def test_project_config_validation_full():
config = {
"vars": {"some_var": 20},
"directories": ["assets", "configs", "corpus", "scripts", "training"],
"assets": [
{
"dest": "x",
"url": "https://example.com",
"checksum": "63373dd656daa1fd3043ce166a59474c",
},
{
"dest": "y",
"git": {
"repo": "https://github.com/example/repo",
"branch": "develop",
"path": "y",
},
},
],
"commands": [
{
"name": "train",
"help": "Train a model",
"script": ["python -m spacy train config.cfg -o training"],
"deps": ["config.cfg", "corpus/training.spcy"],
"outputs": ["training/model-best"],
},
{"name": "test", "script": ["pytest", "custom.py"], "no_skip": True},
],
"workflows": {"all": ["train", "test"], "train": ["train"]},
}
errors = validate(ProjectConfigSchema, config)
assert not errors
def test_doc_to_json_span(doc):
"""Test that Doc.to_json() includes spans"""
doc.spans["test"] = [Span(doc, 0, 2, "test"), Span(doc, 0, 1, "test")]
json_doc = doc.to_json()
assert "spans" in json_doc
assert len(json_doc["spans"]) == 1
assert len(json_doc["spans"]["test"]) == 2
assert json_doc["spans"]["test"][0]["start"] == 0
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_doc_to_json_underscore(doc):
Doc.set_extension("json_test1", default=False)
Doc.set_extension("json_test2", default=False)
doc._.json_test1 = "hello world"
doc._.json_test2 = [1, 2, 3]
json_doc = doc.to_json(underscore=["json_test1", "json_test2"])
assert "_" in json_doc
assert json_doc["_"]["json_test1"] == "hello world"
assert json_doc["_"]["json_test2"] == [1, 2, 3]
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_doc_to_json(doc):
json_doc = doc.to_json()
assert json_doc["text"] == "c d e "
assert len(json_doc["tokens"]) == 3
assert json_doc["tokens"][0]["pos"] == "VERB"
assert json_doc["tokens"][0]["tag"] == "VBP"
assert json_doc["tokens"][0]["dep"] == "ROOT"
assert len(json_doc["ents"]) == 1
assert json_doc["ents"][0]["start"] == 2 # character offset!
assert json_doc["ents"][0]["end"] == 3 # character offset!
assert json_doc["ents"][0]["label"] == "ORG"
assert not schemas.validate(schemas.DocJSONSchema, json_doc)
def test_project_config_validation2(config, n_errors):
errors = validate(ProjectConfigSchema, config)
assert len(errors) == n_errors
