canon 0.1.7 → 0.1.9

data/lib/canon/comparison/html_comparator.rb

@@ -2,6 +2,7 @@
 
 require "nokogiri"
 require_relative "../comparison" # Load base module with constants first
+require_relative "markup_comparator"
 require_relative "xml_comparator"
 require_relative "match_options"
 require_relative "comparison_result"
@@ -11,12 +12,17 @@ require_relative "../diff/diff_node"
 require_relative "../diff/diff_classifier"
 require_relative "strategies/match_strategy_factory"
 require_relative "../html/data_model"
+require_relative "xml_node_comparison"
+# Whitespace sensitivity module (single source of truth for sensitive elements)
+require_relative "whitespace_sensitivity"
 
 module Canon
   module Comparison
     # HTML comparison class
     # Handles comparison of HTML nodes with various options
-    class HtmlComparator
+    #
+    # Inherits shared comparison functionality from MarkupComparator.
+    class HtmlComparator < MarkupComparator
       # Default comparison options for HTML
       DEFAULT_OPTS = {
         # Structural filtering options
@@ -108,6 +114,9 @@ module Canon
 
           # DocumentFragment nodes need special handling - compare their children
           # instead of the fragment nodes themselves
+          # This is a SAFETY CHECK for legacy cases where Nokogiri nodes might still be used
+          # The main path (parse_node) now returns Canon::Xml::Nodes::RootNode, so this
+          # check should rarely trigger, but we keep it for robustness
           if (node1.is_a?(Nokogiri::HTML4::DocumentFragment) ||
               node1.is_a?(Nokogiri::XML::DocumentFragment)) &&
               (node2.is_a?(Nokogiri::HTML4::DocumentFragment) ||
@@ -117,10 +126,8 @@ module Canon
             all_children2 = node2.children.to_a
 
             # Filter children based on match options (e.g., ignore comments)
-            children1 = XmlComparator.send(:filter_children, all_children1,
-                                           opts)
-            children2 = XmlComparator.send(:filter_children, all_children2,
-                                           opts)
+            children1 = XmlNodeComparison.filter_children(all_children1, opts)
+            children2 = XmlNodeComparison.filter_children(all_children2, opts)
 
             if children1.length != children2.length
               result = Comparison::UNEQUAL_ELEMENTS
@@ -130,9 +137,10 @@ module Canon
               # Compare each pair of children
               result = Comparison::EQUIVALENT
               children1.zip(children2).each do |child1, child2|
-                child_result = XmlComparator.send(:compare_nodes, child1, child2,
-                                                  opts, child_opts, diff_children,
-                                                  differences)
+                child_result = XmlNodeComparison.compare_nodes(child1, child2,
+                                                               opts, child_opts,
+                                                               diff_children,
+                                                               differences)
                 if child_result != Comparison::EQUIVALENT
                   result = child_result
                   break
@@ -140,8 +148,9 @@ module Canon
               end
             end
           else
-            result = XmlComparator.send(:compare_nodes, node1, node2, opts,
-                                        child_opts, diff_children, differences)
+            result = XmlNodeComparison.compare_nodes(node1, node2, opts,
+                                                     child_opts, diff_children,
+                                                     differences)
           end
 
           # Classify DiffNodes as normative/informative if we have verbose output
@@ -287,7 +296,16 @@ module Canon
                         end
 
           # Strip DOCTYPE for consistent parsing
-          html_string = html_string.gsub(/<!DOCTYPE[^>]*>/i, "").strip
+          # Use non-regex approach to avoid ReDoS vulnerability
+          # DOCTYPE declarations end with first > character
+          doctype_start = html_string =~ /<!DOCTYPE/i
+          if doctype_start
+            doctype_end = html_string.index(">", doctype_start)
+            html_string = html_string[0...doctype_start] + html_string[(doctype_end + 1)..] if doctype_end
+            html_string.strip!
+          else
+            html_string = html_string.strip
+          end
 
           # Apply preprocessing to HTML string before parsing
           processed_html = case preprocessing
@@ -313,8 +331,15 @@ module Canon
 
