Merge branch 'develop' into 2243-schema.org-json-ld #2243

Conflicts (just imports:
src/main/java/edu/harvard/iq/dataverse/DatasetPage.java

doc/sphinx-guides/source/_static/api/dataset-update-metadata.json

@@ -0,0 +1,86 @@
+{
+  "metadataBlocks": {
+    "citation": {
+      "displayName": "Citation Metadata",
+      "fields": [
+        {
+          "typeName": "title",
+          "multiple": false,
+          "typeClass": "primitive",
+          "value": "newTitle"
+        },
+        {
+          "typeName": "author",
+          "multiple": true,
+          "typeClass": "compound",
+          "value": [
+            {
+              "authorName": {
+                "typeName": "authorName",
+                "multiple": false,
+                "typeClass": "primitive",
+                "value": "Spruce, Sabrina"
+              }
+            }
+          ]
+        },
+        {
+          "typeName": "datasetContact",
+          "multiple": true,
+          "typeClass": "compound",
+          "value": [
+            {
+              "datasetContactName": {
+                "typeName": "datasetContactName",
+                "multiple": false,
+                "typeClass": "primitive",
+                "value": "Spruce, Sabrina"
+              },
+              "datasetContactEmail": {
+                "typeName": "datasetContactEmail",
+                "multiple": false,
+                "typeClass": "primitive",
+                "value": "spruce@mailinator.com"
+              }
+            }
+          ]
+        },
+        {
+          "typeName": "dsDescription",
+          "multiple": true,
+          "typeClass": "compound",
+          "value": [
+            {
+              "dsDescriptionValue": {
+                "typeName": "dsDescriptionValue",
+                "multiple": false,
+                "typeClass": "primitive",
+                "value": "test"
+              }
+            }
+          ]
+        },
+        {
+          "typeName": "subject",
+          "multiple": true,
+          "typeClass": "controlledVocabulary",
+          "value": [
+            "Other"
+          ]
+        },
+        {
+          "typeName": "depositor",
+          "multiple": false,
+          "typeClass": "primitive",
+          "value": "Spruce, Sabrina"
+        },
+        {
+          "typeName": "dateOfDeposit",
+          "multiple": false,
+          "typeClass": "primitive",
+          "value": "2017-04-19"
+        }
+      ]
+    }
+  }
+}

doc/sphinx-guides/source/_static/installation/files/root/auth-providers/orcid-sandbox.json

@@ -3,6 +3,6 @@
     "factoryAlias":"oauth2",
     "title":"ORCID",
     "subtitle":"",
-    "factoryData":"type: orcid | userEndpoint: https://api.sandbox.orcid.org/v1.2/{ORCID}/orcid-profile | clientId: FIXME | clientSecret: FIXME",
+    "factoryData":"type: orcid | userEndpoint: https://api.sandbox.orcid.org/v2.0/{ORCID}/record | clientId: FIXME | clientSecret: FIXME",
     "enabled":true
 }

doc/sphinx-guides/source/_static/installation/files/root/auth-providers/orcid.json

@@ -3,6 +3,6 @@
     "factoryAlias":"oauth2",
     "title":"ORCID",
     "subtitle":"",
-    "factoryData":"type: orcid | userEndpoint: https://api.orcid.org/v1.2/{ORCID}/orcid-profile | clientId: FIXME | clientSecret: FIXME",
+    "factoryData":"type: orcid | userEndpoint: https://api.orcid.org/v2.0/{ORCID}/record | clientId: FIXME | clientSecret: FIXME",
     "enabled":true
 }

doc/sphinx-guides/source/conf.py

@@ -64,9 +64,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '4.8.1'
+version = '4.8.3'
 # The full version, including alpha/beta/rc tags.
-release = '4.8.1'
+release = '4.8.3'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

doc/sphinx-guides/source/developers/big-data-support.rst

@@ -112,7 +112,7 @@ Configuring the RSAL Mock
 
 Info for configuring the RSAL Mock: https://github.com/sbgrid/rsal/tree/master/mocks
 
-Also, to configure Dataverse to use the new workflow you must do the following:
+Also, to configure Dataverse to use the new workflow you must do the following (see also the section below on workflows):
 
 1. Configure the RSAL URL:
 
@@ -160,3 +160,99 @@ To specify replication sites that appear in rsync URLs:
 In the GUI, this is called "Local Access". It's where you can compute on files on your cluster.
 
