spaCy/spacy/lang/sr/__init__.py
Pavle Vidanović d03401f532 Lemmatizer lookup dictionary for Serbian and basic tag set adde… (#4251)
* Serbian stopwords added. (cyrillic alphabet)

* spaCy Contribution agreement included.

* Test initialize updated

* Serbian language code update. --bugfix

* Tokenizer exceptions added. Init file updated.

* Norm exceptions and lexical attributes added.

* Examples added.

* Tests added.

* sr_lang examples update.

* Tokenizer exceptions updated. (Serbian)

* Lemmatizer created. Licence included.

* Test updated.

* Tag map basic added.

* tag_map.py file removed since it uses default spacy tags.
2019-09-08 14:19:15 +02:00

33 lines
1002 B
Python

# coding: utf8
from __future__ import unicode_literals
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
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 SerbianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: "sr"
lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS
)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
resources = {"lemma_lookup": "lemma_lookup.json"}
class Serbian(Language):
lang = "sr"
Defaults = SerbianDefaults
__all__ = ["Serbian"]