Indiana validations

notebooks/validations.ipynb

@@ -0,0 +1,19 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "90cd0bf2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

src/excel2sbol/__init__.py

@@ -4,4 +4,5 @@
 from .helpers import *
 from .library2 import *
 from .library3 import *
-from .lookup_compiler import *
+from .lookup_compiler import *
+from .validator import *

src/excel2sbol/compiler.py

@@ -11,6 +11,15 @@
 
 # the homespace only works if the change is made to pysbol2 shown in https://github.com/SynBioDex/pySBOL2/pull/411/files
 
+def _is_update_true(val):
+    if val is None:
+        return False
+    if isinstance(val, bool):
+        return val
+    if isinstance(val, (int, float)):
+        return val == 1
+    return str(val).strip().upper() in {"TRUE", "T", "YES", "Y", "1"}
+
 def initialise_welcome(file_path_in):
     init_info = pd.read_excel(file_path_in, sheet_name="Init",
                               skiprows=9, index_col=0,
@@ -130,9 +139,17 @@ def initialise(file_path_in):
         lib_df = pd.read_excel(file_path_in, sheet_name=sheet_name,
                                header=0, skiprows=skipval,
                                engine='openpyxl').fillna("")
-
-        sheet_dict['library'] = lib_df.applymap(lambda x: x.strip() if isinstance(x, str) else x).to_dict('list')
 
+        lib_df = lib_df.applymap(lambda x: x.strip() if isinstance(x, str) else x)
+
+        # Only convert rows where Update is TRUE
+        if 'Update' in lib_df.columns:
+            before_count = len(lib_df)
+            lib_df = lib_df[lib_df['Update'].apply(_is_update_true)].copy()
+            after_count = len(lib_df)
+            print(f"INFO: Sheet '{sheet_name}': kept {after_count}/{before_count} rows where Update is TRUE.")
+
+        sheet_dict['library'] = lib_df.to_dict('list')
         # need dicitonary with as keys every column name and as values a list of values (note ordered list and need place holder empty values)
         compiled_sheets[sheet_name] = sheet_dict
 
@@ -354,7 +371,7 @@ def column_parse(to_convert, compiled_sheets, sht_convert_dict, dict_of_objs,
                     # checks that the cell isn't blank
                     col_convert_df = col_read_df.loc[(col_read_df['Sheet Name'] == sht) & (col_read_df['Column Name'] == col)]
                     if col_convert_df.empty:
-                        raise ValueError(f"There is an issue with the column definitions sheet missing values. Sheet:'{sht}' with Column:'{col}' cannot be found. Please check for any spaces.")
+                        continue
 
                     # split method
                     split_on = col_convert_df['Split On'].values[0]