rara-tools 0.7.14__py3-none-any.whl → 0.7.16__py3-none-any.whl

rara_tools/normalizers/authorities.py

@@ -11,7 +11,7 @@ class AuthoritiesRecordNormalizer(RecordNormalizer):
     """ Normalize authorities records """
 
     def __init__(self, linking_results: List[dict] = [], sierra_data: List[dict] = [],
-                 classified_fields: List[str] = [],
+                 classified_fields: List[List[dict]] = [],
                  ALLOW_EDIT_FIELDS: List[str] = ["008", "925"],
                  REPEATABLE_FIELDS: List[str] = ["024", "035", "400", "667"]):
 

rara_tools/normalizers/base.py

@@ -34,7 +34,7 @@ class RecordNormalizer:
         entities: List of Full names (str). If included, will use NormLinker to match with normalized records on KATA elastic.
     """
 
-    def __init__(self, linking_results: List[dict] = [], sierra_data: List[dict] = [], classified_fields: List[str] = [],
+    def __init__(self, linking_results: List[dict] = [], sierra_data: List[dict] = [], classified_fields: List[List[dict]] = [],
                  ALLOW_EDIT_FIELDS: List[str] = ["925"], REPEATABLE_FIELDS: List[str] = ["667"]):
 
         # Include, if will replace existing field
@@ -44,17 +44,30 @@ class RecordNormalizer:
         # leader applied to new records
         self.DEFAULT_LEADER = "01682nz  a2200349n  4500" # must be 24 digits
 
-    def _setup_records(self, linking_results: List[dict], sierra_data: List[dict], classified_fields: List[str] = []) -> JSONReader:
+    def _setup_records(self, linking_results: List[dict], sierra_data: List[dict], classified_fields: List[List[dict]] = []) -> JSONReader:
         """Setup initial MARC records and data.
         
         If no linked entities or more than one linked entity found, we create a new record.
         If one linked entity found, we create an updated record from the linked entity data.
         """
-        
         linked_records = []
         
-        for linked in linking_results or []:
+        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,
-                    "edited": False
-                })
+                handle_create_new_record(entity, idx)
                 continue
             
-            if len(linked_info) > 1:
+            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,
-                    "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,
-                    "type": "linked",
+                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
                     "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 [])
@@ -359,10 +357,12 @@ class RecordNormalizer:
     def _include_classified_fields(self, record: Record, classified_fields: list[dict]) -> None:
         """Include classified fields from core, if any.
         e.g. classified_fields=[{'670': {'ind1': ' ', 'ind2': '0', 'subfields': [{'a': 'Päikesekiri, 2021'}]}}]
+        
+        For each record, we need a list of dicts, to handle repeatable fields.
         """
         if not classified_fields:
             return
-
+        
         fields = [
             Field(
                 tag=str(tag),
@@ -373,7 +373,6 @@ class RecordNormalizer:
             for tag, v in field_dict.items()
         ]
 
-        logger.info(f"Adding classified fields: {[f.tag for f in fields]}")
         self._add_fields_to_record(record, fields)
 
     def _normalize_common(self, record: Record, is_editing_existing_record: bool, classified_fields: List[dict]) -> None:
@@ -464,6 +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(
@@ -472,8 +473,16 @@ 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:
+        """Get normalized record by index."""
+        for idx, record in enumerate(self):
+            if idx == index:
+                return record
+        raise IndexError("Record index out of range.")
 
