pysodafair 0.1.62__py3-none-any.whl → 0.1.64__py3-none-any.whl

pysoda/core/dataset_generation/upload.py

@@ -3830,57 +3830,39 @@ def generate_manifest_file_locally(generate_purpose, soda):
 
 
 def generate_manifest_file_data(dataset_structure):
-    # Define common file extensions with special handling
     double_extensions = {
         ".ome.tiff", ".ome.tif", ".ome.tf2", ".ome.tf8", ".ome.btf", ".ome.xml",
         ".brukertiff.gz", ".mefd.gz", ".moberg.gz", ".nii.gz", ".mgh.gz", ".tar.gz", ".bcl.gz"
     }
 
-    # Helper function: Get the complete file extension
+    # Helper: Determine file extension (handles double extensions)
     def get_file_extension(filename):
         for ext in double_extensions:
             if filename.endswith(ext):
                 base_ext = os.path.splitext(os.path.splitext(filename)[0])[1]
                 return base_ext + ext
         return os.path.splitext(filename)[1]
-    
+
+    # Helper: Create a manifest row for a folder
     def create_folder_entry(folder_name, path_parts):
         full_path = "/".join(path_parts + [folder_name]) + "/"
-        entry = [
-            full_path.lstrip("/"),  # Remove leading slash for consistency
-            "", # Timestamp
-            "", # Description
-            "folder", # File type
-            "",  # Entity (empty)
-            "",  # Data modality (empty)
-            "",  # Also in dataset (empty)
-            "",  # Data dictionary path (empty)
-            "",  # Entity is transitive (empty)
-            "", # Additional Metadata
+        return [
+            full_path.lstrip("/"),
+            "", "", "folder", "", "", "", "", "", ""
         ]
-        return entry
-
-        
-
-    # Helper function: Build a single manifest entry
-    def create_file_entry(item, folder, path_parts, timestamp, filename):
-        full_path = "/".join(path_parts + [filename])
-        file_info = folder["files"][item]
 
+    # Helper: Create a manifest row for a file
+    def create_file_entry(file_name, file_info, path_parts, timestamp):
         entry = [
-            full_path.lstrip("/"),  # Remove leading slash for consistency
-            timestamp, # Timestamp
-            file_info["description"], # Description
-            get_file_extension(filename), # File type
-            "",  # Entity (empty)
-            "",  # Data modality (empty)
-            "",  # Also in dataset (empty)
-            "",  # Data dictionary path (empty)
-            "",  # Entity is transitive (empty)
-            file_info.get("additional-metadata", "") # Additional Metadata
+            "/".join(path_parts + [file_name]).lstrip("/"),
+            timestamp,
+            file_info["description"],
+            get_file_extension(file_name),
+            "", "", "", "", "",
+            file_info.get("additional-metadata", "")
         ]
 
-        # Add any extra columns dynamically
+        # Append any extra columns dynamically
         if "extra_columns" in file_info:
             for key, value in file_info["extra_columns"].items():
                 entry.append(value)
@@ -3889,48 +3871,36 @@ def generate_manifest_file_data(dataset_structure):
 
         return entry
 
-    # Recursive function: Traverse dataset and collect file data
+    # Recursive traversal of folders and files
     def traverse_folders(folder, path_parts):
-        # Add header row if processing files for the first time
         if not manifest_data:
             manifest_data.append(header_row)
-        
-        if "files" in folder:
-            for item, file_info in folder["files"].items():
-
-                if "path" in file_info:
-                    file_path = file_info["path"]
-                elif "pspath" in file_info:
-                    file_path = file_info["pspath"]
-                else: 
-                    continue 
-
-                # If the file is a manifest file, skip it
-                if item in {"manifest.xlsx", "manifest.csv"}:
-                    continue
 
