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 +1,52 @@
|
|
|
1
|
+
# frozen_string: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Devanagari InScript — the Indian national standard layout,
|
|
7
|
+
# which Nepali types on (plan 108).
|
|
8
|
+
#
|
|
9
|
+
# Grid mirrored from the models repo eval harness
|
|
10
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _NE_INSCRIPT,
|
|
11
|
+
# staged by its plan 83 batch-2 eval expansion) and
|
|
12
|
+
# drift-checked against it — the same rule as the other curated
|
|
13
|
+
# national grids. The Nepali Traditional Romanized layout is
|
|
14
|
+
# more common in Nepal, but InScript is the documented
|
|
15
|
+
# standard, so it is the defensible choice (the eval harness
|
|
16
|
+
# made the same call).
|
|
17
|
+
class DevanagariInScript < Layout
|
|
18
|
+
# Key positions for the InScript grid, [row, col] coordinates:
|
|
19
|
+
# row 0 digits, rows 1-3 the Devanagari keys in InScript
|
|
20
|
+
# order (matras left, consonants center/right).
|
|
21
|
+
KEY_POSITIONS = {
|
|
22
|
+
# Number row
|
|
23
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3],
|
|
24
|
+
'4' => [0, 4], '5' => [0, 5], '6' => [0, 6], '7' => [0, 7],
|
|
25
|
+
'8' => [0, 8], '9' => [0, 9], '0' => [0, 10], '-' => [0, 11],
|
|
26
|
+
'ृ' => [0, 12],
|
|
27
|
+
# Top row
|
|
28
|
+
'ौ' => [1, 0], 'ै' => [1, 1], 'ा' => [1, 2], 'ी' => [1, 3],
|
|
29
|
+
'ू' => [1, 4], 'ब' => [1, 5], 'ह' => [1, 6], 'ग' => [1, 7],
|
|
30
|
+
'द' => [1, 8], 'ज' => [1, 9], 'ड' => [1, 10], '़' => [1, 11],
|
|
31
|
+
# Home row
|
|
32
|
+
'ो' => [2, 0], 'े' => [2, 1], '्' => [2, 2], 'ि' => [2, 3],
|
|
33
|
+
'ु' => [2, 4], 'प' => [2, 5], 'र' => [2, 6], 'क' => [2, 7],
|
|
34
|
+
'त' => [2, 8], 'च' => [2, 9], 'ट' => [2, 10],
|
|
35
|
+
# Bottom row
|
|
36
|
+
'ॉ' => [3, 0], 'ं' => [3, 1], 'म' => [3, 2], 'न' => [3, 3],
|
|
37
|
+
'व' => [3, 4], 'ल' => [3, 5], 'स' => [3, 6], ',' => [3, 7],
|
|
38
|
+
'.' => [3, 8], 'य' => [3, 9]
|
|
39
|
+
}.freeze
|
|
40
|
+
|
|
41
|
+
# Initialize DevanagariInScript layout
|
|
42
|
+
def initialize
|
|
43
|
+
super(
|
|
44
|
+
name: 'DevanagariInScript',
|
|
45
|
+
language_codes: %w[ne ne-NP],
|
|
46
|
+
key_positions: KEY_POSITIONS
|
|
47
|
+
)
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
end
|
|
52
|
+
end
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
# frozen_string: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Dubeolsik — the standard Korean 2-set keyboard layout.
