kodexa 7.4.413466578435__tar.gz → 7.4.413508355193__tar.gz

{kodexa-7.4.413466578435 → kodexa-7.4.413508355193}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kodexa
-Version: 7.4.413466578435
+Version: 7.4.413508355193
 Summary: Python SDK for the Kodexa Platform
 Author: Austin Redenbaugh
 Author-email: austin@kodexa.com

{kodexa-7.4.413466578435 → kodexa-7.4.413508355193}/kodexa/model/model.py

@@ -1244,6 +1244,7 @@ class ContentNode(object):
             status=None,
             owner_uri=None,
             is_dirty=None,
+            sort_by_bbox: bool=False,
     ):
         """
         This will tag (see Feature Tagging) the expression groups identified by the regular expression.
@@ -1305,7 +1306,7 @@ class ContentNode(object):
             return str(uuid.uuid4())
 
         def tag_node_position(
-                node_to_check, start, end, node_data, tag_uuid, offset=0, value=None
+                node_to_check, start, end, node_data, tag_uuid, offset=0, value=None, sort_by_bbox: bool=False
         ):
             """
             This function tags a node position in a given data structure. It iterates over the content parts of the node to check,
@@ -1420,6 +1421,7 @@ class ContentNode(object):
                         tag_uuid,
                         offset=offset,
                         value=value,
+                        sort_by_bbox=sort_by_bbox,
                     )
 
                     if result < 0 or (end - result) <= 0:
@@ -1434,7 +1436,16 @@ class ContentNode(object):
                     raise Exception("Invalid part?")
 
             # We need to determine if we have missing children and add them to the end
-            for child_idx, child_node in enumerate(node_to_check.get_children()):
+            node_children = node_to_check.get_children()
+            if node_children and sort_by_bbox:
+                # Sort nodes by x-coordinate if they have bboxes, otherwise use index
+                try:
+                    node_children.sort(key=lambda x: x.get_bbox()[0] if hasattr(x, 'get_bbox') else x.index if hasattr(x, 'index') else 0)
+                except (AttributeError, TypeError, IndexError):
+                    # If sorting fails, keep original order
+                    pass
+            
+            for child_idx, child_node in enumerate(node_children):
                 if child_node.index not in node_to_check.get_content_parts():
                     if content_length > 0:
                         end = end - len(separator)
@@ -1452,6 +1463,7 @@ class ContentNode(object):
                         tag_uuid,
                         offset=offset,
                         value=value,
+                        sort_by_bbox=sort_by_bbox,
                     )
 
                     if result < 0 or (end - result) <= 0:
@@ -1487,6 +1499,7 @@ class ContentNode(object):
                     get_tag_uuid(tag_uuid),
                     0,
                     value=value,
+                    sort_by_bbox=sort_by_bbox,
                 )
 
             else:
@@ -1558,6 +1571,7 @@ class ContentNode(object):
                                             data,
                                             get_tag_uuid(tag_uuid),
                                             value=value,
+                                            sort_by_bbox=sort_by_bbox,
                                         )
 
                         else:
@@ -1572,6 +1586,7 @@ class ContentNode(object):
                                     data,
                                     get_tag_uuid(tag_uuid),
                                     value=value,
+                                    sort_by_bbox=sort_by_bbox,
                                 )
 
     def get_tags(self):

{kodexa-7.4.413466578435 → kodexa-7.4.413508355193}/kodexa/model/objects.py

@@ -3108,6 +3108,10 @@ class Task(BaseModel):
         protected_namespaces=("model_config",),
     )
 
+    id: Optional[str] = Field(None)
+    uuid: Optional[str] = None
+    created_on: Optional[StandardDateTime] = Field(None, alias="createdOn")
+    updated_on: Optional[StandardDateTime] = Field(None, alias="updatedOn")
     project: Optional['Project'] = None
     title: Optional[str] = None
     description: Optional[str] = None

{kodexa-7.4.413466578435 → kodexa-7.4.413508355193}/kodexa/platform/client.py

@@ -4634,14 +4634,18 @@ class DocumentFamilyEndpoint(DocumentFamily, ClientEndpoint):
 
     def get_json(
             self,
-            project_id: str,
+            project_id: Optional[str] = None,
             friendly_names=False,
+            include_ids=True,
+            include_exceptions=False,          
     ) -> str:
         """Get the JSON export for the document family
 
         Args:
             project_id str: The project ID
             friendly_names (bool): Whether to use friendly names. Defaults to False
+            include_ids (bool): Whether to include the IDs. Defaults to True
+            include_exceptions (bool): Whether to include the exceptions. Defaults to False
 
         Returns:
             str: The JSON
@@ -4656,6 +4660,8 @@ class DocumentFamilyEndpoint(DocumentFamily, ClientEndpoint):
             "format": "json",
             "friendlyNames": friendly_names,
             "projectId": project_id,
+            "includeIds": include_ids,
+            "includeExceptions": include_exceptions,
         }
 
         response = self.client.get(url, params=params)

{kodexa-7.4.413466578435 → kodexa-7.4.413508355193}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "kodexa"
-version = "7.4.413466578435"
+version = "7.4.413508355193"
 description = "Python SDK for the Kodexa Platform"
 authors = ["Austin Redenbaugh <austin@kodexa.com>", "Philip Dodds <philip@kodexa.com>", "Romar Cablao <rcablao@kodexa.com>", "Amadea Paula Dodds <amadeapaula@kodexa.com>"]
 readme = "README.md"