apply_symmetry_operations_to_frac

cell2mol/c2m_driver.py

@@ -11,7 +11,7 @@
 from cell2mol.other import handle_error
 import ase.io
 from cell2mol.cell_operations import frac2cart_fromparam
-
+from cell2mol.cell_operations import cart2frac
 
 # if __name__ != "__main__" and __name__ != "cell2mol.c2m_driver": sys.exit(1)
 if __name__ == "__main__" or __name__ == "cell2mol.c2m_driver":
@@ -73,7 +73,7 @@
     atoms = ase.io.read(input_path)
 
     # Get Cartesian coordinates
-    cartesian_coords = atoms.get_positions()
+    cartesian_coords = atoms.get_positions("center")
 
     # Get atomic symbols (labels)
     atomic_labels = atoms.get_chemical_symbols()
@@ -92,15 +92,16 @@
     # Loads the reference molecules and checks_missing_H
     # TODO : reconstruct the unit cell without using reference molecules
     # TODO : reconstruct the unit cell using (only reconstruction of) reference molecules and Space group
-    newcell.get_reference_molecules(ref_labels, ref_fracs,cov_factor=1.3, debug=debug) 
+    newcell.get_reference_molecules(ref_labels, ref_fracs, cov_factor=1.3, debug=debug) 
     ref_pos = frac2cart_fromparam(ref_fracs, cellparam)
     writexyz(current_dir, "Ref_All_{}.xyz".format(name), ref_labels, ref_pos)
+    writexyz(current_dir, "Ref_All_frac_{}.xyz".format(name), ref_labels, ref_fracs)
     if not newcell.has_isolated_H:  newcell.check_missing_H(debug=debug)                                     
     newcell.assess_errors(ref=True)
     newcell.save(ref_cell_fname)
     for idx, ref in enumerate(newcell.refmoleclist):
         writexyz(current_dir, "Ref_Molecule_{}_{}.xyz".format(name, idx), ref.labels, ref.coord)
-
+        writexyz(current_dir, "Ref_Molecule_{}_frac_{}.xyz".format(name, idx), ref.labels, cart2frac(ref.coord, cellvec))
     # sys.exit(0) 
     ######################
     ### CALLS CELL2MOL ###

cell2mol/classes.py

@@ -1484,6 +1484,7 @@ def reconstruct(self, cov_factor: float=None, metal_factor: float=None, debug: i
             if Warning:
                 self.is_fragmented = True
                 self.error_reconstruction = True 
+
             else :
                 self.is_fragmented = False
                 self.error_reconstruction = False 

cell2mol/read_write.py

@@ -3,6 +3,8 @@
 import numpy as np
 import pickle
 import sys
+import re
+from collections import defaultdict
 
 #######################
 def prefiter_cif(input_path):
@@ -340,3 +342,36 @@ def print_unit_cell(cell, output_dir):
         for mol in cell.moleclist:
             for a in mol.atoms:
                 print(a.label, a.coord[0], a.coord[1], a.coord[2], file=fil)
+
+############
+def extract_chemical_formula_moiety(file_path):
+    with open(file_path, 'r') as file:
+        cif_content = file.read()
+
+    # Find the chemical formula moiety using regex
+    pattern = r"_chemical_formula_moiety\s+['\";]([^;'\"]+)['\";]"
+    match = re.search(pattern, cif_content)
+    if not match:
+        raise ValueError("Chemical formula moiety not found.")
+    formula = match.group(1).strip()
+    return formula
+
+def parse_formula_with_quantity(formula: str):
+    element_pattern = r"(\d*)\(?([A-Za-z0-9\s]+)\)?(\d*)(\d+[+-]?)"
+    moieties_info = []
+
+    for match in re.findall(element_pattern, formula):
+        quantity = int(match[0]) if match[0] else 1
+        elements = defaultdict(int)
+        for element, count in re.findall(r"([A-Z][a-z]*)(\d*)", match[1]):
+            elements[element] += int(count) if count else 1
+
+        charge_str = match[3]
+        charge = int(charge_str[:-1]) * (1 if charge_str.endswith("+") else -1)
+
+        moieties_info.append({
+            "elements": dict(elements),
+            "quantity": quantity,
+            "charge": charge
+        })
+    return moieties_info