pysodafair 0.1.66__py3-none-any.whl → 0.1.68__py3-none-any.whl

pysoda/core/dataset_generation/upload.py

@@ -1,4 +1,5 @@
 
+from pysoda.utils.exceptions import PennsieveAgentRPCError
 from ...utils import (
     generate_options_set, generating_locally, generating_on_ps, 
     uploading_with_ps_account, uploading_to_existing_ps_dataset, 
@@ -2148,8 +2149,6 @@ def ps_upload_to_dataset(soda, ps, ds, resume=False):
                     my_bf_existing_files_name_with_extension,
                 ) = ps_get_existing_files_details(my_tracking_folder)
 
-                logger.info(f"Existing files in Pennsieve: {my_bf_existing_files_name_with_extension}")
-
                 list_local_files = []
                 list_projected_names = []
                 list_desired_names = []
@@ -2466,7 +2465,7 @@ def ps_upload_to_dataset(soda, ps, ds, resume=False):
                     relative_path,
                 )
 
-                logger.info(f"List of files to upload: {list_upload_files}")
+                logger.info(f"Amount of files to upload: {len(list_upload_files)} ")
 
 
                 # return and mark upload as completed if nothing is added to the manifest
@@ -3032,6 +3031,7 @@ def ps_upload_to_dataset(soda, ps, ds, resume=False):
         end = timer()
         logger.info(f"Time for ps_upload_to_dataset function: {timedelta(seconds=end - start)}")
     except Exception as e:
+        logger.error(f"An error occurred in ps_upload_to_dataset function: {str(e)}")
         # reset the total bytes uploaded for any file that has not been fully uploaded
         ums.set_main_total_generate_dataset_size(main_total_generate_dataset_size)
         ums.set_total_files_to_upload(total_files)
@@ -3056,6 +3056,7 @@ renaming_files_flow = False
 elapsed_time = None
 manifest_id = None 
 origin_manifest_id = None
+curation_error_message = ""
 
 
 
@@ -3460,10 +3461,7 @@ def validate_dataset_structure(soda, resume):
             connect_pennsieve_client(accountname)
         except Exception as e:
             main_curate_status = "Done"
-            if isinstance(e, AttributeError):
-                raise Exception("The Pennsieve Agent cannot access datasets but needs to in order to work. Please try again. If the issue persists, please contact the SODA team. The SODA team will contact Pennsieve to help resolve this issue.")
-            else:
-                raise PennsieveAccountInvalid("Please select a valid Pennsieve account.")
+            raise e
 
     if uploading_to_existing_ps_dataset(soda):
         # check that the Pennsieve dataset is valid
@@ -3560,6 +3558,7 @@ def reset_upload_session_environment(resume):
     global generated_dataset_id
     global bytes_file_path_dict
     global renaming_files_flow
+    global curation_error_message
 
     start_generate = 0
     myds = ""
@@ -3574,6 +3573,7 @@ def reset_upload_session_environment(resume):
     main_curation_uploaded_files = 0
     uploaded_folder_counter = 0
     generated_dataset_id = None
+    curation_error_message = ""
 
     main_curate_status = "Curating"
     main_curate_progress_message = "Starting dataset curation"
@@ -3602,6 +3602,7 @@ def main_curate_function(soda, resume):
     global manifest_id 
     global origin_manifest_id
     global total_files
+    global curation_error_message
 
     logger.info("Starting generating selected dataset")
     logger.info(f"Generating dataset metadata generate-options={soda['generate-dataset']}")
@@ -3627,7 +3628,9 @@ def main_curate_function(soda, resume):
             ps = connect_pennsieve_client(accountname)
             generate_dataset(soda, resume, ps)
     except Exception as e:
+        logger.error(f"An error occurred in main_curate_function function: {str(e)}")
         main_curate_status = "Done"
+        curation_error_message = str(e)
         raise e
 
     main_curate_status = "Done"
@@ -3665,6 +3668,7 @@ def main_curate_function_progress():
     global renaming_files_flow
     global ums 
     global elapsed_time
+    global curation_error_message
 
 
     prior_elapsed_time = ums.get_elapsed_time()
@@ -3691,6 +3695,7 @@ def main_curate_function_progress():
         "total_files_uploaded": main_curation_uploaded_files,
         "generated_dataset_id": myds["content"]["id"] if myds != "" else None, # when a new dataset gets generated log its id to our analytics
         "generated_dataset_int_id": myds["content"]["intId"] if myds != "" else None,
+        "curation_error_message": curation_error_message,
     }
 
