mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-15 14:17:58 +03:00
fe5f5d6ac6
* Update Makefile For more recent python version * updated for bsc changes New tokenization changes * Update test_text.py * updating tests and requirements * changed failed test in test/lang/ca changed failed test in test/lang/ca * Update .gitignore deleted stashed changes line * back to python 3.6 and remove transformer requirements As per request * Update test_exception.py Change the test * Update test_exception.py Remove test print * Update Makefile For more recent python version * updated for bsc changes New tokenization changes * updating tests and requirements * Update requirements.txt Removed spacy-transfromers from requirements * Update test_exception.py Added final punctuation to ensure consistency * Update Makefile Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Format * Update test to check all tokens Co-authored-by: cayorodriguez <crodriguezp@gmail.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
54 lines
1.3 KiB
Python
Executable File
54 lines
1.3 KiB
Python
Executable File
from typing import Optional, Callable
|
|
|
|
from thinc.api import Model
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
from ...language import Language
|
|
from .lemmatizer import CatalanLemmatizer
|
|
|
|
|
|
class CatalanDefaults(Language.Defaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
prefixes = TOKENIZER_PREFIXES
|
|
stop_words = STOP_WORDS
|
|
lex_attr_getters = LEX_ATTRS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
class Catalan(Language):
|
|
lang = "ca"
|
|
Defaults = CatalanDefaults
|
|
|
|
|
|
@Catalan.factory(
|
|
"lemmatizer",
|
|
assigns=["token.lemma"],
|
|
default_config={
|
|
"model": None,
|
|
"mode": "rule",
|
|
"overwrite": False,
|
|
"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
|
|
},
|
|
default_score_weights={"lemma_acc": 1.0},
|
|
)
|
|
def make_lemmatizer(
|
|
nlp: Language,
|
|
model: Optional[Model],
|
|
name: str,
|
|
mode: str,
|
|
overwrite: bool,
|
|
scorer: Optional[Callable],
|
|
):
|
|
return CatalanLemmatizer(
|
|
nlp.vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
|
|
)
|
|
|
|
|
|
__all__ = ["Catalan"]
|