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.
- 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 +1,470 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Languages
|
|
5
|
+
# English language implementation.
|
|
6
|
+
#
|
|
7
|
+
# Supports multiple dialects: en-US, en-GB, en-AU, en-CA, en-NZ, en-ZA
|
|
8
|
+
#
|
|
9
|
+
# @example American English
|
|
10
|
+
# lang = Kotoshu::Languages::English.new(code: "en-US")
|
|
11
|
+
# checker = lang.create_spell_checker
|
|
12
|
+
# checker.correct?("color") # => true
|
|
13
|
+
# checker.correct?("colour") # => false
|
|
14
|
+
#
|
|
15
|
+
# @example British English
|
|
16
|
+
# lang = Kotoshu::Languages::English.new(code: "en-GB")
|
|
17
|
+
# checker.correct?("colour") # => true
|
|
18
|
+
class English < Language::Base
|
|
19
|
+
# English spell checker.
|
|
20
|
+
#
|
|
21
|
+
# Uses the Lookup algorithm with Hunspell-format dictionaries.
|
|
22
|
+
class SpellChecker < Components::SpellChecker
|
|
23
|
+
attr_reader :aff_path, :dic_path, :script
|
|
24
|
+
|
|
25
|
+
def initialize(aff_path:, dic_path:, script: :latin, encoding: 'ISO-8859-1')
|
|
26
|
+
@aff_path = aff_path
|
|
27
|
+
@dic_path = dic_path
|
|
28
|
+
@script = script
|
|
29
|
+
@encoding = encoding
|
|
30
|
+
@lookuper = Readers::LookupBuilder.new(aff_path, dic_path, encoding: encoding, script: script).build
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
def check(word)
|
|
34
|
+
return { found: false, stem: nil, flags: [] } if word.nil? || word.empty?
|
|
35
|
+
|
|
36
|
+
first_form = @lookuper.good_forms(word).first
|
|
37
|
+
if first_form
|
|
38
|
+
{ found: true, stem: first_form.stem || word, flags: first_form.flags&.to_a || [] }
|
|
39
|
+
else
|
|
40
|
+
{ found: false, stem: nil, flags: [] }
|
|
41
|
+
end
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
def suggest(word, max_suggestions: 10)
|
|
45
|
+
return [] if word.nil? || word.empty?
|
|
46
|
+
|
|
47
|
+
first_form = @lookuper.good_forms(word).first
|
|
48
|
+
return [] if first_form
|
|
49
|
+
|
|
50
|
+
generate_suggestions(word, max_suggestions).take(max_suggestions)
|
|
51
|
+
end
|
|
52
|
+
|
|
53
|
+
def correct?(word)
|
|
54
|
+
check(word)[:found]
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
def lookuper
|
|
58
|
+
@lookuper
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
private
|
|
62
|
+
|
|
63
|
+
def calculate_distance(a, b)
|
|
64
|
+
return a.length if b.empty?
|
|
65
|
+
return b.length if a.empty?
|
|
66
|
+
|
|
67
|
+
matrix = Array.new(a.length + 1) { |i| [i] + ([0] * b.length) }
|
|
68
|
+
(1..b.length).each { |j| matrix[0][j] = j }
|
|
69
|
+
(1..a.length).each do |i|
|
|
70
|
+
(1..b.length).each do |j|
|
|
71
|
+
cost = a[i - 1] == b[j - 1] ? 0 : 1
|
|
72
|
+
matrix[i][j] = [matrix[i - 1][j] + 1, matrix[i][j - 1] + 1, matrix[i - 1][j - 1] + cost].min
|
|
73
|
+
end
|
|
74
|
+
end
|
|
75
|
+
matrix[a.length][b.length]
|
|
76
|
+
end
|
|
77
|
+
|
|
78
|
+
def calculate_score(original, suggestion, rank)
|
|
79
|
+
distance = calculate_distance(original, suggestion)
|
|
80
|
+
max_len = [original.length, suggestion.length].max
|
|
81
|
+
distance_score = 1.0 - (distance.to_f / max_len)
|
|
82
|
+
rank_penalty = rank * 0.05
|
|
83
|
+
[distance_score - rank_penalty, 0.0].max
|
|
84
|
+
end
|
|
85
|
+
|
|
86
|
+
def generate_suggestions(word, _max_suggestions)
|
|
87
|
+
variations = []
|
|
88
|
+
word.chars.each_with_index do |char, i|
|
|
89
|
+
next if i == 0
|
|
90
|
+
|
|
91
|
+
doubled = word.dup
|
|
92
|
+
doubled.insert(i, char)
|
|
93
|
+
variations << doubled if @lookuper.good_forms(doubled).first
|
|
94
|
+
end
|
|
95
|
+
(0...word.length).each do |i|
|
|
96
|
+
deleted = word.dup
|
|
97
|
+
deleted.slice!(i)
|
|
98
|
+
next if deleted.empty?
