SFR-2171: Fixing OCLC bib author mapping

CHANGELOG.md

@@ -45,6 +45,7 @@
 - Changed HATHI_DATAFILES outdated link in development, example, and local yaml files
 - Fixed edition API ID param
 - Fixed usage type bug
+- Fixed OCLC bib author mapping
 
 ## 2024-08-06 -- v0.13.1
 ## Added

mappings/oclc_bib.py

@@ -8,47 +8,41 @@
 
 class OCLCBibMapping(Core):
     def __init__(self, oclc_bib, related_oclc_numbers=[]):
-        identifiers = oclc_bib['identifier']
+        self.record = self._map_to_record(oclc_bib, related_oclc_numbers)
+
+    def _map_to_record(self, oclc_bib, related_oclc_numbers=[]) -> Record:
+        identifiers = oclc_bib.get('identifier', {})
         creators = self._get_creators(oclc_bib)
         authors = self._get_authors(creators)
         contributors = self._get_contributors(creators)
-
-        self.record = Record(
+        
+        return Record(
             uuid=uuid4(),
             frbr_status='complete',
             cluster_status=False,
             source='oclcClassify',
-            source_id=f"{oclc_bib['work']['id']}|owi",
-            title=oclc_bib['title']['mainTitles'][0]['text'],
+            source_id=f"{oclc_bib.get('work', {}).get('id')}|owi",
+            title=oclc_bib.get('title', {}).get('mainTitles', [{}])[0].get('text'),
             subjects=self._map_subjects(oclc_bib),
             authors=self._map_authors(authors),
             contributors=self._map_contributors(contributors),
             identifiers=(
-                [f"{oclc_bib['work']['id']}|owi"] +
-                [f"{identifiers['oclcNumber']}|oclc"] +
+                [f"{oclc_bib.get('work', {}).get('id')}|owi"] +
+                [f"{identifiers.get('oclcNumber')}|oclc"] +
                 [f"{oclc_number}|oclc" for oclc_number in related_oclc_numbers]
             ),
             date_created=datetime.now(timezone.utc).replace(tzinfo=None),
             date_modified=datetime.now(timezone.utc).replace(tzinfo=None)
         )
 
-    def createMapping(self):
-        pass
-
-    def applyFormatting(self):
-        pass
-
-    def applyMapping(self):
-        pass
-
     def _get_creators(self, oclc_bib):
         if not oclc_bib.get('contributor'): 
             return None
 
         return list(
             filter(
-                lambda creator: creator.get('secondName') and creator.get('firstName'), 
-                oclc_bib['contributor'].get('creators', [])
+                lambda creator: creator.get('secondName') or creator.get('firstName'), 
+                oclc_bib.get('contributor', {}).get('creators', [])
             )
         )
 
@@ -58,9 +52,7 @@ def _get_authors(self, creators):
 
         return list(
             filter(
-                lambda creator: 
-                    creator.get('isPrimary', False) or 
-                    self._is_author(creator), 
+                lambda creator: creator.get('isPrimary', False) or self._is_author(creator), 
                 creators
             )
         )
@@ -71,34 +63,68 @@ def _get_contributors(self, creators):
 
         return list(
             filter(
-                lambda creator: 
-                    not creator.get('isPrimary', False) and 
-                    not self._is_author(creator), 
+                lambda creator: not creator.get('isPrimary', False) and not self._is_author(creator), 
                 creators
             )
         )
 
     def _is_author(self, creator):
-        for role in set(map(lambda relator: relator.get('term').lower(), creator.get('relators', []))):
+        for role in set(map(lambda relator: relator.get('term', '').lower(), creator.get('relators', []))):
             if 'author' in role.lower() or 'writer' in role.lower():
                 return True
 
         return False
 
     def _map_subjects(self, oclc_bib) -> list[str]:
-        return [f"{subject['subjectName']['text']}||{subject.get('vocabulary', '')}" for subject in oclc_bib.get('subjects', [])]
+        return [
+            f"{subject_name}||{subject.get('vocabulary', '')}" 
+            for subject in oclc_bib.get('subjects', [])
+            if (subject_name := subject.get('subjectName', {}).get('text'))
+        ]
 
