kotoshu 1.0.2-x86_64-linux

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 (458) hide show
  1. checksums.yaml +7 -0
  2. data/.kotoshu-baseline.json +1 -0
  3. data/.pre-commit-hooks.yaml +18 -0
  4. data/.rspec +3 -0
  5. data/.rubocop.yml +351 -0
  6. data/.yardopts +8 -0
  7. data/CHANGELOG.md +813 -0
  8. data/CLAUDE.md +176 -0
  9. data/CODE_OF_CONDUCT.md +132 -0
  10. data/Cargo.lock +359 -0
  11. data/Cargo.toml +15 -0
  12. data/LICENSE +31 -0
  13. data/README.adoc +1292 -0
  14. data/Rakefile +150 -0
  15. data/SECURITY.md +93 -0
  16. data/TODO.impl/00-cut-0.1.md +121 -0
  17. data/TODO.impl/00-cut-0.2.md +175 -0
  18. data/TODO.impl/00-vision.md +281 -0
  19. data/TODO.impl/01-hunspell-correctness.md +111 -0
  20. data/TODO.impl/02-cli-unification.md +74 -0
  21. data/TODO.impl/03-dynamic-download.md +107 -0
  22. data/TODO.impl/04-language-modules.md +89 -0
  23. data/TODO.impl/05-semantic-path.md +83 -0
  24. data/TODO.impl/06-cjk-support.md +105 -0
  25. data/TODO.impl/07-rtl-support.md +71 -0
  26. data/TODO.impl/08-grammar-engine.md +106 -0
  27. data/TODO.impl/09-integrity-security.md +90 -0
  28. data/TODO.impl/10-testing-ci.md +98 -0
  29. data/TODO.impl/100-full-feature-batch3.md +28 -0
  30. data/TODO.impl/101-int4-tier-experiment.md +32 -0
  31. data/TODO.impl/102-lid-chain.md +28 -0
  32. data/TODO.impl/103-oov-bucket-tables.md +27 -0
  33. data/TODO.impl/104-vscode-marketplace-readiness.md +32 -0
  34. data/TODO.impl/105-personal-dictionary-in-check.md +34 -0
  35. data/TODO.impl/106-native-lid-detection.md +36 -0
  36. data/TODO.impl/107-basic-support-every-staged-language.md +42 -0
  37. data/TODO.impl/108-ko-ne-full-feature.md +37 -0
  38. data/TODO.impl/109-ten-audit.md +26 -0
  39. data/TODO.impl/11-release-v1.md +95 -0
  40. data/TODO.impl/110-sr-latn-and-polish.md +33 -0
  41. data/TODO.impl/111-embedding-bakeoff.md +33 -0
  42. data/TODO.impl/112-deployability-and-gating.md +26 -0
  43. data/TODO.impl/113-language-packs.md +26 -0
  44. data/TODO.impl/114-typo-biencoder-thread.md +33 -0
  45. data/TODO.impl/115-hybrid-retrieval-pricing.md +22 -0
  46. data/TODO.impl/116-baseline-suggestion-skip.md +81 -0
  47. data/TODO.impl/117-deterministic-frequency-tiers.md +110 -0
  48. data/TODO.impl/118-server-gem-floor.md +33 -0
  49. data/TODO.impl/119-embedded-kelly-tiers.md +56 -0
  50. data/TODO.impl/120-setup-metadata-refresh.md +35 -0
  51. data/TODO.impl/121-jekyll-baseline-skip.md +33 -0
  52. data/TODO.impl/122-pack-compression-kpk2.md +66 -0
  53. data/TODO.impl/123-typo-corpus-synthesis.md +55 -0
  54. data/TODO.impl/124-owner-residue.md +19 -0
  55. data/TODO.impl/125-consumer-floor-guards.md +43 -0
  56. data/TODO.impl/126-tier-error-budgets.md +33 -0
  57. data/TODO.impl/127-suggestion-feedback-loop.md +34 -0
  58. data/TODO.impl/128-hybrid-pricing-verdict.md +47 -0
  59. data/TODO.impl/129-pt-fr-corpora.md +23 -0
  60. data/TODO.impl/130-news-truth-0912.md +23 -0
  61. data/TODO.impl/131-hybrid-productization.md +42 -0
  62. data/TODO.impl/132-techniques-page-and-prose.md +27 -0
  63. data/TODO.impl/133-rust-first-distribution.md +68 -0
  64. data/TODO.impl/20-encapsulation-cleanup.md +47 -0
  65. data/TODO.impl/21-autoload-migration.md +64 -0
  66. data/TODO.impl/22-url-pin-single-source-of-truth.md +120 -0
  67. data/TODO.impl/23-fix-url-defaults.md +57 -0
  68. data/TODO.impl/24-cli-auto-setup-prompt.md +76 -0
  69. data/TODO.impl/25-soft-onnxruntime-require.md +75 -0
  70. data/TODO.impl/26-onnx-vocab-json-generation.md +96 -0
  71. data/TODO.impl/27-end-to-end-smoke-spec.md +113 -0
  72. data/TODO.impl/28-readme-quickstart-verification.md +68 -0
  73. data/TODO.impl/29-status-command.md +84 -0
  74. data/TODO.impl/30-language-auto-detection.md +74 -0
  75. data/TODO.impl/31-download-progress.md +58 -0
  76. data/TODO.impl/32-sarif-output-verification.md +72 -0
  77. data/TODO.impl/33-audit-log-rotation.md +54 -0
  78. data/TODO.impl/34-cache-eviction.md +59 -0
  79. data/TODO.impl/35-shell-completion.md +61 -0
  80. data/TODO.impl/36-cleanup-regressions-0.3.1.md +134 -0
  81. data/TODO.impl/37-hunspell-correctness-tier2.md +203 -0
  82. data/TODO.impl/38-onnx-semantic-gating.md +218 -0
  83. data/TODO.impl/39-tier3-and-beyond.md +232 -0
  84. data/TODO.impl/40-spec-drift-cleanup.md +134 -0
  85. data/TODO.impl/50-structure-aware-document-api.md +194 -0
  86. data/TODO.impl/51-grammar-engine-expansion.md +75 -0
  87. data/TODO.impl/52-multi-language-documents.md +95 -0
  88. data/TODO.impl/53-document-plugin-architecture.md +94 -0
  89. data/TODO.impl/54-cjk-support.md +117 -0
  90. data/TODO.impl/55-rtl-support.md +109 -0
  91. data/TODO.impl/56-t4-t5-t6-quality-architecture-ecosystem.md +126 -0
  92. data/TODO.impl/57-t5.1-step3-pure-function-strategies.md +138 -0
  93. data/TODO.impl/58-t5.2-configuration-as-data.md +113 -0
  94. data/TODO.impl/59-yard-api-documentation.md +75 -0
  95. data/TODO.impl/60-lsp-server.md +174 -0
  96. data/TODO.impl/61-editor-ecosystem.md +167 -0
  97. data/TODO.impl/62-framework-integrations.md +159 -0
  98. data/TODO.impl/63-web-playground-wasm.md +186 -0
