rara-tools 0.7.15__py3-none-any.whl → 0.7.17__py3-none-any.whl

rara_tools/normalizers/base.py

@@ -3,6 +3,8 @@ from pymarc import (Field, Subfield, JSONReader, Record)
 from typing import List, Optional, Iterator
 from rara_tools.normalizers.reader import SafeJSONReader
 
+from rara_tools.parsers.tools.validators import filter_names
+
 from rara_tools.normalizers.viaf import VIAFRecord, VIAFClient
 from rara_tools.constants.normalizers import (
     DEFAULT_VIAF_FIELD, ALLOWED_VIAF_FIELDS, ALLOWED_VIAF_WIKILINK_LANGS,
@@ -51,10 +53,23 @@ 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 +77,32 @@ 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 +110,6 @@ class RecordNormalizer:
         self.records_extra_data.extend(
             {
                 "sierraID": obj.get("sierraID"),
-                "type": "sierra",
                 "edited": True
             }
             for obj in (sierra_data or [])
@@ -313,25 +313,34 @@ class RecordNormalizer:
         if viaf_record:
             self._include_name_variations(record, viaf_record)
             
-    def _include_name_variations(self, record: Record, viaf_record: VIAFRecord) -> None:
+    def _include_name_variations(self, record: Record, viaf_record: VIAFRecord, filter_variations=True) -> 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")]
+        existing_variations = [sf.value for field in existing_name_variations for sf in field.get_subfields("a")]
+        
+        if filter_variations:
+            allowed_variations = filter_names(viaf_record.name_variations)
+            logger.debug(
+                f"filtered out {len(viaf_record.name_variations) - len(allowed_variations)} name variations for '{viaf_record.name}'"
+            )
+            
+        else:
+            allowed_variations = viaf_record.name_variations
         
         fields = []
         
-        for variation in viaf_record.name_variations:
+        for variation in allowed_variations:
             if variation not in existing_variations:
                 fields.append(
                     Field(
                         tag="400",
                         indicators=EMPTY_INDICATORS,
                         subfields=[
-                            Subfield("t", variation)
+                            Subfield("a", variation)
                         ]
                     )
                 )
@@ -465,6 +474,8 @@ 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 +484,8 @@ 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 +512,26 @@ 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/normalizers/bibs.py

@@ -73,26 +73,13 @@ class BibRecordNormalizer(RecordNormalizer):
             
           
     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
-        fields = [
-            Field(
-                tag="035",
-                indicators=EMPTY_INDICATORS,
-                subfields=[
-                    Subfield("a", viaf_id)
-                ]
-            )
-        ]
-
-        self._add_fields_to_record(record, fields)
+        
         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, original_entity: str) -> Record:
 

rara_tools/parsers/tools/validators.py

@@ -0,0 +1,54 @@
+import regex as re
+from typing import List
+
+def has_valid_chars(entity: str, allow_cyrillic: bool = True) -> bool:
+    """ Checks if entity contains any valid characters in latin
+    or in cyrillic, if the latter is enabled
+
+    Parameters
+    ------------
+    entity: str
+        String to validate.
+    allow_cyrillic: bool
+        Allow strings in cyrillic?
+
+    Returns
+    ------------
+    bool
+        Boolean value indicating, if the string
+        contains any valid characters.
+
+    """
+    # Check for latin characters
+    is_valid = bool(re.search(r"[a-züõöäA-ZÜÕÖÄ]", entity))
+
+    if allow_cyrillic and not is_valid:
+        # If cyrillic characters are allowed,
+        # check for them as well
+        is_valid = bool(re.search(r"[а-яА-Я]", entity))
+
+    return is_valid
+
+
+def filter_names(names: List[str], allow_cyrillic: bool = True) -> List[str]:
+    """ Filters out names not in allowed encodings (latin / cyrillic).
+
+    Parameters
+    ------------
+    names: List[str]
+        Names to filters.
+    allow_cyrillic: bool
+        Allow strings in cyrillic?
+
+    Returns
+    ------------
+    List[str]
+        List of filtered names.
+
+    """
+    filtered_names = [
+        name for name in names
+        if has_valid_chars(entity=name, allow_cyrillic=allow_cyrillic)
+    ]
+    return filtered_names
+    

{rara_tools-0.7.15.dist-info → rara_tools-0.7.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.7.15
+Version: 0.7.17
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.7.15.dist-info → rara_tools-0.7.17.dist-info}/RECORD

@@ -21,8 +21,8 @@ rara_tools/core_formatters/formatted_meta.py,sha256=WEnMs8K0YeTLGjXn_mxQTpshxcz5
 rara_tools/core_formatters/formatted_object.py,sha256=7a499ZmcZXOqtlwxDi6FWHWF5a6HdCsduS22wV3uHIE,5656
 rara_tools/normalizers/__init__.py,sha256=_NqpS5w710DhaURytHq9JpEt8HgYpSPfRDcOtOymJgE,193
 rara_tools/normalizers/authorities.py,sha256=iW3cYOqqVJKy4CcnG9_T6dN-1bBT1e-0jtLYvco-MyQ,5311
-rara_tools/normalizers/base.py,sha256=LzjQ6HZEdsnEbQzhTRJU23f16nch7ZgM6efXEY45zNY,20190
-rara_tools/normalizers/bibs.py,sha256=s8NGoieCjiftASUb--1YvYZ0VzW6uBt2ZidhLi_wP9A,3938
+rara_tools/normalizers/base.py,sha256=tw64ZK7KXg9O2IPMxICMogYHAG6il10qQqCd4fIjQL0,20941
+rara_tools/normalizers/bibs.py,sha256=5pOw8RsQ4eDwbREbYySeI_b7dQyGlJnfMRSS-tWGJ9c,3632
 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 +39,9 @@ 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-0.7.15.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
-rara_tools-0.7.15.dist-info/METADATA,sha256=_McWtiEQK0TGptlidWNxJ26zgdWB_kNk00DSrIAhtB8,4080
-rara_tools-0.7.15.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rara_tools-0.7.15.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
-rara_tools-0.7.15.dist-info/RECORD,,
+rara_tools/parsers/tools/validators.py,sha256=JTGbfAWcLldlZrX0nb343P9RJ8QwSh3455fYap3UxxY,1335
+rara_tools-0.7.17.dist-info/licenses/LICENSE.md,sha256=hkZVnIZll7e_KNEQzeY94Y9tlzVL8iVZBTMBvDykksU,35142
+rara_tools-0.7.17.dist-info/METADATA,sha256=of0OwoIpSaah24TRi1bIU78dL-rfQOIxcxSdZbRL5IU,4080
+rara_tools-0.7.17.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rara_tools-0.7.17.dist-info/top_level.txt,sha256=JwfB5b8BAtW5OFKRln2AQ_WElTRyIBM4nO0FKN1cupY,11
+rara_tools-0.7.17.dist-info/RECORD,,