pysodafair 0.1.62__py3-none-any.whl

pysoda/core/metadata/performances.py

@@ -0,0 +1,46 @@
+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 os.path import join, getsize
+from openpyxl import load_workbook
+import shutil
+from ...utils import validate_schema
+from .helpers import upload_metadata_file, get_template_path
+
+def create_excel(soda, upload_boolean, local_destination):
+    source = get_template_path(SDS_FILE_PERFORMANCES)
+
+    destination = join(METADATA_UPLOAD_PS_PATH, SDS_FILE_PERFORMANCES) if upload_boolean else local_destination
+
+    shutil.copyfile(source, destination)
+
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+
+    performances = soda["dataset_metadata"]["performances"]
+
+    validate_schema(performances, SCHEMA_NAME_PERFORMANCES)
+
+    # get the ascii column headers
+    row = 2
+    ascii_headers = excel_columns(start_index=0)
+    for performance in performances: 
+        ws1[ascii_headers[0] + str(row)] = performance.get("performance_id", "")
+        ws1[ascii_headers[1] + str(row)] = performance.get("protocol_url_or_doi", "")
+        ws1[ascii_headers[2] + str(row)] = performance.get("date", "")
+        ws1[ascii_headers[3] + str(row)] = performance.get("start_datetime", "")
+        ws1[ascii_headers[4] + str(row)] = performance.get("end_datetime", "")
+        participants = " ".join(performance.get("participants", []))
+        ws1[ascii_headers[5] + str(row)] = participants
+        ws1[ascii_headers[6] + str(row)] = performance.get("additional_metadata", "")
+        row += 1
+
+    wb.save(destination)
+
+    size = getsize(destination)
+
+    ## if generating directly on Pennsieve, call upload function
+    if upload_boolean:
+        upload_metadata_file(SDS_FILE_PERFORMANCES, soda,  destination, True)
+
+    return {"size": size}

pysoda/core/metadata/resources.py

@@ -0,0 +1,53 @@
+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 os.path import join, getsize
+from openpyxl import load_workbook
+import shutil
+from ...utils import validate_schema
+from .helpers import upload_metadata_file, get_template_path
+
+def create_excel(soda, upload_boolean, local_destination):
+    source = get_template_path(SDS_FILE_RESOURCES)
+
+    destination = join(METADATA_UPLOAD_PS_PATH, SDS_FILE_RESOURCES) if upload_boolean else local_destination
+
+    shutil.copyfile(source, destination)
+
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+
+    resources = soda["dataset_metadata"]["resources"]
+
+    validate_schema(resources, SCHEMA_NAME_RESOURCES)
+
+
+    # get the ascii column headers
+    row = 2
+    ascii_headers = excel_columns(start_index=0)
+    for resource in resources: 
+        ws1[ascii_headers[0] + str(row)] = resource.get("rrid", "")
+        ws1[ascii_headers[1] + str(row)] = resource.get("type", "")
+        ws1[ascii_headers[2] + str(row)] = resource.get("name", "")
+        ws1[ascii_headers[3] + str(row)] = resource.get("url", "")
+        ws1[ascii_headers[4] + str(row)] = resource.get("vendor", "")
+        ws1[ascii_headers[5] + str(row)] = resource.get("version", "")
+        ws1[ascii_headers[6] + str(row)] = resource.get("id_in_protocol", "")
+        ws1[ascii_headers[7] + str(row)] = resource.get("additional_metadata", "")
+
+        row += 1
+
+    wb.save(destination)
+
+
+    size = getsize(destination)
+
+
+    ## if generating directly on Pennsieve, call upload function
+    if upload_boolean:
+        upload_metadata_file(SDS_FILE_RESOURCES, soda,  destination, True)
+
+    return {"size": size}
+
+
+

