mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
30d31fd335
* pymorph2 issues #11620, #11626, #11625: - #11620: pymorphy2_lookup - #11626: handle multiple forms pointing to the same normal form + handling empty POS tag - #11625: matching DET that are labelled as PRON by pymorhp2 * Move lemmatizer algorithm changes back into RussianLemmatizer * Fix uk pymorphy3_lookup mode init * Move and update tests for ru/uk lookup lemmatizer modes * Fix typo * Remove traces of previous behavior for uninflected POS * Refactor to private generic-looking pymorphy methods * Remove xfailed uk lemmatizer cases * Update spacy/lang/ru/lemmatizer.py Co-authored-by: Richard Hudson <richard@explosion.ai> Co-authored-by: Dmytro S Lituiev <d.lituiev@gmail.com> Co-authored-by: Richard Hudson <richard@explosion.ai>
46 lines
1.7 KiB
Python
46 lines
1.7 KiB
Python
from typing import Optional, Callable
|
|
|
|
from thinc.api import Model
|
|
|
|
from ..ru.lemmatizer import RussianLemmatizer
|
|
from ...pipeline.lemmatizer import lemmatizer_score
|
|
from ...vocab import Vocab
|
|
|
|
|
|
class UkrainianLemmatizer(RussianLemmatizer):
|
|
def __init__(
|
|
self,
|
|
vocab: Vocab,
|
|
model: Optional[Model],
|
|
name: str = "lemmatizer",
|
|
*,
|
|
mode: str = "pymorphy3",
|
|
overwrite: bool = False,
|
|
scorer: Optional[Callable] = lemmatizer_score,
|
|
) -> None:
|
|
if mode in {"pymorphy2", "pymorphy2_lookup"}:
|
|
try:
|
|
from pymorphy2 import MorphAnalyzer
|
|
except ImportError:
|
|
raise ImportError(
|
|
"The Ukrainian lemmatizer mode 'pymorphy2' requires the "
|
|
"pymorphy2 library and dictionaries. Install them with: "
|
|
"pip install pymorphy2 pymorphy2-dicts-uk"
|
|
) from None
|
|
if getattr(self, "_morph", None) is None:
|
|
self._morph = MorphAnalyzer(lang="uk")
|
|
elif mode in {"pymorphy3", "pymorphy3_lookup"}:
|
|
try:
|
|
from pymorphy3 import MorphAnalyzer
|
|
except ImportError:
|
|
raise ImportError(
|
|
"The Ukrainian lemmatizer mode 'pymorphy3' requires the "
|
|
"pymorphy3 library and dictionaries. Install them with: "
|
|
"pip install pymorphy3 pymorphy3-dicts-uk"
|
|
) from None
|
|
if getattr(self, "_morph", None) is None:
|
|
self._morph = MorphAnalyzer(lang="uk")
|
|
super().__init__(
|
|
vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
|
|
)
|