wp2txt 1.1.3 → 2.1.0

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 (96) hide show
  1. checksums.yaml +4 -4
  2. data/.dockerignore +12 -0
  3. data/.github/workflows/ci.yml +13 -13
  4. data/.gitignore +14 -0
  5. data/CHANGELOG.md +284 -0
  6. data/DEVELOPMENT.md +415 -0
  7. data/DEVELOPMENT_ja.md +415 -0
  8. data/Dockerfile +19 -10
  9. data/Gemfile +2 -8
  10. data/README.md +259 -123
  11. data/README_ja.md +375 -0
  12. data/Rakefile +4 -0
  13. data/bin/wp2txt +863 -161
  14. data/lib/wp2txt/article.rb +98 -13
  15. data/lib/wp2txt/bz2_validator.rb +239 -0
  16. data/lib/wp2txt/category_cache.rb +313 -0
  17. data/lib/wp2txt/cli.rb +319 -0
  18. data/lib/wp2txt/cli_ui.rb +428 -0
  19. data/lib/wp2txt/config.rb +158 -0
  20. data/lib/wp2txt/constants.rb +134 -0
  21. data/lib/wp2txt/data/html_entities.json +2135 -0
  22. data/lib/wp2txt/data/language_metadata.json +4769 -0
  23. data/lib/wp2txt/data/language_tiers.json +59 -0
  24. data/lib/wp2txt/data/mediawiki_aliases.json +12366 -0
  25. data/lib/wp2txt/data/template_aliases.json +193 -0
  26. data/lib/wp2txt/data/wikipedia_entities.json +12 -0
  27. data/lib/wp2txt/extractor.rb +545 -0
  28. data/lib/wp2txt/file_utils.rb +91 -0
  29. data/lib/wp2txt/formatter.rb +352 -0
  30. data/lib/wp2txt/global_data_cache.rb +353 -0
  31. data/lib/wp2txt/index_cache.rb +258 -0
  32. data/lib/wp2txt/magic_words.rb +353 -0
  33. data/lib/wp2txt/memory_monitor.rb +236 -0
  34. data/lib/wp2txt/multistream.rb +1383 -0
  35. data/lib/wp2txt/output_writer.rb +182 -0
  36. data/lib/wp2txt/parser_functions.rb +606 -0
  37. data/lib/wp2txt/ractor_worker.rb +215 -0
  38. data/lib/wp2txt/regex.rb +396 -12
  39. data/lib/wp2txt/section_extractor.rb +354 -0
  40. data/lib/wp2txt/stream_processor.rb +271 -0
  41. data/lib/wp2txt/template_expander.rb +830 -0
  42. data/lib/wp2txt/text_processing.rb +337 -0
  43. data/lib/wp2txt/utils.rb +629 -270
  44. data/lib/wp2txt/version.rb +1 -1
  45. data/lib/wp2txt.rb +53 -26
  46. data/scripts/benchmark_regex.rb +161 -0
  47. data/scripts/fetch_html_entities.rb +94 -0
  48. data/scripts/fetch_language_metadata.rb +180 -0
  49. data/scripts/fetch_mediawiki_data.rb +334 -0
  50. data/scripts/fetch_template_data.rb +186 -0
  51. data/scripts/profile_memory.rb +139 -0
  52. data/spec/article_spec.rb +402 -0
  53. data/spec/auto_download_spec.rb +314 -0
  54. data/spec/bz2_validator_spec.rb +193 -0
  55. data/spec/category_cache_spec.rb +226 -0
  56. data/spec/category_fetcher_spec.rb +504 -0
  57. data/spec/cleanup_spec.rb +197 -0
  58. data/spec/cli_options_spec.rb +678 -0
  59. data/spec/cli_spec.rb +876 -0
  60. data/spec/config_spec.rb +194 -0
  61. data/spec/constants_spec.rb +138 -0
  62. data/spec/file_utils_spec.rb +170 -0
  63. data/spec/fixtures/samples.rb +181 -0
  64. data/spec/formatter_sections_spec.rb +382 -0
  65. data/spec/global_data_cache_spec.rb +186 -0
  66. data/spec/index_cache_spec.rb +210 -0
  67. data/spec/integration_spec.rb +543 -0