  99. data/TODO.impl/64-http-api-and-sdks.md +191 -0
  100. data/TODO.impl/65-universal-kotoshu.md +251 -0
  101. data/TODO.impl/66-kotoshu-core.md +169 -0
  102. data/TODO.impl/67-kotoshu-rs-and-access-libraries.md +137 -0
  103. data/TODO.impl/68-sota-adoption.md +152 -0
  104. data/TODO.impl/69-sota-typo-eval.md +74 -0
  105. data/TODO.impl/70-sota-confidence-cascade.md +59 -0
  106. data/TODO.impl/71-sota-nested-model.md +63 -0
  107. data/TODO.impl/72-model2vec-evaluation.md +49 -0
  108. data/TODO.impl/73-rl-reranker.md +42 -0
  109. data/TODO.impl/74-distilled-reranker.md +36 -0
  110. data/TODO.impl/75-llm-evaluator.md +35 -0
  111. data/TODO.impl/76-optional-llm-backend.md +37 -0
  112. data/TODO.impl/77-model-coverage-expansion.md +96 -0
  113. data/TODO.impl/78-in-browser-playground.md +69 -0
  114. data/TODO.impl/79-news-and-releases.md +60 -0
  115. data/TODO.impl/80-ecosystem-docs.md +56 -0
  116. data/TODO.impl/81-editor-reach.md +68 -0
  117. data/TODO.impl/82-doc-formats-and-ignores.md +81 -0
  118. data/TODO.impl/83-models-batch-2.md +56 -0
  119. data/TODO.impl/84-language-modules-wave2.md +75 -0
  120. data/TODO.impl/85-wasm-model-api.md +48 -0
  121. data/TODO.impl/86-site-truth-wave2.md +45 -0
  122. data/TODO.impl/87-lsp-personal-dictionary.md +36 -0
  123. data/TODO.impl/88-cli-directory-mode.md +54 -0
  124. data/TODO.impl/89-framework-integrations-exec.md +59 -0
  125. data/TODO.impl/90-gem-correctness-residues.md +44 -0
  126. data/TODO.impl/91-unicode-and-sv-aff.md +47 -0
  127. data/TODO.impl/92-tier-mirror-cors.md +88 -0
  128. data/TODO.impl/93-python-wheels.md +32 -0
  129. data/TODO.impl/94-site-integrations-docs.md +35 -0
  130. data/TODO.impl/95-editor-action-polish.md +27 -0
  131. data/TODO.impl/96-server-semantic-models.md +50 -0
  132. data/TODO.impl/97-yard-execution.md +73 -0
  133. data/TODO.impl/98-campaign-cleanup.md +78 -0
  134. data/TODO.impl/99-site-truth-performance-docs.md +31 -0
  135. data/conformance/vectors.jsonl +2630 -0
  136. data/data/en/grammar/rules.yaml +851 -0
  137. data/docs/STABILITY-1.0-AUDIT.md +251 -0
  138. data/docs/STABILITY-1.0.md +137 -0
  139. data/docs/cache-architecture.md +502 -0
  140. data/docs/verification-evidence/correct3/pr_body.md +37 -0
  141. data/docs/verification-evidence/correct3/rspec_final.log +5588 -0
  142. data/docs/verification-evidence/correct3/rspec_full.log +4504 -0
  143. data/docs/verification-evidence/correct3/sv.aff +856 -0
  144. data/docs/verification-evidence/correct3/sv.dic +153717 -0
  145. data/examples/01_basic_word_checking.rb +38 -0
  146. data/examples/02_text_document_checking.rb +77 -0
  147. data/examples/03_dictionary_backends.rb +137 -0
  148. data/examples/04_trie_data_structure.rb +146 -0
  149. data/examples/05_suggestion_algorithms.rb +239 -0
  150. data/examples/06_configuration_advanced.rb +287 -0
  151. data/examples/07_multi_language_dictionaries.rb +278 -0
  152. data/exe/kotoshu +6 -0
  153. data/lib/kotoshu/algorithms/capitalization.rb +276 -0
  154. data/lib/kotoshu/algorithms/edit_distance.rb +128 -0
  155. data/lib/kotoshu/algorithms/lookup/affix_form.rb +132 -0
  156. data/lib/kotoshu/algorithms/lookup/compound_checks.rb +209 -0
  157. data/lib/kotoshu/algorithms/lookup/compound_form.rb +50 -0
  158. data/lib/kotoshu/algorithms/lookup.rb +841 -0
  159. data/lib/kotoshu/algorithms/ngram_suggest.rb +367 -0
  160. data/lib/kotoshu/algorithms/permutations.rb +283 -0
  161. data/lib/kotoshu/algorithms/phonet_suggest.rb +162 -0
  162. data/lib/kotoshu/algorithms/soundex.rb +92 -0
  163. data/lib/kotoshu/algorithms/suggest.rb +794 -0
  164. data/lib/kotoshu/algorithms.rb +23 -0
  165. data/lib/kotoshu/analyzers/semantic_analyzer.rb +405 -0
  166. data/lib/kotoshu/analyzers.rb +8 -0
  167. data/lib/kotoshu/baseline/application.rb +18 -0
  168. data/lib/kotoshu/baseline/entry.rb +33 -0
  169. data/lib/kotoshu/baseline/store.rb +175 -0
  170. data/lib/kotoshu/baseline.rb +20 -0
  171. data/lib/kotoshu/cache/base_cache.rb +778 -0
  172. data/lib/kotoshu/cache/cache.rb +91 -0
  173. data/lib/kotoshu/cache/eviction_policy.rb +66 -0
  174. data/lib/kotoshu/cache/frequency_cache.rb +283 -0
  175. data/lib/kotoshu/cache/language_cache.rb +511 -0
  176. data/lib/kotoshu/cache/lookup_cache.rb +166 -0
  177. data/lib/kotoshu/cache/model_cache.rb +1147 -0
  178. data/lib/kotoshu/cache/model_registry.rb +109 -0
  179. data/lib/kotoshu/cache/staged_languages.rb +45 -0
  180. data/lib/kotoshu/cache/suggestion_cache.rb +113 -0
  181. data/lib/kotoshu/cache.rb +49 -0
  182. data/lib/kotoshu/cli/auto_setup.rb +71 -0
  183. data/lib/kotoshu/cli/baseline_command.rb +119 -0
  184. data/lib/kotoshu/cli/batch_reporter.rb +321 -0
  185. data/lib/kotoshu/cli/cache_command.rb +282 -0
  186. data/lib/kotoshu/cli/completions_command.rb +210 -0
  187. data/lib/kotoshu/cli/dict_command.rb +64 -0
  188. data/lib/kotoshu/cli/directory_check.rb +146 -0
  189. data/lib/kotoshu/cli/directory_walker.rb +132 -0
  190. data/lib/kotoshu/cli/display_formatter.rb +429 -0
  191. data/lib/kotoshu/cli/errors.rb +36 -0
  192. data/lib/kotoshu/cli/ignore_matcher.rb +205 -0
  193. data/lib/kotoshu/cli/interactive_reviewer.rb +314 -0
