mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
35 lines
841 B
Python
35 lines
841 B
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
from ...language import Language
|
|
from ...util import load_config_from_str
|
|
|
|
|
|
DEFAULT_CONFIG = """
|
|
[initialize]
|
|
|
|
[initialize.lookups]
|
|
@misc = "spacy.LookupsDataLoader.v1"
|
|
lang = ${nlp.lang}
|
|
tables = ["lexeme_norm"]
|
|
"""
|
|
|
|
|
|
class GermanDefaults(Language.Defaults):
|
|
config = load_config_from_str(DEFAULT_CONFIG)
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class German(Language):
|
|
lang = "de"
|
|
Defaults = GermanDefaults
|
|
|
|
|
|
__all__ = ["German"]
|