svg_conform 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 43ff84b9d1f47a6a2bd92624483c0445bd3f77d29f0fc36f2c02116a40111bc2
-  data.tar.gz: be072c8772885cd746ee623e028e00517dfcac93250a00f4015cb7122d94739a
+  metadata.gz: c862af872ab16b243d9f6ffaedb7c5a37e8c470a5280915cc96bc33a3572c8e5
+  data.tar.gz: 3b5fbeebd207eb29ac9685a8913799cc8239704566d9efd8b18fa663bf55a8d0
 SHA512:
-  metadata.gz: 0ee8ad3bfab5a2aec10b32caa23141967aa25112e0393ed39242ab83a5f123bb317190392df347f7f4a8665af61bf7de4b09eb3283c4c140e372af1177ba924b
-  data.tar.gz: 20d1871024c131298aa2462bd849e07dfb16b73f2f61913da8f9c2d21b43e87fcfe5ae6ed298971091c0f85734efe8a36790432ccdb18c8878dafc25d238a348
+  metadata.gz: d5808529cca60d31e717f907c5fa9cf11753fb7de4bb65416f7a796f007b4a0157f35c28a7c40f7d58a089eb83738ffc16237e60856b6dd54e475db12132ea91
+  data.tar.gz: e597d1400a180a30a44ce26437f84bdc4fc8d51d6c7e0e7aa5afdf2adefa8c1c7ad1bd749c613fb9c7635d1fa462993d345866f17775671e5b2b687042778196

data/.rubocop_todo.yml

@@ -1,27 +1,66 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2025-11-18 13:36:55 UTC using RuboCop version 1.81.1.
+# on 2025-11-19 09:35:14 UTC using RuboCop version 1.81.1.
 # 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
 # versions of RuboCop, may require this file to be generated again.
 
-# Offense count: 1
+# Offense count: 19
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_argument, with_fixed_indentation
+Layout/ArgumentAlignment:
+  Exclude:
+    - 'compare_dom_sax.rb'
+    - 'lib/svg_conform/requirements/font_family_requirement.rb'
+    - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
+    - 'lib/svg_conform/sax_validation_handler.rb'
+    - 'spec/support/shared_examples_for_validation_modes.rb'
+
+# Offense count: 5
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle, IndentationWidth.
+# SupportedStyles: with_first_element, with_fixed_indentation
+Layout/ArrayAlignment:
+  Exclude:
+    - 'lib/svg_conform/requirements/color_restrictions_requirement.rb'
+    - 'lib/svg_conform/requirements/id_reference_requirement.rb'
+    - 'lib/svg_conform/requirements/invalid_id_references_requirement.rb'
+
+# Offense count: 5
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleAlignWith.
 # SupportedStylesAlignWith: either, start_of_block, start_of_line
 Layout/BlockAlignment:
   Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'check_position_collisions.rb'
+    - 'check_unique_positions.rb'
+    - 'lib/svg_conform/requirements/allowed_elements_requirement.rb'
     - 'spec/svg_conform/profiles/svg_1_2_rfc_profile_spec.rb'
 
-# Offense count: 1
+# Offense count: 8
+# This cop supports safe autocorrection (--autocorrect).
+Layout/BlockEndNewline:
+  Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'check_duplicates.rb'
+    - 'check_position_collisions.rb'
+    - 'check_unique_positions.rb'
+    - 'compare_errors.rb'
+    - 'find_missing_errors.rb'
+    - 'lib/svg_conform/requirements/allowed_elements_requirement.rb'
+
+# Offense count: 4
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowForAlignment.
 Layout/CommentIndentation:
   Exclude:
+    - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
     - 'lib/svg_conform/validation_context.rb'
 
-# Offense count: 1
+# Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 Layout/ElseAlignment:
   Exclude:
@@ -47,17 +86,37 @@ Layout/EmptyLineAfterGuardClause:
 
 # Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EmptyLineBetweenMethodDefs, EmptyLineBetweenClassDefs, EmptyLineBetweenModuleDefs, DefLikeMacros, AllowAdjacentOneLineDefs, NumberOfEmptyLines.
+Layout/EmptyLineBetweenDefs:
+  Exclude:
+    - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Layout/EmptyLines:
+  Exclude:
+    - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Layout/EmptyLinesAroundMethodBody:
+  Exclude:
+    - 'lib/svg_conform/fast_document_analyzer.rb'
+
+# Offense count: 2
+# This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleAlignWith, Severity.
 # SupportedStylesAlignWith: keyword, variable, start_of_line
 Layout/EndAlignment:
   Exclude:
     - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
 
-# Offense count: 21
+# Offense count: 22
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowForAlignment, AllowBeforeTrailingComments, ForceEqualSignAlignment.
 Layout/ExtraSpacing:
   Exclude:
+    - 'benchmark_bsi_samples.rb'
     - 'find_missing_errors.rb'
     - 'lib/svg_conform/element_proxy.rb'
     - 'lib/svg_conform/requirements/id_reference_requirement.rb'
@@ -66,34 +125,61 @@ Layout/ExtraSpacing:
     - 'lib/svg_conform/validation_context.rb'
     - 'lib/svg_conform/validator.rb'
 
-# Offense count: 1
+# Offense count: 2
+# 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:
+    - 'benchmark_bsi_samples.rb'
+    - 'final_demo.rb'
+
+# Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 Layout/HeredocIndentation:
   Exclude:
     - 'test_sax_basic.rb'
 
-# Offense count: 1
+# Offense count: 8
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle.
 # SupportedStyles: normal, indented_internal_methods
 Layout/IndentationConsistency:
   Exclude:
+    - 'check_duplicates.rb'
+    - 'compare_dom_sax.rb'
+    - 'compare_errors.rb'
+    - 'find_missing_errors.rb'
     - 'lib/svg_conform/validation_context.rb'
 
-# Offense count: 1
+# Offense count: 13
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Width, AllowedPatterns.
 Layout/IndentationWidth:
   Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'check_position_collisions.rb'
+    - 'check_unique_positions.rb'
+    - 'lib/svg_conform/requirements/allowed_elements_requirement.rb'
     - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
 
-# Offense count: 604
+# Offense count: 640
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: Max, AllowHeredoc, AllowURI, AllowQualifiedName, URISchemes, IgnoreCopDirectives, AllowedPatterns, SplitStrings.
 # URISchemes: http, https
 Layout/LineLength:
   Enabled: false
 
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+Layout/MultilineBlockLayout:
+  Exclude:
+    - 'check_duplicates.rb'
+    - 'compare_errors.rb'
+    - 'find_missing_errors.rb'
+
 # Offense count: 28
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowForAlignment, EnforcedStyleForExponentOperator, EnforcedStyleForRationalLiterals.
@@ -109,20 +195,19 @@ Layout/SpaceAroundOperators:
     - 'final_demo.rb'
     - 'test_remediation.rb'
 
-# Offense count: 32
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: final_newline, final_blank_line
+Layout/TrailingEmptyLines:
+  Exclude:
+    - 'spec/support/shared_examples_for_validation_modes.rb'
+
+# Offense count: 67
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: AllowInHeredoc.
 Layout/TrailingWhitespace:
-  Exclude:
-    - 'analyze_error_nodes.rb'
-    - 'check_clippath_font.rb'
-    - 'debug_positions.rb'
-    - 'debug_utf8.rb'
-    - 'final_demo.rb'
-    - 'find_missing_errors.rb'
-    - 'lib/svg_conform/fast_document_analyzer.rb'
-    - 'lib/svg_conform/sax_document.rb'
-    - 'test_sax_basic.rb'
+  Enabled: false
 
 # Offense count: 2
 # Configuration parameters: AllowedMethods.
@@ -169,12 +254,20 @@ Lint/MissingSuper:
     - 'lib/svg_conform/sax_validation_handler.rb'
 
 # Offense count: 3
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: AllowedMethods, InferNonNilReceiver, AdditionalNilMethods.
+# AllowedMethods: instance_of?, kind_of?, is_a?, eql?, respond_to?, equal?
+# AdditionalNilMethods: present?, blank?, try, try!
+Lint/RedundantSafeNavigation:
+  Exclude:
+    - 'count_elements.rb'
+    - 'lib/svg_conform/fast_document_analyzer.rb'
+
+# Offense count: 1
 # This cop supports safe autocorrection (--autocorrect).
-Lint/ScriptPermission:
+Lint/RedundantStringCoercion:
   Exclude:
-    - 'benchmark_validation.rb'
-    - 'final_demo.rb'
-    - 'test_remediation.rb'
+    - 'analyze_error_nodes.rb'
 
