From 658fad428afdba327edb322cb40720f298b2262d Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Sun, 27 Sep 2020 22:50:36 +0200 Subject: [PATCH] Fix base schema integration --- spacy/language.py | 11 ++++++++--- spacy/schemas.py | 4 ---- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/spacy/language.py b/spacy/language.py index bf3911888..c1d2df026 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -27,7 +27,7 @@ from .lang.punctuation import TOKENIZER_INFIXES from .tokens import Doc from .tokenizer import Tokenizer from .errors import Errors, Warnings -from .schemas import ConfigSchema +from .schemas import ConfigSchema, ConfigSchemaNlp from .git_info import GIT_VERSION from . import util from . import about @@ -1518,10 +1518,15 @@ class Language: config = util.copy_config(config) orig_pipeline = config.pop("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 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"] before_creation = resolved_nlp["before_creation"] after_creation = resolved_nlp["after_creation"] diff --git a/spacy/schemas.py b/spacy/schemas.py index 6db05bbd9..7951b851b 100644 --- a/spacy/schemas.py +++ b/spacy/schemas.py @@ -295,10 +295,6 @@ class ConfigSchema(BaseModel): arbitrary_types_allowed = True -class NlpSchema(BaseModel): - nlp: ConfigSchemaNlp - - class TrainingSchema(BaseModel): training: ConfigSchemaTraining pretraining: Union[ConfigSchemaPretrain, ConfigSchemaPretrainEmpty] = {}