rara-tools 0.7.15__tar.gz → 0.7.16__tar.gz

{rara_tools-0.7.15/rara_tools.egg-info → rara_tools-0.7.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.15
+Version: 0.7.16
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

rara_tools-0.7.16/VERSION

@@ -0,0 +1 @@
+0.7.16

{rara_tools-0.7.15 → rara_tools-0.7.16}/rara_tools/normalizers/base.py

@@ -51,10 +51,23 @@ class RecordNormalizer:
         If one linked entity found, we create an updated record from the linked entity data.
         """
         linked_records = []
+        
+        def handle_create_new_record(entity, idx):
+            logger.info(f"No linked entities found for {entity}, Creating new record.")
+            linked_records.append({
+                "leader": self.DEFAULT_LEADER,
+                "fields": []
+            })
+            self.records_extra_data.append({
+                "entity": entity,
+                "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
+                "edited": False,
+            })
     
         for idx, linked in enumerate(linking_results or []):
             
             if not isinstance(linked, dict):
+                logger.debug(f"Skipping invalid linked result: {linked}")
                 continue
 
             entity = linked.get("original_entity")
@@ -62,46 +75,32 @@ class RecordNormalizer:
 
             if not isinstance(linked_info, list) or not linked_info:
                 # No linked entities found, create new record
-                logger.info(
-                    f"No linked entities found for {entity}, Creating new record.")
-                linked_records.append({
-                    "leader": self.DEFAULT_LEADER,
-                    "fields": []
-                })
-                self.records_extra_data.append({
-                    "entity": entity,
-                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
-                    "edited": False
-                })
+                handle_create_new_record(entity, idx)
                 continue
             
             elif len(linked_info) > 1:
                 # Multiple linked entities found, create new record
-                logger.info(
-                    f"Multiple linked entities found for {entity}. Creating new record.")
-                linked_records.append({
-                    "leader": self.DEFAULT_LEADER,
-                    "fields": []
-                })
-                self.records_extra_data.append({
-                    "entity": entity,
-                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
-                    "edited": False
-                })
+                handle_create_new_record(entity, idx)
                 continue   
 
             elif len(linked_info) == 1:
+                # one record match found, we update existing record
+                
                 linked_item = linked_info[0]
                 if not isinstance(linked_item, dict):
                     continue
                 
+                # handle case where we have linked an entity without a record
+                if not linked_item.get("json", None):
+                    handle_create_new_record(entity, idx)
+                    continue
+                
                 linked_records.append(linked_item.get("json", {}))
                 
                 self.records_extra_data.append({
                     "entity": entity,
                     "viaf": linked_item.get("viaf", {}),
                     "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
-                    "type": "linked",
                     "edited": True
                 })
                 continue
@@ -109,7 +108,6 @@ class RecordNormalizer:
         self.records_extra_data.extend(
             {
                 "sierraID": obj.get("sierraID"),
-                "type": "sierra",
                 "edited": True
             }
             for obj in (sierra_data or [])
@@ -465,6 +463,8 @@ class RecordNormalizer:
                         verify=verify,
                         threshold=threshold
                     )
+                    if viaf_record:
+                        logger.debug(f"VIAF {search_term}, linked to ID: {viaf_record.viaf_id}")
 
         except Exception as e:
             logger.error(
@@ -473,7 +473,8 @@ class RecordNormalizer:
         return viaf_record
 
     def _normalize_record(self, record: Record, sierraID: str,
-                          viaf_record: VIAFRecord, is_editing_existing_record: bool, original_entity: str) -> Record:
+                          viaf_record: VIAFRecord, is_editing_existing_record: bool, 
+                          original_entity: str) -> Record:
         return record
     
     def get_record(self, index: int) -> Record:
@@ -500,19 +501,26 @@ class RecordNormalizer:
         return next(iter(self))
       
     def __iter__(self) -> Iterator:
-        viaf_id_path = "viaf.queryResult.records.record.0.recordData.VIAFCluster.viafID"
+        # viaf_id_path = "viaf.original.queryResult.viafID"
+        viaf_id_path = "viaf.parsed.viaf_id"
+        
         sierra_id_path = "sierraID"
-
+        
         for record, extra_data in zip(self.records, self.records_extra_data):
             
             sierra_id = glom(extra_data, sierra_id_path, default="")
             viaf_id = glom(extra_data, viaf_id_path, default=None)
-            classified_fields = extra_data.get("classified_fields", [])
             