         # Parse a node from string or return as-is
         # Applies preprocessing transformation before parsing if specified
-        # For DOM comparison, returns Nokogiri nodes (not Canon::Xml::Node)
+        # Returns Nokogiri nodes for DOM comparison (preserves original behavior)
         def parse_node(node, preprocessing = :none, match_opts = {})
+          # If already a Canon::Xml::Node, convert to Nokogiri for DOM path
+          if node.is_a?(Canon::Xml::Node)
+            # Canon nodes used in semantic diff path, convert to Nokogiri for DOM path
+            xml_str = Canon::Xml::DataModel.serialize(node)
+            node = xml_str
+          end
+
           # If already a Nokogiri node, check for incompatible XML documents
           unless node.is_a?(String)
             # Detect if this is an XML document (not HTML)
@@ -357,7 +382,15 @@ module Canon
 
           # Strip DOCTYPE declarations from HTML strings
           # This normalizes parsed HTML (which includes DOCTYPE) with raw HTML strings
-          node = node.gsub(/<!DOCTYPE[^>]*>/i, "").strip
+          # Use non-regex approach to avoid ReDoS vulnerability
+          doctype_start = node =~ /<!DOCTYPE/i
+          if doctype_start
+            doctype_end = node.index(">", doctype_start)
+            node = node[0...doctype_start] + node[(doctype_end + 1)..] if doctype_end
+            node.strip!
+          else
+            node = node.strip
+          end
 
           # Apply preprocessing to HTML string before parsing
           html_string = case preprocessing
@@ -380,10 +413,12 @@ module Canon
           # Use XML fragment parser to avoid auto-inserted meta tags
           frag = Nokogiri::XML.fragment(html_string)
 
-          # Apply :rendered preprocessing if needed
-          if preprocessing == :rendered
+          # Apply post-parsing filtering for :normalize, :format, and :rendered preprocessing
+          if %i[normalize format rendered].include?(preprocessing)
             normalize_html_style_script_comments(frag)
-            normalize_rendered_whitespace(frag, match_opts)
+            if preprocessing == :rendered
+              normalize_rendered_whitespace(frag, match_opts)
+            end
             remove_whitespace_only_text_nodes(frag)
           end
 
@@ -461,9 +496,9 @@ module Canon
         # @param node [Canon::Xml::Node, Nokogiri::HTML::Document] Parsed node
         # @return [String] Serialized HTML string
         def serialize_for_display(node)
-          # Use XmlComparator's serializer for Canon::Xml::Node
+          # Use XmlNodeComparison's serializer for Canon::Xml::Node
           if node.is_a?(Canon::Xml::Node)
-            XmlComparator.send(:serialize_node_to_xml, node)
+            XmlNodeComparison.serialize_node_to_xml(node)
           elsif node.respond_to?(:to_html)
             node.to_html
           elsif node.respond_to?(:to_xml)
@@ -509,16 +544,22 @@ compare_profile = nil)
           return if match_opts[:text_content] == :strict
 
           # Elements where whitespace is significant - don't normalize
-          # Use profile if available, otherwise use default list
+          # SINGLE SOURCE OF TRUTH: WhitespaceSensitivity.format_default_sensitive_elements
+          # This ensures consistency between preprocessing and comparison logic
+          # SINGLE SOURCE OF TRUTH: WhitespaceSensitivity.format_default_sensitive_elements
+          # This ensures consistency between preprocessing and comparison logic
           preserve_whitespace = if compare_profile.is_a?(HtmlCompareProfile)
                                   # Profile handles HTML-specific whitespace rules
-                                  %w[pre code textarea script
-                                     style].select do |elem|
-                                    compare_profile.preserve_whitespace?(elem)
-                                  end
+                                  # Get default list and filter by profile
+                                  WhitespaceSensitivity
+                                    .format_default_sensitive_elements(match_opts)
+                                    .select do |elem|
+                                      compare_profile.preserve_whitespace?(elem.to_s)
+                                    end
+                                    .map(&:to_s)
                                 else
-                                  # Fallback to default list
-                                  %w[pre code textarea script style]
+                                  # Use default list from WhitespaceSensitivity (single source of truth)
+                                  WhitespaceSensitivity.format_default_sensitive_elements(match_opts).map(&:to_s)
                                 end
 
