canon 0.1.8 → 0.1.10

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (101) hide show
  1. checksums.yaml +4 -4
  2. data/.rubocop_todo.yml +83 -22
  3. data/docs/Gemfile +1 -0
  4. data/docs/_config.yml +90 -1
  5. data/docs/advanced/diff-classification.adoc +196 -24
  6. data/docs/features/match-options/index.adoc +239 -1
  7. data/lib/canon/comparison/format_detector.rb +2 -1
  8. data/lib/canon/comparison/html_comparator.rb +19 -8
  9. data/lib/canon/comparison/html_compare_profile.rb +8 -2
  10. data/lib/canon/comparison/markup_comparator.rb +109 -2
  11. data/lib/canon/comparison/match_options/base_resolver.rb +7 -0
  12. data/lib/canon/comparison/whitespace_sensitivity.rb +208 -0
  13. data/lib/canon/comparison/xml_comparator/child_comparison.rb +15 -7
  14. data/lib/canon/comparison/xml_comparator/diff_node_builder.rb +108 -0
  15. data/lib/canon/comparison/xml_comparator/node_parser.rb +10 -5
  16. data/lib/canon/comparison/xml_comparator/node_type_comparator.rb +14 -7
  17. data/lib/canon/comparison/xml_comparator.rb +240 -23
  18. data/lib/canon/comparison/xml_node_comparison.rb +25 -3
  19. data/lib/canon/diff/diff_classifier.rb +119 -5
  20. data/lib/canon/diff/formatting_detector.rb +1 -1
  21. data/lib/canon/diff/xml_serialization_formatter.rb +153 -0
  22. data/lib/canon/rspec_matchers.rb +37 -8
  23. data/lib/canon/version.rb +1 -1
  24. data/lib/canon/xml/data_model.rb +24 -13
  25. metadata +4 -78
  26. data/docs/plans/2025-01-17-html-parser-selection-fix.adoc +0 -250
  27. data/false_positive_analysis.txt +0 -0
  28. data/file1.html +0 -1
  29. data/file2.html +0 -1
  30. data/old-docs/ADVANCED_TOPICS.adoc +0 -20
  31. data/old-docs/BASIC_USAGE.adoc +0 -16
  32. data/old-docs/CHARACTER_VISUALIZATION.adoc +0 -567
  33. data/old-docs/CLI.adoc +0 -497
  34. data/old-docs/CUSTOMIZING_BEHAVIOR.adoc +0 -19
  35. data/old-docs/DIFF_ARCHITECTURE.adoc +0 -435
  36. data/old-docs/DIFF_FORMATTING.adoc +0 -540
  37. data/old-docs/DIFF_PARAMETERS.adoc +0 -261
  38. data/old-docs/DOM_DIFF.adoc +0 -1017
  39. data/old-docs/ENV_CONFIG.adoc +0 -876
  40. data/old-docs/FORMATS.adoc +0 -867
  41. data/old-docs/INPUT_VALIDATION.adoc +0 -477
  42. data/old-docs/MATCHER_BEHAVIOR.adoc +0 -90
  43. data/old-docs/MATCH_ARCHITECTURE.adoc +0 -463
  44. data/old-docs/MATCH_OPTIONS.adoc +0 -912
  45. data/old-docs/MODES.adoc +0 -432
  46. data/old-docs/NORMATIVE_INFORMATIVE_DIFFS.adoc +0 -219
  47. data/old-docs/OPTIONS.adoc +0 -1387
  48. data/old-docs/PREPROCESSING.adoc +0 -491
  49. data/old-docs/README.old.adoc +0 -2831
  50. data/old-docs/RSPEC.adoc +0 -814
  51. data/old-docs/RUBY_API.adoc +0 -485
  52. data/old-docs/SEMANTIC_DIFF_REPORT.adoc +0 -646
  53. data/old-docs/SEMANTIC_TREE_DIFF.adoc +0 -765
  54. data/old-docs/STRING_COMPARE.adoc +0 -345
  55. data/old-docs/TMP.adoc +0 -3384
  56. data/old-docs/TREE_DIFF.adoc +0 -1080
  57. data/old-docs/UNDERSTANDING_CANON.adoc +0 -17
  58. data/old-docs/VERBOSE.adoc +0 -482
  59. data/old-docs/VISUALIZATION_MAP.adoc +0 -625
  60. data/old-docs/WHITESPACE_TREATMENT.adoc +0 -1155
  61. data/scripts/analyze_current_state.rb +0 -85
  62. data/scripts/analyze_false_positives.rb +0 -114
  63. data/scripts/analyze_remaining_failures.rb +0 -105
  64. data/scripts/compare_current_failures.rb +0 -95
  65. data/scripts/compare_dom_tree_diff.rb +0 -158
  66. data/scripts/compare_failures.rb +0 -151
  67. data/scripts/debug_attribute_extraction.rb +0 -66