  194. data/lib/kotoshu/cli/language_resolver.rb +91 -0
  195. data/lib/kotoshu/cli/navigation_manager.rb +273 -0
  196. data/lib/kotoshu/cli/personal_command.rb +113 -0
  197. data/lib/kotoshu/cli/progress_reporter.rb +114 -0
  198. data/lib/kotoshu/cli/status_report.rb +130 -0
  199. data/lib/kotoshu/cli.rb +880 -0
  200. data/lib/kotoshu/components/passthrough_spell_checker.rb +70 -0
  201. data/lib/kotoshu/components/pos_tagger.rb +98 -0
  202. data/lib/kotoshu/components/spell_checker.rb +73 -0
  203. data/lib/kotoshu/components/synthesizer.rb +60 -0
  204. data/lib/kotoshu/components/tokenizer.rb +58 -0
  205. data/lib/kotoshu/components/whitespace_tokenizer.rb +94 -0
  206. data/lib/kotoshu/components.rb +13 -0
  207. data/lib/kotoshu/configuration/builder.rb +207 -0
  208. data/lib/kotoshu/configuration/resolver.rb +124 -0
  209. data/lib/kotoshu/configuration.rb +829 -0
  210. data/lib/kotoshu/conformance_exporter.rb +256 -0
  211. data/lib/kotoshu/conformance_runner.rb +176 -0
  212. data/lib/kotoshu/core/exceptions.rb +186 -0
  213. data/lib/kotoshu/core/indexed_dictionary.rb +293 -0
  214. data/lib/kotoshu/core/models/affix_rule.rb +262 -0
  215. data/lib/kotoshu/core/models/result/document_result.rb +132 -0
  216. data/lib/kotoshu/core/models/result/word_result.rb +131 -0
  217. data/lib/kotoshu/core/models/word.rb +131 -0
  218. data/lib/kotoshu/core/trie/builder.rb +119 -0
  219. data/lib/kotoshu/core/trie/node.rb +94 -0
  220. data/lib/kotoshu/core/trie/trie.rb +249 -0
  221. data/lib/kotoshu/core.rb +28 -0
  222. data/lib/kotoshu/data/common_words/de.yml +1800 -0
  223. data/lib/kotoshu/data/common_words/en.yml +1215 -0
  224. data/lib/kotoshu/data/common_words/es.yml +750 -0
  225. data/lib/kotoshu/data/common_words/fr.yml +1015 -0
  226. data/lib/kotoshu/data/common_words/pt.yml +870 -0
  227. data/lib/kotoshu/data/common_words/ru.yml +484 -0
  228. data/lib/kotoshu/data/common_words_loader.rb +141 -0
  229. data/lib/kotoshu/data/frozen_kelly/en.json +1154 -0
  230. data/lib/kotoshu/data/frozen_kelly.rb +38 -0
  231. data/lib/kotoshu/data.rb +8 -0
  232. data/lib/kotoshu/data_structures/bloom_filter.rb +188 -0
  233. data/lib/kotoshu/data_structures.rb +8 -0
  234. data/lib/kotoshu/debug_logger.rb +146 -0
  235. data/lib/kotoshu/debug_mode.rb +136 -0
  236. data/lib/kotoshu/defaults.rb +84 -0
  237. data/lib/kotoshu/dictionaries/catalog.rb +814 -0
  238. data/lib/kotoshu/dictionaries.rb +8 -0
  239. data/lib/kotoshu/dictionary/base.rb +324 -0
  240. data/lib/kotoshu/dictionary/cspell.rb +243 -0
  241. data/lib/kotoshu/dictionary/custom.rb +225 -0
  242. data/lib/kotoshu/dictionary/hunspell.rb +520 -0
  243. data/lib/kotoshu/dictionary/plain_text.rb +302 -0
  244. data/lib/kotoshu/dictionary/repository.rb +246 -0
  245. data/lib/kotoshu/dictionary/unified.rb +236 -0
  246. data/lib/kotoshu/dictionary/unix_words.rb +218 -0
  247. data/lib/kotoshu/dictionary.rb +15 -0
  248. data/lib/kotoshu/documents/document.rb +120 -0
  249. data/lib/kotoshu/documents/plain_text_document.rb +73 -0
  250. data/lib/kotoshu/documents/source_position.rb +45 -0
  251. data/lib/kotoshu/documents/source_range.rb +76 -0
  252. data/lib/kotoshu/documents/suppressions/scanner.rb +149 -0
  253. data/lib/kotoshu/documents/suppressions/suppression.rb +75 -0
  254. data/lib/kotoshu/documents/suppressions.rb +44 -0
  255. data/lib/kotoshu/documents/text_node.rb +49 -0
  256. data/lib/kotoshu/documents.rb +178 -0
  257. data/lib/kotoshu/embeddings/embedding_pipeline.rb +238 -0
  258. data/lib/kotoshu/embeddings/lru_cache.rb +244 -0
  259. data/lib/kotoshu/embeddings/onnx_runtime_model.rb +411 -0
  260. data/lib/kotoshu/embeddings/protocol.rb +96 -0
  261. data/lib/kotoshu/embeddings/protocols.rb +23 -0
  262. data/lib/kotoshu/embeddings/registry.rb +184 -0
  263. data/lib/kotoshu/embeddings/search.rb +204 -0
  264. data/lib/kotoshu/embeddings/similarity_engine.rb +278 -0
  265. data/lib/kotoshu/embeddings/similarity_search.rb +328 -0
  266. data/lib/kotoshu/embeddings/vocabulary.rb +306 -0
  267. data/lib/kotoshu/embeddings.rb +87 -0
  268. data/lib/kotoshu/fluent_checker.rb +94 -0
  269. data/lib/kotoshu/grammar/pattern_matchers/base_matcher.rb +48 -0
  270. data/lib/kotoshu/grammar/pattern_matchers/double_negative_matcher.rb +179 -0
  271. data/lib/kotoshu/grammar/pattern_matchers/phrase_matcher.rb +86 -0
  272. data/lib/kotoshu/grammar/pattern_matchers/possessive_context_matcher.rb +75 -0
  273. data/lib/kotoshu/grammar/pattern_matchers/possessive_contraction_matcher.rb +87 -0
  274. data/lib/kotoshu/grammar/pattern_matchers/sentence_start_matcher.rb +84 -0
  275. data/lib/kotoshu/grammar/pattern_matchers/vowel_sound_matcher.rb +81 -0
  276. data/lib/kotoshu/grammar/pattern_matchers/word_list_matcher.rb +66 -0
  277. data/lib/kotoshu/grammar/rule.rb +99 -0
  278. data/lib/kotoshu/grammar/rule_engine.rb +96 -0
  279. data/lib/kotoshu/grammar/rule_loader.rb +30 -0
  280. data/lib/kotoshu/grammar.rb +24 -0
  281. data/lib/kotoshu/integrity/audit_log.rb +167 -0
  282. data/lib/kotoshu/integrity/manifest.rb +116 -0
  283. data/lib/kotoshu/integrity/net_http.rb +51 -0
