canon 0.1.18 → 0.1.19

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 34ab9a64b52d8598690536908941e38950bb4071fb6222b50d1cb584236e5286
-  data.tar.gz: 2dffcc8e29fcd1f75d78595ef73350208e7b369f2183c2df93672b94df7a6376
+  metadata.gz: fae901023e2945c8ee14c48a6de4ce793d2735d9f2b098ba9f727b9c0f10e8ad
+  data.tar.gz: 84ed342a12b39a77394275e6159eb16cc60f331c80ed161a6cd4fccc957dc06d
 SHA512:
-  metadata.gz: 41d784c820a7bbafd9874bf369ef303376578e74f7171e8f00a7ed1ed0b8800576ca67f51272f1464f6f36cbaec35b6f1f1e9806916e7a8c59bc6c04e827ee79
-  data.tar.gz: d3e354615ed4b40447ae0be7de64bf6250c40650e25f897a5155f52a74f57a8601003efd37d539abf9f514d5cbe614298a2185db7d72b68b4ff95db6da1b5b99
+  metadata.gz: d88d544b3b961dfa5c0f9fb806f51a473e29b0a018a22dbc9ea2aebaaf459a3aa6317d1cb22c2d5dd32d69eb6162389be274a06886566ab9b63f83e613c4b276
+  data.tar.gz: cc409487c2c38791ec915584a8ebca85672ac7add362c78b5ace99bfd1a1657c6907ac387f321dbc12eda2613ffe998ae7fecdfce6895ff5e285f1f6022d250f

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-03-24 08:58:24 UTC using RuboCop version 1.85.1.
+# on 2026-03-24 10:43:04 UTC using RuboCop version 1.85.1.
 # 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
@@ -11,15 +11,13 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'canon.gemspec'
 
-# Offense count: 10
+# Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, IndentationWidth.
 # SupportedStyles: with_first_argument, with_fixed_indentation
 Layout/ArgumentAlignment:
   Exclude:
-    - 'lib/canon/xml/data_model.rb'
-    - 'spec/canon/comparison/encoding_normalization_spec.rb'
-    - 'spec/canon/comparison/xml_whitespace_spec.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb'
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
@@ -27,46 +25,61 @@ Layout/ArgumentAlignment:
 # SupportedStyles: with_first_element, with_fixed_indentation
 Layout/ArrayAlignment:
   Exclude:
-    - 'lib/canon/comparison/format_detector.rb'
+    - 'lib/canon/diff/path_builder.rb'
+
+# Offense count: 6
+# This cop supports safe autocorrection (--autocorrect).
+Layout/ElseAlignment:
+  Exclude:
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
+
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyleAlignWith.
+# SupportedStylesAlignWith: keyword, variable, start_of_line
+Layout/EndAlignment:
+  Exclude:
+    - 'lib/canon/diff/path_builder.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
-Layout/EmptyLineAfterGuardClause:
+# Configuration parameters: AllowForAlignment, AllowBeforeTrailingComments, ForceEqualSignAlignment.
+Layout/ExtraSpacing:
   Exclude:
-    - 'lib/canon/xml/data_model.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/text_utils.rb'
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: AllowMultipleStyles, EnforcedHashRocketStyle, EnforcedColonStyle, EnforcedLastArgumentHashStyle.
-# SupportedHashRocketStyles: key, separator, table
-# SupportedColonStyles: key, separator, table
-# SupportedLastArgumentHashStyles: always_inspect, always_ignore, ignore_implicit, ignore_explicit
-Layout/HashAlignment:
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: normal, indented_internal_methods
+Layout/IndentationConsistency:
   Exclude:
-    - 'lib/canon/comparison/format_detector.rb'
+    - 'lib/canon/diff/path_builder.rb'
+
+# Offense count: 8
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
+# SupportedStylesAlignWith: start_of_line, relative_to_receiver
+Layout/IndentationWidth:
+  Exclude:
+    - 'lib/canon/diff/path_builder.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
 
