gedcom-x 0.5.10__py3-none-any.whl → 0.5.11__py3-none-any.whl

{gedcom_x-0.5.10.dist-info → gedcom_x-0.5.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gedcom-x
-Version: 0.5.10
+Version: 0.5.11
 Summary: Python implimentation of gedcom-x standard
 Author-email: "David J. Cartwright" <davidcartwright@hotmail.com>
 License: MIT

gedcom_x-0.5.11.dist-info/RECORD

@@ -0,0 +1,57 @@
+gedcomx/TopLevelTypeCollection.py,sha256=p99i-O5LXiXe3GlC6jWuz4nH1TAcKxOLbe0VRxWbSFY,1495
+gedcomx/Zip.py,sha256=lBxcv-Vip45884EHj56wZJJ5I36Q38UuHUidDxQBoS8,14
+gedcomx/__init__.py,sha256=p9oSZV2SxOwWLK69ukr5eQnVw761qkr4wGpBxtcxMJ8,1880
+gedcomx/address.py,sha256=gXQ6xAVNZ1ywM8NhsSIIaOE_CVUsRrYIj452NnZOic8,8138
+gedcomx/agent.py,sha256=Dox8o2YbuEYf8iYnwJ_r_3LL8WJp_5Np3idRKcXZKyE,13037
+gedcomx/attribution.py,sha256=AF3N3sfenHLBJQ52uvGs05oIrZtY1bddYjgZqe5rRCY,4673
+gedcomx/conclusion.py,sha256=B5_lR7bPQ6VT_08uLNLNuiJkgWwoDz61zBCm_mi7Z6I,11377
+gedcomx/converter.py,sha256=H7SUoSdsP0m0AK0BSDOnavJW1uMjdJ-zEHThMRVUCTI,60641
+gedcomx/coverage.py,sha256=59jY_L1-Y20HDoMODd1FfRHF4v3rXMDbAIf51qa7txM,2293
+gedcomx/date.py,sha256=mI7wKIK1AqFebw8zl5dXTLCPLe41lHW2GdJ5QdhQrXs,3649
+gedcomx/document.py,sha256=IsYhqmzOcmYPVaRmqiyt8evWYMCS7J0LUyLDAD0vPuQ,4655
+gedcomx/event.py,sha256=uuujR7XBFro2HqlZ123aMECOicZH-5HlHuPd6Qr_ki4,15519
+gedcomx/evidence_reference.py,sha256=PEOFo3CKGOjPUt42n9EL0EdEFtrof_msWhzRVq7Q3_E,1478
+gedcomx/exceptions.py,sha256=0OdPM3euhBMgX8o61ZwPuKeN8zPuSuuDcSBFflVGFqk,587
+gedcomx/extensible.py,sha256=6-VaJmOax8BoShKMKxKpJEyZf7aILqA8SMEqbRgP5yM,2659
+gedcomx/extensible_enum.py,sha256=DftCZLMBNul3C9hwh-rf0GE3SVdvylvyd5mt7bX_l6o,6535
+gedcomx/fact.py,sha256=_YrdxfL_FdiL5SmXcAjMhLZOfYi4VP_W8IEI7VTGOhc,25169
+gedcomx/gedcom.py,sha256=A8GQ670E6_knfP37kOGHdVl_cC9RXQoc4Dk6D_qlnuQ,2059
+gedcomx/gedcom5x.py,sha256=AjML2hXX5RG3mdc93o_3Q1KHoTI3ecoOB5CTGKqAfGo,24092
+gedcomx/gedcomx.py,sha256=964jNy72flnWNV9xBH44OyQthZarCmwge_8vagB3xd0,19419
+gedcomx/gender.py,sha256=11Pvi6VpclfWKmeAhzaxwt1KlkKxqhfKBChFTkeknCg,3338
+gedcomx/group.py,sha256=H44ie6tV1h-TYgEeNJhHhJLtw0xB2O9lrCCqv7IJ0sg,3105
+gedcomx/identifier.py,sha256=P9pKWh7eFAkFN7C-i63hb7nmMMvYvW7EGmShLqEtBCU,9694
+gedcomx/logging_hub.py,sha256=tU1fi2MUgY5_b_RwfssB3WTmNSVfvET1EBb-LrHmqWk,13528
+gedcomx/mutations.py,sha256=ugQgfQh0o9r8FIB_dz5s6KqPyIDMHn2YSP7DvAHsDv0,7236
+gedcomx/name.py,sha256=Gaa9d9OoMXb6x0Xn4t57uKEaGMENSgqzk3SlVolWwoQ,19712
+gedcomx/note.py,sha256=R6wWVtyAXFIdQMg5Jqyu9WfT3IBeLLpomX_hEKWSiHk,4265
