kotoshu 0.3.0

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 (210) hide show
  1. checksums.yaml +7 -0
  2. data/.rspec +3 -0
  3. data/.rubocop.yml +18 -0
  4. data/CHANGELOG.md +182 -0
  5. data/CLAUDE.md +172 -0
  6. data/CODE_OF_CONDUCT.md +132 -0
  7. data/LICENSE +31 -0
  8. data/README.adoc +955 -0
  9. data/Rakefile +12 -0
  10. data/SECURITY.md +93 -0
  11. data/examples/01_basic_word_checking.rb +38 -0
  12. data/examples/02_text_document_checking.rb +77 -0
  13. data/examples/03_dictionary_backends.rb +137 -0
  14. data/examples/04_trie_data_structure.rb +146 -0
  15. data/examples/05_suggestion_algorithms.rb +239 -0
  16. data/examples/06_configuration_advanced.rb +287 -0
  17. data/examples/07_multi_language_dictionaries.rb +278 -0
  18. data/exe/kotoshu +6 -0
  19. data/lib/kotoshu/algorithms/capitalization.rb +276 -0
  20. data/lib/kotoshu/algorithms/lookup.rb +876 -0
  21. data/lib/kotoshu/algorithms/ngram_suggest.rb +270 -0
  22. data/lib/kotoshu/algorithms/permutations.rb +283 -0
  23. data/lib/kotoshu/algorithms/phonet_suggest.rb +167 -0
  24. data/lib/kotoshu/algorithms/suggest.rb +575 -0
  25. data/lib/kotoshu/algorithms.rb +14 -0
  26. data/lib/kotoshu/analyzers/semantic_analyzer.rb +295 -0
  27. data/lib/kotoshu/cache/base_cache.rb +596 -0
  28. data/lib/kotoshu/cache/cache.rb +91 -0
  29. data/lib/kotoshu/cache/frequency_cache.rb +224 -0
  30. data/lib/kotoshu/cache/language_cache.rb +454 -0
  31. data/lib/kotoshu/cache/lookup_cache.rb +166 -0
  32. data/lib/kotoshu/cache/model_cache.rb +513 -0
  33. data/lib/kotoshu/cache/suggestion_cache.rb +113 -0
  34. data/lib/kotoshu/cache.rb +40 -0
  35. data/lib/kotoshu/cli/auto_setup.rb +71 -0
  36. data/lib/kotoshu/cli/batch_reporter.rb +315 -0
  37. data/lib/kotoshu/cli/cache_command.rb +356 -0
  38. data/lib/kotoshu/cli/display_formatter.rb +431 -0
  39. data/lib/kotoshu/cli/errors.rb +36 -0
  40. data/lib/kotoshu/cli/interactive_reviewer.rb +319 -0
  41. data/lib/kotoshu/cli/language_resolver.rb +91 -0
  42. data/lib/kotoshu/cli/navigation_manager.rb +272 -0
  43. data/lib/kotoshu/cli/progress_reporter.rb +114 -0
  44. data/lib/kotoshu/cli/status_report.rb +130 -0
  45. data/lib/kotoshu/cli.rb +627 -0
  46. data/lib/kotoshu/commands/cache_command.rb +424 -0
  47. data/lib/kotoshu/commands/check_command.rb +312 -0
  48. data/lib/kotoshu/commands/model_command.rb +295 -0
  49. data/lib/kotoshu/components/passthrough_spell_checker.rb +72 -0
  50. data/lib/kotoshu/components/pos_tagger.rb +98 -0
  51. data/lib/kotoshu/components/spell_checker.rb +73 -0
  52. data/lib/kotoshu/components/synthesizer.rb +60 -0
  53. data/lib/kotoshu/components/tokenizer.rb +58 -0
  54. data/lib/kotoshu/components/whitespace_tokenizer.rb +96 -0
  55. data/lib/kotoshu/configuration/builder.rb +209 -0
  56. data/lib/kotoshu/configuration/resolver.rb +124 -0
  57. data/lib/kotoshu/configuration.rb +702 -0
  58. data/lib/kotoshu/core/exceptions.rb +165 -0
  59. data/lib/kotoshu/core/indexed_dictionary.rb +291 -0
  60. data/lib/kotoshu/core/models/affix_rule.rb +260 -0
  61. data/lib/kotoshu/core/models/result/document_result.rb +263 -0
  62. data/lib/kotoshu/core/models/result/word_result.rb +203 -0
