canon 0.2.8 → 0.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b5218e18de7c596c5875ee1cf906331269cd58475a1f00de5c20af398bb07f08
-  data.tar.gz: 0dedd6f9e8ca265d37c610a183ed0e695ba68a9d8c9f0766b890f3d8db7d1f66
+  metadata.gz: a13457a67f3e2ab91e00cec19684c502605ab807bdd87eb1120e77d190a99c2e
+  data.tar.gz: 35c0c873340e12c63048adf2222fda2f8c2ae3972337dcc212b26d391191ac35
 SHA512:
-  metadata.gz: c24944e5600684e24f4b32cd16d90d68f64ca07671da7cd30a4cc7e13e818e98f86ab849ee28f7780f40ae3514df1ba3087cb32f55c7923d5303c65819aa8d59
-  data.tar.gz: 13a3c944492c29a916569b86829cefd8bf7baaf247eea105ee3f608d25789ef7c79ab0b0a95a3806e66b85348dd629169f8e19bef127e3ca79685a0e13d1bca9
+  metadata.gz: 8db915564eebd4ca4dfadd65358f721aa70bca318c22dc1c02eff5e3527cf646ea19722b760072851f358b3fabefd12fc5f6dfc216bce146423c7091f3bf7eac
+  data.tar.gz: f92e7491d781c8762483335558ede985a1653bcfb88613858115aa87e50bb326f95b0b76b845c54154e657fb9f25b3d1f348bf8e9baa926ea1c6bfbbd77d6ca6

data/.rspec-opal

@@ -0,0 +1,7 @@
+--default-path=spec
+--pattern='spec/canon/opal_xml_smoke_spec.rb'
+-I lib
+--opal-opt=-g,canon
+-I spec
+--require=spec_helper
+--require=support/opal

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-05-05 13:09:45 UTC using RuboCop version 1.86.0.
+# on 2026-05-24 10:34:05 UTC 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
@@ -11,58 +11,14 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'canon.gemspec'
 
-# Offense count: 5
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, IndentationWidth.
-# SupportedStyles: with_first_argument, with_fixed_indentation
-Layout/ArgumentAlignment:
-  Exclude:
-    - 'lib/canon/comparison/child_realignment.rb'
-    - 'lib/canon/comparison/xml_comparator/child_comparison.rb'
-    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
-
-# Offense count: 5
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyleAlignWith.
-# SupportedStylesAlignWith: either, start_of_block, start_of_line
-Layout/BlockAlignment:
-  Exclude:
-    - 'spec/canon/comparison/comments_asymmetry_spec.rb'
-    - 'spec/canon/comparison/whitespace_adjacency_spec.rb'
-
-# Offense count: 5
-# This cop supports safe autocorrection (--autocorrect).
-Layout/BlockEndNewline:
-  Exclude:
-    - 'spec/canon/comparison/comments_asymmetry_spec.rb'
-    - 'spec/canon/comparison/whitespace_adjacency_spec.rb'
-
-# Offense count: 10
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
-# SupportedStylesAlignWith: start_of_line, relative_to_receiver
-Layout/IndentationWidth:
-  Exclude:
-    - 'spec/canon/comparison/comments_asymmetry_spec.rb'
-    - 'spec/canon/comparison/whitespace_adjacency_spec.rb'
-
-# Offense count: 1386
+# Offense count: 1358
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, AllowRBSInlineAnnotation, AllowCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
 Layout/LineLength:
   Enabled: false
 
-# Offense count: 6
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowInHeredoc.
-Layout/TrailingWhitespace:
-  Exclude:
-    - 'lib/canon/comparison/child_realignment.rb'
-    - 'lib/canon/comparison/xml_comparator/child_comparison.rb'
-    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
-
-# Offense count: 63
+# Offense count: 58
 # Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
 Lint/DuplicateBranch:
   Enabled: false
@@ -75,13 +31,12 @@ Lint/EmptyConditionalBody:
     - 'spec/canon/comparison/html_comparator_spec.rb'
     - 'spec/canon/comparison_spec.rb'
 