 ``curl http://localhost:8080/api/admin/settings/:LocalDataAccessPath -X PUT -d "/programs/datagrid"``
+
+Workflows
+---------
+
+Dataverse can perform two sequences of actions when datasets are published: one prior to publishing (marked by a ``PrePublishDataset`` trigger), and one after the publication has succeeded (``PostPublishDataset``). The pre-publish workflow is useful for having an external system prepare a dataset for being publicly accessed (a possibly lengthy activity that requires moving files around, uploading videos to a streaming server, etc.), or to start an approval process. A post-publish workflow might be used for sending notifications about the newly published dataset.
+
+Workflow steps are created using *step providers*. Dataverse ships with an internal step provider that offers some basic functionality, and with the ability to load 3rd party step providers. This allows installations to implement functionality they need without changing the Dataverse source code.
+
+Steps can be internal (say, writing some data to the log) or external. External steps involve Dataverse sending a request to an external system, and waiting for the system to reply. The wait period is arbitrary, and so allows the external system unbounded operation time. This is useful, e.g., for steps that require human intervension, such as manual approval of a dataset publication.
+
+The external system reports the step result back to dataverse, by sending a HTTP ``POST`` command to ``api/workflows/{invocation-id}``. The body of the request is passed to the paused step for further processing.
+
+If a step in a workflow fails, Dataverse make an effort to roll back all the steps that preceeded it. Some actions, such as writing to the log, cannot be rolled back. If such an action has a public external effect (e.g. send an EMail to a mailing list) it is advisable to put it in the post-release workflow.
+
+.. tip::
+  For invoking external systems using a REST api, Dataverse's internal step
+  provider offers a step for sending and receiving customizable HTTP requests.
+  It's called *http/sr*, and is detailed below.
+
+Administration
+~~~~~~~~~~~~~~
+
+A Dataverse instance stores a set of workflows in its database. Workflows can be managed using the ``api/admin/workflows/`` endpoints of the :doc:`/api/native-api`. Sample workflow files are available in ``scripts/api/data/workflows``.
+
+At the moment, defining a workflow for each trigger is done for the entire instance, using the endpoint ``api/admin/workflows/default/«trigger type»``.
+
+In order to prevent unauthorized resuming of workflows, Dataverse maintains a "white list" of IP addresses from which resume requests are honored. This list is maintained using the ``/api/admin/workflows/ip-whitelist`` endpoint of the :doc:`/api/native-api`. By default, Dataverse honors resume requests from localhost only (``127.0.0.1;::1``), so set-ups that use a single server work with no additional configuration.
+
+
+Available Steps
+~~~~~~~~~~~~~~~
+
+Dataverse has an internal step provider, whose id is ``:internal``. It offers the following steps:
+
+log
++++
+
+A step that writes data about the current workflow invocation to the instance log. It also writes the messages in its ``parameters`` map.
+
+.. code:: json
+
+  {
+     "provider":":internal",
+     "stepType":"log",
+     "parameters": {
+         "aMessage": "message content",
+         "anotherMessage": "message content, too"
+     }
+  }
+
+
+pause
++++++
+
+A step that pauses the workflow. The workflow is paused until a POST request is sent to ``/api/workflows/{invocation-id}``.
+
+.. code:: json
+
+  {
+      "provider":":internal",
+      "stepType":"pause"
+  }
+
+
+http/sr
++++++++
+
+A step that sends a HTTP request to an external system, and then waits for a response. The response has to match a regular expression specified in the step parameters. The url, content type, and message body can use data from the workflow context, using a simple markup language. This step has specific parameters for rollback.
+
+.. code:: json
+
+  {
+    "provider":":internal",
+    "stepType":"http/sr",
+    "parameters": {
+        "url":"http://localhost:5050/dump/${invocationId}",
+        "method":"POST",
+        "contentType":"text/plain",
+        "body":"START RELEASE ${dataset.id} as ${dataset.displayName}",
+        "expectedResponse":"OK.*",
+        "rollbackUrl":"http://localhost:5050/dump/${invocationId}",
+        "rollbackMethod":"DELETE ${dataset.id}"
+    }
+  }
+
+Available variables are:
+
+* ``invocationId``
+* ``dataset.id``
+* ``dataset.identifier``
+* ``dataset.globalId``
+* ``dataset.displayName``
+* ``dataset.citation``
+* ``minorVersion``
+* ``majorVersion``
+* ``releaseStatus``

doc/sphinx-guides/source/index.rst

@@ -3,23 +3,22 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
-Dataverse 4.8.1 Guides
+Dataverse 4.8.3 Guides
 ======================
 
