mirror of
https://github.com/explosion/spaCy.git
synced 2025-06-28 17:03:04 +03:00
5bebbf7550
In order to support Python 3.13, we had to migrate to Cython 3.0. This caused some tricky interaction with our Pydantic usage, because Cython 3 uses the from __future__ import annotations semantics, which causes type annotations to be saved as strings. The end result is that we can't have Language.factory decorated functions in Cython modules anymore, as the Language.factory decorator expects to inspect the signature of the functions and build a Pydantic model. If the function is implemented in Cython, an error is raised because the type is not resolved. To address this I've moved the factory functions into a new module, spacy.pipeline.factories. I've added __getattr__ importlib hooks to the previous locations, in case anyone was importing these functions directly. The change should have no backwards compatibility implications. Along the way I've also refactored the registration of functions for the config. Previously these ran as import-time side-effects, using the registry decorator. I've created instead a new module spacy.registrations. When the registry is accessed it calls a function ensure_populated(), which cases the registrations to occur. I've made a similar change to the Language.factory registrations in the new spacy.pipeline.factories module. I want to remove these import-time side-effects so that we can speed up the loading time of the library, which can be especially painful on the CLI. I also find that I'm often working to track down the implementations of functions referenced by strings in the config. Having the registrations all happen in one place will make this easier. With these changes I've fortunately avoided the need to migrate to Pydantic v2 properly --- we're still using the v1 compatibility shim. We might not be able to hold out forever though: Pydantic (reasonably) aren't actively supporting the v1 shims. I put a lot of work into v2 migration when investigating the 3.13 support, and it's definitely challenging. In any case, it's a relief that we don't have to do the v2 migration at the same time as the Cython 3.0/Python 3.13 support.
81 lines
2.9 KiB
Python
81 lines
2.9 KiB
Python
import sys
|
|
from pathlib import Path
|
|
from typing import Any, Dict, Iterable, Union
|
|
|
|
# set library-specific custom warning handling before doing anything else
|
|
from .errors import setup_default_warnings
|
|
|
|
setup_default_warnings() # noqa: E402
|
|
|
|
# These are imported as part of the API
|
|
from thinc.api import Config, prefer_gpu, require_cpu, require_gpu # noqa: F401
|
|
|
|
from . import pipeline # noqa: F401
|
|
from . import util
|
|
from .about import __version__ # noqa: F401
|
|
from .cli.info import info # noqa: F401
|
|
from .errors import Errors
|
|
from .glossary import explain # noqa: F401
|
|
from .language import Language
|
|
from .registrations import REGISTRY_POPULATED, populate_registry
|
|
from .util import logger, registry # noqa: F401
|
|
from .vocab import Vocab
|
|
|
|
if sys.maxunicode == 65535:
|
|
raise SystemError(Errors.E130)
|
|
|
|
|
|
def load(
|
|
name: Union[str, Path],
|
|
*,
|
|
vocab: Union[Vocab, bool] = True,
|
|
disable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
|
|
enable: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
|
|
exclude: Union[str, Iterable[str]] = util._DEFAULT_EMPTY_PIPES,
|
|
config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
|
|
) -> Language:
|
|
"""Load a spaCy model from an installed package or a local path.
|
|
|
|
name (str): Package name or model path.
|
|
vocab (Vocab): A Vocab object. If True, a vocab is created.
|
|
disable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to disable. Disabled
|
|
pipes will be loaded but they won't be run unless you explicitly
|
|
enable them by calling nlp.enable_pipe.
|
|
enable (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to enable. All other
|
|
pipes will be disabled (but can be enabled later using nlp.enable_pipe).
|
|
exclude (Union[str, Iterable[str]]): Name(s) of pipeline component(s) to exclude. Excluded
|
|
components won't be loaded.
|
|
config (Dict[str, Any] / Config): Config overrides as nested dict or dict
|
|
keyed by section values in dot notation.
|
|
RETURNS (Language): The loaded nlp object.
|
|
"""
|
|
return util.load_model(
|
|
name,
|
|
vocab=vocab,
|
|
disable=disable,
|
|
enable=enable,
|
|
exclude=exclude,
|
|
config=config,
|
|
)
|
|
|
|
|
|
def blank(
|
|
name: str,
|
|
*,
|
|
vocab: Union[Vocab, bool] = True,
|
|
config: Union[Dict[str, Any], Config] = util.SimpleFrozenDict(),
|
|
meta: Dict[str, Any] = util.SimpleFrozenDict(),
|
|
) -> Language:
|
|
"""Create a blank nlp object for a given language code.
|
|
|
|
name (str): The language code, e.g. "en".
|
|
vocab (Vocab): A Vocab object. If True, a vocab is created.
|
|
config (Dict[str, Any] / Config): Optional config overrides.
|
|
meta (Dict[str, Any]): Overrides for nlp.meta.
|
|
RETURNS (Language): The nlp object.
|
|
"""
|
|
LangClass = util.get_lang_class(name)
|
|
# We should accept both dot notation and nested dict here for consistency
|
|
config = util.dot_to_dict(config)
|
|
return LangClass.from_config(config, vocab=vocab, meta=meta)
|