rara-tools 0.7.10__py3-none-any.whl → 0.7.12__py3-none-any.whl

rara_tools/normalizers/authorities.py

@@ -59,6 +59,9 @@ class AuthoritiesRecordNormalizer(RecordNormalizer):
             record, "046", "f", formatted_birth_date)
         death_date = self.get_subfield(
             record, "046", "g", formatted_death_date)
+        
+        if not birth_date and not death_date:
+            return
 
         subfields_046 = [
             Subfield("f", birth_date),
@@ -117,7 +120,9 @@ class AuthoritiesRecordNormalizer(RecordNormalizer):
         self._add_author(record, viaf_record)
 
     def _normalize_record(self, record: Record, sierraID: str,
-                          viaf_record: VIAFRecord, is_editing_existing_record: bool) -> Record:
+                          viaf_record: VIAFRecord, 
+                          is_editing_existing_record: bool,
+                          original_entity: str) -> Record:
         
         self._normalize_sierra(record, sierraID)
         self._normalize_viaf(record, viaf_record)

rara_tools/normalizers/base.py

@@ -213,13 +213,33 @@ class RecordNormalizer:
         )
 
     def _add_fields_to_record(self, record: Record, fields: List[Field]) -> Record:
-        # filter out subfields that are empty, or 0, as VIAF returns 0 for unknown dates
+        cleaned_fields = []
+        
         for field in fields:
-            field.subfields = [sub for sub in field.subfields if sub.value and sub.value not in ["0", 0]]
             
-        self._handle_repeatable_fields(record, *fields)
-        self._handle_editable_fields(record, *fields)
-        self._handle_default_fields(record, *fields)
+            # Always assume control fields cleaned
+            if field.tag < "010" and field.tag.isdigit():
+                cleaned_fields.append(field)
+                continue
+            
+            # filter out subfields that are empty or 0 (VIAF returns 0 for unknown dates)
+            field.subfields = [
+                sub for sub in field.subfields 
+                if sub.value and sub.value not in ["0", 0]
+            ]
+            
+            # only keep the field if it still has subfields left
+            if field.subfields:
+                cleaned_fields.append(field)
+
+        if not cleaned_fields:
+            return record
+        
+        self._handle_repeatable_fields(record, *cleaned_fields)
+        self._handle_editable_fields(record, *cleaned_fields)
+        self._handle_default_fields(record, *cleaned_fields)
+        
+        return record
 
     def _add_author(self, record: Record, viaf_record: VIAFRecord) -> Optional[Field]:
 
@@ -360,7 +380,7 @@ class RecordNormalizer:
         return viaf_record
 
     def _normalize_record(self, record: Record, sierraID: str,
-                          viaf_record: VIAFRecord, is_editing_existing_record: bool) -> Record:
+                          viaf_record: VIAFRecord, is_editing_existing_record: bool, original_entity: str) -> Record:
         return record
 
     @property
@@ -374,7 +394,11 @@ class RecordNormalizer:
                 logger.error(f"Failed to normalize record: {e}")
                 continue
         return result
-
+    
+    @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"
@@ -391,7 +415,7 @@ class RecordNormalizer:
             record = self._normalize_common(record, is_editing_existing_record)
 
             normalized_record = self._normalize_record(
-                record, sierra_id, viaf_record, is_editing_existing_record)
+                record, sierra_id, viaf_record, is_editing_existing_record, original_entity=entity)
 
             normalized_record.fields.sort(key=lambda field: field.tag)
 

rara_tools/normalizers/bibs.py

@@ -1,4 +1,5 @@
 from pymarc import (Field, Subfield, Record)
+from typing import List, Optional
 
 from rara_tools.constants import EMPTY_INDICATORS
 from rara_tools.normalizers.viaf import VIAFRecord
@@ -34,10 +35,57 @@ class BibRecordNormalizer(RecordNormalizer):
         ]
 
         self._add_fields_to_record(record, fields)
+        
+    def _include_name_variations(self, record: Record, viaf_record: VIAFRecord) -> None:
+        """ Include name variations from VIAF record as 400|t fields """
+        
+        if not viaf_record or not viaf_record.name_variations:
+            return
+        
+        existing_name_variations = record.get_fields("400")
+        existing_variations = [sf.value for field in existing_name_variations for sf in field.get_subfields("t")]
+        
+        fields = []
+        
+        for variation in viaf_record.name_variations:
+            if variation not in existing_variations:
+                fields.append(
+                    Field(
+                        tag="400",
+                        indicators=EMPTY_INDICATORS,
+                        subfields=[
+                            Subfield("t", variation)
+                        ]
+                    )
+                )
+        
+        self._add_fields_to_record(record, fields)
+        
+    def _add_author(self, record: Record, viaf_record: Optional[VIAFRecord], original_entity: str) -> Optional[Field]:
+        if record.get("100") or record.get("110") or record.get("111"):
+            return record
 
