- Updated code as per review comments

- Added unit test workflow

Author: sujata-m

.github/workflows/unit_tests.yml

@@ -0,0 +1,27 @@
+---
+    name: Tests
+    on:
+      pull_request:
+        branches: [develop]
+
+    jobs:
+      Tests:
+        name: Unit tests
+        # Set the agent to run on
+        runs-on: ubuntu-latest
+        steps:
+          - name: Checkout code
+            uses: actions/checkout@v3
+
+          - name: Set up Python
+            uses: actions/setup-python@v4
+            with:
+              python-version: "3.10"
+
+          - name: Install dependencies
+            run: |
+              pip install -r requirement.txt
+
+          - name: Run unit tests
+            run: |
+              python -m unittest discover -v tests/unit_tests

CHANGELOG.md

@@ -1,7 +1,7 @@
 # Change log
 
 ### 0.2.2
-- Added functionality to get the specific umber of errors
+- Added functionality to get the specific number of errors
   ```
   validator = OSWValidation(zipfile_path=<ZIP_FILE_PATH>)
   result = validator.validate() // will return only first 20 errors by default

src/python_osw_validation/__init__.py

@@ -73,8 +73,7 @@ def validate(self, max_errors=20) -> ValidationResult:
             OSW_dataset = {}
             for file in validator.files:
                 file_path = os.path.join(file)
-                osw_file = next(
-                    (osw_file_any for osw_file_any in OSW_dataset_files.keys() if osw_file_any in file_path), '')
+                osw_file = next((osw_file_any for osw_file_any in OSW_dataset_files.keys() if osw_file_any in file_path), '')
                 OSW_dataset[osw_file] = gpd.read_file(file_path)
 
             # Are all id's unique in each file? No need to check uniqueness across files yet since we do not have a global OSW ID format yet
@@ -105,32 +104,26 @@ def validate(self, max_errors=20) -> ValidationResult:
             unmatched = node_ids_edges_u - node_ids
             is_valid = len(unmatched) == 0
             if not is_valid:
-                self.errors.append(
-                    f"All _u_id's in edges should be part of _id's mentioned in nodes, _u_id's not in nodes are: {unmatched}")
+                self.errors.append(f"All _u_id's in edges should be part of _id's mentioned in nodes, _u_id's not in nodes are: {unmatched}")
 
             # Do all node references in _v_id exist in nodes?
             unmatched = node_ids_edges_v - node_ids
             is_valid = len(unmatched) == 0
             if not is_valid:
-                self.errors.append(
-                    f"All _v_id's in edges should be part of _id's mentioned in nodes, _v_id's not in nodes are: {unmatched}")
+                self.errors.append(f"All _v_id's in edges should be part of _id's mentioned in nodes, _v_id's not in nodes are: {unmatched}")
 
             # Do all node references in _w_id exist in nodes?
             unmatched = node_ids_zones_w - node_ids
             is_valid = len(unmatched) == 0
             if not is_valid:
-                self.errors.append(
-                    f"All _w_id's in zones should be part of _id's mentioned in nodes, _w_id's not in nodes are: {unmatched}")
+                self.errors.append(f"All _w_id's in zones should be part of _id's mentioned in nodes, _w_id's not in nodes are: {unmatched}")
 
             # Geometry validation: check geometry type in each file and test if coordinates make a shape that is reasonable geometric shape according to the Simple Feature Access standard
             for osw_file in OSW_dataset:
-                invalid_geojson = OSW_dataset[osw_file][
-                    (OSW_dataset[osw_file].geometry.type != OSW_dataset_files[osw_file]['geometry']) | (
-                          OSW_dataset[osw_file].is_valid == False)]
+                invalid_geojson = OSW_dataset[osw_file][(OSW_dataset[osw_file].geometry.type != OSW_dataset_files[osw_file]['geometry']) | (OSW_dataset[osw_file].is_valid == False)]
                 is_valid = len(invalid_geojson) == 0
                 if not is_valid:
-                    self.errors.append(
-                        f"Invalid {osw_file} geometries found, id's of invalid geometries: {set(invalid_geojson['_id'])}")
+                    self.errors.append(f"Invalid {osw_file} geometries found, id's of invalid geometries: {set(invalid_geojson['_id'])}")
 
             # Validate OSW external extensions
             for file in validator.externalExtensions:
@@ -139,8 +132,7 @@ def validate(self, max_errors=20) -> ValidationResult:
                 invalid_geojson = extensionFile[extensionFile.is_valid == False]
                 is_valid = len(invalid_geojson) == 0
                 if not is_valid:
-                    self.errors.append(
-                        f"Invalid geometries found in extension file {file}, list of invalid geometries: {invalid_geojson.to_json()}")
+                    self.errors.append(f"Invalid geometries found in extension file {file}, list of invalid geometries: {invalid_geojson.to_json()}")
 
             if self.errors:
                 zip_handler.remove_extracted_files()

tests/unit_tests/test_osw_validation.py

@@ -81,14 +81,14 @@ def test_invalid_zipfile_default_error_count(self):
         result = validation.validate()
         self.assertFalse(result.is_valid)
         self.assertIsNotNone(result.errors)
-        self.assertEqual(20, len(result.errors))
+        self.assertLessEqual(len(result.errors), 20)
 
-    def test_invalid_zipfile_should_return_10_errors(self):
+    def test_invalid_zipfile_should_specific_errors_counts(self):
         validation = OSWValidation(zipfile_path=self.invalid_zipfile)
         result = validation.validate(max_errors=10)
         self.assertFalse(result.is_valid)
         self.assertIsNotNone(result.errors)
-        self.assertEqual(10, len(result.errors))
+        self.assertLessEqual(len(result.errors), 10)
 
     def test_invalid_zipfile_with_invalid_schema(self):
         validation = OSWValidation(zipfile_path=self.invalid_zipfile,