 

pysoda/core/metadata/code_description.py

@@ -1,6 +1,6 @@
 from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_CODE_DESCRIPTION, SCHEMA_NAME_CODE_DESCRIPTION
 from .excel_utils import rename_headers, excel_columns
-from openpyxl.styles import PatternFill
+from openpyxl.styles import PatternFill, Font
 from os.path import join, getsize
 from openpyxl import load_workbook
 import shutil
@@ -53,27 +53,47 @@ def populate_input_output_information(ws1, soda):
 
     excel_ascii = excel_columns(start_index=3)[0]
     ws1[excel_ascii + str(row)] = input_output_information["number_of_inputs"]
+    ws1[excel_ascii + str(row)].font = Font(bold=False, size=11, name="Arial")
 
     for input, column in zip(input_output_information["inputs"], excel_columns(start_index=3)):
         row = 28
         ws1[column + str(row)] = input["input_parameter_name"]
+        ws1[column + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 1)] = input["input parameter type"]
+        ws1[column + str(row + 1)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 2)] = input["input_parameter_description"]
+        ws1[column + str(row + 2)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 3)] = input["input_units"]
+        ws1[column + str(row + 3)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 4)] = input["input_default_value"]
+        ws1[column + str(row + 4)].font = Font(bold=False, size=11, name="Arial")
 
     # populate number of outputs into row 34
     row = 34
     ws1[excel_ascii + str(row)] = input_output_information["number_of_outputs"]
+    ws1[excel_ascii + str(row)].font = Font(bold=False, size=11, name="Arial")
 
     # populate the outputs from row 35 - 39
     for output, column in zip(input_output_information["outputs"], excel_columns(start_index=3)):
         row = 35
         ws1[column + str(row)] = output["output_parameter_name"]
+        ws1[column + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 1)] = output["output_parameter_type"]
+        ws1[column + str(row + 1)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 2)] = output["output_parameter_description"]
+        ws1[column + str(row + 2)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 3)] = output["output_units"]
+        ws1[column + str(row + 3)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 4)] = output["output_default_value"]
+        ws1[column + str(row + 4)].font = Font(bold=False, size=11, name="Arial")
 
 
 def populate_basic_information(ws1, soda):
@@ -83,9 +103,16 @@ def populate_basic_information(ws1, soda):
     row = 2
     for info, column in zip(basic_information, excel_columns(start_index=3)):
         ws1[column + str(row)] = info["RRID_term"]
+        ws1[column + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 1)] = info["RRID_identifier"]
+        ws1[column + str(row + 1)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 2)] = info["ontology_term"]
+        ws1[column + str(row + 2)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[column + str(row + 3)] = info["ontology_identifier"]
+        ws1[column + str(row + 3)].font = Font(bold=False, size=11, name="Arial")
 
 
 def populate_ten_simple_rules(ws1, soda):
@@ -94,10 +121,19 @@ def populate_ten_simple_rules(ws1, soda):
     ascii_cols = excel_columns(start_index=3)
     for _, rule in ten_simple_rules.items():
         ws1[ascii_cols[0] + str(row)] = rule.get("Link", "")
+        ws1[ascii_cols[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_cols[1] + str(row)] = rule.get("Rating", "")
+        ws1[ascii_cols[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_cols[2] + str(row)] = rule.get("Target", "")
+        ws1[ascii_cols[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_cols[3] + str(row)] = rule.get("Target Justification", "")
+        ws1[ascii_cols[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_cols[4] + str(row)] = rule.get("Text", "")
+        ws1[ascii_cols[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
         row += 1
 