-# Offense count: 6
+# Offense count: 5
 # Configuration parameters: MaximumRangeSize.
 Lint/MissingCopEnableDirective:
   Exclude:
     - 'lib/canon/commands/format_command.rb'
     - 'lib/canon/xml/attribute_handler.rb'
-    - 'lib/canon/xml/data_model.rb'
     - 'lib/canon/xml/namespace_handler.rb'
     - 'lib/canon/xml/processor.rb'
     - 'lib/canon/xml/xml_base_handler.rb'
@@ -107,7 +62,7 @@ Lint/UselessConstantScoping:
   Exclude:
     - 'lib/canon/diff_formatter/theme.rb'
 
-# Offense count: 321
+# Offense count: 313
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Enabled: false
@@ -123,12 +78,12 @@ Metrics/BlockLength:
 Metrics/BlockNesting:
   Max: 4
 
-# Offense count: 285
+# Offense count: 276
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Enabled: false
 
-# Offense count: 529
+# Offense count: 523
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 146
@@ -138,7 +93,7 @@ Metrics/MethodLength:
 Metrics/ParameterLists:
   Max: 10
 
-# Offense count: 221
+# Offense count: 214
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Enabled: false
@@ -177,7 +132,7 @@ Performance/CollectionLiteralInLoop:
 RSpec/ContextWording:
   Enabled: false
 
-# Offense count: 46
+# Offense count: 47
 # Configuration parameters: IgnoredMetadata.
 RSpec/DescribeClass:
   Enabled: false
@@ -188,7 +143,7 @@ RSpec/DescribeMethod:
     - 'spec/canon/comparison/multiple_differences_spec.rb'
     - 'spec/canon/diff_formatter/character_map_customization_spec.rb'
 
-# Offense count: 876
+# Offense count: 874
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 44
@@ -240,7 +195,7 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/canon/comparison/match_options_spec.rb'
 
-# Offense count: 735
+# Offense count: 736
 RSpec/MultipleExpectations:
   Max: 15
 
@@ -263,12 +218,13 @@ RSpec/NamedSubject:
 RSpec/NestedGroups:
   Max: 4
 
-# Offense count: 10
+# Offense count: 11
 # Configuration parameters: AllowedPatterns.
 # AllowedPatterns: ^expect_, ^assert_
 RSpec/NoExpectationExample:
   Exclude:
     - 'spec/canon/context_grouping_spec.rb'
+    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
     - 'spec/canon/informative_diffs_debug_spec.rb'
     - 'spec/canon/isodoc_blockquotes_spec.rb'
     - 'spec/canon/match_scenarios_spec.rb'
@@ -292,30 +248,17 @@ RSpec/SpecFilePathFormat:
     - 'spec/canon/yaml/formatter_spec.rb'
     - 'spec/xml_c14n_spec.rb'
 
-# Offense count: 100
+# Offense count: 72
 # Configuration parameters: IgnoreNameless, IgnoreSymbolicNames.
 RSpec/VerifiedDoubles:
   Exclude:
     - 'spec/canon/comparison/diff_node_builder_spec.rb'
     - 'spec/canon/comparison/whitespace_sensitivity_spec.rb'
     - 'spec/canon/diff/diff_classifier_spec.rb'
-    - 'spec/canon/diff/path_builder_spec.rb'
     - 'spec/canon/diff/xml_serialization_formatter_spec.rb'
     - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
     - 'spec/canon/tree_diff/operation_converter_spec.rb'
 
-# Offense count: 8
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle, ProceduralMethods, FunctionalMethods, AllowedMethods, AllowedPatterns, AllowBracesOnProceduralOneLiners, BracesRequiredMethods.
-# SupportedStyles: line_count_based, semantic, braces_for_chaining, always_braces
-# ProceduralMethods: benchmark, bm, bmbm, create, each_with_object, measure, new, realtime, tap, with_object
-# FunctionalMethods: let, let!, subject, watch
-# AllowedMethods: lambda, proc, it
-Style/BlockDelimiters:
-  Exclude:
-    - 'spec/canon/comparison/comments_asymmetry_spec.rb'
-    - 'spec/canon/comparison/whitespace_adjacency_spec.rb'
-
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, AllowComments.

