kotoshu 1.0.2-aarch64-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.
- checksums.yaml +7 -0
- data/.kotoshu-baseline.json +1 -0
- data/.pre-commit-hooks.yaml +18 -0
- data/.rspec +3 -0
- data/.rubocop.yml +351 -0
- data/.yardopts +8 -0
- data/CHANGELOG.md +813 -0
- data/CLAUDE.md +176 -0
- data/CODE_OF_CONDUCT.md +132 -0
- data/Cargo.lock +359 -0
- data/Cargo.toml +15 -0
- data/LICENSE +31 -0
- data/README.adoc +1292 -0
- data/Rakefile +150 -0
- data/SECURITY.md +93 -0
- data/TODO.impl/00-cut-0.1.md +121 -0
- data/TODO.impl/00-cut-0.2.md +175 -0
- data/TODO.impl/00-vision.md +281 -0
- data/TODO.impl/01-hunspell-correctness.md +111 -0
- data/TODO.impl/02-cli-unification.md +74 -0
- data/TODO.impl/03-dynamic-download.md +107 -0
- data/TODO.impl/04-language-modules.md +89 -0
- data/TODO.impl/05-semantic-path.md +83 -0
- data/TODO.impl/06-cjk-support.md +105 -0
- data/TODO.impl/07-rtl-support.md +71 -0
- data/TODO.impl/08-grammar-engine.md +106 -0
- data/TODO.impl/09-integrity-security.md +90 -0
- data/TODO.impl/10-testing-ci.md +98 -0
- data/TODO.impl/100-full-feature-batch3.md +28 -0
- data/TODO.impl/101-int4-tier-experiment.md +32 -0
- data/TODO.impl/102-lid-chain.md +28 -0
- data/TODO.impl/103-oov-bucket-tables.md +27 -0
- data/TODO.impl/104-vscode-marketplace-readiness.md +32 -0
- data/TODO.impl/105-personal-dictionary-in-check.md +34 -0
- data/TODO.impl/106-native-lid-detection.md +36 -0
- data/TODO.impl/107-basic-support-every-staged-language.md +42 -0
- data/TODO.impl/108-ko-ne-full-feature.md +37 -0
- data/TODO.impl/109-ten-audit.md +26 -0
- data/TODO.impl/11-release-v1.md +95 -0
- data/TODO.impl/110-sr-latn-and-polish.md +33 -0
- data/TODO.impl/111-embedding-bakeoff.md +33 -0
- data/TODO.impl/112-deployability-and-gating.md +26 -0
- data/TODO.impl/113-language-packs.md +26 -0
- data/TODO.impl/114-typo-biencoder-thread.md +33 -0
- data/TODO.impl/115-hybrid-retrieval-pricing.md +22 -0
- data/TODO.impl/116-baseline-suggestion-skip.md +81 -0
- data/TODO.impl/117-deterministic-frequency-tiers.md +110 -0
- data/TODO.impl/118-server-gem-floor.md +33 -0
- data/TODO.impl/119-embedded-kelly-tiers.md +56 -0
- data/TODO.impl/120-setup-metadata-refresh.md +35 -0
- data/TODO.impl/121-jekyll-baseline-skip.md +33 -0
- data/TODO.impl/122-pack-compression-kpk2.md +66 -0
- data/TODO.impl/123-typo-corpus-synthesis.md +55 -0
- data/TODO.impl/124-owner-residue.md +19 -0
- data/TODO.impl/125-consumer-floor-guards.md +43 -0
- data/TODO.impl/126-tier-error-budgets.md +33 -0
- data/TODO.impl/127-suggestion-feedback-loop.md +34 -0
- data/TODO.impl/128-hybrid-pricing-verdict.md +47 -0
- data/TODO.impl/129-pt-fr-corpora.md +23 -0
- data/TODO.impl/130-news-truth-0912.md +23 -0
- data/TODO.impl/131-hybrid-productization.md +42 -0
- data/TODO.impl/132-techniques-page-and-prose.md +27 -0
- data/TODO.impl/133-rust-first-distribution.md +68 -0
- data/TODO.impl/20-encapsulation-cleanup.md +47 -0
- data/TODO.impl/21-autoload-migration.md +64 -0
- data/TODO.impl/22-url-pin-single-source-of-truth.md +120 -0
- data/TODO.impl/23-fix-url-defaults.md +57 -0
- data/TODO.impl/24-cli-auto-setup-prompt.md +76 -0
- data/TODO.impl/25-soft-onnxruntime-require.md +75 -0
- data/TODO.impl/26-onnx-vocab-json-generation.md +96 -0
- data/TODO.impl/27-end-to-end-smoke-spec.md +113 -0
- data/TODO.impl/28-readme-quickstart-verification.md +68 -0
- data/TODO.impl/29-status-command.md +84 -0
- data/TODO.impl/30-language-auto-detection.md +74 -0
- data/TODO.impl/31-download-progress.md +58 -0
- data/TODO.impl/32-sarif-output-verification.md +72 -0
- data/TODO.impl/33-audit-log-rotation.md +54 -0
- data/TODO.impl/34-cache-eviction.md +59 -0
- data/TODO.impl/35-shell-completion.md +61 -0
- data/TODO.impl/36-cleanup-regressions-0.3.1.md +134 -0
- data/TODO.impl/37-hunspell-correctness-tier2.md +203 -0
- data/TODO.impl/38-onnx-semantic-gating.md +218 -0
- data/TODO.impl/39-tier3-and-beyond.md +232 -0
- data/TODO.impl/40-spec-drift-cleanup.md +134 -0
- data/TODO.impl/50-structure-aware-document-api.md +194 -0
- data/TODO.impl/51-grammar-engine-expansion.md +75 -0
- data/TODO.impl/52-multi-language-documents.md +95 -0
- data/TODO.impl/53-document-plugin-architecture.md +94 -0
- data/TODO.impl/54-cjk-support.md +117 -0
- data/TODO.impl/55-rtl-support.md +109 -0
- data/TODO.impl/56-t4-t5-t6-quality-architecture-ecosystem.md +126 -0
- data/TODO.impl/57-t5.1-step3-pure-function-strategies.md +138 -0
- data/TODO.impl/58-t5.2-configuration-as-data.md +113 -0
- data/TODO.impl/59-yard-api-documentation.md +75 -0
- data/TODO.impl/60-lsp-server.md +174 -0
- data/TODO.impl/61-editor-ecosystem.md +167 -0
- data/TODO.impl/62-framework-integrations.md +159 -0
- data/TODO.impl/63-web-playground-wasm.md +186 -0
- data/TODO.impl/64-http-api-and-sdks.md +191 -0
- data/TODO.impl/65-universal-kotoshu.md +251 -0
- data/TODO.impl/66-kotoshu-core.md +169 -0
- data/TODO.impl/67-kotoshu-rs-and-access-libraries.md +137 -0
- data/TODO.impl/68-sota-adoption.md +152 -0
- data/TODO.impl/69-sota-typo-eval.md +74 -0
- data/TODO.impl/70-sota-confidence-cascade.md +59 -0
- data/TODO.impl/71-sota-nested-model.md +63 -0
- data/TODO.impl/72-model2vec-evaluation.md +49 -0
- data/TODO.impl/73-rl-reranker.md +42 -0
- data/TODO.impl/74-distilled-reranker.md +36 -0
- data/TODO.impl/75-llm-evaluator.md +35 -0
- data/TODO.impl/76-optional-llm-backend.md +37 -0
- data/TODO.impl/77-model-coverage-expansion.md +96 -0
- data/TODO.impl/78-in-browser-playground.md +69 -0
- data/TODO.impl/79-news-and-releases.md +60 -0
- data/TODO.impl/80-ecosystem-docs.md +56 -0
- data/TODO.impl/81-editor-reach.md +68 -0
- data/TODO.impl/82-doc-formats-and-ignores.md +81 -0
- data/TODO.impl/83-models-batch-2.md +56 -0
- data/TODO.impl/84-language-modules-wave2.md +75 -0
- data/TODO.impl/85-wasm-model-api.md +48 -0
- data/TODO.impl/86-site-truth-wave2.md +45 -0
- data/TODO.impl/87-lsp-personal-dictionary.md +36 -0
- data/TODO.impl/88-cli-directory-mode.md +54 -0
- data/TODO.impl/89-framework-integrations-exec.md +59 -0
- data/TODO.impl/90-gem-correctness-residues.md +44 -0
- data/TODO.impl/91-unicode-and-sv-aff.md +47 -0
- data/TODO.impl/92-tier-mirror-cors.md +88 -0
- data/TODO.impl/93-python-wheels.md +32 -0
- data/TODO.impl/94-site-integrations-docs.md +35 -0
- data/TODO.impl/95-editor-action-polish.md +27 -0
- data/TODO.impl/96-server-semantic-models.md +50 -0
- data/TODO.impl/97-yard-execution.md +73 -0
- data/TODO.impl/98-campaign-cleanup.md +78 -0
- data/TODO.impl/99-site-truth-performance-docs.md +31 -0
- data/conformance/vectors.jsonl +2630 -0
- data/data/en/grammar/rules.yaml +851 -0
- data/docs/STABILITY-1.0-AUDIT.md +251 -0
- data/docs/STABILITY-1.0.md +137 -0
- data/docs/cache-architecture.md +502 -0
- data/docs/verification-evidence/correct3/pr_body.md +37 -0