  68. data/scripts/debug_blocks_839.rb +0 -115
  69. data/scripts/debug_meta_matching.rb +0 -52
  70. data/scripts/debug_p_matching.rb +0 -192
  71. data/scripts/debug_signature_matching.rb +0 -118
  72. data/scripts/debug_sourcecode_124.rb +0 -32
  73. data/scripts/debug_whitespace_sensitive.rb +0 -192
  74. data/scripts/extract_false_positives.rb +0 -138
  75. data/scripts/find_actual_false_positives.rb +0 -125
  76. data/scripts/investigate_all_false_positives.rb +0 -161
  77. data/scripts/investigate_batch1.rb +0 -127
  78. data/scripts/investigate_classification.rb +0 -150
  79. data/scripts/investigate_classification_detailed.rb +0 -190
  80. data/scripts/investigate_common_failures.rb +0 -342
  81. data/scripts/investigate_false_negative.rb +0 -80
  82. data/scripts/investigate_false_positive.rb +0 -83
  83. data/scripts/investigate_false_positives.rb +0 -227
  84. data/scripts/investigate_false_positives_batch.rb +0 -163
  85. data/scripts/investigate_mixed_content.rb +0 -125
  86. data/scripts/investigate_remaining_16.rb +0 -214
  87. data/scripts/run_single_test.rb +0 -29
  88. data/scripts/test_all_false_positives.rb +0 -95
  89. data/scripts/test_attribute_details.rb +0 -61
  90. data/scripts/test_both_algorithms.rb +0 -49
  91. data/scripts/test_both_simple.rb +0 -49
  92. data/scripts/test_enhanced_semantic_output.rb +0 -125
  93. data/scripts/test_readme_examples.rb +0 -131
  94. data/scripts/test_semantic_tree_diff.rb +0 -99
  95. data/scripts/test_semantic_ux_improvements.rb +0 -135
  96. data/scripts/test_single_false_positive.rb +0 -119
  97. data/scripts/test_size_limits.rb +0 -99
  98. data/test_html_1.html +0 -21
  99. data/test_html_2.html +0 -21
  100. data/test_nokogiri.rb +0 -33
  101. data/test_normalize.rb +0 -45
data/test_normalize.rb DELETED
@@ -1,45 +0,0 @@
1
- require "bundler/setup"
2
- require "canon/html/data_model"
3
-
4
- html1 = "<html><body><p>Test</p></body></html>"
5
- html2 = "<html>\n\n<body>\n\n<p>Test</p>\n\n</body>\n\n</html>"
6
-
7
- # Parse both without preprocessing
8
- node1 = Canon::Html::DataModel.from_html(html1)
9
- node2 = Canon::Html::DataModel.from_html(html2)
10
-
11
- puts "=== Without preprocessing ==="
12
- puts "node1 root children count: #{node1.children.count}"
13
- node1.children.each_with_index do |child, i|
14
- puts " Child #{i}: #{child.class}"
15
- if child.is_a?(Canon::Xml::Nodes::ElementNode)
16
- puts " Name: #{child.name}"
17
- puts " Children count: #{child.children.count}"
18
- end
19
- end
20
-
21
- puts "\nnode2 root children count: #{node2.children.count}"
22
- node2.children.each_with_index do |child, i|
23
- puts " Child #{i}: #{child.class}"
24
- if child.is_a?(Canon::Xml::Nodes::ElementNode)
25
- puts " Name: #{child.name}"
26
- puts " Children count: #{child.children.count}"
27
- end
28
- end
29
-
30
- # Now with normalize preprocessing
31
- html2_norm = html2.lines.map(&:strip).reject(&:empty?).join("\n")
32
- node2_norm = Canon::Html::DataModel.from_html(html2_norm)
33
-
34
- puts "\n=== With :normalize preprocessing ==="
35
- puts "html2_norm:"
36
- puts html2_norm
37
- puts ""
38
- puts "node2_norm root children count: #{node2_norm.children.count}"
39
- node2_norm.children.each_with_index do |child, i|
40
- puts " Child #{i}: #{child.class}"
41
- if child.is_a?(Canon::Xml::Nodes::ElementNode)
42
- puts " Name: #{child.name}"
43
- puts " Children count: #{child.children.count}"
44
- end
45
- end