 

pysoda/core/metadata/dataset_description.py

@@ -146,7 +146,9 @@ def populate_contributor_info(workbook, soda):
         workbook[column + "28"] = contributor.get("contributor_name", "")
         workbook[column + "29"] = contributor.get("contributor_orcid_id", "")
         workbook[column + "30"] = contributor.get("contributor_affiliation", "")
-        workbook[column + "31"] = contributor.get("contributor_role", "")
+        roles = contributor.get("contributor_roles", [])
+        roles_str = ", ".join(roles) if roles else ""
+        workbook[column + "31"] = roles_str
     # Return the length of the contributor array, or 1 if empty
     return max(1, len(contributor_info))
 

pysoda/core/metadata/performances.py

@@ -1,6 +1,6 @@
 from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_PERFORMANCES, SCHEMA_NAME_PERFORMANCES
 from .excel_utils import rename_headers, excel_columns
-from openpyxl.styles import PatternFill
+from openpyxl.styles import PatternFill, Font
 from os.path import join, getsize
 from openpyxl import load_workbook
 import shutil
@@ -26,13 +26,26 @@ def create_excel(soda, upload_boolean, local_destination):
     ascii_headers = excel_columns(start_index=0)
     for performance in performances: 
         ws1[ascii_headers[0] + str(row)] = performance.get("performance_id", "")
+        ws1[ascii_headers[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[1] + str(row)] = performance.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[2] + str(row)] = performance.get("date", "")
+        ws1[ascii_headers[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[3] + str(row)] = performance.get("start_datetime", "")
+        ws1[ascii_headers[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[4] + str(row)] = performance.get("end_datetime", "")
+        ws1[ascii_headers[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         participants = " ".join(performance.get("participants", []))
         ws1[ascii_headers[5] + str(row)] = participants
+        ws1[ascii_headers[5] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[6] + str(row)] = performance.get("additional_metadata", "")
+        ws1[ascii_headers[6] + str(row)].font = Font(bold=False, size=11, name="Arial")
         row += 1
 
     wb.save(destination)

pysoda/core/metadata/resources.py

@@ -1,6 +1,6 @@
 from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_RESOURCES, SCHEMA_NAME_RESOURCES
 from .excel_utils import rename_headers, excel_columns
-from openpyxl.styles import PatternFill
+from openpyxl.styles import PatternFill, Font
 from os.path import join, getsize
 from openpyxl import load_workbook
 import shutil
@@ -27,13 +27,28 @@ def create_excel(soda, upload_boolean, local_destination):
     ascii_headers = excel_columns(start_index=0)
     for resource in resources: 
         ws1[ascii_headers[0] + str(row)] = resource.get("rrid", "")
+        ws1[ascii_headers[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[1] + str(row)] = resource.get("type", "")
+        ws1[ascii_headers[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[2] + str(row)] = resource.get("name", "")
+        ws1[ascii_headers[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[3] + str(row)] = resource.get("url", "")
+        ws1[ascii_headers[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[4] + str(row)] = resource.get("vendor", "")
+        ws1[ascii_headers[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[5] + str(row)] = resource.get("version", "")
+        ws1[ascii_headers[5] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[6] + str(row)] = resource.get("id_in_protocol", "")
+        ws1[ascii_headers[6] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[7] + str(row)] = resource.get("additional_metadata", "")
+        ws1[ascii_headers[7] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
         row += 1
 

pysoda/core/metadata/samples.py

@@ -49,7 +49,7 @@ def create_excel(soda, upload_boolean, local_destination):
         ws1[ascii_headers[5] + str(row)] = sample.get("sample_type", "")
         ws1[ascii_headers[5] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[6] + str(row)] = sample.get("sample_anatomical_location", "")
+        ws1[ascii_headers[6] + str(row)] = handle_anatomical_location_field(sample)
         ws1[ascii_headers[6] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
         ws1[ascii_headers[7] + str(row)] = sample.get("also_in_dataset", "")
@@ -61,36 +61,39 @@ def create_excel(soda, upload_boolean, local_destination):
         ws1[ascii_headers[9] + str(row)] = sample.get("metadata_only", "")
         ws1[ascii_headers[9] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[10] + str(row)] = sample.get("laboratory_internal_id", "")
+        ws1[ascii_headers[10] + str(row)] = sample.get("number_of_directly_derived_samples", "")
         ws1[ascii_headers[10] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[11] + str(row)] = sample.get("date_of_derivation", "")
+        ws1[ascii_headers[11] + str(row)] = sample.get("laboratory_internal_id", "")
         ws1[ascii_headers[11] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[12] + str(row)] = sample.get("experimental_log_file_path", "")
+        ws1[ascii_headers[12] + str(row)] = sample.get("date_of_derivation", "")
         ws1[ascii_headers[12] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[13] + str(row)] = sample.get("reference_atlas", "")
+        ws1[ascii_headers[13] + str(row)] = sample.get("experimental_log_file_path", "")
         ws1[ascii_headers[13] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[14] + str(row)] = sample.get("pathology", "")
+        ws1[ascii_headers[14] + str(row)] = sample.get("reference_atlas", "")
         ws1[ascii_headers[14] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[15] + str(row)] = sample.get("laterality", "")
+        ws1[ascii_headers[15] + str(row)] = sample.get("pathology", "")
         ws1[ascii_headers[15] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[16] + str(row)] = sample.get("cell_type", "")
+        ws1[ascii_headers[16] + str(row)] = sample.get("laterality", "")
         ws1[ascii_headers[16] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[17] + str(row)] = sample.get("plane_of_section", "")
+        ws1[ascii_headers[17] + str(row)] = sample.get("cell_type", "")
         ws1[ascii_headers[17] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[18] + str(row)] = sample.get("protocol_title", "")
+        ws1[ascii_headers[18] + str(row)] = sample.get("plane_of_section", "")
         ws1[ascii_headers[18] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[19] + str(row)] = sample.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[19] + str(row)] = sample.get("protocol_title", "")
         ws1[ascii_headers[19] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
+        ws1[ascii_headers[20] + str(row)] = sample.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[20] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
         # Handle custom fields
         for field_name, field in sample.items():
             if field_name in sds_headers:
@@ -102,14 +105,14 @@ def create_excel(soda, upload_boolean, local_destination):
 
