canon 0.2.11 → 0.2.12

data/lib/tasks/performance_report.rb

@@ -0,0 +1,309 @@
+# frozen_string_literal: true
+
+require "benchmark/ips"
+require "json"
+require "securerandom"
+require "stringio"
+require "time"
+require "yaml"
+
+lib_path = File.expand_path(File.join(__dir__, "..", "..", "lib"))
+$LOAD_PATH.unshift(lib_path) unless $LOAD_PATH.include?(lib_path)
+
+require "canon"
+
+begin
+  require "canon/xml/sax_builder"
+  SAX_AVAILABLE = true
+rescue LoadError
+  SAX_AVAILABLE = false
+end
+
+# Standalone benchmark runner that emits JSON results on stdout.
+#
+# Used by performance_comparator.rb to run benchmarks in a clean Ruby
+# process per branch — sharing no state with the comparator itself.
+# This isolates each branch's Canon implementation from the other.
+module Performance
+  REPORT_ID = SecureRandom.hex(4).freeze
+
+  DEFAULT_RUN_TIME = Integer(ENV.fetch("CANON_PERF_RUN_TIME", "5"))
+  DEFAULT_WARMUP   = Integer(ENV.fetch("CANON_PERF_WARMUP", "2"))
+  DEFAULT_ITEMS    = Integer(ENV.fetch("CANON_PERF_ITEMS", "50"))
+
+  BENCHMARKS = {
+    xml_parse_dom_simple: { category: "xml_parsing",    name: "DOM (simple)" },
+    xml_parse_sax_simple: { category: "xml_parsing",    name: "SAX (simple)" },
+    xml_parse_dom_large: { category: "xml_parsing",    name: "DOM (large)" },
+    xml_parse_sax_large: { category: "xml_parsing",    name: "SAX (large)" },
+    html_parse_simple: { category: "html_parsing", name: "Simple HTML" },
+    html_parse_complex: { category: "html_parsing", name: "Complex HTML" },
+    xml_compare_identical: { category: "xml_comparison", name: "Identical XML" },
+    xml_compare_similar: { category: "xml_comparison", name: "Similar XML" },
+    xml_compare_different: { category: "xml_comparison", name: "Different XML" },
+    html_compare_identical: { category: "html_comparison", name: "Identical HTML" },
+    html_compare_similar: { category: "html_comparison", name: "Similar HTML" },
+    html_compare_different: { category: "html_comparison", name: "Different HTML" },
+    xml_c14n_format: { category: "formatting", name: "XML C14N" },
+    json_format: { category: "formatting",     name: "JSON" },
+    yaml_format: { category: "formatting",     name: "YAML" },
+  }.freeze
+
+  module DataGenerator
+    DEFAULT_ITEMS = Performance::DEFAULT_ITEMS
+
+    class << self
+      def generate_xml(items: DEFAULT_ITEMS, depth: 1, with_namespaces: false,
+                       with_attributes: true)
+        ns = with_namespaces ? 'xmlns:ns="http://example.org"' : ""
+        prefix = with_namespaces ? "ns:" : ""
+
+        build_xml_element(items, depth, prefix, with_attributes, ns)
+      end
+
+      def build_xml_element(items, depth, prefix, with_attrs, ns_decl)
+        attrs = with_attrs ? " id=\"#{rand(1000)}\" status=\"active\"" : ""
+        ns_attr = ns_decl.empty? ? "" : " #{ns_decl}"
+
+        if depth <= 1
+          children = Array.new(items) do |i|
+            inner_attrs = with_attrs ? " index=\"#{i}\"" : ""
+            "<#{prefix}item#{inner_attrs}>Item #{i} content with some text</#{prefix}item>"
+          end.join
+          "<#{prefix}root#{ns_attr}#{attrs}>#{children}</#{prefix}root>"
+        else
+          child = build_xml_element(items / 2, depth - 1, prefix, with_attrs,
+                                    "")
+          "<#{prefix}root#{ns_attr}#{attrs}>#{child}</#{prefix}root>"
+        end
+      end
+
+      def generate_html(items: DEFAULT_ITEMS, with_scripts: false,
+                        with_tables: false)
+        scripts = if with_scripts
+                    <<~HTML
+                      <script type="text/javascript">
+                        function test() { return true; }
+                      </script>
+                      <style>
+                        body { margin: 0; }
