2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2017-03-15 16:33:39 +00:00
|
|
|
from __future__ import unicode_literals
|
2015-07-07 12:00:07 +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
|
2017-03-15 16:33:29 +00:00
|
|
|
from ..deprecated import fix_glove_vectors_loading
|
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
|
|
|
|
2017-03-15 16:33:39 +00:00
|
|
|
|
2017-03-08 00:37:52 +00:00
|
|
|
try:
|
|
|
|
basestring
|
|
|
|
except NameError:
|
|
|
|
basestring = str
|
|
|
|
|
2016-12-18 15:58:28 +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 21:29:31 +00:00
|
|
|
|
2017-03-15 14:23:22 +00:00
|
|
|
morph_rules = dict(MORPH_RULES)
|
2017-03-15 09:52:50 +00:00
|
|
|
lemma_rules = dict(LEMMA_RULES)
|
|
|
|
lemma_index = dict(LEMMA_INDEX)
|
|
|
|
lemma_exc = dict(LEMMA_EXC)
|
|
|
|
|
2016-12-18 21:29:31 +00:00
|
|
|
|
|
|
|
def __init__(self, **overrides):
|
2017-03-15 16:33:29 +00:00
|
|
|
# Special-case hack for loading the GloVe vectors, to support <1.0
|
|
|
|
overrides = fix_glove_vectors_loading(overrides)
|
2016-12-18 21:29:31 +00:00
|
|
|
Language.__init__(self, **overrides)
|