|
|
7
|
+
#
|
|
8
|
+
# Source: KS X 5002 (2-set Hangeul keyboard), the national
|
|
9
|
+
# standard every Korean IME ships. Each key produces one jamo
|
|
10
|
+
# (shift doubles the fortis consonants); the IME composes
|
|
11
|
+
# lead + vowel + tail into precomposed syllables, so the grid
|
|
12
|
+
# this layout models is jamo-keyed: typo proximity is measured
|
|
13
|
+
# on the jamo a slip actually hit, which is exactly the unit
|
|
14
|
+
# vowel mergers and fortis/lenis confusions operate on. The
|
|
15
|
+
# models repo eval harness models Korean slips as jamo
|
|
16
|
+
# confusion pairs rather than a key grid (eval/noise.py
|
|
17
|
+
# _KO_PAIRS), so there is no eval grid to drift-check against —
|
|
18
|
+
# this grid cites the layout standard itself.
|
|
19
|
+
#
|
|
20
|
+
# Row 1 (QWERTY q..p): ㅂ ㅈ ㄷ ㄱ ㅅ ㅛ ㅕ ㅑ ㅐ ㅔ
|
|
21
|
+
# Row 2 (a..l): ㅁ ㄴ ㅇ ㄹ ㅎ ㅗ ㅓ ㅏ ㅣ
|
|
22
|
+
# Row 3 (z..m): ㅋ ㅌ ㅊ ㅍ ㅠ ㅜ ㅡ
|
|
23
|
+
# Shift row 1: ㅃ ㅉ ㄸ ㄲ ㅆ (and ㅒ ㅖ on o/p)
|
|
24
|
+
class Dubeolsik < Layout
|
|
25
|
+
# Jamo-to-key-position grid, [row, col] coordinates on the
|
|
26
|
+
# three alphabetic rows (0-based col within each row, aligned
|
|
27
|
+
# to the physical QWERTY key columns).
|
|
28
|
+
KEY_POSITIONS = {
|
|
29
|
+
# Top row
|
|
30
|
+
'ㅂ' => [0, 0], 'ㅈ' => [0, 1], 'ㄷ' => [0, 2], 'ㄱ' => [0, 3],
|
|
31
|
+
'ㅅ' => [0, 4], 'ㅛ' => [0, 5], 'ㅕ' => [0, 6], 'ㅑ' => [0, 7],
|
|
32
|
+
'ㅐ' => [0, 8], 'ㅔ' => [0, 9],
|
|
33
|
+
# Shift of the top row: fortis consonants and y-diphthongs
|
|
34
|
+
'ㅃ' => [0, 0], 'ㅉ' => [0, 1], 'ㄸ' => [0, 2], 'ㄲ' => [0, 3],
|
|
35
|
+
'ㅆ' => [0, 4], 'ㅒ' => [0, 8], 'ㅖ' => [0, 9],
|
|
36
|
+
# Home row
|
|
37
|
+
'ㅁ' => [1, 0], 'ㄴ' => [1, 1], 'ㅇ' => [1, 2], 'ㄹ' => [1, 3],
|
|
38
|
+
'ㅎ' => [1, 4], 'ㅗ' => [1, 5], 'ㅓ' => [1, 6], 'ㅏ' => [1, 7],
|
|
39
|
+
'ㅣ' => [1, 8],
|
|
40
|
+
# Bottom row
|
|
41
|
+
'ㅋ' => [2, 0], 'ㅌ' => [2, 1], 'ㅊ' => [2, 2], 'ㅍ' => [2, 3],
|
|
42
|
+
'ㅠ' => [2, 4], 'ㅜ' => [2, 5], 'ㅡ' => [2, 6]
|
|
43
|
+
}.freeze
|
|
44
|
+
|
|
45
|
+
# Initialize Dubeolsik layout
|
|
46
|
+
def initialize
|
|
47
|
+
super(
|
|
48
|
+
name: 'Dubeolsik',
|
|
49
|
+
language_codes: %w[ko ko-KR],
|
|
50
|
+
key_positions: KEY_POSITIONS
|
|
51
|
+
)
