Canon::Xml::Node, Nokogiri::XML::Node] HTML node

data/lib/canon/comparison/node_inspector.rb

@@ -10,37 +10,25 @@ module Canon
     # * Canon::TreeDiff::Core::TreeNode — semantic tree diff nodes.
     # * Backend-specific nodes (Nokogiri or Moxml) — live parsed nodes.
     #
-    # All type dispatch uses backend-branching (`if XmlBackend.nokogiri?`)
-    # rather than `case/when` with constant references. This prevents
-    # NameError when Nokogiri constants are undefined under Opal.
-    #
-    # Every node query in the codebase should go through this module.
-    # Do not create private dispatch methods in consumers.
+    # Architecture: NodeInspector handles Canon-native types (Canon::Xml::Node,
+    # TreeNode) directly, then delegates ALL backend-specific queries to
+    # XmlParsing. No Moxml/Nokogiri constants are referenced here — that
+    # knowledge lives exclusively in XmlParsing.
     module NodeInspector
-      NOKOGIRI_TEXT_TYPE = defined?(Nokogiri::XML::Node::TEXT_NODE) ? Nokogiri::XML::Node::TEXT_NODE : 3
-
       # --- Type predicates ---
 
       def self.text_node?(node)
         return false unless node
         return node.node_type == :text if node.is_a?(Canon::Xml::Node)
 
-        if XmlBackend.nokogiri?
-          node.is_a?(Nokogiri::XML::Text) || node.is_a?(Moxml::Text)
-        else
-          node.is_a?(Moxml::Text)
-        end
+        XmlParsing.text_node?(node)
       end
 
       def self.element_node?(node)
         return false unless node
         return node.node_type == :element if node.is_a?(Canon::Xml::Node)
 
-        if XmlBackend.nokogiri?
-          node.is_a?(Nokogiri::XML::Element) || node.is_a?(Moxml::Element)
-        else
-          node.is_a?(Moxml::Element)
-        end
+        XmlParsing.element?(node)
       end
 
       def self.comment_node?(node)
@@ -57,7 +45,7 @@ module Canon
           end
           false
         else
-          node.is_a?(Moxml::Comment)
+          XmlParsing.comment?(node)
         end
       end
 
@@ -100,7 +88,6 @@ module Canon
 
       # --- Node queries ---
 
-      # Unified node name extraction across all node types.
       def self.name(node)
         return nil unless node
         return node.name if node.is_a?(Canon::Xml::Node)
@@ -109,7 +96,6 @@ module Canon
         XmlParsing.name(node)
       end
 
-      # Unified parent access across all node types.
       def self.parent(node)
         return nil unless node
         return node.parent if node.is_a?(Canon::Xml::Node)
@@ -118,7 +104,6 @@ module Canon
         XmlParsing.parent(node)
       end
 
-      # Unified children access across all node types.
       def self.children(node)
         return [] unless node
         return node.children if node.is_a?(Canon::Xml::Node)
@@ -127,34 +112,21 @@ module Canon
         XmlParsing.children(node)
       end
 
-      # Extract the text content of +node+ as a String.
       def self.text_content(node)
-        case node
-        when Canon::Xml::Nodes::TextNode
-          node.value.to_s
-        when Canon::Xml::Node
-          node.text_content.to_s
-        when Moxml::Text
-          node.content.to_s
-        else
-          XmlParsing.text_content(node).to_s
-        end
+        return node.value.to_s if node.is_a?(Canon::Xml::Nodes::TextNode)
+        return node.text_content.to_s if node.is_a?(Canon::Xml::Node)
+
+        XmlParsing.text_content(node).to_s
       end
 
-      # Unified node type that always returns a symbol.
-      # Returns nil for unrecognised nodes.
       def self.node_type(node)
         return nil unless node
         return node.node_type if node.is_a?(Canon::Xml::Node)
+        return node.type&.to_sym if node.is_a?(Canon::TreeDiff::Core::TreeNode)
 
-        if node.is_a?(Canon::TreeDiff::Core::TreeNode)
-          node.type&.to_sym
-        else
-          XmlParsing.node_type(node)
-        end
+        XmlParsing.node_type(node)
       end
 
-      # Unified attribute value access.
       def self.attribute_value(node, attr_name)
         return nil unless node
 
@@ -168,7 +140,6 @@ module Canon
         end
       end
 
-      # Unified namespace URI access.
       def self.namespace_uri(node)
         return nil unless node
 
