Method component

spacy/language.py:556–622

Register a new pipeline component. Can be used for stateless function components that don't require a separate factory. Can be used as a decorator on a function or classmethod, or called as a function with the factory provided as the func keyword argument. To create a compone

(
        cls,
        name: str,
        *,
        assigns: Iterable[str] = SimpleFrozenList(),
        requires: Iterable[str] = SimpleFrozenList(),
        retokenizes: bool = False,
        func: Optional[PipeCallable] = None,
    )

    @classmethod
    def component(
        cls,
        name: str,
        *,
        assigns: Iterable[str] = SimpleFrozenList(),
        requires: Iterable[str] = SimpleFrozenList(),
        retokenizes: bool = False,
        func: Optional[PipeCallable] = None,
    ) -> Callable[..., Any]:
        """Register a new pipeline component. Can be used for stateless function
        components that don't require a separate factory. Can be used as a
        decorator on a function or classmethod, or called as a function with the
        factory provided as the func keyword argument. To create a component and
        add it to the pipeline, you can use nlp.add_pipe(name).

        name (str): The name of the component factory.
        assigns (Iterable[str]): Doc/Token attributes assigned by this component,
            e.g. "token.ent_id". Used for pipeline analysis.
        requires (Iterable[str]): Doc/Token attributes required by this component,
            e.g. "token.ent_id". Used for pipeline analysis.
        retokenizes (bool): Whether the component changes the tokenization.
            Used for pipeline analysis.
        func (Optional[Callable[[Doc], Doc]): Factory function if not used as a decorator.

        DOCS: https://spacy.io/api/language#component
        """
        if name is not None:
            if not isinstance(name, str):
                raise ValueError(Errors.E963.format(decorator="component"))
            if "." in name:
                raise ValueError(Errors.E853.format(name=name))
        component_name = name if name is not None else util.get_object_name(func)

        def add_component(component_func: PipeCallable) -> Callable:
            if isinstance(func, type):  # function is a class
                raise ValueError(Errors.E965.format(name=component_name))

            def factory_func(nlp, name: str) -> PipeCallable:
                return component_func

            internal_name = cls.get_factory_name(name)
            if internal_name in registry.factories:
                # We only check for the internal name here – it's okay if it's a
                # subclass and the base class has a factory of the same name. We
                # also only raise if the function is different to prevent raising
                # if module is reloaded. It's hacky, but we need to check the
                # existing functure for a closure and whether that's identical
                # to the component function (because factory_func created above
                # will always be different, even for the same function)
                existing_func = registry.factories.get(internal_name)
                closure = existing_func.__closure__
                wrapped = [c.cell_contents for c in closure][0] if closure else None
                if util.is_same_func(wrapped, component_func):
                    factory_func = existing_func  # noqa: F811

            cls.factory(
                component_name,
                assigns=assigns,