canon 0.1.3 → 0.1.5

data/lib/canon/xml/whitespace_normalizer.rb

@@ -0,0 +1,72 @@
+# frozen_string_literal: true
+
+module Canon
+  module Xml
+    # Handles whitespace normalization for flexible XML/HTML comparison
+    #
+    # Provides methods for normalizing different categories of whitespace:
+    # 1. Indentation whitespace
+    # 2. Inter-element whitespace (between tags)
+    # 3. Text content whitespace (within text nodes)
+    # 4. Tag boundary whitespace (inside tags)
+    # 5. Attribute formatting (handled by existing ignore_attr_order)
+    class WhitespaceNormalizer
+      # Normalize text content by collapsing all whitespace sequences
+      # to single spaces and trimming leading/trailing whitespace
+      #
+      # @param text [String] Text to normalize
+      # @return [String] Normalized text
+      def normalize_text_content(text)
+        return "" if text.nil?
+
+        text.to_s
+          .gsub(/\s+/, " ")  # Collapse all whitespace sequences to single space
+          .strip             # Remove leading/trailing whitespace
+      end
+
+      # Normalize indentation by removing all leading whitespace from each line
+      #
+      # @param text [String] Text with indentation
+      # @return [String] Text with indentation removed
+      def normalize_indentation(text)
+        return "" if text.nil?
+
+        text.to_s
+          .lines
+          .map(&:lstrip) # Remove leading whitespace from each line
+          .join
+      end
+
+      # Normalize inter-element whitespace (whitespace between tags)
+      # This removes whitespace-only text nodes between elements
+      #
+      # @param node [Moxml::Node] Node to check
+      # @return [Boolean] true if node is whitespace-only and should be ignored
+      def inter_element_whitespace?(node)
+        return false unless node.respond_to?(:text?) && node.text?
+
+        text = node.respond_to?(:content) ? node.content.to_s : node.text.to_s
+        text.strip.empty?
+      end
+
+      # Normalize tag boundary whitespace
+      # This is the same as normalizing text content for now,
+      # but kept separate for clarity
+      #
+      # @param text [String] Text at tag boundary
+      # @return [String] Normalized text
+      def normalize_tag_boundaries(text)
+        normalize_text_content(text)
+      end
+
+      # Check if two text strings are equivalent under flexible whitespace rules
+      #
+      # @param text1 [String] First text
+      # @param text2 [String] Second text
+      # @return [Boolean] true if equivalent after normalization
+      def flexible_equivalent?(text1, text2)
+        normalize_text_content(text1) == normalize_text_content(text2)
+      end
+    end
+  end
+end

