{"id":24668,"library":"sudachidict-small","title":"SudachiDict (Small Edition) for SudachiPy","description":"A small-sized dictionary for use with SudachiPy, the Japanese morphological analyzer. This package provides the dictionary core required by sudachipy to perform tokenization and part-of-speech tagging. Current version 20260428 is regularly updated (monthly) with neologisms and synonyms. It is the recommended dictionary for most use cases, balancing coverage and performance.","status":"active","version":"20260428","language":"python","source_language":"en","source_url":"https://github.com/WorksApplications/SudachiDict","tags":["japanese","tokenization","morphological-analysis","nlp"],"install":[{"cmd":"pip install sudachidict-small","lang":"bash","label":"Install from PyPI"}],"dependencies":[{"reason":"This dictionary is a data package; sudachipy is required to use it.","package":"sudachipy","optional":false}],"imports":[{"note":"sudachidict-small is not imported directly; it is used automatically by sudachipy when set as dict_type.","wrong":"import sudachidict_small","symbol":"SudachiPy","correct":"from sudachipy import tokenizer\nfrom sudachipy import dictionary"}],"quickstart":{"code":"from sudachipy import tokenizer\nfrom sudachipy import dictionary\n\n# Instantiate tokenizer with the small dictionary\ntokenizer_obj = tokenizer.Tokenizer()\n# Or explicitly: tokenizer_obj = tokenizer.Tokenizer(dict_type='small')\nmorphemes = tokenizer_obj.tokenize('本日は晴天なり')\nfor m in morphemes:\n    print(f\"{m.surface()}\\t{m.part_of_speech()}\")","lang":"python","description":"Initialize SudachiPy tokenizer using the small dictionary and tokenize a sample sentence."},"warnings":[{"fix":"Use the new style: tokenizer.Tokenizer(dict_type='sudachidict-small') or omit (defaults to small).","message":"Removal of legacy dict_type names: 'small', 'core', 'full' used to be set directly; now they are replaced by package names (e.g., 'sudachidict-small'). If you set dict_type='small' in old code, it may break.","severity":"breaking","affected_versions":"<= 20230807"},{"fix":"Always use sudachipy to access the dictionary. The package is automatically loaded by sudachipy based on dict_type.","message":"Do not import sudachidict_small directly. The dictionary package only contains data files; importing it yields no useful symbols and may cause confusion.","severity":"gotcha","affected_versions":"all"}],"env_vars":null,"last_verified":"2026-05-01T00:00:00.000Z","next_check":"2026-07-30T00:00:00.000Z","problems":[{"fix":"Do not import from sudachidict_small. Instead, import from sudachipy and specify dict_type='small'.","cause":"Trying to import a class from the dictionary package, which does not expose Python symbols.","error":"ImportError: cannot import name 'Small' from 'sudachidict_small'"},{"fix":"Uninstall the extra dictionary: pip uninstall sudachidict-core (or use distinct dict_type names).","cause":"Having both sudachidict-small and sudachidict-core installed simultaneously with the same dict_type name.","error":"sudachipy.errors.MultipleDictionaryError: multiple dictionaries found for 'small'"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"install_tag":null,"quickstart_score":null,"quickstart_tag":null}