Fix: Empty entity name/special name fixes in powerbi

ingestion/src/metadata/ingestion/models/custom_basemodel_validation.py

@@ -22,6 +22,9 @@
 RESERVED_COLON_KEYWORD = "__reserved__colon__"
 RESERVED_ARROW_KEYWORD = "__reserved__arrow__"
 RESERVED_QUOTE_KEYWORD = "__reserved__quote__"
+RESERVED_NEWLINE_KEYWORD = "__reserved__newline__"
+RESERVED_CARRIAGE_RETURN_KEYWORD = "__reserved__carriage_return__"
+RESERVED_TAB_KEYWORD = "__reserved__tab__"
 
 
 class TransformDirection(Enum):
@@ -115,6 +118,9 @@
         value.replace(RESERVED_COLON_KEYWORD, "::")
         .replace(RESERVED_ARROW_KEYWORD, ">")
         .replace(RESERVED_QUOTE_KEYWORD, '"')
+        .replace(RESERVED_NEWLINE_KEYWORD, "\n")
+        .replace(RESERVED_CARRIAGE_RETURN_KEYWORD, "\r")
+        .replace(RESERVED_TAB_KEYWORD, "\t")
     )
 
 
@@ -123,6 +129,9 @@
         value.replace("::", RESERVED_COLON_KEYWORD)
         .replace(">", RESERVED_ARROW_KEYWORD)
         .replace('"', RESERVED_QUOTE_KEYWORD)
+        .replace("\n", RESERVED_NEWLINE_KEYWORD)
+        .replace("\r", RESERVED_CARRIAGE_RETURN_KEYWORD)
+        .replace("\t", RESERVED_TAB_KEYWORD)
     )
 
 
@@ -174,7 +183,7 @@
                 if hasattr(constraint, "columns"):
                     constraint.columns = [transformer(col) for col in constraint.columns]
 
     if transformer == replace_separators and type(name) == str:  # noqa: E721
         obj.name = transformer(name)
 
 

ingestion/src/metadata/ingestion/source/dashboard/powerbi/client.py

@@ -339,7 +339,7 @@
             logger.warning(f"Error converting regex '{regex}' to OData condition: {exc}")
             return ""
 
     def create_filter_query(self, filter_pattern) -> Optional[str]:  # noqa: UP045
         """
         Create a complete filter query for workspaces from filter_pattern
         """
@@ -379,7 +379,7 @@
             return None
 
     # pylint: disable=too-many-branches,too-many-statements
     def fetch_all_workspaces(self, filter_pattern: Optional[FilterPattern] = None) -> Optional[List[Group]]:  # noqa: C901, UP006, UP045
         """Method to fetch all powerbi workspace details
         Returns:
             Group
@@ -542,19 +542,41 @@
         return None
 
     def fetch_workspace_scan_result(self, scan_id: str) -> Optional[Workspaces]:  # noqa: UP045
-        """Get Workspace scan result by id method
-        Args:
-            scan_id:
-        Returns:
-            Workspaces
+        """Get Workspace scan result by id method.
+
+        Parse each workspace individually so a single malformed workspace
+        (or any nested entity that still fails validation) does not invalidate
+        the whole scan-result response and drop the entire chunk of workspaces.
         """
         try:
             logger.debug(
                 f"Calling the API({str(self.client._base_url)}/myorg/admin/workspaces/scanResult/{scan_id})"  # pylint: disable=protected-access  # noqa: RUF010
                 " to get workspace scan result"
             )
             response_data = self.client.get(f"/myorg/admin/workspaces/scanResult/{scan_id}")
-            return Workspaces(**response_data)
+            if not response_data:
+                return None
+            parsed_workspaces: List[Group] = []  # noqa: UP006
+            for raw_ws in response_data.get("workspaces", []) or []:  # pyright: ignore[reportAttributeAccessIssue]
+                if isinstance(raw_ws, dict) and raw_ws.get("id") is not None:
+                    try:
+                        parsed_workspaces.append(Group(**raw_ws))
+                    except Exception as ws_exc:  # pylint: disable=broad-except
+                        logger.debug(traceback.format_exc())
+                        logger.warning(
+                            "Skipping workspace [id=%s] in scan [%s] due to parse error: %s",
+                            raw_ws.get("id"),
+                            scan_id,
+                            ws_exc,
+                        )
+                else:
+                    workspace_entry_type = type(raw_ws).__name__
+                    logger.warning(
+                        "Skipping a workspace in scan [%s] due to missing 'id' field or invalid format. Entry type: %s",
+                        scan_id,
+                        workspace_entry_type,
+                    )
+            return Workspaces(workspaces=parsed_workspaces)
         except Exception as exc:  # pylint: disable=broad-except
             logger.debug(traceback.format_exc())
             logger.warning(f"Error fetching workspace scan result: {exc}")
@@ -616,4 +638,4 @@
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     api_client: PowerBiApiClient
     file_client: Optional[PowerBiFileClient]  # noqa: UP045