mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
62 lines
1.4 KiB
Python
62 lines
1.4 KiB
Python
from typing import Set, Dict, Callable, Any
|
|
from thinc.api import Config
|
|
|
|
from ...language import Language
|
|
from ...util import registry
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
|
from .syntax_iterators import noun_chunks
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
[nlp]
|
|
lang = "fa"
|
|
stop_words = {"@language_data": "spacy.fa.stop_words"}
|
|
lex_attr_getters = {"@language_data": "spacy.fa.lex_attr_getters"}
|
|
get_noun_chunks = {"@language_data": "spacy.de.get_noun_chunks"}
|
|
|
|
[nlp.writing_system]
|
|
direction = "rtl"
|
|
has_case = false
|
|
has_letters = true
|
|
|
|
[nlp.lemmatizer]
|
|
@lemmatizers = "spacy.Lemmatizer.v1"
|
|
|
|
[nlp.lemmatizer.data]
|
|
@language_data = "spacy-lookups-data"
|
|
lang = ${nlp:lang}
|
|
tables = ["lemma_rules", "lemma_index", "lemma_exc"]
|
|
"""
|
|
|
|
|
|
@registry.language_data("spacy.fa.stop_words")
|
|
def stop_words() -> Set[str]:
|
|
return STOP_WORDS
|
|
|
|
|
|
@registry.language_data("spacy.fa.lex_attr_getters")
|
|
def lex_attr_getters() -> Dict[int, Callable[[str], Any]]:
|
|
return LEX_ATTRS
|
|
|
|
|
|
@registry.language_data("spacy.fa.get_noun_chunks")
|
|
def get_noun_chunks() -> Callable:
|
|
return noun_chunks
|
|
|
|
|
|
class PersianDefaults(Language.Defaults):
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
|
|
|
|
class Persian(Language):
|
|
lang = "fa"
|
|
Defaults = PersianDefaults
|
|
default_config = Config().from_str(DEFAULT_CONFIG)
|
|
|
|
|
|
__all__ = ["Persian"]
|