  68. data/spec/magic_words_spec.rb +261 -0
  69. data/spec/markers_spec.rb +476 -0
  70. data/spec/memory_monitor_spec.rb +192 -0
  71. data/spec/multistream_spec.rb +690 -0
  72. data/spec/output_writer_spec.rb +400 -0
  73. data/spec/parser_functions_spec.rb +455 -0
  74. data/spec/ractor_worker_spec.rb +197 -0
  75. data/spec/regex_spec.rb +281 -0
  76. data/spec/section_extractor_spec.rb +397 -0
  77. data/spec/spec_helper.rb +63 -0
  78. data/spec/stream_processor_spec.rb +579 -0
  79. data/spec/template_data_spec.rb +246 -0
  80. data/spec/template_expander_spec.rb +472 -0
  81. data/spec/template_processing_spec.rb +217 -0
  82. data/spec/text_processing_spec.rb +312 -0
  83. data/spec/utils_spec.rb +195 -16
  84. data/spec/wp2txt_spec.rb +510 -0
  85. data/wp2txt.gemspec +5 -3
  86. metadata +146 -18
  87. data/.rubocop.yml +0 -80
  88. data/data/output_samples/testdata_en.txt +0 -23002
  89. data/data/output_samples/testdata_en_category.txt +0 -132
  90. data/data/output_samples/testdata_en_summary.txt +0 -1376
  91. data/data/output_samples/testdata_ja.txt +0 -22774
  92. data/data/output_samples/testdata_ja_category.txt +0 -206
  93. data/data/output_samples/testdata_ja_summary.txt +0 -1560
  94. data/data/testdata_en.bz2 +0 -0
  95. data/data/testdata_ja.bz2 +0 -0
  96. data/image/screenshot.png +0 -0
@@ -0,0 +1,59 @@
1
+ {
2
+ "meta": {
3
+ "description": "Language tier configuration for validation framework",
4
+ "version": "1.1.0",
5
+ "updated_at": "2026-01-08"
6
+ },
7
+ "tiers": {
8
+ "tier1": {
9
+ "name": "Primary",
10
+ "description": "Core quality assurance - English as reference language",
11
+ "languages": {
12
+ "en": 10000
13
+ }
14
+ },
15
+ "tier2": {
16
+ "name": "Multilingual Validation",
17
+ "description": "Keyword and namespace validation for major languages",
18
+ "languages": {
19
+ "ja": 5000,
20
+ "zh": 3000,
21
+ "ru": 3000,
22
+ "ar": 3000,
23
+ "ko": 3000
24
+ }
25
+ },
26
+ "tier3": {
27
+ "name": "Coverage",
28
+ "description": "Major language coverage testing",
29
+ "default_sample_size": 50,
30
+ "languages": [
31
+ "de", "fr", "es", "pt", "it", "nl", "pl", "sv", "vi", "uk",
32
+ "fa", "he", "id", "cs", "fi", "hu", "ro", "tr", "th", "da",
33
+ "no", "sk", "bg", "hr", "sr", "sl", "lt", "lv", "et", "el",
34
+ "ca", "ms", "hi", "bn", "ta", "te", "mr", "ml", "kn", "gu",
35
+ "pa", "ur", "az", "ka", "hy", "be", "kk", "uz", "tg", "ky"
36
+ ]
37
+ },
38
+ "tier4": {
39
+ "name": "Smoke Test",
40
+ "description": "Basic functionality verification for all other languages",
41
+ "default_sample_size": 10,
42
+ "languages": "_remaining"
43
+ }
44
+ },
45
+ "test_levels": {
46
+ "smoke": {
47
+ "description": "Quick smoke test - uses tier-defined sample sizes",
48
+ "multiplier": 1.0
49
+ },
50
+ "standard": {
51
+ "description": "Standard validation - uses tier-defined sample sizes",
52
+ "multiplier": 1.0
53
+ },
54
+ "thorough": {
55
+ "description": "Thorough validation - 2x tier-defined sample sizes",
56
+ "multiplier": 2.0
57
+ }
58
+ }
59
+ }