 # Offense count: 1
 Lint/UnreachableCode:
@@ -204,7 +297,7 @@ Lint/UselessAccessModifier:
 Metrics/AbcSize:
   Enabled: false
 
-# Offense count: 21
+# Offense count: 22
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns, inherit_mode.
 # AllowedMethods: refine
 Metrics/BlockLength:
@@ -215,12 +308,12 @@ Metrics/BlockLength:
 Metrics/BlockNesting:
   Max: 4
 
-# Offense count: 125
+# Offense count: 126
 # Configuration parameters: AllowedMethods, AllowedPatterns, Max.
 Metrics/CyclomaticComplexity:
   Enabled: false
 
-# Offense count: 257
+# Offense count: 258
 # Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
 Metrics/MethodLength:
   Max: 154
@@ -273,7 +366,7 @@ RSpec/DescribeClass:
     - 'spec/svg_conform/profiles/svg_1_2_rfc_with_rdf_profile_spec.rb'
     - 'spec/svgcheck_compatibility_spec.rb'
 
-# Offense count: 106
+# Offense count: 109
 # Configuration parameters: CountAsOne.
 RSpec/ExampleLength:
   Max: 53
@@ -288,7 +381,7 @@ RSpec/MultipleDescribes:
   Exclude:
     - 'spec/svg_conform/batch_report_spec.rb'
 
-# Offense count: 71
+# Offense count: 73
 RSpec/MultipleExpectations:
   Max: 6
 
@@ -297,6 +390,23 @@ Rake/MethodDefinitionInTask:
   Exclude:
     - 'lib/tasks/svgcheck.rake'
 
+# Offense count: 9
+# 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:
+    - 'benchmark_bsi_samples.rb'
+    - 'check_duplicates.rb'
+    - 'check_position_collisions.rb'
+    - 'check_unique_positions.rb'
+    - 'compare_errors.rb'
+    - 'find_missing_errors.rb'
+    - 'lib/svg_conform/requirements/allowed_elements_requirement.rb'
+
 # Offense count: 3
 # This cop supports unsafe autocorrection (--autocorrect-all).
 Style/CombinableLoops:
@@ -326,7 +436,29 @@ Style/MissingRespondToMissing:
   Exclude:
     - 'lib/svg_conform/cli.rb'
 
-# Offense count: 6
+# Offense count: 3
+# This cop supports safe autocorrection (--autocorrect).
+Style/MultilineIfModifier:
+  Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'lib/svg_conform/sax_validation_handler.rb'
+
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Style/MultilineTernaryOperator:
+  Exclude:
+    - 'lib/svg_conform/requirements/namespace_attributes_requirement.rb'
+
+# Offense count: 2
+# This cop supports unsafe autocorrection (--autocorrect-all).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: literals, strict
+Style/MutableConstant:
+  Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'test_sax_on_slow_files.rb'
+
+# Offense count: 8
 # This cop supports unsafe autocorrection (--autocorrect-all).
 # Configuration parameters: EnforcedStyle, AllowedMethods, AllowedPatterns.
 # SupportedStyles: predicate, comparison
@@ -335,6 +467,7 @@ Style/NumericPredicate:
     - 'spec/**/*'
     - 'benchmark_validation.rb'
     - 'check_unique_positions.rb'
+    - 'compare_dom_sax.rb'
     - 'lib/svg_conform/validation_context.rb'
     - 'test_remediation.rb'
     - 'test_sax_basic.rb'
@@ -366,6 +499,12 @@ Style/RedundantInterpolation:
   Exclude:
     - 'analyze_error_nodes.rb'
 
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+Style/RedundantParentheses:
+  Exclude:
+    - 'compare_dom_sax.rb'
+
 # Offense count: 2
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle.
@@ -384,23 +523,36 @@ Style/SafeNavigation:
     - 'count_elements.rb'
     - 'lib/svg_conform/fast_document_analyzer.rb'
 
