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 +1,266 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Parameterized Latin-script layout family.
|
|
7
|
+
#
|
|
8
|
+
# The wave-1 Latin languages type on one of two physical base
|
|
9
|
+
# grids — QWERTY (it nl pl ro ca vi da nb sv) or QWERTZ (cs hu) —
|
|
10
|
+
# optionally with per-language physical extras: the Nordic layouts
|
|
11
|
+
# have real å/æ/ø and å/ä/ö keys where US QWERTY carries
|
|
12
|
+
# [ ] ; '. Their remaining diacritics are dead-key or AltGr
|
|
13
|
+
# sequences, not physical keys, so they do not appear in the key
|
|
14
|
+
# grid. This mirrors the models repo eval model
|
|
15
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py: LANG_LAYOUT maps
|
|
16
|
+
# the Latin newcomers onto the qwerty/qwertz grids and handles
|
|
17
|
+
# diacritics as _LANG_ALTERNATES slips), keeping gem suggestion
|
|
18
|
+
# adjacency and eval adjacency in sync. Batch 3 (plan 100) adds
|
|
19
|
+
# id sk et lt lv on the same qwerty base grid.
|
|
20
|
+
#
|
|
21
|
+
# One family, per-language declarations — no near-duplicate
|
|
22
|
+
# layout files. The five pre-existing layouts (qwerty qwertz
|
|
23
|
+
# azerty jcuken dvorak) are untouched.
|
|
24
|
+
#
|
|
25
|
+
# @example Declaring a member of the family
|
|
26
|
+
# class Italian < Latin
|
|
27
|
+
# layout_name 'Italian-QWERTY'
|
|
28
|
+
# languages %w[it it-IT]
|
|
29
|
+
# base_grid :qwerty
|
|
30
|
+
# end
|
|
31
|
+
class Latin < Layout
|
|
32
|
+
# Sentinel distinguishing "reader call" from "writer call".
|
|
33
|
+
NOT_SET = Object.new.freeze
|
|
34
|
+
|
|
35
|
+
class << self
|
|
36
|
+
# Get or set the layout display name.
|
|
37
|
+
#
|
|
38
|
+
# @param value [String, NOT_SET] name when declaring
|
|
39
|
+
# @return [String, nil] the declared name
|
|
40
|
+
def layout_name(value = NOT_SET)
|
|
41
|
+
return @layout_name if value.equal?(NOT_SET)
|
|
42
|
+
|
|
43
|
+
@layout_name = value
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
# Get or set the supported language codes.
|
|
47
|
+
#
|
|
48
|
+
# @param value [Array<String>, NOT_SET] codes when declaring
|
|
49
|
+
# @return [Array<String>, nil] the declared codes
|
|
50
|
+
def languages(value = NOT_SET)
|
|
51
|
+
return @languages if value.equal?(NOT_SET)
|
|
52
|
+
|
|
53
|
+
@languages = Array(value).freeze
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
# Get or set the base physical grid.
|
|
57
|
+
#
|
|
58
|
+
# @param value [Symbol, NOT_SET] :qwerty or :qwertz
|
|
59
|
+
# @return [Symbol, nil] the declared base grid
|
|
60
|
+
def base_grid(value = NOT_SET)
|
|
61
|
+
return @base_grid if value.equal?(NOT_SET)
|
|
62
|
+
|
|
63
|
+
@base_grid = value
|
|
64
|
+
end
|
|
65
|
+
|
|
66
|
+
# Get or set keys removed from the base grid.
|
|
67
|
+
#
|
|
68
|
+
# Used by the Nordic members, whose å/æ/ø keys replace the
|
|
69
|
+
# US bracket and semicolon keys.
|
|
70
|
+
#
|
|
71
|
+
# @param value [Array<String>, NOT_SET] keys to remove
|
|
72
|
+
# @return [Array<String>, nil] the removed keys
|
|
73
|
+
def removed_keys(value = NOT_SET)
|
|
74
|
+
return @removed_keys if value.equal?(NOT_SET)