+                      </style>
+                    HTML
+                  else
+                    ""
+                  end
+
+        tables = if with_tables
+                   rows = Array.new(items) do |i|
+                     "<tr><td>Cell #{i}A</td><td>Cell #{i}B</td></tr>"
+                   end.join
+                   "<table>#{rows}</table>"
+                 else
+                   ""
+                 end
+
+        list_items = Array.new(items) do |i|
+          "<li class=\"item-#{i}\">List item #{i} with bold text</li>"
+        end.join("\n              ")
+
+        nav_count = [(items / 5), 2].max
+        nav_items = items.times.first(nav_count).map do |i|
+          "<li class=\"nav-#{i}\">Nav #{i}</li>"
+        end.join("\n                ")
+
+        <<~HTML
+          <!DOCTYPE html>
+          <html lang="en">
+          <head>
+            <meta charset="UTF-8">
+            <title>Benchmark Document</title>
+            #{scripts}
+          </head>
+          <body>
+            <header>
+              <h1>Benchmark Test Document</h1>
+              <nav>
+                <ul>
+                #{nav_items}
+                </ul>
+              </nav>
+            </header>
+            <main>
+              <section id="content">
+                <p>This is a paragraph with emphasized and strong text.</p>
+                <ul>
+                #{list_items}
+                </ul>
+                #{tables}
+              </section>
+            </main>
+            <footer>
+              <p>Copyright 2024</p>
+            </footer>
+          </body>
+          </html>
+        HTML
+      end
+
+      def generate_json(items: DEFAULT_ITEMS)
+        data = {
+          metadata: { version: "1.0", generated: Time.now.iso8601 },
+          items: Array.new(items) do |i|
+            {
+              id: i,
+              name: "Item #{i}",
+              value: rand * 1000,
+              tags: ["tag1", "tag2", "tag#{i % 10}"],
+              nested: {
+                level1: { level2: { data: "deeply nested value #{i}" } },
+              },
+            }
+          end,
+        }
+        JSON.generate(data)
+      end
+
+      def generate_yaml(items: DEFAULT_ITEMS)
+        JSON.parse(generate_json(items: items)).to_yaml
+      end
+
+      def generate_large_xml(items: 500)
+        generate_xml(items: items, depth: 3, with_namespaces: true,
+                     with_attributes: true)
+      end
+    end
+  end
+
+  class Report
+    def initialize(run_time: DEFAULT_RUN_TIME, warmup: DEFAULT_WARMUP,
+                   items: DEFAULT_ITEMS)
+      @run_time = run_time
+      @warmup = warmup
+      @items = items
+      @results = {}
+    end
+
+    def run_all
+      BENCHMARKS.each do |method, meta|
+        next if method.to_s.start_with?("xml_parse_sax") && !SAX_AVAILABLE
+
+        label = "#{meta[:category]}: #{meta[:name]}"
+        @results[label] = run_benchmark(method)
+      end
+      @results
+    end
+
+    def as_json
+      {
+        report_id: REPORT_ID,
+        ruby_version: RUBY_VERSION,
+        platform: RUBY_PLATFORM,
+        run_time: @run_time,
+        warmup: @warmup,
+        items: @items,
+        sax_available: SAX_AVAILABLE,
+        benchmarks: @results,
+      }
+    end
+
+    private
+
+    def run_benchmark(method)
+      original_stdout = $stdout
+      $stdout = StringIO.new
+      begin
+        job = Benchmark::IPS::Job.new
+        job.config(time: @run_time, warmup: @warmup)
+        job.report("test") { dispatch(method) }
+        job.run
+
+        entry = job.full_report.entries.first
+      ensure
+        $stdout = original_stdout
+      end
+
+      samples = entry.stats.samples
+      return { lower: 0, upper: 0 } if samples.empty?
