def test_forge_anonymous(capsys):
f = Forge(anonymous=True)
# Test search
assert len(
f.search("mdf.source_name:ab_initio_solute_database",
advanced=True,
limit=300)) == 300
# Test aggregation
assert len(f.aggregate("mdf.source_name:nist_xps_db")) > 10000
# Error on auth-only functions
# http_download
assert f.http_download({})["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous HTTP download not yet supported." in out
# globus_download
assert f.globus_download({})["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous Globus Transfer not supported." in out
# http_stream
res = f.http_stream({})
assert next(res)["success"] is False
out, err = capsys.readouterr()
assert "Error: Anonymous HTTP download not yet supported." in out
with pytest.raises(StopIteration):
next(res)
def test_forge_http_download(capsys):
f = Forge(index="mdf")
# Simple case
f.http_download(example_result1)
assert os.path.exists("./test_fetch.txt")
# Test conflicting filenames
f.http_download(example_result1)
assert os.path.exists("./test_fetch(1).txt")
f.http_download(example_result1)
assert os.path.exists("./test_fetch(2).txt")
os.remove("./test_fetch.txt")
os.remove("./test_fetch(1).txt")
os.remove("./test_fetch(2).txt")
# With dest and preserve_dir, and tuple of results
dest_path = os.path.expanduser("~/mdf")
f.http_download(([example_result1], {
"info": None
}),
dest=dest_path,
preserve_dir=True)
assert os.path.exists(os.path.join(dest_path, "test", "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test", "test_fetch.txt"))
os.rmdir(os.path.join(dest_path, "test"))
# With multiple files
f.http_download(example_result2, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "petrel_fetch.txt"))
os.remove(os.path.join(dest_path, "petrel_multifetch.txt"))
f.http_download(example_result3, dest=dest_path)
assert os.path.exists(os.path.join(dest_path, "test_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "test_multifetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert os.path.exists(os.path.join(dest_path, "petrel_multifetch.txt"))
os.remove(os.path.join(dest_path, "test_fetch.txt"))
os.remove(os.path.join(dest_path, "test_multifetch.txt"))
os.remove(os.path.join(dest_path, "petrel_fetch.txt"))
os.remove(os.path.join(dest_path, "petrel_multifetch.txt"))
# Too many files
assert f.http_download(list(range(10001)))["success"] is False
out, err = capsys.readouterr()
assert "Too many results supplied. Use globus_download()" in out
# "Missing" files
f.http_download(example_result_missing)
out, err = capsys.readouterr()
assert not os.path.exists("./should_not_exist.txt")
assert (
"Error 404 when attempting to access "
"'https://data.materialsdatafacility.org/test/should_not_exist.txt'"
) in out
# No datasets
f.http_download(example_dataset)
out, err = capsys.readouterr()
assert not os.path.exists(os.path.join(dest_path, "petrel_fetch.txt"))
assert (
"Skipping datset entry for 'foobar_v1': Cannot download dataset over HTTPS. "
"Use globus_download() for datasets.") in out
# Bad resource_type
f.http_download(example_bad_resource)
out, err = capsys.readouterr()
assert "Error: Found unknown resource_type 'foobar'. Skipping entry." in out
