gedcom-x 0.5.6__py3-none-any.whl → 0.5.7__py3-none-any.whl

gedcomx/SourceDescription.py

@@ -1,24 +1,44 @@
-import base64
-import uuid
 import warnings
 
 from enum import Enum
 from typing import List, Optional, Dict, Any
 
+from typing import Optional, TYPE_CHECKING
+if TYPE_CHECKING:
+    from .Document import Document
+
+"""
+======================================================================
+ Project: Gedcom-X
+ File:    SourceDescription.py
+ Author:  David J. Cartwright
+ Purpose: 
+
+ Created: 2025-07-25
+ Updated:
+   - 2025-08-31: _as_dict_ refactored to ignore empty fields, changed id creation to make_uid()
+ 
+   
+======================================================================
+"""
+
+"""
+======================================================================
+GEDCOM Module Types
+======================================================================
+"""
 from .Agent import Agent
 from .Attribution import Attribution
 from .Coverage import Coverage
 from .Date import Date
-from .Identifier import Identifier, IdentifierList
+from .Identifier import Identifier, IdentifierList, make_uid
 from .Note import Note
+from .Resource import Resource
 from .SourceCitation import SourceCitation
 from .SourceReference import SourceReference
 from .TextValue import TextValue
-from .Resource import Resource, get_resource_as_dict
-from .Serialization import Serialization
 from .URI import URI
-
-from collections.abc import Sized
+#=====================================================================
 
 class ResourceType(Enum):
     Collection = "http://gedcomx.org/Collection"
@@ -38,41 +58,66 @@ class ResourceType(Enum):
         return descriptions.get(self, "No description available.")
     
 class SourceDescription:
-    """
-    The SourceDescription data type defines a description of a source of genealogical information.
-    http://gedcomx.org/v1/SourceDescription
-
-    Parameters
-    ----------
-    id : str
-        Unique identifier for this SourceDescription.
-    attribution : Attribution Object
-        Attribution information for the Genealogy
-    filepath : str
-        Not Implimented.
-    description : str
-        Description of the Genealogy: ex. 'My Family Tree'
-
-    Raises
-    ------
-    ValueError
-        If `id` is not a valid UUID.
-    """
-    identifier = "http://gedcomx.org/v1/SourceDescription"
-    """
-    Gedcom-X Specification Identifier
+    """Description of a genealogical information source.
+
+    See: http://gedcomx.org/v1/SourceDescription
+
+    Args:
+        id (str | None): Unique identifier for this `SourceDescription`.
+        resourceType (ResourceType | None): Type/category of the resource being
+            described (e.g., digital artifact, physical artifact).
+        citations (list[SourceCitation] | None): Citations that reference or
+            justify this source description.
+        mediaType (str | None): IANA media (MIME) type of the resource
+            (e.g., ``"application/pdf"``).
+        about (URI | None): Canonical URI that the description is about.
+        mediator (Resource | None): The mediator resource (if any) involved in
+            providing access to the source.
+        publisher (Resource | Agent | None): Publisher of the resource.
+        authors (list[Resource] | None): Authors/creators of the resource.
+        sources (list[SourceReference] | None): Other sources this description
+            derives from or references.
+        analysis (Resource | None): Analysis document associated with the
+            resource (often a `Document`; kept generic to avoid circular imports).
+        componentOf (SourceReference | None): Reference to a parent/containing
+            source (this is a component/child of that source).
+        titles (list[TextValue] | None): One or more titles for the resource.
+        notes (list[Note] | None): Human-authored notes about the resource.
+        attribution (Attribution | None): Attribution metadata for who supplied
+            or curated this description.
+        rights (list[Resource] | None): Rights statements or licenses.
+        coverage (list[Coverage] | None): Spatial/temporal coverage of the
+            source’s content.
+        descriptions (list[TextValue] | None): Short textual summaries or
+            descriptions.
+        identifiers (IdentifierList | None): Alternative identifiers for the
+            resource (DOI, ARK, call numbers, etc.).
+        created (Date | None): Creation date of the resource.
+        modified (Date | None): Last modified date of the resource.
+        published (Date | None): Publication/release date of the resource.
+        repository (Agent | None): Repository or agency that holds the resource.
+        max_note_count (int): Maximum number of notes to retain/emit. Defaults to 20.
+
+    Raises:
+        ValueError: If `id` is not a valid UUID.
+
+    Attributes:
+        identifier (str): Gedcom-X specification identifier for this type.
     """
 
+    identifier = "http://gedcomx.org/v1/SourceDescription"
+    version = 'http://gedcomx.org/conceptual-model/v1'
+    
     def __init__(self, id: Optional[str] = None,
                  resourceType: Optional[ResourceType] = None,
                  citations: Optional[List[SourceCitation]] = [],
                  mediaType: Optional[str] = None,
                  about: Optional[URI] = None,
-                 mediator: Optional[Resource] = None,
-                 publisher: Optional[Resource|Agent] = None,
+                 mediator: Optional[Agent|Resource] = None,
+                 publisher: Optional[Agent|Resource] = None,
                  authors: Optional[List[Resource]] = None,
                  sources: Optional[List[SourceReference]] = None, # SourceReference
-                 analysis: Optional[Resource] = None,  # analysis should be of type 'Document', not specified to avoid circular import
+                 analysis: Optional["Document|Resource"] = None,  #TODO add type checker so its a document
                  componentOf: Optional[SourceReference] = None, # SourceReference
                  titles: Optional[List[TextValue]] = None,
                  notes: Optional[List[Note]] = None,
@@ -87,7 +132,7 @@ class SourceDescription:
                  repository: Optional[Agent] = None,
                  max_note_count: int = 20):
         