  63. data/lib/kotoshu/core/models/word.rb +142 -0
  64. data/lib/kotoshu/core/trie/builder.rb +119 -0
  65. data/lib/kotoshu/core/trie/node.rb +94 -0
  66. data/lib/kotoshu/core/trie/trie.rb +249 -0
  67. data/lib/kotoshu/core.rb +28 -0
  68. data/lib/kotoshu/data/common_words/de.yml +1800 -0
  69. data/lib/kotoshu/data/common_words/en.yml +1215 -0
  70. data/lib/kotoshu/data/common_words/es.yml +750 -0
  71. data/lib/kotoshu/data/common_words/fr.yml +1015 -0
  72. data/lib/kotoshu/data/common_words/pt.yml +870 -0
  73. data/lib/kotoshu/data/common_words/ru.yml +484 -0
  74. data/lib/kotoshu/data/common_words_loader.rb +152 -0
  75. data/lib/kotoshu/data_structures/bloom_filter.rb +176 -0
  76. data/lib/kotoshu/debug_logger.rb +146 -0
  77. data/lib/kotoshu/debug_mode.rb +134 -0
  78. data/lib/kotoshu/defaults.rb +86 -0
  79. data/lib/kotoshu/dictionaries/catalog.rb +817 -0
  80. data/lib/kotoshu/dictionary/base.rb +237 -0
  81. data/lib/kotoshu/dictionary/cspell.rb +254 -0
  82. data/lib/kotoshu/dictionary/custom.rb +224 -0
  83. data/lib/kotoshu/dictionary/hunspell.rb +526 -0
  84. data/lib/kotoshu/dictionary/plain_text.rb +282 -0
  85. data/lib/kotoshu/dictionary/repository.rb +248 -0
  86. data/lib/kotoshu/dictionary/unified.rb +260 -0
  87. data/lib/kotoshu/dictionary/unix_words.rb +218 -0
  88. data/lib/kotoshu/documents/asciidoc_document.rb +441 -0
  89. data/lib/kotoshu/documents/document.rb +229 -0
  90. data/lib/kotoshu/documents/location.rb +139 -0
  91. data/lib/kotoshu/documents/markdown_document.rb +389 -0
  92. data/lib/kotoshu/documents/plain_text_document.rb +147 -0
  93. data/lib/kotoshu/embeddings/embedding_pipeline.rb +244 -0
  94. data/lib/kotoshu/embeddings/lru_cache.rb +233 -0
  95. data/lib/kotoshu/embeddings/onnx_runtime_model.rb +388 -0
  96. data/lib/kotoshu/embeddings/protocol.rb +83 -0
  97. data/lib/kotoshu/embeddings/protocols.rb +17 -0
  98. data/lib/kotoshu/embeddings/registry.rb +182 -0
  99. data/lib/kotoshu/embeddings/search.rb +192 -0
  100. data/lib/kotoshu/embeddings/similarity_engine.rb +248 -0
  101. data/lib/kotoshu/embeddings/similarity_search.rb +331 -0
  102. data/lib/kotoshu/embeddings/vocabulary.rb +257 -0
  103. data/lib/kotoshu/embeddings.rb +97 -0
  104. data/lib/kotoshu/fluent_checker.rb +91 -0
  105. data/lib/kotoshu/grammar/pattern_matchers/base_matcher.rb +48 -0
  106. data/lib/kotoshu/grammar/pattern_matchers/double_negative_matcher.rb +105 -0
  107. data/lib/kotoshu/grammar/pattern_matchers/possessive_context_matcher.rb +77 -0
  108. data/lib/kotoshu/grammar/pattern_matchers/vowel_sound_matcher.rb +83 -0
  109. data/lib/kotoshu/grammar/rule.rb +95 -0
  110. data/lib/kotoshu/grammar/rule_engine.rb +111 -0
  111. data/lib/kotoshu/grammar/rule_loader.rb +31 -0
  112. data/lib/kotoshu/grammar.rb +18 -0
  113. data/lib/kotoshu/integrity/audit_log.rb +88 -0
  114. data/lib/kotoshu/integrity/manifest.rb +117 -0
  115. data/lib/kotoshu/integrity/net_http.rb +46 -0
  116. data/lib/kotoshu/integrity.rb +25 -0
  117. data/lib/kotoshu/keyboard/layout.rb +115 -0
  118. data/lib/kotoshu/keyboard/layouts/azerty.rb +57 -0
  119. data/lib/kotoshu/keyboard/layouts/dvorak.rb +56 -0
  120. data/lib/kotoshu/keyboard/layouts/jcuken.rb +59 -0