|
|
75
|
+
|
|
76
|
+
@removed_keys = Array(value).freeze
|
|
77
|
+
end
|
|
78
|
+
|
|
79
|
+
# Get or set extra physical keys merged over the base grid.
|
|
80
|
+
#
|
|
81
|
+
# @param value [Hash{String => Array<Integer>}, NOT_SET]
|
|
82
|
+
# key => [row, col] pairs
|
|
83
|
+
# @return [Hash{String => Array<Integer>}, nil] the extras
|
|
84
|
+
def extra_positions(value = NOT_SET)
|
|
85
|
+
return @extra_positions if value.equal?(NOT_SET)
|
|
86
|
+
|
|
87
|
+
@extra_positions = value.freeze
|
|
88
|
+
end
|
|
89
|
+
end
|
|
90
|
+
|
|
91
|
+
# Build the layout from the class declarations: the base grid,
|
|
92
|
+
# minus removed keys, plus extra physical keys.
|
|
93
|
+
def initialize
|
|
94
|
+
super(
|
|
95
|
+
name: self.class.layout_name,
|
|
96
|
+
language_codes: self.class.languages,
|
|
97
|
+
key_positions: build_positions
|
|
98
|
+
)
|
|
99
|
+
end
|
|
100
|
+
|
|
101
|
+
private
|
|
102
|
+
|
|
103
|
+
# Compose the final key-position grid.
|
|
104
|
+
#
|
|
105
|
+
# @return [Hash{String => Array<Integer>}] the composed grid
|
|
106
|
+
def build_positions
|
|
107
|
+
positions = base_grid_positions
|
|
108
|
+
removed = self.class.removed_keys
|
|
109
|
+
positions = positions.except(*removed) if removed
|
|
110
|
+
extras = self.class.extra_positions
|
|
111
|
+
extras ? positions.merge(extras) : positions
|
|
112
|
+
end
|
|
113
|
+
|
|
114
|
+
# Resolve the base grid constant.
|
|
115
|
+
#
|
|
116
|
+
# @return [Hash{String => Array<Integer>}] the base key positions
|
|
117
|
+
# @raise [ArgumentError] when no known base grid was declared
|
|
118
|
+
def base_grid_positions
|
|
119
|
+
case self.class.base_grid
|
|
120
|
+
when :qwerty then Layouts::QWERTY::KEY_POSITIONS
|
|
121
|
+
when :qwertz then Layouts::QWERTZ::KEY_POSITIONS
|
|
122
|
+
else
|
|
123
|
+
raise ArgumentError,
|
|
124
|
+
"#{self.class} must declare base_grid :qwerty or :qwertz"
|
|
125
|
+
end
|
|
126
|
+
end
|
|
127
|
+
|
|
128
|
+
# Italian: US QWERTY physical layout; accents are dead keys.
|
|
129
|
+
class Italian < Latin
|
|
130
|
+
layout_name 'Italian-QWERTY'
|
|
131
|
+
languages %w[it it-IT]
|
|
132
|
+
base_grid :qwerty
|
|
133
|
+
end
|
|
134
|
+
|
|
135
|
+
# Dutch: US QWERTY physical layout; accents are dead keys.
|
|
136
|
+
class Dutch < Latin
|
|
137
|
+
layout_name 'Dutch-QWERTY'
|
|
138
|
+
languages %w[nl nl-NL]
|
|
139
|
+
base_grid :qwerty
|
|
140
|
+
end
|
|
141
|
+
|
|
142
|
+
# Polish: programmers' (US-equivalent) QWERTY layout, the
|
|
143
|
+
# layout Polish fastText corpora are typed on; ą ć ę ł ń ó ś
|
|
144
|
+
# ź ż are AltGr sequences.
|
|
145
|
+
class Polish < Latin
|
|
146
|
+
layout_name 'Polish-QWERTY'
|
|
147
|
+
languages %w[pl pl-PL]
|
|
148
|
+
base_grid :qwerty
|
|
149
|
+
end
|
|
150
|
+
|
|
151
|
+
# Czech: QWERTZ physical layout (z/y swapped, ü ö ä keys);
|
|
152
|
+
# háčky and čárky are dead keys.
|
|
153
|
+
class Czech < Latin
|
|
154
|
+
layout_name 'Czech-QWERTZ'
|
|
155
|
+
languages %w[cs cs-CZ]
|
|
156
|
+
base_grid :qwertz
|
|
157
|
+
end
|
|
158
|
+
|
|
159
|
+
# Hungarian: QWERTZ physical layout; ő ű are dead keys.
|
|
160
|
+
class Hungarian < Latin
|
|
161
|
+
layout_name 'Hungarian-QWERTZ'
|
|
162
|
+
languages %w[hu hu-HU]
