spaCy/spacy/lang/it/__init__.py
Sofie 9a478b6db8 Clean up of char classes, few tokenizer fixes and faster default French tokenizer (#3293)
* splitting up latin unicode interval

* removing hyphen as infix for French

* adding failing test for issue 1235

* test for issue #3002 which now works

* partial fix for issue #2070

* keep the hyphen as infix for French (as it was)

* restore french expressions with hyphen as infix (as it was)

* added succeeding unit test for Issue #2656

* Fix issue #2822 with custom Italian exception

* Fix issue #2926 by allowing numbers right before infix /

* splitting up latin unicode interval

* removing hyphen as infix for French

* adding failing test for issue 1235

* test for issue #3002 which now works

* partial fix for issue #2070

* keep the hyphen as infix for French (as it was)

* restore french expressions with hyphen as infix (as it was)

* added succeeding unit test for Issue #2656

* Fix issue #2822 with custom Italian exception

* Fix issue #2926 by allowing numbers right before infix /

* remove duplicate

* remove xfail for Issue #2179 fixed by Matt

* adjust documentation and remove reference to regex lib
2019-02-20 22:10:13 +01:00

37 lines
999 B
Python

# coding: utf8
from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from .tag_map import TAG_MAP
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
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 .punctuation import TOKENIZER_INFIXES
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
lemma_lookup = LOOKUP
tag_map = TAG_MAP
infixes = TOKENIZER_INFIXES
class Italian(Language):
lang = "it"
Defaults = ItalianDefaults
__all__ = ["Italian"]