canon 0.1.23 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '08086e588946bb0f5f39a8235984058b5a5e8aea956b9652e0e366ff84500232'
-  data.tar.gz: bb078d67c1a68da1ca88b3d29fde336e291b0ff95186ade125ee1ccfb1a82de4
+  metadata.gz: bfa3648b7c5308716c22fbdc377d875dc60d479eb0e376cfe347eb02a279d3d7
+  data.tar.gz: 87024447cc6a13eaa8cb9d1edf91d360e35d2e6cb5a1f2b7035c067050fae24a
 SHA512:
-  metadata.gz: 35f7888d948f86fa4b504b060ee6d9976dc38b32232e8c86b9b8986ee08448cdad265fe4d091e810e5f63f0b0702e125317e07d15761b5cd6404905190546234
-  data.tar.gz: 4f57564289fdff8c73020f3ed9f9184b363688062cf1b89baea79f0d25c57905bcbc225b5e946afeb30305b91402b557ae65ce61b99a0d63b8bb1c569ec2d57f
+  metadata.gz: 6299802984ef5bab4c658c534105491f853c9d6cd297a5df49e5f8c83e0b36d1b01d140c1ea510002cf2916f3902035e764dcd589e4e01c5eec10c4ba76fda28
+  data.tar.gz: 42e73a1c3f80942d7ad102187b8a19148eb8a4046539eabb45561a716711fa3a51ea228e7bc372b4f675f4777db9ad964ed6c4873c19a5be9dc375af8639d92d

data/.rubocop_todo.yml

@@ -1,6 +1,6 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2026-04-01 00:03:16 UTC using RuboCop version 1.86.0.
+# on 2026-04-12 07:40:40 UTC using RuboCop version 1.86.0.
 # 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
@@ -11,39 +11,147 @@ Gemspec/RequiredRubyVersion:
   Exclude:
     - 'canon.gemspec'
 
-# Offense count: 2
+# Offense count: 49
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'lib/canon/comparison/whitespace_sensitivity.rb'
+    - 'lib/canon/comparison/xml_comparator.rb'
+    - 'lib/canon/comparison/xml_node_comparison.rb'
+    - 'lib/canon/config.rb'
+    - 'lib/canon/diff/diff_classifier.rb'
+    - 'lib/canon/diff_formatter.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb'
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+    - 'spec/canon/config/profile_spec.rb'
+    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
+
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_element, with_fixed_indentation
+Layout/ArrayAlignment:
+  Exclude:
+    - 'lib/canon/comparison/match_options/base_resolver.rb'
+    - 'lib/canon/comparison/match_options/xml_resolver.rb'
+    - 'spec/canon/config/profile_spec.rb'
+
+# Offense count: 16
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleAlignWith.
 # SupportedStylesAlignWith: either, start_of_block, start_of_line
 Layout/BlockAlignment:
   Exclude:
-    - 'lib/canon/tree_diff/matchers/hash_matcher.rb'
-    - 'spec/canon/hash_matcher_regression_spec.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+    - 'spec/canon/diff_formatter/display_preprocessing_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
 
-# Offense count: 2
+# Offense count: 16
 # This cop supports safe autocorrection (--autocorrect).
 Layout/BlockEndNewline:
   Exclude:
-    - 'lib/canon/tree_diff/matchers/hash_matcher.rb'
-    - 'spec/canon/hash_matcher_regression_spec.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+    - 'spec/canon/diff_formatter/display_preprocessing_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
 
-# Offense count: 4
+# Offense count: 5
+# This cop supports safe autocorrection (--autocorrect).
+Layout/ClosingParenthesisIndentation:
+  Exclude:
+    - 'lib/canon/config/profile_loader.rb'
+    - 'lib/canon/diff/diff_classifier.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+Layout/ElseAlignment:
+  Exclude:
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.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_formatter/diff_detail_formatter/dimension_formatter.rb'
+
+# Offense count: 5
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: consistent, consistent_relative_to_receiver, special_for_inner_method_call, special_for_inner_method_call_in_parentheses
+Layout/FirstArgumentIndentation:
+  Exclude:
+    - 'lib/canon/config/profile_loader.rb'
+    - 'lib/canon/diff/diff_classifier.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+
+# Offense count: 30
+# 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:
+  Exclude:
+    - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
+    - 'spec/canon/diff_formatter/display_preprocessing_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
+
+# Offense count: 36
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Width, EnforcedStyleAlignWith, AllowedPatterns.
 # SupportedStylesAlignWith: start_of_line, relative_to_receiver
 Layout/IndentationWidth:
   Exclude:
-    - 'lib/canon/tree_diff/matchers/hash_matcher.rb'
-    - 'spec/canon/hash_matcher_regression_spec.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+    - 'spec/canon/diff_formatter/display_preprocessing_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
 