- data/docs/verification-evidence/correct3/rspec_final.log +5588 -0
- data/docs/verification-evidence/correct3/rspec_full.log +4504 -0
- data/docs/verification-evidence/correct3/sv.aff +856 -0
- data/docs/verification-evidence/correct3/sv.dic +153717 -0
- data/examples/01_basic_word_checking.rb +38 -0
- data/examples/02_text_document_checking.rb +77 -0
- data/examples/03_dictionary_backends.rb +137 -0
- data/examples/04_trie_data_structure.rb +146 -0
- data/examples/05_suggestion_algorithms.rb +239 -0
- data/examples/06_configuration_advanced.rb +287 -0
- data/examples/07_multi_language_dictionaries.rb +278 -0
- data/exe/kotoshu +6 -0
- data/lib/kotoshu/algorithms/capitalization.rb +276 -0
- data/lib/kotoshu/algorithms/edit_distance.rb +128 -0
- data/lib/kotoshu/algorithms/lookup/affix_form.rb +132 -0
- data/lib/kotoshu/algorithms/lookup/compound_checks.rb +209 -0
- data/lib/kotoshu/algorithms/lookup/compound_form.rb +50 -0
- data/lib/kotoshu/algorithms/lookup.rb +841 -0
- data/lib/kotoshu/algorithms/ngram_suggest.rb +367 -0
- data/lib/kotoshu/algorithms/permutations.rb +283 -0
- data/lib/kotoshu/algorithms/phonet_suggest.rb +162 -0
- data/lib/kotoshu/algorithms/soundex.rb +92 -0
- data/lib/kotoshu/algorithms/suggest.rb +794 -0
- data/lib/kotoshu/algorithms.rb +23 -0
- data/lib/kotoshu/analyzers/semantic_analyzer.rb +405 -0
- data/lib/kotoshu/analyzers.rb +8 -0
- data/lib/kotoshu/baseline/application.rb +18 -0
- data/lib/kotoshu/baseline/entry.rb +33 -0
- data/lib/kotoshu/baseline/store.rb +175 -0
- data/lib/kotoshu/baseline.rb +20 -0
- data/lib/kotoshu/cache/base_cache.rb +778 -0
- data/lib/kotoshu/cache/cache.rb +91 -0
- data/lib/kotoshu/cache/eviction_policy.rb +66 -0
- data/lib/kotoshu/cache/frequency_cache.rb +283 -0
- data/lib/kotoshu/cache/language_cache.rb +511 -0
- data/lib/kotoshu/cache/lookup_cache.rb +166 -0
- data/lib/kotoshu/cache/model_cache.rb +1147 -0
- data/lib/kotoshu/cache/model_registry.rb +109 -0
- data/lib/kotoshu/cache/staged_languages.rb +45 -0
- data/lib/kotoshu/cache/suggestion_cache.rb +113 -0
- data/lib/kotoshu/cache.rb +49 -0
- data/lib/kotoshu/cli/auto_setup.rb +71 -0
- data/lib/kotoshu/cli/baseline_command.rb +119 -0
- data/lib/kotoshu/cli/batch_reporter.rb +321 -0
- data/lib/kotoshu/cli/cache_command.rb +282 -0
- data/lib/kotoshu/cli/completions_command.rb +210 -0
- data/lib/kotoshu/cli/dict_command.rb +64 -0
- data/lib/kotoshu/cli/directory_check.rb +146 -0
- data/lib/kotoshu/cli/directory_walker.rb +132 -0
- data/lib/kotoshu/cli/display_formatter.rb +429 -0
- data/lib/kotoshu/cli/errors.rb +36 -0
- data/lib/kotoshu/cli/ignore_matcher.rb +205 -0
- data/lib/kotoshu/cli/interactive_reviewer.rb +314 -0
- data/lib/kotoshu/cli/language_resolver.rb +91 -0
- data/lib/kotoshu/cli/navigation_manager.rb +273 -0
- data/lib/kotoshu/cli/personal_command.rb +113 -0
- data/lib/kotoshu/cli/progress_reporter.rb +114 -0
- data/lib/kotoshu/cli/status_report.rb +130 -0
- data/lib/kotoshu/cli.rb +880 -0
- data/lib/kotoshu/components/passthrough_spell_checker.rb +70 -0
- data/lib/kotoshu/components/pos_tagger.rb +98 -0
- data/lib/kotoshu/components/spell_checker.rb +73 -0
- data/lib/kotoshu/components/synthesizer.rb +60 -0
- data/lib/kotoshu/components/tokenizer.rb +58 -0
- data/lib/kotoshu/components/whitespace_tokenizer.rb +94 -0
- data/lib/kotoshu/components.rb +13 -0
- data/lib/kotoshu/configuration/builder.rb +207 -0
- data/lib/kotoshu/configuration/resolver.rb +124 -0
- data/lib/kotoshu/configuration.rb +829 -0
- data/lib/kotoshu/conformance_exporter.rb +256 -0
- data/lib/kotoshu/conformance_runner.rb +176 -0
- data/lib/kotoshu/core/exceptions.rb +186 -0
- data/lib/kotoshu/core/indexed_dictionary.rb +293 -0
- data/lib/kotoshu/core/models/affix_rule.rb +262 -0
- data/lib/kotoshu/core/models/result/document_result.rb +132 -0
- data/lib/kotoshu/core/models/result/word_result.rb +131 -0
- data/lib/kotoshu/core/models/word.rb +131 -0
- data/lib/kotoshu/core/trie/builder.rb +119 -0
- data/lib/kotoshu/core/trie/node.rb +94 -0
- data/lib/kotoshu/core/trie/trie.rb +249 -0
- data/lib/kotoshu/core.rb +28 -0
- data/lib/kotoshu/data/common_words/de.yml +1800 -0
- data/lib/kotoshu/data/common_words/en.yml +1215 -0
- data/lib/kotoshu/data/common_words/es.yml +750 -0
- data/lib/kotoshu/data/common_words/fr.yml +1015 -0
- data/lib/kotoshu/data/common_words/pt.yml +870 -0
- data/lib/kotoshu/data/common_words/ru.yml +484 -0
- data/lib/kotoshu/data/common_words_loader.rb +141 -0
- data/lib/kotoshu/data/frozen_kelly/en.json +1154 -0
- data/lib/kotoshu/data/frozen_kelly.rb +38 -0
- data/lib/kotoshu/data.rb +8 -0
- data/lib/kotoshu/data_structures/bloom_filter.rb +188 -0
- data/lib/kotoshu/data_structures.rb +8 -0
- data/lib/kotoshu/debug_logger.rb +146 -0
- data/lib/kotoshu/debug_mode.rb +136 -0
- data/lib/kotoshu/defaults.rb +84 -0
- data/lib/kotoshu/dictionaries/catalog.rb +814 -0
- data/lib/kotoshu/dictionaries.rb +8 -0
- data/lib/kotoshu/dictionary/base.rb +324 -0
- data/lib/kotoshu/dictionary/cspell.rb +243 -0
- data/lib/kotoshu/dictionary/custom.rb +225 -0
- data/lib/kotoshu/dictionary/hunspell.rb +520 -0
- data/lib/kotoshu/dictionary/plain_text.rb +302 -0
- data/lib/kotoshu/dictionary/repository.rb +246 -0
- data/lib/kotoshu/dictionary/unified.rb +236 -0
- data/lib/kotoshu/dictionary/unix_words.rb +218 -0
- data/lib/kotoshu/dictionary.rb +15 -0
- data/lib/kotoshu/documents/document.rb +120 -0
- data/lib/kotoshu/documents/plain_text_document.rb +73 -0
- data/lib/kotoshu/documents/source_position.rb +45 -0
- data/lib/kotoshu/documents/source_range.rb +76 -0
- data/lib/kotoshu/documents/suppressions/scanner.rb +149 -0
- data/lib/kotoshu/documents/suppressions/suppression.rb +75 -0
- data/lib/kotoshu/documents/suppressions.rb +44 -0
- data/lib/kotoshu/documents/text_node.rb +49 -0
- data/lib/kotoshu/documents.rb +178 -0
- data/lib/kotoshu/embeddings/embedding_pipeline.rb +238 -0
- data/lib/kotoshu/embeddings/lru_cache.rb +244 -0
- data/lib/kotoshu/embeddings/onnx_runtime_model.rb +411 -0
- data/lib/kotoshu/embeddings/protocol.rb +96 -0
- data/lib/kotoshu/embeddings/protocols.rb +23 -0
- data/lib/kotoshu/embeddings/registry.rb +184 -0
- data/lib/kotoshu/embeddings/search.rb +204 -0
- data/lib/kotoshu/embeddings/similarity_engine.rb +278 -0
- data/lib/kotoshu/embeddings/similarity_search.rb +328 -0
- data/lib/kotoshu/embeddings/vocabulary.rb +306 -0
- data/lib/kotoshu/embeddings.rb +87 -0
- data/lib/kotoshu/fluent_checker.rb +94 -0
- data/lib/kotoshu/grammar/pattern_matchers/base_matcher.rb +48 -0
- data/lib/kotoshu/grammar/pattern_matchers/double_negative_matcher.rb +179 -0
- data/lib/kotoshu/grammar/pattern_matchers/phrase_matcher.rb +86 -0
- data/lib/kotoshu/grammar/pattern_matchers/possessive_context_matcher.rb +75 -0
- data/lib/kotoshu/grammar/pattern_matchers/possessive_contraction_matcher.rb +87 -0