-                # Determine timestamp 
-                filename = os.path.basename(file_path.replace("\\", "/"))
-                if file_info["location"] == "ps":
-                    timestamp = file_info["timestamp"]
-                else:
-                    local_path = pathlib.Path(file_info["path"])
-                    timestamp = datetime.fromtimestamp(
-                        local_path.stat().st_mtime, tz=local_timezone
-                    ).isoformat().replace(".", ",").replace("+00:00", "Z")
-
-                # Add file entry
-                manifest_data.append(create_file_entry(item, folder, path_parts, timestamp, filename))
-
-        if "folders" in folder:
-            for subfolder_name, subfolder in folder["folders"].items():
-                # Add folder entry
-                manifest_data.append(create_folder_entry(subfolder_name, path_parts))
-                traverse_folders(subfolder, path_parts + [subfolder_name])
-
-    # Initialize variables
-    manifest_data = []  # Collects all rows for the manifest
-    # TODO: Update to SDS 3.0
+        # Process files
+        for file_name, file_info in folder.get("files", {}).items():
+            file_path = file_info.get("path")
+            if not file_path:
+                continue
+            if file_name in {"manifest.xlsx", "manifest.csv"}:
+                continue
+
+            if file_info["location"] == "ps":
+                timestamp = file_info["timestamp"]
+            else:
+                local_path = pathlib.Path(file_info["path"])
+                timestamp = datetime.fromtimestamp(
+                    local_path.stat().st_mtime, tz=local_timezone
+                ).isoformat().replace(".", ",").replace("+00:00", "Z")
+
+            manifest_data.append(create_file_entry(file_name, file_info, path_parts, timestamp))
+
+        # Process subfolders
+        for subfolder_name, subfolder in folder.get("folders", {}).items():
+            manifest_data.append(create_folder_entry(subfolder_name, path_parts))
+            traverse_folders(subfolder, path_parts + [subfolder_name])
+
+    # Initialize manifest data and header
+    manifest_data = []
     header_row = [
         "filename", "timestamp", "description", "file type", "entity",
         "data modality", "also in dataset", "data dictionary path",
@@ -3938,9 +3908,6 @@ def generate_manifest_file_data(dataset_structure):
     ]
     local_timezone = TZLOCAL()
 
-    # Log the dataset structure
-
-    # Start recursive traversal from the root
     traverse_folders(dataset_structure, [])
 
     return manifest_data
@@ -3948,4 +3915,3 @@ def generate_manifest_file_data(dataset_structure):
 
 
 
-

pysoda/core/metadata/dataset_description.py

@@ -3,8 +3,8 @@ from os.path import join, getsize
 from openpyxl import load_workbook
 import shutil
 from .excel_utils import rename_headers, excel_columns
-import itertools
-from openpyxl.styles import PatternFill
+from copy import copy
+from openpyxl.styles import PatternFill, Font, Alignment, Border, Side
 from ...utils import validate_schema
 from .helpers import upload_metadata_file, get_template_path
 
@@ -44,15 +44,24 @@ def create_excel(
 
     populate_standards_info(ws1, soda)
 
-    keyword_array = populate_basic_info(ws1, soda)
-
-    populate_study_info(ws1, soda)
-    populate_contributor_info(ws1, soda)
-    populate_related_resource_information(ws1, soda)
+    keyword_array_len = populate_basic_info(ws1, soda)
+    study_arr_len = populate_study_info(ws1, soda)
+    contributor_arr_len = populate_contributor_info(ws1, soda)
+    related_resource_arr_len = populate_related_resource_information(ws1, soda)
     populate_funding_info(ws1, soda)
     populate_participant_information(ws1, soda)
     data_dictionary_information(ws1, soda)
 
+    max_len = max(
+        keyword_array_len,
+        study_arr_len,
+        contributor_arr_len,
+        related_resource_arr_len,
+    )
+
+    # 3 is the first value column position
+    extend_value_header(ws1, max_len, start_index=3)
+
     wb.save(destination)
 
     size = getsize(destination)
@@ -167,22 +176,81 @@ def data_dictionary_information(workbook, soda):
     workbook["D44"] = data_dictionary_info.get("data_dictionary_type", "")
     workbook["D45"] = data_dictionary_info.get("data_dictionary_description", "")
 