  121. data/lib/kotoshu/keyboard/layouts/qwerty.rb +54 -0
  122. data/lib/kotoshu/keyboard/layouts/qwertz.rb +57 -0
  123. data/lib/kotoshu/keyboard/registry.rb +146 -0
  124. data/lib/kotoshu/keyboard.rb +60 -0
  125. data/lib/kotoshu/language/detector.rb +242 -0
  126. data/lib/kotoshu/language/identifier.rb +378 -0
  127. data/lib/kotoshu/language/languages/base.rb +256 -0
  128. data/lib/kotoshu/language/normalizer/base.rb +137 -0
  129. data/lib/kotoshu/language/registry.rb +147 -0
  130. data/lib/kotoshu/language/resources/ar/common_words.txt +6753 -0
  131. data/lib/kotoshu/language/resources/ar/confusion_sets.txt +11 -0
  132. data/lib/kotoshu/language/resources/de/common_words.txt +10003 -0
  133. data/lib/kotoshu/language/resources/de/confusion_sets.txt +246 -0
  134. data/lib/kotoshu/language/resources/en/common_words.txt +9979 -0
  135. data/lib/kotoshu/language/resources/en/confusion_sets.txt +871 -0
  136. data/lib/kotoshu/language/resources/es/common_words.txt +9992 -0
  137. data/lib/kotoshu/language/resources/es/confusion_sets.txt +17 -0
  138. data/lib/kotoshu/language/resources/fr/common_words.txt +9993 -0
  139. data/lib/kotoshu/language/resources/fr/confusion_sets.txt +76 -0
  140. data/lib/kotoshu/language/resources/pt/common_words.txt +9977 -0
  141. data/lib/kotoshu/language/resources/pt/confusion_sets.txt +18 -0
  142. data/lib/kotoshu/language/resources/ru/common_words.txt +9951 -0
  143. data/lib/kotoshu/language/resources/ru/confusion_sets.txt +5 -0
  144. data/lib/kotoshu/language/tokenizer/base.rb +170 -0
  145. data/lib/kotoshu/language/tokenizer/french_tokenizer.rb +170 -0
  146. data/lib/kotoshu/language/tokenizer/german_tokenizer.rb +41 -0
  147. data/lib/kotoshu/language/tokenizer/japanese_tokenizer.rb +60 -0
  148. data/lib/kotoshu/language/tokenizer/latin_tokenizer.rb +141 -0
  149. data/lib/kotoshu/language/tokenizer/portuguese_tokenizer.rb +160 -0
  150. data/lib/kotoshu/language/tokenizer/russian_tokenizer.rb +95 -0
  151. data/lib/kotoshu/language/tokenizer/spanish_tokenizer.rb +122 -0
  152. data/lib/kotoshu/language.rb +99 -0
  153. data/lib/kotoshu/languages/de/language.rb +546 -0
  154. data/lib/kotoshu/languages/en/language.rb +448 -0
  155. data/lib/kotoshu/languages/es/language.rb +459 -0
  156. data/lib/kotoshu/languages/fr/language.rb +493 -0
  157. data/lib/kotoshu/languages/ja/language.rb +477 -0
  158. data/lib/kotoshu/languages/pt/language.rb +423 -0
  159. data/lib/kotoshu/languages/ru/language.rb +404 -0
  160. data/lib/kotoshu/languages.rb +43 -0
  161. data/lib/kotoshu/metrics_collector.rb +222 -0
  162. data/lib/kotoshu/metrics_module.rb +110 -0
  163. data/lib/kotoshu/models/context.rb +119 -0
  164. data/lib/kotoshu/models/embedding_model.rb +182 -0
  165. data/lib/kotoshu/models/fasttext_model.rb +220 -0
  166. data/lib/kotoshu/models/nearest_neighbor.rb +87 -0
  167. data/lib/kotoshu/models/onnx_model.rb +333 -0
  168. data/lib/kotoshu/models/semantic_error.rb +165 -0
  169. data/lib/kotoshu/models/suggestion.rb +106 -0
  170. data/lib/kotoshu/models/word_embedding.rb +107 -0
  171. data/lib/kotoshu/paths.rb +53 -0
  172. data/lib/kotoshu/personal_dictionary.rb +94 -0