     @property
     def data(self) -> List[dict]:
@@ -490,21 +499,28 @@ class RecordNormalizer:
     @property
     def first(self) -> Record:
         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/normalizers/bibs.py

@@ -12,7 +12,7 @@ class BibRecordNormalizer(RecordNormalizer):
     """ Normalize bib records. """
 
     def __init__(self, linking_results: List[dict] = [], sierra_data: List[dict] = [],
-                 classified_fields: List[str] = [],
+                 classified_fields: List[List[dict]] = [],
                  ALLOW_EDIT_FIELDS: List[str] = ["008", "925"],
                  REPEATABLE_FIELDS: List[str] = ["667"]):
         super().__init__(linking_results, sierra_data, classified_fields)

{rara_tools-0.7.14.dist-info → rara_tools-0.7.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.14
+Version: 0.7.16
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.14.dist-info → rara_tools-0.7.16.dist-info}/RECORD

@@ -20,9 +20,9 @@ rara_tools/core_formatters/formatted_keyword.py,sha256=hhi6wh4ErFionjBqYsEeKGbf1
 rara_tools/core_formatters/formatted_meta.py,sha256=WEnMs8K0YeTLGjXn_mxQTpshxcz5_9YjvqcbRFa3M1g,5605
 rara_tools/core_formatters/formatted_object.py,sha256=7a499ZmcZXOqtlwxDi6FWHWF5a6HdCsduS22wV3uHIE,5656
 rara_tools/normalizers/__init__.py,sha256=_NqpS5w710DhaURytHq9JpEt8HgYpSPfRDcOtOymJgE,193
-rara_tools/normalizers/authorities.py,sha256=U3IjQW3XaxAiIJ30Jlq6ON8fdXgrtgNwrvX8oy_iKL0,5304
-rara_tools/normalizers/base.py,sha256=SkbzmAOX5C6PbEFC9i_mpzK1u6LMAh7PavG52ULeO2Y,19744
-rara_tools/normalizers/bibs.py,sha256=DMjJj1mCVVWRpL2NuR6b7W1RWqkx50xix34X_tyxJig,3931
+rara_tools/normalizers/authorities.py,sha256=iW3cYOqqVJKy4CcnG9_T6dN-1bBT1e-0jtLYvco-MyQ,5311
+rara_tools/normalizers/base.py,sha256=DhMicY5p_N2SC_E3lbWUvSM77AOy_pBjQpbLSvYWDxM,20488
+rara_tools/normalizers/bibs.py,sha256=s8NGoieCjiftASUb--1YvYZ0VzW6uBt2ZidhLi_wP9A,3938
 rara_tools/normalizers/reader.py,sha256=GYCkAtnsNx135w5lD-_MqCZzdHQHHPDF-pDxYj839Vo,1595
 rara_tools/normalizers/viaf.py,sha256=C-NfbvL83ZcHVB9ICMw43wAMYKTqDTHU3ZT2mXKec00,24288
 rara_tools/parsers/marc_parsers/base_parser.py,sha256=Kdw4aivJf2FkWgIK7pJtHtVXF_G1pjHVQ7IcFItSqy8,1649
@@ -39,8 +39,8 @@ rara_tools/parsers/marc_records/title_record.py,sha256=XrtJ4gj7wzSaGxNaPtPuawmqq
 rara_tools/parsers/tools/entity_normalizers.py,sha256=VyCy_NowCLpOsL0luQ55IW-Qi-J5oBH0Ofzr7HRFBhM,8949
 rara_tools/parsers/tools/marc_converter.py,sha256=LgSHe-7n7aiDrw2bnsB53r3fXTRFjZXTwBYfTpL0pfs,415
 rara_tools/parsers/tools/russian_transliterator.py,sha256=5ZU66iTqAhr7pmfVqXPAI_cidF43VqqmuN4d7H4_JuA,9770
-rara_tools-0.7.14.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
-rara_tools-0.7.14.dist-info/METADATA,sha256=GIybax1V5ZqALB6SH-oN-e0Cu9-0dbt7rRph7lsEY-Q,4080
-rara_tools-0.7.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rara_tools-0.7.14.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
-rara_tools-0.7.14.dist-info/RECORD,,
+rara_tools-0.7.16.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
+rara_tools-0.7.16.dist-info/METADATA,sha256=yBmOUFVy7V6RyZdN_qBGkY7M8zH7H7h7v_QLQeZ3bAM,4080
+rara_tools-0.7.16.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rara_tools-0.7.16.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
+rara_tools-0.7.16.dist-info/RECORD,,