-def grayout_subheaders(workbook, max_len, start_index):
+def grayout_subheaders(workbook, col):
     """
-    Gray out sub-header rows for values exceeding 3 (SDS2.0).
+    Gray out the cells at workbook[row][col] for the specified cells in 
+    positions 2, 3, 4, 7, 8, 9, 10, 13, 14, 15, 19, 20, 21, 22, 26, 27, 32, 37, 
+    38, 39, 40, 41, 42
     """
-    headers_list = ["4", "10", "18", "23", "28"]
-    columns_list = excel_columns(start_index=start_index)
-
-    for (i, column), no in itertools.product(zip(range(2, max_len + 1), columns_list[1:]), headers_list):
-        cell = workbook[column + no]
-        fillColor("B2B2B2", cell)
-
-
+    gray_out_rows_for_column = [2, 3, 4, 7, 8, 9, 10, 13, 14, 15, 19, 20, 21, 22, 26, 27, 32, 37, 
+    38, 39, 40, 41, 42]
 
+    for row in gray_out_rows_for_column:    
+        cell = workbook[col + str(row)]
+        if row in [4, 7, 15, 19, 27, 32, 37, 42]:
+            fillColor("b2b2b2", cell)
+        else:
+            fillColor("cccccc", cell)
 
 
 def fillColor(color, cell):
     colorFill = PatternFill(start_color=color, end_color=color, fill_type="solid")
 
     cell.fill = colorFill
+
+
+def apply_calibri_bold_12(cell):
+    """Apply Calibri Bold 12pt font formatting to a cell"""
+    calibri_bold_font = Font(name='Calibri', size=12, bold=True)
+    cell.font = calibri_bold_font
+
+
+def set_cell_alignment(cell, horizontal='left', vertical='top', wrap_text=False):
+    """Set text alignment for a cell
+    
+    Args:
+        cell: The cell to format
+        horizontal: 'left', 'center', 'right', 'justify', 'distributed'
+        vertical: 'top', 'center', 'bottom', 'justify', 'distributed'
+        wrap_text: Boolean to enable text wrapping
+    """
+    cell.alignment = Alignment(
+        horizontal=horizontal,
+        vertical=vertical,
+        wrap_text=wrap_text
+    )
+
+
+def apply_dashed_border(cell, workbook):
+    """Apply border copied from cell A1 to the target cell"""
+    # Copy the border from cell A1
+    cell.border = copy(workbook["A1"].border)
+    
+
+
+
+
+
+def extend_value_header(workbook, max_len, start_index):
+    """
+    The headers starting at G1 are the 'Value' headers that correspond to the maximum number of entries for either the 
+    keywords, contributor information, or data dictionary information arrays. This function extends those headers based on the max_len of the 
+    three arrays.
+    """
+
+    column_list = excel_columns(start_index=start_index)
+
+    # if max len is less than 4 then no need to extend headers
+    if max_len < 4:
+        return
+    
+    # replace the 4th value with header value 'Value 4' and so on for max len
+    for i in range(4, max_len + 1):
+        header_cell = workbook[column_list[i - 1] + "1"]
+        header_cell.value = f"Value {i}"
+        # make the new header blue
+        fillColor("9cc2e5", header_cell)
+        apply_calibri_bold_12(header_cell)
+        set_cell_alignment(header_cell, horizontal='center', vertical='center')
+        apply_dashed_border(header_cell, workbook)
+        grayout_subheaders(workbook, column_list[i - 1])

