fix(cli): add check of missing references

Author: jirikuncar

renku/cli/_checks/__init__.py

@@ -19,9 +19,11 @@
 
 from .files_in_datasets import check_missing_files
 from .location_datasets import check_dataset_metadata
+from .references import check_missing_references
 
 # Checks will be executed in the order as they are listed in __all__
 __all__ = (
     'check_dataset_metadata',
     'check_missing_files',
+    'check_missing_references',
 )

renku/cli/_checks/references.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright 2019 - Swiss Data Science Center (SDSC)
+# A partnership between École Polytechnique Fédérale de Lausanne (EPFL) and
+# Eidgenössische Technische Hochschule Zürich (ETHZ).
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Check missing references."""
+
+import click
+
+from .._echo import WARNING
+
+
+def check_missing_references(client):
+    """Find missing references."""
+    from renku.models.refs import LinkReference
+
+    missing = [
+        ref for ref in LinkReference.iter_items(client)
+        if not ref.reference.exists()
+    ]
+
+    if not missing:
+        return True
+
+    click.secho(
+        WARNING + 'There are missing references.'
+        '\n  (use "git rm <name>" to clean them)\n\n\t' + '\n\t  '.join(
+            click.style(str(ref.path), fg='yellow') + ' -> ' +
+            click.style(str(ref.reference), fg='red') for ref in missing
+        ) + '\n'
+    )
+    return False

renku/models/refs.py

@@ -94,6 +94,8 @@ def iter_items(cls, client, common_path=None):
             path = path / common_path
 
         for name in path.rglob('*'):
+            if name.is_dir():
+                continue
             yield cls(client=client, name=str(name.relative_to(refs_path)))
 
     @classmethod