-# Offense count: 831
+# Offense count: 841
 # 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: 9
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: EnforcedStyle.
-# SupportedStyles: symmetrical, new_line, same_line
-Layout/MultilineMethodCallBraceLayout:
-  Exclude:
-    - 'spec/canon/comparison/encoding_normalization_spec.rb'
-    - 'spec/canon/comparison/xml_whitespace_spec.rb'
-
-# Offense count: 2
+# Offense count: 3
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowInHeredoc.
 Layout/TrailingWhitespace:
   Exclude:
-    - 'lib/canon/comparison/format_detector.rb'
+    - 'lib/canon/diff/path_builder.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb'
 
 # Offense count: 49
 # Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
@@ -97,13 +110,6 @@ Lint/UnreachableCode:
   Exclude:
     - 'lib/canon/diff_formatter/debug_output.rb'
 
-# Offense count: 1
-# This cop supports safe autocorrection (--autocorrect).
-# Configuration parameters: IgnoreEmptyBlocks, AllowUnusedKeywordArguments.
-Lint/UnusedBlockArgument:
-  Exclude:
-    - 'lib/canon/xml/data_model.rb'
-
 # Offense count: 6
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowUnusedKeywordArguments, IgnoreEmptyMethods, IgnoreNotImplementedMethods, NotImplementedExceptions.
@@ -115,7 +121,7 @@ Lint/UnusedMethodArgument:
     - 'lib/canon/diff_formatter/by_line/xml_formatter.rb'
     - 'lib/canon/diff_formatter/by_object/base_formatter.rb'
 
-# Offense count: 236
+# Offense count: 238
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Enabled: false
@@ -126,12 +132,12 @@ Metrics/AbcSize:
 Metrics/BlockLength:
   Max: 84
 
-# Offense count: 193
+# Offense count: 196
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Enabled: false
 
-# Offense count: 403
+# Offense count: 405
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 95
@@ -141,7 +147,7 @@ Metrics/MethodLength:
 Metrics/ParameterLists:
   Max: 9
 
-# Offense count: 160
+# Offense count: 162
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Enabled: false
@@ -172,19 +178,13 @@ Performance/CollectionLiteralInLoop:
     - 'lib/canon/comparison/html_comparator.rb'
     - 'lib/canon/xml/xml_base_handler.rb'
 
-# Offense count: 1
-# This cop supports unsafe autocorrection (--autocorrect-all).
-Performance/UnfreezeString:
-  Exclude:
-    - 'spec/canon/comparison/encoding_normalization_spec.rb'
-
 # Offense count: 68
 # Configuration parameters: Prefixes, AllowedPatterns.
 # Prefixes: when, with, without
 RSpec/ContextWording:
   Enabled: false
 
-# Offense count: 29
+# Offense count: 30
 # Configuration parameters: IgnoredMetadata.
 RSpec/DescribeClass:
   Enabled: false
@@ -195,7 +195,7 @@ RSpec/DescribeMethod:
     - 'spec/canon/comparison/multiple_differences_spec.rb'
     - 'spec/canon/diff_formatter/character_map_customization_spec.rb'
 
-# Offense count: 695
+# Offense count: 699
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 43
@@ -247,7 +247,7 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/canon/comparison/match_options_spec.rb'
 
-# Offense count: 536
+# Offense count: 537
 RSpec/MultipleExpectations:
   Max: 15
 
@@ -298,7 +298,7 @@ RSpec/SpecFilePathFormat:
     - 'spec/canon/yaml/formatter_spec.rb'
     - 'spec/xml_c14n_spec.rb'
 
-# Offense count: 126
+# Offense count: 128
 # Configuration parameters: IgnoreNameless, IgnoreSymbolicNames.
 RSpec/VerifiedDoubles:
   Exclude:
@@ -307,19 +307,9 @@ RSpec/VerifiedDoubles:
     - '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: 1
-# 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/encoding_normalization_spec.rb'
-
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, AllowComments.
@@ -342,12 +332,12 @@ Style/IdenticalConditionalBranches:
     - 'lib/canon/diff_formatter/by_object/base_formatter.rb'
     - 'lib/canon/diff_formatter/legend.rb'
 
