spaCy/spacy/lang/ca/__init__.py
Adriane Boyd b98d216205
Update Catalan language data (#8308)
* Update Catalan language data

Update Catalan language data based on contributions from the Text Mining
Unit at the Barcelona Supercomputing Center:

https://github.com/TeMU-BSC/spacy4release/tree/main/lang_data

* Update tokenizer settings for UD Catalan AnCora

Update for UD Catalan AnCora v2.7 with merged multi-word tokens.

* Update test

* Move prefix patternt to more generic infix pattern

* Clean up
2021-06-11 10:21:22 +02:00

41 lines
1.1 KiB
Python

from typing import Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
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
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},
default_score_weights={"lemma_acc": 1.0},
)
def make_lemmatizer(
nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
):
return CatalanLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
__all__ = ["Catalan"]