+gedcomx/online_account.py,sha256=lSHtynqo1_eNlziJ8-QqbO1BVMCPHjohBgOOFPkJbao,1189
+gedcomx/person.py,sha256=kDh7nmNE7_WkQZXIMYbRRF85JNShEvFyJZR1YhSbZjU,9090
+gedcomx/place_description.py,sha256=IRyDvl_HWYtP-diEowwE9WNpRz3yblugSg5BYwIes3s,7664
+gedcomx/place_reference.py,sha256=9pyvQmo5NTzwmzvRo9cgWpWrrQ0q9oikAVGN5xSTH2w,3039
+gedcomx/qualifier.py,sha256=bXlqopQHju-hSUuk_SFH66S1Ou5YfSuxiITzpIXkcPA,2404
+gedcomx/relationship.py,sha256=maTCMOxRKVEF3dIzZ7qQaKZ2XmfqyjfwzYdNO1HjCDI,5972
+gedcomx/resource.py,sha256=B0Ey-RSGWthx8apWIN_5vHEMlxfj4s2nYY81Gob5LCw,4245
+gedcomx/schemas.py,sha256=gTc4RL348GtTeR9O8_qrztAGgfZZ9PGUwLEYzl0MZyE,20666
+gedcomx/serialization.py,sha256=JqnLq1Tyq3Kn9i1DceLXHES4ENSSLXWVw6y_ItQLZRM,31865
+gedcomx/source_citation.py,sha256=w6Ha9WTzLCzHELyTlYkwRJ176H6a8-sPZpFM3AK5-9w,1792
+gedcomx/source_description.py,sha256=rC1ItCuLj2Mm4JHm7oug1RkqJbse7XJG-VHvSlNbocU,19358
+gedcomx/source_reference.py,sha256=zutj_M4asKbGJUf_C9F6ZTxoe_gDlnHvBY6NGuiWl_E,7614
+gedcomx/subject.py,sha256=2LbZ_xHuirKENRJlJFRMsGFIiJWypRt21cWGRmFGc9c,5054
+gedcomx/textvalue.py,sha256=ChjlNzXB1DpiuHko85_KHzVmIxNBBgoP7c6AXVowVBk,3660
+gedcomx/translation.py,sha256=4REL68WaWqcC5f3XcBCZ1dn0gtaZftQJTCkvl1Sf-NA,61395
+gedcomx/uri.py,sha256=frFAHgKN6IX_-kS6btNpbxGu9jeaTD7laEkAopPzp5M,9765
+gedcomx/Extensions/__init__.py,sha256=MQzi_whzlxiLiknUNh10hG8OVrNqJE38l6n-AwCssx8,24
+gedcomx/Extensions/rs10/__init__.py,sha256=nSHoZiD8hsCAyE-KyRTuWSLqSJSFh12kSz7hqilAMps,26
+gedcomx/Extensions/rs10/rsLink.py,sha256=JhfaHBOK_rl1tPWmD5a8KYgfWl-nEjBpAO1pk4Z8osY,6056
+gedcomx/gedcom7/Exceptions.py,sha256=xeKr4x8b7r8pOqJ9yMpsCVTyxPeOlREDGgKoM5rX4U0,149
+gedcomx/gedcom7/GedcomStructure.py,sha256=45p6o01j_bmgCasfprDnGTVy-gyKM_8BuvAakLqCl3c,3431
+gedcomx/gedcom7/__init__.py,sha256=izlM3__nzpZ32qLU8cqqyIpGQ4cA9vlQh3_RXxgMCg4,682
+gedcomx/gedcom7/g7interop.py,sha256=hSzwqeok2n7xziEvN2QiJY7bVCWrOnZIZWXubnkrv7w,9945
+gedcomx/gedcom7/gedcom7.py,sha256=oAp94vmkGtyqqI8-3uA1t5bepxLovMSi3r9rZFlZ0Lg,5620
+gedcomx/gedcom7/logger.py,sha256=QM1SySyh91UEhs90d2DMhH-s9qGF8XS8I8gr1eOcmfw,617
+gedcomx/gedcom7/specification.py,sha256=H6l4IW4UX7YRKoNH6t84REFeGl52kEyRnn6a9f21gbg,288703
+gedcom_x-0.5.11.dist-info/METADATA,sha256=vOaxtFRW521ZXaucmUhih5LBt_tUezBCX-ZfuB7A06k,4333
+gedcom_x-0.5.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+gedcom_x-0.5.11.dist-info/top_level.txt,sha256=smVBF4nxSU-mzCd6idtRYTbYjPICMMi8pTqewEmqF8Y,8
+gedcom_x-0.5.11.dist-info/RECORD,,