- data/lib/kotoshu/grammar/pattern_matchers/sentence_start_matcher.rb +84 -0
- data/lib/kotoshu/grammar/pattern_matchers/vowel_sound_matcher.rb +81 -0
- data/lib/kotoshu/grammar/pattern_matchers/word_list_matcher.rb +66 -0
- data/lib/kotoshu/grammar/rule.rb +99 -0
- data/lib/kotoshu/grammar/rule_engine.rb +96 -0
- data/lib/kotoshu/grammar/rule_loader.rb +30 -0
- data/lib/kotoshu/grammar.rb +24 -0
- data/lib/kotoshu/integrity/audit_log.rb +167 -0
- data/lib/kotoshu/integrity/manifest.rb +116 -0
- data/lib/kotoshu/integrity/net_http.rb +51 -0
- data/lib/kotoshu/integrity/rotation_policy.rb +88 -0
- data/lib/kotoshu/integrity.rb +26 -0
- data/lib/kotoshu/jekyll.rb +101 -0
- data/lib/kotoshu/keyboard/layout.rb +116 -0
- data/lib/kotoshu/keyboard/layouts/arabic.rb +59 -0
- data/lib/kotoshu/keyboard/layouts/azerty.rb +55 -0
- data/lib/kotoshu/keyboard/layouts/bulgarian.rb +57 -0
- data/lib/kotoshu/keyboard/layouts/devanagari_inscript.rb +52 -0
- data/lib/kotoshu/keyboard/layouts/dubeolsik.rb +56 -0
- data/lib/kotoshu/keyboard/layouts/dvorak.rb +54 -0
- data/lib/kotoshu/keyboard/layouts/greek.rb +52 -0
- data/lib/kotoshu/keyboard/layouts/hebrew.rb +57 -0
- data/lib/kotoshu/keyboard/layouts/hrsl.rb +94 -0
- data/lib/kotoshu/keyboard/layouts/jcuken.rb +57 -0
- data/lib/kotoshu/keyboard/layouts/latin.rb +266 -0
- data/lib/kotoshu/keyboard/layouts/persian.rb +58 -0
- data/lib/kotoshu/keyboard/layouts/qwerty.rb +52 -0
- data/lib/kotoshu/keyboard/layouts/qwertz.rb +55 -0
- data/lib/kotoshu/keyboard/layouts/serbian.rb +59 -0
- data/lib/kotoshu/keyboard/layouts/turkish_q.rb +52 -0
- data/lib/kotoshu/keyboard/layouts/ukrainian.rb +51 -0
- data/lib/kotoshu/keyboard/registry.rb +201 -0
- data/lib/kotoshu/keyboard.rb +96 -0
- data/lib/kotoshu/kotoshu_native.so +0 -0
- data/lib/kotoshu/language/detector.rb +242 -0
- data/lib/kotoshu/language/identifier.rb +376 -0
- data/lib/kotoshu/language/languages/base.rb +271 -0
- data/lib/kotoshu/language/lid_detector.rb +188 -0
- data/lib/kotoshu/language/normalizer/arabic.rb +113 -0
- data/lib/kotoshu/language/normalizer/base.rb +133 -0
- data/lib/kotoshu/language/normalizer/greek.rb +63 -0
- data/lib/kotoshu/language/normalizer/hebrew.rb +72 -0
- data/lib/kotoshu/language/normalizer/persian.rb +36 -0
- data/lib/kotoshu/language/normalizer/turkish.rb +38 -0
- data/lib/kotoshu/language/registry.rb +209 -0
- data/lib/kotoshu/language/resources/ar/common_words.txt +6753 -0
- data/lib/kotoshu/language/resources/ar/confusion_sets.txt +11 -0
- data/lib/kotoshu/language/resources/de/common_words.txt +10003 -0
- data/lib/kotoshu/language/resources/de/confusion_sets.txt +246 -0
- data/lib/kotoshu/language/resources/en/common_words.txt +9979 -0
- data/lib/kotoshu/language/resources/en/confusion_sets.txt +871 -0
- data/lib/kotoshu/language/resources/es/common_words.txt +9992 -0
- data/lib/kotoshu/language/resources/es/confusion_sets.txt +17 -0
- data/lib/kotoshu/language/resources/fr/common_words.txt +9993 -0
- data/lib/kotoshu/language/resources/fr/confusion_sets.txt +76 -0
- data/lib/kotoshu/language/resources/pt/common_words.txt +9977 -0
- data/lib/kotoshu/language/resources/pt/confusion_sets.txt +18 -0
- data/lib/kotoshu/language/resources/ru/common_words.txt +9951 -0
- data/lib/kotoshu/language/resources/ru/confusion_sets.txt +5 -0
- data/lib/kotoshu/language/script.rb +128 -0
- data/lib/kotoshu/language/segmenter.rb +122 -0
- data/lib/kotoshu/language/suika.rb +38 -0
- data/lib/kotoshu/language/tokenizer/base.rb +187 -0
- data/lib/kotoshu/language/tokenizer/cyrillic_tokenizer.rb +76 -0
- data/lib/kotoshu/language/tokenizer/devanagari_tokenizer.rb +70 -0
- data/lib/kotoshu/language/tokenizer/french_tokenizer.rb +172 -0
- data/lib/kotoshu/language/tokenizer/german_tokenizer.rb +41 -0
- data/lib/kotoshu/language/tokenizer/greek_tokenizer.rb +72 -0
- data/lib/kotoshu/language/tokenizer/hangul_tokenizer.rb +70 -0
- data/lib/kotoshu/language/tokenizer/japanese_tokenizer.rb +55 -0
- data/lib/kotoshu/language/tokenizer/latin_tokenizer.rb +153 -0
- data/lib/kotoshu/language/tokenizer/portuguese_tokenizer.rb +160 -0
- data/lib/kotoshu/language/tokenizer/russian_tokenizer.rb +93 -0
- data/lib/kotoshu/language/tokenizer/script_tokenizer.rb +62 -0
- data/lib/kotoshu/language/tokenizer/spanish_tokenizer.rb +122 -0
- data/lib/kotoshu/language.rb +127 -0
- data/lib/kotoshu/languages/ar/language.rb +98 -0
- data/lib/kotoshu/languages/bg/language.rb +37 -0
- data/lib/kotoshu/languages/ca/language.rb +22 -0
- data/lib/kotoshu/languages/cs/language.rb +22 -0
- data/lib/kotoshu/languages/da/language.rb +22 -0
- data/lib/kotoshu/languages/de/language.rb +554 -0
- data/lib/kotoshu/languages/el/language.rb +50 -0
- data/lib/kotoshu/languages/en/language.rb +470 -0
- data/lib/kotoshu/languages/es/language.rb +476 -0
- data/lib/kotoshu/languages/et/language.rb +24 -0
- data/lib/kotoshu/languages/fa/language.rb +91 -0
- data/lib/kotoshu/languages/fr/language.rb +505 -0