|
|
52
|
+
end
|
|
53
|
+
end
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
end
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Dvorak keyboard layout
|
|
7
|
+
#
|
|
8
|
+
# Dvorak Simplified Keyboard layout designed for efficiency:
|
|
9
|
+
# - English (en, en-US) with Dvorak layout
|
|
10
|
+
#
|
|
11
|
+
# Key differences from QWERTY:
|
|
12
|
+
# - Vowels (AOEUIDHTNS) on home row left
|
|
13
|
+
# - Most common consonants on home row right
|
|
14
|
+
# - Designed to minimize finger movement
|
|
15
|
+
# - ~70% of keystrokes on home row (vs ~32% for QWERTY)
|
|
16
|
+
#
|
|
17
|
+
# Key positions use [row, col] coordinates where:
|
|
18
|
+
# - row 0: number row (`1"2>...)
|
|
19
|
+
# - row 1: top row (',.<pyfg...)
|
|
20
|
+
# - row 2: home row (aoeuidhtns...)
|
|
21
|
+
# - row 3: bottom row (;qjkxbmwvz)
|
|
22
|
+
class Dvorak < Layout
|
|
23
|
+
# Key positions for Dvorak layout
|
|
24
|
+
# Each key maps to [row, column] coordinates
|
|
25
|
+
KEY_POSITIONS = {
|
|
26
|
+
# Number row
|
|
27
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
28
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
29
|
+
'0' => [0, 10], '[' => [0, 11], ']' => [0, 12],
|
|
30
|
+
# Top row (punctuation and high-frequency consonants)
|
|
31
|
+
'\'' => [1, 0], ',' => [1, 1], '.' => [1, 2], 'p' => [1, 3], 'y' => [1, 4],
|
|
32
|
+
'f' => [1, 5], 'g' => [1, 6], 'c' => [1, 7], 'r' => [1, 8], 'l' => [1, 9],
|
|
33
|
+
'/' => [1, 10], '=' => [1, 11],
|
|
34
|
+
# Home row (vowels left, high-frequency consonants right)
|
|
35
|
+
'a' => [2, 0], 'o' => [2, 1], 'e' => [2, 2], 'u' => [2, 3], 'i' => [2, 4],
|
|
36
|
+
'd' => [2, 5], 'h' => [2, 6], 't' => [2, 7], 'n' => [2, 8], 's' => [2, 9],
|
|
37
|
+
'-' => [2, 10],
|
|
38
|
+
# Bottom row (low-frequency letters)
|
|
39
|
+
';' => [3, 0], 'q' => [3, 1], 'j' => [3, 2], 'k' => [3, 3], 'x' => [3, 4],
|
|
40
|
+
'b' => [3, 5], 'm' => [3, 6], 'w' => [3, 7], 'v' => [3, 8], 'z' => [3, 9]
|
|
41
|
+
}.freeze
|
|
42
|
+
|
|
43
|
+
# Initialize Dvorak layout
|
|
44
|
+
def initialize
|
|
45
|
+
super(
|
|
46
|
+
name: 'Dvorak',
|
|
47
|
+
language_codes: %w[en en-US],
|
|
48
|
+
key_positions: KEY_POSITIONS
|
|
49
|
+
)
|
|
50
|
+
end
|
|
51
|
+
end
|
|
52
|
+
end
|
|
53
|
+
end
|
|
54
|
+
end
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Greek phonetic keyboard layout.
|
|
7
|
+
#
|
|
8
|
+
# The mnemonic/phonetic mapping used by Greek typists: each Greek
|
|
9
|
+
# letter sits on the Latin letter it transliterates to (; is the
|
|
10
|
+
# semicolon key doubling as the Greek question mark). Accented
|
|
11
|
+
# vowels are dead-key sequences, not physical keys, so they do not
|
|
12
|
+
# appear in the grid — matching the models repo eval model, where
|
|
13
|
+
# accents are diacritic slips handled outside the layout.
|
|
14
|
+
#
|
|
15
|
+
# The key grid is mirrored from the models repo eval harness
|
|
16
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _EL_PHONETIC,
|
|
17
|
+
# wave 1 of the model coverage expansion). The drift spec
|
|
18
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
19
|
+
# the sync.
|
|
20
|
+
#
|
|
21
|
+
# Languages: el, el-GR
|
|
22
|
+
class GreekPhonetic < Layout
|
|
23
|
+
# Key positions for the Greek phonetic layout.
|
|
24
|
+
# Each key maps to [row, column] coordinates.
|
|
25
|
+
KEY_POSITIONS = {
|
|
26
|
+
# Number row
|
|
27
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
28
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
29
|
+
'0' => [0, 10], '-' => [0, 11], '=' => [0, 12],
|
|
30
|
+
# Top row (;ΣΕΡΤΥΘΙΟΠ)
|
|
31
|
+
';' => [1, 0], 'σ' => [1, 1], 'ε' => [1, 2], 'ρ' => [1, 3], 'τ' => [1, 4],
|
|
32
|
+
'υ' => [1, 5], 'θ' => [1, 6], 'ι' => [1, 7], 'ο' => [1, 8], 'π' => [1, 9],
|
|
33
|
+
# Home row (ΑΔΦΓΗΞΚΛ)
|
|
34
|
+
'α' => [2, 0], 'δ' => [2, 1], 'φ' => [2, 2], 'γ' => [2, 3], 'η' => [2, 4],
|
|
35
|
+
'ξ' => [2, 5], 'κ' => [2, 6], 'λ' => [2, 7],
|
|
36
|
+
# Bottom row (ΖΧΨΩΒΝΜ)
|
|
37
|
+
'ζ' => [3, 0], 'χ' => [3, 1], 'ψ' => [3, 2], 'ω' => [3, 3], 'β' => [3, 4],
|
|
38
|
+
'ν' => [3, 5], 'μ' => [3, 6]
|
|
39
|
+
}.freeze
|
|
40
|
+
|
|
41
|
+
# Initialize the Greek phonetic layout.
|
|
42
|
+
def initialize
|
|
43
|
+
super(
|
|
44
|
+
name: 'Greek-Phonetic',
|
|
45
|
+
language_codes: %w[el el-GR],
|
|
46
|
+
key_positions: KEY_POSITIONS
|
|
47
|
+
)
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
end
|
|
52
|
+
end
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Hebrew standard keyboard layout (SI-1452).
