Bunch of technical fixes (#65)

* fix AutoAUX for Z>86; note regarding basis set choice; missing init entry and linting correction

Signed-off-by: Marcel Müller <[email protected]>

* fix typo

Signed-off-by: Marcel Müller <[email protected]>

---------

Signed-off-by: Marcel Müller <[email protected]>

README.md

@@ -91,6 +91,11 @@ There are two related aspects of the element composition:
 - **Example 1**: `C:1-3, O:1-1, H:1-*` would result in a molecule with 1, 2, or 3 carbon atoms, exactly 1 oxygen atom, and between 1 and an undefined number of hydrogen atoms (i.e., at least 1).
 - **Example 2**: `Na:10-10, In:10-10, O:20-20`. This example would result in a molecule with exactly 10 sodium atoms, 10 indium atoms, and 20 oxygen atoms. **For a fixed element composition, the number of atoms (40) has to be within the min_num_atoms and max_num_atom interval.** `mindlessgen` will consequently always return a molecule with exactly 40 atoms.
 
+> [!WARNING]
+> When using `orca` and specifying elements with `Z > 86`, ensure that the basis set you've selected is compatible with (super-)heavy elements like actinides.
+> You can find a list of available basis sets [here](https://www.faccts.de/docs/orca/6.0/manual/contents/detailed/basisset.html#built-in-basis-sets).
+> A reliable standard choice that covers the entire periodic table is `def2-mTZVPP`.
+
 ## Citation
 
 When using the program for academic purposes, please cite:

src/mindlessgen/molecules/__init__.py

@@ -17,6 +17,7 @@
     get_four_d_metals,
     get_five_d_metals,
     get_lanthanides,
+    get_actinides,
     get_alkali_metals,
     get_alkaline_earth_metals,
 )
@@ -34,6 +35,7 @@
     "get_four_d_metals",
     "get_five_d_metals",
     "get_lanthanides",
+    "get_actinides",
     "get_alkali_metals",
     "get_alkaline_earth_metals",
     "PSE_NUMBERS",

src/mindlessgen/molecules/molecule.py

@@ -246,8 +246,10 @@ def read_mol_from_file(file: str | Path) -> Molecule:
         molecule = Molecule()
         if isinstance(file, str):
             file_path = Path(file).resolve()
-        if isinstance(file, Path):
+        elif isinstance(file, Path):
             file_path = file.resolve()
+        else:
+            raise TypeError("String or Path expected.")
         molecule.read_xyz_from_file(file_path)
         if file_path.with_suffix(".CHRG").exists():
             molecule.read_charge_from_file(file_path.with_suffix(".CHRG"))

src/mindlessgen/qm/orca.py

@@ -165,6 +165,9 @@ def _gen_input(
         orca_input = f"! {self.cfg.functional} {self.cfg.basis}\n"
         orca_input += f"! DEFGRID{self.cfg.gridsize}\n"
         orca_input += "! NoTRAH NoSOSCF SlowConv\n"
+        # "! AutoAux" keyword for super-heavy elements as def2/J ends at Rn
+        if any(atom >= 86 for atom in molecule.ati):
+            orca_input += "! AutoAux\n"
         if optimization:
             orca_input += "! OPT\n"
             if opt_cycles is not None:

src/mindlessgen/qm/xtb.py

@@ -205,12 +205,12 @@ def _run(self, temp_path: Path, arguments: list[str]) -> tuple[str, str, int]:
                 check=True,
             )
             # get the output of the xtb calculation (of both stdout and stderr)
-            xtb_log_out = xtb_out.stdout.decode("utf8")
-            xtb_log_err = xtb_out.stderr.decode("utf8")
+            xtb_log_out = xtb_out.stdout.decode("utf8", errors="replace")
+            xtb_log_err = xtb_out.stderr.decode("utf8", errors="replace")
             return xtb_log_out, xtb_log_err, 0
         except sp.CalledProcessError as e:
-            xtb_log_out = e.stdout.decode("utf8")
-            xtb_log_err = e.stderr.decode("utf8")
+            xtb_log_out = e.stdout.decode("utf8", errors="replace")
+            xtb_log_err = e.stderr.decode("utf8", errors="replace")
             return xtb_log_out, xtb_log_err, e.returncode