Ohsu training

.gitignore

@@ -1,4 +1,3 @@
-Secrets/
 *.lock*
 *.env
 *.bak
@@ -10,4 +9,14 @@ Secrets/
 *.pytest_cache
 *.cache
 *pyc
-docker-compose.override.yml
+#docker-compose.override.yml
+# for local dev
+credential*.json
+venv/
+.idea/
+
+/fence/
+
+/output/
+
+

README.md

@@ -1,6 +1,17 @@
+
+ACED - Training
+===
+> This repo was established as a sandbox to introduce Gen3 in a local, docker-compose laptop friendly environment.
+
+Follow the instructions below to introduce Gen3.  Then, see ACED specific steps [here](docs/aced.md) 
+
+
+
 Compose-Services
 ===
 
+
+
 Docker-compose setup for experimental commons, small commons, or local development of the Gen3 stack. Production use should use [cloud-automation](https://github.com/uc-cdis/cloud-automation).
 
 This setup uses Docker containers for the [Gen3 microservices](https://github.com/uc-cdis/) and nginx. The microservices and nginx images are pulled from quay.io (master), while Postgres (9.5) images are pulled from Docker Hub. Nginx is used as a reverse proxy to each of the services. 

datadictionary/README.md

@@ -1,3 +1,15 @@
+
+
+ACED - Training
+===
+> This repo was established as a sandbox to introduce Gen3 in a local, docker-compose laptop friendly environment.
+
+```commandline
+cp ../data_model/DATA/gen3/*.yaml datadictionary/gdcdictionary/schemas/
+
+
+```
+
 # Data Dictionary
 
 The data dictionary provides the first level of validation for all data

datadictionary/gdcdictionary/schemas/_core_metadata_collection.yaml

@@ -0,0 +1,140 @@
+$schema: "http://json-schema.org/draft-04/schema#"
+
+#
+# included because of windmill portal.
+# portal wont build unless this entity exists
+#
+
+id: "core_metadata_collection"
+title: Core Metadata Collection
+type: object
+nodeTerms: null
+namespace: https://data.midrc.org
+category: administrative
+program: '*'
+project: '*'
+description: A collection of data files in a project.  DEPRECATED - included for portal compatibility
+additionalProperties: false
+submittable: true
+validators: null
+
+systemProperties:
+  - id
+  - project_id
+  - state
+  - created_datetime
+  - updated_datetime
+
+links:
+  - name: projects
+    backref: core_metadata_collections
+    label: data_from
+    target_type: project
+    multiplicity: many_to_one
+    required: true
+
+required:
+  - submitter_id
+  - type
+  - projects
+
+uniqueKeys:
+  - [id]
+  - [project_id, submitter_id]
+
+properties:
+
+  $ref: "_definitions.yaml#/ubiquitous_properties"
+
+  contributor:
+    description: An entity responsible for making contributions to the resource. Examples
+      of a Contributor include a person, an organization, or a service. Typically,
+      the name of a Contributor should be used to indicate the entity.
+    type: string
+
+  coverage:
+    description: The spatial or temporal topic of the resource, the spatial applicability
+      of the resource, or the jurisdiction under which the resource is relevant. Spatial
+      topic and spatial applicability may be a named place or a location specified
+      by its geographic coordinates. Temporal topic may be a named period, date, or
+      date range. A jurisdiction may be a named administrative entity or a geographic
+      place to which the resource applies. Recommended best practice is to use a controlled
+      vocabulary such as the Thesaurus of Geographic Names [TGN] (http-//www.getty.edu/research/tools/vocabulary/tgn/index.html).
+      Where appropriate, named places or time periods can be used in preference to
+      numeric identifiers such as sets of coordinates or date ranges.
+    type: string
+
+  creator:
+    description: An entity primarily responsible for making the resource. Examples
+      of a Creator include a person, an organization, or a service. Typically, the
+      name of a Creator should be used to indicate the entity.
+    type: string
+
+  data_type:
+    description: The nature or genre of the resource. Recommended best practice is
+      to use a controlled vocabulary such as the DCMI Type Vocabulary [DCMITYPE].
+      To describe the file format, physical medium, or dimensions of the resource,
+      use the Format element.
+    type: string
+
+  date:
+    description: The date the collection of data was created.
+    type: string
+
+  description:
+    description: An account of the resource. Description may include but is not limited
+      to- an abstract, a table of contents, a graphical representation, or a free-text
+      account of the resource.
+    type: string
+
+  format:
+    description: The file format, physical medium, or dimensions of the resource.
+      Examples of dimensions include size and duration. Recommended best practice
+      is to use a controlled vocabulary such as the list of Internet Media Types [MIME]
+      (http-//www.iana.org/assignments/media-types/).
+    type: string
+
+  language:
+    description: A language of the resource. Recommended best practice is to use a
+      controlled vocabulary such as RFC 4646 (http-//www.ietf.org/rfc/rfc4646.txt).
+    type: string
+
+  publisher:
+    description: An entity responsible for making the resource available. Examples
+      of a Publisher include a person, an organization, or a service. Typically, the
+      name of a Publisher should be used to indicate the entity.
+    type: string
+
+  relation:
+    description: A related resource. Recommended best practice is to identify the
+      related resource by means of a string conforming to a formal identification
+      system.
+    type: string
+
+  rights:
+    description: Information about rights held in and over the resource. Typically,
+      rights information includes a statement about various property rights associated
+      with the resource, including intellectual property rights.
+    type: string
+
+  source:
+    description: A related resource from which the described resource is derived.
+      The described resource may be derived from the related resource in whole or
+      in part. Recommended best practice is to identify the related resource by means
+      of a string conforming to a formal identification system.
+    type: string
+
+  subject:
+    description: The topic of the resource. Typically, the subject will be represented
+      using keywords, key phrases, or classification codes. Recommended best practice
+      is to use a controlled vocabulary.
+    type: string
+
+  title:
+    description: A name given to the resource. Typically, a Title will be a name by
+      which the resource is formally known.
+    type: string
+
+  projects:
+    description: The project code for the record in the project node that this core_metadata_collection belongs to, i.e., a link to the parent node.
+    $ref: "_definitions.yaml#/to_one_project"

