Merge branch 'release/v0.1.10'

.github/workflows/bulk_disseminate.yml

@@ -22,10 +22,10 @@ jobs:
       NEW_IDS: ${{ steps.get-ids.outputs.NEW_IDS }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: '3.10'
 

.github/workflows/disseminate.yml

@@ -21,7 +21,7 @@ jobs:
         work-id: ${{ fromJSON(inputs.work-ids) }}
     steps:
       - name: Make all platform credentials available to later steps (with names lowercased)
-        uses: oNaiPs/secrets-to-env-action@v1
+        uses: oNaiPs/secrets-to-env-action@v1.5
         with:
           secrets: ${{ toJSON(secrets) }}
           convert: lower

.github/workflows/docker_build_and_push_to_dockerhub.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       - name: Docker meta
         id: meta
         uses: docker/metadata-action@v4
@@ -23,17 +23,17 @@ jobs:
             type=semver,pattern={{major}}.{{minor}}
             type=semver,pattern={{major}}
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@v3
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
       - name: Login to DockerHub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
       - name: Build and push
         id: docker_build
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v5
         with:
           push: true
           tags: ${{ steps.meta.outputs.tags }}

.github/workflows/manual_disseminate.yml

@@ -9,6 +9,7 @@
 # named IA_S3_ACCESS (access key) and IA_S3_SECRET (secret key).
 # It is advised not to upload until the work is published and all metadata finalised.
 name: manual-disseminate
+run-name: 'manual-disseminate to ${{ github.event.inputs.platform }}: ${{ github.event.inputs.workIds }}'
 
 on:
   workflow_dispatch:

CHANGELOG.md

@@ -6,6 +6,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [[0.1.10]](https://github.com/thoth-pub/thoth-dissemination/releases/tag/v0.1.10) - 2024-03-27
+### Changed
+  - Enhanced basic SWORD v2 (DSpace v7) functionality to fit CUL requirements
+  - Upgraded GitHub Actions dependencies from Node 16 to 20 (`docker/setup-qemu-action@v3`, `docker/setup-buildx-action@v3`, `docker/login-action@v3`, `docker/build-push-action@v5`, `actions/checkout@v4`, `actions/setup-python@v5`, `oNaiPs/secrets-to-env-action@v1.5`)
+
 ## [[0.1.9]](https://github.com/thoth-pub/thoth-dissemination/releases/tag/v0.1.9) - 2023-12-05
 ### Added
   - GitHub Actions for recurring automatic uploads of newly published works to Figshare

README.md

@@ -28,6 +28,6 @@ docker run --rm ${imagename} ./disseminator.py --work ${work_id} --platform ${pl
 ### Options
 `--work` = Thoth ID of work to be disseminated
 
-`--platform` = Destination distribution/archiving platform (one of `InternetArchive`, `OAPEN`, `ScienceOpen`, `SWORD`, `Crossref`, `Figshare`)
+`--platform` = Destination distribution/archiving platform (one of `InternetArchive`, `OAPEN`, `ScienceOpen`, `CUL`, `Crossref`, `Figshare`)
 
 See also `--help`.

culuploader.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+"""
+Retrieve and disseminate files and metadata to
+Cambridge University Library DSpace
+"""
+
+from dspaceuploader import DSpaceUploader, MetadataProfile
+
+
+class CULUploader(DSpaceUploader):
+    def __init__(self, work_id, export_url, client_url, version):
+        """Set CUL-specific parameters and pass them to DSpaceUploader"""
+        user_name_string = 'cam_ds7_user'
+        user_pass_string = 'cam_ds7_pw'
+        service_document_iri = (
+            'https://copim-b-dev.lib.cam.ac.uk/server/swordv2/servicedocument'
+        )
+        collection_iri = (
+            'https://copim-b-dev.lib.cam.ac.uk/server/swordv2/collection/1811/'
+            '7'
+        )
+        metadata_profile = MetadataProfile.JISC_ROUTER
+        super().__init__(
+            work_id,
+            export_url,
+            client_url,
+            version,
+            user_name_string,
+            user_pass_string,
+            service_document_iri,
+            collection_iri,
+            metadata_profile)

disseminator.py

@@ -6,7 +6,7 @@
 and upload them in the appropriate format to various platforms.
 """
 
-__version__ = '0.1.9'
+__version__ = '0.1.10'
 
 import argparse
 import logging
@@ -16,15 +16,15 @@
 from iauploader import IAUploader
 from oapenuploader import OAPENUploader
 from souploader import SOUploader
-from swordv2uploader import SwordV2Uploader
+from culuploader import CULUploader
 from crossrefuploader import CrossrefUploader
 from fsuploader import FigshareUploader
 
 UPLOADERS = {
     "InternetArchive": IAUploader,
     "OAPEN": OAPENUploader,
     "ScienceOpen": SOUploader,
-    "SWORD": SwordV2Uploader,
+    "CUL": CULUploader,
     "Crossref": CrossrefUploader,
     "Figshare": FigshareUploader,
 }
@@ -48,15 +48,22 @@
         "action": "store",
         "default": "https://export.thoth.pub",
         "help": "Thoth's Export API endpoint URL",
+    }, {
+        "val": "--client-url",
+        "dest": "client_url",
+        "action": "store",
+        "default": None,
+        "help": "URL of GraphQL API endpoint to use with Thoth Client",
     }
 ]
 