-# Offense count: 4
+# Offense count: 7
 # This cop supports unsafe autocorrection (--autocorrect-all).
 # Configuration parameters: Mode.
 Style/StringConcatenation:
   Exclude:
+    - 'benchmark_bsi_samples.rb'
     - 'benchmark_sax.rb'
     - 'benchmark_validation.rb'
     - 'final_demo.rb'
     - 'test_remediation.rb'
 
-# Offense count: 78
+# Offense count: 105
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyle, ConsistentQuotesInMultiline.
 # SupportedStyles: single_quotes, double_quotes
 Style/StringLiterals:
   Enabled: false
 
+# Offense count: 5
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyle.
+# SupportedStyles: single_quotes, double_quotes
+Style/StringLiteralsInInterpolation:
+  Exclude:
+    - 'benchmark_bsi_samples.rb'
+    - 'benchmark_sax.rb'
+    - 'benchmark_validation.rb'
+    - 'final_demo.rb'
+    - 'test_remediation.rb'
+
 # Offense count: 34
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleForMultiline.
@@ -423,6 +575,14 @@ Style/TrailingCommaInArguments:
     - 'lib/svg_conform/sax_validation_handler.rb'
     - 'lib/svg_conform/validator.rb'
 
+# Offense count: 1
+# This cop supports safe autocorrection (--autocorrect).
+# Configuration parameters: EnforcedStyleForMultiline.
+# SupportedStylesForMultiline: comma, consistent_comma, diff_comma, no_comma
+Style/TrailingCommaInArrayLiteral:
+  Exclude:
+    - 'test_sax_on_slow_files.rb'
+
 # Offense count: 12
 # This cop supports safe autocorrection (--autocorrect).
 # Configuration parameters: EnforcedStyleForMultiline.

data/README.adoc

@@ -1364,6 +1364,61 @@ $ svg_conform svgcheck compare diagram.svg --svgcheck-report diagram.svg.svgchec
 ====
 
 
+
+== Performance
+
+=== SAX streaming validation
+
+SvgConform implements SAX (Simple API for XML) streaming validation for
+high-performance processing of large SVG files.
+
+Performance characteristics:
+
+* Small files (<1 MB): ~0.5s validation time
+* Medium files (1-5 MB): ~1s validation time (vs 60-80s with DOM)
+* Large files (>5 MB): ~2s validation time (vs minutes-hours with DOM)
+
+Real-world samples results:
+
+* 5.93 MB file: >` 60s → 1.89s (30x faster)
+* 4.57 MB file: >60s → 1.37s (40x faster)
+* 3.44 MB file: >60s → 0.29s (200x faster)
+
+How it works:
+
+SAX streaming validation processes XML events without building a full DOM tree
+in memory. This provides:
+
+* Forward-only processing: Single pass through XML stream
+* Constant memory: No full DOM tree in memory
+* Predictable performance: O(n) complexity guaranteed
+* No object identity issues: Path-based node identification
+
+Mode selection:
+
+By default, SAX mode is used for all validation operations. DOM mode is
+automatically used when remediation is requested (`fix: true`).
+
+[source,ruby]
+----
+# Default: SAX mode (best performance)
+validator = SvgConform::Validator.new
+result = validator.validate_file('large.svg', profile: :metanorma)
+
+# Explicit mode selection
+validator_sax = SvgConform::Validator.new(mode: :sax)  # Force SAX
+validator_dom = SvgConform::Validator.new(mode: :dom)  # Force DOM
+validator_auto = SvgConform::Validator.new(mode: :auto)  # File size based (>1MB uses SAX)
+----
+
+Validation parity:
+
+SAX mode produces identical validation results to DOM mode on 18/19 test files
+(94.7% parity). The one exception is `full-tiny.svg`, a comprehensive test file
+with known architectural differences.
+
+
+
 == Testing
 
 Run the test suite:

data/lib/svg_conform/element_proxy.rb

@@ -11,7 +11,7 @@ module SvgConform
     end
 
     def namespace
-      nil  # Simplified for now
+      nil # DOM handles namespaces via XPath; SAX checks attribute names directly
     end
   end
 
