2016-12-17 11:25:44 +00:00
|
|
|
# encoding: utf8
|
2015-08-25 13:37:30 +00:00
|
|
|
from __future__ import unicode_literals, print_function
|
2015-07-07 12:00:07 +00:00
|
|
|
|
2015-08-25 13:37:30 +00:00
|
|
|
from os import path
|
2014-12-24 06:42:00 +00:00
|
|
|
|
2015-08-25 13:37:30 +00:00
|
|
|
from ..language import Language
|
2016-09-25 12:49:53 +00:00
|
|
|
from ..lemmatizer import Lemmatizer
|
|
|
|
from ..vocab import Vocab
|
|
|
|
from ..tokenizer import Tokenizer
|
2016-10-18 16:52:48 +00:00
|
|
|
from ..attrs import LANG
|
2016-12-08 12:58:32 +00:00
|
|
|
|
2016-12-18 15:54:19 +00:00
|
|
|
from .language_data import *
|
2016-01-19 01:54:56 +00:00
|
|
|
|
2015-08-25 13:37:30 +00:00
|
|
|
class English(Language):
|
2015-12-28 15:54:03 +00:00
|
|
|
lang = 'en'
|
2015-12-18 08:52:55 +00:00
|
|
|
|
2016-09-24 18:26:17 +00:00
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
2016-10-18 16:52:48 +00:00
|
|
|
lex_attr_getters[LANG] = lambda text: 'en'
|
2016-09-24 18:26:17 +00:00
|
|
|
|
2016-12-08 12:58:32 +00:00
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
|
|
|
tag_map = TAG_MAP
|
|
|
|
stop_words = STOP_WORDS
|
2016-12-18 14:50:09 +00:00
|
|
|
lemma_rules = LEMMA_RULES
|