|
|
99
|
+
|
|
100
|
+
variations << deleted if @lookuper.good_forms(deleted).first
|
|
101
|
+
end
|
|
102
|
+
common_substitutions = {
|
|
103
|
+
'a' => %w[e i o u],
|
|
104
|
+
'e' => %w[a i o u],
|
|
105
|
+
'i' => %w[a e o u],
|
|
106
|
+
'o' => %w[a e i u],
|
|
107
|
+
'u' => %w[a e i o],
|
|
108
|
+
's' => %w[z c],
|
|
109
|
+
'z' => %w[s],
|
|
110
|
+
'c' => %w[k s],
|
|
111
|
+
'k' => %w[c],
|
|
112
|
+
'ph' => %w[f],
|
|
113
|
+
'f' => %w[ph]
|
|
114
|
+
}
|
|
115
|
+
word.chars.each_with_index do |char, i|
|
|
116
|
+
next unless common_substitutions.key?(char.downcase)
|
|
117
|
+
|
|
118
|
+
common_substitutions[char.downcase].each do |sub|
|
|
119
|
+
substituted = word.dup
|
|
120
|
+
substituted[i] = sub
|
|
121
|
+
variations << substituted if @lookuper.good_forms(substituted).first
|
|
122
|
+
end
|
|
123
|
+
end
|
|
124
|
+
variations.uniq!
|
|
125
|
+
variations.map do |suggestion|
|
|
126
|
+
{ word: suggestion, distance: calculate_distance(word, suggestion),
|
|
127
|
+
score: calculate_score(word, suggestion, 0) }
|
|
128
|
+
end.sort_by { |s| s[:distance] }
|
|
129
|
+
end
|
|
130
|
+
end
|
|
131
|
+
|
|
132
|
+
# English tokenizer with contraction handling.
|
|
133
|
+
class Tokenizer < Components::WhitespaceTokenizer
|
|
134
|
+
CONTRACTIONS = {
|
|
135
|
+
"n't" => ['not', 'NEG'],
|
|
136
|
+
"'ll" => ['will', 'MD'],
|
|
137
|
+
"'ve" => ['have', 'VBP'],
|
|
138
|
+
"'re" => ['are', 'VBP'],
|
|
139
|
+
"'m" => ['am', 'VBP'],
|
|
140
|
+
"'d" => ['would', 'MD'],
|
|
141
|
+
"'s" => ['is', 'VBZ'],
|
|
142
|
+
"'clock" => ['of', 'IN'],
|
|
143
|
+
}.freeze
|
|
144
|
+
WONT_EXCEPTION = { "won't" => ['will', 'not'] }.freeze
|
|
145
|
+
CANT_EXCEPTION = { "can't" => ['can', "'t"] }.freeze
|
|
146
|
+
POSSESSIVE_PATTERN = /([A-Za-z]+)('s)(?=[A-Za-z]|$)/
|
|
147
|
+
CONTRACTION_WITH_S = %w[it he that what who there].freeze
|
|
148
|
+
|
|
149
|
+
def initialize(expand_contractions: true)
|
|
150
|
+
super()
|
|
151
|
+
@expand_contractions = expand_contractions
|
|
152
|
+
end
|
|
153
|
+
|
|
154
|
+
def tokenize(text)
|
|
155
|
+
return [] if text.nil? || text.empty?