|
|
163
|
+
base_grid :qwertz
|
|
164
|
+
end
|
|
165
|
+
|
|
166
|
+
# Romanian: US QWERTY physical layout; ă â î ș ț are AltGr
|
|
167
|
+
# sequences.
|
|
168
|
+
class Romanian < Latin
|
|
169
|
+
layout_name 'Romanian-QWERTY'
|
|
170
|
+
languages %w[ro ro-RO]
|
|
171
|
+
base_grid :qwerty
|
|
172
|
+
end
|
|
173
|
+
|
|
174
|
+
# Catalan: Spanish (US-equivalent) QWERTY physical layout; the
|
|
175
|
+
# gem keys Catalan to the qwerty grid like the eval model does.
|
|
176
|
+
class Catalan < Latin
|
|
177
|
+
layout_name 'Catalan-QWERTY'
|
|
178
|
+
languages %w[ca ca-ES]
|
|
179
|
+
base_grid :qwerty
|
|
180
|
+
end
|
|
181
|
+
|
|
182
|
+
# Vietnamese: US QWERTY physical layout; all tone and vowel
|
|
183
|
+
# marks are typed with dead keys over the ASCII letters.
|
|
184
|
+
class Vietnamese < Latin
|
|
185
|
+
layout_name 'Vietnamese-QWERTY'
|
|
186
|
+
languages %w[vi vi-VN]
|
|
187
|
+
base_grid :qwerty
|
|
188
|
+
end
|
|
189
|
+
|
|
190
|
+
# Danish: Nordic QWERTY with real å æ ø keys replacing the
|
|
191
|
+
# US bracket/semicolon keys.
|
|
192
|
+
class Danish < Latin
|
|
193
|
+
layout_name 'Danish-QWERTY'
|
|
194
|
+
languages %w[da da-DK]
|
|
195
|
+
base_grid :qwerty
|
|
196
|
+
removed_keys %w([ ] ; ')
|
|
197
|
+
extra_positions({ 'å' => [1, 10], 'æ' => [2, 9], 'ø' => [2, 10] })
|
|
198
|
+
end
|
|
199
|
+
|
|
200
|
+
# Norwegian Bokmal: same Nordic physical grid as Danish (å æ ø).
|
|
201
|
+
class Norwegian < Latin
|
|
202
|
+
layout_name 'Norwegian-QWERTY'
|
|
203
|
+
languages %w[nb nb-NO]
|
|
204
|
+
base_grid :qwerty
|
|
205
|
+
removed_keys %w([ ] ; ')
|
|
206
|
+
extra_positions({ 'å' => [1, 10], 'æ' => [2, 9], 'ø' => [2, 10] })
|
|
207
|
+
end
|
|
208
|
+
|
|
209
|
+
# Swedish: Nordic QWERTY with real å ä ö keys (ä ö where
|
|
210
|
+
# Danish/Norwegian carry æ ø).
|
|
211
|
+
class Swedish < Latin
|
|
212
|
+
layout_name 'Swedish-QWERTY'
|
|
213
|
+
languages %w[sv sv-SE]
|
|
214
|
+
base_grid :qwerty
|
|
215
|
+
removed_keys %w([ ] ; ')
|
|
216
|
+
extra_positions({ 'å' => [1, 10], 'ä' => [2, 9], 'ö' => [2, 10] })
|
|
217
|
+
end
|
|
218
|
+
|
|
219
|
+
# Indonesian: US QWERTY physical layout — the Indonesian
|
|
220
|
+
# national standard types on the unmodified US grid, and the
|
|
221
|
+
# eval harness maps id the same way (plan 83 batch 2).
|
|
222
|
+
class Indonesian < Latin
|
|
223
|
+
layout_name 'Indonesian-QWERTY'
|
|
224
|
+
languages %w[id id-ID]
|
|
225
|
+
base_grid :qwerty
|
|
226
|
+
end
|
|
227
|
+
|
|
228
|
+
# Slovak: US QWERTY physical layout; the eval harness maps sk
|
|
229
|
+
# to the qwerty grid (plan 83 batch 2) with the háčik
|
|
230
|
+
# diacritics as dead-key slips, exactly the Polish
|
|
231
|
+
# programmers' pattern. The Slovak QWERTZ national variant
|
|
232
|
+
# exists, but Slovak QWERTY is the widely-typed form.
|
|
233
|
+
class Slovak < Latin
|
|
234
|
+
layout_name 'Slovak-QWERTY'
|
|
235
|
+
languages %w[sk sk-SK]