gedcomx/Extensions/rs10/rsLink.py

@@ -20,6 +20,7 @@ GEDCOM Module Types
 """
 from ...exceptions import GedcomClassAttributeError
 from ...logging_hub import hub, logging
+from ...schemas import schema_class
 from ...uri import URI
 """
 ======================================================================
@@ -31,7 +32,7 @@ serial_log = "gedcomx.serialization"
 deserial_log = "gedcomx.deserialization"
 #=====================================================================
 
-
+@schema_class()
 class rsLink():
     """A link description object. RS Extension to GedcomX by FamilySearch.
 

gedcomx/__init__.py

@@ -1,4 +1,5 @@
 from .schemas import SCHEMA
+from .subject import Subject
 from .agent import Agent
 from .address import Address
 from .attribution import Attribution
@@ -24,7 +25,6 @@ from .gedcomx import GedcomX
 from .gender import Gender, GenderType
 from .group import Group, GroupRole
 from .identifier import Identifier, IdentifierType, IdentifierList
-from .Logging import get_logger
 from .name import Name, NameForm, NamePart, NamePartType, NameType, NamePartQualifier
 from .note import Note
 from .online_account import OnlineAccount
@@ -38,10 +38,12 @@ from .source_citation import SourceCitation
 from .source_description import SourceDescription
 from .source_description import ResourceType
 from .source_reference import SourceReference
-from .subject import Subject
+
 from .textvalue import TextValue
 from .resource import Resource
+SCHEMA.set_resource_class(Resource)
 from .uri import URI
+SCHEMA.set_uri_class(URI)
 
 
 from .Extensions.rs10.rsLink import rsLink
@@ -49,5 +51,5 @@ from .Extensions.rs10.rsLink import rsLink
 from .gedcom7.gedcom7 import Gedcom7, GedcomStructure
 from .translation import g7toXtable
 
-
+SCHEMA.normalize_all()
 

gedcomx/address.py

@@ -10,6 +10,7 @@ from typing import Any, Dict, Optional, List
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json_ refactoring
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -20,6 +21,7 @@ GEDCOM Module Types
 ======================================================================
 """
 from .logging_hub import hub, logging
+from .schemas import schema_class
 """
 ======================================================================
 Logging
@@ -29,6 +31,7 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
+@schema_class()
 class Address:
     """A GedcomX Address Data Type
     A GedcomX Address Data Type.

gedcomx/agent.py

@@ -1,7 +1,8 @@
-import base64
-import uuid
+from __future__ import annotations
 
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Union, TYPE_CHECKING
+if TYPE_CHECKING:
+    from .person import Person
 """
 ======================================================================
  Project: Gedcom-X
@@ -12,6 +13,7 @@ from typing import Any, Dict, List, Optional
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json_ refactor
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -25,6 +27,7 @@ from .address import Address
 from .identifier import Identifier, IdentifierList, make_uid
 from .online_account import OnlineAccount
 from .resource import Resource
+from .schemas import schema_class
 from .textvalue import TextValue
 from .uri import URI
 from .logging_hub import hub, logging
@@ -37,7 +40,7 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
-
+@schema_class(toplevel=True)
 class Agent:
     """A GedcomX Agent Data Type.
 