           # Walk all text nodes
@@ -574,9 +615,12 @@ compare_profile = nil)
         #
         # CRITICAL: Do NOT remove whitespace-only text nodes from whitespace-sensitive
         # elements like <pre>, <code>, <textarea>, <script>, <style>
+        #
+        # SINGLE SOURCE OF TRUTH: Uses WhitespaceSensitivity.format_default_sensitive_elements
         def remove_whitespace_only_text_nodes(doc)
           # Elements where whitespace is significant - don't remove whitespace-only nodes
-          preserve_whitespace = %w[pre code textarea script style]
+          # SINGLE SOURCE OF TRUTH: WhitespaceSensitivity.format_default_sensitive_elements
+          preserve_whitespace = WhitespaceSensitivity.format_default_sensitive_elements(format: :html).map(&:to_s)
 
           doc.xpath(".//text()").each do |text_node|
             # CRITICAL: Skip if this text node is inside a whitespace-preserving element

data/lib/canon/comparison/html_compare_profile.rb

@@ -1,6 +1,8 @@
 # frozen_string_literal: true
 
 require_relative "compare_profile"
+# Whitespace sensitivity module (single source of truth for sensitive elements)
+require_relative "whitespace_sensitivity"
 
 module Canon
   module Comparison
@@ -82,9 +84,13 @@ module Canon
       private
 
       # Elements where whitespace is semantically significant in HTML
-      # @return [Array<String>] List of element names
+      #
+      # SINGLE SOURCE OF TRUTH: Delegates to WhitespaceSensitivity.format_default_sensitive_elements
+      # This ensures consistency across the codebase.
+      #
+      # @return [Array<String>] List of element names (as strings)
       def whitespace_sensitive_elements
-        %w[pre code textarea script style]
+        WhitespaceSensitivity.format_default_sensitive_elements(format: @html_version).map(&:to_s)
       end
 
       # Check if a dimension is explicitly set to :strict

data/lib/canon/comparison/html_parser.rb

@@ -0,0 +1,80 @@
+# frozen_string_literal: true
+
+require "nokogiri"
+
+module Canon
+  module Comparison
+    # HTML parsing service with version detection and fragment support
+    #
+    # Provides HTML parsing capabilities with automatic HTML4/HTML5 version
+    # detection. Handles both full documents and fragments.
+    #
+    # @example Parse HTML string
+    #   HtmlParser.parse("<div>content</div>", :html5)
+    #
+    # @example Auto-detect and parse
+    #   HtmlParser.detect_and_parse("<!DOCTYPE html><html>...</html>")
+    class HtmlParser
+      class << self
+        # Parse HTML string into Nokogiri document with the correct parser
+        #
+        # @param content [String, Object] Content to parse (returns as-is if not a string)
+        # @param format [Symbol] HTML format (:html, :html4, :html5)
+        # @return [Nokogiri::HTML::Document, Nokogiri::HTML5::Document, Nokogiri::HTML::DocumentFragment, Object]
+        def parse(content, format)
+          return content unless content.is_a?(String)
+          return content if already_parsed?(content)
+
+          begin
+            case format
+            when :html5
+              Nokogiri::HTML5.fragment(content)
+            when :html4
+              Nokogiri::HTML4.fragment(content)
+            when :html
+              detect_and_parse(content)
+            else
+              content
+            end
+          rescue StandardError
+            # Fallback to raw string if parsing fails (maintains backward compatibility)
+            content
+          end
+        end
+
+        # Check if content is already a parsed HTML document/fragment
+        #
+        # @param content [Object] Content to check
+        # @return [Boolean] true if already parsed
+        def already_parsed?(content)
+          content.is_a?(Nokogiri::HTML::Document) ||
+            content.is_a?(Nokogiri::HTML5::Document) ||
+            content.is_a?(Nokogiri::HTML::DocumentFragment) ||
+            content.is_a?(Nokogiri::HTML5::DocumentFragment)
+        end
+
+        # Detect HTML version from content and parse with appropriate parser
+        #
+        # @param content [String] HTML content to parse
+        # @return [Nokogiri::HTML::DocumentFragment] Parsed fragment
+        def detect_and_parse(content)
+          version = detect_version(content)
+          if version == :html5
+            Nokogiri::HTML5.fragment(content)
+          else
+            Nokogiri::HTML4.fragment(content)
+          end
+        end
+
+        # Detect HTML version from content string
+        #
+        # @param content [String] HTML content
+        # @return [Symbol] :html5 or :html4
+        def detect_version(content)
+          # Check for HTML5 DOCTYPE (case-insensitive)
+          content.include?("<!DOCTYPE html>") ? :html5 : :html4
+        end
+      end
+    end
+  end
+end

