spaCy/spacy/lang/lt/__init__.py

48 lines
1.3 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
2019-07-08 08:25:22 +00:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
2019-07-08 08:25:22 +00:00
from .lex_attrs import LEX_ATTRS
from .tag_map import TAG_MAP
from .morph_rules import MORPH_RULES
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
2019-07-08 08:25:22 +00:00
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2019-07-08 08:25:22 +00:00
def _return_lt(_):
return "lt"
class LithuanianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
2019-07-08 08:25:22 +00:00
lex_attr_getters[LANG] = _return_lt
lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
)
lex_attr_getters.update(LEX_ATTRS)
infixes = TOKENIZER_INFIXES
suffixes = TOKENIZER_SUFFIXES
2020-03-25 11:28:12 +00:00
mod_base_exceptions = {
exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")
}
del mod_base_exceptions["8)"]
tokenizer_exceptions = update_exc(mod_base_exceptions, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
2019-07-08 08:25:22 +00:00
tag_map = TAG_MAP
morph_rules = MORPH_RULES
class Lithuanian(Language):
lang = "lt"
Defaults = LithuanianDefaults
__all__ = ["Lithuanian"]