Add final set of Datacite field methods

tests/sources/xml/test_datacite.py

@@ -757,6 +757,193 @@ def test_get_locations_transforms_correctly_if_fields_missing():
     assert Datacite.get_locations(source_record) is None
 
 
+def test_get_notes_success():
+    source_record = create_datacite_source_record_stub(
+        """
+        <resourceType resourceTypeGeneral="Dataset">Survey Data</resourceType>
+        <descriptions>
+         <description descriptionType="TechnicalInfo">Stata, 13</description>
+        </descriptions>
+        """
+    )
+    assert Datacite.get_notes(source_record) == [
+        Note(value=["Survey Data"], kind="Datacite resource type"),
+        Note(value=["Stata, 13"], kind="TechnicalInfo"),
+    ]
+
+
+def test_get_notes_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub(
+        "<descriptions><description /></descriptions>"
+    )
+    assert Datacite.get_notes(source_record) is None
+
+
+def test_get_notes_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_notes(source_record) is None
+
+
+def test_get_publishers_success():
+    source_record = create_datacite_source_record_stub(
+        "<publisher>Harvard Dataverse</publisher>"
+    )
+    assert Datacite.get_publishers(source_record) == [Publisher(name="Harvard Dataverse")]
+
+
+def test_get_publishers_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub("<publisher />")
+    assert Datacite.get_publishers(source_record) is None
+
+
+def test_get_publishers_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_publishers(source_record) is None
+
+
+def test_get_related_items_success():
+    metadata_insert = (
+        '<relatedIdentifiers><relatedIdentifier relatedIdentifierType="DOI" '
+        'relationType="IsCitedBy">10.1257/app.20150390</relatedIdentifier>'
+        '<relatedIdentifier relationType="IsVersionOf">10.5281/zenodo.5524464'
+        '</relatedIdentifier><relatedIdentifier relatedIdentifierType="ISBN" '
+        'relationType="Other">1234567.5524464</relatedIdentifier><relatedIdentifier '
+        'relatedIdentifierType="URL" relationType="IsPartOf">'
+        "https://zenodo.org/communities/astronomy-general</relatedIdentifier>"
+        "</relatedIdentifiers>"
+    )
+    source_record = create_datacite_source_record_stub(metadata_insert)
+    assert Datacite.get_related_items(source_record) == [
+        RelatedItem(relationship="IsCitedBy", uri="https://doi.org/10.1257/app.20150390"),
+        RelatedItem(relationship="IsVersionOf", uri="10.5281/zenodo.5524464"),
+        RelatedItem(relationship="Other", uri="1234567.5524464"),
+        RelatedItem(
+            relationship="IsPartOf",
+            uri="https://zenodo.org/communities/astronomy-general",
+        ),
+    ]
+
+
+def test_get_related_items_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub(
+        "<relatedIdentifiers><relatedIdentifier /></relatedIdentifiers>"
+    )
+    assert Datacite.get_related_items(source_record) is None
+
+
+def test_get_related_items_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_related_items(source_record) is None
+
+
+def test_get_rights_success():
+    source_record = create_datacite_source_record_stub(
+        """
+        <rightsList>
+          <rights rightsURI="info:eu-repo/semantics/openAccess" />
+          <rights
+          rightsURI="http://creativecommons.org/publicdomain/zero/1.0">CC0 1.0</rights>
+        </rightsList>
+        """
+    )
+    assert Datacite.get_rights(source_record) == [
+        Rights(description=None, kind=None, uri="info:eu-repo/semantics/openAccess"),
+        Rights(
+            description="CC0 1.0",
+            kind=None,
+            uri="http://creativecommons.org/publicdomain/zero/1.0",
+        ),
+    ]
+
+
+def test_get_rights_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub(
+        "<rightsList><rights /></rightsList>"
+    )
+    assert Datacite.get_rights(source_record) is None
+
+
+def test_get_rights_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_rights(source_record) is None
+
+
+def test_get_subjects_success():
+    source_record = create_datacite_source_record_stub(
+        """
+        <subjects>
+         <subject>Social Sciences</subject>
+         <subject>Educational materials</subject>
+         <subject subjectScheme="LCSH"
+         >Adult education, education inputs, field experiments</subject>
+         <subject subjectScheme="LCSH">Education</subject>
+        </subjects>
+        """
+    )
+    assert Datacite.get_subjects(source_record) == [
+        Subject(
+            value=["Social Sciences", "Educational materials"],
+            kind="Subject scheme not provided",
+        ),
+        Subject(
+            value=[
+                "Adult education, education inputs, field experiments",
+                "Education",
+            ],
+            kind="LCSH",
+        ),
+    ]
+
+
+def test_get_subjects_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub("<subjects><subject /></subjects>")
+    assert Datacite.get_subjects(source_record) is None
+
+
+def test_get_subjects_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_subjects(source_record) is None
+
+
+def test_get_summary_success():
+    metadata_insert = (
+        '<descriptions><description descriptionType="Abstract">Using a '
+        "randomized field experiment in India, we evaluate the effectiveness of adult "
+        "literacy and parental involvement interventions in improving children's "
+        "learning. Households were assigned to receive either adult literacy (language "
+        "and math) classes for mothers, training for mothers on how to enhance their "
+        "children's learning at home, or a combination of the two programs. All three "
+        "interventions had significant but modest impacts on childrens math scores. The "
+        "interventions also increased mothers' test scores in both language and math, as "
+        "well as a range of other outcomes reflecting greater involvement of mothers in "
+        "their children's education.</description>"
+    )
+    source_record = create_datacite_source_record_stub(metadata_insert)
+    assert Datacite.get_summary(source_record) == [
+        "Using a randomized field experiment in India, we evaluate the effectiveness "
+        "of adult literacy and parental involvement interventions in improving "
+        "children's learning. Households were assigned to receive either adult "
+        "literacy (language and math) classes for mothers, training for mothers on "
+        "how to enhance their children's learning at home, or a combination of the "
+        "two programs. All three interventions had significant but modest impacts on "
+        "childrens math scores. The interventions also increased mothers' test scores"
+        " in both language and math, as well as a range of other outcomes reflecting "
+        "greater involvement of mothers in their children's education."
+    ]
+
+
+def test_get_summarty_transforms_correctly_if_fields_blank():
+    source_record = create_datacite_source_record_stub(
+        '<descriptions><description descriptionType="Abstract" /></descriptions>'
+    )
+    assert Datacite.get_summary(source_record) is None
+
+
+def test_get_summary_transforms_correctly_if_fields_missing():
+    source_record = create_datacite_source_record_stub()
+    assert Datacite.get_summary(source_record) is None
+
+
 def test_generate_name_identifier_url_orcid_scheme(datacite_record_all_fields):
     assert next(datacite_record_all_fields).contributors[0].identifier == [
         "https://orcid.org/0000-0000-0000-0000"