|
|
236
|
+
base_grid :qwerty
|
|
237
|
+
end
|
|
238
|
+
|
|
239
|
+
# Estonian: US QWERTY physical layout; ä ö õ ü š ž are dead-key
|
|
240
|
+
# or AltGr sequences on the eval model grid (plan 83 batch 2).
|
|
241
|
+
class Estonian < Latin
|
|
242
|
+
layout_name 'Estonian-QWERTY'
|
|
243
|
+
languages %w[et et-EE]
|
|
244
|
+
base_grid :qwerty
|
|
245
|
+
end
|
|
246
|
+
|
|
247
|
+
# Lithuanian: US QWERTY physical layout; ą č ę ė į š ų ū ž are
|
|
248
|
+
# dead-key or AltGr sequences (plan 83 batch 2 eval mapping).
|
|
249
|
+
class Lithuanian < Latin
|
|
250
|
+
layout_name 'Lithuanian-QWERTY'
|
|
251
|
+
languages %w[lt lt-LT]
|
|
252
|
+
base_grid :qwerty
|
|
253
|
+
end
|
|
254
|
+
|
|
255
|
+
# Latvian: US QWERTY physical layout; ā č ē ģ ī ķ ļ ņ š ū ž
|
|
256
|
+
# are dead-key or AltGr sequences (plan 83 batch 2 eval
|
|
257
|
+
# mapping).
|
|
258
|
+
class Latvian < Latin
|
|
259
|
+
layout_name 'Latvian-QWERTY'
|
|
260
|
+
languages %w[lv lv-LV]
|
|
261
|
+
base_grid :qwerty
|
|
262
|
+
end
|
|
263
|
+
end
|
|
264
|
+
end
|
|
265
|
+
end
|
|
266
|
+
end
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Persian standard keyboard layout (ISIRI 9147).
