Adding data curation tool to Harvard Dataverse

.gitignore

@@ -1,3 +1,9 @@
+# do not track IntelliJ IDEA files #
+####################################
+.idea
+**/*.iml
+/bin/
+
 # Logs and databases #
 ######################
 docker-dev-volumes/

README.md

@@ -7,4 +7,7 @@ Additionally, configuration files for Harvard Dataverse are kept here, including
 - [customization](customization): custom header, footer, etc.
 - [metadatablocks](metadatablocks): custom metadata blocks
 
+### External Tools:
+- [datacurationtool](scripts/datacurationtool): Data Curation Tool
+
 You may also find a script or two.

scripts/datacurationtool/README.md

@@ -0,0 +1,42 @@
+# Data Curation Tool
+
+An external tool for exploring and curating Dataverse tab delimited DataFiles
+The tool source can be found in this GitHub repositiry:
+https://github.com/scholarsportal/Dataverse-Data-Explorer/blob/main/README.md
+
+## Installing the tool in Apache:
+
+This is used for installing in demo and production.
+
+Build the source per the instructions in the README of the Dataverse-Data-Explorer project linked above. Use ng build to create the dist folder.
+
+- ng build
+
+(Note: If the dist/index.html file has 'base href="/"' change it to base href="./" )
+
+zip the dist/ directory and copy it to the Dataverse server
+On the Dataverse server unzip the file and rename dist/ to datacuration/
+- unzip dist.zip
+- mv dist/ datacuration/
+- sudo cp -r datacuration/ /var/www/html/
+- sudo vi /etc/httpd/conf.d/ssl.conf
+
+  Add to ssl.conf 'ProxyPassMatch ^/datacuration !' to the '# don't pass paths used by rApache...' section.
+- sudo apachectl graceful
+
+Load the setting to configure Dataverse to use the external tool:
+
+Copy the appropriate json file to the server
+
+    dataverse-manifest-demo.json or dataverse-manifest-prod.json and rename it to local-dataverse-manifest.json
+curl -X POST -H 'Content-type: application/json' http://localhost:8080/api/admin/externalTools --upload-file local-dataverse-manifest.json
+
+## Installing the tool in Docker:
+
+This is used primarily for development work (where dataverse is also running in docker)
+
+From the scripts/docker directory run the setup-datacurationtool.sh (make sure Dataverse is running so the settings api will work)
+
+- ./setup-datacurationtool.sh
+
+This script will build the image for the tool directly from GitHub. The script is not designed to install a specific release version.

scripts/datacurationtool/dataverse-manifest-demo.json

@@ -0,0 +1,44 @@
+{
+  "displayName": "Data Curation Tool",
+  "description": "Data Curation Tool for curation of variables",
+  "scope": "file",
+  "type": "configure",
+  "contentType": "text/tab-separated-values",
+  "toolUrl": "https://demo.dataverse.org/datacuration/",
+  "toolParameters": {
+    "queryParameters": [
+      {
+        "fileId": "{fileId}"
+      },
+      {
+        "fileMetadataId": "{fileMetadataId}"
+      },
+      {
+        "datasetPid": "{datasetPid}"
+      },
+      {
+        "locale": "{localeCode}"
+      }
+    ]
+  },
+  "allowedApiCalls": [
+    {
+      "name": "retrieveDataFileDDI",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}/metadata/ddi",
+      "timeOut": 270
+    },
+    {
+      "name": "retrieveDataFile",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}",
+      "timeOut": 270
+    },
+    {
+      "name": "uploadDataFile",
+      "httpMethod": "PUT",
+      "urlTemplate": "/api/v1/edit/{fileId}",
+      "timeOut": 270
+    }
+  ]
+}

scripts/datacurationtool/dataverse-manifest-prod.json

@@ -0,0 +1,44 @@
+{
+  "displayName": "Data Curation Tool",
+  "description": "Data Curation Tool for curation of variables",
+  "scope": "file",
+  "type": "configure",
+  "contentType": "text/tab-separated-values",
+  "toolUrl": "https://dataverse.harvard.edu/datacuration/",
+  "toolParameters": {
+    "queryParameters": [
+      {
+        "fileId": "{fileId}"
+      },
+      {
+        "fileMetadataId": "{fileMetadataId}"
+      },
+      {
+        "datasetPid": "{datasetPid}"
+      },
+      {
+        "locale": "{localeCode}"
+      }
+    ]
+  },
+  "allowedApiCalls": [
+    {
+      "name": "retrieveDataFileDDI",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}/metadata/ddi",
+      "timeOut": 270
+    },
+    {
+      "name": "retrieveDataFile",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}",
+      "timeOut": 270
+    },
+    {
+      "name": "uploadDataFile",
+      "httpMethod": "PUT",
+      "urlTemplate": "/api/v1/edit/{fileId}",
+      "timeOut": 270
+    }
+  ]
+}

scripts/datacurationtool/docker/compose.yml

@@ -0,0 +1,21 @@
+version: "2.4"
+
+services:
+  dev_datacurationtool:
+    container_name: "dev_datacurationtool"
+    hostname: datacurationtool
+    image: datacurationtool
+    restart: on-failure
+    build: https://github.com/scholarsportal/Dataverse-Data-Curation-Tool.git
+    environment:
+      - http.host=0.0.0.0
+      - transport.host=localhost
+      - network.host=0.0.0.0
+    ports:
+      - "4200:80" # Proxy HTTP (Data Curation Tool Listener) / NGINX(Docker)
+    networks:
+      - dataverse
+
+networks:
+  dataverse:
+    external: true

scripts/datacurationtool/docker/dataverse-manifest.json

@@ -0,0 +1,44 @@
+{
+  "displayName": "Data Curation Tool",
+  "description": "Data Curation Tool for curation of variables",
+  "scope": "file",
+  "type": "configure",
+  "contentType": "text/tab-separated-values",
+  "toolUrl": "http://127.0.0.1:4200",
+  "toolParameters": {
+    "queryParameters": [
+      {
+        "fileId": "{fileId}"
+      },
+      {
+        "fileMetadataId": "{fileMetadataId}"
+      },
+      {
+        "datasetPid": "{datasetPid}"
+      },
+      {
+        "locale": "{localeCode}"
+      }
+    ]
+  },
+  "allowedApiCalls": [
+    {
+      "name": "retrieveDataFileDDI",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}/metadata/ddi",
+      "timeOut": 270
+    },
+    {
+      "name": "retrieveDataFile",
+      "httpMethod": "GET",
+      "urlTemplate": "/api/v1/access/datafile/{fileId}",
+      "timeOut": 270
+    },
+    {
+      "name": "uploadDataFile",
+      "httpMethod": "PUT",
+      "urlTemplate": "/api/v1/edit/{fileId}",
+      "timeOut": 270
+    }
+  ]
+}

scripts/datacurationtool/docker/setup-datacurationtool.sh

@@ -0,0 +1,12 @@
+#!/bin/sh
+echo "Setting up Data Curation Tool"
+TOOL=$(curl http://localhost:8080/api/admin/externalTools | grep "Data Curation Tool")
+if [ -z "${TOOL}" ]; then
+    response=$(curl -X POST -H 'Content-type: application/json'  http://localhost:8080/api/admin/externalTools --upload-file dataverse-manifest.json 2>&1)
+    if [ $? -ne 0 ] ; then
+       echo "Error: ""$response" && exit;
+    fi
+fi
+
+docker compose up -d &
+