canon 0.3.21 → 0.3.22

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fd899c17d1512c815d189076fe08721dbe66b7d964f8bac69abde35f207b8c76
-  data.tar.gz: 205ad0b365288bf883f2ce57f68b612217151e30ae90fb0f959b29f252063826
+  metadata.gz: 4a369d56aae65493ad94c6352f01a15915eb0af020cde2c98868b7d51a8b0658
+  data.tar.gz: f667f5bf42ed4f1e581ee32951d561653187c06b74b6b996f9bcd1bb9fb0f073
 SHA512:
-  metadata.gz: 5aa4d552592cda5a55417415efb225151eb0d39d899fe0471eb26f10ceeca64ae56de786d8e807e0085264ba800cfd5937a6ec15e182e71957381414f3036105
-  data.tar.gz: b52ceb55e3ca6c6affcca3c7091a0e3f6e22d1c077b65732e7073915c3f6914cb86a61e675b11636baeb1ea09e94c223c933e961c0b366fb3e621c592a50170b
+  metadata.gz: 6741dac3a19b779fbbd9fe49edaa7f3d6c71497fe4a1cc6339eb65f0d749bcfe9e0800323cb321f4cfd35a756e0ebfab5f8740f8c3aa5e895b70d7c71adc3a84
+  data.tar.gz: 8a360875b2c5597c9e87e81eb0a8037979efa6b8166fe18155a68efc432626d4efebc1aa8ad82ea66ec398681aa1d03f83d35aa1c8fe0684e74a616f0ee96913

data/lib/canon/comparison/node_inspector.rb

@@ -68,8 +68,11 @@ module Canon
       def self.whitespace_only_text?(node)
         return false unless text_node?(node)
 
+        # This runs per child pair in the realignment walk — the
+        # zero-allocation form of `text.strip.empty?` (exactly
+        # String#strip's character set; see WhitespacePolicy).
         text = text_content(node)
-        !text.empty? && text.strip.empty?
+        !text.empty? && text.match?(Canon::Xml::WhitespacePolicy::STRIP_ONLY)
       end
 
       # --- Noise classification ---

data/lib/canon/formatters/html_formatter_base.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require "nokogiri" unless RUBY_ENGINE == "opal"
+require "set"
 
 module Canon
   module Formatters
@@ -55,6 +56,14 @@ module Canon
       WHITESPACE_SENSITIVE_ELEMENTS = %w[
         pre code textarea script style
       ].freeze
+      # Set form for the per-sibling hot lookup; Nokogiri lowercases
+      # HTML element names, so the downcase fallback only runs for
+      # unusual (already-mixed-case) input.
+      BLOCK_ELEMENT_SET = BLOCK_ELEMENTS.to_set
+      # Compiled once — building the alternation and compiling the
+      # regex per format call cost more than the gsub it drives.
+      BLOCK_SPACING_PATTERN =
+        Regexp.new("(</(?:#{BLOCK_ELEMENTS.join('|')})>)(<(?:#{BLOCK_ELEMENTS.join('|')})[\s>])").freeze
       # Format HTML using canonical form
       # @param html [String] HTML document to canonicalize
       # @return [String] Canonical form of HTML
@@ -100,6 +109,15 @@ module Canon
           next unless node.element?
           next if node.attributes.empty?
 
+          names = node.attributes.keys
+          # Already-sorted un-namespaced is the common case — removing
+          # and re-adding every attribute is expensive, so check first.
+          # Namespaced attributes must take the slow path: the
+          # remove/re-add below flattens their prefix, and skipping
+          # would change the canonical output.
+          next if names.each_cons(2).all? { |a, b| (a <=> b) <= 0 } &&
+            node.attributes.each_value.all? { |a| a.namespace.nil? }
+
           sorted_attrs = node.attributes.sort_by { |name, _| name }
           node.attributes.each_key { |name| node.remove_attribute(name) }
           sorted_attrs.each { |name, attr| node[name] = attr.value }
@@ -122,7 +140,7 @@ module Canon
           end
 
           # Handle whitespace-only text nodes
-          if node.text.strip.empty? && node.parent&.element?
+          if node.text.match?(Canon::Xml::WhitespacePolicy::STRIP_ONLY) && node.parent&.element?
             # Check if this text node is between block-level elements
             prev_sibling = node.previous_sibling
             next_sibling = node.next_sibling
@@ -138,14 +156,17 @@ module Canon
           else
             # Collapse multiple whitespace characters into single spaces
             # but preserve leading/trailing single spaces for inline content
-            normalized = node.text.gsub(/\s+/, " ")
+            text = node.text
+            normalized = text.gsub(/\s+/, " ")
             # Only strip if the entire parent chain suggests it's appropriate
             # (e.g., at document boundaries)
             if node.parent&.name == "body" &&
                 (node.previous_sibling.nil? || node.next_sibling.nil?)
               normalized = normalized.strip
             end
-            node.content = normalized
+            # node.content= re-parses the string — skip it when nothing
+            # changed (text with no collapsible whitespace).
+            node.content = normalized unless normalized == text
           end
         end
       end
@@ -154,19 +175,20 @@ module Canon
       # @param html [String] Serialized HTML string
       # @return [String] HTML with proper spacing between block elements
       def self.ensure_block_element_spacing(html)
-        # Build regex pattern for block element tags
-        block_tags = BLOCK_ELEMENTS.join("|")
-
         # Add space between closing and opening block element tags
-        # Match: ><opening_block_tag or </closing_block_tag><opening_block_tag
-        html.gsub(/(<\/(?:#{block_tags})>)(<(?:#{block_tags})[\s>])/, '\1 \2')
+        # (pattern compiled once — see BLOCK_SPACING_PATTERN)
+        html.gsub(BLOCK_SPACING_PATTERN, '\1 \2')
       end
 
       # Check if a node is a block-level element
       # @param node [Nokogiri::XML::Node, nil] Node to check
       # @return [Boolean] true if node is a block element
       def self.block_element?(node)
-        node&.element? && BLOCK_ELEMENTS.include?(node.name.downcase)
+        return false unless node&.element?
+
+        name = node.name
+        BLOCK_ELEMENT_SET.include?(name) ||
+          BLOCK_ELEMENT_SET.include?(name.downcase)
       end
 
       # Check if a node is a whitespace-sensitive element
@@ -178,8 +200,14 @@ module Canon
         # Check if this element or any ancestor is whitespace-sensitive
         current = node
         while current
-          if current.element? && WHITESPACE_SENSITIVE_ELEMENTS.include?(current.name.downcase)
-            return true
+          if current.element?
+            name = current.name
+            # Nokogiri lowercases HTML names — the downcase fallback
+            # only allocates for unusual mixed-case input.
+            if WHITESPACE_SENSITIVE_ELEMENTS.include?(name) ||
+                WHITESPACE_SENSITIVE_ELEMENTS.include?(name.downcase)
+              return true
+            end
           end
           # Stop at document root - documents don't have parents
           break if current.is_a?(Nokogiri::XML::Document) || current.is_a?(Nokogiri::HTML5::Document)

data/lib/canon/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Canon
-  VERSION = "0.3.21"
+  VERSION = "0.3.22"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: canon
 version: !ruby/object:Gem::Version
-  version: 0.3.21
+  version: 0.3.22
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-09-06 00:00:00.000000000 Z
+date: 2026-09-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: diff-lcs