rara-tools 0.7.14__tar.gz → 0.7.15__tar.gz

{rara_tools-0.7.14/rara_tools.egg-info → rara_tools-0.7.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.14
+Version: 0.7.15
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

rara_tools-0.7.15/VERSION

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

{rara_tools-0.7.14 → rara_tools-0.7.15}/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-0.7.14 → rara_tools-0.7.15}/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
@@ -44,16 +44,16 @@ 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 []:
+    
+        for idx, linked in enumerate(linking_results or []):
+            
             if not isinstance(linked, dict):
                 continue
 
@@ -70,12 +70,12 @@ class RecordNormalizer:
                 })
                 self.records_extra_data.append({
                     "entity": entity,
-                    "classified_fields": classified_fields,
+                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
                     "edited": False
                 })
                 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.")
@@ -85,7 +85,7 @@ class RecordNormalizer:
                 })
                 self.records_extra_data.append({
                     "entity": entity,
-                    "classified_fields": classified_fields,
+                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
                     "edited": False
                 })
                 continue   
@@ -100,7 +100,7 @@ class RecordNormalizer:
                 self.records_extra_data.append({
                     "entity": entity,
                     "viaf": linked_item.get("viaf", {}),
-                    "classified_fields": classified_fields,
+                    "classified_fields": classified_fields[idx] if idx < len(classified_fields) else [],
                     "type": "linked",
                     "edited": True
                 })
@@ -359,10 +359,12 @@ 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 +375,6 @@ 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:
@@ -474,6 +475,13 @@ class RecordNormalizer:
     def _normalize_record(self, record: Record, sierraID: str,
                           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]:
@@ -490,7 +498,7 @@ 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"
         sierra_id_path = "sierraID"

{rara_tools-0.7.14 → rara_tools-0.7.15}/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 → rara_tools-0.7.15/rara_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.14
+Version: 0.7.15
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.14 → rara_tools-0.7.15}/tests/test_normalization.py

@@ -741,6 +741,7 @@ def test_classified_fields_added_to_linked_record():
     """ Test that classified fields Can be passed to normalizer & added to linked record """
     
     classified_fields = [
+    [
         {
             "670": {
                 "ind1": " ",
@@ -753,6 +754,7 @@ def test_classified_fields_added_to_linked_record():
             }
         }
     ]
+    ]
     # Case 1 - no 670 exists, should be added to linked record
     for normalizer in (AuthoritiesRecordNormalizer, BibRecordNormalizer):
         linking_results = [MOCK_LINKER_NOT_FOUND]
@@ -776,4 +778,67 @@ def test_classified_fields_added_to_linked_record():
         record = normalizer.first
         fields_670 = record.get_fields("670")
         assert len(fields_670) == 1
-        assert fields_670[0].get_subfields("a")[0] == "Eesti kirjarahva leksikon, 1995."
+        assert fields_670[0].get_subfields("a")[0] == "Eesti kirjarahva leksikon, 1995."
+        
+def test_classified_data_with_multiple_records():
+    """ Test classified data with multiple records - should match by sierraID """
+    
+    classified_fields = [
+        [{
+            "670": {
+                "ind1": " ",
+                "ind2": "0",
+                "subfields": [
+                    {
+                        "a": "Päikesekiri, 2021"
+                    }
+                ]
+            },
+            "111": {
+                "ind1": "2",
+                "ind2": " ",
+                "subfields": [
+                    {
+                        "a": "Eesti Kirjandusmuuseum"
+                    }
+                ]
+            }
+        }],
+       [],
+       [{
+            "670": {
+                "ind1": " ",
+                "ind2": "0",
+                "subfields": [
+                    {
+                        "a": "Teine kirjeldus, 2022"
+                    }
+                ]
+            }
+        }], 
+    ]
+    
+    # Case 1 - no 670 exists, should be added to linked record
+    for normalizer in (AuthoritiesRecordNormalizer, BibRecordNormalizer):
+        linking_results = [MOCK_LINKER_NOT_FOUND, MOCK_LINKER_ONE_FOUND, MOCK_LINKER_NOT_FOUND]
+        normalizer = normalizer(linking_results=linking_results, classified_fields=classified_fields)
+        
+        # Check first record - should have 670 & 111 from classified data
+        record = normalizer.first
+        assert len(record.get_fields("670")) == 1
+        fields_670 = record.get_fields("670")[0]
+        fields_111 = record.get_fields("111")[0]
+        assert fields_670.get_subfields("a")[0] == "Päikesekiri, 2021"
+        assert fields_111.get_subfields("a")[0] == "Eesti Kirjandusmuuseum"
+        
+        # Check second record - should not have 670 from classified data
+        record = normalizer.get_record(1)
+        assert len(record.get_fields("670")) == 1
+        fields_670 = record.get_fields("670")[0]
+        assert fields_670.get_subfields("a")[0] == "Eesti kirjarahva leksikon, 1995."
+        
+        # Check third record - should have 670 from classified data
+        record = normalizer.get_record(2)
+        assert len(record.get_fields("670")) == 1
+        fields_670 = record.get_fields("670")[0]
+        assert fields_670.get_subfields("a")[0] == "Teine kirjeldus, 2022"

rara_tools-0.7.14/VERSION

@@ -1 +0,0 @@
-0.7.14