Tests for cli

bia-ingest-shared-models/bia_ingest_sm/biostudies.py

@@ -97,7 +97,7 @@ class Submission(BaseModel):
     attributes: List[Attribute]
 
     def as_tsv(self) -> str:
-        tsv_rep = f"Submission"
+        tsv_rep = "Submission"
         if self.accno:
             tsv_rep += f"\t{self.accno}"
         tsv_rep += "\n"
@@ -136,7 +136,6 @@ class QueryResult(BaseModel):
 
 
 def load_submission(accession_id: str) -> Submission:
-
     url = STUDY_URL_TEMPLATE.format(accession=accession_id)
     logger.info(f"Fetching submission from {url}")
     headers = {
@@ -146,19 +145,18 @@ def load_submission(accession_id: str) -> Submission:
 
     assert r.status_code == 200
 
-    submission = Submission.parse_raw(r.content)
+    submission = Submission.model_validate_json(r.content)
 
     return submission
 
 
 def attributes_to_dict(
     attributes: List[Attribute],
 ) -> Dict[str, Optional[str | List[str]]]:
-
     attr_dict = {}
     for attr in attributes:
         if attr.name in attr_dict:
-            if type(attr_dict[attr.name]) is list:
+            if isinstance(attr_dict[attr.name], list):
                 attr_dict[attr.name].append(attr.value)
             else:
                 attr_dict[attr.name] = [
@@ -175,7 +173,7 @@ def find_file_lists_in_section(
 ) -> List[Dict[str, Union[str, None, List[str]]]]:
     """
     Find all of the File Lists in a Section, recursively descending through the subsections.
-    
+
     Return a list of dictionaries.
     """
 
@@ -206,14 +204,12 @@ def find_file_lists_in_section(
 def find_file_lists_in_submission(
     submission: Submission,
 ) -> List[Dict[str, Union[str, None, List[str]]]]:
-
     return find_file_lists_in_section(submission.section, [])
 
 
 def flist_from_flist_fname(
     accession_id: str, flist_fname: str, extra_attribute: Union[List[str], str] = None
 ) -> List[File]:
-
     flist_url = FLIST_URI_TEMPLATE.format(
         accession_id=accession_id, flist_fname=flist_fname
     )
@@ -231,7 +227,7 @@ def flist_from_flist_fname(
     fl = TypeAdapter(List[File]).validate_json(filtered_content)
 
     if extra_attribute:
-        if type(extra_attribute) is not list:
+        if not isinstance(extra_attribute, list):
             extra_attribute = [
                 extra_attribute,
             ]
@@ -269,7 +265,6 @@ def get_file_uri_template_for_accession(accession_id: str) -> str:
 
 
 def find_files_in_submission_file_lists(submission: Submission) -> List[File]:
-
     file_list_dicts = find_file_lists_in_submission(submission)
     file_lists = []
     for file_list_dict in file_list_dicts:
@@ -298,7 +293,6 @@ def find_files_in_submission(submission: Submission) -> List[File]:
     all_files = find_files_in_submission_file_lists(submission)
 
     def descend_and_find_files(section, files_list=[]):
-
         section_type = type(section)
         if section_type == Section:
             for file in section.files:

bia-ingest-shared-models/test/conftest.py

@@ -1,15 +1,16 @@
+from unittest.mock import Mock
+from typing import Dict
 from pathlib import Path
 import json
 import pytest
-from bia_ingest_sm.biostudies import Submission
+from bia_ingest_sm.biostudies import Submission, requests
 from .utils import accession_id
 from bia_ingest_sm.cli_logging import ObjectValidationResult
 
+
 @pytest.fixture
 def base_path() -> Path:
-    """Return full path to test directory
-
-    """
+    """Return full path to test directory"""
     return Path(__file__).parent
 
 
@@ -23,4 +24,19 @@ def test_submission(base_path: Path) -> Submission:
 
 @pytest.fixture
 def result_summary():
-    return {accession_id: ObjectValidationResult()}
+    return {accession_id: ObjectValidationResult()}
+
+
+@pytest.fixture
+def mock_request_get(monkeypatch):
+    """Requests.get mocked to read file from disk"""
+
+    def _mock_request_get(flist_url: str) -> Dict[str, str]:
+        data_dir = Path(__file__).parent / "data"
+        path_to_load = data_dir / Path(flist_url).name
+        return_value = Mock()
+        return_value.status_code = 200
+        return_value.content = path_to_load.read_text()
+        return return_value
+
+    monkeypatch.setattr(requests, "get", _mock_request_get)