data/lib/canon/xml/xml_base_handler.rb

@@ -0,0 +1,188 @@
+# frozen_string_literal: true
+
+require "uri"
+
+module Canon
+  module Xml
+    # Handler for xml:base fixup in document subsets
+    # Implements RFC 3986 URI joining with C14N 1.1 modifications
+    class XmlBaseHandler
+      # Perform xml:base fixup on an element
+      # Returns the fixed-up xml:base value or nil if no fixup needed
+      def fixup_xml_base(element, omitted_ancestors)
+        return nil if omitted_ancestors.empty?
+
+        # Collect xml:base values from omitted ancestors
+        base_values = collect_base_values(element, omitted_ancestors)
+        return nil if base_values.empty?
+
+        # Join the base values in reverse document order
+        join_base_values(base_values)
+      end
+
+      private
+
+      # Collect xml:base attribute values from element and omitted ancestors
+      def collect_base_values(element, omitted_ancestors)
+        values = []
+
+        # Collect from omitted ancestors (in document order)
+        omitted_ancestors.each do |ancestor|
+          base_attr = ancestor.attribute_nodes.find(&:xml_base?)
+          values << base_attr.value if base_attr
+        end
+
+        # Add element's own xml:base if present
+        element_base = element.attribute_nodes.find(&:xml_base?)
+        values << element_base.value if element_base
+
+        values
+      end
+
+      # Join URI references per RFC 3986 with C14N 1.1 modifications
+      def join_base_values(values)
+        result = values.first
+
+        values[1..].each do |ref|
+          result = join_uri_references(result, ref)
+        end
+
+        result
+      end
+
+      # Join two URI references per RFC 3986 sections 5.2.1, 5.2.2, 5.2.4
+      # with C14N 1.1 modifications
+      # rubocop:disable Metrics/MethodLength
+      def join_uri_references(base, ref)
+        # Parse reference (ignore fragment per C14N 1.1)
+        ref_parts = parse_uri(ref)
+
+        # If ref has a scheme, return ref (without fragment)
+        if ref_parts[:scheme]
+          return remove_dot_segments(ref_parts[:path] || "")
+        end
+
+        # Parse base
+        base_parts = parse_uri(base)
+
+        # Build result
+        result_parts = {}
+
+        if ref_parts[:authority]
+          result_parts[:authority] = ref_parts[:authority]
+          result_parts[:path] = remove_dot_segments(ref_parts[:path] || "")
+          result_parts[:query] = ref_parts[:query]
+        else
+          if ref_parts[:path].nil? || ref_parts[:path].empty?
+            result_parts[:path] = base_parts[:path]
+            result_parts[:query] = ref_parts[:query] || base_parts[:query]
+          else
+            if ref_parts[:path].start_with?("/")
+              result_parts[:path] = remove_dot_segments(ref_parts[:path])
+            else
+              result_parts[:path] = merge_paths(base_parts[:path],
+                                                ref_parts[:path])
+              result_parts[:path] = remove_dot_segments(result_parts[:path])
+            end
+            result_parts[:query] = ref_parts[:query]
+          end
+          result_parts[:authority] = base_parts[:authority]
+        end
+
+        result_parts[:scheme] = base_parts[:scheme]
+
+        # Reconstruct URI
+        reconstruct_uri(result_parts)
+      end
+
+      # Parse URI into components
+      def parse_uri(uri_str)
+        parts = {}
+
+        # Simple regex-based parsing
+        if uri_str =~ %r{^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?}
+          parts[:scheme] = Regexp.last_match(2)
+          parts[:authority] = Regexp.last_match(4)
+          parts[:path] = Regexp.last_match(5)
+          parts[:query] = Regexp.last_match(7)
+        end
+
+        parts
+      end
+
+      # Merge paths per RFC 3986 section 5.2.3
+      def merge_paths(base_path, ref_path)
+        if base_path&.include?("/")
+          base_path.sub(%r{/[^/]*$}, "/#{ref_path}")
+        else
+          ref_path
+        end
+      end
+
+      # Remove dot segments per RFC 3986 section 5.2.4
+      # with C14N 1.1 modifications
+      # rubocop:disable Metrics/MethodLength
+      def remove_dot_segments(path)
+        input = path.dup
+        output = ""
+
+        # Replace trailing ".." with "../"
+        input = input.sub(%r{/\.\.$}, "/../")
+
+        while input.length.positive?
+          # A: If input starts with "../" or "./"
+          if input.start_with?("../")
+            input = input[3..]
+          elsif input.start_with?("./")
+            input = input[2..]
+          # B: If input starts with "/./" or is "/."
+          elsif input.start_with?("/./")
+            input = "/#{input[3..]}"
+          elsif input == "/."
+            input = "/"
+          # C: If input starts with "/../" or is "/.."
+          elsif input.start_with?("/../")
+            input = "/#{input[4..]}"
+            output = output.sub(%r{/[^/]*$}, "")
+          elsif input == "/.."
+            input = "/"
+            output = output.sub(%r{/[^/]*$}, "")
+          # D: If input is "." or ".."
+          elsif [".", ".."].include?(input)
+            input = ""
+          # E: Move first path segment to output
+          else
+            seg_match = if input.start_with?("/")
+                          input.match(%r{^(/[^/]*)})
+                        else
+                          input.match(/^([^\/]*)/)
+                        end
+            seg = seg_match[1]
+            input = input[seg.length..]
+            output += seg
+          end
+        end
+
+        # Replace multiple consecutive "/" with single "/"
+        output = output.squeeze("/")
+
+        # Append "/" to trailing ".."
+        output += "/" if output.end_with?("/..")
+
+        output
+      end
+
+      # Reconstruct URI from parts
+      def reconstruct_uri(parts)
+        result = ""
+
+        result += "#{parts[:scheme]}:" if parts[:scheme]
+        result += "//#{parts[:authority]}" if parts[:authority]
+        result += parts[:path] if parts[:path]
+        result += "?#{parts[:query]}" if parts[:query]
+
+        result
+      end
+    end
+  end
+end