|
|
7
|
+
#
|
|
8
|
+
# Shares the Arabic letter skeleton but carries the four Persian
|
|
9
|
+
# letters as real keys: پ چ ژ گ replace their Arabic equivalents
|
|
10
|
+
# at standard positions, and ک ی are the Persian keheh/yeh
|
|
11
|
+
# keycaps. The ZWNJ and diacritics are dead keys and stay out of
|
|
12
|
+
# the grid; the Arabic→Persian letter slips (ك→ک ي→ی) are
|
|
13
|
+
# handled at the normalizer level.
|
|
14
|
+
#
|
|
15
|
+
# The key grid is mirrored from the models repo eval harness
|
|
16
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _FA_STD, plan 83
|
|
17
|
+
# batch 2 of the model coverage expansion, verified there
|
|
18
|
+
# against ISIRI 9147 renderings) so typo-adjacency used for
|
|
19
|
+
# suggestion ranking matches the adjacency used to evaluate the
|
|
20
|
+
# models. spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb
|
|
21
|
+
# enforces the sync.
|
|
22
|
+
#
|
|
23
|
+
# Languages: fa, fa-IR
|
|
24
|
+
class PersianStandard < Layout
|
|
25
|
+
# Key positions for the Persian standard layout.
|
|
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], '-' => [0, 11],
|
|
32
|
+
'=' => [0, 12],
|
|
33
|
+
# Top row (ض ص ث ق ف غ ع ه خ ح ج چ)
|
|
34
|
+
'ض' => [1, 0], 'ص' => [1, 1], 'ث' => [1, 2], 'ق' => [1, 3],
|
|
35
|
+
'ف' => [1, 4], 'غ' => [1, 5], 'ع' => [1, 6], 'ه' => [1, 7],
|
|
36
|
+
'خ' => [1, 8], 'ح' => [1, 9], 'ج' => [1, 10], 'چ' => [1, 11],
|
|
37
|
+
# Home row (ش س ی ب ل ا ت ن م ک گ)
|
|
38
|
+
'ش' => [2, 0], 'س' => [2, 1], 'ی' => [2, 2], 'ب' => [2, 3],
|
|
39
|
+
'ل' => [2, 4], 'ا' => [2, 5], 'ت' => [2, 6], 'ن' => [2, 7],
|
|
40
|
+
'م' => [2, 8], 'ک' => [2, 9], 'گ' => [2, 10],
|
|
41
|
+
# Bottom row (ظ ط ز ر ذ د پ و ۀ .)
|
|
42
|
+
'ظ' => [3, 0], 'ط' => [3, 1], 'ز' => [3, 2], 'ر' => [3, 3],
|
|
43
|
+
'ذ' => [3, 4], 'د' => [3, 5], 'پ' => [3, 6], 'و' => [3, 7],
|
|
44
|
+
'ۀ' => [3, 8], '.' => [3, 9]
|
|
45
|
+
}.freeze
|
|
46
|
+
|
|
47
|
+
# Initialize the Persian standard layout.
|
|
48
|
+
def initialize
|
|
49
|
+
super(
|
|
50
|
+
name: 'Persian-Standard',
|
|
51
|
+
language_codes: %w[fa fa-IR],
|
|
52
|
+
key_positions: KEY_POSITIONS
|
|
53
|
+
)
|
|
54
|
+
end
|
|
55
|
+
end
|
|
56
|
+
end
|
|
57
|
+
end
|
|
58
|
+
end
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# QWERTY keyboard layout
|
|
7
|
+
#
|
|
8
|
+
# Standard QWERTY layout used for:
|
|
9
|
+
# - English (en, en-US, en-GB, etc.)
|
|
10
|
+
# - Spanish (es)
|
|
11
|
+
# - Portuguese (pt, pt-BR, pt-PT)
|
|
12
|
+
# - United States (us)
|
|
13
|
+
#
|
|
14
|
+
# Key positions use [row, col] coordinates where:
|
|
15
|
+
# - row 0: number row (`1`2`3...)
|
|
16
|
+
# - row 1: top row (qwerty...)
|
|
17
|
+
# - row 2: home row (asdfg...)
|
|
18
|
+
# - row 3: bottom row (zxcvb...)
|
|
19
|
+
class QWERTY < Layout
|
|
20
|
+
# Key positions for QWERTY layout
|
|
21
|
+
# Each key maps to [row, column] coordinates
|
|
22
|
+
KEY_POSITIONS = {
|
|
23
|
+
# Number row
|
|
24
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
25
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
26
|
+
'0' => [0, 10], '-' => [0, 11], '=' => [0, 12],
|
|
27
|
+
# Top row (QWERTY)
|
|
28
|
+
'q' => [1, 0], 'w' => [1, 1], 'e' => [1, 2], 'r' => [1, 3], 't' => [1, 4],
|
|
29
|
+
'y' => [1, 5], 'u' => [1, 6], 'i' => [1, 7], 'o' => [1, 8], 'p' => [1, 9],
|
|
30
|
+
'[' => [1, 10], ']' => [1, 11], '\\' => [1, 12],
|
|
31
|
+
# Home row (ASDFG)
|
|
32
|
+
'a' => [2, 0], 's' => [2, 1], 'd' => [2, 2], 'f' => [2, 3], 'g' => [2, 4],
|
|
33
|
+
'h' => [2, 5], 'j' => [2, 6], 'k' => [2, 7], 'l' => [2, 8], ';' => [2, 9],
|
|
34
|
+
'\'' => [2, 10],
|
|
35
|
+
# Bottom row (ZXCVB)
|
|
36
|
+
'z' => [3, 0], 'x' => [3, 1], 'c' => [3, 2], 'v' => [3, 3], 'b' => [3, 4],
|
|
37
|
+
'n' => [3, 5], 'm' => [3, 6], ',' => [3, 7], '.' => [3, 8], '/' => [3, 9]
|
|
38
|
+
}.freeze
|
|
39
|
+
|
|
40
|
+
# Initialize QWERTY layout
|
|
41
|
+
def initialize
|
|
42
|
+
super(
|
|
43
|
+
name: 'QWERTY',
|
|
44
|
+
language_codes: %w[en es pt us en-US en-GB en-AU en-CA en-NZ en-ZA
|
|
45
|
+
es-ES es-MX pt-BR pt-PT],
|
|
46
|
+
key_positions: KEY_POSITIONS
|
|
47
|
+
)