data/Rakefile

@@ -5,10 +5,27 @@ require "rspec/core/rake_task"
 
 RSpec::Core::RakeTask.new(:spec)
 
+begin
+  require "opal/rspec/rake_task"
+rescue LoadError
+  # Opal not available or incompatible with current Ruby version
+end
+
 require "rubocop/rake_task"
 
 RuboCop::RakeTask.new
 
 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"
+      runner.default_path = "spec"
+      runner.pattern = "spec/canon/opal_xml_smoke_spec.rb"
+    end
+  end
+end
+
 task default: %i[spec rubocop]

data/lib/canon/cli.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require "thor"
+require "thor" unless RUBY_ENGINE == "opal"
 require_relative "commands/format_command"
 require_relative "commands/diff_command"
 require_relative "options/registry"

data/lib/canon/color_detector.rb

@@ -67,11 +67,9 @@ module Canon
       # @param io [IO] Output stream
       # @return [Boolean] true if the stream is a TTY
       def tty?(io)
-        return false unless io.respond_to?(:tty?)
-        return false unless io.respond_to?(:isatty)
-
-        # Ruby 2.5+ uses tty?, older uses isatty
-        io.tty? || io.isatty
+        io.tty?
+      rescue NoMethodError
+        false
       rescue ArgumentError, IOError
         # Stream might be closed or invalid
         false

data/lib/canon/comparison/compare_profile.rb

@@ -82,14 +82,11 @@ module Canon
         %i[text_content structural_whitespace].include?(dimension)
       end
 
-      private
-
       # Get the behavior setting for a dimension
       # @param dimension [Symbol] The match dimension
       # @return [Symbol] The behavior (:strict, :normalize, :ignore)
       def behavior_for(dimension)
-        # Handle both ResolvedMatchOptions and Hash
-        if match_options.respond_to?(:behavior_for)
+        if match_options.is_a?(ResolvedMatchOptions)
           match_options.behavior_for(dimension)
         elsif match_options.is_a?(Hash)
           match_options[dimension] || :strict

data/lib/canon/comparison/dimensions/attribute_order_dimension.rb

@@ -21,14 +21,10 @@ module Canon
         def extract_data(node)
           return [] unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            []
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/attribute_presence_dimension.rb

@@ -21,14 +21,10 @@ module Canon
         def extract_data(node)
           return [] unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            []
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/attribute_values_dimension.rb

@@ -27,14 +27,10 @@ module Canon
         def extract_data(node)
           return {} unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            {}
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/comments_dimension.rb

@@ -21,14 +21,10 @@ module Canon
         def extract_data(node)
           return [] unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            []
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/element_position_dimension.rb

@@ -23,14 +23,10 @@ module Canon
         def extract_data(node)
           return 0 unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            0
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/structural_whitespace_dimension.rb

@@ -25,14 +25,10 @@ module Canon
         def extract_data(node)
           return [] unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
           else
-            []
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/dimensions/text_content_dimension.rb

@@ -23,12 +23,10 @@ module Canon
         def extract_data(node)
           return nil unless node
 
-          # Handle Moxml nodes
-          if node.is_a?(Moxml::Node)
-            extract_from_moxml(node)
-          # Handle Nokogiri nodes
-          elsif node.is_a?(Nokogiri::XML::Node)
+          if Canon::XmlBackend.nokogiri?
             extract_from_nokogiri(node)
+          else
+            extract_from_moxml(node)
           end
         end
 