data/lib/canon.rb

@@ -1,14 +1,19 @@
 # frozen_string_literal: true
 
 require_relative "canon/version"
+require_relative "canon/errors"
 require_relative "canon/formatters/xml_formatter"
 require_relative "canon/formatters/yaml_formatter"
 require_relative "canon/formatters/json_formatter"
+require_relative "canon/formatters/html_formatter"
+require_relative "canon/formatters/html4_formatter"
+require_relative "canon/formatters/html5_formatter"
+require_relative "canon/comparison"
 
 require_relative "canon/rspec_matchers" if defined?(::RSpec)
 
 module Canon
-  SUPPORTED_FORMATS = %i[xml yaml json].freeze
+  SUPPORTED_FORMATS = %i[xml yaml json html html4 html5 string].freeze
 
   # Format content based on the specified format type
   # @param content [String] The content to format
@@ -26,6 +31,7 @@ module Canon
     get_formatter(format).parse(content)
   end
 
+  # rubocop:disable Metrics/MethodLength
   def self.get_formatter(format)
     case format.to_sym
     when :xml
@@ -34,10 +40,17 @@ module Canon
       Formatters::YamlFormatter
     when :json
       Formatters::JsonFormatter
+    when :html
+      Formatters::HtmlFormatter
+    when :html4
+      Formatters::Html4Formatter
+    when :html5
+      Formatters::Html5Formatter
     else
       raise Error, "Unsupported format: #{format}"
     end
   end
+  # rubocop:enable Metrics/MethodLength
 
   # Define shorthand methods for each supported format
   # Creates parse_{format} and format_{format} methods
@@ -50,6 +63,4 @@ module Canon
       format(content, format)
     end
   end
-
-  class Error < StandardError; end
 end