data/lib/canon/comparison/json_comparator.rb

@@ -125,6 +125,18 @@ module Canon
           if match_opts[:key_order] != :strict
             keys1 = keys1.sort_by(&:to_s)
             keys2 = keys2.sort_by(&:to_s)
+          elsif keys1 != keys2
+            # Strict mode: key order matters
+            # Check if keys are in same order
+            # Keys are different or in different order
+            # First check if it's just ordering (same keys, different order)
+            if keys1.sort_by(&:to_s) == keys2.sort_by(&:to_s)
+              # Same keys, different order - this is a key_order difference
+              key_path = path.empty? ? "(key order)" : "#{path}.(key order)"
+              add_ruby_difference(key_path, keys1, keys2,
+                                  Comparison::UNEQUAL_HASH_KEY_ORDER, opts, differences)
+              return Comparison::UNEQUAL_HASH_KEY_ORDER
+            end
           end
 
           # Check for missing keys

data/lib/canon/comparison/json_parser.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Canon
+  module Comparison
+    # Public API for JSON parsing operations
+    # Provides access to parsing functionality without using send()
+    class JsonParser
+      # Parse an object to Ruby object
+      #
+      # @param obj [String, Hash, Array] Object to parse
+      # @return [Hash, Array] Parsed Ruby object
+      def self.parse_json(obj)
+        # Delegate to JsonComparator's private method via public API
+        require_relative "json_comparator"
+        JsonComparator.parse_json(obj)
+      end
+    end
+  end
+end

