mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 17:06:29 +03:00
Remove default initialize lookups
This commit is contained in:
parent
1700c8541e
commit
d48ddd6c9a
|
@ -3,21 +3,9 @@ from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class DanishDefaults(Language.Defaults):
|
class DanishDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
infixes = TOKENIZER_INFIXES
|
infixes = TOKENIZER_INFIXES
|
||||||
suffixes = TOKENIZER_SUFFIXES
|
suffixes = TOKENIZER_SUFFIXES
|
||||||
|
|
|
@ -3,21 +3,9 @@ from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIX
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from .syntax_iterators import SYNTAX_ITERATORS
|
from .syntax_iterators import SYNTAX_ITERATORS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class GermanDefaults(Language.Defaults):
|
class GermanDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
prefixes = TOKENIZER_PREFIXES
|
prefixes = TOKENIZER_PREFIXES
|
||||||
suffixes = TOKENIZER_SUFFIXES
|
suffixes = TOKENIZER_SUFFIXES
|
||||||
|
|
|
@ -9,21 +9,9 @@ from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIX
|
||||||
from .lemmatizer import GreekLemmatizer
|
from .lemmatizer import GreekLemmatizer
|
||||||
from ...lookups import Lookups
|
from ...lookups import Lookups
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class GreekDefaults(Language.Defaults):
|
class GreekDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
prefixes = TOKENIZER_PREFIXES
|
prefixes = TOKENIZER_PREFIXES
|
||||||
suffixes = TOKENIZER_SUFFIXES
|
suffixes = TOKENIZER_SUFFIXES
|
||||||
|
|
|
@ -4,21 +4,9 @@ from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from .syntax_iterators import SYNTAX_ITERATORS
|
from .syntax_iterators import SYNTAX_ITERATORS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class IndonesianDefaults(Language.Defaults):
|
class IndonesianDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
prefixes = TOKENIZER_PREFIXES
|
prefixes = TOKENIZER_PREFIXES
|
||||||
suffixes = TOKENIZER_SUFFIXES
|
suffixes = TOKENIZER_SUFFIXES
|
||||||
|
|
|
@ -3,21 +3,9 @@ from .punctuation import TOKENIZER_INFIXES
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class LuxembourgishDefaults(Language.Defaults):
|
class LuxembourgishDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
infixes = TOKENIZER_INFIXES
|
infixes = TOKENIZER_INFIXES
|
||||||
lex_attr_getters = LEX_ATTRS
|
lex_attr_getters = LEX_ATTRS
|
||||||
|
|
|
@ -3,21 +3,9 @@ from .stop_words import STOP_WORDS
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class PortugueseDefaults(Language.Defaults):
|
class PortugueseDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
infixes = TOKENIZER_INFIXES
|
infixes = TOKENIZER_INFIXES
|
||||||
prefixes = TOKENIZER_PREFIXES
|
prefixes = TOKENIZER_PREFIXES
|
||||||
|
|
|
@ -7,21 +7,9 @@ from .lex_attrs import LEX_ATTRS
|
||||||
from .lemmatizer import RussianLemmatizer
|
from .lemmatizer import RussianLemmatizer
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...lookups import Lookups
|
from ...lookups import Lookups
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class RussianDefaults(Language.Defaults):
|
class RussianDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
lex_attr_getters = LEX_ATTRS
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
|
@ -2,21 +2,9 @@ from .stop_words import STOP_WORDS
|
||||||
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class SerbianDefaults(Language.Defaults):
|
class SerbianDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||||||
lex_attr_getters = LEX_ATTRS
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
|
@ -1,21 +1,9 @@
|
||||||
from .stop_words import STOP_WORDS
|
from .stop_words import STOP_WORDS
|
||||||
from .lex_attrs import LEX_ATTRS
|
from .lex_attrs import LEX_ATTRS
|
||||||
from ...language import Language
|
from ...language import Language
|
||||||
from ...util import load_config_from_str
|
|
||||||
|
|
||||||
|
|
||||||
DEFAULT_CONFIG = """
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
|
||||||
|
|
||||||
|
|
||||||
class TamilDefaults(Language.Defaults):
|
class TamilDefaults(Language.Defaults):
|
||||||
config = load_config_from_str(DEFAULT_CONFIG)
|
|
||||||
lex_attr_getters = LEX_ATTRS
|
lex_attr_getters = LEX_ATTRS
|
||||||
stop_words = STOP_WORDS
|
stop_words = STOP_WORDS
|
||||||
|
|
||||||
|
|
|
@ -10,13 +10,6 @@ DEFAULT_CONFIG = """
|
||||||
|
|
||||||
[nlp.tokenizer]
|
[nlp.tokenizer]
|
||||||
@tokenizers = "spacy.th.ThaiTokenizer"
|
@tokenizers = "spacy.th.ThaiTokenizer"
|
||||||
|
|
||||||
[initialize]
|
|
||||||
|
|
||||||
[initialize.lookups]
|
|
||||||
@misc = "spacy.LookupsDataLoader.v1"
|
|
||||||
lang = ${nlp.lang}
|
|
||||||
tables = ["lexeme_norm"]
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -339,7 +339,6 @@ def test_ner_warns_no_lookups(caplog):
|
||||||
nlp.vocab.lookups = Lookups()
|
nlp.vocab.lookups = Lookups()
|
||||||
assert not len(nlp.vocab.lookups)
|
assert not len(nlp.vocab.lookups)
|
||||||
nlp.add_pipe("ner")
|
nlp.add_pipe("ner")
|
||||||
nlp.config["initialize"]["lookups"] = None
|
|
||||||
with caplog.at_level(logging.DEBUG):
|
with caplog.at_level(logging.DEBUG):
|
||||||
nlp.initialize()
|
nlp.initialize()
|
||||||
assert "W033" in caplog.text
|
assert "W033" in caplog.text
|
||||||
|
|
Loading…
Reference in New Issue
Block a user