SOF-7010: implement class method to strip label and return atomic symbol

.github/workflows/cicd.yml

@@ -8,7 +8,7 @@ concurrency:
 
 jobs:
   run-py-linter:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     strategy:
       matrix:
         python-version: [3.10.13]
@@ -33,7 +33,7 @@ jobs:
 
   run-py-tests:
     needs: run-py-linter
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     strategy:
       matrix:
         python-version:

dist/js/basis/basis.d.ts

@@ -210,6 +210,15 @@ export declare class Basis {
     get hashString(): string;
     get atomicLabelsArray(): string[];
     get elementsWithLabelsArray(): string[];
+    /**
+     * Strips any label associated with atomic symbol
+     * Possible labels:
+     *   (1) Fe1, Fe11
+     *   (2) Fe-a, Fe-b, Fe-1, Fe-1a
+     *   (3) Fe_a, Fe_b, Fe_1, Fe_1a
+     * As of Mar 2025, only single digit numerical labels are allowed
+     */
+    static stripLabelToGetElementSymbol: (elementWithLabel: string) => string;
     /**
      * Returns an array of strings with chemical elements and their atomic positions.
      * E.g., ``` ['Si 0 0 0', 'Li 0.5 0.5 0.5']```

dist/js/basis/basis.js

@@ -322,9 +322,7 @@ class Basis {
         const clsInstance = new Basis(this.toJSON());
         clsInstance.toStandardRepresentation();
         const standardRep = clsInstance.elementsAndCoordinatesAndLabelsArray.map((entry) => {
-            const element = entry[0];
-            const coordinate = entry[1];
-            const atomicLabel = entry[2];
+            const [element, coordinate, atomicLabel] = entry;
             const toleratedCoordinates = coordinate.map((x) => math_1.default.round(x, constants_1.HASH_TOLERANCE));
             return `${element}${atomicLabel} ${toleratedCoordinates.join()}`;
         });
@@ -367,10 +365,8 @@ class Basis {
      * E.g., ``` ['Si 0 0 0', 'Li 0.5 0.5 0.5']```
      */
     get atomicPositions() {
-        return this.elementsAndCoordinatesAndLabelsArray.map((entry, idx) => {
-            const element = entry[0];
-            const coordinate = entry[1];
-            const atomicLabel = this.atomicLabelsArray[idx];
+        return this.elementsAndCoordinatesAndLabelsArray.map((entry) => {
+            const [element, coordinate, atomicLabel] = entry;
             return `${element}${atomicLabel} ${coordinate
                 .map((x) => underscore_string_1.default.sprintf("%14.9f", x).trim())
                 .join(" ")}`;
@@ -522,3 +518,22 @@ class Basis {
     }
 }
 exports.Basis = Basis;
+/**
+ * Strips any label associated with atomic symbol
+ * Possible labels:
+ *   (1) Fe1, Fe11
+ *   (2) Fe-a, Fe-b, Fe-1, Fe-1a
+ *   (3) Fe_a, Fe_b, Fe_1, Fe_1a
+ * As of Mar 2025, only single digit numerical labels are allowed
+ */
+Basis.stripLabelToGetElementSymbol = (elementWithLabel) => {
+    // Strip anything after `-` or `_`
+    let elementSymbol = elementWithLabel.split(/[- _]/)[0];
+    // Exclude digit labels at the end of the symbol if present
+    elementSymbol = elementSymbol.replace(/\d+$/, "");
+    // Return symbol in title case
+    elementSymbol =
+        elementSymbol.charAt(0).toUpperCase() + elementSymbol.slice(1).toLowerCase();
+    // We can improve by validating element symbol matches one from the periodic table
+    return elementSymbol;
+};