@@ -80,10 +83,10 @@ class Agent:
                     emails: Optional[List[URI]] = [], 
                     phones: Optional[List[URI]] = [], 
                     addresses: Optional[List[Address]] = [], 
-                    person: Optional[object] | Optional[Resource] = None, # should be of Type 'Person', 'object' to avoid circular imports
+                    person: Optional[Union[Resource,Person]] = None, # should be of Type 'Person', 'object' to avoid circular imports
                     #xnotes: Optional[List[Note]] = None,
                     attribution: Optional[object] = None, # Added for compatibility with GEDCOM5/7 Imports
-                    uri: Optional[URI | Resource] = None): 
+                    ): 
         
         
         self.id = id if id else make_uid()
@@ -123,6 +126,8 @@ class Agent:
             for current_name in self.names:
                 if name_to_add == current_name:
                     return
+            if name_to_add.value is None or name_to_add == '':
+                assert False
             self.names.append(name_to_add)
         else:
             raise ValueError(f'name must be of type str or TextValue, recived {type(name_to_add)}')

gedcomx/attribution.py

@@ -13,6 +13,7 @@ from typing import Optional, Dict, Any
  Updated:
    - 2025-08-31: fixed _as_dict_ to deal with Resources and ignore empty fields
    - 2025-09-03: _from_json_ refactor
+   - 2025-09-09: added schema_class
 
    
 ======================================================================
@@ -25,6 +26,7 @@ GEDCOM Module Types
 """
 from .agent import Agent
 from .resource import Resource
+from .schemas import schema_class
 from .logging_hub import hub, logging
 """
 ======================================================================
@@ -35,7 +37,7 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
-
+@schema_class()
 class Attribution:
     """Attribution Information for a Genealogy, Conclusion, Subject and child classes
 

gedcomx/conclusion.py

@@ -1,7 +1,7 @@
-
+from __future__ import annotations
 import warnings
 
-from typing import Any, Optional, List
+from typing import Any, Optional, List, Union, TYPE_CHECKING
 
 """
 ======================================================================
@@ -13,6 +13,7 @@ from typing import Any, Optional, List
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json_ refactor 
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -23,11 +24,14 @@ GEDCOM Module Type Imports
 ======================================================================
 """
 from .attribution import Attribution
+if TYPE_CHECKING:
+    from .document import Document
 from .Extensions.rs10.rsLink import _rsLinks, rsLink
 from .identifier import make_uid
 from .note import Note
 from .qualifier import Qualifier
 from .resource import Resource, URI
+from .schemas import schema_class
 from .source_reference import SourceReference
 from .logging_hub import hub, logging
 """
@@ -112,7 +116,7 @@ class ConfidenceLevel(Qualifier):
         key = getattr(self, "value", self)
         return descriptions.get(key, "No description available.")
 
-    
+@schema_class()    
 class Conclusion():
     """
     Represents a conclusion in the GEDCOM X conceptual model. A conclusion is a 
@@ -146,11 +150,10 @@ class Conclusion():
                  id: Optional[str] = None,
                  lang: Optional[str] = None,
                  sources: Optional[List[SourceReference]] = None,
-                 analysis: Optional[object | Resource] = None,
+                 analysis: Optional[Union[Resource,Document]] = None,
                  notes: Optional[List[Note]] = None,
                  confidence: Optional[ConfidenceLevel] = None,
                  attribution: Optional[Attribution] = None,
-                 uri: Optional[Resource] = None,
                  _max_note_count: int = 20,
                  links: Optional[_rsLinks] = None) -> None:
         
@@ -164,6 +167,7 @@ class Conclusion():
         self.attribution = attribution
         self.max_note_count = _max_note_count
         self.links = links if links else _rsLinks()    #NOTE This is not in specification, following FS format
+        self.uri = URI(fragment=id) if id else None
     
     def add_note(self,note_to_add: Note):
         if self.notes and len(self.notes) >= self.max_note_count:

gedcomx/converter.py

@@ -1,10 +1,11 @@
-DEBUG = False
 import logging
 import mimetypes
 import re
 import xml.etree.ElementTree as ET
 
 from typing import Any, Mapping
+from typing import Iterable, Callable, TypeVar, Hashable, List, Optional
+
 import math
 import shutil
 
@@ -73,6 +74,8 @@ serial_log = "gedcomx.serialization"
 convert_log = "gedcomx.convert.GEDCOM5x"
 #=====================================================================
 
+
+
 hub.start_channel(
     ChannelConfig(
         name=convert_log,
@@ -81,16 +84,22 @@ hub.start_channel(
         rotation="size:10MB:3",   # rotate by size, keep 3 backups
     ))
 