-        self.id = id if id else SourceDescription.default_id_generator()
+        self.id = id if id else make_uid()
         self.resourceType = resourceType
         self.citations = citations or []
         self.mediaType = mediaType
@@ -111,7 +156,7 @@ class SourceDescription:
         self.repository = repository
         self.max_note_count = max_note_count
 
-        self.uri = URI(fragment=id)
+        self.uri = URI(fragment=id) if id else None #TODO Should i take care of this in the collections?
     
     @property
     def publisher(self) -> Resource | Agent | None:
@@ -150,8 +195,7 @@ class SourceDescription:
                     return False
             self.notes.append(note_to_add)
     
-    def add_source(self, source_to_add: object):
-        #from .SourceReference import SourceReference
+    def add_source(self, source_to_add: SourceReference):
         if source_to_add and isinstance(object,SourceReference):
             for current_source in self.sources:
                 if current_source == source_to_add:
@@ -167,44 +211,59 @@ class SourceDescription:
             self.titles.append(title_to_add)
         else:
             raise ValueError(f"Cannot add title of type {type(title_to_add)}")
-        
-    @staticmethod
-    def default_id_generator():
-        # Generate a standard UUID
-        standard_uuid = uuid.uuid4()
-        # Convert UUID to bytes
-        uuid_bytes = standard_uuid.bytes
-        # Encode bytes to a Base64 string
-        short_uuid = base64.urlsafe_b64encode(uuid_bytes).rstrip(b'=').decode('utf-8')
-        return 'SD-' + str(short_uuid)
-    
+            
     @property
     def _as_dict_(self) -> Dict[str, Any]:
-        type_as_dict = {
-            'id': self.id,
-            'about': self.about._as_dict_ if self.about else None,
-            'resourceType': self.resourceType.value if self.resourceType else None,
-            'citations': [c._as_dict_ for c in self.citations] or None,
-            'mediaType': self.mediaType,
-            'mediator': self.mediator._as_dict_ if self.mediator else None,
-            'publisher': self.publisher._as_dict_ if self.publisher else None,
-            'authors': self.authors and [a._as_dict_ for a in self.authors] or None,
-            'sources': [s._as_dict_ for s in self.sources] or None,
-            'analysis': self.analysis._as_dict_ if self.analysis else None,
-            'componentOf': self.componentOf._as_dict_ if self.componentOf else None,
-            'titles': [t._as_dict_ for t in self.titles] or None,
-            'notes': [n._as_dict_ for n in self.notes] or None,
-            'attribution': self.attribution._as_dict_ if self.attribution else None,
-            'rights': [r._as_dict_ for r in self.rights] or None,
-            'coverage': [c._as_dict_ for c in self.coverage] or None,
-            'descriptions': [d._as_dict_ for d in self.descriptions] or None,
-            'identifiers': self.identifiers._as_dict_ if self.identifiers else None,
-            'created': self.created if self.created else None,
-            'modified': self.modified if self.modified else None,
-            'published': self.published if self.published else None,
-            'repository': self.repository._as_dict_ if self.repository else None,
-            'uri': self.uri.value
-        }
+        from .Serialization import Serialization
+        type_as_dict = {}
+
+        if self.id:
+            type_as_dict['id'] = self.id
+        if self.about:
+            type_as_dict['about'] = self.about._as_dict_
+        if self.resourceType:
+            type_as_dict['resourceType'] = getattr(self.resourceType, 'value', self.resourceType)
+        if self.citations:
+            type_as_dict['citations'] = [c._as_dict_ for c in self.citations if c]
+        if self.mediaType:
+            type_as_dict['mediaType'] = self.mediaType
+        if self.mediator:
+            type_as_dict['mediator'] = self.mediator._as_dict_
+        if self.publisher:
+            type_as_dict['publisher'] = self.publisher._as_dict_ #TODO Resource this
+        if self.authors:
+            type_as_dict['authors'] = [a._as_dict_ for a in self.authors if a]
+        if self.sources:
+            type_as_dict['sources'] = [s._as_dict_ for s in self.sources if s]
+        if self.analysis:
+            type_as_dict['analysis'] = self.analysis._as_dict_
+        if self.componentOf:
+            type_as_dict['componentOf'] = self.componentOf._as_dict_ 
+        if self.titles:
+            type_as_dict['titles'] = [t._as_dict_ for t in self.titles if t]
+        if self.notes:
+            type_as_dict['notes'] = [n._as_dict_ for n in self.notes if n]
+        if self.attribution:
+            type_as_dict['attribution'] = self.attribution._as_dict_
+        if self.rights:
+            type_as_dict['rights'] = [r._as_dict_ for r in self.rights if r]
+        if self.coverage:
+            type_as_dict['coverage'] = [c._as_dict_ for c in self.coverage if c]
+        if self.descriptions:
+            type_as_dict['descriptions'] = [d for d in self.descriptions if d]
+        if self.identifiers:
+            type_as_dict['identifiers'] = self.identifiers._as_dict_
+        if self.created is not None:
+            type_as_dict['created'] = self.created
+        if self.modified is not None:
+            type_as_dict['modified'] = self.modified
+        if self.published is not None:
+            type_as_dict['published'] = self.published
+        if self.repository:
+            type_as_dict['repository'] = self.repository._as_dict_ #TODO Resource this
+        if self.uri and self.uri.value:
+            type_as_dict['uri'] = self.uri.value
+
         