+
+      mean = samples.sum.to_f / samples.size
+      variance = samples.sum { |x| (x - mean)**2 } / (samples.size - 1)
+      std_dev = Math.sqrt(variance)
+      error_margin = std_dev / mean
+      error_pct = error_margin.round(4)
+
+      # Clamp lower bound to positive — for very fast operations the
+      # error margin can exceed the mean, producing nonsensical
+      # negative IPS values that break the regression comparison.
+      lower = (mean * (1 - error_pct)).round(4)
+      lower = (mean * 0.5).round(4) if lower <= 0
+      upper = (mean * (1 + error_pct)).round(4)
+
+      { lower: lower, upper: upper }
+    end
+
+    def dispatch(method)
+      case method
+      when :xml_parse_dom_simple
+        Canon::Xml::DataModel.from_xml(DataGenerator.generate_xml(items: @items))
+      when :xml_parse_sax_simple
+        Canon::Xml::SaxBuilder.parse(DataGenerator.generate_xml(items: @items))
+      when :xml_parse_dom_large
+        Canon::Xml::DataModel.from_xml(DataGenerator.generate_large_xml(items: @items * 5))
+      when :xml_parse_sax_large
+        Canon::Xml::SaxBuilder.parse(DataGenerator.generate_large_xml(items: @items * 5))
+      when :html_parse_simple
+        Canon.parse_html(DataGenerator.generate_html(items: @items))
+      when :html_parse_complex
+        Canon.parse_html(DataGenerator.generate_html(items: @items,
+                                                     with_scripts: true,
+                                                     with_tables: true))
+      when :xml_compare_identical
+        xml = DataGenerator.generate_xml(items: @items)
+        Canon::Comparison.equivalent?(xml, xml, format: :xml)
+      when :xml_compare_similar
+        Canon::Comparison.equivalent?(
+          DataGenerator.generate_xml(items: @items),
+          DataGenerator.generate_xml(items: @items),
+          format: :xml,
+        )
+      when :xml_compare_different
+        Canon::Comparison.equivalent?(
+          DataGenerator.generate_xml(items: @items),
+          DataGenerator.generate_xml(items: @items, with_namespaces: true),
+          format: :xml,
+        )
+      when :html_compare_identical
+        html = DataGenerator.generate_html(items: @items)
+        Canon::Comparison.equivalent?(html, html, format: :html)
+      when :html_compare_similar
+        Canon::Comparison.equivalent?(
+          DataGenerator.generate_html(items: @items),
+          DataGenerator.generate_html(items: @items),
+          format: :html,
+        )
+      when :html_compare_different
+        Canon::Comparison.equivalent?(
+          DataGenerator.generate_html(items: @items),
+          DataGenerator.generate_html(items: @items, with_tables: true),
+          format: :html,
+        )
+      when :xml_c14n_format
+        Canon.format_xml(DataGenerator.generate_xml(items: @items,
+                                                    with_namespaces: true))
+      when :json_format
+        Canon.format_json(JSON.parse(DataGenerator.generate_json(items: @items)))
+      when :yaml_format
+        Canon.format_yaml(YAML.safe_load(DataGenerator.generate_yaml(items: @items),
+                                         permitted_classes: [Time]))
+      else
+        raise "Unknown benchmark: #{method}"
+      end
+    end
+  end
+end
+
+if $PROGRAM_NAME == __FILE__
