finished first draft of tests

.gitignore

@@ -3,3 +3,7 @@
 
 # Jupyter Notebook
 **.ipynb_checkpoints
+
+**__pycache__
+src/__pycache__
+tests/__pycache__

Dockerfile

@@ -10,4 +10,5 @@ RUN conda install -y \
     scikit-learn=1.3.2 \
     requests=2.31.0 \
     notebook=7.0.6 \
-    pytest=7.4.3
+    pytest=7.4.3 \
+    responses=0.24.1

README.md

@@ -105,6 +105,11 @@ where you launched the container, and then type `docker compose rm`
 
 5. Send a pull request to merge the changes into the `main` branch. 
 
+#### Running the tests
+Tests are run using the `pytest` command in the root of the project.
+More details about the test suite can be found in the 
+[`tests`](tests) directory.
+
 ## License
 
 The Breast Cancer Predictor report contained herein are licensed under the

src/read_zip.py

@@ -18,6 +18,19 @@ def read_zip(url, directory):
     None
     """
     request = requests.get(url)
+
+    # check if URL exists, if not raise an error
+    if request.status_code != 200:
+        raise ValueError('The URL provided does not exist.')
+
+    # check if the URL points to a zip file, if not raise an error  
+    if request.headers['content-type'] != 'application/zip':
+        raise ValueError('The URL provided does not point to a zip file.')
+
+    # check if the directory exists, if not raise an error
+    if not os.path.isdir(directory):
+        raise ValueError('The directory provided does not exist.')
+
     filename_from_url = os.path.basename(url)
     path_to_zip_file = os.path.join(directory, filename_from_url)
     with open(path_to_zip_file, 'wb') as f:

tests/README.md

@@ -11,8 +11,6 @@ If for some reason they go missing from the remote repository,
 we can re-run the `generate_test_zip_files.py` script to re-generate them
 and then push them to the remote repository.
 
-
-
 ### Test teardown
 `conftest.py` contains the code to delete the files and directories 
 created by the tests which need to be deleted at the end of the tests.

tests/test_read_zip.py

@@ -1,6 +1,7 @@
 import pytest
 import os
 import shutil
+import responses
 import sys
 sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
 from src.read_zip import read_zip
@@ -29,6 +30,13 @@
 # URL for Case 3 (empty zip file)
 url_empty_zip = 'https://github.com/ttimbers/breast_cancer_predictor_py/raw/main/tests/empty.zip'
 
+# mock non-existing URL
+@pytest.fixture
+def mock_response():
+    # Mock a response with a non-200 status code
+    with responses.RequestsMock() as rsps:
+        rsps.add(responses.GET, 'https://example.com', status=404)
+        yield
 
 # Tests
 
@@ -59,17 +67,13 @@ def test_read_zip_subdir():
     if os.path.exists('testss/test_zip_data1/subdir'):
         shutil.rmtree('testss/test_zip_data1/subdir')
 
-# test read_zip function throws an error if the zip file is empty
-#def test_read_zip_error_on_empty():
-    # add tests here
-
 # test read_zip function throws an error if the input URL is invalid 
-# (e.g., points to a non-existent file or a non-zip file)
-#def test_read_zip_error_on_invalid_url():
-    # add tests here
+def test_read_zip_error_on_invalid_url(mock_response):
+    with pytest.raises(ValueError, match='The URL provided does not exist.'):
+        read_zip('https://example.com', 'tests/test_zip_data1')    # add tests here
 
 # test read_zip function throws an error 
 # if the  directory path provided does not exist
-#def test_read_zip_error_on_missing_dir():
-    # add tests here
-
+def test_read_zip_error_on_missing_dir():
+    with pytest.raises(ValueError, match='The directory provided does not exist.'):
+        read_zip(url_txt_csv_zip, 'tests/test_zip_data3')