+T = TypeVar("T")
+K = TypeVar("K", bound=Hashable)
 
 class GedcomConverter():
     def __init__(self) -> None:
-        self.gedcomx = GedcomX()
+        self.gedcomx: GedcomX = GedcomX()
         self.object_map: dict[Any, Any] = {-1:self.gedcomx}
         self.missing_handler_count = {}
     
     type_name_type = {
         'aka': NameType.AlsoKnownAs
     }
+
+    personal_events = ["BARM", "BASM", "BLES", "CHRA", "CONF", "CENS", "CREM", "EMIG", "GRAD", "NATU", "ORDN", "RETI", "WILL"]
+
+
     gedcom_even_to_fact = {
     # Person Fact Types
     "ADOP": FactType.Adoption,
@@ -193,24 +202,25 @@ class GedcomConverter():
     
     def parse_gedcom5x_record(self,record: Gedcom5xRecord):
         if record is not None: 
-            with hub.use(convert_log):       
-                handler_name = 'handle_' + record.tag.lower()
-                
-                if hasattr(self,handler_name): 
+            with hub.use(convert_log):
+                handler_name = 'handle_' + record.tag.lower() 
+                if record.tag in self.personal_events:
+                    self.handle_pevent(record)
+                elif hasattr(self,handler_name):                                            
                     log.info(f'Using {handler_name} to pars Record: {record.describe()}')         
                     handler = getattr(self,handler_name)            
                     handler(record)
-                    if record.tag != 'FAM':
-                        for sub_record in record.subRecords():
-                            log.debug(sub_record.describe())
-                            self.parse_gedcom5x_record(sub_record)
                 else:
                     if record.tag in self.missing_handler_count:
                         self.missing_handler_count[record.tag] += 1
                     else:
                         self.missing_handler_count[record.tag] = 1
-                    
                     log.error(f'Failed Parsing Record: {record.describe()}')
+                    return
+                if record.tag != 'FAM':
+                    for sub_record in record.subRecords():
+                        log.debug(sub_record.describe())
+                        self.parse_gedcom5x_record(sub_record)
                 log.debug(f"{record.tag} with id: {record.xref} has {len(record.subRecords())} subRecords")
                 
         else:
@@ -436,12 +446,12 @@ class GedcomConverter():
 
     def handle_cont(self, record: Gedcom5xRecord):
         if isinstance(self.object_map[record.level-1], Note):
-            gxobject = str("\n" + record.value if record.value else '')
+            gxobject = str(" " + record.value if record.value else '')
             self.object_map[record.level-1].append(gxobject)
         elif isinstance(self.object_map[record.level-1], Agent):
-            gxobject = str("\n" + record.value if record.value else '')
+            gxobject = str(" " + record.value if record.value else '')
         elif isinstance(self.object_map[record.level-1], Qualifier):
-            gxobject = str("\n" + record.value if record.value else '')
+            gxobject = str(" " + record.value if record.value else '')
             self.object_map[record.level-1].append(gxobject)
         elif isinstance(self.object_map[record.level-1], TextValue):
             #gxobject = TextValue(value="\n" + record.value)
@@ -471,6 +481,12 @@ class GedcomConverter():
         else:
             raise ValueError(f"Could not handle '{record.tag}' tag in record {record.describe()}, last stack object {self.object_map[record.level-1]}")
     
+    def handle__crea(self, record: Gedcom5xRecord):
+        if isinstance(self.object_map[record.level-1], SourceDescription):
+            if  record.value is not None:
+                self.object_map[record.level-1].created = Date(original=record.value)
+            else: raise ValueError('DATE had not value')   
+
     def handle_ctry(self, record: Gedcom5xRecord):
         if isinstance(self.object_map[record.level-1], Address):
             if record.value is not None:
@@ -526,6 +542,13 @@ class GedcomConverter():
         else:
             raise TagConversionError(record=record,levelstack=self.object_map)
 
+    def handle_pevent(self, record: Gedcom5xRecord):
+        if record.tag in self.gedcom_even_to_fact.keys():
+            if isinstance(self.object_map[record.level-1], Person):
+                gxobject = Fact(type=self.gedcom_even_to_fact[record.tag])
+                self.object_map[record.level-1].add_fact(gxobject)
+                self.object_map[record.level] = gxobject
+
     def handle_even(self, record: Gedcom5xRecord):
         # TODO If events in a @S, check if only 1 person matches?
         if record.value and (not record.value.strip() == ''):
@@ -733,8 +756,9 @@ class GedcomConverter():
             
             self.object_map[record.level] = gxobject
         elif isinstance(self.object_map[record.level-1], Agent):
-            
+            print(record.describe())
             gxobject = TextValue(value=record.value)
+            print(gxobject)
             self.object_map[record.level-1].add_name(gxobject)
             
