explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 04:10:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix import cycles as a result of import sorting

Browse Source
This commit is contained in:
Daniël de Kok 2023-06-13 09:57:37 +02:00
parent 8e4cfc8e56
commit 866d57342a
3 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/tokens/_serialize.py
View File

@ -13,12 +13,9 @@ from ..errors import Errors
from ..util import SimpleFrozenList, ensure_path
from ..vocab import Vocab
from ._dict_proxies import SpanGroups
from .doc import DOCBIN_ALL_ATTRS as ALL_ATTRS
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:
"""Pack Doc objects for binary serialization.

8
spacy/tokens/doc.pyx
View File

@ -52,12 +52,18 @@ from ..errors import Errors, Warnings
from ..morphology import Morphology
from ..util import get_words_and_spaces
from ._retokenize import Retokenizer
from ._serialize import ALL_ATTRS as DOCBIN_ALL_ATTRS
from .underscore import Underscore, get_ext_args
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:
if (i + padding) < 0:
raise IndexError(Errors.E026.format(i=i, length=length))

8
spacy/training/callbacks.py
View File

@ -1,15 +1,17 @@
from typing import Callable, Optional
from typing import TYPE_CHECKING, Callable, Optional
from ..errors import Errors
from ..language import Language
from ..util import load_model, logger, registry
if TYPE_CHECKING:
from ..language import Language
@registry.callbacks("spacy.copy_from_base_model.v1")
def create_copy_from_base_model(
tokenizer: Optional[str] = None,
vocab: Optional[str] = None,
) -> Callable[[Language], Language]:
) -> Callable[["Language"], "Language"]:
def copy_from_base_model(nlp):
if tokenizer:
logger.info("Copying tokenizer from: %s", tokenizer)