rara-tools 0.6.11__tar.gz → 0.6.13__tar.gz

{rara_tools-0.6.11/rara_tools.egg-info → rara_tools-0.6.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.6.11
+Version: 0.6.13
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

rara_tools-0.6.13/VERSION

@@ -0,0 +1 @@
+0.6.13

{rara_tools-0.6.11 → rara_tools-0.6.13}/rara_tools/parsers/marc_records/base_record.py

@@ -1,13 +1,14 @@
 from typing import List, NoReturn, Tuple
 from abc import abstractmethod
 from pymarc.record import Record
+from pymarc.marcjson import JSONHandler
 from rara_tools.constants.parsers import GeneralMarcIDs
 
 
 class BaseRecord:
     """ Implements general logic of parsing MARC files.
     """
-    def __init__(self, record: Record, add_variations: bool = False) -> NoReturn:
+    def __init__(self, record: Record | dict, add_variations: bool = False) -> NoReturn:
         """ Initializes BaseRecord object.
 
         Parameters
@@ -21,8 +22,8 @@ class BaseRecord:
             via rara-norm-linker, it is necessary to enable this.
         """
         self.add_variations: bool = add_variations
-        self.__record_mrc: Record = record
-        self.__record_dict: dict = record.as_dict()["fields"]
+        self.__record_marc: Record = self._get_record_marc(record)
+        self.__record_dict: dict = self.marc_record.as_dict()["fields"]
 
         self.__id_field_id: List[str] = GeneralMarcIDs.ID
         self.__id_source_field_id: List[str] = GeneralMarcIDs.ID_SOURCE
@@ -30,6 +31,13 @@ class BaseRecord:
         self.__identifier: str = ""
         self.__identifier_source: str = ""
 
+    def _get_record_marc(self, record: Record | dict) -> Record:
+        """ Converts dict-type records into pymarc.Record objects.
+        """
+        if isinstance(record, dict):
+            record = JSONHandler().elements([record])[0]
+        return record
+
     def get_values(self,
             marc_ids: List[str],
             subfield_id: str | List[str] = "",
@@ -101,7 +109,7 @@ class BaseRecord:
 
     @property
     def marc_record(self) -> Record:
-        return self.__record_mrc
+        return self.__record_marc
 
     @property
     def marc_json_record(self) -> dict:

{rara_tools-0.6.11 → rara_tools-0.6.13}/rara_tools/parsers/marc_records/organization_record.py

@@ -1,7 +1,7 @@
 from typing import List, NoReturn
 from pymarc.record import Record
 from rara_tools.parsers.marc_records.base_record import BaseRecord
-from rara_tools.constants.parsers import OrganizationMarcIDs
+from rara_tools.constants.parsers import OrganizationMarcIDs, LOGGER
 import regex as re
 import json
 
@@ -38,9 +38,9 @@ class OrganizationRecord(BaseRecord):
         self.__name: str = ""
         self.__original_name: dict = {}
         self.__name_specification: str = ""
-        self.__life_years: str = ""
-        self.__birth_year: int = -1
-        self.__death_year: int = -1
+        self.__dates: str = ""
+        self.__location: str = ""
+        self.__numeration: str = ""
         self.__name_variations: List[str] = []
         self.__source: str = ""
         self.__description: str = ""
@@ -57,7 +57,10 @@ class OrganizationRecord(BaseRecord):
 
 
     def _clean_value(self, value: str) -> str:
-        cleaned_value = value.strip("., ")
+        try:
+            cleaned_value = value.strip("., ")
+        except Exception as e:
+            cleaned_value = ""
         return cleaned_value
 
     def _merge_and_clean(self, value: dict, keys: List[str]) -> str:
@@ -82,7 +85,10 @@ class OrganizationRecord(BaseRecord):
                     "b": self._clean_value(values[0].get("b", ""))
                 }
             else:
-                print(self.marc_record)
+                LOGGER.info(
+                    f"Could not parse subfields 'a' and/or 'b' from " \
+                    f"field {self.__name_field_id}. Record:\n{self.marc_record}"
+                )
         return self.__original_name
 