pysoda/core/metadata/samples.py

@@ -0,0 +1,184 @@
+from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_SAMPLES, SCHEMA_NAME_SAMPLES
+from .excel_utils import excel_columns
+from openpyxl.styles import PatternFill, Font
+from os.path import join, getsize
+from openpyxl import load_workbook
+import shutil
+from ...utils import validate_schema, get_sds_headers
+from .helpers import upload_metadata_file, get_template_path
+
+
+def create_excel(soda, upload_boolean, local_destination):
+    source = get_template_path(SDS_FILE_SAMPLES)
+
+    samples = soda["dataset_metadata"]["samples"]
+
+    validate_schema(samples, SCHEMA_NAME_SAMPLES)
+
+    destination = join(METADATA_UPLOAD_PS_PATH, SDS_FILE_SAMPLES) if upload_boolean else local_destination
+    shutil.copyfile(source, destination)
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+
+    orangeFill = PatternFill(
+        start_color="FFD965", end_color="FFD965", fill_type="solid"
+    )
+
+    row = 2
+    ascii_headers = excel_columns(start_index=0)
+    custom_headers_to_column = {}
+    sds_headers = get_sds_headers(SCHEMA_NAME_SAMPLES)
+
+    # Populate the Excel file with the data
+    for sample in samples:
+        ws1[ascii_headers[0] + str(row)] = sample.get("sample_id", "")
+        ws1[ascii_headers[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[1] + str(row)] = sample.get("subject_id", "")
+        ws1[ascii_headers[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[2] + str(row)] = sample.get("was_derived_from", "")
+        ws1[ascii_headers[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[3] + str(row)] = sample.get("pool_id", "")
+        ws1[ascii_headers[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[4] + str(row)] = sample.get("sample_experimental_group", "")
+        ws1[ascii_headers[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[7] + str(row)] = sample.get("also_in_dataset", "")
+        ws1[ascii_headers[7] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[8] + str(row)] = sample.get("member_of", "")
+        ws1[ascii_headers[8] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        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)].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)].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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[13] + str(row)] = sample.get("reference_atlas", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[15] + str(row)] = sample.get("laterality", "")
+        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)].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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[18] + str(row)] = sample.get("protocol_title", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        # Handle custom fields
+        for field_name, field in sample.items():
+            if field_name in sds_headers:
+                continue
+
+            # Check if the field is already in the custom_headers_to_column dictionary
+            if field_name not in custom_headers_to_column:
+                custom_headers_to_column[field_name] = len(custom_headers_to_column.keys()) + 1
+
+                # 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")
+
+            # 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")
+
+        row += 1
+
+    wb.save(destination)
+
+    size = getsize(destination)
+
+    # If generating directly on Pennsieve, call upload function
+    if upload_boolean:
+        upload_metadata_file(SDS_FILE_SAMPLES, soda, destination, True)
+
+    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}")

pysoda/core/metadata/sites.py

@@ -0,0 +1,51 @@
+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 os.path import join, getsize
+from openpyxl import load_workbook
+import shutil
+from ...utils import validate_schema
+from .helpers import upload_metadata_file, get_template_path
+
+def create_excel(soda, upload_boolean, local_destination):
+    source = get_template_path(SDS_FILE_SITES)
+
+    destination = join(METADATA_UPLOAD_PS_PATH, SDS_FILE_SITES) if upload_boolean else local_destination
+
+    shutil.copyfile(source, destination)
+
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+
+    sites = soda["dataset_metadata"]["sites"]
+
+    validate_schema(sites, SCHEMA_NAME_SITES)
+
+
+    # get the ascii column headers
+    row = 2
+    ascii_headers = excel_columns(start_index=0)
+    for performance in sites: 
+        ws1[ascii_headers[0] + str(row)] = performance.get("site_id", "")
+        ws1[ascii_headers[1] + str(row)] = performance.get("specimen_id", "")
+        ws1[ascii_headers[2] + str(row)] = performance.get("site_type", "")
+        ws1[ascii_headers[3] + str(row)] = performance.get("laboratory_internal_id", "")
+        ws1[ascii_headers[4] + str(row)] = performance.get("coordinate_system", "")
+        ws1[ascii_headers[5] + str(row)] = performance.get("coordinate_system_position", "")
+        ws1[ascii_headers[6] + str(row)] = performance.get("more...", "")
+        row += 1
+
+    wb.save(destination)
+
+    size = getsize(destination)
+
+
+    ## if generating directly on Pennsieve, call upload function
+    if upload_boolean:
+        upload_metadata_file(SDS_FILE_SITES, soda,  destination, True)
+
+    return {"size": size}
+    
+
+
+

