Merge pull request #1386 from harshitbansal05/develop

Add test and doc string for get_datasets_upstream

retriever/lib/__init__.py

@@ -17,6 +17,7 @@
 from .fetch import fetch
 from .scripts import reload_scripts
 from .scripts import get_script_upstream
+from .scripts import get_dataset_names_upstream
 
 __all__ = [
     'check_for_updates',
@@ -36,5 +37,6 @@
     'install_json',
     'install_xml',
     'fetch',
-    'get_script_upstream'
+    'get_script_upstream',
+    'get_dataset_names_upstream'
 ]

retriever/lib/scripts.py

@@ -306,7 +306,11 @@ def get_script_version_upstream(dataset, repo=REPOSITORY):
 
 
 def get_dataset_names_upstream(keywords=None, licenses=None, repo=REPOSITORY):
-    """Search all datasets upstream by keywords and licenses."""
+    """Search all datasets upstream by keywords and licenses. If the keywords
+    or licenses argument is passed, Github's search API is used for looking
+    in the repositories. Else, the version.txt file is read and the script
+    names are then returned.
+    """
     if not keywords and not licenses:
         version_file_request = get_data_upstream(repo + "version.txt")
         if not version_file_request:

test/test_retriever.py

@@ -202,6 +202,16 @@ def test_dataset_names():
     assert 'mammal-masses' in dataset_names
 
 
+def test_dataset_names_upstream():
+    """Check if upstream datasets include a known value"""
+    datasets = rt.get_dataset_names_upstream()
+    assert 'portal' in datasets
+    license_datasets = rt.get_dataset_names_upstream(licenses=['CC0-1.0'])
+    assert 'bird-size' in license_datasets
+    keyword_datasets = rt.get_dataset_names_upstream(keywords=['plants'])
+    assert 'biodiversity-response' in keyword_datasets
+
+
 def test_drop_statement():
     """Test the creation of drop statements."""
     assert test_engine.drop_statement(