pysoda/schema/dataset_description.json

@@ -136,8 +136,8 @@
           },
           "contributor_name": {
             "type": "string",
-            "pattern": "^[A-Za-z]+, [A-Za-z]+( [A-Za-z]+)?$",
-            "description": "The name of the contributor. The format should be 'Last Name, First Name'."
+            "pattern": "^(([Vv]an|[Vv]an [Dd]e[rn]?|[Vv]an [Tt]|[Vv]ander|[Vv]on|[Vv]on [Dd]e[rn]?|[Zz]u|[Zz]ur|[Vv]om|[Dd]e|[Dd]es|[Dd]u|[Dd]e [Ll]a|[Dd]e [Ll]es|[Dd]e [Ll]os|[Ll]e|[Ll]a|[Ll]es|[Dd]el|[Dd]e [Ll]os|[Dd]e [Ll]a|[Dd]e [Ll]as|[Dd]a|[Dd]o|[Dd]i|[Dd]ell[ao]|[Dd]ell[ei]|[Dd]ai|[Dd]al|[Dd]alle|[Oo]'|[Mm]c|[Mm]ac|[Aa]l|[Ee]l|[Aa]bd [Aa]l|[Aa]bu|[Ii]bn|[Ff]itz|[Aa]p|[Bb]en|[Bb]ar|[Bb]at) )?[^, ]+, [^,]+$",
+            "description": "The name of the contributor. The format should be 'Last Name, First Name'. Supports international family name prefixes (van, von, de, del, etc.)."
           },
           "contributor_role": {
             "type": "string",

pysoda/schema/resources.json

@@ -8,6 +8,10 @@
         "type": "string",
         "description": "Unique identifier for the site, typically an RRID"
       },
+      "type": {
+        "type": "string",
+        "description": "The type of resource, e.g., 'instrument', 'software', 'reagent', etc."
+      },
       "name": {
         "type": "string",
         "description": "The resources name"
@@ -34,6 +38,6 @@
         "description": "Additional metadata about the resource, such as usage notes or specific details"
       }
     },
-    "required": ["rrid", "name", "url", "vendor", "version", "id_in_protocol"]
+    "required": ["rrid"]
   }
 }

{pysodafair-0.1.62.dist-info → pysodafair-0.1.64.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pysodafair
-Version: 0.1.62
+Version: 0.1.64
 Summary: Pysoda package for Fairdataihub tools
 License: MIT
 License-File: LICENSE