         return Serialization.serialize_dict(type_as_dict)
          
@@ -222,7 +281,7 @@ class SourceDescription:
         about        = URI._from_json_(data['about']) if data.get('about') else None
         mediator     = Resource._from_json_(data['mediator']) if data.get('mediator') else None
         publisher    = Resource._from_json_(data['publisher']) if data.get('publisher') else None
-        authors      = [Resource._from_json_(a) for a in data.get('authors', [])]
+        authors      = [Resource._from_json_(a) for a in data.get('authors', [])] if data.get('authors') else None
         sources      = [SourceReference._from_json_(s) for s in data.get('sources', [])]
         analysis     = Resource._from_json_(data['analysis']) if data.get('analysis') else None
         component_of = SourceReference._from_json_(data['componentOf']) if data.get('componentOf') else None

gedcomx/SourceReference.py

@@ -1,10 +1,14 @@
-from typing import List, Optional
+from __future__ import annotations
+from typing import List, Optional, TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from .SourceDescription import SourceDescription
 
 from .Attribution import Attribution
 from .Qualifier import Qualifier
 
 from .Resource import Resource
-from .Serialization import Serialization
+
 from .URI import URI
 
 from collections.abc import Sized
@@ -48,7 +52,7 @@ class SourceReference:
     version = 'http://gedcomx.org/conceptual-model/v1'
     
     def __init__(self,
-                 description: URI | object | None = None,
+                 description: URI | SourceDescription | None = None,
                  descriptionId: Optional[str] = None,
                  attribution: Optional[Attribution] = None,
                  qualifiers: Optional[List[Qualifier]] = None
@@ -81,18 +85,15 @@ class SourceReference:
     
     @property    
     def _as_dict_(self):
-        # Only add Relationship-specific fields
+        from .Serialization import Serialization
         type_as_dict = {
             'description':self.description._as_dict_ if self.description else None,
             'descriptionId': self.descriptionId.replace("\n"," ").replace("\r"," ") if self.descriptionId else None,
             'attribution': self.attribution._as_dict_ if self.attribution else None,
-            'qualifiers':[qualifier.value for qualifier in self.qualifiers ] if self.qualifiers else None
+            'qualifiers':[qualifier.__as_dict__ for qualifier in self.qualifiers] if (self.qualifiers and len(self.qualifiers) > 0) else None
             }
         return Serialization.serialize_dict(type_as_dict)
-
-        
-        
-
+      
     @classmethod
     def _from_json_(cls, data: dict):         
         """

gedcomx/Subject.py

@@ -6,7 +6,7 @@ from .Conclusion import Conclusion, ConfidenceLevel
 from .EvidenceReference import EvidenceReference
 from .Identifier import Identifier, IdentifierList
 from .Note import Note
-from .Serialization import Serialization
+
 from .SourceReference import SourceReference
 from .Resource import Resource
 from .Extensions.rs10.rsLink import _rsLinkList
@@ -45,31 +45,15 @@ class Subject(Conclusion):
    
     @property
     def _as_dict_(self):
-        def _serialize(value):
-            if isinstance(value, (str, int, float, bool, type(None))):
-                return value
-            elif isinstance(value, dict):
-                return {k: _serialize(v) for k, v in value.items()}
-            elif isinstance(value, (list, tuple, set)):
-                return [_serialize(v) for v in value]
-            elif hasattr(value, "_as_dict_"):
-                return value._as_dict_
-            else:
-                return str(value)  # fallback for unknown objects
+        from .Serialization import Serialization
 
-        subject_fields = super()._as_dict_  # Start with base class fields
+        type_as_dict = super()._as_dict_  # Start with base class fields
         # Only add Relationship-specific fields
-        subject_fields.update({
+        type_as_dict.update({
             "extracted": self.extracted,
             "evidence": [evidence_ref for evidence_ref in self.evidence] if self.evidence else None,
             "media": [media for media in self.media] if self.media else None,
             "identifiers": self.identifiers._as_dict_ if self.identifiers else None
                            
         })
-
-        # Serialize and exclude None values
-        for key, value in subject_fields.items():
-            if value is not None:
-                subject_fields[key] = _serialize(value)
-
-        return subject_fields
+        return Serialization.serialize_dict(type_as_dict)