transmogrifier/sources/xml/datacite.py

@@ -25,7 +25,6 @@ def get_optional_fields(self, source_record: Tag) -> dict | None:
                 oai_datacite XML.
         """
         fields: dict = {}
-        source_record_id = self.get_source_record_id(source_record)
 
         # alternate_titles
         fields["alternate_titles"] = self.get_alternate_titles(source_record)
@@ -64,83 +63,22 @@ def get_optional_fields(self, source_record: Tag) -> dict | None:
         fields["locations"] = self.get_locations(source_record)
 
         # notes
-        if resource_type := source_record.metadata.find("resourceType", string=True):
-            fields.setdefault("notes", []).append(
-                timdex.Note(
-                    value=[str(resource_type.string)],
-                    kind="Datacite resource type",
-                )
-            )
-        descriptions = source_record.metadata.find_all("description", string=True)
-        for description in descriptions:
-            if "descriptionType" not in description.attrs:
-                logger.warning(
-                    "Datacite record %s missing required Datacite attribute "
-                    "@descriptionType",
-                    source_record_id,
-                )
-            if description.get("descriptionType") != "Abstract":
-                fields.setdefault("notes", []).append(
-                    timdex.Note(
-                        value=[description.string],
-                        kind=description.get("descriptionType") or None,
-                    )
-                )
+        fields["notes"] = self.get_notes(source_record)
 
         # publishers
-        if publisher := source_record.metadata.find("publisher", string=True):
-            fields["publishers"] = [timdex.Publisher(name=publisher.string)]
-        else:
-            logger.warning(
-                "Datacite record %s missing required Datacite field publisher",
-                source_record_id,
-            )
+        fields["publishers"] = self.get_publishers(source_record)
 
         # related_items, uses related_identifiers retrieved for identifiers
-        for related_identifier in [
-            ri
-            for ri in source_record.metadata.find_all("relatedIdentifier", string=True)
-            if ri.get("relationType") != "IsIdenticalTo"
-        ]:
-            fields.setdefault("related_items", []).append(
-                timdex.RelatedItem(
-                    uri=self.generate_related_item_identifier_url(related_identifier),
-                    relationship=related_identifier.get("relationType")
-                    or "Not specified",
-                )
-            )
+        fields["related_items"] = self.get_related_items(source_record)
 
         # rights
-        for right in [
-            r
-            for r in source_record.metadata.find_all("rights")
-            if r.string or r.get("rightsURI")
-        ]:
-            fields.setdefault("rights", []).append(
-                timdex.Rights(
-                    description=right.string or None, uri=right.get("rightsURI") or None
-                )
-            )
+        fields["rights"] = self.get_rights(source_record)
 
