mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
cf52510631
* Add Amharic to space * clean up * Add some PRON_LEMMA * add Tigrinya support * remove text_noun_chunks * Tigrinya Support * added some more details for ti * fix unit test * add amharic char range * changes from review * amharic and tigrinya share same unicode block * get rid of _amharic/_tigrinya in char_classes Co-authored-by: Josiah Solomon <jsolomon@meteorcomm.com>
35 lines
1.0 KiB
Python
35 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_SUFFIXES
|
|
|
|
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
|
|
|
|
|
|
class AmharicDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "am"
|
|
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
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
writing_system = {"direction": "ltr", "has_case": False, "has_letters": True}
|
|
|
|
|
|
class Amharic(Language):
|
|
lang = "am"
|
|
Defaults = AmharicDefaults
|
|
|
|
|
|
__all__ = ["Amharic"]
|