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
end
|
|
52
|
+
end
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# QWERTZ keyboard layout
|
|
7
|
+
#
|
|
8
|
+
# Standard QWERTZ layout used for:
|
|
9
|
+
# - German (de, de-DE, de-AT, de-CH)
|
|
10
|
+
# - Austria (at)
|
|
11
|
+
# - Switzerland (ch)
|
|
12
|
+
#
|
|
13
|
+
# Key differences from QWERTY:
|
|
14
|
+
# - z and y are swapped (z/y → y/z)
|
|
15
|
+
# - Has umlaut keys: ä, ö, ü
|
|
16
|
+
# - Has ß key (Eszett)
|
|
17
|
+
#
|
|
18
|
+
# Key positions use [row, col] coordinates where:
|
|
19
|
+
# - row 0: number row (^°1"2...)
|
|
20
|
+
# - row 1: top row (qwertz...)
|
|
21
|
+
# - row 2: home row (asdfg...)
|
|
22
|
+
# - row 3: bottom row (yxcvb...) - note: y is here, not in top row
|
|
23
|
+
class QWERTZ < Layout
|
|
24
|
+
# Key positions for QWERTZ 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], '4' => [0, 4],
|
|
29
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
30
|
+
'0' => [0, 10], 'ß' => [0, 11], '´' => [0, 12],
|
|
31
|
+
# Top row (QWERTZ - note z and y are swapped)
|
|
32
|
+
'q' => [1, 0], 'w' => [1, 1], 'e' => [1, 2], 'r' => [1, 3], 't' => [1, 4],
|
|
33
|
+
'z' => [1, 5], 'u' => [1, 6], 'i' => [1, 7], 'o' => [1, 8], 'p' => [1, 9],
|
|
34
|
+
'ü' => [1, 10], '+' => [1, 11],
|
|
35
|
+
# Home row (ASDFG)
|
|
36
|
+
'a' => [2, 0], 's' => [2, 1], 'd' => [2, 2], 'f' => [2, 3], 'g' => [2, 4],
|
|
37
|
+
'h' => [2, 5], 'j' => [2, 6], 'k' => [2, 7], 'l' => [2, 8], 'ö' => [2, 9],
|
|
38
|
+
'ä' => [2, 10],
|
|
39
|
+
# Bottom row (YXCVB - note y is here)
|
|
40
|
+
'y' => [3, 0], 'x' => [3, 1], 'c' => [3, 2], 'v' => [3, 3], 'b' => [3, 4],
|
|
41
|
+
'n' => [3, 5], 'm' => [3, 6], ',' => [3, 7], '.' => [3, 8], '-' => [3, 9]
|
|
42
|
+
}.freeze
|
|
43
|
+
|
|
44
|
+
# Initialize QWERTZ layout
|
|
45
|
+
def initialize
|
|
46
|
+
super(
|
|
47
|
+
name: 'QWERTZ',
|
|
48
|
+
language_codes: %w[de at ch de-DE de-AT de-CH],
|
|
49
|
+
key_positions: KEY_POSITIONS
|
|
50
|
+
)
|
|
51
|
+
end
|
|
52
|
+
end
|
|
53
|
+
end
|
|
54
|
+
end
|
|
55
|
+
end
|
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Serbian Cyrillic keyboard layout (ЉЊЕРТЗУИОПШ /