-These guides are for the most recent version of Dataverse. For the guides for **version 4.7.1** please go `here <http://guides.dataverse.org/en/4.7.1/>`_.
+These guides are for the most recent version of Dataverse. For the guides for **version 4.8.2** please go `here <http://guides.dataverse.org/en/4.8.2/>`_.
 
 .. toctree::
   :glob:
   :titlesonly:
   :maxdepth: 2
 
   user/index
-  installation/index
+  admin/index
   api/index
+  installation/index
   developers/index
   style/index
-  admin/index
-  workflows
 
 How the Guides Are Organized
 =============================

doc/sphinx-guides/source/user/dataset-management.rst

@@ -225,14 +225,14 @@ your own custom Terms of Use for your Datasets.
 Custom Terms of Use for Datasets
 --------------------------------
 
-If you are unable to use a CC0 waiver for your datasets you are able to set your own custom terms of use. To do so, select "No, do not apply CC0 - "Public Domain Dedication" and a Terms of Use textbox will show up allowing you to enter your own custom terms of use for your dataset. To add more information about the Terms of Use, click on "Additional Information \[+]".
+If you are unable to use a CC0 waiver for your datasets you are able to set your own custom terms of use. To do so, select "No, do not apply CC0 - "Public Domain Dedication" and a Terms of Use textbox will show up allowing you to enter your own custom terms of use for your dataset. To add more information about the Terms of Use, we have provided fields like Special Permissions, Restrictions, Citation Requirements, etc.
 
 Here is an `example of a Data Usage Agreement <http://best-practices.dataverse.org/harvard-policies/sample-dua.html>`_ for datasets that have de-identified human subject data.
 
 Restricted Files + Terms of Access 
 ----------------------------------
 
-If you restrict any files in your dataset, you will be prompted by a pop-up to enter Terms of Access for the data. This can also be edited in the Terms tab or selecting Terms in the "Edit" dropdown button in the dataset. You may also allow users to request access for your restricted files by enabling "Request Access". To add more information about the Terms of Access, click on "Additional Information \[+]".
+If you restrict any files in your dataset, you will be prompted by a pop-up to enter Terms of Access for the data. This can also be edited in the Terms tab or selecting Terms in the "Edit" dropdown button in the dataset. You may also allow users to request access for your restricted files by enabling "Request Access". To add more information about the Terms of Access, we have provided fields like Data Access Place, Availability Status, Contact for Access, etc.
 
 **Note:** Some Dataverse installations do not allow for file restriction.
 

pom.xml

@@ -4,7 +4,7 @@
 
     <groupId>edu.harvard.iq</groupId>
     <artifactId>dataverse</artifactId>
-    <version>4.8.1</version>
+    <version>4.8.3</version>
     <packaging>war</packaging>
 
     <name>dataverse</name>

scripts/api/data/authentication-providers/orcid-sandbox.json

@@ -1,8 +1,8 @@
 {
-    "id":"orcid-sandbox",
+    "id":"orcid-v2-sandbox",
     "factoryAlias":"oauth2",
     "title":"ORCID Sandbox",
-    "subtitle":"ORCiD - sandbox",
-    "factoryData":"type: orcid | userEndpoint: https://api.sandbox.orcid.org/v1.2/{ORCID}/orcid-profile | clientId: APP-HIV99BRM37FSWPH6 | clientSecret: ee844b70-f223-4f15-9b6f-4991bf8ed7f0",
+    "subtitle":"ORCiD - sandbox (v2)",
+    "factoryData":"type: orcid | userEndpoint: https://api.sandbox.orcid.org/v2.0/{ORCID}/person | clientId: APP-HIV99BRM37FSWPH6 | clientSecret: ee844b70-f223-4f15-9b6f-4991bf8ed7f0",
     "enabled":true
 }