Merge ce3cca2 into 9c776fb

.docker-compose.env

@@ -1 +1,11 @@
+CELERY_BROKER_URL=amqp://guest:guest@rabbitmq:5672
+DATABASE_HOST=postgres
+ELASTICSEARCH_URL=http://elasticsearch:9200/
+EMBER_SHARE_URL=http://frontend:4200
+LOGIN_REDIRECT_URL=http://localhost:8003/
+OSF_API_URL=http://localhost:8000
+RABBITMQ_HOST=rabbitmq
+RABBITMQ_PORT=5672
+SHARE_API_URL=http://web:8000/
+
 #PYTHONUNBUFFERED=0 # This when set to 0 will allow print statements to be visible in the Docker logs

README.md

@@ -24,7 +24,7 @@ We'll be expanding this section in the near future, but, beyond using our API fo
 ## Setup for testing
 It is useful to set up a [virtual environment](http://virtualenvwrapper.readthedocs.io/en/latest/install.html) to ensure [python3](https://www.python.org/downloads/) is your designated version of python and make the python requirements specific to this project.
 
-    mkvirtualenv share -p `which python3.5`
+    mkvirtualenv share -p `which python3.6`
     workon share
 
 Once in the `share` virtual environment, install the necessary requirements, then setup SHARE.

api/normalizeddata/serializers.py

@@ -12,9 +12,12 @@ class FullNormalizedDataSerializer(serializers.ModelSerializer):
     tasks = serializers.PrimaryKeyRelatedField(many=True, read_only=False, queryset=models.CeleryTaskResult.objects.all())
     source = serializers.HiddenField(default=serializers.CurrentUserDefault())
 
+    # TODO make suid required
+    suid = serializers.CharField(write_only=True, required=False)
+
     class Meta:
         model = models.NormalizedData
-        fields = ('data', 'source', 'raw', 'tasks', 'url')
+        fields = ('data', 'source', 'raw', 'tasks', 'url', 'suid')
 
 
 class BasicNormalizedDataSerializer(serializers.ModelSerializer):
@@ -23,6 +26,9 @@ class BasicNormalizedDataSerializer(serializers.ModelSerializer):
 
     source = serializers.HiddenField(default=serializers.CurrentUserDefault())
 
+    # TODO make suid required
+    suid = serializers.CharField(write_only=True, required=False)
+
     class Meta:
         model = models.NormalizedData
-        fields = ('data', 'source', 'url')
+        fields = ('data', 'source', 'url', 'suid')

api/normalizeddata/views.py

@@ -3,11 +3,14 @@
 
 from rest_framework import status
 from rest_framework import generics
+from rest_framework.exceptions import ValidationError
 from rest_framework.response import Response
 
 from share import models
 from share.tasks import ingest
 from share.util import IDObfuscator
+from share.util.graph import MutableGraph
+from share.util.osf import guess_osf_guid
 from share.ingest.ingester import Ingester
 
 from api.base.views import ShareViewSet
@@ -64,9 +67,18 @@ def get_queryset(self):
     def create(self, request, *args, **kwargs):
         serializer = self.get_serializer_class()(data=request.data, context={'request': request})
         serializer.is_valid(raise_exception=True)
+
+        data = serializer.validated_data['data']
+        suid = serializer.validated_data.get('suid', None)
+        if not suid:
+            # HACK: try for an osf guid -- may still be None tho
+            suid = guess_osf_guid(MutableGraph.from_jsonld(data))
+            if not suid:
+                raise ValidationError("'suid' is a required attribute")
+
         with transaction.atomic():
             # Hack for back-compat: Ingest halfway synchronously, then apply changes asynchronously
-            ingester = Ingester(serializer.validated_data['data']).as_user(request.user).ingest(apply_changes=False)
+            ingester = Ingester(data, suid).as_user(request.user).ingest(apply_changes=False)
             ingester.job.reschedule(claim=True)
 
             nd_id = models.NormalizedData.objects.filter(

api/search/views.py

@@ -45,7 +45,7 @@ def get(self, request, *args, url_bits='', **kwargs):
         params = request.query_params.copy()
 
         v = params.pop('v', None)
-        index = settings.ELASTICSEARCH['INDEX']
+        index = settings.ELASTICSEARCH['PRIMARY_INDEX']
         if v:
             v = 'v{}'.format(v[0])
             if v not in settings.ELASTICSEARCH['INDEX_VERSIONS']:
@@ -75,7 +75,7 @@ def post(self, request, *args, url_bits='', **kwargs):
         params = request.query_params.copy()
 
         v = params.pop('v', None)
-        index = settings.ELASTICSEARCH['INDEX']
+        index = settings.ELASTICSEARCH['PRIMARY_INDEX']
         if v:
             v = 'v{}'.format(v[0])
             if v not in settings.ELASTICSEARCH['INDEX_VERSIONS']:
@@ -117,7 +117,7 @@ def _handle_request(self, request, url_bits):
             return http.HttpResponseForbidden(reason='Scroll is not supported.')
 
         v = params.pop('v', None)
-        index = settings.ELASTICSEARCH['INDEX']
+        index = settings.ELASTICSEARCH['PRIMARY_INDEX']
         if v:
             v = 'v{}'.format(v[0])
             if v not in settings.ELASTICSEARCH['INDEX_VERSIONS']:

api/views/feeds.py

@@ -84,7 +84,7 @@ def get_object(self, request):
 
     def items(self, obj):
         headers = {'Content-Type': 'application/json'}
-        search_url = '{}{}/creativeworks/_search'.format(settings.ELASTICSEARCH['URL'], settings.ELASTICSEARCH['INDEX'])
+        search_url = '{}{}/creativeworks/_search'.format(settings.ELASTICSEARCH['URL'], settings.ELASTICSEARCH['PRIMARY_INDEX'])
         elastic_response = requests.post(search_url, data=json.dumps(obj), headers=headers)
         json_response = elastic_response.json()