         else:
@@ -808,7 +832,7 @@ class GedcomConverter():
     def handle_page(self, record: Gedcom5xRecord):
         if isinstance(self.object_map[record.level-1], SourceReference):
             #self.object_map[record.level-1].descriptionId = record.value
-            gx_object = KnownSourceReference(name=KnownSourceReference.Page,value=record.value)
+            gx_object = Qualifier(name=KnownSourceReference.Page,value=record.value)
             self.object_map[record.level-1].add_qualifier(gx_object)
             self.object_map[record.level] = self.object_map[record.level-1]
         else:
@@ -854,15 +878,19 @@ class GedcomConverter():
     
     def handle_publ(self, record: Gedcom5xRecord):
         if isinstance(self.object_map[record.level-1], SourceDescription):
-            if record.value and self.gedcomx.agents.byName(record.value):
-                gxobject = self.gedcomx.agents.byName(record.value)[0]
+            if record.value == None:
+                #check for date
+                if (date := record['DATE']) is not None:
+                    self.object_map[record.level-1].published = date
+                    print("found date")
             else:
-                gxobject = Agent(names=[TextValue(record.value)])
-                self.gedcomx.add_agent(gxobject)
-            self.object_map[record.level-1].publisher = gxobject
-
-            
-            self.object_map[record.level] = gxobject
+                if record.value and self.gedcomx.agents.byName(record.value):
+                    gxobject = self.gedcomx.agents.byName(record.value)[0]
+                else:
+                    gxobject = Agent(names=[TextValue(record.value)])
+                    self.gedcomx.add_agent(gxobject)
+                self.object_map[record.level-1].publisher = gxobject
+                self.object_map[record.level] = gxobject
         else:
             raise TagConversionError(record=record,levelstack=self.object_map)
 
@@ -900,8 +928,10 @@ class GedcomConverter():
     def handle_repo(self, record: Gedcom5xRecord):
 
         if record.level == 0:
-            if (gxobject := self.gedcomx.agents.byId(id=record.xref)) is None:
-                gxobject = Agent(id=record.xref)
+            if record.value is not None and self.gedcomx.agents.byName(record.value):
+                gxobject = self.gedcomx.agents.byName(record.value)[0]
+            else:
+                gxobject = Agent(id=record.xref,names = [TextValue(record.value)] if record.value else [])
                 self.gedcomx.add_agent(gxobject)
             
             self.object_map[record.level] = gxobject
@@ -1128,6 +1158,34 @@ class GedcomConverter():
                     line.append(cell.ljust(cell_width))
             print("".join(line).rstrip())
 
+    def has_duplicates(self,seq) -> bool:
+        """Fast True/False check (works for hashable items)."""
+        return len(seq) != len(set(seq))
+
+    def find_duplicates(self, seq):
+        """Return duplicate items once each, in the order they first repeat."""
+        seen, dups = set(), []
+        for x in seq:
+            if x in seen and x not in dups:
+                dups.append(x)
+            seen.add(x)
+        return dups
+      
+    def unique(self, seq: Iterable[T], key: Optional[Callable[[T], K]] = None) -> List[T]:
+        """
+        Return a list with duplicates removed, keeping the first occurrence.
+        If `key` is provided, it’s used to compute a hashable identity for each item.
+        """
+        
+        seen: set[K] = set()
+        out: List[T] = []
+        for item in seq:
+            k = item if key is None else key(item)
+            if k not in seen:
+                seen.add(k)
+                out.append(item)
+        return out
+
     def Gedcom5x_GedcomX(self, gedcom5x: Gedcom5x):
         print(f'Parsing GEDCOM Version {gedcom5x.version}')
         individual_ids = set()
@@ -1173,7 +1231,14 @@ class GedcomConverter():
                     self.parse_gedcom5x_record(repo)
                 for family in gedcom5x.families:
                     self.parse_gedcom5x_record(family)
-        
+
+                #clean up notes, and TextValue descriptions:
+                for sd in self.gedcomx.sourceDescriptions:
+                    log.debug(f"Removing dupliate notes in SourceDescriptions")
+                    sd.notes = self.unique(sd.notes,key=lambda n: n._key())
+                    log.debug(f"Removing dupliate descriptions in SourceDescriptions")
+                    sd.descriptions = self.unique(sd.descriptions,key=lambda n: n._key())
+
         self.print_counts_table(self.missing_handler_count)
         