data/lib/canon/comparison/markup_comparator.rb

@@ -0,0 +1,293 @@
+# frozen_string_literal: true
+
+require_relative "../comparison" # Load base module with constants
+require_relative "../diff/diff_node"
+require_relative "../diff/path_builder"
+
+module Canon
+  module Comparison
+    # Base class for markup document comparison (XML, HTML)
+    #
+    # Provides shared comparison functionality for markup documents,
+    # including node type checking, text extraction, filtering,
+    # and difference creation.
+    #
+    # Format-specific comparators (XmlComparator, HtmlComparator)
+    # inherit from this class and add format-specific behavior.
+    class MarkupComparator
+      class << self
+        # Add a difference to the differences array
+        #
+        # Creates a DiffNode with enriched metadata including path,
+        # serialized content, and attributes for Stage 4 rendering.
+        #
+        # @param node1 [Object, nil] First node
+        # @param node2 [Object, nil] Second node
+        # @param diff1 [Symbol] Difference type for node1
+        # @param diff2 [Symbol] Difference type for node2
+        # @param dimension [Symbol] The match dimension causing this difference
+        # @param _opts [Hash] Options (unused but kept for interface compatibility)
+        # @param differences [Array] Array to append difference to
+        def add_difference(node1, node2, diff1, diff2, dimension, _opts,
+                           differences)
+          # All differences must be DiffNode objects (OO architecture)
+          if dimension.nil?
+            raise ArgumentError,
+                  "dimension required for DiffNode"
+          end
+
+          # Build informative reason message
+          reason = build_difference_reason(node1, node2, diff1, diff2,
+                                           dimension)
+
+          # Enrich with path, serialized content, and attributes for Stage 4 rendering
+          metadata = enrich_diff_metadata(node1, node2)
+
+          diff_node = Canon::Diff::DiffNode.new(
+            node1: node1,
+            node2: node2,
+            dimension: dimension,
+            reason: reason,
+            **metadata,
+          )
+          differences << diff_node
+        end
+
+        # Enrich DiffNode with canonical path, serialized content, and attributes
+        # This extracts presentation-ready metadata from nodes for Stage 4 rendering
+        #
+        # @param node1 [Object, nil] First node
+        # @param node2 [Object, nil] Second node
+        # @return [Hash] Enriched metadata hash
+        def enrich_diff_metadata(node1, node2)
+          {
+            path: build_path_for_node(node1 || node2),
+            serialized_before: serialize_node(node1),
+            serialized_after: serialize_node(node2),
+            attributes_before: extract_attributes(node1),
+            attributes_after: extract_attributes(node2),
+          }
+        end
+
+        # Build canonical path for a node
+        #
+        # @param node [Object] Node to build path for
+        # @return [String, nil] Canonical path with ordinal indices
+        def build_path_for_node(node)
+          return nil if node.nil?
+
+          Canon::Diff::PathBuilder.build(node, format: :document)
+        end
+
+        # Serialize a node to string for display
+        #
+        # @param node [Object, nil] Node to serialize
+        # @return [String, nil] Serialized content
+        def serialize_node(node)
+          return nil if node.nil?
+
+          # Canon::Xml::Node types
+          if node.is_a?(Canon::Xml::Nodes::RootNode)
+            # Serialize all children of root
+            node.children.map { |child| serialize_node(child) }.join
+          elsif node.is_a?(Canon::Xml::Nodes::ElementNode)
+            serialize_element_node(node)
+          elsif node.is_a?(Canon::Xml::Nodes::TextNode)
+            node.value
+          elsif node.is_a?(Canon::Xml::Nodes::CommentNode)
+            "<!--#{node.value}-->"
+          elsif node.is_a?(Canon::Xml::Nodes::ProcessingInstructionNode)
+            "<?#{node.target} #{node.data}?>"
+          elsif node.respond_to?(:to_xml)
+            node.to_xml
+          elsif node.respond_to?(:to_html)
+            node.to_html
+          else
+            node.to_s
+          end
+        end
+
+        # Extract attributes from a node
+        #
+        # @param node [Object, nil] Node to extract attributes from
+        # @return [Hash, nil] Hash of attribute name => value pairs
+        def extract_attributes(node)
+          return nil if node.nil?
+
+          # Canon::Xml::Node ElementNode
+          if node.is_a?(Canon::Xml::Nodes::ElementNode)
+            node.attribute_nodes.each_with_object({}) do |attr, hash|
+              hash[attr.name] = attr.value
+            end
+          # Nokogiri nodes
+          elsif node.respond_to?(:attributes)
+            node.attributes.each_with_object({}) do |(_, attr), hash|
+              hash[attr.name] = attr.value
+            end
+          else
+            {}
+          end
+        end
+
+        # Filter children based on options
+        #
+        # Removes nodes that should be excluded from comparison based on
+        # options like :ignore_nodes, :ignore_comments, etc.
+        #
+        # @param children [Array] Array of child nodes
+        # @param opts [Hash] Comparison options
+        # @return [Array] Filtered array of children
+        def filter_children(children, opts)
+          children.reject do |child|
+            node_excluded?(child, opts)