{pysodafair-0.1.62.dist-info → pysodafair-0.1.64.dist-info}/RECORD

@@ -4,13 +4,13 @@ pysoda/core/__init__.py,sha256=bXnu4fYemJ915xId8nwh-Gy2IUEvVuoS9Hk3CXyJp8U,235
 pysoda/core/dataset_generation/__init__.py,sha256=tisLmJeXLeAINXf7BdNZGi2i9vQwImWGa_S5FNwQFbs,299
 pysoda/core/dataset_generation/manifestSession/__init__.py,sha256=kqkTAFEhluyQJ9mmMhYQTh1tgowBeJdH-Q9s5ifGkSE,51
 pysoda/core/dataset_generation/manifestSession/manifest_session.py,sha256=TML_KOJ-1REohqSaHCZNFJrbDR1UDQ9sFcithJRx9t8,4669
-pysoda/core/dataset_generation/upload.py,sha256=ATx8D-Ck1xDzrT_rI-YSDmi9hFFqiz2E0FgCrPlyJQA,174022
+pysoda/core/dataset_generation/upload.py,sha256=FtEQoyg3ly0lXmnUtKDXXHln1dLN6reb9knOdFTBFeA,172657
 pysoda/core/dataset_importing/__init__.py,sha256=NbWs4HAqqydFLACFoVwl6g457dkYvjiZKx9NzB9wFxE,114
 pysoda/core/dataset_importing/import_dataset.py,sha256=cx8qCQmR_BKdC2G-jzqE4dWg2JhkOS3jM8kpjLIsObk,29487
 pysoda/core/metadata/__init__.py,sha256=Tkx6vdEQEPwAHmVSc9GfdbDZUkvuAqEgHJOxRDeX5vE,821
 pysoda/core/metadata/code_description.py,sha256=sWbRPWPf32txpN048oQ9lT3y7GAoDkrS-GHivwwv55Y,4104
 pysoda/core/metadata/constants.py,sha256=PR78huqBKdBpzDUGxVKy9YW3pUrJ4ftuF4MfqpNb1bU,1052
-pysoda/core/metadata/dataset_description.py,sha256=uwVC0tBVglQPs57LQL22nEXKLjCm1j6rtmGj8ByOeoA,7332
+pysoda/core/metadata/dataset_description.py,sha256=K1yWYQkbn4d7DCjQH5vT9Y6dhcWWlx823XLACgkIS2M,9749
 pysoda/core/metadata/excel_utils.py,sha256=FQ8-DBq2lxFdpDUZeABfFKe284JzRTe6AYPxEw7yzsg,1216
 pysoda/core/metadata/helpers.py,sha256=jDf4KPTbx4unHT7pDlFEa0jls1OZY-dpdKf3kUGMtvg,10609
 pysoda/core/metadata/manifest.py,sha256=MjID-r52Yn3i9WlrT5IWeYvmkVdfzQuqGOmoMsZQVJg,4197
@@ -50,10 +50,10 @@ pysoda/core/upload_manifests/__init__.py,sha256=SOiyflYmZDtkLwWpeu7flyn3J2SAj9WL
 pysoda/core/upload_manifests/upload_manifests.py,sha256=Hd2XSXYieG-EMcPTLSYXvdtraipp1XBSo5cGpZR-vbA,1223
 pysoda/schema/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pysoda/schema/code_description.json,sha256=FJOyJBC2TKjTTdtew3B4wdq_WIrti-r2F-M6t5OVNB0,17854
-pysoda/schema/dataset_description.json,sha256=rRuQiYthOwrlmzP_d3F1cG_ceIpefzxGuINorEcrA5g,8626
+pysoda/schema/dataset_description.json,sha256=qxhzQzoE7CGuXvtY9fVWV31-daf5Ivms7_PkVW4i858,9053
 pysoda/schema/manifest.json,sha256=bsVzhnZHd2566KhrxQPBcwH376fgE8pSY8eXviTXrWA,2636
 pysoda/schema/performances.json,sha256=TJw7ERC6eMR-9cImOg7xoEVRyOR4xViJqZO8U2X2OXo,1254
-pysoda/schema/resources.json,sha256=FADf1p0IG_gliQlSr04cRtLKQMm8XhEktlnbnw_XG1U,1140
+pysoda/schema/resources.json,sha256=9-rwCTX523V5XaKmXLTUGzackOl7tk-qijbbBDoeuhY,1232
 pysoda/schema/samples.json,sha256=NvuYhskV9QFrkSX4ant9G4KFCe9JLnVG98vDv2Puuvk,3340
 pysoda/schema/sites.json,sha256=lMkglgi4R7_qqUHh6uwbZ38TjkUzRKGY9pdF1CpZh4E,1133
 pysoda/schema/soda_schema.json,sha256=QSe8G39wOMO5wS_MUU0mW6yeM4etufACE6iuAzZMBoA,19290
@@ -71,7 +71,7 @@ pysoda/utils/profile.py,sha256=di4D_IE1rGSfHl0-SRVjrJK2bCdedW4ugp0W-j1HarQ,937
 pysoda/utils/schema_validation.py,sha256=3w3FRPyn4P3xMhITzItk-jYte8TTlNrgCWmY-s05x9Y,4438
 pysoda/utils/time_utils.py,sha256=g5848bivtzWj6TDoWo6CcohF-THxShETP4qTyHTjBWw,131
 pysoda/utils/upload_utils.py,sha256=-BCvfXsJSFqnwEZVCFQX1PLfkdeW0gyGLjLGW6Uxdf8,4607
-pysodafair-0.1.62.dist-info/METADATA,sha256=J4JLeWI1aGB18L8QAl__4vgRS8Z5hNqvK-i2zFTHMVQ,7011
-pysodafair-0.1.62.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-pysodafair-0.1.62.dist-info/licenses/LICENSE,sha256=Jlt0uGnx87qPRGXPQHsBkg_S7MOsYS2E9Rh1zy47bfw,1082
-pysodafair-0.1.62.dist-info/RECORD,,
+pysodafair-0.1.64.dist-info/METADATA,sha256=mgUEcj-8RZdfFlMBD94Joq0bmRP4CXOF0C6S3JxYX20,7011
+pysodafair-0.1.64.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+pysodafair-0.1.64.dist-info/licenses/LICENSE,sha256=Jlt0uGnx87qPRGXPQHsBkg_S7MOsYS2E9Rh1zy47bfw,1082
+pysodafair-0.1.64.dist-info/RECORD,,