datadictionary/gdcdictionary/schemas/_definitions.yaml

@@ -18,8 +18,8 @@ foreign_key_project:
     # Allow true here because we can have other unique keys defined on
     # a target type
     additionalProperties: true
-    # Can either use 'id' which are Gen3 IDs (UUID) or 'code'
-    # which is the user defined ID for project
+    #Can either use 'id' which are Gen3 IDs (UUID) or 'code'
+    #which is the user defined ID for project
     properties:
         id:
             $ref: "#/UUID"
@@ -48,8 +48,8 @@ foreign_key:
     # Allow true here because we can have other unique keys defined on
     # a target type
     additionalProperties: True
-    # Can either use 'id' which are GDC IDs (UUID) or 'submitter_id'
-    # which are user defined IDs ("submitter IDs in the backend")
+    #Can either use 'id' which are GDC IDs (UUID) or 'submitter_id'
+    #which are user defined IDs ("submitter IDs in the backend")
     properties:
         id:
             $ref: "#/UUID"
@@ -88,19 +88,24 @@ file_name:
 
 file_size:
     type: integer
-    term: 
+    term:
         $ref: "_terms.yaml#/file_size"
 
 file_format:
     type: string
     term:
         $ref: "_terms.yaml#/file_format"
 
+ga4gh_drs_uri:
+    type: string
+    term:
+        $ref: "_terms.yaml#/ga4gh_drs_uri"
+
 md5sum:
     type: string
-    pattern: "^[a-f0-9]{32}$"
     term:
         $ref: "_terms.yaml#/md5sum"
+    pattern: "^[a-f0-9]{32}$"
 
 object_id:
     type: string
@@ -135,7 +140,7 @@ data_file_error_type:
 
 state:
     term:
-        $ref: "_terms.yaml#/state" 
+        $ref: "_terms.yaml#/state"
     default: validated
     downloadable:
         - uploaded
@@ -166,7 +171,7 @@ state:
 
 file_state:
     term:
-        $ref: "_terms.yaml#/file_state" 
+        $ref: "_terms.yaml#/file_state"
     default: registered
     enum:
         - registered
@@ -194,49 +199,26 @@ project_id:
         $ref: "_terms.yaml#/project_id"
 
 data_file_properties:
-  id:
-    $ref: "#/UUID"
-    systemAlias: node_id
-  submitter_id:
-    type:
-      - string
-      - "null"
-    description: "The file ID assigned by the submitter." # TOREVIEW
+  $ref: "#/ubiquitous_properties"
   file_name:
     $ref: "#/file_name"
   file_size:
     $ref: "#/file_size"
+  file_format:
+    $ref: "#/file_format"  
   md5sum:
-    $ref: "#/md5sum" 
-  file_state:
-    $ref: "#/file_state"
+    $ref: "#/md5sum"
   object_id:
     $ref: "#/object_id"
-  state:
-    $ref: "#/state"
+  file_state:
+    $ref: "#/file_state"
   error_type:
     $ref: "#/data_file_error_type"
-  state_comment:
-    type: string
-    description: > 
-      Optional comment about why the file is in the
-      current state, mainly for invalid state.
-  project_id:
-    $ref: "#/project_id"
-  created_datetime:
-    $ref: "#/datetime"
-  updated_datetime:
-    $ref: "#/datetime"
+  ga4gh_drs_uri:
+    $ref: "#/ga4gh_drs_uri"
 
 workflow_properties:
-  id:
-    $ref: "#/UUID"
-    systemAlias: node_id
-  submitter_id:
-    type:
-      - string
-      - "null"
-    description: "The file ID assigned by the submitter." # TOREVIEW
+  $ref: "#/ubiquitous_properties"
   workflow_link:
     description: "Link to Github hash for the CWL workflow used."
     type: string
@@ -247,14 +229,6 @@ workflow_properties:
     $ref: "#/datetime"
   workflow_end_datetime:
     $ref: "#/datetime"
-  state:
-    $ref: "#/state"
-  project_id:
-    $ref: "#/project_id"
-  created_datetime:
-    $ref: "#/datetime"
-  updated_datetime:
-    $ref: "#/datetime"
 
 ubiquitous_properties:
   type:
@@ -276,3 +250,15 @@ ubiquitous_properties:
     $ref: "#/datetime"
   updated_datetime:
     $ref: "#/datetime"
+
+
+fhir_resource:
+    type: object
+    # Allow true here because we can have other unique keys defined on
+    # a target type
+    additionalProperties: true
+    properties:
+        id:
+            $ref: "#/UUID"
+        resource_type:
+            type: string