mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 20:09:18 +03:00
7e821c2776
* added tr_vocab to config * basic test * added syntax iterator to Turkish lang class * first version for Turkish syntax iter, without flat * added simple tests with nmod, amod, det * more tests to amod and nmod * separated noun chunks and parser test * rearrangement after nchunk parser separation * added recursive NPs * tests with complicated recursive NPs * tests with conjed NPs * additional tests for conj NP * small modification for shaving off conj from NP * added tests with flat * more tests with flat * added examples with flats conjed * added inner func for flat trick * corrected parse Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
37 lines
1.0 KiB
Python
37 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .morph_rules import MORPH_RULES
|
|
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class TurkishDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
lex_attr_getters[LANG] = lambda text: "tr"
|
|
lex_attr_getters[NORM] = add_lookups(
|
|
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
|
|
)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
morph_rules = MORPH_RULES
|
|
|
|
|
|
class Turkish(Language):
|
|
lang = "tr"
|
|
Defaults = TurkishDefaults
|
|
|
|
|
|
__all__ = ["Turkish"]
|