data/lib/canon/comparison/format_detector.rb

@@ -22,27 +22,36 @@ module Canon
         # @param obj [Object] Object to detect format of
         # @return [Symbol] Format type (:xml, :html, :json, :yaml, :ruby_object, :string)
         def detect(obj)
-          case obj
-          when Moxml::Node, Moxml::Document
-            :xml
-          when Nokogiri::HTML::DocumentFragment, Nokogiri::HTML5::DocumentFragment
-            # HTML DocumentFragments
-            :html
-          when Nokogiri::XML::DocumentFragment
-            # XML DocumentFragments - check if it's actually HTML
-            obj.document&.html? ? :html : :xml
-          when Nokogiri::XML::Document, Nokogiri::XML::Node
-            # Check if it's HTML by looking at the document type
-            obj.html? ? :html : :xml
-          when Nokogiri::HTML::Document, Nokogiri::HTML5::Document
-            :html
-          when String
-            detect_string(obj)
-          when Hash, Array
-            # Raw Ruby objects (from parsed JSON/YAML)
-            :ruby_object
+          if XmlBackend.moxml?
+            case obj
+            when Moxml::Node, Moxml::Document
+              :xml
+            when String
+              detect_string(obj)
+            when Hash, Array
+              :ruby_object
+            else
+              raise Canon::Error, "Unknown format for object: #{obj.class}"
+            end
           else
-            raise Canon::Error, "Unknown format for object: #{obj.class}"
+            case obj
+            when Moxml::Node, Moxml::Document
+              :xml
+            when Nokogiri::HTML::DocumentFragment, Nokogiri::HTML5::DocumentFragment
+              :html
+            when Nokogiri::XML::DocumentFragment
+              obj.document&.html? ? :html : :xml
+            when Nokogiri::XML::Document, Nokogiri::XML::Node
+              obj.html? ? :html : :xml
+            when Nokogiri::HTML::Document, Nokogiri::HTML5::Document
+              :html
+            when String
+              detect_string(obj)
+            when Hash, Array
+              :ruby_object
+            else
+              raise Canon::Error, "Unknown format for object: #{obj.class}"
+            end
           end
         end
 

data/lib/canon/comparison/html_comparator.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require "nokogiri"
+require "nokogiri" unless RUBY_ENGINE == "opal"
 require_relative "../comparison" # Load base module with constants first
 require_relative "markup_comparator"
 require_relative "xml_comparator"
@@ -167,6 +167,11 @@ module Canon
           end
         end
 
+        # Public parsing API for external callers
+        def parse(html, preprocessing = :none)
+          parse_node_for_semantic(html, preprocessing)
+        end
+
         private
 
         # Check if both nodes are document fragments
@@ -337,13 +342,10 @@ module Canon
           # Convert to string if needed
           html_string = if html.is_a?(String)
                           html
-                        elsif html.respond_to?(:to_html)
+                        elsif Canon::XmlParsing.xml_node?(html)
                           html.to_html
-                        elsif html.respond_to?(:to_s)
-                          html.to_s
                         else
-                          raise Canon::Error,
-                                "Unable to convert HTML to string: #{html.class}"
+                          html.to_s
                         end
 
           # Strip DOCTYPE for consistent parsing
@@ -492,22 +494,18 @@ module Canon
         end
 
         def find_and_normalize_style_script(node)
-          return unless node.respond_to?(:children)
+          return unless node.is_a?(Canon::Xml::Node)
 
           node.children.each do |child|
             next unless child.is_a?(Canon::Xml::Nodes::ElementNode)
 
             # If this is a style or script element, normalize its text content
             if %w[style script].include?(child.name.downcase)
-              # Get text children and remove HTML comments from them
               child.children.each do |text_child|
                 next unless text_child.is_a?(Canon::Xml::Nodes::TextNode)
 
-                # Remove HTML comments from text content without using regex
-                # to avoid ReDoS/incomplete sanitization vulnerabilities
                 normalized = remove_html_comments(text_child.value)
-                # Update the text value
-                text_child.instance_variable_set(:@value, normalized)
+                text_child.value = normalized
               end
             end
 