|
|
7
|
+
#
|
|
8
|
+
# The 27 Hebrew letters all sit on key faces in the standard
|
|
9
|
+
# ordering, including the five final-letter forms ם ן ך ף ץ as
|
|
10
|
+
# real keys. Niqqud (vowel points) are dead keys and are not in
|
|
11
|
+
# the grid; geresh/gershayim are shift states, not base keys.
|
|
12
|
+
#
|
|
13
|
+
# The key grid is mirrored from the models repo eval harness
|
|
14
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _HE_SI1452, plan 83
|
|
15
|
+
# batch 2 of the model coverage expansion, verified there
|
|
16
|
+
# against the Culmus SI-1452 layout table) so typo-adjacency
|
|
17
|
+
# used for suggestion ranking matches the adjacency used to
|
|
18
|
+
# evaluate the models.
|
|
19
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
20
|
+
# the sync.
|
|
21
|
+
#
|
|
22
|
+
# Languages: he, he-IL
|
|
23
|
+
class HebrewSI1452 < Layout
|
|
24
|
+
# Key positions for the Hebrew SI-1452 layout.
|
|
25
|
+
# Each key maps to [row, column] coordinates.
|
|
26
|
+
KEY_POSITIONS = {
|
|
27
|
+
# Number row
|
|
28
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3],
|
|
29
|
+
'4' => [0, 4], '5' => [0, 5], '6' => [0, 6], '7' => [0, 7],
|
|
30
|
+
'8' => [0, 8], '9' => [0, 9], '0' => [0, 10], '-' => [0, 11],
|
|
31
|
+
'=' => [0, 12],
|
|
32
|
+
# Top row (ק ר א ט ו ן ם פ)
|
|
33
|
+
'/' => [1, 0], "'" => [1, 1], 'ק' => [1, 2], 'ר' => [1, 3],
|
|
34
|
+
'א' => [1, 4], 'ט' => [1, 5], 'ו' => [1, 6], 'ן' => [1, 7],
|
|
35
|
+
'ם' => [1, 8], 'פ' => [1, 9], '[' => [1, 10], ']' => [1, 11],
|
|
36
|
+
# Home row (ש ד ג כ ע י ח ל ך ף)
|
|
37
|
+
'ש' => [2, 0], 'ד' => [2, 1], 'ג' => [2, 2], 'כ' => [2, 3],
|
|
38
|
+
'ע' => [2, 4], 'י' => [2, 5], 'ח' => [2, 6], 'ל' => [2, 7],
|
|
39
|
+
'ך' => [2, 8], 'ף' => [2, 9], ',' => [2, 10],
|
|
40
|
+
# Bottom row (ז ס ב ה נ מ צ ת ץ)
|
|
41
|
+
'ז' => [3, 0], 'ס' => [3, 1], 'ב' => [3, 2], 'ה' => [3, 3],
|
|
42
|
+
'נ' => [3, 4], 'מ' => [3, 5], 'צ' => [3, 6], 'ת' => [3, 7],
|
|
43
|
+
'ץ' => [3, 8], '.' => [3, 9]
|
|
44
|
+
}.freeze
|
|
45
|
+
|
|
46
|
+
# Initialize the Hebrew SI-1452 layout.
|
|
47
|
+
def initialize
|
|
48
|
+
super(
|
|
49
|
+
name: 'Hebrew-SI-1452',
|
|
50
|
+
language_codes: %w[he he-IL],
|
|
51
|
+
key_positions: KEY_POSITIONS
|
|
52
|
+
)
|
|
53
|
+
end
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
end
|
|
57
|
+
end
|
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Croatian and Slovenian QWERTZ keyboard layouts (KBDCRO /