@@ -179,7 +150,6 @@ module Canon
         end
       end
 
-      # Extract parse-time errors carried on a node or its owning document.
       def self.parse_errors(node)
         return [] if node.nil?
         return Array(node.parse_errors).map(&:to_s) if node.is_a?(Canon::Xml::Node)
@@ -194,11 +164,6 @@ module Canon
           []
         end
       end
-
-      # Deprecated: use NodeInspector.parent instead.
-      def self.parent_of(node)
-        parent(node)
-      end
     end
   end
 end

data/lib/canon/comparison/xml_comparator/attribute_comparator.rb

@@ -15,8 +15,8 @@ module Canon
         # @return [Symbol] Comparison result
         def self.compare(node1, node2, opts, differences)
           # Get attributes using the appropriate method for each node type
-          raw_attrs1 = node1.respond_to?(:attribute_nodes) ? node1.attribute_nodes : node1.attributes
-          raw_attrs2 = node2.respond_to?(:attribute_nodes) ? node2.attribute_nodes : node2.attributes
+          raw_attrs1 = get_raw_attributes(node1)
+          raw_attrs2 = get_raw_attributes(node2)
 
           attrs1 = XmlComparatorHelpers::AttributeFilter.filter(raw_attrs1,
                                                                 opts)
@@ -171,6 +171,23 @@ dimension:, differences:, **opts)
           )
           differences << diff_node if diff_node
         end
+
+        # Get raw attributes from a node, dispatching by type.
+        # Nokogiri::XML::Element has attribute_nodes (NodeSet),
+        # Canon::Xml::Nodes::ElementNode has attribute_nodes (Array),
+        # Moxml::Element has attributes (Hash-like).
+        def self.get_raw_attributes(node)
+          case node
+          when Canon::Xml::Nodes::ElementNode
+            node.attribute_nodes
+          else
+            if Canon::XmlBackend.nokogiri? && node.is_a?(Nokogiri::XML::Element)
+              node.attribute_nodes
+            else
+              node.attributes
+            end
+          end
+        end
       end
     end
   end

data/lib/canon/comparison/xml_comparator/diff_node_builder.rb

@@ -72,6 +72,11 @@ module Canon
           return build_attribute_difference_reason(attrs1, attrs2)
         end
 
+        # For attribute value differences, show which attributes changed
+        if dimension == :attribute_values
+          return build_attribute_values_reason(node1, node2)
+        end
+
         # For text content differences, show the actual text (truncated if needed)
         if dimension == :text_content
           text1 = extract_text_content(node1)
@@ -186,6 +191,31 @@ module Canon
         end
       end
 
+      # Build a reason message for attribute value differences
+      # Shows each changed attribute with its before/after values
+      #
+      # @param node1 [Object, nil] First node
+      # @param node2 [Object, nil] Second node
+      # @return [String] Clear explanation of the attribute value differences
+      def self.build_attribute_values_reason(node1, node2)
+        attrs1 = extract_attributes(node1) || {}
+        attrs2 = extract_attributes(node2) || {}
+
+        differing = (attrs1.keys | attrs2.keys).sort.reject do |k|
+          attrs1[k.to_s] == attrs2[k.to_s]
+        end
+
+        changed_parts = differing.map do |k|
+          "Changed: #{k}=\"#{attrs1[k.to_s]}\" → \"#{attrs2[k.to_s]}\""
+        end
+
+        if changed_parts.empty?
+          "attributes differ"
+        else
+          "Attributes differ (#{changed_parts.join('; ')})"
+        end
+      end
+
       # Extract text content from a node
       #
       # @param node [Object, nil] Node to extract text from

data/lib/canon/comparison/xml_comparator/node_parser.rb

@@ -37,7 +37,7 @@ module Canon
           # Select parser backend
           resolved_parser = parser || resolve_parser_config
 
-          if resolved_parser == :sax
+          if resolved_parser == :sax && RUBY_ENGINE != "opal"
             require_relative "../../xml/sax_builder"
             Canon::Xml::SaxBuilder.parse(xml_string,
                                          preserve_whitespace: preserve_whitespace)
@@ -97,7 +97,7 @@ parser: nil)
 
           resolved_parser = parser || resolve_parser_config
 
-          if resolved_parser == :sax
+          if resolved_parser == :sax && RUBY_ENGINE != "opal"
             require_relative "../../xml/sax_builder"
             Canon::Xml::SaxBuilder.parse(xml_str,
                                          preserve_whitespace: preserve_whitespace)

data/lib/canon/comparison/xml_comparator.rb

@@ -875,7 +875,7 @@ differences)
         end
 
         def whitespace_adjacency_parent_label(ws_node)
-          parent = NodeInspector.parent_of(ws_node)
+          parent = NodeInspector.parent(ws_node)
           return "(unknown parent)" unless parent
 
           name = parent.name
@@ -890,7 +890,7 @@ differences)
         # "adjacent to" as a degenerate fallback when neither neighbour
         # exists.
         def whitespace_partner_direction(ws_node)
-          parent = NodeInspector.parent_of(ws_node)
+          parent = NodeInspector.parent(ws_node)
           return "adjacent to" unless parent
 
           siblings = parent.children

data/lib/canon/comparison.rb

@@ -284,7 +284,7 @@ module Canon
         (custom + presets).sort.uniq
       end
 