-# Offense count: 1103
+# Offense count: 1375
 # 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: 55
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: symmetrical, new_line, same_line
+Layout/MultilineMethodCallBraceLayout:
+  Exclude:
+    - 'lib/canon/config/profile_loader.rb'
+    - 'lib/canon/diff/diff_classifier.rb'
+
+# Offense count: 57
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: AllowInHeredoc.
+Layout/TrailingWhitespace:
+  Enabled: false
+
+# Offense count: 56
 # Configuration parameters: IgnoreLiteralBranches, IgnoreConstantBranches, IgnoreDuplicateElseBranch.
 Lint/DuplicateBranch:
   Enabled: false
@@ -88,7 +196,7 @@ Lint/UselessConstantScoping:
   Exclude:
     - 'lib/canon/diff_formatter/theme.rb'
 
-# Offense count: 298
+# Offense count: 309
 # Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes, Max.
 Metrics/AbcSize:
   Enabled: false
@@ -99,27 +207,27 @@ Metrics/AbcSize:
 Metrics/BlockLength:
   Max: 92
 
-# Offense count: 1
+# Offense count: 3
 # Configuration parameters: CountBlocks, CountModifierForms.
 Metrics/BlockNesting:
   Max: 4
 
-# Offense count: 262
+# Offense count: 272
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Enabled: false
 
-# Offense count: 485
+# Offense count: 498
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 146
 
-# Offense count: 56
+# Offense count: 58
 # Configuration parameters: CountKeywordArgs, MaxOptionalParameters.
 Metrics/ParameterLists:
   Max: 10
 
-# Offense count: 213
+# Offense count: 219
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/PerceivedComplexity:
   Enabled: false
@@ -152,13 +260,13 @@ Performance/CollectionLiteralInLoop:
     - 'lib/canon/xml/xml_base_handler.rb'
     - 'spec/canon/diff/diff_node_mapper_comments_spec.rb'
 
-# Offense count: 71
+# Offense count: 82
 # Configuration parameters: Prefixes, AllowedPatterns.
 # Prefixes: when, with, without
 RSpec/ContextWording:
   Enabled: false
 
-# Offense count: 34
+# Offense count: 37
 # Configuration parameters: IgnoredMetadata.
 RSpec/DescribeClass:
   Enabled: false
@@ -169,7 +277,7 @@ RSpec/DescribeMethod:
     - 'spec/canon/comparison/multiple_differences_spec.rb'
     - 'spec/canon/diff_formatter/character_map_customization_spec.rb'
 
-# Offense count: 741
+# Offense count: 804
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 44
@@ -183,7 +291,7 @@ RSpec/ExpectActual:
     - 'spec/canon/rspec_matchers_spec.rb'
     - 'spec/canon/string_matcher_spec.rb'
 
-# Offense count: 175
+# Offense count: 177
 # Configuration parameters: Max, AllowedIdentifiers, AllowedPatterns.
 RSpec/IndexedLet:
   Exclude:
@@ -221,14 +329,14 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/canon/comparison/match_options_spec.rb'
 
-# Offense count: 595
+# Offense count: 654
 RSpec/MultipleExpectations:
   Max: 15
 
-# Offense count: 71
+# Offense count: 93
 # Configuration parameters: AllowSubject.
 RSpec/MultipleMemoizedHelpers:
-  Max: 13
+  Max: 16
 
 # Offense count: 17
 # Configuration parameters: EnforcedStyle, IgnoreSharedExamples.
@@ -239,7 +347,7 @@ RSpec/NamedSubject:
     - 'spec/canon/pretty_printer/json_spec.rb'
     - 'spec/canon/pretty_printer/xml_spec.rb'
 
-# Offense count: 40
+# Offense count: 50
 # Configuration parameters: AllowedGroups.
 RSpec/NestedGroups:
   Max: 4
@@ -273,7 +381,7 @@ RSpec/SpecFilePathFormat:
     - 'spec/canon/yaml/formatter_spec.rb'
     - 'spec/xml_c14n_spec.rb'
 
-# Offense count: 128
+# Offense count: 131
 # Configuration parameters: IgnoreNameless, IgnoreSymbolicNames.
 RSpec/VerifiedDoubles:
   Exclude:
@@ -285,7 +393,7 @@ RSpec/VerifiedDoubles:
     - 'spec/canon/diff_formatter/diff_detail_formatter_spec.rb'
     - 'spec/canon/tree_diff/operation_converter_spec.rb'
 