+          end
+        end
+
+        # Check if node should be excluded from comparison
+        #
+        # @param node [Object] Node to check
+        # @param opts [Hash] Comparison options
+        # @return [Boolean] true if node should be excluded
+        def node_excluded?(node, opts)
+          return false if node.nil?
+          return true if opts[:ignore_nodes]&.include?(node)
+          return true if opts[:ignore_comments] && comment_node?(node)
+          return true if opts[:ignore_text_nodes] && text_node?(node)
+
+          # Check structural_whitespace match option
+          match_opts = opts[:match_opts]
+          # Filter out whitespace-only text nodes
+          if match_opts && %i[ignore
+                              normalize].include?(match_opts[:structural_whitespace]) && text_node?(node)
+            text = node_text(node)
+            return true if MatchOptions.normalize_text(text).empty?
+          end
+
+          false
+        end
+
+        # Check if two nodes are the same type
+        #
+        # @param node1 [Object] First node
+        # @param node2 [Object] Second node
+        # @return [Boolean] true if nodes are same type
+        def same_node_type?(node1, node2)
+          return false if node1.class != node2.class
+
+          # For Nokogiri/Canon::Xml nodes, check node type
+          if node1.respond_to?(:node_type) && node2.respond_to?(:node_type)
+            node1.node_type == node2.node_type
+          else
+            true
+          end
+        end
+
+        # Check if a node is a comment node
+        #
+        # @param node [Object] Node to check
+        # @return [Boolean] true if node is a comment
+        def comment_node?(node)
+          node.respond_to?(:comment?) && node.comment? ||
+            node.respond_to?(:node_type) && node.node_type == :comment
+        end
+
+        # Check if a node is a text node
+        #
+        # @param node [Object] Node to check
+        # @return [Boolean] true if node is a text node
+        def text_node?(node)
+          node.respond_to?(:text?) && node.text? &&
+            !node.respond_to?(:element?) ||
+            node.respond_to?(:node_type) && node.node_type == :text
+        end
+
+        # Get text content from a node
+        #
+        # @param node [Object] Node to get text from
+        # @return [String] Text content
+        def node_text(node)
+          # Canon::Xml::Node TextNode uses .value
+          if node.respond_to?(:value)
+            node.value.to_s
+          # Nokogiri nodes use .content
+          elsif node.respond_to?(:content)
+            node.content.to_s
+          else
+            node.to_s
+          end
+        end
+
+        # Check if difference between two texts is only whitespace
+        #
+        # @param text1 [String] First text
+        # @param text2 [String] Second text
+        # @return [Boolean] true if difference is only in whitespace
+        def whitespace_only_difference?(text1, text2)
+          # Normalize both texts (collapse/trim whitespace)
+          norm1 = MatchOptions.normalize_text(text1)
+          norm2 = MatchOptions.normalize_text(text2)
+
+          # If normalized texts are the same, the difference was only whitespace
+          norm1 == norm2
+        end
+
+        # Build a human-readable reason for a difference
+        #
+        # @param node1 [Object, nil] First node
+        # @param node2 [Object, nil] Second node
+        # @param diff1 [Symbol] Difference type for node1
+        # @param diff2 [Symbol] Difference type for node2
+        # @param dimension [Symbol] The dimension of the difference
+        # @return [String] Human-readable reason
+        def build_difference_reason(_node1, _node2, diff1, diff2, dimension)
+          # Default reason - can be overridden in subclasses
+          "Difference in #{dimension}: #{diff1} vs #{diff2}"
+        end
+
+        # Serialize an element node to string
+        #
+        # @param node [Canon::Xml::Nodes::ElementNode] Element node
+        # @return [String] Serialized element
+        def serialize_element_node(node)
+          attrs = node.attribute_nodes.map do |a|
+            " #{a.name}=\"#{a.value}\""
+          end.join
+          children_xml = node.children.map { |c| serialize_node(c) }.join
+
+          if children_xml.empty?
+            "<#{node.name}#{attrs}/>"
+          else
+            "<#{node.name}#{attrs}>#{children_xml}</#{node.name}>"
+          end
+        end
+
+        # Determine the appropriate dimension for a node type
+        #
+        # @param node [Object] The node to check
+        # @return [Symbol] The dimension symbol
+        def determine_node_dimension(node)
+          # Canon::Xml::Node types
+          if node.respond_to?(:node_type) && node.node_type.is_a?(Symbol)
+            case node.node_type
+            when :comment then :comments
+            when :text, :cdata then :text_content
+            when :processing_instruction then :processing_instructions
+            else :text_content
+            end
+          # Moxml/Nokogiri types
+          elsif node.respond_to?(:comment?) && node.comment?
+            :comments
+          elsif node.respond_to?(:text?) && node.text?
+            :text_content
+          elsif node.respond_to?(:cdata?) && node.cdata?
+            :text_content
+          elsif node.respond_to?(:processing_instruction?) && node.processing_instruction?
+            :processing_instructions
+          else
+            :text_content
+          end
+        end
+      end
+    end
+  end
+end