 
-def run(work_id, platform, export_url):
+def run(work_id, platform, export_url, client_url):
     """Execute a dissemination uploader based on input parameters"""
     logging.info('Beginning upload of {} to {}'.format(work_id, platform))
     try:
-        uploader = UPLOADERS[platform](work_id, export_url, __version__)
+        uploader = UPLOADERS[platform](
+            work_id, export_url, client_url, __version__)
     except KeyError:
         logging.error('{} not supported: platform must be one of {}'.format(
             platform, UPLOADERS_STR))
@@ -91,4 +98,5 @@ def get_arguments():
     dotenv_path = Path('./config.env')
     load_dotenv(dotenv_path=dotenv_path)
     ARGUMENTS = get_arguments()
-    run(ARGUMENTS.work_id, ARGUMENTS.platform, ARGUMENTS.export_url)
+    run(ARGUMENTS.work_id, ARGUMENTS.platform,
+        ARGUMENTS.export_url, ARGUMENTS.client_url)

dspaceuploader.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+"""
+Retrieve and disseminate files and metadata to a DSpace repository
+"""
+
+from swordv2uploader import SwordV2Uploader, MetadataProfile
+
+
+class DSpaceUploader(SwordV2Uploader):
+    # Currently DSpace dissemination is only implemented via SWORDv2
+    # This class will be extended once we implement e.g. DSpace REST API
+    def __init__(
+            self,
+            work_id,
+            export_url,
+            client_url,
+            version,
+            user_name_string,
+            user_pass_string,
+            service_document_iri,
+            collection_iri,
+            metadata_profile):
+        super().__init__(
+            work_id,
+            export_url,
+            client_url,
+            version,
+            user_name_string,
+            user_pass_string,
+            service_document_iri,
+            collection_iri,
+            metadata_profile)

fsuploader.py

@@ -18,9 +18,9 @@
 class FigshareUploader(Uploader):
     """Dissemination logic for Figshare"""
 
-    def __init__(self, work_id, export_url, version):
+    def __init__(self, work_id, export_url, client_url, version):
         """Instantiate class for accessing Figshare API."""
-        super().__init__(work_id, export_url, version)
+        super().__init__(work_id, export_url, client_url, version)
         try:
             api_token = self.get_credential_from_env(
                 'figshare_token', 'Figshare')
@@ -125,9 +125,8 @@ def upload_to_platform(self):
     def parse_metadata(self):
         """Convert work metadata into Figshare format."""
         work_metadata = self.metadata.get('data').get('work')
-        try:
-            long_abstract = work_metadata.get('longAbstract')
-        except KeyError:
+        long_abstract = work_metadata.get('longAbstract')
+        if long_abstract is None:
             logging.error(
                 'Cannot upload to Figshare: Work must have a Long Abstract')
             sys.exit(1)
@@ -261,7 +260,7 @@ def get_figshare_authors(metadata):
         """
         # fullName is mandatory so we do not expect KeyErrors
         authors = [{'name': n['fullName']} for n in metadata.get('contributions')
-                   if n.get('mainContribution') == True]
+                   if n.get('mainContribution') is True]
         if len(authors) < 1:
             logging.error(
                 'Cannot upload to Figshare: Work must have at least one Main Contribution')

iauploader.py

@@ -102,7 +102,8 @@ def parse_metadata(self):
         # Repeatable fields such as 'creator', 'isbn', 'subject'
         # can be set by submitting a list of values
         creators = [n.get('fullName')
-                    for n in work_metadata.get('contributions') if n.get('mainContribution') == True]
+                    for n in work_metadata.get('contributions')
+                    if n.get('mainContribution') is True]
         # IA metadata schema suggests hyphens should be omitted,
         # although including them does not cause any errors
         isbns = [n.get('isbn').replace(

obtain_new_ids.py

@@ -216,7 +216,8 @@ def get_thoth_ids(self):
                 break
             offset += 1
             next_work = next_batch[0]
-            next_work_pub_date = datetime.strptime(next_work.publicationDate, "%Y-%m-%d").date()
+            next_work_pub_date = datetime.strptime(
+                next_work.publicationDate, "%Y-%m-%d").date()
             if next_work_pub_date > previous_month_end:
                 # This work will be handled in next month's run - don't cause duplication
                 continue

requirements.txt

@@ -3,4 +3,4 @@ pysftp==0.2.9
 python-dotenv==0.19.2
 requests==2.31.0
 sword2==0.3.0
-thothlibrary==0.20.1
+thothlibrary==0.25.0

requirements_obtain_new_ids.txt

@@ -1,2 +1,2 @@
 internetarchive==3.0.2
-thothlibrary==0.20.0
+thothlibrary==0.25.0