-# Offense count: 2
+# Offense count: 25
 # 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
@@ -294,8 +402,13 @@ RSpec/VerifiedDoubles:
 # AllowedMethods: lambda, proc, it
 Style/BlockDelimiters:
   Exclude:
-    - 'lib/canon/tree_diff/matchers/hash_matcher.rb'
-    - 'spec/canon/hash_matcher_regression_spec.rb'
+    - 'lib/canon/diff_formatter/diff_detail_formatter/node_utils.rb'
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+    - 'spec/canon/config/profile_loader_spec.rb'
+    - 'spec/canon/diff_formatter/display_preprocessing_spec.rb'
+    - 'spec/canon/diff_formatter/pretty_diff_spec.rb'
+    - 'spec/canon/diff_formatter/show_diffs_filtering_spec.rb'
+    - 'spec/canon/pretty_printer/xml_normalized_spec.rb'
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
@@ -319,6 +432,18 @@ Style/IdenticalConditionalBranches:
     - 'lib/canon/diff_formatter/by_object/base_formatter.rb'
     - 'lib/canon/diff_formatter/legend.rb'
 
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+Style/MultilineIfModifier:
+  Exclude:
+    - 'lib/canon/pretty_printer/xml_normalized.rb'
+
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
+Style/MultilineTernaryOperator:
+  Exclude:
+    - 'lib/canon/diff_formatter/diff_detail_formatter/dimension_formatter.rb'
+
 # Offense count: 1
 # Configuration parameters: AllowedMethods.
 # AllowedMethods: respond_to_missing?

data/docs/INDEX.adoc

@@ -98,6 +98,7 @@ Choose your interface:
 === Level 4: Master Features (1 hour)
 
 . link:features/match-options/[Match options and profiles]
+. link:features/configuration-profiles/[Configuration profiles] - YAML-based presets with element-level whitespace control
 . link:features/canonicalization/[Format-specific canonicalization]
 . link:features/diff-formatting/[Customizing diff output]
 
@@ -111,6 +112,7 @@ Choose your interface:
 
 * link:reference/options-across-interfaces[Options Across Interfaces] - Same options in CLI, Ruby API, and RSpec
 * link:reference/environment-variables[Environment Variables] - Configure Canon via ENV variables
+* link:features/configuration-profiles/[Configuration Profiles] - YAML presets with element-level whitespace control
 * link:features/match-options/profiles[Match Profiles] - Pre-configured comparison strategies
 * link:features/diff-formatting/colors-and-symbols[Color-Coded Diffs] - Understanding diff output
 * link:features/environment-configuration/size-limits[Size Limits] - Preventing hangs on large files
@@ -135,5 +137,7 @@ See link:contributing[Contributing to Documentation]
 * Size limits for large files
 * Enhanced character visualization
 * Environment variable configuration
+* Configuration profiles with element-level whitespace classification
+* Three-way whitespace sensitivity: strict, normalize, insensitive
 
 See link:https://github.com/lutaml/canon/blob/main/CHANGELOG.md[Full Changelog]

data/docs/advanced/diff-classification.adoc

@@ -324,7 +324,7 @@ html2 = '<code>indented</code><p>text</p>'
 Canon::Comparison.equivalent?(html1, html2,
   format: :html,
   match: {
-    whitespace_insensitive_elements: [:code],
+    strip_whitespace_elements: [:code],
   }
 )
 # => true
@@ -423,9 +423,10 @@ def classify(diff_node)
   end
 
   # SECOND: Handle content-level formatting for text_content with :normalize
+  # Skipped for :preserve elements (<pre>, <code>, etc.) where whitespace is always normative
   if diff_node.dimension == :text_content &&
       profile.send(:behavior_for, :text_content) == :normalize &&
-      !inside_whitespace_sensitive_element?(diff_node) &&
+      !inside_preserve_element?(diff_node) &&
       formatting_only_diff?(diff_node)
     diff_node.formatting = true
     diff_node.normative = false

data/docs/advanced/verbose-mode-architecture.adoc

@@ -130,10 +130,33 @@ Each difference displays:
 * **Status indicator**: `[NORMATIVE]` (green) or `[INFORMATIVE]` (yellow)
 * **Dimension**: Which aspect differs (colorized in magenta)
 * **Location**: XPath for XML/HTML, path for JSON/YAML (colorized in blue)
+* **Reason**: When the reason contains visualized whitespace characters (░),
+  it is split across two lines with the before and after text vertically
+  aligned for easier visual comparison:
++
+[source]
+----
+Reason:  Text: "░░term2░definition░░"
+          vs.: "░term2░definition░"
+----
++
+When no visualized whitespace is present, the reason remains a single line.
 * **Expected section**: What was in File 1 (red heading, bold)
 * **Actual section**: What was in File 2 (green heading, bold)
 * **Changes summary**: Actionable description of the difference (yellow, bold)
 
+When both the Expected and Actual values are short (under 30 characters), they
+are rendered as compact single lines with aligned colons for succinctness:
+
+[source]
+----
+⊖ Expected (File 1): "term2 definition"
+⊕ Actual (File 2)  : "term2 definition"
+----
+
+For longer values, they appear on separate lines with no blank line between
+them.
+
 === Dimension-specific formats
 
 ==== Attribute presence differences