mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 20:28:20 +03:00
1a944e5976
Improve Italian tokenization for UD_Italian-ISDT.
35 lines
995 B
Python
35 lines
995 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .tag_map import TAG_MAP
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
|
|
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
|
|
|
|
|
|
class ItalianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "it"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
tag_map = TAG_MAP
|
|
prefixes = TOKENIZER_PREFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
|
|
class Italian(Language):
|
|
lang = "it"
|
|
Defaults = ItalianDefaults
|
|
|
|
|
|
__all__ = ["Italian"]
|