-# Offense count: 1
+# Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowMethodComparison, ComparisonsThreshold.
 Style/MultipleComparison:
   Exclude:
-    - 'lib/canon/comparison/format_detector.rb'
+    - 'lib/canon/diff/path_builder.rb'
 
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
@@ -355,3 +345,24 @@ Style/MultipleComparison:
 Style/OptionalBooleanParameter:
   Exclude:
     - 'lib/canon/diff_formatter/debug_output.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Style/RedundantParentheses:
+  Exclude:
+    - 'lib/canon/diff/path_builder.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowModifier.
+Style/SoleNestedConditional:
+  Exclude:
+    - 'lib/canon/diff/path_builder.rb'
+
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyleForMultiline.
+# SupportedStylesForMultiline: comma, consistent_comma, diff_comma, no_comma
+Style/TrailingCommaInArguments:
+  Exclude:
+    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'

data/lib/canon/diff/path_builder.rb

@@ -83,6 +83,20 @@ module Canon
         # Get ordinal index (position among siblings with same label)
         index = ordinal_index(tree_node)
 
+        # For text nodes, use parent element name for clarity
+        # e.g., instead of "/p/#text[0]" use "/p/text()[0]"
+        if ["text",
+            "#text"].include?(label) && tree_node.respond_to?(:parent) && tree_node.parent
+          parent_name = if tree_node.parent.respond_to?(:label)
+                          tree_node.parent.label
+                        elsif tree_node.parent.respond_to?(:name)
+                          tree_node.parent.name
+                        end
+          if parent_name && parent_name != "#document" && parent_name != "#document-fragment"
+            return "#{parent_name}/text()[#{index}]"
+          end
+        end
+
         "#{label}[#{index}]"
       end
 

data/lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb

@@ -340,10 +340,24 @@ module Canon
               TextUtils.visualize_whitespace(text2), :green, use_color
             )
           else
-            detail1 = ColorHelper.colorize(format_json_value(text1), :red,
-                                           use_color)
-            detail2 = ColorHelper.colorize(format_json_value(text2), :green,
-                                           use_color)
+            # Escape non-ASCII characters for better terminal display
+            # JSON.generate doesn't escape chars like NBSP (U+00A0) or em-dash (U+2014)
+            detail1 = if TextUtils.needs_escaping?(text1)
+                        ColorHelper.colorize(
+                          TextUtils.escape_for_display(text1), :red, use_color
+                        )
+                      else
+                        ColorHelper.colorize(format_json_value(text1), :red,
+                                             use_color)
+                      end
+            detail2 = if TextUtils.needs_escaping?(text2)
+                        ColorHelper.colorize(
+                          TextUtils.escape_for_display(text2), :green, use_color
+                        )
+                      else
+                        ColorHelper.colorize(format_json_value(text2), :green,
+                                             use_color)
+                      end
           end
 
           changes = "Content differs: #{detail1} → #{detail2}"

data/lib/canon/diff_formatter/diff_detail_formatter/location_extractor.rb

@@ -16,7 +16,12 @@ module Canon
         def self.extract_location(diff)
           return "" unless diff
 
-          # Get the appropriate node based on diff type
+          # Prefer pre-computed path if available (populated by MetadataEnricher)
+          if diff.respond_to?(:path) && !diff.path.nil? && !diff.path.empty?
+            return "Location: #{diff.path}"
+          end
+
+          # Fall back to extracting from nodes
           node = if diff.respond_to?(:node1)
                    diff.node1 || diff.node2
                  elsif diff.is_a?(Hash)

data/lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb

@@ -159,21 +159,47 @@ module Canon
         def self.get_node_text(node)
           return "" unless node
 
