From 21b5e8c90186e05bda840ee1bf51acc34583c153 Mon Sep 17 00:00:00 2001
From: Sean Kelly <kelly@seankelly.biz>
Date: Wed, 9 Jun 2021 16:50:17 -0500
Subject: [PATCH] Resolve #13
---
README.md | 33 +++++--------------
docker-compose.yaml | 18 +++++-----
.../edrn/rdf/dmccprotocolrdfgenerator.py | 18 ++++++++--
3 files changed, 33 insertions(+), 36 deletions(-)
diff --git a/README.md b/README.md
index 9882ba3..bbabdb1 100644
--- a/README.md
+++ b/README.md
@@ -59,6 +59,7 @@ Here are the environment variables you'll need to set (substituting values betwe
- `EDRN_CANCERDATAEXPO_DATA` — set to a path to contain blobstorage, filestorage, and logs.
- `EDRN_CANCERDATAEXPO_PORT` — set to a free port number
- `EDRN_CANCERDATAEXPO_VERSION` — set to a version number of `latest`
+- `EDRN_IMAGE_OWNER` — set to `nutjob4life` or leave it blank to use your local Docker containers
### 🧱 Building the Image
@@ -89,19 +90,16 @@ To run the CancerDataExpo for the **first time**, create empty directories to ho
--project-name cancerdataexpo \
up --detach
+The `docker-compose.yaml` assumes that `EDRN_CANCERDATAEXPO_DATA` is `usr/local/labcas/cancerdataexpo/docker-data` which is appropriate for `edrn-docker.jpl.nasa.gov` where this normally runs, and that `EDRN_CANCERDATAEXPO_PORT` is 2131, and that `EDRN_CANCERDATAEXPO_VERSION` is `latest`, so you can simply say:
+
+ docker-compose --project-name cancerdataexpo up --detach
+
You can check the logs with:
- env \
- EDRN_CANCERDATAEXPO_DATA=/usr/local/labcas/cancerdataexpo/docker-data \
- EDRN_CANCERDATAEXPO_VERSION=latest \
- EDRN_CANCERDATAEXPO_PORT=2131 \
- docker-compose \
- --project-name cancerdataexpo \
- logs --follow
+ docker-compose --project-name cancerdataexpo logs --follow
**📝 Note:** With no existing database, the initiall startup might fail (see the logs, message "Resource Busy"). If this happens, stop it and start it again.
-
Once this is up and running, head to http://localhost:${EDRN_CANCERDATAEXPO_PORT}/manage_main and log in (with username `admin` and password `admin`) and change the default password in the `acl_users` object. Next, create an instance of the CancerDataExpo by visiting http://localhost:${EDRN_CANCERDATAEXPO_PORT}/@@plone-addsite?site_id=Plone&advanced=1 and entering the following:
- Path identifier: `cancerdataexpo`
@@ -123,25 +121,14 @@ Then click "Save". Lastly, head to the RDF Generators and give the LabCAS genera
Need to bring it all down?
- env \
- EDRN_CANCERDATAEXPO_DATA=/usr/local/labcas/cancerdataexpo/docker-data \
- EDRN_CANCERDATAEXPO_VERSION=latest \
- EDRN_CANCERDATAEXPO_PORT=2131 \
- docker-compose \
- --project-name cancerdataexpo \
- down
+ docker-compose --project-name cancerdataexpo down
+
### 🎽 Subsequent Runs
Start it up again?
- env \
- EDRN_CANCERDATAEXPO_DATA=/usr/local/labcas/cancerdataexpo/docker-data \
- EDRN_CANCERDATAEXPO_VERSION=latest \
- EDRN_CANCERDATAEXPO_PORT=2131 \
- docker-compose \
- --project-name cancerdataexpo \
- up --detach
+ docker-compose --project-name cancerdataexpo up --detach
#### 🐛 Advanced Debugging
@@ -160,5 +147,3 @@ Add a Manager user (not through the web, like above):
Get a shell:
docker container run --volume ${EDRN_CANCERDATAEXPO_DATA}/blobstorage:/data/blobstorage --tty --rm --interactive --network cancerdataexpo_frontsidebus --entrypoint /bin/bash cancerdataexpo:latest
-
-
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 8e727cb..11b094d 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -4,17 +4,16 @@
---
services:
appserver:
- # image: cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
- image: nutjob4life/cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
+ image: ${EDRN_IMAGE_OWNER-nutjob4life/}cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
volumes:
-
type: bind
- source: ${EDRN_CANCERDATAEXPO_DATA}/blobstorage
+ source: ${EDRN_CANCERDATAEXPO_DATA:-/usr/local/labcas/cancerdataexpo/docker-data}/blobstorage
target: /data/blobstorage
consistency: consistent
-
type: bind
- source: ${EDRN_CANCERDATAEXPO_DATA}/log
+ source: ${EDRN_CANCERDATAEXPO_DATA:-/usr/local/labcas/cancerdataexpo/docker-data}/log
target: /data/log
consistency: delegated
ports:
@@ -41,23 +40,22 @@ services:
org.label-schema.name: CancerDataExpo Application Server
org.label-schema.description: Zope appserver running the exposition for cancer data.