|
|
156
|
+
|
|
157
|
+
tokens = super
|
|
158
|
+
if @expand_contractions
|
|
159
|
+
tokens = expand_contractions(tokens)
|
|
160
|
+
end
|
|
161
|
+
tokens
|
|
162
|
+
end
|
|
163
|
+
|
|
164
|
+
private
|
|
165
|
+
|
|
166
|
+
def expand_contractions(tokens)
|
|
167
|
+
result = []
|
|
168
|
+
i = 0
|
|
169
|
+
while i < tokens.length
|
|
170
|
+
token = tokens[i]
|
|
171
|
+
if token[:token] == "won't"
|
|
172
|
+
result << { token: 'will', position: token[:position], length: 5 }
|
|
173
|
+
result << { token: 'not', position: token[:position] + 5, length: 3 }
|
|
174
|
+
i += 1
|
|
175
|
+
next
|
|
176
|
+
end
|
|
177
|
+
if token[:token] == "can't"
|
|
178
|
+
result << { token: 'can', position: token[:position], length: 3 }
|
|
179
|
+
result << { token: "'t", position: token[:position] + 3, length: 2 }
|
|
180
|
+
i += 1
|
|
181
|
+
next
|
|
182
|
+
end
|
|
183
|
+
expanded = expand_single_contraction(token)
|
|
184
|
+
if expanded
|
|
185
|
+
result.concat(expanded)
|
|
186
|
+
else
|
|
187
|
+
result << token
|
|
188
|
+
end
|
|
189
|
+
i += 1
|
|
190
|
+
end
|
|
191
|
+
result
|
|
192
|
+
end
|
|
193
|
+
|
|
194
|
+
def expand_single_contraction(token)
|
|
195
|
+
word = token[:token]
|
|
196
|
+
if POSSESSIVE_PATTERN.match?(word)
|
|
197
|
+
base = word[0..-3]
|
|
198
|
+
if CONTRACTION_WITH_S.include?(base.downcase)
|
|
199
|
+
return [{ token: base, position: token[:position], length: base.length },
|
|
200
|
+
{ token: "'s", position: token[:position] + base.length, length: 2 }]
|
|
201
|
+
else
|
|
202
|
+
return [{ token: base, position: token[:position], length: base.length },
|
|
203
|
+
{ token: "'s", position: token[:position] + base.length, length: 2 }]
|
|
204
|
+
end
|
|
205
|
+
end
|
|
206
|
+
CONTRACTIONS.each do |suffix, _expansion|
|
|
207
|
+
next if ["'s", "'clock"].include?(suffix)
|
|
208
|
+
|
|
209
|
+
if word.end_with?(suffix) && word.length > suffix.length
|
|
210
|
+
prefix = word[0...-suffix.length]
|
|
211
|
+
return [{ token: prefix, position: token[:position], length: prefix.length },
|
|
212
|
+
{ token: suffix, position: token[:position] + prefix.length, length: suffix.length }]
|
|
213
|
+
end
|
|
214
|
+
end
|
|
215
|
+
nil
|
|
216
|
+
end
|
|
217
|
+
end
|
|
218
|
+
|
|
219
|
+
# English POS tagger.
|
|
220
|
+
class POSTagger < Components::PosTagger
|
|
221
|
+
FLAG_TO_POS = {
|
|
222
|
+
'N' => 'NOUN', 'NN' => 'NOUN', 'NNS' => 'NOUN', 'NNP' => 'NOUN', 'NP' => 'NOUN_PROPER',
|
|
223
|
+
'V' => 'VERB', 'VB' => 'VERB', 'VBD' => 'VERB', 'VBG' => 'VERB', 'VBN' => 'VERB',
|
|
224
|
+
'VBP' => 'VERB', 'VBZ' => 'VERB', 'MD' => 'VERB_MODAL',
|
|
225
|
+
'A' => 'ADJ', 'JJ' => 'ADJ', 'JJR' => 'ADJ', 'JJS' => 'ADJ',
|
|