                 # Create the column header in the Excel file
                 offset_from_final_sds_header = custom_headers_to_column[field_name]
-                ws1[ascii_headers[19 + offset_from_final_sds_header] + "1"] = field_name
-                ws1[ascii_headers[19 + offset_from_final_sds_header] + "1"].fill = orangeFill
-                ws1[ascii_headers[19 + offset_from_final_sds_header] + "1"].font = Font(bold=True, size=12, name="Calibri")
+                ws1[ascii_headers[20 + offset_from_final_sds_header] + "1"] = field_name
+                ws1[ascii_headers[20 + offset_from_final_sds_header] + "1"].fill = orangeFill
+                ws1[ascii_headers[20 + offset_from_final_sds_header] + "1"].font = Font(bold=True, size=12, name="Calibri")
 
             # Add the field value to the corresponding cell in the Excel file
             offset_from_final_sds_header = custom_headers_to_column[field_name]
-            ws1[ascii_headers[19 + offset_from_final_sds_header] + str(row)] = field
-            ws1[ascii_headers[19 + offset_from_final_sds_header] + str(row)].font = Font(bold=False, size=11, name="Arial")
+            ws1[ascii_headers[20 + offset_from_final_sds_header] + str(row)] = field
+            ws1[ascii_headers[20 + offset_from_final_sds_header] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
         row += 1
 
@@ -124,61 +127,9 @@ def create_excel(soda, upload_boolean, local_destination):
     return size
 
 
-# soda = {
-#     "dataset_metadata": {
-#         "samples": [
-#             {
-#                 "sample_id": "sample_1",
-#                 "subject_id": "subject_1",
-#                 "was_derived_from": "derived_from_1",
-#                 "pool_id": "pool_1",
-#                 "sample_experimental_group": "experimental_group_1",
-#                 "sample_type": "type_1",
-#                 "sample_anatomical_location": "location_1",
-#                 "also_in_dataset": "dataset_1",
-#                 "member_of": "member_1",
-#                 "metadata_only": "False",
-#                 "laboratory_internal_id": "internal_id_1",
-#                 "date_of_derivation": "2023-01-01",
-#                 "experimental_log_file_path": "/path/to/log/file",
-#                 "reference_atlas": "/path/to/atlas",
-#                 "pathology": "pathology_1",
-#                 "laterality": "left",
-#                 "cell_type": "cell_type_1",
-#                 "plane_of_section": "plane_1",
-#                 "protocol_title": "protocol_title_1",
-#                 "protocol_url_or_doi": "/path/to/protocol",
-#                 "custom_field_1": "custom_value_1",
-#             },
-#             {
-#                 "sample_id": "sample_2",
-#                 "subject_id": "subject_2",
-#                 "was_derived_from": "derived_from_2",
-#                 "pool_id": "pool_2",
-#                 "sample_experimental_group": "experimental_group_2",
-#                 "sample_type": "type_2",
-#                 "sample_anatomical_location": "location_2",
-#                 "also_in_dataset": "dataset_2",
-#                 "member_of": "member_2",
-#                 "metadata_only": "True",
-#                 "laboratory_internal_id": "internal_id_2",
-#                 "date_of_derivation": "2023-02-01",
-#                 "experimental_log_file_path": "/path/to/log/file2",
-#                 "reference_atlas": "/path/to/atlas2",
-#                 "pathology": "pathology_2",
-#                 "laterality": "right",
-#                 "cell_type": "cell_type_2",
-#                 "plane_of_section": "plane_2",
-#                 "protocol_title": "protocol_title_2",
-#                 "protocol_url_or_doi": "/path/to/protocol2",
-#                 "custom_field_1": "custom_value_12",
-
-#             }
-#         ]
-#     }
-# }
-
-# try:
-#     create_excel(soda, False, "samples.xlsx")
-# except Exception as e:
-#     print(f"An error occurred: {e}")
+
+def handle_anatomical_location_field(sample):
+    anatomical_location = sample.get("sample_anatomical_location", "")
+    if isinstance(anatomical_location, list):
+        return " ".join(anatomical_location)
+    return anatomical_location