pysoda/core/metadata/subjects.py

@@ -0,0 +1,172 @@
+from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH, SDS_FILE_SUBJECTS,SCHEMA_NAME_SUBJECTS
+from .excel_utils import rename_headers, excel_columns
+from openpyxl.styles import PatternFill
+from os.path import join, getsize
+from openpyxl import load_workbook
+import shutil
+import numpy as np
+from ...utils import validate_schema, get_sds_headers
+from openpyxl.styles import Font
+from .helpers import transposeMatrix, getMetadataCustomFields, sortedSubjectsTableData, upload_metadata_file, get_template_path
+
+
+def create_excel(soda, upload_boolean, local_destination):
+    source = get_template_path(SDS_FILE_SUBJECTS)
+
+
+    subjects = soda["dataset_metadata"]["subjects"]
+
+    validate_schema(subjects, SCHEMA_NAME_SUBJECTS)
+
+    destination = join(METADATA_UPLOAD_PS_PATH, SDS_FILE_SUBJECTS) if upload_boolean else local_destination
+    shutil.copyfile(source, destination)
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+
+
+
+    # 1. see if the length of datastructure[0] == length of datastructure. If yes, go ahead. If no, add new columns from headers[n-1] onward.
+    orangeFill = PatternFill(
+        start_color="FFD965", end_color="FFD965", fill_type="solid"
+    )
+
+
+    # 1.1 (optional) add custom fields to the headers of the workbook
+    
+    # for column, header in zip(
+    #     excel_columns(start_index=29), subjects[0].keys()
+    # ):
+    #     cell = column + str(1)
+    #     ws1[cell] = header
+    #     ws1[cell].fill = orangeFill
+    #     ws1[cell].font = Font(bold=True, size=12, name="Calibri")
+
+    row = 2
+    ascii_headers = excel_columns(start_index=0)
+    custom_headers_to_column = {}
+    sds_headers = get_sds_headers(SCHEMA_NAME_SUBJECTS)
+
+    # 2. populate excel file with the data 
+    for subject in subjects:
+        ws1[ascii_headers[0] + str(row)] = subject.get("subject_id", "")
+        ws1[ascii_headers[0] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[1] + str(row)] = subject.get("pool_id", "")
+        ws1[ascii_headers[1] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[2] + str(row)] = subject.get("subject_experimental_group", "")
+        ws1[ascii_headers[2] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[3] + str(row)] = subject.get("age", "")
+        ws1[ascii_headers[3] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[4] + str(row)] = subject.get("sex", "")
+        ws1[ascii_headers[4] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[5] + str(row)] = subject.get("species", "")
+        ws1[ascii_headers[5] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[6] + str(row)] = subject.get("strain", "")
+        ws1[ascii_headers[6] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[7] + str(row)] = subject.get("rrid_for_strain", "")
+        ws1[ascii_headers[7] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[8] + str(row)] = subject.get("age_category", "")
+        ws1[ascii_headers[8] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[9] + str(row)] = subject.get("also_in_dataset", "")
+        ws1[ascii_headers[9] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[10] + str(row)] = subject.get("member_of", "")
+        ws1[ascii_headers[10] + str(row)].font = Font(bold=False, size=11, name="Arial")
+
+        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)].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)].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)].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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[16] + str(row)] = subject.get("body_mass", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[18] + str(row)] = subject.get("phenotype", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[20] + str(row)] = subject.get("reference_atlas", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[22] + str(row)] = subject.get("experiment_date", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[24] + str(row)] = subject.get("intervention", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        ws1[ascii_headers[26] + str(row)] = subject.get("protocol_title", "")
+        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)].font = Font(bold=False, size=11, name="Arial")
+
+        # handle custom fields
+        for field_name, field in subject.items():
+            if field_name in sds_headers:
+                continue
+
+            # check if the field is already in the custom_headers_to_column dictionary
+            if field_name not in custom_headers_to_column:
+                print(field_name)
+
+
+                custom_headers_to_column[field_name] = len(custom_headers_to_column.keys()) + 1
+
+                # 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")
+
+
+
+            # 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")
+
+
+        row += 1
+
+    wb.save(destination)
+
+    size = getsize(destination)
+
+    ## if generating directly on Pennsieve, then call upload function and then delete the destination path
+    if upload_boolean:
+        upload_metadata_file(SDS_FILE_SUBJECTS, soda, destination, True)
+
+    return {size: size}