- data/lib/kotoshu/languages/he/language.rb +98 -0
- data/lib/kotoshu/languages/hr/language.rb +24 -0
- data/lib/kotoshu/languages/hu/language.rb +22 -0
- data/lib/kotoshu/languages/id/language.rb +25 -0
- data/lib/kotoshu/languages/it/language.rb +22 -0
- data/lib/kotoshu/languages/ja/language.rb +476 -0
- data/lib/kotoshu/languages/ko/language.rb +56 -0
- data/lib/kotoshu/languages/latin_base.rb +53 -0
- data/lib/kotoshu/languages/lt/language.rb +24 -0
- data/lib/kotoshu/languages/lv/language.rb +24 -0
- data/lib/kotoshu/languages/nb/language.rb +25 -0
- data/lib/kotoshu/languages/ne/language.rb +60 -0
- data/lib/kotoshu/languages/nl/language.rb +22 -0
- data/lib/kotoshu/languages/nn/language.rb +26 -0
- data/lib/kotoshu/languages/pl/language.rb +22 -0
- data/lib/kotoshu/languages/pt/language.rb +439 -0
- data/lib/kotoshu/languages/ro/language.rb +22 -0
- data/lib/kotoshu/languages/ru/language.rb +420 -0
- data/lib/kotoshu/languages/sk/language.rb +25 -0
- data/lib/kotoshu/languages/sl/language.rb +25 -0
- data/lib/kotoshu/languages/sr/language.rb +39 -0
- data/lib/kotoshu/languages/sr-Latn/language.rb +35 -0
- data/lib/kotoshu/languages/sv/language.rb +22 -0
- data/lib/kotoshu/languages/tr/language.rb +36 -0
- data/lib/kotoshu/languages/uk/language.rb +38 -0
- data/lib/kotoshu/languages/vi/language.rb +22 -0
- data/lib/kotoshu/languages.rb +64 -0
- data/lib/kotoshu/metrics_collector.rb +238 -0
- data/lib/kotoshu/metrics_module.rb +121 -0
- data/lib/kotoshu/models/context.rb +119 -0
- data/lib/kotoshu/models/embedding_model.rb +181 -0
- data/lib/kotoshu/models/fasttext_model.rb +212 -0
- data/lib/kotoshu/models/nearest_neighbor.rb +96 -0
- data/lib/kotoshu/models/onnx_model.rb +330 -0
- data/lib/kotoshu/models/semantic_error.rb +204 -0
- data/lib/kotoshu/models/suggestion.rb +106 -0
- data/lib/kotoshu/models/word_embedding.rb +97 -0
- data/lib/kotoshu/models.rb +27 -0
- data/lib/kotoshu/multi_language_checker.rb +127 -0
- data/lib/kotoshu/native.rb +83 -0
- data/lib/kotoshu/native_backend.rb +131 -0
- data/lib/kotoshu/paths.rb +79 -0
- data/lib/kotoshu/personal_dictionary.rb +105 -0
- data/lib/kotoshu/plugins/plugin.rb +61 -0
- data/lib/kotoshu/plugins/registry.rb +118 -0
- data/lib/kotoshu/plugins.rb +9 -0
- data/lib/kotoshu/project_config.rb +76 -0
- data/lib/kotoshu/readers/aff_data.rb +530 -0
- data/lib/kotoshu/readers/aff_reader.rb +393 -0
- data/lib/kotoshu/readers/condition_checker.rb +125 -0
- data/lib/kotoshu/readers/dic_reader.rb +208 -0
- data/lib/kotoshu/readers/file_reader.rb +377 -0
- data/lib/kotoshu/readers/lookup_builder.rb +584 -0
- data/lib/kotoshu/readers/readers.rb +17 -0
- data/lib/kotoshu/readers.rb +25 -0
- data/lib/kotoshu/resource_bundle.rb +55 -0
- data/lib/kotoshu/resource_manager.rb +600 -0
- data/lib/kotoshu/results/result.rb +165 -0
- data/lib/kotoshu/results.rb +8 -0
- data/lib/kotoshu/rspec.rb +163 -0
- data/lib/kotoshu/scripts/fasttext_to_onnx.py +275 -0
- data/lib/kotoshu/source_registry.rb +104 -0
- data/lib/kotoshu/spellchecker/parallel_checker.rb +90 -0
- data/lib/kotoshu/spellchecker.rb +406 -0
- data/lib/kotoshu/string_metrics.rb +153 -0
- data/lib/kotoshu/suggestions/context.rb +43 -0
- data/lib/kotoshu/suggestions/frequency_provider.rb +80 -0
- data/lib/kotoshu/suggestions/generator.rb +169 -0
- data/lib/kotoshu/suggestions/pipeline.rb +135 -0
- data/lib/kotoshu/suggestions/semantic_cascade.rb +73 -0
- data/lib/kotoshu/suggestions/strategies/base_strategy.rb +315 -0
- data/lib/kotoshu/suggestions/strategies/composite_strategy.rb +197 -0
- data/lib/kotoshu/suggestions/strategies/edit_distance_strategy.rb +631 -0
- data/lib/kotoshu/suggestions/strategies/keyboard_proximity_strategy.rb +207 -0
- data/lib/kotoshu/suggestions/strategies/ngram_strategy.rb +165 -0
- data/lib/kotoshu/suggestions/strategies/phonetic_strategy.rb +284 -0
- data/lib/kotoshu/suggestions/strategies/semantic_strategy.rb +317 -0
- data/lib/kotoshu/suggestions/strategies/symspell_strategy.rb +270 -0
- data/lib/kotoshu/suggestions/strategies/word_index.rb +78 -0
- data/lib/kotoshu/suggestions/suggestion.rb +154 -0
- data/lib/kotoshu/suggestions/suggestion_set.rb +270 -0
- data/lib/kotoshu/suggestions/sweep_index.rb +137 -0
- data/lib/kotoshu/suggestions.rb +29 -0
- data/lib/kotoshu/tasks/check_task.rb +104 -0
- data/lib/kotoshu/tasks.rb +11 -0
- data/lib/kotoshu/validators/spelling_validator.rb +101 -0
- data/lib/kotoshu/validators.rb +9 -0
- data/lib/kotoshu/version.rb +5 -0
- data/lib/kotoshu.rb +538 -0
- data/rakelib/compile.rake +10 -0
- data/script/validate_all_dictionaries.rb +444 -0
- data/scripts/build_native_gem.rb +45 -0
- data/scripts/extract_eval_grids.rb +37 -0
- data/scripts/generate_frozen_tiers.rb +44 -0
- data/sig/kotoshu.rbs +435 -0
- data/test_oop.rb +79 -0
- metadata +546 -0
|
@@ -0,0 +1,444 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
# frozen_string_literal: true
|
|
3
|
+
|
|
4
|
+
# Dictionary Validation Script
|