-      private
+      # --- Internal methods (public for testability) ---
 
       # Perform semantic tree diff comparison
       def semantic_diff(obj1, obj2, opts = {})

data/lib/canon/diff/diff_line_builder.rb

@@ -843,6 +843,8 @@ new_line_ranges)
         index
       end
 
+      public :build_line_index
+
       # Sort char ranges by start_col for consistent rendering.
       def sort_ranges(ranges)
         (ranges || []).sort_by(&:start_col)

data/lib/canon/diff/diff_node_mapper.rb

@@ -323,7 +323,7 @@ module Canon
       # @param line2 [String] New line content (for +/!)
       # @return [Boolean] true if formatting-only
       def formatting?(node, line1, line2)
-        return true if node.respond_to?(:formatting?) && node.formatting?
+        return true if node.is_a?(Canon::Diff::DiffNode) && node.formatting?
         return false if node
         return true if comment_only_line?(line1) || comment_only_line?(line2)
 
@@ -394,14 +394,14 @@ module Canon
                            end
 
           nodes_to_check.any? do |node|
-            # Check if the node itself has the matching name
-            if node.respond_to?(:name) && node.name == line_element_name
-              true
-            # Check if the node's parent has the matching name (for TextNode diffs)
-            elsif node.respond_to?(:parent) && node.parent.respond_to?(:name) && node.parent.name == line_element_name # rubocop:disable Style/IfWithBooleanLiteralBranches
+            next false unless node
+
+            node_name = Canon::Comparison::NodeInspector.name(node)
+            if node_name == line_element_name
               true
             else
-              false
+              parent = Canon::Comparison::NodeInspector.parent(node)
+              parent && Canon::Comparison::NodeInspector.name(parent) == line_element_name
             end
           end
         end
@@ -453,6 +453,8 @@ module Canon
         comment_lines
       end
 
+      public :build_comment_lines
+
       # Find a comment DiffNode for a line that falls within a comment range.
       # Matches by checking if the DiffNode's source node has name "comment".
       #
@@ -463,7 +465,7 @@ module Canon
         @comment_diff_nodes&.find do |diff_node|
           nodes_to_check = [diff_node.node1, diff_node.node2].compact
           nodes_to_check.any? do |node|
-            node.respond_to?(:name) && node.name == "comment"
+            Canon::Comparison::NodeInspector.name(node) == "comment"
           end
         end
       end

data/lib/canon/diff/formatting_detector.rb

@@ -297,8 +297,9 @@ module Canon
         [close_idx + 1, "<#{sorted}#{suffix}"]
       end
 
-      private_class_method :normalize_for_comparison, :blank?,
-                           :decode_xml_entities, :normalize_attribute_order,
+      public_class_method :normalize_for_comparison, :blank?
+
+      private_class_method :decode_xml_entities, :normalize_attribute_order,
                            :sort_tag_attributes, :tokenize_tag_content,
                            :process_tag, :process_processing_instruction,
                            :process_comment, :process_regular_tag

data/lib/canon/diff/xml_serialization_formatter.rb

@@ -57,9 +57,6 @@ module Canon
       rescue StandardError
         nil
       end
-
-      private_class_method :blank?, :text_node?, :extract_text_content,
-                           :empty_text_content_serialization_diff?
     end
   end
 end

data/lib/canon/diff_formatter/by_object/base_formatter.rb

@@ -270,9 +270,12 @@ show_diffs: :all, theme: nil)
 
             if diffs && !diffs.empty?
               # Render all differences at this path
+              has_children = value.is_a?(Hash) &&
+                (value.keys - [:__diffs__]).any?
+
               diffs.each_with_index do |diff, diff_idx|
-                # Use proper connector for each diff
-                current_connector = if diff_idx == diffs.length - 1
+                is_last_diff = diff_idx == diffs.length - 1
+                current_connector = if is_last_diff && !has_children
                                       connector
                                     else
                                       is_last_item ? "├── " : "├── "
@@ -282,6 +285,13 @@ show_diffs: :all, theme: nil)
                 output << line
                 @line_count += line.count("\n") + 1
               end
+
+              # Recurse into child diffs at this path
+              if has_children
+                subtree = render_tree(value, prefix: prefix + continuation,
+                                             is_last: is_last_item)
+                output << subtree
+              end
             else
               # Render intermediate path
               line = colorize("#{prefix}#{connector}#{key}:",