  284. data/lib/kotoshu/integrity/rotation_policy.rb +88 -0
  285. data/lib/kotoshu/integrity.rb +26 -0
  286. data/lib/kotoshu/jekyll.rb +101 -0
  287. data/lib/kotoshu/keyboard/layout.rb +116 -0
  288. data/lib/kotoshu/keyboard/layouts/arabic.rb +59 -0
  289. data/lib/kotoshu/keyboard/layouts/azerty.rb +55 -0
  290. data/lib/kotoshu/keyboard/layouts/bulgarian.rb +57 -0
  291. data/lib/kotoshu/keyboard/layouts/devanagari_inscript.rb +52 -0
  292. data/lib/kotoshu/keyboard/layouts/dubeolsik.rb +56 -0
  293. data/lib/kotoshu/keyboard/layouts/dvorak.rb +54 -0
  294. data/lib/kotoshu/keyboard/layouts/greek.rb +52 -0
  295. data/lib/kotoshu/keyboard/layouts/hebrew.rb +57 -0
  296. data/lib/kotoshu/keyboard/layouts/hrsl.rb +94 -0
  297. data/lib/kotoshu/keyboard/layouts/jcuken.rb +57 -0
  298. data/lib/kotoshu/keyboard/layouts/latin.rb +266 -0
  299. data/lib/kotoshu/keyboard/layouts/persian.rb +58 -0
  300. data/lib/kotoshu/keyboard/layouts/qwerty.rb +52 -0
  301. data/lib/kotoshu/keyboard/layouts/qwertz.rb +55 -0
  302. data/lib/kotoshu/keyboard/layouts/serbian.rb +59 -0
  303. data/lib/kotoshu/keyboard/layouts/turkish_q.rb +52 -0
  304. data/lib/kotoshu/keyboard/layouts/ukrainian.rb +51 -0
  305. data/lib/kotoshu/keyboard/registry.rb +201 -0
  306. data/lib/kotoshu/keyboard.rb +96 -0
  307. data/lib/kotoshu/kotoshu_native.so +0 -0
  308. data/lib/kotoshu/language/detector.rb +242 -0
  309. data/lib/kotoshu/language/identifier.rb +376 -0
  310. data/lib/kotoshu/language/languages/base.rb +271 -0
  311. data/lib/kotoshu/language/lid_detector.rb +188 -0
  312. data/lib/kotoshu/language/normalizer/arabic.rb +113 -0
  313. data/lib/kotoshu/language/normalizer/base.rb +133 -0
  314. data/lib/kotoshu/language/normalizer/greek.rb +63 -0
  315. data/lib/kotoshu/language/normalizer/hebrew.rb +72 -0
  316. data/lib/kotoshu/language/normalizer/persian.rb +36 -0
  317. data/lib/kotoshu/language/normalizer/turkish.rb +38 -0
  318. data/lib/kotoshu/language/registry.rb +209 -0
  319. data/lib/kotoshu/language/resources/ar/common_words.txt +6753 -0
  320. data/lib/kotoshu/language/resources/ar/confusion_sets.txt +11 -0
  321. data/lib/kotoshu/language/resources/de/common_words.txt +10003 -0
  322. data/lib/kotoshu/language/resources/de/confusion_sets.txt +246 -0
  323. data/lib/kotoshu/language/resources/en/common_words.txt +9979 -0
  324. data/lib/kotoshu/language/resources/en/confusion_sets.txt +871 -0
  325. data/lib/kotoshu/language/resources/es/common_words.txt +9992 -0
  326. data/lib/kotoshu/language/resources/es/confusion_sets.txt +17 -0
  327. data/lib/kotoshu/language/resources/fr/common_words.txt +9993 -0
  328. data/lib/kotoshu/language/resources/fr/confusion_sets.txt +76 -0
  329. data/lib/kotoshu/language/resources/pt/common_words.txt +9977 -0
  330. data/lib/kotoshu/language/resources/pt/confusion_sets.txt +18 -0
  331. data/lib/kotoshu/language/resources/ru/common_words.txt +9951 -0
  332. data/lib/kotoshu/language/resources/ru/confusion_sets.txt +5 -0
  333. data/lib/kotoshu/language/script.rb +128 -0
  334. data/lib/kotoshu/language/segmenter.rb +122 -0
  335. data/lib/kotoshu/language/suika.rb +38 -0
  336. data/lib/kotoshu/language/tokenizer/base.rb +187 -0
  337. data/lib/kotoshu/language/tokenizer/cyrillic_tokenizer.rb +76 -0
  338. data/lib/kotoshu/language/tokenizer/devanagari_tokenizer.rb +70 -0
  339. data/lib/kotoshu/language/tokenizer/french_tokenizer.rb +172 -0
  340. data/lib/kotoshu/language/tokenizer/german_tokenizer.rb +41 -0
  341. data/lib/kotoshu/language/tokenizer/greek_tokenizer.rb +72 -0
  342. data/lib/kotoshu/language/tokenizer/hangul_tokenizer.rb +70 -0
  343. data/lib/kotoshu/language/tokenizer/japanese_tokenizer.rb +55 -0
  344. data/lib/kotoshu/language/tokenizer/latin_tokenizer.rb +153 -0
  345. data/lib/kotoshu/language/tokenizer/portuguese_tokenizer.rb +160 -0
  346. data/lib/kotoshu/language/tokenizer/russian_tokenizer.rb +93 -0
  347. data/lib/kotoshu/language/tokenizer/script_tokenizer.rb +62 -0
  348. data/lib/kotoshu/language/tokenizer/spanish_tokenizer.rb +122 -0
  349. data/lib/kotoshu/language.rb +127 -0
  350. data/lib/kotoshu/languages/ar/language.rb +98 -0
  351. data/lib/kotoshu/languages/bg/language.rb +37 -0
  352. data/lib/kotoshu/languages/ca/language.rb +22 -0
  353. data/lib/kotoshu/languages/cs/language.rb +22 -0
  354. data/lib/kotoshu/languages/da/language.rb +22 -0
  355. data/lib/kotoshu/languages/de/language.rb +554 -0
  356. data/lib/kotoshu/languages/el/language.rb +50 -0
  357. data/lib/kotoshu/languages/en/language.rb +470 -0
  358. data/lib/kotoshu/languages/es/language.rb +476 -0
  359. data/lib/kotoshu/languages/et/language.rb +24 -0
  360. data/lib/kotoshu/languages/fa/language.rb +91 -0
  361. data/lib/kotoshu/languages/fr/language.rb +505 -0
  362. data/lib/kotoshu/languages/he/language.rb +98 -0
  363. data/lib/kotoshu/languages/hr/language.rb +24 -0
  364. data/lib/kotoshu/languages/hu/language.rb +22 -0
  365. data/lib/kotoshu/languages/id/language.rb +25 -0
  366. data/lib/kotoshu/languages/it/language.rb +22 -0
  367. data/lib/kotoshu/languages/ja/language.rb +476 -0