|
5
|
+
#
|
|
6
|
+
# This script validates all dictionaries in the kotoshu/dictionaries catalog
|
|
7
|
+
# by loading them from GitHub and testing basic functionality.
|
|
8
|
+
#
|
|
9
|
+
# Usage:
|
|
10
|
+
# ruby script/validate_all_dictionaries.rb [--full] [--lang LANG] [--code CODE]
|
|
11
|
+
#
|
|
12
|
+
# Options:
|
|
13
|
+
# --full Run full validation including suggestion tests (slow)
|
|
14
|
+
# --lang LANG Only test dictionaries for this language (e.g., en, de, fr)
|
|
15
|
+
# --code CODE Only test this specific dictionary code (e.g., en-GB, de-AT)
|
|
16
|
+
# --format FMT Only test dictionaries with this format (hunspell, plain_text)
|
|
17
|
+
|
|
18
|
+
require_relative "../lib/kotoshu"
|
|
19
|
+
require "optparse"
|
|
20
|
+
require "benchmark"
|
|
21
|
+
require "json"
|
|
22
|
+
|
|
23
|
+
# ANSI color codes for terminal output
|
|
24
|
+
module Colors
|
|
25
|
+
RESET = "\e[0m"
|
|
26
|
+
RED = "\e[31m"
|
|
27
|
+
GREEN = "\e[32m"
|
|
28
|
+
YELLOW = "\e[33m"
|
|
29
|
+
BLUE = "\e[34m"
|
|
30
|
+
MAGENTA = "\e[35m"
|
|
31
|
+
CYAN = "\e[36m"
|
|
32
|
+
BOLD = "\e[1m"
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
# Validation result for a single dictionary
|
|
36
|
+
class ValidationResult
|
|
37
|
+
attr_reader :code, :status, :load_time, :size, :test_results, :error
|
|
38
|
+
|
|
39
|
+
def initialize(code)
|
|
40
|
+
@code = code
|
|
41
|
+
@status = :pending # :pending, :success, :warning, :error
|
|
42
|
+
@load_time = nil
|
|
43
|
+
@size = nil
|
|
44
|
+
@test_results = {}
|
|
45
|
+
@error = nil
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def success!(load_time, size)
|
|
49
|
+
@status = :success
|
|
50
|
+
@load_time = load_time
|
|
51
|
+
@size = size
|
|
52
|
+
end
|
|
53
|
+
|
|
54
|
+
def warning!(load_time, size, message)
|
|
55
|
+
@status = :warning
|
|
56
|
+
@load_time = load_time
|
|
57
|
+
@size = size
|
|
58
|
+
@test_results[:warning] = message
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
def error!(error)
|
|
62
|
+
@status = :error
|
|
63
|
+
@error = error
|
|
64
|
+
end
|
|
65
|
+
|
|
66
|
+
def add_test_result(name, passed, details = nil)
|
|
67
|
+
@test_results[name] = { passed: passed, details: details }
|
|
68
|
+
end
|
|
69
|
+
|
|
70
|
+
def success?
|
|
71
|
+
@status == :success
|
|
72
|
+
end
|
|
73
|
+
|
|
74
|
+
def error?
|
|
75
|
+
@status == :error
|
|
76
|
+
end
|
|
77
|
+
|
|
78
|
+
def warning?
|
|
79
|
+
@status == :warning
|
|
80
|
+
end
|
|
81
|
+
|
|
82
|
+
def to_h
|
|
83
|
+
{
|
|
84
|
+
code: @code,
|
|
85
|
+
status: @status,
|
|
86
|
+
load_time: @load_time,
|
|
87
|
+
size: @size,
|
|
88
|
+
test_results: @test_results,
|
|
89
|
+
error: @error&.message
|
|
90
|
+
}
|
|
91
|
+
end
|
|
92
|
+
end
|
|
93
|
+
|
|
94
|
+
# Main validator class
|
|
95
|
+
class DictionaryValidator
|
|
96
|
+
attr_reader :options, :results
|
|
97
|
+
|
|
98
|
+
def initialize(options = {})
|
|
99
|
+
@options = options
|
|
100
|
+
@results = []
|
|
101
|
+
@catalog = Kotoshu::Dictionaries::Catalog
|
|
102
|
+
end
|
|
103
|
+
|
|
104
|
+
# Run validation
|
|
105
|
+
def run
|
|
106
|
+
print_header
|
|
107
|
+
|
|
108
|
+
dictionaries = select_dictionaries
|
|
109
|
+
|
|
110
|
+
print "Validating #{dictionaries.size} dictionaries...\n\n"
|
|
111
|
+
|
|
112
|
+
dictionaries.each_with_index do |entry, index|
|
|
113
|
+
validate_dictionary(entry, index + 1, dictionaries.size)
|
|
114
|
+
end
|
|
115
|
+
|
|
116
|
+
print_summary
|
|
117
|
+
|
|
118
|
+
write_report if @options[:report]
|
|
119
|
+
|
|
120
|
+
exit_with_code
|
|
121
|
+
end
|
|
122
|
+
|
|
123
|
+
private
|
|
124
|
+
|
|
125
|
+
def select_dictionaries
|
|
126
|
+
dicts = @catalog.all
|
|
127
|
+
|
|
128
|
+
dicts = dicts.select { |d| d.language == @options[:lang] } if @options[:lang]
|
|
129
|
+
dicts = [dicts.find { |d| d.code.casecmp(@options[:code]).zero? }].compact if @options[:code]
|
|
130
|
+
dicts = dicts.select { |d| d.format == @options[:format].to_sym } if @options[:format]
|
|
131
|
+
|
|
132
|
+
dicts
|
|
133
|
+
end
|
|
134
|
+
|
|
135
|
+
def validate_dictionary(entry, index, total)
|
|
136
|
+
result = ValidationResult.new(entry.code)
|
|
137
|
+
|
|
138
|
+
print_status(entry, index, total, result)
|
|
139
|
+
|
|
140
|
+
begin
|
|
141
|
+
# Load dictionary with timing
|
|
142
|
+
dict = nil
|
|
143
|
+
load_time = Benchmark.realtime do
|
|
144
|
+
dict = entry.load
|
|
145
|
+
end
|
|
146
|
+
|
|
147
|
+
# Basic validation
|
|
148
|
+
size = dict.size
|
|
149
|
+
|
|
150
|
+
if size.zero?
|
|
151
|
+
result.warning!(load_time, size, "Dictionary has zero words")
|
|
152
|
+
elsif size < 100
|
|
153
|
+
result.warning!(load_time, size, "Dictionary has fewer than 100 words")
|
|
154
|
+
else
|
|
155
|
+
result.success!(load_time, size)
|
|
156
|
+
end
|
|
157
|
+
|
|
158
|
+
# Run tests if --full
|
|
159
|
+
run_full_tests(dict, entry, result) if @options[:full] && result.success?
