Merge pull request #36 from dlcs/feature/composite_id

Handle "compositeId" parameter

README.md

@@ -24,7 +24,7 @@ Additionally, the project uses:
 The project ships with a [`docker-compose.yml`](docker-compose.yml) that can be used to get a local version of the component running:
 
 ```bash
-docker-compose up
+docker compose up
 ```
 
 > Note that for the Composite Handler to be able to interact with the target S3 bucket, the Docker Compose assumes that the `AWS_PROFILE` environment variable has been set and a valid AWS session is available.
@@ -58,7 +58,7 @@ The administrator user can be used to browse the database and manage the queue (
 There are 3 possible entrypoints to make the above easier:
 
 * `entrypoint.sh` - this will wait for Postgres to be available and run `manage.py migrate` and `manage.py createcachetable` if `MIGRATE=True`. It will run `manage.py createsuperuser` is `INIT_SUPERUSER=True` (also needs `DJANGO_SUPERUSER_*` envvars)
-* `entrypoint-api.sh` - this runs above then `python manage.py runserver 0.0.0.0:8000`
+* `entrypoint-api.sh` - this runs above then starts nginx instance fronting gunicorn process
 * `entrypoint-worker.sh` - this runs above then `python manage.py qcluster`
 
 ## Configuration
@@ -88,6 +88,7 @@ The following list of environment variables are supported:
 | `ENGINE_WORKER_MAX_ATTEMPTS`  | `0`                            | Engine       | The number of processing attempts a single task will undergo before it is abandoned. Setting this value to `0` will cause a task to be retried forever.                                                                                                                      |
 | `MIGRATE`                     | None                           | API, Engine  | If "True" will run migrations + createcachetable on startup if entrypoint used.                                                                                                                                                                                              |
 | `INIT_SUPERUSER`              | None                           | API, Engine  | If "True" will attempt to create superuser. Needs standard Django envvars to be set (e.g. `DJANGO_SUPERUSER_USERNAME`, `DJANGO_SUPERUSER_EMAIL`, `DJANGO_SUPERUSER_PASSWORD`) if entrypoint used.                                                                            |
+| `GUNICORN_WORKERS`            | `2`                            | API          | The value of [`--workers`](https://docs.gunicorn.org/en/stable/run.html) arg when running gunicorn                                                                                                                                                                           |
 
 Note that in order to access the S3 bucket, the Composite Handler assumes that valid AWS credentials are available in the environment - this can be in the former of [environment variables](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-envvars.html), or in the form of ambient credentials.
 
@@ -96,15 +97,15 @@ Note that in order to access the S3 bucket, the Composite Handler assumes that v
 The project ships with a [`Dockerfile`](./Dockerfile):
 
 ```bash
-docker build -t dlcs/composite-handler:latest .
+docker build -t dlcs/composite-handler:local .
 ```
 
 This will produce a single image that can be used to execute any of the supported Django commands, including running the API and the engine:
 
 ```bash
-docker run dlcs/composite-handler:latest python manage.py migrate # Apply any pending DB schema changes
-docker run dlcs/composite-handler:latest python manage.py createcachetable # Create the cache table (if it doesn't exist)
-docker run dlcs/composite-handler:latest python manage.py runserver 0.0.0.0:8000 # Run the API
-docker run dlcs/composite-handler:latest python manage.py qcluster # Run the engine
-docker run dlcs/composite-handler:latest python manage.py qmonitor # Monitor the workers
+docker run dlcs/composite-handler:local python manage.py migrate # Apply any pending DB schema changes
+docker run dlcs/composite-handler:local python manage.py createcachetable # Create the cache table (if it doesn't exist)
+docker run --env-file .env -it --rm dlcs/composite-handler:local /srv/dlcs/entrypoint-api.sh # Run the API
+docker run --env-file .env -it --rm dlcs/composite-handler:local /srv/dlcs/entrypoint-worker.sh # Run the engine
+docker run dlcs/composite-handler:local python manage.py qmonitor # Monitor the workers
 ```

src/app/api/schemas/member.schema.json

@@ -71,6 +71,9 @@
     },
     "incrementSeed": {
       "type": "integer"
+    },
+    "compositeId": {
+      "type": "string"
     }
   },
   "required": [

src/app/engine/builder.py

@@ -4,7 +4,7 @@
 class MemberBuilder:
     STATIC_FIELDS = {"mediaType": "image/jpeg", "family": "I"}
 
-    STRIP_FIELDS = ["@type", "originFormat", "incrementSeed"]
+    STRIP_FIELDS = ["@type", "originFormat", "incrementSeed", "compositeId"]
 
     FORMAT_FIELDS = [
         "id",
@@ -26,7 +26,8 @@ def __init__(self, template):
     def __build_template(self, original_template):
         template = dict(original_template) | self.STATIC_FIELDS
         for strip_field in self.STRIP_FIELDS:
-            template.pop(strip_field)
+            if strip_field in template:
+                template.pop(strip_field)
         return template
 
     def build_member(self, dlcs_uri):

src/app/engine/s3.py

@@ -26,9 +26,13 @@ def __build_bucket_base_url(self):
         else:
             return f"https://s3.amazonaws.com/{self._bucket_name}"
 
-    def put_images(self, submission_id, images):
+    def put_images(self, images, submission_id, composite_id, customer_id, space_id):
         s3_uris = []
 
+        key_prefix = self.__get_key_prefix(
+            submission_id, composite_id, customer_id, space_id
+        )
+
         with tqdm.tqdm(
             desc=f"[{submission_id}] Upload images to S3",
             unit=" image",
@@ -39,14 +43,17 @@ def put_images(self, submission_id, images):
                 # same order as the list of images provided to it. '.map(...)' gives us that,
                 # whilst '.submit(...)' does not.
                 for s3_uri in executor.map(
-                    self.__put_image, repeat(submission_id), images
+                    self.__put_image, repeat(key_prefix), images
                 ):
                     s3_uris.append(s3_uri)
                     progress_bar.update(1)
         return s3_uris
 
-    def __put_image(self, submission_id, image):
-        object_key = f"{self._object_key_prefix}/{submission_id}/{os.path.basename(image.filename)}"
+    def __get_key_prefix(self, submission_id, composite_id, customer, space):
+        return f"{self._object_key_prefix}/{customer}/{space}/{composite_id or submission_id}"
+
+    def __put_image(self, key_prefix, image):
+        object_key = f"{key_prefix}/{os.path.basename(image.filename)}"
         with open(image.filename, "rb") as file:
             self._client.put_object(Bucket=self._bucket_name, Key=object_key, Body=file)
         return f"{self._bucket_base_url}/{object_key}"

src/app/engine/tasks.py

@@ -57,7 +57,10 @@ def __rasterize_composite(member, pdf_path):
 
 def __push_images_to_dlcs(member, images):
     __update_status(member, "PUSHING_TO_DLCS", image_count=len(images))
-    return s3_client.put_images(member.id, images)
+    composite_id = member.json_data.get("compositeId")
+    customer = member.collection.customer
+    space = member.json_data["space"]
+    return s3_client.put_images(images, member.id, composite_id, customer, space)
 
 
 def __build_dlcs_requests(member, dlcs_uris):