  368. data/lib/kotoshu/languages/ko/language.rb +56 -0
  369. data/lib/kotoshu/languages/latin_base.rb +53 -0
  370. data/lib/kotoshu/languages/lt/language.rb +24 -0
  371. data/lib/kotoshu/languages/lv/language.rb +24 -0
  372. data/lib/kotoshu/languages/nb/language.rb +25 -0
  373. data/lib/kotoshu/languages/ne/language.rb +60 -0
  374. data/lib/kotoshu/languages/nl/language.rb +22 -0
  375. data/lib/kotoshu/languages/nn/language.rb +26 -0
  376. data/lib/kotoshu/languages/pl/language.rb +22 -0
  377. data/lib/kotoshu/languages/pt/language.rb +439 -0
  378. data/lib/kotoshu/languages/ro/language.rb +22 -0
  379. data/lib/kotoshu/languages/ru/language.rb +420 -0
  380. data/lib/kotoshu/languages/sk/language.rb +25 -0
  381. data/lib/kotoshu/languages/sl/language.rb +25 -0
  382. data/lib/kotoshu/languages/sr/language.rb +39 -0
  383. data/lib/kotoshu/languages/sr-Latn/language.rb +35 -0
  384. data/lib/kotoshu/languages/sv/language.rb +22 -0
  385. data/lib/kotoshu/languages/tr/language.rb +36 -0
  386. data/lib/kotoshu/languages/uk/language.rb +38 -0
  387. data/lib/kotoshu/languages/vi/language.rb +22 -0
  388. data/lib/kotoshu/languages.rb +64 -0
  389. data/lib/kotoshu/metrics_collector.rb +238 -0
  390. data/lib/kotoshu/metrics_module.rb +121 -0
  391. data/lib/kotoshu/models/context.rb +119 -0
  392. data/lib/kotoshu/models/embedding_model.rb +181 -0
  393. data/lib/kotoshu/models/fasttext_model.rb +212 -0
  394. data/lib/kotoshu/models/nearest_neighbor.rb +96 -0
  395. data/lib/kotoshu/models/onnx_model.rb +330 -0
  396. data/lib/kotoshu/models/semantic_error.rb +204 -0
  397. data/lib/kotoshu/models/suggestion.rb +106 -0
  398. data/lib/kotoshu/models/word_embedding.rb +97 -0
  399. data/lib/kotoshu/models.rb +27 -0
  400. data/lib/kotoshu/multi_language_checker.rb +127 -0
  401. data/lib/kotoshu/native.rb +83 -0
  402. data/lib/kotoshu/native_backend.rb +131 -0
  403. data/lib/kotoshu/paths.rb +79 -0
  404. data/lib/kotoshu/personal_dictionary.rb +105 -0
  405. data/lib/kotoshu/plugins/plugin.rb +61 -0
  406. data/lib/kotoshu/plugins/registry.rb +118 -0
  407. data/lib/kotoshu/plugins.rb +9 -0
  408. data/lib/kotoshu/project_config.rb +76 -0
  409. data/lib/kotoshu/readers/aff_data.rb +530 -0
  410. data/lib/kotoshu/readers/aff_reader.rb +393 -0
  411. data/lib/kotoshu/readers/condition_checker.rb +125 -0
  412. data/lib/kotoshu/readers/dic_reader.rb +208 -0
  413. data/lib/kotoshu/readers/file_reader.rb +377 -0
  414. data/lib/kotoshu/readers/lookup_builder.rb +584 -0
  415. data/lib/kotoshu/readers/readers.rb +17 -0
  416. data/lib/kotoshu/readers.rb +25 -0
  417. data/lib/kotoshu/resource_bundle.rb +55 -0
  418. data/lib/kotoshu/resource_manager.rb +600 -0
  419. data/lib/kotoshu/results/result.rb +165 -0
  420. data/lib/kotoshu/results.rb +8 -0
  421. data/lib/kotoshu/rspec.rb +163 -0
  422. data/lib/kotoshu/scripts/fasttext_to_onnx.py +275 -0
  423. data/lib/kotoshu/source_registry.rb +104 -0
  424. data/lib/kotoshu/spellchecker/parallel_checker.rb +90 -0
  425. data/lib/kotoshu/spellchecker.rb +406 -0
  426. data/lib/kotoshu/string_metrics.rb +153 -0
  427. data/lib/kotoshu/suggestions/context.rb +43 -0
  428. data/lib/kotoshu/suggestions/frequency_provider.rb +80 -0
  429. data/lib/kotoshu/suggestions/generator.rb +169 -0
  430. data/lib/kotoshu/suggestions/pipeline.rb +135 -0
  431. data/lib/kotoshu/suggestions/semantic_cascade.rb +73 -0
  432. data/lib/kotoshu/suggestions/strategies/base_strategy.rb +315 -0
  433. data/lib/kotoshu/suggestions/strategies/composite_strategy.rb +197 -0
  434. data/lib/kotoshu/suggestions/strategies/edit_distance_strategy.rb +631 -0
  435. data/lib/kotoshu/suggestions/strategies/keyboard_proximity_strategy.rb +207 -0
  436. data/lib/kotoshu/suggestions/strategies/ngram_strategy.rb +165 -0
  437. data/lib/kotoshu/suggestions/strategies/phonetic_strategy.rb +284 -0
  438. data/lib/kotoshu/suggestions/strategies/semantic_strategy.rb +317 -0
  439. data/lib/kotoshu/suggestions/strategies/symspell_strategy.rb +270 -0
  440. data/lib/kotoshu/suggestions/strategies/word_index.rb +78 -0
  441. data/lib/kotoshu/suggestions/suggestion.rb +154 -0
  442. data/lib/kotoshu/suggestions/suggestion_set.rb +270 -0
  443. data/lib/kotoshu/suggestions/sweep_index.rb +137 -0
  444. data/lib/kotoshu/suggestions.rb +29 -0
  445. data/lib/kotoshu/tasks/check_task.rb +104 -0
  446. data/lib/kotoshu/tasks.rb +11 -0
  447. data/lib/kotoshu/validators/spelling_validator.rb +101 -0
  448. data/lib/kotoshu/validators.rb +9 -0
  449. data/lib/kotoshu/version.rb +5 -0
  450. data/lib/kotoshu.rb +538 -0
  451. data/rakelib/compile.rake +10 -0
  452. data/script/validate_all_dictionaries.rb +444 -0
  453. data/scripts/build_native_gem.rb +45 -0
  454. data/scripts/extract_eval_grids.rb +37 -0
  455. data/scripts/generate_frozen_tiers.rb +44 -0
  456. data/sig/kotoshu.rbs +435 -0
  457. data/test_oop.rb +79 -0
  458. metadata +546 -0
data/sig/kotoshu.rbs ADDED
@@ -0,0 +1,435 @@
1
+ module Kotoshu
2
+ VERSION: String
3
+
4
+ module Keyboard
5
+ module Layouts
6
+ # Wave-1 national layouts (plan 84); grids mirrored from the
7
+ # models repo eval harness (eval/noise.py).