|
|
160
|
+
rescue StandardError => e
|
|
161
|
+
result.error!(e)
|
|
162
|
+
end
|
|
163
|
+
|
|
164
|
+
@results << result
|
|
165
|
+
print_result(entry, result)
|
|
166
|
+
end
|
|
167
|
+
|
|
168
|
+
def run_full_tests(dict, entry, result)
|
|
169
|
+
# Test 1: Lookup basic word (varies by language)
|
|
170
|
+
test_word = basic_test_word(entry.language)
|
|
171
|
+
if dict.lookup?(test_word)
|
|
172
|
+
result.add_test_result(:basic_lookup, true, test_word)
|
|
173
|
+
else
|
|
174
|
+
result.add_test_result(:basic_lookup, false, "Could not find '#{test_word}'")
|
|
175
|
+
end
|
|
176
|
+
|
|
177
|
+
# Test 2: Lookup non-existent word
|
|
178
|
+
nonsense_word = nonsense_test_word(entry.language)
|
|
179
|
+
if !dict.lookup?(nonsense_word)
|
|
180
|
+
result.add_test_result(:nonexistent_lookup, true, nonsense_word)
|
|
181
|
+
else
|
|
182
|
+
result.add_test_result(:nonexistent_lookup, false, "Incorrectly found '#{nonsense_word}'")
|
|
183
|
+
end
|
|
184
|
+
|
|
185
|
+
# Test 3: Suggestions (if supported)
|
|
186
|
+
begin
|
|
187
|
+
misspelled = misspelled_test_word(entry.language)
|
|
188
|
+
suggestions = dict.suggest(misspelled, max_suggestions: 5)
|
|
189
|
+
if suggestions&.any?
|
|
190
|
+
result.add_test_result(:suggestions, true, "Found #{suggestions.size} suggestions for '#{misspelled}'")
|
|
191
|
+
else
|
|
192
|
+
result.add_test_result(:suggestions, false, "No suggestions for '#{misspelled}'")
|
|
193
|
+
end
|
|
194
|
+
rescue StandardError => e
|
|
195
|
+
result.add_test_result(:suggestions, false, e.message)
|
|
196
|
+
end
|
|
197
|
+
|
|
198
|
+
# Test 4: Case sensitivity (if not case-sensitive)
|
|
199
|
+
return if dict.case_sensitive?
|
|
200
|
+
|
|
201
|
+
if dict.lookup?(test_word.upcase) || dict.lookup?(test_word.downcase)
|
|
202
|
+
result.add_test_result(:case_insensitive, true, "Case-insensitive lookup works")
|
|
203
|
+
else
|
|
204
|
+
result.add_test_result(:case_insensitive, false, "Case-insensitive lookup failed")
|
|
205
|
+
end
|
|
206
|
+
end
|
|
207
|
+
|
|
208
|
+
def basic_test_word(language)
|
|
209
|
+
# Common words in different languages
|
|
210
|
+
{
|
|
211
|
+
"en" => "the",
|
|
212
|
+
"de" => "der",
|
|
213
|
+
"es" => "el",
|
|
214
|
+
"fr" => "le",
|
|
215
|
+
"it" => "il",
|
|
216
|
+
"pt" => "o",
|
|
217
|
+
"ru" => "и",
|
|
218
|
+
"nl" => "de",
|
|
219
|
+
"pl" => "i",
|
|
220
|
+
"cs" => "a",
|
|
221
|
+
"sv" => "och",
|
|
222
|
+
"da" => "og",
|
|
223
|
+
"no" => "og",
|
|
224
|
+
"fi" => "ja",
|
|
225
|
+
"tr" => "ve",
|
|
226
|
+
"ko" => "그",
|
|
227
|
+
"vi" => "là",
|
|
228
|
+
"ja" => "は",
|
|
229
|
+
"zh" => "的",
|
|
230
|
+
"ar" => "في",
|
|
231
|
+
"he" => "ו",
|
|
232
|
+
"el" => "το",
|
|
233
|
+
"hu" => "a",
|
|
234
|
+
"ro" => "şi",
|
|
235
|
+
"bg" => "и",
|
|
236
|
+
"uk" => "і",
|
|
237
|
+
"ga" => "an",
|
|
238
|
+
"cy" => "y",
|
|
239
|
+
"is" => "og",
|
|
240
|
+
"mt" => "u",
|
|
241
|
+
"lv" => "un",
|
|
242
|
+
"et" => "ja",
|
|
243
|
+
"lt" => "ir",
|
|
244
|
+
"sk" => "a",
|
|
245
|
+
"sl" => "in",
|
|
246
|
+
"hr" => "i",
|
|
247
|
+
"sr" => "и",
|
|
248
|
+
"sq" => "dhe",
|
|
249
|
+
"be" => "і",
|
|
250
|
+
"mk" => "и",
|
|
251
|
+
"hy" => "և",
|
|
252
|
+
"ka" => "და",
|
|
253
|
+
"fa" => "و",
|
|
254
|
+
"ur" => "اور",
|
|
255
|
+
"hi" => "और",
|
|
256
|
+
"bn" => "এবং",
|
|
257
|
+
"th" => "และ",
|
|
258
|
+
"id" => "dan",
|
|
259
|
+
"ms" => "dan",
|
|
260
|
+
"sw" => "na",
|
|
261
|
+
"af" => "en",
|
|
262
|
+
"ca" => "i",
|
|
263
|
+
"gl" => "e",
|
|
264
|
+
"eu" => "eta",
|
|
265
|
+
"lb" => "an",
|
|
266
|
+
"fy" => "en",
|
|
267
|
+
"ku" => "û",
|
|
268
|
+
"eo" => "kaj",
|
|
269
|
+
"ia" => "e"
|
|
270
|
+
}.fetch(language, "a")
|
|
271
|
+
end
|
|
272
|
+
|
|
273
|
+
def nonsense_test_word(_language)
|
|
274
|
+
# Nonsense words that shouldn't exist
|
|
275
|
+
"zzzzzzzzz"
|
|
276
|
+
end
|
|
277
|
+
|
|
278
|
+
def misspelled_test_word(language)
|
|
279
|
+
# Common misspellings in different languages
|
|
280
|
+
{
|
|
281
|
+
"en" => "helo",
|
|
282
|
+
"de" => "hallo",
|
|
283
|
+
"es" => "ola",
|
|
284
|
+
"fr" => "bonjur",
|
|
285
|
+
"it" => "ciao",
|
|
286
|
+
"pt" => "ola",
|
|
287
|
+
"ru" => "привет",
|
|
288
|
+
"nl" => "halo",
|
|
289
|
+
"pl" => "czesc"
|
|
290
|
+
}.fetch(language, "teest")
|
|
291
|
+
end
|
|
292
|
+
|
|
293
|
+
def print_header
|
|
294
|
+
print "#{Colors::BOLD}Kotoshu Dictionary Validator#{Colors::RESET}\n"
|
|
295
|
+
print "#{"=" * 60}\n\n"
|
|
296
|
+
|
|
297
|
+
stats = @catalog.statistics
|
|
298
|
+
print "Catalog Statistics:\n"
|
|
299
|
+
print " Total dictionaries: #{stats[:total]}\n"
|
|
300
|
+
print " Hunspell dictionaries: #{stats[:hunspell]}\n"
|
|
301
|
+
print " Plain text dictionaries: #{stats[:plain_text]}\n"
|
|
302
|
+
print " Languages: #{stats[:languages]}\n"
|
|
303
|
+
print " Total words: #{stats[:total_words].round}\n"
|
|
304
|
+
print "\n"
|
|
305
|
+
print "#{"=" * 60}\n\n"
|
|
306
|
+
end
|
|
307
|
+
|
|
308
|
+
def print_status(entry, index, total, _result)
|
|
309
|
+
print "[#{index}/#{total}] #{Colors::CYAN}#{entry.code}#{Colors::RESET} - #{entry.description}\n"
|
|
310
|
+
print " Format: #{entry.format}, License: #{entry.license}\n"
|
|
311
|
+
end
|
|
312
|
+
|
|
313
|
+
def print_result(_entry, result)
|
|
314
|
+
if result.success?