         # subjects
-        subjects_dict: dict[str, list[str]] = {}
-        for subject in source_record.metadata.find_all("subject", string=True):
-            if not subject.get("subjectScheme"):
-                subjects_dict.setdefault("Subject scheme not provided", []).append(
-                    subject.string
-                )
-            else:
-                subjects_dict.setdefault(subject["subjectScheme"], []).append(
-                    subject.string
-                )
-        fields["subjects"] = [
-            timdex.Subject(value=value, kind=key) for key, value in subjects_dict.items()
-        ] or None
+        fields["subjects"] = self.get_subjects(source_record)
 
         # summary
-        fields["summary"] = [
-            d.string for d in descriptions if d.get("descriptionType") == "Abstract"
-        ] or None
+        fields["summary"] = self.get_summary(source_record)
 
         return fields
 
@@ -425,6 +363,100 @@ def get_locations(cls, source_record: Tag) -> list[timdex.Location] | None:
             )
         ] or None
 
+    @classmethod
+    def get_notes(cls, source_record: Tag) -> list[timdex.Note] | None:
+        notes = []
+        notes.extend(list(cls._get_resource_type_note(source_record)))
+        notes.extend(list(cls._get_description_notes(source_record)))
+        return notes or None
+
+    @classmethod
+    def _get_resource_type_note(cls, source_record: Tag) -> Iterator[timdex.Note]:
+        if resource_type := source_record.metadata.find("resourceType", string=True):
+            yield timdex.Note(
+                value=[str(resource_type.string)],
+                kind="Datacite resource type",
+            )
+
+    @classmethod
+    def _get_description_notes(cls, source_record: Tag) -> Iterator[timdex.Note]:
+        descriptions = source_record.metadata.find_all("description", string=True)
+        for description in descriptions:
+            if "descriptionType" not in description.attrs:
+                logger.warning(
+                    "Datacite record %s missing required Datacite attribute "
+                    "@descriptionType",
+                    cls.get_source_record_id(source_record),
+                )
+            if description.get("descriptionType") != "Abstract":
+                yield timdex.Note(
+                    value=[str(description.string)],
+                    kind=description.get("descriptionType") or None,
+                )
+
+    @classmethod
+    def get_publishers(cls, source_record: Tag) -> list[timdex.Publisher] | None:
+        publishers = []
+        if publisher := source_record.metadata.find("publisher", string=True):
+            publishers.append(timdex.Publisher(name=str(publisher.string)))
+        else:
+            logger.warning(
+                "Datacite record %s missing required Datacite field publisher",
+                cls.get_source_record_id(source_record),
+            )
+        return publishers or None
+
+    @classmethod
+    def get_related_items(cls, source_record: Tag) -> list[timdex.RelatedItem] | None:
+        return [
+            timdex.RelatedItem(
+                uri=cls.generate_related_item_identifier_url(related_identifier),
+                relationship=related_identifier.get("relationType") or "Not specified",
+            )
+            for related_identifier in source_record.metadata.find_all(
+                "relatedIdentifier", string=True
+            )
+            if related_identifier.get("relationType") != "IsIdenticalTo"
+        ] or None
+
+    @classmethod
+    def get_rights(cls, source_record: Tag) -> list[timdex.Rights] | None:
+        return [
+            timdex.Rights(
+                description=rights.string or None,
+                uri=rights.get("rightsURI") or None,
+            )
+            for rights in source_record.metadata.find_all("rights")
+            if rights.string or rights.get("rightsURI")
+        ] or None
+
+    @classmethod
+    def get_subjects(cls, source_record: Tag) -> list[timdex.Subject] | None:
+        subjects_dict: dict[str, list[str]] = {}
+
+        for subject in source_record.metadata.find_all("subject", string=True):
+            if not subject.get("subjectScheme"):
+                subjects_dict.setdefault("Subject scheme not provided", []).append(
+                    str(subject.string)
+                )
+            else:
+                subjects_dict.setdefault(subject["subjectScheme"], []).append(
+                    str(subject.string)
+                )
+
+        return [
+            timdex.Subject(value=subject_value, kind=subject_scheme)
+            for subject_scheme, subject_value in subjects_dict.items()
+        ] or None
+
+    @classmethod
+    def get_summary(cls, source_record: Tag) -> list[str] | None:
+        return [
+            str(description.string)
+            for description in source_record.metadata.find_all("description", string=True)
+            if description.get("descriptionType") == "Abstract"
+        ] or None
+
     @classmethod
     def get_main_titles(cls, source_record: Tag) -> list[str]:
         """