Create SCCS workflow (#77)

Why these changes are being introduced:
* Support deposits requested by Scholarly Communications and Collections Strategy (SCCS).

How this addresses that need:
* Create SCCS workflow and metadata mapping JSON file
* Move DemoWorkflow metadata mapping JSON file
* Make 'delimiter' and 'language' optional configs
* Omit null and empty string configs from metadata mapping JSON files
* Change Workflow.email_recipients to list[str]
* Clean up Workflow and SimpleCSV fixtures
* Rename DemoWorkflow -> Demo

Side effects of this change:
* None

Relevant ticket(s):
* https://mitlibraries.atlassian.net/browse/IN-1098

dsc/cli.py

@@ -70,7 +70,7 @@ def main(
     workflow = workflow_class(
         collection_handle=collection_handle,
         batch_id=batch_id,
-        email_recipients=tuple(email_recipients.split(",")),
+        email_recipients=email_recipients.split(","),
         s3_bucket=s3_bucket,
         output_queue=output_queue,
     )

dsc/workflows/__init__.py

@@ -5,6 +5,7 @@
 
 from dsc.workflows.base import Workflow
 from dsc.workflows.base.simple_csv import SimpleCSV
-from dsc.workflows.demo import DemoWorkflow
+from dsc.workflows.demo import Demo
+from dsc.workflows.sccs import SCCS
 
-__all__ = ["DemoWorkflow", "SimpleCSV", "Workflow"]
+__all__ = ["SCCS", "Demo", "SimpleCSV", "Workflow"]

dsc/workflows/base/__init__.py

@@ -35,7 +35,7 @@ def __init__(
         self,
         collection_handle: str,
         batch_id: str,
-        email_recipients: tuple[str, ...],
+        email_recipients: list[str],
         s3_bucket: str | None = None,
         output_queue: str | None = None,
     ) -> None:
@@ -259,12 +259,19 @@ def create_dspace_metadata(self, item_metadata: dict[str, Any]) -> dict[str, Any
         A metadata mapping is a dict with the format seen below:
 
         {
-        "dc.contributor": {
-            "source_field_name": "contributor",
-            "language": None,
-            "delimiter": "|",
+            "dc.contributor": {
+                "source_field_name": "contributor",
+                "language": "<language>",
+                "delimiter": "<delimiting character>",
+                "required": true | false
+            }
         }
 
+        When setting up the metadata mapping JSON file, "language" and "delimiter"
+        can be omitted from the file if not applicable. Required fields ("item_identifier"
+        and "title") must be set as required (true); if "required" is not listed as a
+        a config, the field defaults as not required (false).
+
         MUST NOT be overridden by workflow subclasses.
 
         Args:
@@ -281,8 +288,8 @@ def create_dspace_metadata(self, item_metadata: dict[str, Any]) -> dict[str, Any
                         f"{field_mapping["source_field_name"]}'"
                     )
                 if field_value:
-                    delimiter = field_mapping["delimiter"]
-                    language = field_mapping["language"]
+                    delimiter = field_mapping.get("delimiter")
+                    language = field_mapping.get("language")
                     if delimiter:
                         metadata_entries.extend(
                             [

dsc/workflows/demo.py

@@ -1,8 +1,8 @@
 from dsc.workflows.base.simple_csv import SimpleCSV
 
 
-class DemoWorkflow(SimpleCSV):
+class Demo(SimpleCSV):
 
     workflow_name: str = "demo"
     submission_system: str = "DSpace@MIT"
-    metadata_mapping_path: str = "tests/fixtures/demo_metadata_mapping.json"
+    metadata_mapping_path: str = "dsc/workflows/metadata_mapping/demo.json"

tests/fixtures/demo_metadata_mapping.json → dsc/workflows/metadata_mapping/demo.json

@@ -1,62 +1,47 @@
 {
     "item_identifier": {
         "source_field_name": "item_identifier",
-        "language": null,
-        "delimiter": ""
+        "required": true
+    },
+    "dc.title": {
+        "source_field_name": "dc.title",
+        "language": "en_US",
+        "required": true
     },
     "dc.publisher": {
         "source_field_name": "dc.publisher",
-        "language": "en_US",
-        "delimiter": ""
+        "language": "en_US"
     },
     "dc.eprint.version": {
         "source_field_name": "dc.eprint.version",
-        "language": "en_US",
-        "delimiter": ""
+        "language": "en_US"
     },
     "dc.type": {
         "source_field_name": "dc.type",
-        "language": "en_US",
-        "delimiter": ""
+        "language": "en_US"
     },
     "dc.source": {
         "source_field_name": "dc.source",
-        "language": "en_US",
-        "delimiter": ""
+        "language": "en_US"
     },
     "dc.contributor.author": {
         "source_field_name": "dc.contributor.author",
         "language": "en_US",
         "delimiter": "|"
     },
     "dc.relation.isversionof": {
-        "source_field_name": "dc.relation.isversionof",
-        "language": "",
-        "delimiter": ""
-    },
-    "dc.title": {
-        "source_field_name": "dc.title",
-        "language": "en_US",
-        "delimiter": ""
+        "source_field_name": "dc.relation.isversionof"
     },
     "dc.relation.journal": {
-        "source_field_name": "dc.relation.journal",
-        "language": "",
-        "delimiter": ""
+        "source_field_name": "dc.relation.journal"
     },
     "dc.identifier.issn": {
-        "source_field_name": "dc.identifier.issn",
-        "language": "",
-        "delimiter": ""
+        "source_field_name": "dc.identifier.issn"
     },
     "dc.date.issued": {
-        "source_field_name": "dc.date.issued",
-        "language": "",
-        "delimiter": ""
+        "source_field_name": "dc.date.issued"
     },
     "dc.rights.uri": {
-        "source_field_name": "dc.rights.uri",
-        "language": "",
-        "delimiter": ""
+        "source_field_name": "dc.rights.uri"
     }
 }