     @property
@@ -91,6 +97,39 @@ class OrganizationRecord(BaseRecord):
             self.__name = self._merge_and_clean(self.original_name, ["a", "b"])
         return self.__name
 
+    @property
+    def dates(self) -> str:
+        if not self.__dates:
+            values = self.get_values(
+                marc_ids=self.__name_field_id,
+                subfield_id="d"
+            )
+            if values:
+                self.__dates = self._clean_value(values[0])
+        return self.__dates
+
+    @property
+    def location(self) -> str:
+        if not self.__location:
+            values = self.get_values(
+                marc_ids=self.__name_field_id,
+                subfield_id="c"
+            )
+            if values:
+                self.__location = self._clean_value(values[0])
+        return self.__location
+
+    @property
+    def numeration(self) -> str:
+        if not self.__numeration:
+            values = self.get_values(
+                marc_ids=self.__name_field_id,
+                subfield_id="n"
+            )
+            if values:
+                self.__numeration = self._clean_value(values[0])
+        return self.__numeration
+
     @property
     def acronyms(self) -> List[str]:
         if not self.__acronyms:

{rara_tools-0.6.11 → rara_tools-0.6.13/rara_tools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rara-tools
-Version: 0.6.11
+Version: 0.6.13
 Summary: Tools to support Kata's work.
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10

{rara_tools-0.6.11 → rara_tools-0.6.13}/tests/test_marc_parsers.py

@@ -5,13 +5,19 @@ from rara_tools.parsers.marc_parsers.person_parser import PersonsMARCParser
 from rara_tools.parsers.marc_parsers.organization_parser import OrganizationsMARCParser
 from rara_tools.parsers.marc_parsers.location_parser import LocationMARCParser
 from rara_tools.parsers.marc_parsers.title_parser import TitlesMARCParser
+from rara_tools.parsers.marc_records.person_record import PersonRecord
+from rara_tools.parsers.marc_records.organization_record import OrganizationRecord
+from tests.test_utils import read_json_file
 
-
-MARC_ROOT_DIR = os.path.join("tests", "test_data", "marc_records")
+ROOT_DIR = os.path.join("tests", "test_data", "marc_records")
+MARC_ROOT_DIR = os.path.join(ROOT_DIR, "mrc")
+JSON_ROOT_DIR = os.path.join(ROOT_DIR, "json")
 EMS_TEST_FILE = os.path.join(MARC_ROOT_DIR, "ems_test_subset.mrc")
 PER_TEST_FILE = os.path.join(MARC_ROOT_DIR, "per_test_subset.mrc")
 ORG_TEST_FILE = os.path.join(MARC_ROOT_DIR, "org_test_subset.mrc")
 TITLE_TEST_FILE = os.path.join(MARC_ROOT_DIR, "title_test_subset.mrc")
+PER_JSON_TEST_FILE = os.path.join(JSON_ROOT_DIR, "per_marc_json_record.json")
+ORG_JSON_TEST_FILE = os.path.join(JSON_ROOT_DIR, "org_marc_json_record.json")
 
 def test_ems_parser_without_variations():
     ems_marc_parser = EMSMARCParser(EMS_TEST_FILE, add_variations=False)
@@ -56,3 +62,18 @@ def test_title_parser_with_variations():
         assert "name" in record
         assert "link_variations" in record
         assert len(record["link_variations"]) > 0
+
+def test_creating_per_marc_record_with_json_input():
+    json_data = read_json_file(PER_JSON_TEST_FILE)
+    record = PersonRecord(json_data)
+    assert record.name == "Koidula, Lydia"
+
+
+def test_creating_org_marc_record_with_json_input():
+    json_data = read_json_file(ORG_JSON_TEST_FILE)
+    record = OrganizationRecord(json_data)
+    assert record.original_name.get("a") == "Eesti"
+    assert record.original_name.get("b") == "Riigikogu"
+    assert not record.location
+    assert not record.dates
+    assert not record.numeration

rara_tools-0.6.11/VERSION

@@ -1 +0,0 @@
-0.6.11