|
|
7
|
+
# АСДФГХЈКЛЧЋ / ЏЦВБНМ, KBDSR driver table).
|
|
8
|
+
#
|
|
9
|
+
# The Serbian-specific letters љ њ ђ ћ џ ј are real keys: љ њ
|
|
10
|
+
# take the q/w faces, ђ sits where QWERTY carries the right
|
|
11
|
+
# bracket, and џ ц в б н м fill the bottom row. Serbian Latin
|
|
12
|
+
# (sr-Latn) types on the South-Slavic QWERTZ grid and is
|
|
13
|
+
# claimed by its own layout (Layouts::SerbianLatin, plan 110),
|
|
14
|
+
# not this one.
|
|
15
|
+
#
|
|
16
|
+
# The key grid is mirrored from the models repo eval harness
|
|
17
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _SR_CYR, plan 83
|
|
18
|
+
# batch 2 of the model coverage expansion) so typo-adjacency
|
|
19
|
+
# used for suggestion ranking matches the adjacency used to
|
|
20
|
+
# evaluate the models.
|
|
21
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
22
|
+
# the sync.
|
|
23
|
+
#
|
|
24
|
+
# Languages: sr, sr-RS
|
|
25
|
+
class SerbianCyrillic < Layout
|
|
26
|
+
# Key positions for the Serbian Cyrillic layout.
|
|
27
|
+
# Each key maps to [row, column] coordinates.
|
|
28
|
+
KEY_POSITIONS = {
|
|
29
|
+
# Number row
|
|
30
|
+
'`' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3],
|
|
31
|
+
'4' => [0, 4], '5' => [0, 5], '6' => [0, 6], '7' => [0, 7],
|
|
32
|
+
'8' => [0, 8], '9' => [0, 9], '0' => [0, 10],
|
|
33
|
+
"'" => [0, 11], '+' => [0, 12],
|
|
34
|
+
# Top row (љ њ е р т з у и о п ш ђ)
|
|
35
|
+
'љ' => [1, 0], 'њ' => [1, 1], 'е' => [1, 2], 'р' => [1, 3],
|
|
36
|
+
'т' => [1, 4], 'з' => [1, 5], 'у' => [1, 6], 'и' => [1, 7],
|
|
37
|
+
'о' => [1, 8], 'п' => [1, 9], 'ш' => [1, 10], 'ђ' => [1, 11],
|
|
38
|
+
# Home row (а с д ф г х ј к л ч ћ ж)
|
|
39
|
+
'а' => [2, 0], 'с' => [2, 1], 'д' => [2, 2], 'ф' => [2, 3],
|
|
40
|
+
'г' => [2, 4], 'х' => [2, 5], 'ј' => [2, 6], 'к' => [2, 7],
|
|
41
|
+
'л' => [2, 8], 'ч' => [2, 9], 'ћ' => [2, 10], 'ж' => [2, 11],
|
|
42
|
+
# Bottom row (џ ц в б н м , . -)
|
|
43
|
+
'џ' => [3, 0], 'ц' => [3, 1], 'в' => [3, 2], 'б' => [3, 3],
|
|
44
|
+
'н' => [3, 4], 'м' => [3, 5], ',' => [3, 6], '.' => [3, 7],
|
|
45
|
+
'-' => [3, 8]
|
|
46
|
+
}.freeze
|
|
47
|
+
|
|
48
|
+
# Initialize the Serbian Cyrillic layout.
|
|
49
|
+
def initialize
|
|
50
|
+
super(
|
|
51
|
+
name: 'Serbian-Cyrillic',
|
|
52
|
+
language_codes: %w[sr sr-RS],
|
|
53
|
+
key_positions: KEY_POSITIONS
|
|
54
|
+
)
|
|
55
|
+
end
|
|
56
|
+
end
|
|
57
|
+
end
|
|
58
|
+
end
|
|
59
|
+
end
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Turkish-Q keyboard layout (standard Turkish physical layout).
|
|
7
|
+
#
|
|
8
|
+
# The Turkish-specific letters ı ğ ü ş i ö ç are real keys:
|
|
9
|
+
# ı sits where i is on QWERTY, i replaces the semicolon key, and
|
|
10
|
+
# ğ ü ş ö ç replace the bracket/apostrophe/slash family.
|
|
11
|
+
#
|
|
12
|
+
# The key grid is mirrored from the models repo eval harness
|
|
13
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _TR_Q, wave 1 of the
|
|
14
|
+
# model coverage expansion) so typo-adjacency used for suggestion
|
|
15
|
+
# ranking matches the adjacency used to evaluate the models.
|
|
16
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
17
|
+
# the sync.
|
|
18
|
+
#
|
|
19
|
+
# Languages: tr, tr-TR
|
|
20
|
+
class TurkishQ < Layout
|
|
21
|
+
# Key positions for the Turkish-Q layout.
|
|
22
|
+
# Each key maps to [row, column] coordinates.
|
|
23
|
+
KEY_POSITIONS = {
|
|
24
|
+
# Number row
|
|
25
|
+
'"' => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
26
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
27
|
+
'0' => [0, 10], '*' => [0, 11], '-' => [0, 12],
|
|
28
|
+
# Top row (QWERTY + ı ğ ü)
|
|
29
|
+
'q' => [1, 0], 'w' => [1, 1], 'e' => [1, 2], 'r' => [1, 3], 't' => [1, 4],
|
|
30
|
+
'y' => [1, 5], 'u' => [1, 6], 'ı' => [1, 7], 'o' => [1, 8], 'p' => [1, 9],
|
|
31
|
+
'ğ' => [1, 10], 'ü' => [1, 11],
|
|
32
|
+
# Home row (ASDFG + ş i)
|
|
33
|
+
'a' => [2, 0], 's' => [2, 1], 'd' => [2, 2], 'f' => [2, 3], 'g' => [2, 4],
|
|
34
|
+
'h' => [2, 5], 'j' => [2, 6], 'k' => [2, 7], 'l' => [2, 8], 'ş' => [2, 9],
|
|
35
|
+
'i' => [2, 10],
|
|
36
|
+
# Bottom row (ZXCVB + ö ç)
|
|
37
|
+
'z' => [3, 0], 'x' => [3, 1], 'c' => [3, 2], 'v' => [3, 3], 'b' => [3, 4],
|
|
38
|
+
'n' => [3, 5], 'm' => [3, 6], 'ö' => [3, 7], 'ç' => [3, 8], '.' => [3, 9]