pysoda/core/metadata/submission.py

@@ -0,0 +1,91 @@
+from os.path import join, getsize
+from openpyxl import load_workbook
+from openpyxl.styles import Font
+import shutil
+import tempfile
+from .helpers import upload_metadata_file, get_template_path
+
+
+from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH
+from .excel_utils import rename_headers, excel_columns
+from ...utils import validate_schema
+
+
+### Create submission file
+def create_excel(soda, upload_boolean, local_destination):
+    """
+    Create an Excel file for submission metadata.
+
+    Args:
+        soda (dict): The soda object containing dataset metadata.
+        upload_boolean (bool): Whether to upload the file to Pennsieve.
+        destination_path (str): The path to save the Excel file.
+
+    Returns:
+        dict: A dictionary containing the size of the metadata file.
+    """
+
+    validate_schema(soda["dataset_metadata"]["submission"], "submission_schema.json")
+
+    font_submission = Font(name="Calibri", size=14, bold=False)
+
+    source = get_template_path("submission.xlsx")
+
+    destination = join(METADATA_UPLOAD_PS_PATH, "submission.xlsx") if upload_boolean else local_destination
+
+    try:
+        shutil.copyfile(source, destination)
+    except FileNotFoundError as e:
+        raise e
+    
+    #TODO: Do not use an array for the non-array values; zipping for the sake of the ascii value is not necessary until milestone_achieved
+    submission_metadata_list = [
+        soda["dataset_metadata"]["submission"]
+    ]
+
+    # write to excel file
+    wb = load_workbook(destination)
+    ws1 = wb["Sheet1"]
+    start_index = 2
+    for column, submission_data in zip(excel_columns(start_index), submission_metadata_list):
+        ws1[column + "2"] = submission_data["consortium_data_standard"]
+        ws1[column + "3"] = submission_data["funding_consortium"]
+        ws1[column + "4"] = submission_data["award_number"]
+        for col, milestone in zip(excel_columns(start_index), submission_data["milestone_achieved"]):
+            ws1[col + str(5)] = milestone
+        ws1[column + "6"] = submission_data["milestone_completion_date"]
+        ws1[column + "2"].font = font_submission
+        ws1[column + "3"].font = font_submission
+        ws1[column + "4"].font = font_submission
+        ws1[column + "5"].font = font_submission
+        ws1[column + "6"].font = font_submission
+
+    # TODO: should milestone completion date also be an array?
+    rename_headers(ws1, len(submission_metadata_list[0]["milestone_achieved"]), 2)
+
+    wb.save(destination)
+
+    print("Excel file created successfully at:", destination)
+
+    wb.close()
+
+    # calculate the size of the metadata file
+    size = getsize(destination)
+
+    
+
+    ## if generating directly on Pennsieve, then call upload function and then delete the destination path
+    if upload_boolean:
+        print("Uploading Excel file to Pennsieve...")
+        upload_metadata_file("submission.xlsx", soda, destination, True)
+        print("Excel file uploaded successfully to Pennsieve.")
+    return {"size": size}
+
+
+
+
+
+
+
+
+

pysoda/core/metadata/text_metadata.py

@@ -0,0 +1,47 @@
+from .constants import METADATA_UPLOAD_PS_PATH, TEMPLATE_PATH
+from os.path import join, getsize
+from .helpers import upload_metadata_file, get_template_path
+import shutil
+
+
+# this function saves and uploads the README/CHANGES to Pennsieve, just when users choose to generate onto Pennsieve
+## (not used for generating locally)
+def create_text_file(soda, upload_boolean, local_destination, metadata_filename):
+    """
+    Create a text file for README, LICENSE, or CHANGES metadata using a template.
+
+    Args:
+        soda (dict): The soda object containing dataset metadata.
+        upload_boolean (bool): Whether to upload the file to Pennsieve.
+        local_destination (str): The path to save the text file.
+        metadata_filename (str): The name of the metadata file to be created (e.g., "README.md", "LICENSE", "CHANGES").
+
+    Returns:
+        int: The size of the metadata file in bytes.
+    """
+
+    # Use metadata_filename directly for template and output filename
+    source = get_template_path(metadata_filename)
+    destination = join(METADATA_UPLOAD_PS_PATH, metadata_filename) if upload_boolean else local_destination
+
+    # Copy the template to the destination (if it exists)
+    try:
+        shutil.copyfile(source, destination)
+    except FileNotFoundError:
+        # If template not found, just create a new file
+        with open(destination, "w", encoding="utf-8") as f:
+            pass
+
+    # Write the actual content from soda into the file (overwriting template content)
+    # Use metadata_filename as the key for content
+    text = soda["dataset_metadata"].get(metadata_filename, "")
+    with open(destination, "w", encoding="utf-8") as file:
+        file.write(text)
+
+    size = getsize(destination)
+    if upload_boolean:
+        upload_metadata_file(metadata_filename, soda, destination, True)
+
+    return size
+
+

pysoda/core/metadata_templates/CHANGES

@@ -0,0 +1 @@
+Optional text file that contains information about the history of the dataset

pysoda/core/metadata_templates/LICENSE

@@ -0,0 +1 @@
+Optional text file that contains information about the history of the dataset

pysoda/core/metadata_templates/README.md

@@ -0,0 +1,4 @@
+# My dataset readme (change this line)
+
+A require markdown file that provides an introduction to and
+background for the dataset.