bia-ingest-shared-models/test/test_bia_ingest_cli.py

@@ -0,0 +1,71 @@
+from typer.testing import CliRunner
+from bia_ingest_sm import cli
+from bia_ingest_sm.conversion.utils import settings
+from bia_ingest_sm import biostudies
+from . import utils
+from bia_shared_datamodels import bia_data_model
+
+runner = CliRunner()
+
+accession_id = "S-BIADTEST"
+
+expected_objects_dict = {
+    "studies": utils.get_test_study(),
+    "experimental_imaging_dataset": utils.get_test_experimental_imaging_dataset(),
+    "specimens": utils.get_test_specimen(),
+    "biosamples": utils.get_test_biosample(),
+    "image_acquisitions": utils.get_test_image_acquisition(),
+    "specimen_growth_protocol": utils.get_test_specimen_growth_protocol(),
+    "specimen_imaging_protocol": utils.get_test_specimen_imaging_preparation_protocol(),
+}
+
+# File references are a special case as they depend on experimental dataset
+expected_file_references = utils.get_test_file_reference(
+    ["file_list_study_component_1.json", "file_list_study_component_2.json"]
+)
+expected_objects_dict["file_references"] = expected_file_references
+
+n_expected_objects = 0
+for expected_objects in expected_objects_dict.values():
+    if isinstance(expected_objects, list):
+        n_expected_objects += len(expected_objects)
+    else:
+        n_expected_objects += 1
+
+
+def test_cli_writes_expected_files(
+    monkeypatch, tmp_path, test_submission, mock_request_get
+):
+    monkeypatch.setattr(settings, "bia_data_dir", str(tmp_path))
+
+    def _load_submission(accession_id: str) -> biostudies.Submission:
+        return test_submission
+
+    monkeypatch.setattr(cli, "load_submission", _load_submission)
+
+    result = runner.invoke(cli.app, ["ingest", accession_id])
+    assert result.exit_code == 0
+
+    files_written = [f for f in tmp_path.rglob("*.json")]
+
+    assert len(files_written) == n_expected_objects
+
+    for dir_name, expected_objects in expected_objects_dict.items():
+        dir_path = tmp_path / dir_name / accession_id
+
+        if not isinstance(expected_objects, list):
+            expected_objects = [
+                expected_objects,
+            ]
+            for expected_object in expected_objects:
+                if dir_name == "studies":
+                    created_object_path = tmp_path / "studies" / f"{accession_id}.json"
+                else:
+                    created_object_path = dir_path / f"{expected_object.uuid}.json"
+                created_object_type = getattr(
+                    bia_data_model, expected_object.model.type_name
+                )
+                created_object = created_object_type.model_validate_json(
+                    created_object_path.read_text()
+                )
+                assert created_object == expected_object

bia-ingest-shared-models/test/test_file_reference.py

@@ -1,33 +1,16 @@
-""" Test FileReference creation
-   
-    Test FileReference creation separately from other shared models as it
-    now has a different pattern of creation from other artefacts i.e. 
-    it now needs a submitted dataset
+"""Test FileReference creation
+
+Test FileReference creation separately from other shared models as it
+now has a different pattern of creation from other artefacts i.e.
+it now needs a submitted dataset
 """
 
-from typing import Dict
-from pathlib import Path
-from unittest.mock import Mock
-import pytest
 from . import utils
 from bia_ingest_sm.conversion import (
-    experimental_imaging_dataset,
     file_reference,
 )
-from bia_ingest_sm.biostudies import requests, File
-from pydantic import TypeAdapter
-
-# TODO: Mock requests.get correctly!!!
-def mock_request_get(flist_url: str) -> Dict[str, str]:
-    data_dir = Path(__file__).parent / "data"
-    path_to_load = data_dir / Path(flist_url).name
-    return_value = Mock()
-    return_value.status_code = 200
-    return_value.content = path_to_load.read_text()
-    return return_value
-
+from bia_ingest_sm.biostudies import File
 
-requests.get = mock_request_get
 
 # Get second study component as dataset in submission
 datasets_in_submission = [
@@ -47,17 +30,19 @@ def test_get_file_reference_for_submission_dataset(test_submission, result_summa
         accession_id=test_submission.accno,
         submission_dataset=datasets_in_submission[0],
         files_in_file_list=files_in_filelist,
-        result_summary=result_summary
+        result_summary=result_summary,
     )
     assert created == expected
 
 
-def test_create_file_reference_for_study_component(test_submission, caplog, result_summary):
-
+def test_create_file_reference_for_study_component(
+    test_submission, caplog, result_summary, mock_request_get
+):
     expected = {datasets_in_submission[0].title_id: utils.get_test_file_reference()}
     created = file_reference.get_file_reference_by_dataset(
-        test_submission, datasets_in_submission=datasets_in_submission, result_summary=result_summary
-
+        test_submission,
+        datasets_in_submission=datasets_in_submission,
+        result_summary=result_summary,
     )
     assert created == expected
 
@@ -68,14 +53,18 @@ def test_create_file_reference_for_study_component(test_submission, caplog, resu
 def test_create_file_reference_for_study_component_when_no_matching_sc_in_file_list(
     test_submission, caplog, result_summary
 ):
-    """Test attempted creation of study FileReferences when study 
-        components in dataset do not match does in file_list
+    """Test attempted creation of study FileReferences when study
+    components in dataset do not match does in file_list
     """
 
     dataset = utils.get_test_experimental_imaging_dataset()[0]
     dataset.title_id = "Test name not in file list"
     created = file_reference.get_file_reference_by_dataset(
-        test_submission, datasets_in_submission=[dataset,], result_summary=result_summary
+        test_submission,
+        datasets_in_submission=[
+            dataset,
+        ],
+        result_summary=result_summary,
     )
 
     assert created is None