|
|
315
|
+
print " #{Colors::GREEN}✓ PASS#{Colors::RESET}"
|
|
316
|
+
print " - #{result.size.round} words, #{(result.load_time * 1000).round(1)}ms"
|
|
317
|
+
print " - Tests: #{result.test_results.size}" if @options[:full]
|
|
318
|
+
elsif result.warning?
|
|
319
|
+
print " #{Colors::YELLOW}⚠ WARN#{Colors::RESET}"
|
|
320
|
+
print " - #{result.size.round} words, #{(result.load_time * 1000).round(1)}ms"
|
|
321
|
+
print " - #{result.test_results[:warning]}"
|
|
322
|
+
else
|
|
323
|
+
print " #{Colors::RED}✗ FAIL#{Colors::RESET}"
|
|
324
|
+
print " - #{result.error.class}: #{result.error.message}"
|
|
325
|
+
end
|
|
326
|
+
print "\n"
|
|
327
|
+
|
|
328
|
+
# Print test results details
|
|
329
|
+
if @options[:full] && result.test_results.any?
|
|
330
|
+
result.test_results.each do |name, test_result|
|
|
331
|
+
next if name == :warning
|
|
332
|
+
|
|
333
|
+
status = test_result[:passed] ? "#{Colors::GREEN}✓#{Colors::RESET}" : "#{Colors::RED}✗#{Colors::RESET}"
|
|
334
|
+
print " #{status} #{name}: #{test_result[:details]}\n"
|
|
335
|
+
end
|
|
336
|
+
end
|
|
337
|
+
|
|
338
|
+
print "\n"
|
|
339
|
+
end
|
|
340
|
+
|
|
341
|
+
def print_summary
|
|
342
|
+
print "#{"=" * 60}\n"
|
|
343
|
+
print "#{Colors::BOLD}Validation Summary#{Colors::RESET}\n"
|
|
344
|
+
print "#{"=" * 60}\n\n"
|
|
345
|
+
|
|
346
|
+
total = @results.size
|
|
347
|
+
success = @results.count(&:success?)
|
|
348
|
+
warnings = @results.count(&:warning?)
|
|
349
|
+
errors = @results.count(&:error?)
|
|
350
|
+
|
|
351
|
+
print "Total: #{total}\n"
|
|
352
|
+
print "#{Colors::GREEN}✓ Passed: #{success}#{Colors::RESET}\n"
|
|
353
|
+
print "#{Colors::YELLOW}⚠ Warnings: #{warnings}#{Colors::RESET}\n"
|
|
354
|
+
print "#{Colors::RED}✗ Failed: #{errors}#{Colors::RESET}\n"
|
|
355
|
+
print "\n"
|
|
356
|
+
|
|
357
|
+
if success.positive?
|
|
358
|
+
avg_load_time = @results.select(&:success?).map(&:load_time).sum / success
|
|
359
|
+
avg_size = @results.select(&:success?).map(&:size).sum / success
|
|
360
|
+
print "Average load time: #{(avg_load_time * 1000).round(1)}ms\n"
|
|
361
|
+
print "Average size: #{avg_size.round} words\n"
|
|
362
|
+
print "\n"
|
|
363
|
+
end
|
|
364
|
+
|
|
365
|
+
if errors.positive?
|
|
366
|
+
print "#{Colors::BOLD}Failed Dictionaries:#{Colors::RESET}\n"
|
|
367
|
+
@results.select(&:error?).each do |result|
|
|
368
|
+
print " #{Colors::RED}#{result.code}#{Colors::RESET}: #{result.error.message}\n"
|
|
369
|
+
end
|
|
370
|
+
print "\n"
|
|
371
|
+
end
|
|
372
|
+
|
|
373
|
+
return unless warnings.positive?
|
|
374
|
+
|
|
375
|
+
print "#{Colors::BOLD}Warnings:#{Colors::RESET}\n"
|
|
376
|
+
@results.select(&:warning?).each do |result|
|
|
377
|
+
print " #{Colors::YELLOW}#{result.code}#{Colors::RESET}: #{result.test_results[:warning]}\n"
|
|
378
|
+
end
|
|
379
|
+
print "\n"
|
|
380
|
+
end
|
|
381
|
+
|
|
382
|
+
def write_report
|
|
383
|
+
report_path = "dictionary_validation_report.json"
|
|
384
|
+
File.write(report_path, JSON.pretty_generate({
|
|
385
|
+
timestamp: Time.now.iso8601,
|
|
386
|
+
summary: {
|
|
387
|
+
total: @results.size,
|
|
388
|
+
success: @results.count(&:success?),
|
|
389
|
+
warnings: @results.count(&:warning?),
|
|
390
|
+
errors: @results.count(&:error?)
|
|
391
|
+
},
|
|
392
|
+
results: @results.map(&:to_h)
|
|
393
|
+
}))
|
|
394
|
+
print "Report written to: #{report_path}\n"
|
|
395
|
+
end
|
|
396
|
+
|
|
397
|
+
def exit_with_code
|
|
398
|
+
# Exit with error code if any failures
|
|
399
|
+
exit 1 if @results.any?(&:error?)
|
|
400
|
+
exit 0
|
|
401
|
+
end
|
|
402
|
+
end
|
|
403
|
+
|
|
404
|
+
# Parse options
|
|
405
|
+
options = {
|
|
406
|
+
full: false,
|
|
407
|
+
lang: nil,
|
|
408
|
+
code: nil,
|
|
409
|
+
format: nil,
|
|
410
|
+
report: false
|
|
411
|
+
}
|
|
412
|
+
|
|
413
|
+
OptionParser.new do |opts|
|
|
414
|
+
opts.banner = "Usage: ruby script/validate_all_dictionaries.rb [options]"
|
|
415
|
+
|
|
416
|
+
opts.on("--full", "Run full validation including tests") do
|
|
417
|
+
options[:full] = true
|
|
418
|
+
end
|
|
419
|
+
|
|
420
|
+
opts.on("--lang LANG", "Filter by language (e.g., en, de, fr)") do |lang|
|
|
421
|
+
options[:lang] = lang
|
|
422
|
+
end
|
|
423
|
+
|
|
424
|
+
opts.on("--code CODE", "Filter by dictionary code (e.g., en-GB)") do |code|
|
|
425
|
+
options[:code] = code
|
|
426
|
+
end
|
|
427
|
+
|
|
428
|
+
opts.on("--format FORMAT", "Filter by format (hunspell, plain_text)") do |fmt|
|
|
429
|
+
options[:format] = fmt
|
|
430
|
+
end
|
|
431
|
+
|
|
432
|
+
opts.on("--report", "Write JSON report file") do
|
|
433
|
+
options[:report] = true
|
|
434
|
+
end
|
|
435
|
+
|
|
436
|
+
opts.on("-h", "--help", "Show this message") do
|
|
437
|
+
puts opts
|
|
438
|
+
exit
|
|
439
|
+
end
|
|
440
|
+
end.parse!