|
|
7
|
+
# KBDYCL driver tables — the two national standards share one
|
|
8
|
+
# physical grid).
|
|
9
|
+
#
|
|
10
|
+
# The five South-Slavic Latin letters are real keys: š đ take
|
|
11
|
+
# the top-row bracket faces, č ć ž the home-row umlaut faces
|
|
12
|
+
# and the key right of them. Everything else is the QWERTZ
|
|
13
|
+
# physical arrangement (z/y swapped), so diacritic slips are not
|
|
14
|
+
# possible for these five — they are key slips.
|
|
15
|
+
#
|
|
16
|
+
# The shared key grid is mirrored from the models repo eval
|
|
17
|
+
# harness (kotoshu/models-fasttext-onnx eval/noise.py _HRSL,
|
|
18
|
+
# plan 83 batch 2 of the model coverage expansion, verified
|
|
19
|
+
# there against the kbdlayout.info driver tables) so
|
|
20
|
+
# typo-adjacency used for suggestion ranking matches the
|
|
21
|
+
# adjacency used to evaluate the models.
|
|
22
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
23
|
+
# the sync.
|
|
24
|
+
module HrSlQwertz
|
|
25
|
+
# Key positions for the Croatian/Slovenian QWERTZ grid.
|
|
26
|
+
# Each key maps to [row, column] coordinates.
|
|
27
|
+
KEY_POSITIONS = {
|
|
28
|
+
# Number row
|
|
29
|
+
'‚' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3],
|
|
30
|
+
'4' => [0, 4], '5' => [0, 5], '6' => [0, 6], '7' => [0, 7],
|
|
31
|
+
'8' => [0, 8], '9' => [0, 9], '0' => [0, 10],
|
|
32
|
+
"'" => [0, 11], '+' => [0, 12],
|
|
33
|
+
# Top row (QWERTZ + š đ)
|
|
34
|
+
'q' => [1, 0], 'w' => [1, 1], 'e' => [1, 2], 'r' => [1, 3],
|
|
35
|
+
't' => [1, 4], 'z' => [1, 5], 'u' => [1, 6], 'i' => [1, 7],
|
|
36
|
+
'o' => [1, 8], 'p' => [1, 9], 'š' => [1, 10], 'đ' => [1, 11],
|
|
37
|
+
# Home row (ASDFG + č ć ž)
|
|
38
|
+
'a' => [2, 0], 's' => [2, 1], 'd' => [2, 2], 'f' => [2, 3],
|
|
39
|
+
'g' => [2, 4], 'h' => [2, 5], 'j' => [2, 6], 'k' => [2, 7],
|
|
40
|
+
'l' => [2, 8], 'č' => [2, 9], 'ć' => [2, 10], 'ž' => [2, 11],
|
|
41
|
+
# Bottom row (YXCVB)
|
|
42
|
+
'y' => [3, 0], 'x' => [3, 1], 'c' => [3, 2], 'v' => [3, 3],
|
|
43
|
+
'b' => [3, 4], 'n' => [3, 5], 'm' => [3, 6],
|
|
44
|
+
',' => [3, 7], '.' => [3, 8], '-' => [3, 9]
|
|
45
|
+
}.freeze
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
# Croatian QWERTZ (KBDCRO / Croatian standard grid).
|
|
49
|
+
#
|
|
50
|
+
# Languages: hr, hr-HR
|
|
51
|
+
class Croatian < Layout
|
|
52
|
+
# Initialize the Croatian layout.
|
|
53
|
+
def initialize
|
|
54
|
+
super(
|
|
55
|
+
name: 'Croatian-QWERTZ',
|
|
56
|
+
language_codes: %w[hr hr-HR],
|
|
57
|
+
key_positions: HrSlQwertz::KEY_POSITIONS
|
|
58
|
+
)
|
|
59
|
+
end
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
# Slovenian QWERTZ (KBDYCL / Slovenian standard grid — the same
|
|
63
|
+
# physical arrangement as Croatian).
|
|
64
|
+
#
|
|
65
|
+
# Languages: sl, sl-SI
|
|
66
|
+
class Slovenian < Layout
|
|
67
|
+
# Initialize the Slovenian layout.
|
|
68
|
+
def initialize
|
|
69
|
+
super(
|
|
70
|
+
name: 'Slovenian-QWERTZ',
|
|
71
|
+
language_codes: %w[sl sl-SI],
|
|
72
|
+
key_positions: HrSlQwertz::KEY_POSITIONS
|
|
73
|
+
)
