canon 0.2.8 → 0.2.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b5218e18de7c596c5875ee1cf906331269cd58475a1f00de5c20af398bb07f08
-  data.tar.gz: 0dedd6f9e8ca265d37c610a183ed0e695ba68a9d8c9f0766b890f3d8db7d1f66
+  metadata.gz: 8fcacddf719d0cb69472bc55b2a23d724c938fdf76f995eb77be962aeda42182
+  data.tar.gz: 3a1d14c811209e8353c7539d12c2f7a4d23d44c1e6742b6f48a8d94f65282bd5
 SHA512:
-  metadata.gz: c24944e5600684e24f4b32cd16d90d68f64ca07671da7cd30a4cc7e13e818e98f86ab849ee28f7780f40ae3514df1ba3087cb32f55c7923d5303c65819aa8d59
-  data.tar.gz: 13a3c944492c29a916569b86829cefd8bf7baaf247eea105ee3f608d25789ef7c79ab0b0a95a3806e66b85348dd629169f8e19bef127e3ca79685a0e13d1bca9
+  metadata.gz: f4685b05d13d6cedad780751a8011a722511a9a5623a3a3fa14ce548b95d036c8fd36cabb10d8793ede0a97cf5a1e72d8f53729022c90c8b316c510dc133983e
+  data.tar.gz: 5201625d93a1ed9c2efb929905c1d14f4a292e914604149f8e5902a61d1ea6059b987c8875b073ec71340adb1833a33bbce450f58006f29736a37d810f326d6d

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.
+# `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
@@ -11,58 +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: 1357
 # 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: 316
 # 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: 527
 # 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
@@ -152,6 +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
@@ -177,7 +140,7 @@ Performance/CollectionLiteralInLoop:
 RSpec/ContextWording:
   Enabled: false
 
-# Offense count: 46
+# Offense count: 48
 # Configuration parameters: IgnoredMetadata.
 RSpec/DescribeClass:
   Enabled: false
@@ -188,7 +151,7 @@ RSpec/DescribeMethod:
     - 'spec/canon/comparison/multiple_differences_spec.rb'
     - 'spec/canon/diff_formatter/character_map_customization_spec.rb'
 
-# Offense count: 876
+# Offense count: 893
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 44
@@ -240,7 +203,7 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/canon/comparison/match_options_spec.rb'
 
-# Offense count: 735
+# Offense count: 749
 RSpec/MultipleExpectations:
   Max: 15
 
@@ -263,12 +226,13 @@ 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 +256,17 @@ RSpec/SpecFilePathFormat:
     - 'spec/canon/yaml/formatter_spec.rb'
     - 'spec/xml_c14n_spec.rb'
 
-# Offense count: 100
+# Offense count: 18
 # 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.
@@ -331,12 +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

@@ -5,10 +5,47 @@ require "rspec/core/rake_task"
 
 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
+
 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|
+      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
+end
+
 task default: %i[spec rubocop]

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/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