|
|
441
|
+
|
|
442
|
+
# Run validator
|
|
443
|
+
validator = DictionaryValidator.new(options)
|
|
444
|
+
validator.run
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
# frozen_string_literal: true
|
|
3
|
+
|
|
4
|
+
# Build a precompiled platform gem (plan 133): assemble kotoshu's
|
|
5
|
+
# gemspec around the ALREADY-COMPILED extension binary, exactly the
|
|
6
|
+
# surgery rb_sys's cross-compiling blocks perform — the rb_sys build
|
|
7
|
+
# dependency goes away (nothing builds at install), the Rust sources,
|
|
8
|
+
# Cargo files, and extconf drop out of the file list, and the platform
|
|
9
|
+
# tag makes RubyGems resolve this gem on matching platforms while the
|
|
10
|
+
# pure-Ruby gem keeps serving everything else.
|
|
11
|
+
#
|
|
12
|
+
# Usage: ruby scripts/build_native_gem.rb [platform]
|
|
13
|
+
# platform defaults to Gem::Platform.local; pass e.g. x86_64-linux
|
|
14
|
+
# when the binary was produced for another host. The compiled
|
|
15
|
+
# extension must already sit at lib/kotoshu/kotoshu_native.<dlext>
|
|
16
|
+
# (rake compile on the matching platform).
|
|
17
|
+
|
|
18
|
+
require "rubygems/package"
|
|
19
|
+
require "rbconfig"
|
|
20
|
+
|
|
21
|
+
platform = ARGV[0]
|
|
22
|
+
dlext = RbConfig::CONFIG["DLEXT"]
|
|
23
|
+
binary = File.join("lib", "kotoshu", "kotoshu_native.#{dlext}")
|
|
24
|
+
|
|
25
|
+
unless File.exist?(binary)
|
|
26
|
+
abort "missing #{binary} — run `rake compile` on the target platform first"
|
|
27
|
+
end
|
|
28
|
+
|
|
29
|
+
spec = Gem::Specification.load("kotoshu.gemspec")
|
|
30
|
+
spec.platform = platform ? Gem::Platform.new(platform) : Gem::Platform.local
|
|
31
|
+
# The darwin deployment-target suffix (-23, -25, ...) differs per build
|
|
32
|
+
# machine; RubyGems matches a versionless darwin tag on any macOS of
|
|
33
|
+
# the same CPU, so normalize it off (the convention shipped binary
|
|
34
|
+
# gems use). Linux and mingw tags carry no version to begin with.
|
|
35
|
+
if spec.platform.os == "darwin" && spec.platform.version
|
|
36
|
+
spec.platform = Gem::Platform.new("#{spec.platform.cpu}-darwin")
|
|
37
|
+
end
|
|
38
|
+
spec.files += [binary]
|
|
39
|
+
spec.extensions = []
|
|
40
|
+
spec.dependencies.reject! { |d| d.name == "rb_sys" }
|
|
41
|
+
spec.files.reject! { |f| f.start_with?("ext/") }
|
|
42
|
+
|
|
43
|
+
path = Gem::Package.build(spec)
|
|
44
|
+
puts "built #{path}"
|
|
45
|
+
path
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
# One-off generator for spec/fixtures/models_eval_grids.json.
|
|
4
|
+
# Not part of the gem or the suite; kept next to the fixture it makes.
|
|
5
|
+
#
|
|
6
|
+
# Reads the models repo eval noise.py and extracts the tr/uk/el key
|
|
7
|
+
# grids into the JSON fixture used by the drift-check spec.
|
|
8
|
+
#
|
|
9
|
+
# Usage: ruby scripts/extract_eval_grids.rb PATH_TO_NOISE_PY
|
|
10
|
+
|
|
11
|
+
require "json"
|
|
12
|
+
|
|
13
|
+
source = ARGV[0]
|
|
14
|
+
abort "usage: ruby #{__FILE__} PATH_TO_models-fasttext-onnx/eval/noise.py" unless source
|
|
15
|
+
abort "noise.py not found: #{source}" unless File.exist?(source)
|
|
16
|
+
|
|
17
|
+
src = File.read(source)
|
|
18
|
+
grids = {}
|
|
19
|
+
%w[
|
|
20
|
+
_TR_Q _UK_JCUKEN _EL_PHONETIC _AR_101 _FA_STD _HE_SI1452 _BG_BDS
|
|
21
|
+
_SR_CYR _HRSL _NE_INSCRIPT
|
|
22
|
+
].each do |name|
|
|
23
|
+
body = src[/^#{name} = \{(.*?)^\}/m, 1]
|
|
24
|
+
abort "grid #{name} not found in #{source}" unless body
|
|
25
|
+
grid = {}
|
|
26
|
+
body.scan(/"((?:[^"\\]|\\.)*)"\s*:\s*\((\d+),\s*(\d+)\)/) do |key, row, col|
|
|
27
|
+
key = key.gsub('\\"', '"').gsub("\\\\", "\\")
|
|
28
|
+
grid[key] = [Integer(row), Integer(col)]
|
|
29
|
+
end
|
|
30
|
+
abort "grid #{name} empty" if grid.empty?
|
|
31
|
+
|
|
32
|
+
grids[name] = grid
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
out = File.expand_path("../spec/fixtures/models_eval_grids.json", __dir__)
|
|
36
|
+
File.write(out, JSON.pretty_generate({ "source" => source, "grids" => grids }) + "\n")
|
|
37
|
+
puts "wrote #{out}: #{grids.map { |k, v| "#{k}=#{v.size}" }.join(' ')}"
|
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
# Generates lib/kotoshu/data/frozen_kelly.rb from the Rust engine's
|
|
4
|
+
# frozen tier tables (kotoshu-rs kotoshu/src/suggest/frequency_data.rs)
|
|
5
|
+
# so both engines carry byte-identical frequency data for `en`
|
|
6
|
+
# (plan 119). The rs tables are themselves frozen from the Kelly
|
|
7
|
+
# en.json sha256 97535823f41aa3f0… — this script preserves that
|
|
8
|
+
# provenance rather than re-deriving from the raw Kelly data.
|
|
9
|
+
#
|
|
10
|
+
# Usage: ruby scripts/generate_frozen_tiers.rb <path-to-frequency_data.rs>
|
|
11
|
+
#
|
|
12
|
+
# The generator is deterministic: same input file, same output bytes.
|
|
13
|
+
|
|
14
|
+
require "json"
|
|
15
|
+
|
|
16
|
+
SRC = ARGV[0]
|
|
17
|
+
abort "usage: #{$PROGRAM_NAME} <kotoshu-rs frequency_data.rs>" unless SRC
|
|
18
|
+
abort "not found: #{SRC}" unless File.exist?(SRC)
|
|
19
|
+
|
|
20
|
+
def parse_tier(source, name)
|
|
21
|
+
match = source.match(/pub const #{name}: &\[&str\] = &\[(.*?)\];/m)
|
|
22
|
+
abort "tier #{name} not found in #{SRC}" unless match
|
|
23
|
+
|
|
24
|
+
match[1].scan(/"([^"]+)"/).flatten
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
source = File.read(SRC)
|
|
28
|
+
tiers = { "top_50" => parse_tier(source, "TOP_50"),
|
|
29
|
+
"top_200" => parse_tier(source, "TOP_200"),
|
|
30
|
+
"top_1000" => parse_tier(source, "TOP_1000") }
|
|
31
|
+
abort "unparsed" if tiers.values.any?(&:empty?)
|
|
32
|
+
|
|
33
|
+
data = {
|
|
34
|
+
"provenance" => {
|
|
35
|
+
"source" => "kotoshu-rs kotoshu/src/suggest/frequency_data.rs",
|
|
36
|
+
"upstream" => "kotoshu/frequency-list-kelly data/en.json",
|
|
37
|
+
"upstream_sha256" => "97535823f41aa3f06c2087dfc162aec0a591412b8b95c0594fcbb2cea79b0e61"
|
|
38
|
+
},
|
|
39
|
+
"tiers" => tiers.transform_keys(&:downcase)
|
|
40
|
+
}
|
|
41
|
+
|
|
42
|
+
dest = File.expand_path("../lib/kotoshu/data/frozen_kelly/en.json", __dir__)
|
|
43
|
+
File.write(dest, JSON.pretty_generate(data) + "\n")
|
|
44
|
+
puts "wrote #{dest}: #{tiers.map { |k, v| "#{k}=#{v.size}" }.join(' ')}"
|