-    def _normalize_viaf(self, record: Record, viaf_record: VIAFRecord) -> None:
+        type_map = {
+            "Personal": "100",
+            "Corporate": "110",
+            "Collective": "111"
+        }
+        
+        tag = type_map.get(getattr(viaf_record, "name_type", None), "100")
+        title = getattr(viaf_record, "name", None) or original_entity
 
+        fields = [Field(tag=tag, indicators=EMPTY_INDICATORS, subfields=[Subfield("t", title)])]
+        
+        self._add_fields_to_record(record, fields)
+        
+        if viaf_record:
+            self._include_name_variations(record, viaf_record)
+
+    def _normalize_viaf(self, record: Record, viaf_record: VIAFRecord, original_entity: str) -> None:
+        
         if not viaf_record:
+            # viaf record not found, include original entity as 100|t
+            self._add_author(record, viaf_record=None, original_entity=original_entity)
             return record
 
         viaf_id = viaf_record.viaf_id
@@ -52,12 +100,12 @@ class BibRecordNormalizer(RecordNormalizer):
         ]
 
         self._add_fields_to_record(record, fields)
-        self._add_author(record, viaf_record)
+        self._add_author(record, viaf_record, original_entity=original_entity)
 
     def _normalize_record(self, record: Record, sierraID: str,
-                          viaf_record: VIAFRecord, is_editing_existing_record: bool) -> Record:
+                          viaf_record: VIAFRecord, is_editing_existing_record: bool, original_entity: str) -> Record:
 
         self._normalize_sierra(record)
-        self._normalize_viaf(record, viaf_record)
+        self._normalize_viaf(record, viaf_record, original_entity=original_entity)
 
         return record

{rara_tools-0.7.10.dist-info → rara_tools-0.7.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.10
+Version: 0.7.12
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.10.dist-info → rara_tools-0.7.12.dist-info}/RECORD

@@ -20,9 +20,9 @@ rara_tools/core_formatters/formatted_keyword.py,sha256=hhi6wh4ErFionjBqYsEeKGbf1
 rara_tools/core_formatters/formatted_meta.py,sha256=r0RPG4eM-REPIR1DrIJnvYPQtQrzkgdvX9tvhNWjQ0Y,5250
 rara_tools/core_formatters/formatted_object.py,sha256=7a499ZmcZXOqtlwxDi6FWHWF5a6HdCsduS22wV3uHIE,5656
 rara_tools/normalizers/__init__.py,sha256=_NqpS5w710DhaURytHq9JpEt8HgYpSPfRDcOtOymJgE,193
-rara_tools/normalizers/authorities.py,sha256=7YlUFlhQTCJOT7umcrZE2Td_w1YIpBxVqW0b7rBDTbU,4645
-rara_tools/normalizers/base.py,sha256=BpRI2BSA9qKW0ux3rFJMTQsxjPB8gYObHtcvDoJwMOU,15256
-rara_tools/normalizers/bibs.py,sha256=5NZooArBYaRE_MCG2g3A4kxiRzMoXAqGkx_hCbPzKlM,2018
+rara_tools/normalizers/authorities.py,sha256=w7r2KIFSnmo57Pt9YGsxYYCH8AkdNkiBBFHhpf1GLJA,4794
+rara_tools/normalizers/base.py,sha256=LzWdjzG_5zFGbzOCpUSOdmzrJJ7p23iODEtar8wDrrY,15942
+rara_tools/normalizers/bibs.py,sha256=7H-spiqj6x8Xk4JQkBY5GK7q5pKjYUmXTRFf0RgzC-w,4040
 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-0.7.10.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
-rara_tools-0.7.10.dist-info/METADATA,sha256=hQFvtq4KzNHR_aDzynXw2WJH-HbdKJshP0oYoy1kmss,4080
-rara_tools-0.7.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rara_tools-0.7.10.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
-rara_tools-0.7.10.dist-info/RECORD,,
+rara_tools-0.7.12.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
+rara_tools-0.7.12.dist-info/METADATA,sha256=N8gNFTv8yIgSSp2DgZ7q97V_t_KC-YZHIjsfiAlTcPo,4080
+rara_tools-0.7.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rara_tools-0.7.12.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
+rara_tools-0.7.12.dist-info/RECORD,,