+  report = Performance::Report.new
+  report.run_all
+  puts JSON.generate(report.as_json)
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: canon
 version: !ruby/object:Gem::Version
-  version: 0.2.11
+  version: 0.2.12
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-05-29 00:00:00.000000000 Z
+date: 2026-06-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: diff-lcs
@@ -219,6 +219,7 @@ files:
 - lib/canon/cache.rb
 - lib/canon/cli.rb
 - lib/canon/color_detector.rb
+- lib/canon/commands.rb
 - lib/canon/commands/diff_command.rb
 - lib/canon/commands/format_command.rb
 - lib/canon/comparison.rb
@@ -226,16 +227,11 @@ files:
 - lib/canon/comparison/child_realignment.rb
 - lib/canon/comparison/compare_profile.rb
 - lib/canon/comparison/comparison_result.rb
+- lib/canon/comparison/diff_node_builder.rb
 - lib/canon/comparison/dimensions.rb
-- lib/canon/comparison/dimensions/attribute_order_dimension.rb
-- lib/canon/comparison/dimensions/attribute_presence_dimension.rb
-- lib/canon/comparison/dimensions/attribute_values_dimension.rb
-- lib/canon/comparison/dimensions/base_dimension.rb
-- lib/canon/comparison/dimensions/comments_dimension.rb
-- lib/canon/comparison/dimensions/element_position_dimension.rb
+- lib/canon/comparison/dimensions/dimension.rb
+- lib/canon/comparison/dimensions/dimension_set.rb
 - lib/canon/comparison/dimensions/registry.rb
-- lib/canon/comparison/dimensions/structural_whitespace_dimension.rb
-- lib/canon/comparison/dimensions/text_content_dimension.rb
 - lib/canon/comparison/format_detector.rb
 - lib/canon/comparison/html_comparator.rb
 - lib/canon/comparison/html_compare_profile.rb
@@ -249,8 +245,10 @@ files:
 - lib/canon/comparison/match_options/xml_resolver.rb
 - lib/canon/comparison/match_options/yaml_resolver.rb
 - lib/canon/comparison/node_inspector.rb
+- lib/canon/comparison/pipeline.rb
 - lib/canon/comparison/profile_definition.rb
 - lib/canon/comparison/ruby_object_comparator.rb
+- lib/canon/comparison/strategies.rb
 - lib/canon/comparison/strategies/base_match_strategy.rb
 - lib/canon/comparison/strategies/match_strategy_factory.rb
 - lib/canon/comparison/strategies/semantic_tree_match_strategy.rb
@@ -259,14 +257,15 @@ files:
 - lib/canon/comparison/xml_comparator/attribute_comparator.rb
 - lib/canon/comparison/xml_comparator/attribute_filter.rb
 - lib/canon/comparison/xml_comparator/child_comparison.rb
-- lib/canon/comparison/xml_comparator/diff_node_builder.rb
 - lib/canon/comparison/xml_comparator/namespace_comparator.rb
 - lib/canon/comparison/xml_comparator/node_parser.rb
 - lib/canon/comparison/xml_comparator/node_type_comparator.rb
+- lib/canon/comparison/xml_comparator_helpers.rb
 - lib/canon/comparison/xml_node_comparison.rb
 - lib/canon/comparison/xml_parser.rb
 - lib/canon/comparison/yaml_comparator.rb
 - lib/canon/config.rb
+- lib/canon/config/config_dsl.rb
 - lib/canon/config/env_provider.rb
 - lib/canon/config/env_schema.rb
 - lib/canon/config/override_resolver.rb
@@ -275,6 +274,7 @@ files:
 - lib/canon/config/profiles/metanorma_debug.yml
 - lib/canon/config/type_converter.rb
 - lib/canon/data_model.rb
+- lib/canon/diff.rb
 - lib/canon/diff/diff_block.rb
 - lib/canon/diff/diff_block_builder.rb
 - lib/canon/diff/diff_char_range.rb
@@ -315,10 +315,12 @@ files:
 - lib/canon/diff_formatter/diff_detail_formatter/location_extractor.rb
 - lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb
 - lib/canon/diff_formatter/diff_detail_formatter/text_utils.rb
+- lib/canon/diff_formatter/diff_detail_formatter_helpers.rb
 - lib/canon/diff_formatter/legend.rb
 - lib/canon/diff_formatter/pretty_diff_formatter.rb
 - lib/canon/diff_formatter/theme.rb
 - lib/canon/errors.rb
+- lib/canon/formatters.rb
 - lib/canon/formatters/html4_formatter.rb
 - lib/canon/formatters/html5_formatter.rb
 - lib/canon/formatters/html_formatter.rb
@@ -328,8 +330,10 @@ files:
 - lib/canon/formatters/yaml_formatter.rb
 - lib/canon/html.rb
 - lib/canon/html/data_model.rb
+- lib/canon/options.rb
 - lib/canon/options/cli_generator.rb
 - lib/canon/options/registry.rb
+- lib/canon/pretty_printer.rb
 - lib/canon/pretty_printer/html.rb
 - lib/canon/pretty_printer/html_void_elements.rb
 - lib/canon/pretty_printer/json.rb
@@ -337,34 +341,41 @@ files:
 - lib/canon/pretty_printer/xml_normalized.rb
 - lib/canon/rspec_matchers.rb
 - lib/canon/tree_diff.rb
+- lib/canon/tree_diff/adapters.rb
 - lib/canon/tree_diff/adapters/html_adapter.rb
 - lib/canon/tree_diff/adapters/json_adapter.rb
 - lib/canon/tree_diff/adapters/xml_adapter.rb
 - lib/canon/tree_diff/adapters/yaml_adapter.rb
+- lib/canon/tree_diff/core.rb
 - lib/canon/tree_diff/core/attribute_comparator.rb
 - lib/canon/tree_diff/core/matching.rb
 - lib/canon/tree_diff/core/node_signature.rb
 - lib/canon/tree_diff/core/node_weight.rb
 - lib/canon/tree_diff/core/tree_node.rb
 - lib/canon/tree_diff/core/xml_entity_decoder.rb
+- lib/canon/tree_diff/matchers.rb
 - lib/canon/tree_diff/matchers/hash_matcher.rb
 - lib/canon/tree_diff/matchers/similarity_matcher.rb
 - lib/canon/tree_diff/matchers/structural_propagator.rb
 - lib/canon/tree_diff/matchers/universal_matcher.rb
 - lib/canon/tree_diff/operation_converter.rb
+- lib/canon/tree_diff/operation_converter_helpers.rb
 - lib/canon/tree_diff/operation_converter_helpers/metadata_enricher.rb
 - lib/canon/tree_diff/operation_converter_helpers/post_processor.rb
 - lib/canon/tree_diff/operation_converter_helpers/reason_builder.rb
 - lib/canon/tree_diff/operation_converter_helpers/update_change_handler.rb
+- lib/canon/tree_diff/operations.rb
 - lib/canon/tree_diff/operations/operation.rb
 - lib/canon/tree_diff/operations/operation_detector.rb
 - lib/canon/tree_diff/tree_diff_integrator.rb
+- lib/canon/validators.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.rb
 - lib/canon/xml/attribute_handler.rb
 - lib/canon/xml/c14n.rb
 - lib/canon/xml/character_encoder.rb
@@ -374,6 +385,7 @@ files:
 - lib/canon/xml/namespace_handler.rb
 - lib/canon/xml/namespace_helper.rb
 - lib/canon/xml/node.rb
+- lib/canon/xml/nodes.rb
 - lib/canon/xml/nodes/attribute_node.rb
 - lib/canon/xml/nodes/comment_node.rb
 - lib/canon/xml/nodes/element_node.rb
@@ -392,6 +404,7 @@ files:
 - lib/tasks/performance.rake
 - lib/tasks/performance_comparator.rb
 - lib/tasks/performance_helpers.rb
+- lib/tasks/performance_report.rb
 - lib/xml-c14n.rb
 - sig/xml/c14n.rbs
 homepage: https://github.com/lutaml/canon

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

@@ -1,64 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "base_dimension"
-
-module Canon
-  module Comparison
-    module Dimensions
-      # Attribute order dimension
-      #
-      # Handles comparison of attribute ordering.