8
+ class TurkishQ < Layout
9
+ KEY_POSITIONS: Hash[String, [Integer, Integer]]
10
+ def initialize: () -> void
11
+ end
12
+
13
+ class Ukrainian < Layout
14
+ KEY_POSITIONS: Hash[String, [Integer, Integer]]
15
+ def initialize: () -> void
16
+ end
17
+
18
+ class GreekPhonetic < Layout
19
+ KEY_POSITIONS: Hash[String, [Integer, Integer]]
20
+ def initialize: () -> void
21
+ end
22
+
23
+ # Parameterized Latin layout family (plan 84): members declare a
24
+ # name, language codes, a qwerty/qwertz base grid and optional
25
+ # extra physical keys (the Nordic å/æ/ø, å/ä/ö).
26
+ class Latin < Layout
27
+ NOT_SET: Object
28
+
29
+ def self.layout_name: (String value) -> String
30
+ | () -> String?
31
+ def self.languages: (Array[String] value) -> Array[String]
32
+ | () -> Array[String]?
33
+ def self.base_grid: (Symbol value) -> Symbol
34
+ | () -> Symbol?
35
+ def self.removed_keys: (Array[String] value) -> Array[String]
36
+ | () -> Array[String]?
37
+ def self.extra_positions: (Hash[String, [Integer, Integer]] value) -> Hash[String, [Integer, Integer]]
38
+ | () -> Hash[String, [Integer, Integer]]?
39
+
40
+ def initialize: () -> void
41
+
42
+ class Italian < Latin
43
+ end
44
+ class Dutch < Latin
45
+ end
46
+ class Polish < Latin
47
+ end
48
+ class Czech < Latin
49
+ end
50
+ class Hungarian < Latin
51
+ end
52
+ class Romanian < Latin
53
+ end
54
+ class Catalan < Latin
55
+ end
56
+ class Vietnamese < Latin
57
+ end
58
+ class Danish < Latin
59
+ end
60
+ class Norwegian < Latin
61
+ end
62
+ class Swedish < Latin
63
+ end
64
+ end
65
+ end
66
+ end
67
+
68
+ module Language
69
+ module Tokenizer
70
+ # Script-aware tokenizers (plan 84).
71
+ class GreekTokenizer < Base
72
+ WORD_SEPARATORS: Regexp
73
+
74
+ def initialize: () -> void
75
+ def tokenize: (String? text) -> Array[String]
76
+ def word_boundary_regex: () -> Regexp
77
+ def spellcheck_word_regex: () -> Regexp
78
+ def spellcheck_word_regex: () -> Regexp
79
+ def skip_token?: (String token) -> bool
80
+ end
81
+
82
+ class CyrillicTokenizer < Base
83
+ WORD_SEPARATORS: Regexp
84
+
85
+ def initialize: () -> void
86
+ def tokenize: (String? text) -> Array[String]
87
+ def word_boundary_regex: () -> Regexp
88
+ def skip_token?: (String token) -> bool
89
+ end
90
+
91
+ # Regex-parameterized tokenizer for scripts without a dedicated
92
+ # class (plan 107 basic tier).
93
+ class ScriptTokenizer < Base
94
+ def initialize: (word_regex: Regexp) -> void
95
+ def tokenize: (String? text) -> Array[String]
96
+ def word_boundary_regex: () -> Regexp
97
+ def spellcheck_word_regex: () -> Regexp
98
+ end
99
+
100
+ # Korean eojeol tokenizer (plan 108): runs of Hangul syllables
101
+ # plus bare jamo that escaped IME composition.
102
+ class HangulTokenizer < Base
103
+ HANGUL_WORD_CHARS: String
104
+
105
+ def initialize: () -> void
106
+ def tokenize: (String? text) -> Array[String]
107
+ def word_boundary_regex: () -> Regexp
108
+ def spellcheck_word_regex: () -> Regexp
109
+ end
110
+
111
+ # Devanagari tokenizer (plan 108): matras and virama conjuncts
112
+ # stay attached to the base consonant.
113
+ class DevanagariTokenizer < Base
114
+ DEVANAGARI_WORD_CHARS: String
115
+
116
+ def initialize: () -> void
117
+ def tokenize: (String? text) -> Array[String]
118
+ def word_boundary_regex: () -> Regexp
119
+ def spellcheck_word_regex: () -> Regexp
120
+ end
121
+ end
122
+
123
+ # Script classification for module-less languages (plan 107):
124
+ # language code -> writing script -> script-appropriate tokenizer.
125
+ module Script
126
+ SCRIPT_BY_LANGUAGE: Hash[String, Symbol]
127
+ SCRIPT_WORD_REGEXES: Hash[Symbol, Regexp]
128
+
129
+ def self.script_for: (String? code) -> Symbol
130
+ def self.tokenizer_for: (String? code) -> Tokenizer::Base?
131
+ end
132
+
133
+ module Normalizer
134
+ # Greek-aware normalization (plan 84): final-sigma folding and
135
+ # opt-in accent stripping.
136
+ class Greek < Base
137
+ COMBINING_MARKS: Regexp
138
+
139
+ def initialize: () -> void
140
+ def normalize: (String? text, ?options ::Hash[Symbol, untyped]) -> String
141
+ def normalize_word: (String word) -> String
142
+ end
143
+
144
+ # Turkish case folding (plan 84): I -> ı, İ -> i.
145
+ class Turkish < Base
146
+ def initialize: () -> void
147
+ def normalize: (String? text, ?options ::Hash[Symbol, untyped]) -> String
148
+ end
149
+ end
150
+
151
+ # One language detection: top label code and its probability
152
+ # (plan 106). Plain-data Struct.
153
+ class Detection
154
+ attr_reader code: String?
155
+ attr_reader score: Float
156
+
157
+ def initialize: (?code: String?, ?score: Float) -> void
158
+ def to_s: () -> String
159
+ end
160
+
161
+ # Document language detection through the pure-Rust LID reader
162
+ # (plan 106): kotoshu://models/lid/lid-176 scored by the native
163
+ # extension, Language::Detector heuristic as the fallback.
164
+ class LidDetector
165
+ def self.detect: (String? text, ?config: Configuration) -> Detection
166
+ def self.available?: (?config: Configuration) -> bool
167
+ def self.setup: (?config: Configuration, ?force: bool) -> Hash[Symbol, untyped]
168
+ def self.setup?: (?config: Configuration) -> bool
169
+ def self.reset: () -> nil
170
+ end
171
+ end
172
+
173
+ module Languages
174
+ # Shared base for the thin wave-1 Latin modules (plan 84).