226
|
+
'R' => 'ADV', 'RB' => 'ADV', 'RBR' => 'ADV', 'RBS' => 'ADV',
|
|
227
|
+
'D' => 'DET', 'DT' => 'DET', 'PDT' => 'DET',
|
|
228
|
+
'P' => 'PRON', 'PP' => 'PRON', 'PRP' => 'PRON', 'PRP$' => 'PRON_POSS',
|
|
229
|
+
'WP' => 'PRON', 'WP$' => 'PRON_POSS',
|
|
230
|
+
'I' => 'PREP', 'IN' => 'PREP',
|
|
231
|
+
'C' => 'CONJ', 'CC' => 'CONJ',
|
|
232
|
+
'U' => 'PART', 'RP' => 'PART',
|
|
233
|
+
'INTJ' => 'INTJ', 'UH' => 'INTJ',
|
|
234
|
+
'CD' => 'NUM', 'FW' => 'X',
|
|
235
|
+
'PUNCT' => 'PUNCT', '.' => 'PUNCT', ',' => 'PUNCT', '!' => 'PUNCT',
|
|
236
|
+
'?' => 'PUNCT', ';' => 'PUNCT', ':' => 'PUNCT'
|
|
237
|
+
}.freeze
|
|
238
|
+
|
|
239
|
+
attr_reader :aff_path, :dic_path, :script
|
|
240
|
+
|
|
241
|
+
def initialize(aff_path:, dic_path:, script: :latin, encoding: 'ISO-8859-1', flag_mapping: FLAG_TO_POS)
|
|
242
|
+
@aff_path = aff_path
|
|
243
|
+
@dic_path = dic_path
|
|
244
|
+
@script = script
|
|
245
|
+
@encoding = encoding
|
|
246
|
+
@flag_mapping = flag_mapping
|
|
247
|
+
@lookuper = Readers::LookupBuilder.new(aff_path, dic_path, encoding: encoding, script: script).build
|
|
248
|
+
@lookup_cache = {}
|
|
249
|
+
end
|
|
250
|
+
|
|
251
|
+
def tag(tokens)
|
|
252
|
+
return [] if tokens.nil? || tokens.empty?
|
|
253
|
+
|
|
254
|
+
tokens.map do |token|
|
|
255
|
+
word = token[:token]
|
|
256
|
+
if word.nil? || word.empty?
|
|
257
|
+
token.merge(pos_tag: nil, lemma: nil)
|
|
258
|
+
else
|
|
259
|
+
lookup_result = lookup_with_pos(word)
|
|
260
|
+
token.merge(pos_tag: lookup_result[:pos_tag], lemma: lookup_result[:lemma] || word)
|
|
261
|
+
end
|
|
262
|
+
end
|
|
263
|
+
end
|
|
264
|
+
|
|
265
|
+
def flag_mapping
|
|
266
|
+
@flag_mapping
|
|
267
|
+
end
|
|
268
|
+
|
|
269
|
+
def flag_mapping=(mapping)
|
|
270
|
+
@flag_mapping = mapping
|
|
271
|
+
end
|
|
272
|
+
|
|
273
|
+
def clear_cache
|
|
274
|
+
@lookup_cache.clear
|
|
275
|
+
end
|
|
276
|
+
|
|
277
|
+
def cache_size
|
|
278
|
+
@lookup_cache.size
|
|
279
|
+
end
|
|
280
|
+
|
|
281
|
+
private
|
|
282
|
+
|
|
283
|
+
def lookup_with_pos(word)
|
|
284
|
+
return { pos_tag: nil, lemma: nil } if word.nil? || word.empty?
|
|
285
|
+
return @lookup_cache[word] if @lookup_cache.key?(word)
|
|
286
|
+
|
|
287
|
+
first_form = @lookuper.good_forms(word).first
|
|
288
|
+
pos_tag = derive_pos_tag(first_form)
|
|
289
|
+
cache_result = { pos_tag: pos_tag, lemma: first_form&.stem }
|
|
290
|
+
@lookup_cache[word] = cache_result
|
|
291
|
+
cache_result
|
|
292
|
+
end
|
|
293
|
+
|
|
294
|
+
def derive_pos_tag(result)
|
|
295
|
+
return nil unless result
|
|
296
|
+
|
|
297
|
+
flags = result.flags&.to_a || []
|
|
298
|
+
return guess_pos_from_affix(result) if flags.empty?