|
|
39
|
+
}.freeze
|
|
40
|
+
|
|
41
|
+
# Initialize the Turkish-Q layout.
|
|
42
|
+
def initialize
|
|
43
|
+
super(
|
|
44
|
+
name: 'Turkish-Q',
|
|
45
|
+
language_codes: %w[tr tr-TR],
|
|
46
|
+
key_positions: KEY_POSITIONS
|
|
47
|
+
)
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
end
|
|
52
|
+
end
|
|
@@ -0,0 +1,51 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Kotoshu
|
|
4
|
+
module Keyboard
|
|
5
|
+
module Layouts
|
|
6
|
+
# Ukrainian JCUKEN keyboard layout (standard Ukrainian layout).
|
|
7
|
+
#
|
|
8
|
+
# Extends the Russian JCUKEN grid with the Ukrainian-only keys:
|
|
9
|
+
# і replaces ы, ї replaces ъ, є replaces э, and ґ sits right of х.
|
|
10
|
+
# The Russian-only ы ъ э ё keys do not exist on the Ukrainian grid.
|
|
11
|
+
#
|
|
12
|
+
# The key grid is mirrored from the models repo eval harness
|
|
13
|
+
# (kotoshu/models-fasttext-onnx eval/noise.py _UK_JCUKEN, wave 1
|
|
14
|
+
# of the model coverage expansion). The drift spec
|
|
15
|
+
# spec/kotoshu/keyboard/layouts/eval_grid_drift_spec.rb enforces
|
|
16
|
+
# the sync.
|
|
17
|
+
#
|
|
18
|
+
# Languages: uk, uk-UA
|
|
19
|
+
class Ukrainian < Layout
|
|
20
|
+
# Key positions for the Ukrainian JCUKEN layout.
|
|
21
|
+
# Each key maps to [row, column] coordinates.
|
|
22
|
+
KEY_POSITIONS = {
|
|
23
|
+
# Number row
|
|
24
|
+
"'" => [0, 0], '1' => [0, 1], '2' => [0, 2], '3' => [0, 3], '4' => [0, 4],
|
|
25
|
+
'5' => [0, 5], '6' => [0, 6], '7' => [0, 7], '8' => [0, 8], '9' => [0, 9],
|
|
26
|
+
'0' => [0, 10], '-' => [0, 11], '=' => [0, 12],
|
|
27
|
+
# Top row (ЙЦУКЕН + ї ґ)
|
|
28
|
+
'й' => [1, 0], 'ц' => [1, 1], 'у' => [1, 2], 'к' => [1, 3], 'е' => [1, 4],
|
|
29
|
+
'н' => [1, 5], 'г' => [1, 6], 'ш' => [1, 7], 'щ' => [1, 8], 'з' => [1, 9],
|
|
30
|
+
'х' => [1, 10], 'ї' => [1, 11], 'ґ' => [1, 12],
|
|
31
|
+
# Home row (ФІВАПР + є)
|
|
32
|
+
'ф' => [2, 0], 'і' => [2, 1], 'в' => [2, 2], 'а' => [2, 3], 'п' => [2, 4],
|
|
33
|
+
'р' => [2, 5], 'о' => [2, 6], 'л' => [2, 7], 'д' => [2, 8], 'ж' => [2, 9],
|
|
34
|
+
'є' => [2, 10],
|
|
35
|
+
# Bottom row (ЯЧСМИТ + ь б ю)
|
|
36
|
+
'я' => [3, 0], 'ч' => [3, 1], 'с' => [3, 2], 'м' => [3, 3], 'и' => [3, 4],
|
|
37
|
+
'т' => [3, 5], 'ь' => [3, 6], 'б' => [3, 7], 'ю' => [3, 8], '.' => [3, 9]
|
|
38
|
+
}.freeze
|
|
39
|
+
|
|
40
|
+
# Initialize the Ukrainian JCUKEN layout.
|
|
41
|
+
def initialize
|
|
42
|
+
super(
|
|
43
|
+
name: 'Ukrainian-JCUKEN',
|
|
44
|
+
language_codes: %w[uk uk-UA],
|
|
45
|
+
key_positions: KEY_POSITIONS
|
|
46
|
+
)
|
|
47
|
+
end
|
|
48
|
+
end
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
end
|