dsc/workflows/metadata_mapping/sccs.json

@@ -0,0 +1,59 @@
+{
+    "item_identifier": {
+        "source_field_name": "item_identifier",
+        "required": true
+    },
+    "dc.title": {
+        "source_field_name": "dc.title",
+        "language": "en_US",
+        "required": true
+    },
+    "dc.publisher": {
+        "source_field_name": "dc.publisher",
+        "language": "en_US"
+    },
+    "dc.identifier.mitlicense": {
+        "source_field_name": "dc.identifier.mitlicense",
+        "language": "en_US"
+    },
+    "dc.eprint.version": {
+        "source_field_name": "dc.eprint.version",
+        "language": "en_US"
+    },
+    "dc.type": {
+        "source_field_name": "dc.type",
+        "language": "en_US"
+    },
+    "dc.source": {
+        "source_field_name": "dc.source",
+        "language": "en_US"
+    },
+    "dc.contributor.author": {
+        "source_field_name": "dc.contributor.author",
+        "language": "en_US",
+        "delimiter": "|"
+    },
+    "dc.relation.isversionof": {
+        "source_field_name": "dc.relation.isversionof"
+    },
+    "dc.relation.journal": {
+        "source_field_name": "dc.relation.journal"
+    },
+    "dc.identifier.issn": {
+        "source_field_name": "dc.identifier.issn"
+    },
+    "dc.date.issued": {
+        "source_field_name": "dc.date.issued"
+    },
+    "dc.rights": {
+        "source_field_name": "dc.rights",
+        "language": "en_US"
+    },
+    "dc.rights.uri": {
+        "source_field_name": "dc.rights.uri"
+    },
+    "dc.description.sponsorship": {
+        "source_field_name": "dc.description.sponsorship",
+        "language": "en_US"
+    }
+}

dsc/workflows/sccs.py

@@ -0,0 +1,13 @@
+from dsc.workflows import SimpleCSV
+
+
+class SCCS(SimpleCSV):
+    """Workflow for SCCS-requested deposits.
+
+    The deposits managed by this workflow are requested by the Scholarly
+    Communication and Collection Strategy (SCCS) department
+    and are for submission to DSpace@MIT.
+    """
+
+    workflow_name: str = "sccs"
+    metadata_mapping_path: str = "dsc/workflows/metadata_mapping/sccs.json"

tests/conftest.py

@@ -20,7 +20,6 @@ class TestWorkflow(Workflow):
 
     workflow_name: str = "test"
     submission_system: str = "Test@MIT"
-    email_recipients: tuple[str] = ("test@test.test",)
     metadata_mapping_path: str = "tests/fixtures/test_metadata_mapping.json"
 
     def item_metadata_iter(self):
@@ -56,10 +55,7 @@ class TestSimpleCSV(SimpleCSV):
 
     workflow_name = "simple_csv"
     submission_system: str = "Test@MIT"
-    email_recipients: tuple[str] = ("test@test.test",)
     metadata_mapping_path: str = "tests/fixtures/test_metadata_mapping.json"
-    s3_bucket: str = "dsc"
-    output_queue: str = "mock-output_queue"
 
 
 @pytest.fixture(autouse=True)
@@ -79,6 +75,7 @@ def base_workflow_instance(item_metadata, metadata_mapping, mocked_s3):
         collection_handle="123.4/5678",
         batch_id="batch-aaa",
         email_recipients=["test@test.test"],
+        output_queue="mock-output_queue",
     )
 
 
@@ -88,6 +85,7 @@ def simple_csv_workflow_instance(metadata_mapping):
         collection_handle="123.4/5678",
         batch_id="batch-aaa",
         email_recipients=["test@test.test"],
+        output_queue="mock-output_queue",
     )
 
 

tests/fixtures/test_metadata_mapping.json

@@ -1,19 +1,15 @@
 {
     "item_identifier": {
         "source_field_name": "item_identifier",
-        "language": null,
-        "delimiter": "",
         "required": true
     },
     "dc.title": {
         "source_field_name": "title",
         "language": "en_US",
-        "delimiter": "",
         "required": true
     },
     "dc.contributor": {
         "source_field_name": "contributor",
-        "language": null,
         "delimiter": "|"
     }
 }