         return self.gedcomx

gedcomx/coverage.py

@@ -9,6 +9,7 @@ from typing import Optional
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json_ refactor 
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -21,6 +22,7 @@ GEDCOM Module Types
 from .date import Date
 from .place_reference import PlaceReference
 from .logging_hub import hub, logging
+from .schemas import schema_class
 """
 ======================================================================
 Logging
@@ -30,7 +32,7 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
-
+@schema_class()
 class Coverage:
     identifier = 'http://gedcomx.org/v1/Coverage'
     version = 'http://gedcomx.org/conceptual-model/v1'

gedcomx/date.py

@@ -11,6 +11,7 @@ from dateutil import parser
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json refactored
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -21,6 +22,7 @@ GEDCOM Module Types
 ======================================================================
 """
 from .logging_hub import hub, logging
+from .schemas import schema_class
 """
 ======================================================================
 Logging
@@ -38,6 +40,7 @@ class DateFormat:
 class DateNormalization():
     pass        
 
+@schema_class()
 class Date:
     identifier = 'http://gedcomx.org/v1/Date'
     version = 'http://gedcomx.org/conceptual-model/v1'

gedcomx/document.py

@@ -10,6 +10,7 @@ from typing import Any, Dict, List, Optional
  Created: 2025-08-25
  Updated:
    - 2025-09-03: _from_json_ refactored 
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -23,6 +24,7 @@ from .attribution import Attribution
 from .conclusion import Conclusion, ConfidenceLevel
 from .note import Note
 from .resource import Resource
+from .schemas import schema_class
 from .source_reference import SourceReference
 from .logging_hub import hub, logging
 """
@@ -34,7 +36,7 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
-
+@schema_class(toplevel=True)
 class DocumentType(Enum):
     Abstract = "http://gedcomx.org/Abstract"
     Transcription = "http://gedcomx.org/Transcription"

gedcomx/event.py

@@ -13,6 +13,7 @@ from typing import Any, Dict, List, Optional
    - 2025-08-31: fixed mutible [] in init, replaced List[Identifer] with IdentifierList
    - 2025-09-03: _from_json_ refactor
    - 2025-09-04: changed _as_dict_ to std dict creation and removed call to serailization
+   - 2025-09-09: added schema_class
    
 ======================================================================
 """
@@ -30,6 +31,7 @@ from .identifier import IdentifierList
 from .note import Note
 from .place_reference import PlaceReference
 from .resource import Resource
+from .schemas import schema_class
 from .source_reference import SourceReference
 from .subject import Subject
 from .logging_hub import hub, logging
@@ -272,6 +274,7 @@ class EventType(Enum):
 
         return None  # Default to UNKNOWN if no match is found
 
+@schema_class(toplevel=True)
 class Event(Subject):
     identifier = 'http://gedcomx.org/v1/Event'
     version = 'http://gedcomx.org/conceptual-model/v1'

gedcomx/evidence_reference.py

@@ -1,7 +1,29 @@
-from typing import Optional
+from typing import Optional, TYPE_CHECKING
+"""
+======================================================================
+ Project: Gedcom-X
+ File:    evidence_reference.py
+ Author:  David J. Cartwright
+ Purpose: 
+
+ Created: 2025-08-25
+ Updated:
+    - 2025-09-09: added schema_class
+   
+   
+======================================================================
+"""
 
+"""
+======================================================================
+GEDCOM Module Type Imports
+======================================================================
+"""
 from .attribution import Attribution
 from .resource import Resource
+from .schemas import schema_class
+if TYPE_CHECKING:
+    from .subject import Subject
 from .logging_hub import hub, logging
 """
 ======================================================================
@@ -12,9 +34,14 @@ log = logging.getLogger("gedcomx")
 serial_log = "gedcomx.serialization"
 #=====================================================================
 
+@schema_class()
 class EvidenceReference:
     identifier = 'http://gedcomx.org/v1/EvidenceReference'
     version = 'http://gedcomx.org/conceptual-model/v1'
 
-    def __init__(self, resource: Resource, attribution: Optional[Attribution]) -> None:
-        pass
+    def __init__(self, resource: "Resource | Subject", attribution: Optional[Attribution]) -> None:
+        self.resource = resource
+        self.attribution: Attribution = attribution
+    
+    def _validate(self):
+        raise NotImplemented