pysoda/core/metadata/sites.py

@@ -1,6 +1,6 @@
 from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_SITES, SCHEMA_NAME_SITES
 from .excel_utils import rename_headers, excel_columns
-from openpyxl.styles import PatternFill
+from openpyxl.styles import PatternFill, Font
 from os.path import join, getsize
 from openpyxl import load_workbook
 import shutil
@@ -27,12 +27,25 @@ def create_excel(soda, upload_boolean, local_destination):
     ascii_headers = excel_columns(start_index=0)
     for performance in sites: 
         ws1[ascii_headers[0] + str(row)] = performance.get("site_id", "")
+        ws1[ascii_headers[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[1] + str(row)] = performance.get("specimen_id", "")
+        ws1[ascii_headers[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[2] + str(row)] = performance.get("site_type", "")
+        ws1[ascii_headers[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[3] + str(row)] = performance.get("laboratory_internal_id", "")
+        ws1[ascii_headers[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[4] + str(row)] = performance.get("coordinate_system", "")
+        ws1[ascii_headers[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[5] + str(row)] = performance.get("coordinate_system_position", "")
+        ws1[ascii_headers[5] + str(row)].font = Font(bold=False, size=11, name="Arial")
+        
         ws1[ascii_headers[6] + str(row)] = performance.get("more...", "")
+        ws1[ascii_headers[6] + str(row)].font = Font(bold=False, size=11, name="Arial")
         row += 1
 
     wb.save(destination)

