mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
b892b446cc
* Added the same punctuation rules as danish language. * Added abbreviations and also the possibility to have capitalized abbreviations on some. Added a few specific cases too * Added test for long texts in swedish * Added morph rules, infixes and suffixes to __init__.py for swedish * Added some tests for prefixes, infixes and suffixes * Added tests for lemma * Renamed files to follow convention * [sv] Removed ambigious abbreviations * Added more tests for tokenizer exceptions * Added test for problem with punctuation in issue #2578 * Contributor agreement * Removed faulty lemmatization of 'jag' ('I') as it was lemmatized to 'jaga' ('hunt')
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .morph_rules import MORPH_RULES
|
|
from .lemmatizer import LEMMA_RULES, LOOKUP
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
|
|
|
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 SwedishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'sv'
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
morph_rules = MORPH_RULES
|
|
infixes = TOKENIZER_INFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
stop_words = STOP_WORDS
|
|
lemma_rules = LEMMA_RULES
|
|
lemma_lookup = LOOKUP
|
|
|
|
class Swedish(Language):
|
|
lang = 'sv'
|
|
Defaults = SwedishDefaults
|
|
|
|
|
|
__all__ = ['Swedish']
|