175
+ class LatinBase < Language::Base
176
+ def initialize: (?code: String code, ?name: String name, ?variant: String? variant) -> void
177
+ def tokenizer: () -> Language::Tokenizer::LatinTokenizer
178
+ def normalizer: () -> Language::Normalizer::Base
179
+ def dictionary_class: () -> Class
180
+ def script_type: () -> :latin
181
+ def create_tokenizer: () -> Language::Tokenizer::Base
182
+ def default_dictionary_paths: () -> Array[String]
183
+ end
184
+
185
+ class Catalan < LatinBase
186
+ end
187
+ class Czech < LatinBase
188
+ end
189
+ class Danish < LatinBase
190
+ end
191
+ class Greek < LatinBase
192
+ def tokenizer: () -> Language::Tokenizer::GreekTokenizer
193
+ def normalizer: () -> Language::Normalizer::Greek
194
+ def script_type: () -> :greek
195
+ end
196
+ class Hungarian < LatinBase
197
+ end
198
+ class Italian < LatinBase
199
+ end
200
+ class Dutch < LatinBase
201
+ end
202
+ class Polish < LatinBase
203
+ end
204
+ class Romanian < LatinBase
205
+ end
206
+ class Swedish < LatinBase
207
+ end
208
+ class Turkish < LatinBase
209
+ def normalizer: () -> Language::Normalizer::Turkish
210
+ end
211
+ class Ukrainian < LatinBase
212
+ def tokenizer: () -> Language::Tokenizer::CyrillicTokenizer
213
+ def script_type: () -> :cyrillic
214
+ end
215
+ class Vietnamese < LatinBase
216
+ end
217
+ # Batch-3 modules (plan 100): id hr sl sk et lt lv (Latin) and
218
+ # bg sr (Cyrillic).
219
+ class Bulgarian < LatinBase
220
+ def tokenizer: () -> Language::Tokenizer::CyrillicTokenizer
221
+ def script_type: () -> :cyrillic
222
+ end
223
+ class Croatian < LatinBase
224
+ end
225
+ class Estonian < LatinBase
226
+ end
227
+ class Indonesian < LatinBase
228
+ end
229
+ class Latvian < LatinBase
230
+ end
231
+ class Lithuanian < LatinBase
232
+ end
233
+ class Serbian < LatinBase
234
+ def tokenizer: () -> Language::Tokenizer::CyrillicTokenizer
235
+ def script_type: () -> :cyrillic
236
+ end
237
+ class Slovak < LatinBase
238
+ end
239
+ class Slovenian < LatinBase
240
+ end
241
+ # Norwegian Nynorsk (plan 107): dictionary + model staged, wired
242
+ # as full feature while basic support opened the manifest.
243
+ class NorwegianNynorsk < LatinBase
244
+ end
245
+ # Korean and Nepali (plan 108): the last big-population languages
246
+ # — Hangul eojeol tokenizer + Dubeolsik grid, Devanagari grapheme
247
+ # tokenizer + InScript grid.
248
+ class Korean < Language::Base
249
+ def tokenizer: () -> Language::Tokenizer::HangulTokenizer
250
+ def script_type: () -> :hangul
251
+ end
252
+ class Nepali < Language::Base
253
+ def tokenizer: () -> Language::Tokenizer::DevanagariTokenizer
254
+ def script_type: () -> :devanagari
255
+ end
256
+ end
257
+
258
+ module Cli
259
+ # .gitignore/.ignore glob-subset matcher (plan 88).
260
+ class IgnoreMatcher
261
+ IGNORE_FILENAMES: Array[String]
262
+
263
+ class Pattern
264
+ def initialize: (String line) -> void
265
+ attr_reader source (): String
266
+ attr_reader negated (): bool
267
+ attr_reader dir_only (): bool
268
+ attr_reader regex (): Regexp
269
+ def matches?: (String relative, ?directory: bool directory) -> bool
270
+ end
271
+
272
+ def self.load_directory: (String directory) -> IgnoreMatcher
273
+ def self.present_in?: (String directory) -> bool
274
+
275
+ def initialize: (Array[String] lines) -> void
276
+ def patterns: () -> Array[Pattern]
277
+ def ignored?: (String relative, ?directory: bool directory) -> bool
278
+ end
279
+
280
+ # Directory-tree file selection (plan 88).
281
+ class DirectoryWalker
282
+ TEXT_EXTENSIONS: Array[String]
283
+ DEFAULT_SKIP_DIRS: Array[String]
284
+
285
+ def initialize: (?include_globs: Array[String] include_globs, ?exclude_globs: Array[String] exclude_globs) -> void
286
+ def files: (String root) -> Array[String]
287
+ end
288
+
289
+ # Multi-target check runner (plan 88).
290
+ class DirectoryCheck
291
+ class FileOutcome < Struct[String path, Models::Result::DocumentResult result, Baseline::Store::Application? application]
292
+ end
293
+
294
+ attr_reader outcomes (): Array[FileOutcome]
295
+
296
+ def initialize: (Array[String] roots, check: untyped check, ?baseline_path: String? baseline_path,
297
+ ?include_globs: Array[String] include_globs, ?exclude_globs: Array[String] exclude_globs) -> void
298
+ def run: () -> Array[FileOutcome]
299
+ def file_count: () -> Integer
300
+ def error_count: () -> Integer
301
+ def word_count: () -> Integer
302
+ def failed?: () -> bool
303
+ def suppressed_count: () -> Integer
304
+ def stale_count: () -> Integer
305
+ end
306
+ end
307
+
308
+ module Validators
309
+ ACTIVE_MODEL_LOADED: bool
310
+
311
+ class ActiveModelUnavailable < Kotoshu::Error
312
+ def initialize: () -> void
313
+ end
314
+
315
+ class SpellingValidator
316
+ def initialize: (untyped options) -> void
317
+ def validate_each: (untyped record, untyped attribute, untyped value) -> void
318
+ end
319
+ end
320
+
321
+ module Rspec
322
+ module Matchers
323
+ def expect_words: (*String words) -> untyped
324
+ def expect_document: (String path) -> untyped
325
+ def all_be_spelled_correctly: () -> AllWordsSpelledCorrectlyMatcher
326
+ def be_spelled_correctly: (?in: (String | Symbol)? language) -> SpelledCorrectlyMatcher
327
+
328
+ class AllWordsSpelledCorrectlyMatcher
329
+ def matches?: (untyped words) -> bool
330
+ def failure_message: () -> String
331
+ def failure_message_when_negated: () -> String
332
+ def description: () -> String
333
+ end
334
+
335
+ class SpelledCorrectlyMatcher
336
+ def initialize: (?language: (String | Symbol)? language) -> void
337
+ def matches?: (untyped target) -> bool
338
+ def failure_message: () -> String
339
+ def failure_message_when_negated: () -> String
340
+ def description: () -> String
341
+ end
342
+ end
343
+ end
344
+
345
+ module Tasks
346
+ class CheckTask
347
+ include Rake::DSL
348
+
349
+ def initialize: (?Symbol name) ?{ (CheckTask task) -> void } -> void
350
+ attr_accessor name (): Symbol
351
+ attr_accessor files (): (untyped)?
352
+ attr_accessor root (): String
353
+ attr_accessor language (): (String | Symbol)?
354
+ attr_accessor fail_on_error (): bool
355
+ attr_accessor baseline_path (): (String)?
