Method __init__

spacy/language.py:156–226

Initialise a Language object. vocab (Vocab): A `Vocab` object. If `True`, a vocab is created. meta (dict): Custom meta data for the Language class. Is written to by models to add model meta data. max_length (int): Maximum number of characters in a single text. Th

(
        self,
        vocab: Union[Vocab, bool] = True,
        *,
        max_length: int = 10**6,
        meta: Dict[str, Any] = {},
        create_tokenizer: Optional[Callable[["Language"], Callable[[str], Doc]]] = None,
        create_vectors: Optional[Callable[["Vocab"], BaseVectors]] = None,
        batch_size: int = 1000,
        **kwargs,
    )

    _factory_meta: Dict[str, "FactoryMeta"] = {}  # meta by factory

    def __init__(
        self,
        vocab: Union[Vocab, bool] = True,
        *,
        max_length: int = 10**6,
        meta: Dict[str, Any] = {},
        create_tokenizer: Optional[Callable[["Language"], Callable[[str], Doc]]] = None,
        create_vectors: Optional[Callable[["Vocab"], BaseVectors]] = None,
        batch_size: int = 1000,
        **kwargs,
    ) -> None:
        """Initialise a Language object.

        vocab (Vocab): A `Vocab` object. If `True`, a vocab is created.
        meta (dict): Custom meta data for the Language class. Is written to by
            models to add model meta data.
        max_length (int): Maximum number of characters in a single text. The
            current models may run out memory on extremely long texts, due to
            large internal allocations. You should segment these texts into
            meaningful units, e.g. paragraphs, subsections etc, before passing
            them to spaCy. Default maximum length is 1,000,000 charas (1mb). As
            a rule of thumb, if all pipeline components are enabled, spaCy's
            default models currently requires roughly 1GB of temporary memory per
            100,000 characters in one text.
        create_tokenizer (Callable): Function that takes the nlp object and
            returns a tokenizer.
        batch_size (int): Default batch size for pipe and evaluate.

        DOCS: https://spacy.io/api/language#init
        """
        from .pipeline.factories import register_factories

        register_factories()
        # We're only calling this to import all factories provided via entry
        # points. The factory decorator applied to these functions takes care
        # of the rest.
        util.registry._entry_point_factories.get_all()

        self._config = DEFAULT_CONFIG.merge(self.default_config)
        self._meta = dict(meta)
        self._path = None
        self._optimizer: Optional[Optimizer] = None
        # Component meta and configs are only needed on the instance
        self._pipe_meta: Dict[str, "FactoryMeta"] = {}  # meta by component
        self._pipe_configs: Dict[str, Config] = {}  # config by component

        if not isinstance(vocab, Vocab) and vocab is not True:
            raise ValueError(Errors.E918.format(vocab=vocab, vocab_type=type(Vocab)))
        if vocab is True:
            vectors_name = meta.get("vectors", {}).get("name")
            vocab = create_vocab(self.lang, self.Defaults, vectors_name=vectors_name)
            if not create_vectors:
                vectors_cfg = {"vectors": self._config["nlp"]["vectors"]}
                create_vectors = registry.resolve(vectors_cfg)["vectors"]
            vocab.vectors = create_vectors(vocab)
        else:
            if (self.lang and vocab.lang) and (self.lang != vocab.lang):
                raise ValueError(Errors.E150.format(nlp=self.lang, vocab=vocab.lang))