@@ -24,12 +24,12 @@ module SvgConform
 
     def initialize(name:, attributes:, position:, path:, parent:)
       @name = name
-      @raw_attributes = attributes  # Hash of attribute name => value
+      @raw_attributes = attributes # Hash of attribute name => value
       @position = position
-      @path = path  # Array of parent path parts
+      @path = path # Array of parent path parts
       @parent = parent
-      @text_content = String.new  # Mutable string
-      @child_counters = {}  # Track child element positions
+      @text_content = +"" # Mutable string
+      @child_counters = {} # Track child element positions
     end
 
     # Build full path ID for this element
@@ -61,7 +61,7 @@ module SvgConform
 
     # Get namespace from attributes or parent
     def namespace
-      @raw_attributes['xmlns'] || @parent&.namespace
+      @raw_attributes["xmlns"] || @parent&.namespace
     end
 
     # Check if this is a text node (always false for ElementProxy)
@@ -70,10 +70,10 @@ module SvgConform
     end
 
     # Support dynamic attribute access
-    def method_missing(method, *args)
-      if method.to_s.end_with?('?')
+    def method_missing(method, *_args)
+      if method.to_s.end_with?("?")
         # Boolean check
-        has_attribute?(method.to_s.chomp('?'))
+        has_attribute?(method.to_s.chomp("?"))
       else
         # Attribute access
         @attributes[method.to_s] || @attributes[method.to_sym]
@@ -86,7 +86,7 @@ module SvgConform
 
     # For compatibility with validation context
     def line
-      nil  # SAX doesn't provide line numbers easily
+      nil # SAX doesn't provide line numbers easily
     end
 
     def column

data/lib/svg_conform/fast_document_analyzer.rb

@@ -3,79 +3,79 @@
 module SvgConform
   # Fast document analyzer that pre-computes node relationships and IDs
   # in a single pass to avoid repeated expensive traversals
-  # 
+  #
   # IMPORTANT: Stores paths indexed by the path itself (not object_id)
   # since node object_ids change between traversals
   class FastDocumentAnalyzer
     attr_reader :path_cache
-    
+
     def initialize(document)
       @document = document
       @path_cache = {}
-      
+
       analyze_document
     end
-    
+
     # Get cached path-based ID for a node by computing its path once
     def get_node_id(node)
       return nil unless node.respond_to?(:name) && node.name
-      
+
       # Compute path for this node (fast with forward traversal counting)
-      path = compute_path_forward(node)
-      path
+      compute_path_forward(node)
     end
-    
+
     private
-    
+
     def analyze_document
       # Pre-populate cache is not needed since we compute on demand
       # The optimization comes from forward-counting siblings instead of backward
     end
-    
+
     def compute_path_forward(node)
       path_parts = []
       current = node
-      
+
       while current
         if current.respond_to?(:name) && current.name
           # Count position among siblings by iterating forward from parent
           position = calculate_position_fast(current)
           path_parts.unshift("#{current.name}[#{position}]")
         end
-        
+
         break unless current.respond_to?(:parent)
-        
+
         begin
           current = current.parent
         rescue NoMethodError
           break
         end
-        
+
         break unless current
       end
-      
+
       "/#{path_parts.join('/')}"
     end
-    
+
     def calculate_position_fast(node)
       return 1 unless node.respond_to?(:parent)
-      
+
       parent = begin
         node.parent
       rescue NoMethodError
         nil
       end
-      
-      return 1 unless parent && parent.respond_to?(:children)
-      
+
+      return 1 unless parent.respond_to?(:children)
+
       # Count this node's position among siblings with same name
       position = 0
       parent.children.each do |child|
         next unless child.respond_to?(:name) && child.name == node.name
+
         position += 1
-        break if child.object_id == node.object_id
+        break if child.equal?(node)
       end
-      
+
       position
     end
   end

data/lib/svg_conform/node_index_builder.rb

@@ -39,6 +39,7 @@ module SvgConform
         node.children.each do |child|
           # Only process nodes with name (skip text nodes, etc.)
           next unless child.respond_to?(:name) && child.name
+
           build_index(child, child_counter)
         end
       end