mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
d83e3c44c5
* Remove corpus-specific morph rules * Add options similar to tag maps to provide them in the `train` and `debug-data` CLIs
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
# Punctuation stolen from Danish
|
|
from ..da.punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
|
|
|
|
class SwedishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "sv"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
stop_words = STOP_WORDS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
|
|
class Swedish(Language):
|
|
lang = "sv"
|
|
Defaults = SwedishDefaults
|
|
|
|
|
|
__all__ = ["Swedish"]
|