@@ -584,13 +582,10 @@ module Canon
         # @param node [Canon::Xml::Node, Nokogiri::HTML::Document] Parsed node
         # @return [String] Serialized HTML string
         def serialize_for_display(node)
-          # Use XmlNodeComparison's serializer for Canon::Xml::Node
           if node.is_a?(Canon::Xml::Node)
             XmlNodeComparison.serialize_node_to_xml(node)
-          elsif node.respond_to?(:to_html)
-            node.to_html
-          elsif node.respond_to?(:to_xml)
-            node.to_xml
+          elsif Canon::XmlParsing.xml_node?(node)
+            Canon::XmlBackend.nokogiri? ? node.to_html : Canon::XmlParsing.serialize(node)
           else
             node.to_s
           end
@@ -605,16 +600,11 @@ module Canon
           if html.is_a?(String)
             html
           elsif html.is_a?(Canon::Xml::Node)
-            # Serialize Canon nodes to string
             Canon::Xml::DataModel.serialize(html)
-          elsif html.respond_to?(:to_html)
-            # Nokogiri nodes - use to_html to preserve formatting
-            html.to_html
-          elsif html.respond_to?(:to_s)
-            html.to_s
+          elsif Canon::XmlParsing.xml_node?(html)
+            Canon::XmlBackend.nokogiri? ? html.to_html : html.to_s
           else
-            raise Canon::Error,
-                  "Unable to extract original string from: #{html.class}"
+            html.to_s
           end
         end
 
@@ -727,11 +717,10 @@ compare_profile = nil)
         # Check if any ancestor of the given node preserves whitespace
         def ancestor_preserves_whitespace?(node, preserve_list)
           current = node
-          while current.respond_to?(:name)
+          while current.is_a?(Canon::Xml::Node) || Canon::XmlParsing.xml_node?(current)
             return true if preserve_list.include?(current.name.downcase)
 
-            # Stop at document root - documents don't have parents
-            break if current.is_a?(Nokogiri::XML::Document)
+            break if Canon::XmlParsing.document?(current)
 
             current = current.parent
           end
@@ -811,7 +800,7 @@ compare_profile = nil)
           end
 
           # Check if it's a fragment that contains XML processing instructions
-          if node.respond_to?(:children) && node.children.any? do |child|
+          if (node.is_a?(Canon::Xml::Node) || Canon::XmlParsing.xml_node?(node)) && node.children.any? do |child|
             child.is_a?(Nokogiri::XML::ProcessingInstruction) &&
                 child.name == "xml"
           end

data/lib/canon/comparison/html_compare_profile.rb

@@ -48,9 +48,8 @@ module Canon
 
             # If key exists, check if it's :strict
             return match_options[:comments] == :strict
-          elsif match_options.respond_to?(:behavior_for)
+          elsif match_options.is_a?(ResolvedMatchOptions)
             behavior = behavior_for(dimension)
-            # In HTML, only :strict makes comments affect equivalence
             return behavior == :strict
           end
           # Default: comments don't affect equivalence in HTML
@@ -106,14 +105,8 @@ module Canon
       def has_explicit_option?(dimension)
         if match_options.is_a?(Hash)
           match_options.key?(dimension)
-        elsif match_options.respond_to?(:[])
-          # For ResolvedMatchOptions, check if key exists
-          begin
-            match_options[dimension]
-            true
-          rescue StandardError
-            false
-          end
+        elsif match_options.is_a?(ResolvedMatchOptions)
+          !match_options.options[dimension].nil?
         else
           false
         end

data/lib/canon/comparison/html_parser.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require "nokogiri"
+require "nokogiri" unless RUBY_ENGINE == "opal"
 
 module Canon
   module Comparison

data/lib/canon/comparison/json_comparator.rb

@@ -26,6 +26,14 @@ module Canon
       }.freeze
 
       class << self
+        # Parse JSON from string or return as-is
+        #
+        # @param obj [String, Hash, Array] JSON string or parsed object
+        # @return [Object] Parsed JSON object
+        def parse(obj)
+          parse_json(obj)
+        end
+
         # Compare two JSON objects for equivalence
         #
         # @param json1 [String, Hash, Array] First JSON