spaCy/spacy/hu/__init__.py

27 lines
675 B
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
from __future__ import unicode_literals, print_function
2017-01-23 23:27:49 +03:00
from .tokenizer_exceptions import TOKEN_MATCH
2016-12-21 00:28:20 +03:00
from .language_data import *
from ..attrs import LANG
from ..language import Language
class Hungarian(Language):
lang = 'hu'
class Defaults(Language.Defaults):
2016-12-21 00:28:20 +03:00
tokenizer_exceptions = dict(TOKENIZER_EXCEPTIONS)
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'hu'
2016-12-21 00:28:20 +03:00
prefixes = tuple(TOKENIZER_PREFIXES)
2016-12-21 00:28:20 +03:00
suffixes = tuple(TOKENIZER_SUFFIXES)
2016-12-21 00:28:20 +03:00
infixes = tuple(TOKENIZER_INFIXES)
2016-12-21 00:28:20 +03:00
stop_words = set(STOP_WORDS)
2017-01-14 17:51:59 +03:00
token_match = TOKEN_MATCH