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 . import language_data
|
|
|
|
from .. import util
|
|
|
|
from ..lemmatizer import Lemmatizer
|
|
|
|
from ..vocab import Vocab
|
|
|
|
from ..tokenizer import Tokenizer
|
2015-09-14 07:48:51 +00:00
|
|
|
|
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)
|
|
|
|
|
2016-09-25 12:49:53 +00:00
|
|
|
tokenizer_exceptions = dict(language_data.TOKENIZER_EXCEPTIONS)
|
|
|
|
|
|
|
|
prefixes = tuple(language_data.TOKENIZER_PREFIXES)
|
|
|
|
|
|
|
|
suffixes = tuple(language_data.TOKENIZER_SUFFIXES)
|
|
|
|
|
|
|
|
infixes = tuple(language_data.TOKENIZER_INFIXES)
|
|
|
|
|
|
|
|
tag_map = dict(language_data.TAG_MAP)
|
|
|
|
|
|
|
|
stop_words = set(language_data.STOP_WORDS)
|
|
|
|
|