db:
- # image: cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
- image: nutjob4life/cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
+ image: ${EDRN_IMAGE_OWNER-nutjob4life/}cancerdataexpo:${EDRN_CANCERDATAEXPO_VERSION:-latest}
command: zeo
volumes:
-
type: bind
- source: ${EDRN_CANCERDATAEXPO_DATA}/filestorage
+ source: ${EDRN_CANCERDATAEXPO_DATA:-/usr/local/labcas/cancerdataexpo/docker-data}/filestorage
target: /data/filestorage
consistency: consistent
-
type: bind
- source: ${EDRN_CANCERDATAEXPO_DATA}/blobstorage
+ source: ${EDRN_CANCERDATAEXPO_DATA:-/usr/local/labcas/cancerdataexpo/docker-data}/blobstorage
target: /data/blobstorage
consistency: consistent
-
type: bind
- source: ${EDRN_CANCERDATAEXPO_DATA}/log
+ source: ${EDRN_CANCERDATAEXPO_DATA:-/usr/local/labcas/cancerdataexpo/docker-data}/log
target: /data/log
consistency: delegated
networks:
@@ -72,7 +70,7 @@ services:
org.label-schema.name: CancerDataExpo DB Server
org.label-schema.description: Zope Enterprise Objects DB server for the cancer data exposition.
memory-cache:
- image: memcached
+ image: memcached:1.6.9-alpine
networks:
- frontsidebus
restart: on-failure
diff --git a/src/edrn.rdf/edrn/rdf/dmccprotocolrdfgenerator.py b/src/edrn.rdf/edrn/rdf/dmccprotocolrdfgenerator.py
index 38eba07..d2c7d52 100644
--- a/src/edrn.rdf/edrn/rdf/dmccprotocolrdfgenerator.py
+++ b/src/edrn.rdf/edrn/rdf/dmccprotocolrdfgenerator.py
@@ -1,5 +1,5 @@
# encoding: utf-8
-# Copyright 2012 California Institute of Technology. ALL RIGHTS
+# Copyright 2012–2021 California Institute of Technology. ALL RIGHTS
# RESERVED. U.S. Government Sponsorship acknowledged.
'''DMCC Protocol RDF Generator. An RDF generator that describes EDRN protocols using the DMCC's bungling web services.
@@ -178,6 +178,12 @@ class IDMCCProtocolRDFGenerator(IRDFGenerator):
description=_('Uniform Resource Identifier for the cancer type predicate.'),
required=True,
)
+ cancerTypeURIPrefix = schema.TextLine(
+ title=_('Disease URI Prefix'),
+ description=_('URI prefix to identity Disease objects for the cancer type studied by a protocol.'),
+ required=True,
+ default='http://edrn.nci.nih.gov/data/diseases/'
+ )
commentsURI = schema.TextLine(
title=_('Comments URI'),
description=_('Uniform Resource Identifier for the comments predicate.'),
@@ -412,7 +418,6 @@ def addToGraph(self, graph, context):
'Protocol_Aims': 'aimsURI',
'Protocol_Analytic_Method': 'analyticMethodURI',
'Protocol_Blinding': 'blindingURI',
- 'Protocol_Cancer_Type': 'cancerTypeURI',
'Protocol_Collaborative_Group': 'collaborativeGroupTextURI',
'Protocol_Comments': 'commentsURI',
'Protocol_Data_Sharing_Plan': 'dataSharingPlanURI',
@@ -484,13 +489,22 @@ def _addMiscFields(self, graph, context):
if not obj: continue
predicateURI = URIRef(getattr(context, predicateFieldName))
graph.add((subjectURI, predicateURI, Literal(obj)))
+ def _addCancerTypes(self, graph, context):
+ subjectURI, predicateURI = self.getSubjectURI(context), URIRef(context.cancerTypeURI)
+ values = self.slots.get('Protocol_Cancer_Type', '')
+ for value in values.strip().split(', '):
+ value = value.strip()
+ if value:
+ graph.add((subjectURI, predicateURI, URIRef(context.cancerTypeURIPrefix + value)))
def addToGraph(self, graph, specifics, context):
self._addInvolvedInvestigatorSites(graph, specifics, context)
self._addOtherSites(graph, context)
self._addPublications(graph, context)
self._addFieldsOfResearch(graph, context)
+ self._addCancerTypes(graph, context)
self._addMiscFields(graph, context)
+
_specificsMap = {
'Animal_Subject_Training_Received': 'animalTraining',
'Human_Subject_Training_Recieved': 'humanTraining',