  173. data/lib/kotoshu/plugins/plugin.rb +61 -0
  174. data/lib/kotoshu/plugins/registry.rb +120 -0
  175. data/lib/kotoshu/project_config.rb +76 -0
  176. data/lib/kotoshu/readers/aff_data.rb +356 -0
  177. data/lib/kotoshu/readers/aff_reader.rb +375 -0
  178. data/lib/kotoshu/readers/condition_checker.rb +142 -0
  179. data/lib/kotoshu/readers/dic_reader.rb +118 -0
  180. data/lib/kotoshu/readers/file_reader.rb +347 -0
  181. data/lib/kotoshu/readers/lookup_builder.rb +299 -0
  182. data/lib/kotoshu/readers/readers.rb +6 -0
  183. data/lib/kotoshu/readers.rb +9 -0
  184. data/lib/kotoshu/resource_bundle.rb +30 -0
  185. data/lib/kotoshu/resource_manager.rb +295 -0
  186. data/lib/kotoshu/results/result.rb +165 -0
  187. data/lib/kotoshu/scripts/fasttext_to_onnx.py +275 -0
  188. data/lib/kotoshu/source_registry.rb +74 -0
  189. data/lib/kotoshu/spellchecker/parallel_checker.rb +90 -0
  190. data/lib/kotoshu/spellchecker.rb +298 -0
  191. data/lib/kotoshu/string_metrics.rb +153 -0
  192. data/lib/kotoshu/suggestions/context.rb +55 -0
  193. data/lib/kotoshu/suggestions/generator.rb +175 -0
  194. data/lib/kotoshu/suggestions/pipeline.rb +135 -0
  195. data/lib/kotoshu/suggestions/strategies/base_strategy.rb +296 -0
  196. data/lib/kotoshu/suggestions/strategies/composite_strategy.rb +140 -0
  197. data/lib/kotoshu/suggestions/strategies/edit_distance_strategy.rb +671 -0
  198. data/lib/kotoshu/suggestions/strategies/keyboard_proximity_strategy.rb +228 -0
  199. data/lib/kotoshu/suggestions/strategies/ngram_strategy.rb +130 -0
  200. data/lib/kotoshu/suggestions/strategies/phonetic_strategy.rb +329 -0
  201. data/lib/kotoshu/suggestions/strategies/semantic_strategy.rb +316 -0
  202. data/lib/kotoshu/suggestions/strategies/symspell_strategy.rb +275 -0
  203. data/lib/kotoshu/suggestions/suggestion.rb +174 -0
  204. data/lib/kotoshu/suggestions/suggestion_set.rb +238 -0
  205. data/lib/kotoshu/version.rb +5 -0
  206. data/lib/kotoshu.rb +493 -0
  207. data/script/validate_all_dictionaries.rb +444 -0
  208. data/sig/kotoshu.rbs +4 -0
  209. data/test_oop.rb +79 -0
  210. metadata +298 -0
data/lib/kotoshu/language/resources/pt/confusion_sets.txt ADDED
@@ -0,0 +1,18 @@
1
+ # Portuguese confusion sets
2
+ # License: GNU LESSER GENERAL PUBLIC LICENSE Version 2
3
+ #
4
+ # Line format:
5
+ # <word1>|<description1>; <word2>|<description2>; <factor> # optional comment
6
+ # <word1> and <word2> are words that can easily be confused
7
+ # <description> will be used in the error message to explain the word (optional)
8
+ # <factor> is the factor of how much more the other word must be more
9
+ # probable so the text is considered potentially incorrect.
10
+ # Use a higher value for better precision but lower recall.
11
+ # Precision (p) and recall (r) values in the comments come from ConfusionRuleEvaluator
12
+ # and are based on Wikipedia, Tatoeba, and Enron data, usually with 1000 random
13
+ # sentences (if that many sentence are available for that pair). The number after recall
14
+ # is the number of sentences used for evaluation.
15
+ # Order is relevant for ambiguous cases like 'know' ('no' or 'now') where the match
16
+ # is used whose pair comes first in this file.
17
+ #
18
+