pysoda/core/metadata/subjects.py

@@ -84,54 +84,57 @@ def create_excel(soda, upload_boolean, local_destination):
         ws1[ascii_headers[11] + str(row)] = subject.get("metadata_only", "")
         ws1[ascii_headers[11] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[12] + str(row)] = subject.get("laboratory_internal_id", "")
+        ws1[ascii_headers[12] + str(row)] = subject.get("number_of_directly_derived_samples", "")
         ws1[ascii_headers[12] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[13] + str(row)] = subject.get("date_of_birth", "")
+        ws1[ascii_headers[13] + str(row)] = subject.get("laboratory_internal_id", "")
         ws1[ascii_headers[13] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[14] + str(row)] = subject.get("age_range_min", "")
+        ws1[ascii_headers[14] + str(row)] = subject.get("date_of_birth", "")
         ws1[ascii_headers[14] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[15] + str(row)] = subject.get("age_range_max", "")
+        ws1[ascii_headers[15] + str(row)] = subject.get("age_range_min", "")
         ws1[ascii_headers[15] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[16] + str(row)] = subject.get("body_mass", "")
+        ws1[ascii_headers[16] + str(row)] = subject.get("age_range_max", "")
         ws1[ascii_headers[16] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[17] + str(row)] = subject.get("genotype", "")
+        ws1[ascii_headers[17] + str(row)] = normalize_body_mass(subject.get("body_mass", ""))
         ws1[ascii_headers[17] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[18] + str(row)] = subject.get("phenotype", "")
+        ws1[ascii_headers[18] + str(row)] = subject.get("genotype", "")
         ws1[ascii_headers[18] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[19] + str(row)] = subject.get("handedness", "")
+        ws1[ascii_headers[19] + str(row)] = subject.get("phenotype", "")
         ws1[ascii_headers[19] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[20] + str(row)] = subject.get("reference_atlas", "")
+        ws1[ascii_headers[20] + str(row)] = subject.get("handedness", "")
         ws1[ascii_headers[20] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[21] + str(row)] = subject.get("experimental_log_file_path", "")
+        ws1[ascii_headers[21] + str(row)] = subject.get("reference_atlas", "")
         ws1[ascii_headers[21] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[22] + str(row)] = subject.get("experiment_date", "")
+        ws1[ascii_headers[22] + str(row)] = subject.get("experimental_log_file_path", "")
         ws1[ascii_headers[22] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[23] + str(row)] = subject.get("disease_or_disorder", "")
+        ws1[ascii_headers[23] + str(row)] = subject.get("experiment_date", "")
         ws1[ascii_headers[23] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[24] + str(row)] = subject.get("intervention", "")
+        ws1[ascii_headers[24] + str(row)] = subject.get("disease", "")
         ws1[ascii_headers[24] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[25] + str(row)] = subject.get("disease_model", "")
+        ws1[ascii_headers[25] + str(row)] = subject.get("intervention", "")
         ws1[ascii_headers[25] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[26] + str(row)] = subject.get("protocol_title", "")
+        ws1[ascii_headers[26] + str(row)] = subject.get("disease_model", "")
         ws1[ascii_headers[26] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
-        ws1[ascii_headers[27] + str(row)] = subject.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[27] + str(row)] = subject.get("protocol_title", "")
         ws1[ascii_headers[27] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
+        ws1[ascii_headers[28] + str(row)] = subject.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[28] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
         # handle custom fields
         for field_name, field in subject.items():
             if field_name in sds_headers:
@@ -146,17 +149,17 @@ def create_excel(soda, upload_boolean, local_destination):
 
                 # create the column header in the excel file
                 offset_from_final_sds_header = custom_headers_to_column[field_name]
-                ws1[ascii_headers[27 + offset_from_final_sds_header] + "1"] = field_name
-                ws1[ascii_headers[27 + offset_from_final_sds_header] + "1"].fill = orangeFill
-                ws1[ascii_headers[27 + offset_from_final_sds_header] + "1"].font = Font(bold=True, size=12, name="Calibri")
+                ws1[ascii_headers[28 + offset_from_final_sds_header] + "1"] = field_name
+                ws1[ascii_headers[28 + offset_from_final_sds_header] + "1"].fill = orangeFill
+                ws1[ascii_headers[28 + offset_from_final_sds_header] + "1"].font = Font(bold=True, size=12, name="Calibri")
 
 
 
             # add the field value to the corresponding cell in the excel file
             offset_from_final_sds_header = custom_headers_to_column[field_name]
 
-            ws1[ascii_headers[27 + offset_from_final_sds_header] + str(row)] = field
-            ws1[ascii_headers[27 + offset_from_final_sds_header] + str(row)].font = Font(bold=False, size=11, name="Arial")
+            ws1[ascii_headers[28 + offset_from_final_sds_header] + str(row)] = field
+            ws1[ascii_headers[28 + offset_from_final_sds_header] + str(row)].font = Font(bold=False, size=11, name="Arial")
 
 
         row += 1
@@ -169,4 +172,30 @@ def create_excel(soda, upload_boolean, local_destination):
     if upload_boolean:
         upload_metadata_file(SDS_FILE_SUBJECTS, soda, destination, True)
 
-    return {size: size}
+    return {size: size}
+
+
+
+def normalize_body_mass(body_mass_value):
+    """
+    Ensures that a body_mass value is normalized to a string for Excel export.
+    Handles cases where 'body_mass' is a string, number, or an object with 'value' and 'unit'.
+    """
+    # If already a string or empty, leave as is
+    if isinstance(body_mass_value, str):
+        return body_mass_value
+    # If a number, convert to string
+    if isinstance(body_mass_value, (int, float)):
+        return str(body_mass_value)
+    # If an object with value and unit
+    if isinstance(body_mass_value, dict):
+            value = body_mass_value.get("value")
+            unit = body_mass_value.get("unit")
+            if value is not None and unit:
+                return f"{value} {unit}"
+            elif value is not None:
+                return str(value)
+            else:
+                return ""
+    else:
+        return ""

pysoda/core/metadata_templates/.dss

@@ -0,0 +1 @@
+(sds 3.0.1)