MSD-4058 - Replace native ID spaces with underscores.

.github/workflows/run_tests.yml

@@ -8,7 +8,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [ '3.9', '3.10', '3.11' ]
+        python-version: [ '3.9', '3.10', '3.11', '3.12' ]
       fail-fast: false
 
     steps:
@@ -30,7 +30,7 @@ jobs:
         uses: actions/upload-artifact@v3
         with:
           name: Test results for Python ${{ matrix.python-version }}
-          path: tests/reports/
+          path: tests/reports/earthdata-varinfo_junit.xml
 
       - name: Archive coverage report
         uses: actions/upload-artifact@v3

CHANGELOG.md

@@ -1,3 +1,23 @@
+## v3.0.1
+### 2024-10-18
+
+### Changed:
+
+* CMR native IDs generated from variable names with spaces in them will replace
+  those space characters with underscores to avoid errors when trying to ingest
+  such variables.
+* The `python-cmr` requirement is updated to v0.12.0, which adds type hints for
+  that package. A couple of type hints in `earthdata-varinfo` have been updated
+  accordingly.
+* The `numpy` requirement has been relaxed to allow broader compatibility with
+  client software. Note: This enables Python 3.12 compatibility.
+* To ensure compatibility with Python 3.12, the tests are now run using
+  `pytest`. This allows JUnit style output to be produced, as the previously
+  used `unittets-xml-runner` package was not compatible with Python 3.12. The
+  tests themselves are still written using classes and syntax from `unittest`.
+  The CI/CD for running the tests has been updated to also run the tests under
+  Python 3.12.
+
 ## v3.0.0
 ### 2024-09-11
 

Makefile

@@ -30,5 +30,4 @@ prepare-test:
 	mkdir -p tests/reports tests/coverage
 
 test: prepare-test
-	coverage run -m xmlrunner discover tests -o tests/reports
-	coverage html --omit="*tests/*" -d tests/coverage
+	pytest --junitxml=tests/reports/earthdata-varinfo_junit.xml --cov varinfo --cov-report html:tests/coverage --cov-report term

README.md

@@ -216,7 +216,7 @@ for a PR review):
 $ make lint
 ```
 
-Run `unittest` suite:
+Run `unittest` suite (run via `pytest`, but written using `unittest` classes):
 
 ```bash
 $ make test

VERSION

@@ -1 +1 @@
-3.0.0
+3.0.1

dev-requirements.txt

@@ -1,7 +1,7 @@
-coverage ~= 5.5
 ipython ~= 8.0.1
 jsonschema ~= 4.17.3
 pre-commit ~= 3.7.0
 pycodestyle ~= 2.11.0
 pylint >= 2.5.0
-unittest-xml-reporting ~= 3.0.4
+pytest ~= 8.3.3
+pytest-cov ~= 5.0.0

requirements.txt

@@ -1,4 +1,4 @@
 netCDF4 ~= 1.6.3
-numpy ~= 1.24.2
-python-cmr ~= 0.9.0
+numpy >= 1.24.2,< 2.0
+python-cmr ~= 0.12.0
 requests ~= 2.31.0

tests/unit/test_umm_var.py

@@ -977,6 +977,13 @@ def test_generate_variable_native_id(self):
                 'C1234567890-PROV-Grid_time',
             )
 
+        with self.subTest('Space in variable name is replaced with underscore'):
+            umm_var_json = {'Name': '/Grid/variable with space'}
+            self.assertEqual(
+                generate_variable_native_id('C1234567890-PROV', umm_var_json),
+                'C1234567890-PROV-Grid_variable_with_space',
+            )
+
     def test_get_variable_type(self):
         """Test that 'VariableType' in a UMM-Var record is set to
         'SCIENCE_VARIABLE', when a variable is a science variable.

varinfo/cmr_search.py

@@ -5,6 +5,7 @@
 
 from __future__ import annotations
 
+from collections.abc import Sequence
 from typing import Literal
 import os.path
 
@@ -36,7 +37,7 @@ def get_granules(
     provider: str | None = None,
     cmr_env: CmrEnvType = CMR_OPS,
     auth_header: str | None = None,
-) -> list:
+) -> Sequence:
     """Search CMR to retrieve granules for a specific collection given:
 
     * concept_id: a CMR collection or granule concept ID. For most
@@ -79,7 +80,7 @@ def get_granules(
         # If neither condition is met, there aren't enough CMR query parameters
         # to identify the collection.
         raise MissingPositionalArguments(
-            'concept_id or collection_shortname, ' 'collection_version, and provider'
+            'concept_id or collection_shortname, collection_version, and provider'
         )
 
     # Assign parameters to GranuleQuery
@@ -98,13 +99,13 @@ def get_granules(
     if len(granule_response) == 0:
         # No granules were identified, so no files can be downloaded and parsed
         raise IndexError(
-            'No granules were found with selected ' 'parameters and user permissions'
+            'No granules were found with selected parameters and user permissions'
         )
 
     return granule_response
 
 
-def get_granule_link(granule_response: list) -> str:
+def get_granule_link(granule_response: Sequence) -> str:
     """Get the granule download link from CMR."""
     granule_link = next(
         (
@@ -164,7 +165,7 @@ def get_edl_token_from_launchpad(
       <Launchpad token>
     * cmr_env/mode: CMR environments (OPS, UAT, and SIT)
     """
-    url_urs_endpoint = urs_token_endpoints.get(cmr_env)
+    url_urs_endpoint = urs_token_endpoints[cmr_env]
     try:
         response = requests.post(
             url=url_urs_endpoint, data=f'token={launchpad_token}', timeout=10

varinfo/umm_var.py

@@ -403,7 +403,10 @@ def generate_variable_native_id(
 
     """
     return '-'.join(
-        [collection_concept_id, umm_var_record['Name'].replace('/', '_').lstrip('_')]
+        [
+            collection_concept_id,
+            umm_var_record['Name'].replace('/', '_').replace(' ', '_').lstrip('_'),
+        ]
     )