mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-12 10:16:27 +03:00
Add missing lex_attr_getters (resolves #5806 )
This commit is contained in:
parent
c003d26b94
commit
4a0a692875
|
@ -3,6 +3,7 @@ from thinc.api import Config
|
||||||
|
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from .tag_map import TAG_MAP
|
from .tag_map import TAG_MAP
|
||||||
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...tokens import Doc
|
from ...tokens import Doc
|
||||||
from ...compat import copy_reg
|
from ...compat import copy_reg
|
||||||
|
@ -64,6 +65,7 @@ class KoreanTokenizer(DummyTokenizer):
|
||||||
|
|
||||||
class KoreanDefaults(Language.Defaults):
|
class KoreanDefaults(Language.Defaults):
|
||||||
config = Config().from_str(DEFAULT_CONFIG)
|
config = Config().from_str(DEFAULT_CONFIG)
|
||||||
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
|
writing_system = {"direction": "ltr", "has_case": False, "has_letters": False}
|
||||||
|
|
||||||
|
|
|
@ -1,8 +1,10 @@
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
|
|
||||||
|
|
||||||
class MalayalamDefaults(Language.Defaults):
|
class MalayalamDefaults(Language.Defaults):
|
||||||
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -2,6 +2,7 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
||||||
from .punctuation import TOKENIZER_SUFFIXES
|
from .punctuation import TOKENIZER_SUFFIXES
|
||||||
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
|
|
||||||
# Lemma data note:
|
# Lemma data note:
|
||||||
|
@ -14,6 +15,7 @@ class RomanianDefaults(Language.Defaults):
|
||||||
prefixes = TOKENIZER_PREFIXES
|
prefixes = TOKENIZER_PREFIXES
|
||||||
suffixes = TOKENIZER_SUFFIXES
|
suffixes = TOKENIZER_SUFFIXES
|
||||||
infixes = TOKENIZER_INFIXES
|
infixes = TOKENIZER_INFIXES
|
||||||
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -1,10 +1,12 @@
|
||||||
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
|
|
||||||
|
|
||||||
class TurkishDefaults(Language.Defaults):
|
class TurkishDefaults(Language.Defaults):
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue
Block a user