356
+ def target_files: () -> Array[String]
357
+ end
358
+ end
359
+
360
+ module Jekyll
361
+ JEKYLL_LOADED: bool
362
+
363
+ class JekyllUnavailable < Kotoshu::Error
364
+ def initialize: () -> void
365
+ end
366
+
367
+ class Generator
368
+ def self.safe: () -> bool
369
+ def self.priority: () -> Symbol
370
+ def generate: (untyped site) -> void
371
+ end
372
+ end
373
+
374
+ module Baseline
375
+ class Entry < Lutaml::Model::Serializable
376
+ def initialize: (?file: String?, ?line: Integer, ?word: String, ?count: Integer, **untyped kwargs) -> void
377
+ attr_reader file (): String?
378
+ attr_reader line (): Integer
379
+ attr_reader word (): String
380
+ attr_reader count (): Integer
381
+ def key: () -> [String, String]
382
+ end
383
+
384
+ class Store < Lutaml::Model::Serializable
385
+ DEFAULT_FILENAME: String
386
+ CURRENT_VERSION: Integer
387
+
388
+ def initialize: (?version: Integer, ?entries: Array[Entry], **untyped kwargs) -> void
389
+ attr_reader version (): Integer
390
+ attr_reader entries (): Array[Entry]
391
+
392
+ def self.load: (String path) -> Store
393
+ def self.from_checks: (Hash[String, Array[Models::Result::DocumentResult, String]] checks) -> Store
394
+ def self.canonical_entries: (Array[Entry] entries) -> Array[Entry]
395
+
396
+ def save: (String path) -> Store
397
+ def entries_for: (String file) -> Array[Entry]
398
+ def apply: (Models::Result::DocumentResult result, file: String file) -> Application
399
+ end
400
+
401
+ # Outcome of applying a Store to one check result (plain Struct).
402
+ class Application
403
+ def result: () -> Models::Result::DocumentResult
404
+ def suppressed_count: () -> Integer
405
+ def stale_count: () -> Integer
406
+ def initialize: (result: Models::Result::DocumentResult result, suppressed_count: Integer suppressed_count, stale_count: Integer stale_count) -> void
407
+ end
408
+ end
409
+
410
+ module Documents
411
+ module Suppressions
412
+ def self.scan: (?String? source, ?format: Symbol format) -> Array[Suppression]
413
+
414
+ class Suppression
415
+ KINDS: Array[Symbol]
416
+
417
+ def initialize: (kind: Symbol kind, directive_line: Integer directive_line, start_line: Integer start_line, end_line: Integer end_line, ?words: Array[String] words) -> void
418
+ attr_reader kind (): Symbol
419
+ attr_reader words (): Array[String]
420
+ attr_reader directive_line (): Integer
421
+ attr_reader start_line (): Integer
422
+ attr_reader end_line (): Integer
423
+
424
+ def file_block?: () -> bool
425
+ def covers_line?: (Integer line) -> bool
426
+ def word_scoped?: () -> bool
427
+ def applies_to?: (Integer line, ?word: String? word) -> bool
428
+ end
429
+
430
+ class Scanner
431
+ def self.scan: (?String? source, ?format: Symbol format) -> Array[Suppression]
432
+ end
433
+ end
434
+ end
435
+ end
data/test_oop.rb ADDED
@@ -0,0 +1,79 @@
1
+ # frozen_string_literal: true
2
+
3
+ require "bundler/setup"
4
+ require_relative "lib/kotoshu"
5
+
6
+ # Test IndexedDictionary
7
+ puts "=== Testing IndexedDictionary ==="
8
+ dict = Kotoshu::Core::IndexedDictionary.new(%w[hello world help held heap])
9
+ puts "Has 'hello': #{dict.has_word?('hello')}"
10
+ puts "Has 'HELLO' (ignorecase): #{dict.has_word_ignorecase?('HELLO')}"
11
+ puts "Words starting with 'he': #{dict.find_by_prefix('he').inspect}"
12
+ puts "Words ending with 'ld': #{dict.find_by_suffix('ld').inspect}"
13
+ puts "Words with length 5: #{dict.find_by_length(5).inspect}"
14
+ puts "Statistics: #{dict.statistics.inspect}"
15
+ puts
16
+
17
+ # Test Trie
18
+ puts "=== Testing Trie ==="
19
+ trie = Kotoshu::Core::Trie::Builder.from_array(%w[hello help held heap world])
20
+ puts "Has 'hello': #{trie.lookup('hello')}"
21
+ puts "Has prefix 'he': #{trie.has_prefix?('he')}"
22
+ puts "Words with prefix 'he': #{trie.words_with_prefix('he').inspect}"
23
+ puts "Suggestions for 'hel': #{trie.suggestions('hel').inspect}"
24
+ puts "All words: #{trie.all_words.inspect}"
25
+ puts
26
+
27
+ # Test Suggestion
28
+ puts "=== Testing Suggestion ==="
29
+ suggestion = Kotoshu::Suggestions::Suggestion.new(
30
+ word: "hello",
31
+ distance: 1,
32
+ confidence: 0.9,
33
+ source: :test
34
+ )
35
+ puts "High confidence: #{suggestion.high_confidence?}"
36
+ puts "Combined score: #{suggestion.combined_score}"
37
+ puts "Same word as 'HELLO': #{suggestion.same_word?('HELLO')}"
38
+ puts
39
+
40
+ # Test SuggestionSet
41
+ puts "=== Testing SuggestionSet ==="
42
+ suggestions = Kotoshu::Suggestions::SuggestionSet.from_words(
43
+ %w[hello help held],
44
+ source: :test
45
+ )
46
+ puts "Size: #{suggestions.size}"
47
+ puts "First: #{suggestions.first.inspect}"
48
+ puts "Has word 'help': #{suggestions.has_word?('help')}"
49
+ puts "Top 2: #{suggestions.top(2).map(&:word).inspect}"
50
+ puts
51
+
52
+ # Test Context
53
+ puts "=== Testing Context ==="
54
+ context = Kotoshu::Suggestions::Context.new(
55
+ word: "helo",
56
+ dictionary: dict,
57
+ max_results: 5
58
+ )
59
+ puts "Word: #{context.word}"
60
+ puts "Max results: #{context.max_results}"
61
+ puts
62
+
63
+ # Test EditDistanceStrategy
64
+ puts "=== Testing EditDistanceStrategy ==="
65
+ strategy = Kotoshu::Suggestions::Strategies::EditDistanceStrategy.new
66
+ result = strategy.generate(context)
67
+ puts "Suggestions for 'helo': #{result.to_words.inspect}"
68
+ puts
69
+
70
+ # Test CompositeStrategy (Pipeline)
71
+ puts "=== Testing CompositeStrategy ==="
72
+ pipeline = Kotoshu.suggestion_pipeline(
73
+ Kotoshu::Suggestions::Strategies::EditDistanceStrategy.new
74
+ )
75
+ result = pipeline.generate(context)
76
+ puts "Pipeline suggestions: #{result.to_words.inspect}"
77
+ puts
78
+
79
+ puts "All tests passed!"