2015-09-06 23:10:37 +03:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
|
|
|
|
from os import path
|
|
|
|
|
|
|
|
|
|
from ..language import Language
|
2016-11-02 21:56:32 +03:00
|
|
|
from ..attrs import LANG
|
|
|
|
|
from . import language_data
|
2015-09-06 23:10:37 +03:00
|
|
|
|
|
|
|
|
|
2016-11-02 22:03:24 +03:00
|
|
|
class Italian(Language):
|
2016-11-02 21:56:32 +03:00
|
|
|
lang = 'it'
|
|
|
|
|
|
|
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
|
tokenizer_exceptions = dict(language_data.TOKENIZER_EXCEPTIONS)
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'it'
|
|
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
