def substitute_project_variables(
config: Dict[str, Any],
overrides: Dict[str, Any] = SimpleFrozenDict(),
key: str = "vars",
env_key: str = "env",
) -> Dict[str, Any]:
"""Interpolate variables in the project file using the config system.
config (Dict[str, Any]): The project config.
overrides (Dict[str, Any]): Optional config overrides.
key (str): Key containing variables in project config.
env_key (str): Key containing environment variable mapping in project config.
RETURNS (Dict[str, Any]): The interpolated project config.
"""
config.setdefault(key, {})
config.setdefault(env_key, {})
# Substitute references to env vars with their values
for config_var, env_var in config[env_key].items():
config[env_key][config_var] = _parse_override(
os.environ.get(env_var, ""))
# Need to put variables in the top scope again so we can have a top-level
# section "project" (otherwise, a list of commands in the top scope wouldn't)
# be allowed by Thinc's config system
cfg = Config({
"project": config,
key: config[key],
env_key: config[env_key]
})
cfg = Config().from_str(cfg.to_str(), overrides=overrides)
interpolated = cfg.interpolate()
return dict(interpolated["project"])
def substitute_project_variables(config: Dict[str, Any], overrides: Dict = {}):
key = "vars"
config.setdefault(key, {})
config[key].update(overrides)
# Need to put variables in the top scope again so we can have a top-level
# section "project" (otherwise, a list of commands in the top scope wouldn't)
# be allowed by Thinc's config system
cfg = Config({"project": config, key: config[key]})
interpolated = cfg.interpolate()
return dict(interpolated["project"])
def test_config_interpolation():
config = Config().from_str(nlp_config_string, interpolate=False)
assert config["corpora"]["train"]["path"] == "${paths.train}"
interpolated = config.interpolate()
assert interpolated["corpora"]["train"]["path"] is None
nlp = English.from_config(config)
assert nlp.config["corpora"]["train"]["path"] == "${paths.train}"
# Ensure that variables are preserved in nlp config
width = "${components.tok2vec.model.width}"
assert config["components"]["tagger"]["model"]["tok2vec"]["width"] == width
assert nlp.config["components"]["tagger"]["model"]["tok2vec"]["width"] == width
interpolated2 = nlp.config.interpolate()
assert interpolated2["corpora"]["train"]["path"] is None
assert interpolated2["components"]["tagger"]["model"]["tok2vec"]["width"] == 342
nlp2 = English.from_config(interpolated)
assert nlp2.config["corpora"]["train"]["path"] is None
assert nlp2.config["components"]["tagger"]["model"]["tok2vec"]["width"] == 342