|
|
299
|
+
|
|
300
|
+
flags.each do |flag|
|
|
301
|
+
pos_tag = flag_to_pos(flag)
|
|
302
|
+
return pos_tag if pos_tag
|
|
303
|
+
end
|
|
304
|
+
guess_pos_from_affix(result)
|
|
305
|
+
end
|
|
306
|
+
|
|
307
|
+
def flag_to_pos(flag)
|
|
308
|
+
return @flag_mapping[flag] if @flag_mapping.key?(flag)
|
|
309
|
+
|
|
310
|
+
first_char = flag[0]
|
|
311
|
+
@flag_mapping[first_char]
|
|
312
|
+
end
|
|
313
|
+
|
|
314
|
+
def guess_pos_from_affix(result)
|
|
315
|
+
suffix = result.suffix
|
|
316
|
+
if suffix
|
|
317
|
+
# suffix is a Hash with :add, :strip, :type keys
|
|
318
|
+
suffix_text = suffix[:add] || suffix['add']
|
|
319
|
+
return guess_pos_from_suffix(suffix_text) if suffix_text
|
|
320
|
+
end
|
|
321
|
+
prefix = result.prefix
|
|
322
|
+
return nil unless prefix
|
|
323
|
+
|
|
324
|
+
nil
|
|
325
|
+
end
|
|
326
|
+
|
|
327
|
+
def guess_pos_from_suffix(suffix)
|
|
328
|
+
return nil unless suffix.is_a?(String)
|
|
329
|
+
return 'VERB' if suffix.match?(/^(ing|ed|es|s)$/)
|
|
330
|
+
return 'ADV' if suffix.end_with?('ly')
|
|
331
|
+
return 'NOUN' if suffix.match?(/^(tion|sion|ment|ness|ity|ship|er|or|ist)$/)
|
|
332
|
+
return 'ADJ' if suffix.match?(/^(able|ible|al|ial|ic|ive|ful|less|ous)$/)
|
|
333
|
+
|
|
334
|
+
nil
|
|
335
|
+
end
|
|
336
|
+
end
|
|
337
|
+
|
|
338
|
+
# Registration and configuration
|
|
339
|
+
register "en"
|
|
340
|
+
register "en-US"
|
|
341
|
+
register "en-GB"
|
|
342
|
+
register "en-AU"
|
|
343
|
+
register "en-CA"
|
|
344
|
+
register "en-NZ"
|
|
345
|
+
register "en-ZA"
|
|
346
|
+
|
|
347
|
+
HUNSPELL_DICTIONARIES = {
|
|
348
|
+
'en-US' => {
|
|
349
|
+
aff: 'spec/integrational/fixtures/en_US.aff',
|
|
350
|
+
dic: 'spec/integrational/fixtures/en_US.dic'
|
|
351
|
+
},
|
|
352
|
+
}.freeze
|
|
353
|
+
|
|
354
|
+
VARIANT_NAMES = {
|
|
355
|
+
'US' => 'American',
|
|
356
|
+
'GB' => 'British',
|
|
357
|
+
'CA' => 'Canadian',
|
|
358
|
+
'AU' => 'Australian',
|
|
359
|
+
'NZ' => 'New Zealand',
|
|
360
|
+
'ZA' => 'South African'
|
|
361
|
+
}.freeze
|
|
362
|
+
|
|
363
|
+
def initialize(code: "en", name: "English", variant: nil)
|
|
364
|
+
variant ||= extract_region_code(code)
|
|
365
|
+
super
|
|
366
|
+
@hunspell_paths = resolve_hunspell_paths(code)
|
|
367
|
+
end
|
|
368
|
+
|
|
369
|
+
def description
|
|
370
|
+
return name unless variant
|
|
371
|
+
|
|
372
|
+
variant_name = VARIANT_NAMES[variant] || variant
|
|
373
|
+
"#{name} (#{variant_name})"
|
|
374
|
+
end
|
|
375
|
+
|
|
376
|
+
def tokenizer
|
|
377
|
+
@tokenizer ||= Tokenizer.new
|
|
378
|
+
end
|
|
379
|
+
|
|
380
|
+
def normalizer
|
|
381
|
+
@normalizer ||= Language::Normalizer::Base.new
|
|
382
|
+
end
|
|
383
|
+
|
|
384
|
+
def dictionary_class
|
|