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: canon
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.5
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-08-24 00:00:00.000000000 Z
+date: 2025-10-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: compare-xml
+  name: diff-lcs
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -25,7 +25,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: diffy
+  name: json
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -39,7 +39,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: json
+  name: moxml
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -67,13 +67,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: paint
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -81,13 +81,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: table_tennis
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -95,13 +95,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rubocop
+  name: thor
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -109,24 +109,27 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rubocop-performance
+  name: unicode-name
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: Library for canonicalizing and pretty-printing XML, YAML, and JSON with
-  RSpec matchers for equivalence testing
+description: |-
+  Canon provides canonicalization and pretty-printing for various serialization
+  formats (XML, HTML, JSON, YAML), producing standardized forms suitable for
+  comparison, testing, digital signatures, and human-readable output.
 email:
 - open.source@ribose.com
-executables: []
+executables:
+- canon
 extensions: []
 extra_rdoc_files: []
 files:
@@ -136,21 +139,112 @@ files:
 - CODE_OF_CONDUCT.md
 - README.adoc
 - Rakefile
+- _config.yml
+- docs/ADVANCED_TOPICS.adoc
+- docs/BASIC_USAGE.adoc
+- docs/CHARACTER_VISUALIZATION.adoc
+- docs/CLI.adoc
+- docs/CUSTOMIZING_BEHAVIOR.adoc
+- docs/DIFF_ARCHITECTURE.adoc
+- docs/DIFF_FORMATTING.adoc
+- docs/FORMATS.adoc
+- docs/INDEX.adoc
+- docs/INPUT_VALIDATION.adoc
+- docs/MATCH_ARCHITECTURE.adoc
+- docs/MATCH_OPTIONS.adoc
+- docs/MODES.adoc
+- docs/NORMATIVE_INFORMATIVE_DIFFS.adoc
+- docs/OPTIONS.adoc
+- docs/PREPROCESSING.adoc
+- docs/RSPEC.adoc
+- docs/RUBY_API.adoc
+- docs/SEMANTIC_DIFF_REPORT.adoc
+- docs/UNDERSTANDING_CANON.adoc
+- docs/VERBOSE.adoc
+- exe/canon
 - lib/canon.rb
+- lib/canon/cli.rb
+- lib/canon/commands/diff_command.rb
+- lib/canon/commands/format_command.rb
+- lib/canon/comparison.rb
+- lib/canon/comparison/base_comparator.rb
+- lib/canon/comparison/comparison_result.rb
+- lib/canon/comparison/html_comparator.rb
+- lib/canon/comparison/json_comparator.rb
+- lib/canon/comparison/match_options.rb
+- lib/canon/comparison/xml_comparator.rb
+- lib/canon/comparison/yaml_comparator.rb
+- lib/canon/config.rb
+- lib/canon/diff/diff_block.rb
+- lib/canon/diff/diff_block_builder.rb
+- lib/canon/diff/diff_classifier.rb
+- lib/canon/diff/diff_context.rb
+- lib/canon/diff/diff_context_builder.rb
+- lib/canon/diff/diff_line.rb
+- lib/canon/diff/diff_node.rb
+- lib/canon/diff/diff_node_mapper.rb
+- lib/canon/diff/diff_report.rb
+- lib/canon/diff/diff_report_builder.rb
+- lib/canon/diff_formatter.rb
+- lib/canon/diff_formatter/by_line/base_formatter.rb
+- lib/canon/diff_formatter/by_line/html_formatter.rb
+- lib/canon/diff_formatter/by_line/json_formatter.rb
+- lib/canon/diff_formatter/by_line/simple_formatter.rb
+- lib/canon/diff_formatter/by_line/xml_formatter.rb
+- lib/canon/diff_formatter/by_line/yaml_formatter.rb
+- lib/canon/diff_formatter/by_object/base_formatter.rb
+- lib/canon/diff_formatter/by_object/json_formatter.rb
+- lib/canon/diff_formatter/by_object/xml_formatter.rb
+- lib/canon/diff_formatter/by_object/yaml_formatter.rb
+- lib/canon/diff_formatter/character_map.yml
+- lib/canon/diff_formatter/debug_output.rb
+- lib/canon/diff_formatter/diff_detail_formatter.rb
+- lib/canon/diff_formatter/legend.rb
+- lib/canon/errors.rb
+- lib/canon/formatters/html4_formatter.rb
+- lib/canon/formatters/html5_formatter.rb
+- lib/canon/formatters/html_formatter.rb
+- lib/canon/formatters/html_formatter_base.rb
 - lib/canon/formatters/json_formatter.rb
 - lib/canon/formatters/xml_formatter.rb
 - lib/canon/formatters/yaml_formatter.rb
+- lib/canon/pretty_printer/html.rb
+- lib/canon/pretty_printer/json.rb
+- lib/canon/pretty_printer/xml.rb
 - lib/canon/rspec_matchers.rb
+- lib/canon/validators/base_validator.rb
+- lib/canon/validators/html_validator.rb
+- lib/canon/validators/json_validator.rb
+- lib/canon/validators/xml_validator.rb
+- lib/canon/validators/yaml_validator.rb
 - lib/canon/version.rb
+- lib/canon/xml/attribute_handler.rb
+- lib/canon/xml/c14n.rb
+- lib/canon/xml/character_encoder.rb
+- lib/canon/xml/data_model.rb
+- lib/canon/xml/element_matcher.rb
+- lib/canon/xml/line_range_mapper.rb
+- lib/canon/xml/namespace_handler.rb
+- lib/canon/xml/node.rb
+- lib/canon/xml/nodes/attribute_node.rb
+- lib/canon/xml/nodes/comment_node.rb
+- lib/canon/xml/nodes/element_node.rb
+- lib/canon/xml/nodes/namespace_node.rb
+- lib/canon/xml/nodes/processing_instruction_node.rb
+- lib/canon/xml/nodes/root_node.rb
+- lib/canon/xml/nodes/text_node.rb
+- lib/canon/xml/processor.rb
+- lib/canon/xml/whitespace_normalizer.rb
+- lib/canon/xml/xml_base_handler.rb
 - lib/xml-c14n.rb
 - sig/xml/c14n.rbs
-homepage: https://github.com/metanorma/canon
+homepage: https://github.com/lutaml/canon
 licenses:
 - BSD-2-Clause
 metadata:
-  homepage_uri: https://github.com/metanorma/canon
-  source_code_uri: https://github.com/metanorma/canon
-  changelog_uri: https://github.com/metanorma/canon
+  homepage_uri: https://github.com/lutaml/canon
+  source_code_uri: https://github.com/lutaml/canon
+  changelog_uri: https://github.com/lutaml/canon
 post_install_message:
 rdoc_options: []
 require_paths:
@@ -169,5 +263,6 @@ requirements: []
 rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
-summary: Library for canonicalization of serialization formats
+summary: Canonicalization, formatting and comparison library for serialization formats
+  (XML, HTML, JSON, YAML)
 test_files: []