-      # Supports :strict and :ignore behaviors.
-      #
-      # Behaviors:
-      # - :strict - Attributes must appear in the same order
-      # - :ignore - Attribute order doesn't matter
-      class AttributeOrderDimension < BaseDimension
-        # Extract attribute order from a node
-        #
-        # @param node [Moxml::Node, Nokogiri::XML::Node] Node to extract from
-        # @return [Array<Symbol>] Array of attribute names in order
-        def extract_data(node)
-          return [] unless node
-
-          if Canon::XmlBackend.nokogiri?
-            extract_from_nokogiri(node)
-          else
-            extract_from_moxml(node)
-          end
-        end
-
-        # Strict attribute order comparison
-        #
-        # @param order1 [Array<Symbol>] First attribute order
-        # @param order2 [Array<Symbol>] Second attribute order
-        # @return [Boolean] true if attribute order is exactly the same
-        def compare_strict(order1, order2) # rubocop:disable Naming/PredicateMethod
-          order1 == order2
-        end
-
-        private
-
-        # Extract attribute order from Moxml node
-        #
-        # @param node [Moxml::Node] Moxml node
-        # @return [Array<Symbol>] Array of attribute names in order
-        def extract_from_moxml(node)
-          return [] unless node.node_type == :element
-
-          node.attributes.map { |attr| attr.name.to_sym }
-        end
-
-        # Extract attribute order from Nokogiri node
-        #
-        # @param node [Nokogiri::XML::Node] Nokogiri node
-        # @return [Array<Symbol>] Array of attribute names in order
-        def extract_from_nokogiri(node)
-          return [] unless node.node_type == Nokogiri::XML::Node::ELEMENT_NODE
-
-          node.attribute_nodes.map { |attr| attr.name.to_sym }
-        end
-      end
-    end
-  end
-end

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

@@ -1,64 +0,0 @@
-# frozen_string_literal: true
-
-require_relative "base_dimension"
-
-module Canon
-  module Comparison
-    module Dimensions
-      # Attribute presence dimension
-      #
-      # Handles comparison of attribute presence (which attributes exist).
-      # Supports :strict and :ignore behaviors.
-      #
-      # Behaviors:
-      # - :strict - Attribute names must match exactly
-      # - :ignore - Skip attribute presence comparison
-      class AttributePresenceDimension < BaseDimension
-        # Extract attribute names from a node
-        #
-        # @param node [Moxml::Node, Nokogiri::XML::Node] Node to extract from
-        # @return [Array<Symbol>] Array of attribute names
-        def extract_data(node)
-          return [] unless node
-
-          if Canon::XmlBackend.nokogiri?
-            extract_from_nokogiri(node)
-          else
-            extract_from_moxml(node)
-          end
-        end
-
-        # Strict attribute presence comparison
-        #
-        # @param names1 [Array<Symbol>] First attribute names
-        # @param names2 [Array<Symbol>] Second attribute names
-        # @return [Boolean] true if attribute names are exactly equal
-        def compare_strict(names1, names2) # rubocop:disable Naming/PredicateMethod
-          names1.sort == names2.sort
-        end
-
-        private
-
-        # Extract attribute names from Moxml node
-        #
-        # @param node [Moxml::Node] Moxml node
-        # @return [Array<Symbol>] Array of attribute names
-        def extract_from_moxml(node)
-          return [] unless node.node_type == :element
-
-          node.attributes.map { |attr| attr.name.to_sym }
-        end
-
-        # Extract attribute names from Nokogiri node
-        #
-        # @param node [Nokogiri::XML::Node] Nokogiri node
-        # @return [Array<Symbol>] Array of attribute names
-        def extract_from_nokogiri(node)
-          return [] unless node.node_type == Nokogiri::XML::Node::ELEMENT_NODE
-
-          node.attribute_nodes.map { |attr| attr.name.to_sym }
-        end
-      end
-    end
-  end
-end