mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 21:57:15 +03:00
28 lines
746 B
Python
28 lines
746 B
Python
|
from __future__ import unicode_literals, print_function
|
||
|
|
|
||
|
|
from os import path
|
||
|
|
|
||
|
|
from ..language import Language
|
||
|
|
from ..attrs import LANG
|
||
|
|
from . import language_data
|
||
|
|
|
||
|
|
|
||
|
|
class Portuguese(Language):
|
||
|
|
lang = 'pt'
|
||
|
|
|
||
|
|
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: 'pt'
|
||
|
|
|
||
|
|
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)
|
||
|
|
|