385
|
+
Dictionary::UnixWords
|
|
386
|
+
end
|
|
387
|
+
|
|
388
|
+
def default_dictionary_paths
|
|
389
|
+
case code
|
|
390
|
+
when "en-GB", "en-AU", "en-NZ", "en-ZA"
|
|
391
|
+
["/usr/share/dict/british-english"]
|
|
392
|
+
when "en-US", "en-CA"
|
|
393
|
+
["/usr/share/dict/american-english"]
|
|
394
|
+
else
|
|
395
|
+
["/usr/share/dict/words"]
|
|
396
|
+
end
|
|
397
|
+
end
|
|
398
|
+
|
|
399
|
+
def script_type
|
|
400
|
+
:latin
|
|
401
|
+
end
|
|
402
|
+
|
|
403
|
+
def create_spell_checker
|
|
404
|
+
SpellChecker.new(
|
|
405
|
+
aff_path: @hunspell_paths[:aff],
|
|
406
|
+
dic_path: @hunspell_paths[:dic],
|
|
407
|
+
script: :latin
|
|
408
|
+
)
|
|
409
|
+
end
|
|
410
|
+
|
|
411
|
+
def create_tokenizer
|
|
412
|
+
Tokenizer.new
|
|
413
|
+
end
|
|
414
|
+
|
|
415
|
+
def create_pos_tagger
|
|
416
|
+
POSTagger.new(
|
|
417
|
+
aff_path: @hunspell_paths[:aff],
|
|
418
|
+
dic_path: @hunspell_paths[:dic],
|
|
419
|
+
script: :latin,
|
|
420
|
+
flag_mapping: english_pos_flag_mapping
|
|
421
|
+
)
|
|
422
|
+
end
|
|
423
|
+
|
|
424
|
+
def create_grammar_rules
|
|
425
|
+
Grammar::RuleEngine.new(language: 'en')
|
|
426
|
+
end
|
|
427
|
+
|
|
428
|
+
def valid_in_other_variant?(word)
|
|
429
|
+
return nil if @variant.nil? || @code == 'en'
|
|
430
|
+
|
|
431
|
+
HUNSPELL_DICTIONARIES.each do |variant_code, paths|
|
|
432
|
+
next if variant_code == @code
|
|
433
|
+
next unless File.exist?(paths[:aff]) && File.exist?(paths[:dic])
|
|
434
|
+
|
|
435
|
+
checker = SpellChecker.new(aff_path: paths[:aff], dic_path: paths[:dic], script: :latin,
|
|
436
|
+
encoding: 'ISO-8859-1')
|
|
437
|
+
if checker.correct?(word)
|
|
438
|
+
region = variant_code.split('-').last.upcase
|
|
439
|
+
variant_name = VARIANT_NAMES[region] || variant_code
|
|
440
|
+
return { variant: variant_name, code: "en-#{region}" }
|
|
441
|
+
end
|
|
442
|
+
end
|
|
443
|
+
nil
|
|
444
|
+
end
|
|
445
|
+
|
|
446
|
+
private
|
|
447
|
+
|
|
448
|
+
def extract_region_code(code)
|
|
449
|
+
return nil unless code.include?("-")
|
|
450
|
+
|
|
451
|
+
code.split("-", 2).last.upcase
|
|
452
|
+
end
|
|
453
|
+
|
|
454
|
+
def resolve_hunspell_paths(code)
|
|
455
|
+
HUNSPELL_DICTIONARIES[code] || HUNSPELL_DICTIONARIES['en-US']
|
|
456
|
+
end
|
|
457
|
+
|
|
458
|
+
def english_pos_flag_mapping
|
|
459
|
+
mappings = POSTagger::FLAG_TO_POS.dup
|
|
460
|
+
mappings.merge!(
|
|
461
|
+
'VBD' => 'VERB', 'VBG' => 'VERB', 'VBN' => 'VERB',
|
|
462
|
+
'VBP' => 'VERB', 'VBZ' => 'VERB',
|
|
463
|
+
'DT' => 'DET', 'WDT' => 'DET',
|
|
464
|
+
'PRP' => 'PRON', 'PRP$' => 'PRON_POSS',
|
|
465
|
+
'WP' => 'PRON', 'WP$' => 'PRON_POSS'
|
|
466
|
+
)
|
|
467
|
+
end
|
|
468
|
+
end
|
|
469
|
+
end
|
|
470
|
+
end
|