|
|
74
|
+
end
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
# Serbian Latin QWERTZ (the srp driver table — the same
|
|
78
|
+
# South-Slavic physical arrangement as Croatian and Slovenian;
|
|
79
|
+
# plan 110).
|
|
80
|
+
#
|
|
81
|
+
# Languages: sr-Latn
|
|
82
|
+
class SerbianLatin < Layout
|
|
83
|
+
# Initialize the Serbian Latin layout.
|
|
84
|
+
def initialize
|
|
85
|
+
super(
|
|
86
|
+
name: 'Serbian-Latin-QWERTZ',
|
|
87
|
+
language_codes: %w[sr-Latn],
|
|
88
|
+
key_positions: HrSlQwertz::KEY_POSITIONS
|
|
89
|
+
)
|
|
90
|
+
end
|
|
91
|
+
end
|
|
92
|
+
end
|
|
93
|
+
end
|
|
94
|
+
end
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# JCUKEN keyboard layout
|
|
7
|
+
#
|
|
8
|
+
# Standard JCUKEN layout used for:
|
|
9
|
+
# - Russian (ru, ru-RU)
|
|
10
|
+
# - Ukrainian (uk)
|
|
11
|
+
# - Belarusian (be)
|
|
12
|
+
# - Bulgarian (bg)
|
|
13
|
+
#
|
|
14
|
+
# This is the standard Cyrillic keyboard layout.
|
|
15
|
+
# Key differences from QWERTY:
|
|
16
|
+
# - Completely different alphabet (Cyrillic: 33 letters)
|
|
17
|
+
# - JCUKEN mapping corresponds to QWERTY positions
|
|
18
|
+
# - Has special keys: ё, ъ, ь
|
|
19
|
+
#
|
|
20
|
+
# Key positions use [row, col] coordinates where:
|
|
21
|
+
# - row 0: number row (ё1"2...)
|
|
22
|
+
# - row 1: top row (йцукен...)
|
|
23
|
+
# - row 2: home row (фывап...)
|
|
24
|
+
# - row 3: bottom row (ячсми...)
|
|
25
|
+
class JCUKEN < Layout
|
|
26
|
+
# Key positions for JCUKEN layout (Cyrillic)
|
|
27
|
+
# Each key maps to [row, column] coordinates
|
|
28
|
+
KEY_POSITIONS = {
|
|
29
|
+
# Number row
|
|
30
|
+
'ё' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
31
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
32
|
+
'0' => [0, 10], '-' => [0, 11], '=' => [0, 12],
|
|
33
|
+
# Top row (ЙЦУКЕН - corresponds to QWERTY)
|
|
34
|
+
'й' => [1, 0], 'ц' => [1, 1], 'у' => [1, 2], 'к' => [1, 3], 'е' => [1, 4],
|
|
35
|
+
'н' => [1, 5], 'г' => [1, 6], 'ш' => [1, 7], 'щ' => [1, 8], 'з' => [1, 9],
|
|
36
|
+
'х' => [1, 10], 'ъ' => [1, 11],
|
|
37
|
+
# Home row (ФЫВАПРОЛД - corresponds to ASDFGHJKL)
|
|
38
|
+
'ф' => [2, 0], 'ы' => [2, 1], 'в' => [2, 2], 'а' => [2, 3], 'п' => [2, 4],
|
|
39
|
+
'р' => [2, 5], 'о' => [2, 6], 'л' => [2, 7], 'д' => [2, 8], 'ж' => [2, 9],
|
|
40
|
+
'э' => [2, 10],
|
|
41
|
+
# Bottom row (ЯЧСМИТЬБЮ - corresponds to ZXCVBNM)
|
|
42
|
+
'я' => [3, 0], 'ч' => [3, 1], 'с' => [3, 2], 'м' => [3, 3], 'и' => [3, 4],
|
|
43
|
+
'т' => [3, 5], 'ь' => [3, 6], 'б' => [3, 7], 'ю' => [3, 8], '.' => [3, 9]
|
|
44
|
+
}.freeze
|
|
45
|
+
|
|
46
|
+
# Initialize JCUKEN layout
|
|
47
|
+
def initialize
|
|
48
|
+
super(
|
|
49
|
+
name: 'JCUKEN',
|
|
50
|
+
language_codes: %w[ru uk be bg ru-RU],
|
|
51
|
+
key_positions: KEY_POSITIONS
|
|
52
|
+
)
|
|
53
|
+
end
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
end
|
|
57
|
+
end
|