+            classified_fields = extra_data.get("classified_fields", [])
             entity = extra_data.get("entity")
             is_editing_existing_record = extra_data.get("edited") == True
 
             viaf_record = self._get_viaf_record(record, viaf_id, entity)
+            if viaf_record:
+                logger.debug(
+                    f"linked VIAF record with ID {viaf_record.viaf_id} for entity '{entity}'"
+                )
+            
             record = self._normalize_common(record, is_editing_existing_record, classified_fields)
 
             normalized_record = self._normalize_record(

{rara_tools-0.7.15 → rara_tools-0.7.16/rara_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.15
+Version: 0.7.16
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.15 → rara_tools-0.7.16}/tests/test_normalization.py

@@ -5,6 +5,7 @@ from rara_tools.constants import YYMMDD_FORMAT
 from rara_tools.normalizers import (BibRecordNormalizer, AuthoritiesRecordNormalizer)
 from tests.test_utils import (get_linker_res_example, get_formatted_sierra_response,
                         check_record_tags_sorted, check_no_dupe_tag_values, check_record_tags_have_values)
+from rara_tools.normalizers.viaf import VIAFRecord
 
 from rara_tools.constants.linker import EntityType
 
@@ -842,3 +843,58 @@ def test_classified_data_with_multiple_records():
         assert len(record.get_fields("670")) == 1
         fields_670 = record.get_fields("670")[0]
         assert fields_670.get_subfields("a")[0] == "Teine kirjeldus, 2022"
+        
+        
+def test_viaf_name_variations():
+    """ Test adding alternative name forms from VIAF to 4XX fields. Should skip some variants """
+    
+    normalizer = AuthoritiesRecordNormalizer()
+    record = Record()
+    
+    viaf_record: VIAFRecord = normalizer._get_viaf_record(
+        record,
+        entity="Jaan Kaplinski"
+    )
+    
+    assert viaf_record is not None
+    assert len(viaf_record.name_variations) > 0
+    
+    normalizer._add_author(record, viaf_record)
+    
+    fields_4xx = record.get_fields("400") + record.get_fields("410") + record.get_fields("430")
+    assert len(fields_4xx) > 0
+    
+def test_existing_record_linked_to_viaf_record():
+    """ Test existing record linked to VIAF record - should enrich with VIAF data """
+    
+    base_path = "tests/test_data/marc_records/json/"
+    with open(os.path.join(base_path, "imbi.json"), "r", encoding="utf-8") as f, \
+        open(os.path.join(base_path, "ernits.json"), "r", encoding="utf-8") as f2, \
+        open(os.path.join(base_path, "rowling.json"), "r", encoding="utf-8") as f3:
+        imbi = json.load(f)
+        ernits = json.load(f2)
+        rowling = json.load(f3)
+        
+    linking_results = [
+        imbi, 
+        ernits,
+        rowling
+    ]
+    
+    normalizer = AuthoritiesRecordNormalizer(
+        linking_results=linking_results,
+    )
+    
+    def get_viaf_url(record: Record):
+        field_024 = record.get_fields("024")
+        if len(field_024) == 0:
+            return None
+        return field_024[0].get_subfields("0")[0]
+    
+    viaf_base_url = "http://viaf.org/viaf"
+    assert get_viaf_url(normalizer.get_record(0)) == f"{viaf_base_url}/167120147/"
+    assert get_viaf_url(normalizer.get_record(1)) == f"{viaf_base_url}/22458146/"
+    assert get_viaf_url(normalizer.get_record(1)) == f"{viaf_base_url}/22458146/"
+    assert get_viaf_url(normalizer.get_record(2)) == f"{viaf_base_url}/116796842/"
+    
+  

rara_tools-0.7.15/VERSION

@@ -1 +0,0 @@
-0.7.15