-          if node.respond_to?(:text)
-            node.text
-          elsif node.respond_to?(:content)
-            node.content
-          elsif node.respond_to?(:inner_text)
-            node.inner_text
-          elsif node.respond_to?(:value)
-            node.value
-          elsif node.respond_to?(:node_info)
-            node.node_info
-          elsif node.respond_to?(:to_s)
-            node.to_s
-          else
-            ""
-          end.to_s.strip
+          text = if node.respond_to?(:text)
+                   node.text
+                 elsif node.respond_to?(:content)
+                   node.content
+                 elsif node.respond_to?(:inner_text)
+                   node.inner_text
+                 elsif node.respond_to?(:value)
+                   node.value
+                 elsif node.respond_to?(:node_info)
+                   node.node_info
+                 elsif node.respond_to?(:to_s)
+                   node.to_s
+                 else
+                   ""
+                 end
+
+          strip_ascii_whitespace(text.to_s)
+        end
+
+        # Strip only ASCII whitespace (space, tab, CR, LF) but preserve Unicode
+        # whitespace like non-breaking space (\u00A0). Ruby's String#strip removes
+        # all Unicode whitespace, which destroys meaningful content like \u00A0.
+        #
+        # @param str [String] String to strip
+        # @return [String] String with leading/trailing ASCII whitespace removed
+        ASCII_WHITESPACE_BYTES = [32, 9, 13, 10].freeze # ' ', '\t', '\r', '\n'
+
+        def self.strip_ascii_whitespace(str)
+          return "" if str.nil?
+          return str if str.empty?
+
+          # Find first non-ASCII-whitespace character position
+          first_pos = str.index(/[^ \t\r\n]/)
+          return "" unless first_pos
+
+          # Find last non-ASCII-whitespace character position (from end)
+          # Use reverse and index, then convert back to forward position
+          reversed_pos = str.reverse.index(/[^ \t\r\n]/)
+          last_pos = str.length - 1 - reversed_pos
+
+          str[first_pos..last_pos]
         end
 
         # Get element name for display

data/lib/canon/diff_formatter/diff_detail_formatter/text_utils.rb

@@ -20,7 +20,8 @@ module Canon
 
         # Visualize whitespace characters in text
         #
-        # Shows spaces as ·, tabs as →, newlines as ¬
+        # Shows spaces as ·, tabs as →, newlines as ¬, and Unicode whitespace
+        # like non-breaking space as <NBSP>, etc.
         #
         # @param text [String] Text to visualize
         # @return [String] Text with visible whitespace
@@ -31,6 +32,9 @@ module Canon
             .gsub(" ", "·")
             .gsub("\t", "→")
             .gsub("\n", "¬")
+            .gsub("\u00A0", "<NBSP>") # Non-breaking space
+            .gsub("\u2028", "<LSEP>")    # Line separator
+            .gsub("\u2029", "<PSEP>")    # Paragraph separator
         end
 
         # Extract a content preview from a node
@@ -55,6 +59,42 @@ module Canon
           text = text.strip.gsub(/\s+/, " ")
           truncate_text(text, max_length)
         end
+
+        # Escape non-ASCII and non-printable characters for display
+        #
+        # Converts characters outside the printable ASCII range (32-126) to
+        # their \uXXXX escape sequences. This ensures special characters like
+        # non-breaking space (\u00A0) and em-dash (\u2014) are visible in
+        # terminal output.
+        #
+        # @param text [String] Text to escape
+        # @return [String] Escaped text safe for terminal display
+        def self.escape_for_display(text)
+          return "" if text.nil?
+
+          text.chars.map do |c|
+            codepoint = c.ord
+            if codepoint < 32 || codepoint >= 127 || codepoint == 34 || codepoint == 92
+              # Escape control characters, non-ASCII, double-quote, and backslash
+              "\\u#{codepoint.to_s(16).upcase.rjust(4, '0')}"
+            else
+              c
+            end
+          end.join
+        end
+
+        # Check if text contains non-ASCII or non-printable characters
+        #
+        # @param text [String] Text to check
+        # @return [Boolean] true if text needs escaping for display
+        def self.needs_escaping?(text)
+          return false if text.nil?
+
+          text.each_char.any? do |c|
+            codepoint = c.ord
+            codepoint < 32 || codepoint >= 127 || codepoint == 34 || codepoint == 92
+          end
+        end
       end
     end
   end

data/lib/canon/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Canon
-  VERSION = "0.1.18"
+  VERSION = "0.1.19"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: canon
 version: !ruby/object:Gem::Version
-  version: 0.1.18
+  version: 0.1.19
 platform: ruby
 authors:
 - Ribose Inc.