diff --git a/nomad/api/raw.py b/nomad/api/raw.py
index 4096ff669dbde82504081b2f70e238406420e0f7..51fe17f7d4eb95f09a9dfe4691705fcbcd16f596 100644
--- a/nomad/api/raw.py
+++ b/nomad/api/raw.py
@@ -379,7 +379,7 @@ class RawFileQueryResource(Resource):
with zipfile_cache:
for filename in list(upload_files.raw_file_manifest(path_prefix=os.path.dirname(mainfile))):
- yield filename, upload_files
+ yield os.path.join(upload_id, filename), filename, upload_files
return _streamed_zipfile(generator(), zipfile_name='nomad_raw_files.zip')
@@ -399,12 +399,12 @@ def respond_to_get_raw_files(upload_id, files, compress=False):
with zipfile_cache:
return _streamed_zipfile(
- [(filename, upload_files) for filename in files],
+ [(filename, filename, upload_files) for filename in files],
zipfile_name='%s.zip' % upload_id, compress=compress)
def _streamed_zipfile(
- files: Iterable[Tuple[str, UploadFiles]], zipfile_name: str, compress: bool = False):
+ files: Iterable[Tuple[str, str, UploadFiles]], zipfile_name: str, compress: bool = False):
def generator():
""" Stream a zip file with all files using zipstream. """
@@ -413,10 +413,10 @@ def _streamed_zipfile(
Replace the directory based iter of zipstream with an iter over all given
files.
"""
- for filename, upload_files in files:
+ for zipped_filename, upload_filename, upload_files in files:
# Write a file to the zipstream.
try:
- with upload_files.raw_file(filename, 'rb') as f:
+ with upload_files.raw_file(upload_filename, 'rb') as f:
def iter_content():
while True:
data = f.read(100000)
@@ -424,7 +424,7 @@ def _streamed_zipfile(
break
yield data
- yield dict(arcname=filename, iterable=iter_content())
+ yield dict(arcname=zipped_filename, iterable=iter_content())
except KeyError:
# files that are not found, will not be returned
pass
diff --git a/nomad/datamodel/base.py b/nomad/datamodel/base.py
index 9b416118227a8e6f53b16ddd0fe53e4cbb6a9c63..2808f1beab373f4c2a86806a614f6cfdc9e37acb 100644
--- a/nomad/datamodel/base.py
+++ b/nomad/datamodel/base.py
@@ -269,7 +269,10 @@ class Domain:
mainfile=DomainQuantity(description='Search for the mainfile.'),
datasets=DomainQuantity(
elastic_field='datasets.name', multi=True,
- description='Search for a particular dataset by name.'))
+ description='Search for a particular dataset by name.'),
+ doi=DomainQuantity(
+ elastic_field='datasets.doi', elastic_search_type='match', multi=True,
+ description='Search for a particular dataset by doi (incl. http://dx.doi.org).'))
def __init__(
self, name: str, domain_entry_class: Type[CalcWithMetadata],
diff --git a/tests/conftest.py b/tests/conftest.py
index 63d173d93d4d11641198d4bd45be89322c2d70c8..d322b9f5a162a4cfee3c301883762e2b56775b0d 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -12,7 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-from typing import Tuple
+from typing import Tuple, List
import pytest
import logging
from sqlalchemy.orm import Session
@@ -555,6 +555,18 @@ def processed(uploaded: Tuple[str, str], test_user: coe_repo.User, proc_infra) -
return test_processing.run_processing(uploaded, test_user)
+@pytest.mark.timeout(config.tests.default_timeout)
+@pytest.fixture(scope='function')
+def processeds(non_empty_example_upload: str, test_user: coe_repo.User, proc_infra) -> List[processing.Upload]:
+ result: List[processing.Upload] = []
+ for i in range(2):
+ upload_id = '%s_%d' % (os.path.basename(non_empty_example_upload).replace('.zip', ''), i)
+ result.append(
+ test_processing.run_processing((upload_id, non_empty_example_upload), test_user))
+
+ return result
+
+
@pytest.mark.timeout(config.tests.default_timeout)
@pytest.fixture(scope='function')
def non_empty_processed(non_empty_uploaded: Tuple[str, str], test_user: coe_repo.User, proc_infra) -> processing.Upload:
diff --git a/tests/test_api.py b/tests/test_api.py
index 53ccaf807a1f93726f26df48caedb57a84688448..d3323319b183a16dff59dfbf691e938b669f82ae 100644
--- a/tests/test_api.py
+++ b/tests/test_api.py
@@ -1030,7 +1030,7 @@ class TestRaw(UploadFilesBasedTests):
assert zip_file.testzip() is None
assert len(zip_file.namelist()) == len(example_file_contents)
- def test_raw_files_from_query(self, client, non_empty_processed, test_user_auth):
+ def test_raw_files_from_query_upload_id(self, client, non_empty_processed, test_user_auth):
url = '/raw/query?upload_id=%s' % non_empty_processed.upload_id
rv = client.get(url, headers=test_user_auth)
@@ -1040,6 +1040,21 @@ class TestRaw(UploadFilesBasedTests):
assert zip_file.testzip() is None
assert len(zip_file.namelist()) == len(example_file_contents)
+ @pytest.mark.parametrize('query_params', [
+ {'atoms': 'Si'},
+ {'authors': 'Cooper, Sheldon'}
+ ])
+ def test_raw_files_from_query(self, client, processeds, test_user_auth, query_params):
+
+ url = '/raw/query?%s' % urlencode(query_params)
+ rv = client.get(url, headers=test_user_auth)
+
+ assert rv.status_code == 200
+ assert len(rv.data) > 0
+ with zipfile.ZipFile(io.BytesIO(rv.data)) as zip_file:
+ assert zip_file.testzip() is None
+ assert len(zip_file.namelist()) == len(example_file_contents) * len(processeds)
+
def test_raw_files_from_empty_query(self, client, elastic):
url = '/raw/query?upload_id=doesNotExist'
rv = client.get(url)