     def _map_authors(self, authors) -> Optional[list[str]]:
         if not authors:
             return None
-
-        return [f"{author['secondName']['text']}, {author['firstName']['text']}|||true" for author in authors]
+
+        return [
+            f'{author_name}|||true' 
+            for author in authors 
+            if (author_name := self._get_contributor_name(author))
+        ]
 
     def _map_contributors(self, contributors) -> Optional[list[str]]:
         if not contributors:
             return None
-
+        
         return [
-            f"{contributor['secondName']['text']}, {contributor['firstName']['text']}|||{', '.join(list(map(lambda relator: relator.get('term', ''), contributor.get('relators', []))))}"
-            for contributor in contributors
+            f"{contributor_name}|||{', '.join(list(map(lambda relator: relator.get('term', ''), contributor.get('relators', []))))}"
+            for contributor in contributors 
+            if (contributor_name := self._get_contributor_name(contributor))
         ]
+
+    def _get_contributor_name(self, contributor) -> Optional[str]:
+        first_name = self._get_name(contributor.get('firstName'))
+        second_name = self._get_name(contributor.get('secondName'))
+
+        if not first_name and not second_name:
+            return None
+
+        if first_name and second_name:
+            return f'{second_name}, {first_name}'
+
+        return f'{first_name or second_name}'
+
+    def _get_name(self, name_data) -> Optional[str]:
+        if not name_data:
+            return None
+
+        return name_data.get('text') or name_data.get('romanizedText')
+
+    def createMapping(self):
+        pass
+
+    def applyFormatting(self):
+        pass
+
+    def applyMapping(self):
+        pass

tests/unit/test_oclc_bib_mapping.py

@@ -0,0 +1,84 @@
+from mappings.oclc_bib import OCLCBibMapping
+
+base_oclc_bib = {
+    'identifier': {
+        'oclcNumber': 1234
+    },
+    'work': {
+        'id': 1
+    },
+    'title': {
+        'mainTitles': [{
+            'text': 'The Story of DRB'
+        }]
+    },
+    'subjects': [{
+        'subjectName': {
+            'text': 'Subject'
+        },
+        'vocabulary': 'fast'
+    }],
+    'contributor': {
+        'creators': [{
+            'firstName': {
+                'text': 'Hathi'
+            },
+            'secondName': {
+                'text': 'Trust'
+            },
+            'isPrimary': True
+        }]
+    }
+}
+
+
+def test_oclc_bib_mapping_full_name():
+    oclc_bib_mapping = OCLCBibMapping(base_oclc_bib)
+
+    assert ['Trust, Hathi|||true'] == oclc_bib_mapping.record.authors
+
+
+def test_oclc_bib_mapping_no_first_name():
+    base_oclc_bib['contributor'] = {
+        'creators': [{
+            'secondName': {
+                'text': 'Trust'
+            },
+            'isPrimary': True
+        }]
+    }
+
+    oclc_bib_mapping = OCLCBibMapping(base_oclc_bib)
+
+    assert ['Trust|||true'] == oclc_bib_mapping.record.authors
+
+def test_oclc_bib_mapping_no_second_name():
+    base_oclc_bib['contributor'] = {
+        'creators': [{
+            'firstName': {
+                'text': 'Hathi'
+            },
+            'isPrimary': True
+        }]
+    }
+
+    oclc_bib_mapping = OCLCBibMapping(base_oclc_bib)
+
+    assert ['Hathi|||true'] == oclc_bib_mapping.record.authors
+
+def test_oclc_bib_mapping_fallback_to_romanized_text():
+    base_oclc_bib['contributor'] = {
+        'creators': [{
+            'firstName': {
+                'romanizedText': 'Homer'
+            },
+            'secondName': {
+                'romanizedText': 'Simpson'
+            },
+            'isPrimary': True
+        }]
+    }
+
+    oclc_bib_mapping = OCLCBibMapping(base_oclc_bib)
+
+    assert ['Simpson, Homer|||true'] == oclc_bib_mapping.record.authors