Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix base schema integration

This commit is contained in:
Ines Montani 2020-09-27 22:50:36 +02:00
parent e04bd16f7f
commit 658fad428a
2 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/language.py
View File

@ -27,7 +27,7 @@ from .lang.punctuation import TOKENIZER_INFIXES
from .tokens import Doc from .tokens import Doc
from .tokenizer import Tokenizer from .tokenizer import Tokenizer
from .errors import Errors, Warnings from .errors import Errors, Warnings
from .schemas import ConfigSchema from .schemas import ConfigSchema, ConfigSchemaNlp
from .git_info import GIT_VERSION from .git_info import GIT_VERSION
from . import util from . import util
from . import about from . import about
@ -1518,10 +1518,15 @@ class Language:
config = util.copy_config(config) config = util.copy_config(config)
orig_pipeline = config.pop("components", {}) orig_pipeline = config.pop("components", {})
config["components"] = {} config["components"] = {}
filled = registry.fill(config, validate=validate, schema=ConfigSchema) if auto_fill:
filled = registry.fill(config, validate=validate, schema=ConfigSchema)
else:
filled = config
filled["components"] = orig_pipeline filled["components"] = orig_pipeline
config["components"] = orig_pipeline config["components"] = orig_pipeline
resolved_nlp = registry.resolve(filled["nlp"], validate=validate) resolved_nlp = registry.resolve(
filled["nlp"], validate=validate, schema=ConfigSchemaNlp
)
create_tokenizer = resolved_nlp["tokenizer"] create_tokenizer = resolved_nlp["tokenizer"]
before_creation = resolved_nlp["before_creation"] before_creation = resolved_nlp["before_creation"]
after_creation = resolved_nlp["after_creation"] after_creation = resolved_nlp["after_creation"]

4
spacy/schemas.py
View File

@ -295,10 +295,6 @@ class ConfigSchema(BaseModel):
arbitrary_types_allowed = True arbitrary_types_allowed = True
class NlpSchema(BaseModel):
nlp: ConfigSchemaNlp
class TrainingSchema(BaseModel): class TrainingSchema(BaseModel):
training: ConfigSchemaTraining training: ConfigSchemaTraining
pretraining: Union[ConfigSchemaPretrain, ConfigSchemaPretrainEmpty] = {} pretraining: Union[ConfigSchemaPretrain, ConfigSchemaPretrainEmpty] = {}