mirror of
https://github.com/explosion/spaCy.git
synced 2025-08-04 04:10:20 +03:00
Fix import cycles as a result of import sorting
This commit is contained in:
parent
8e4cfc8e56
commit
866d57342a
|
@ -13,12 +13,9 @@ from ..errors import Errors
|
||||||
from ..util import SimpleFrozenList, ensure_path
|
from ..util import SimpleFrozenList, ensure_path
|
||||||
from ..vocab import Vocab
|
from ..vocab import Vocab
|
||||||
from ._dict_proxies import SpanGroups
|
from ._dict_proxies import SpanGroups
|
||||||
|
from .doc import DOCBIN_ALL_ATTRS as ALL_ATTRS
|
||||||
from .doc import Doc
|
from .doc import Doc
|
||||||
|
|
||||||
# fmt: off
|
|
||||||
ALL_ATTRS = ("ORTH", "NORM", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "ENT_KB_ID", "ENT_ID", "LEMMA", "MORPH", "POS", "SENT_START")
|
|
||||||
# fmt: on
|
|
||||||
|
|
||||||
|
|
||||||
class DocBin:
|
class DocBin:
|
||||||
"""Pack Doc objects for binary serialization.
|
"""Pack Doc objects for binary serialization.
|
||||||
|
|
|
@ -52,12 +52,18 @@ from ..errors import Errors, Warnings
|
||||||
from ..morphology import Morphology
|
from ..morphology import Morphology
|
||||||
from ..util import get_words_and_spaces
|
from ..util import get_words_and_spaces
|
||||||
from ._retokenize import Retokenizer
|
from ._retokenize import Retokenizer
|
||||||
from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
|
|
||||||
from .underscore import Underscore, get_ext_args
|
from .underscore import Underscore, get_ext_args
|
||||||
|
|
||||||
DEF PADDING = 5
|
DEF PADDING = 5
|
||||||
|
|
||||||
|
|
||||||
|
# We store the docbin attrs here rather than in _serialize to avoid
|
||||||
|
# import cycles.
|
||||||
|
|
||||||
|
# fmt: off
|
||||||
|
DOCBIN_ALL_ATTRS = ("ORTH", "NORM", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "ENT_KB_ID", "ENT_ID", "LEMMA", "MORPH", "POS", "SENT_START")
|
||||||
|
# fmt: on
|
||||||
|
|
||||||
cdef int bounds_check(int i, int length, int padding) except -1:
|
cdef int bounds_check(int i, int length, int padding) except -1:
|
||||||
if (i + padding) < 0:
|
if (i + padding) < 0:
|
||||||
raise IndexError(Errors.E026.format(i=i, length=length))
|
raise IndexError(Errors.E026.format(i=i, length=length))
|
||||||
|
|
|
@ -1,15 +1,17 @@
|
||||||
from typing import Callable, Optional
|
from typing import TYPE_CHECKING, Callable, Optional
|
||||||
|
|
||||||
from ..errors import Errors
|
from ..errors import Errors
|
||||||
from ..language import Language
|
|
||||||
from ..util import load_model, logger, registry
|
from ..util import load_model, logger, registry
|
||||||
|
|
||||||
|
if TYPE_CHECKING:
|
||||||
|
from ..language import Language
|
||||||
|
|
||||||
|
|
||||||
@registry.callbacks("spacy.copy_from_base_model.v1")
|
@registry.callbacks("spacy.copy_from_base_model.v1")
|
||||||
def create_copy_from_base_model(
|
def create_copy_from_base_model(
|
||||||
tokenizer: Optional[str] = None,
|
tokenizer: Optional[str] = None,
|
||||||
vocab: Optional[str] = None,
|
vocab: Optional[str] = None,
|
||||||
) -> Callable[[Language], Language]:
|
) -> Callable[["Language"], "Language"]:
|
||||||
def copy_from_base_model(nlp):
|
def copy_from_base_model(nlp):
|
||||||
if tokenizer:
|
if tokenizer:
|
||||||
logger.info("Copying tokenizer from: %s", tokenizer)
|
logger.info("Copying tokenizer from: %s", tokenizer)
|
||||||
|
|
Loading…
Reference in New Issue
Block a user