Merge branch 'crest' into crest_debug_statement

Author: calvinp0

arc/job/adapters/ts/heuristics.py

@@ -36,7 +36,7 @@
 from arc.job.adapters.common import _initialize_adapter, ts_adapters_by_rmg_family
 from arc.job.factory import register_job_adapter
 from arc.plotter import save_geo
-from arc.species.converter import compare_zmats, relocate_zmat_dummy_atoms_to_the_end, zmat_from_xyz, zmat_to_xyz, str_to_xyz, xyz_to_str
+from arc.species.converter import compare_zmats, relocate_zmat_dummy_atoms_to_the_end, zmat_from_xyz, zmat_to_xyz, str_to_xyz, xyz_to_str, str_to_str
 from arc.mapping.engine import map_arc_rmg_species, map_two_species
 from arc.species.species import ARCSpecies, TSGuess, colliding_atoms
 from arc.species.zmat import get_parameter_from_atom_indices, remove_1st_atom, up_param
@@ -1097,28 +1097,30 @@ def h_abstraction(arc_reaction: 'ARCReaction',
             second_lowest = unique_sorted_values[1]
             print(f"The second lowest unique value in H21 is: {second_lowest}")
             cols_second_lowest = h_row[h_row == second_lowest].index.tolist()
-        else:
-            crest_run = False
-            print("H21 does not have a second lowest unique value. Will not do CREST")
-        
-        if len(cols_second_lowest) == 1:
 
-            h_str = row_col_pairs[0][0]  # 'H21'
-            print(f"h str = {h_str}")
-            b_str = row_col_pairs[0][1]  # 'C14'
-            print(f"b str {b_str}")
-            a_str = cols_second_lowest[0]     # 'C4'
-            print(f"a str {a_str}")
+            if len(cols_second_lowest) == 1:
+
+                h_str = row_col_pairs[0][0]  # 'H21'
+                print(f"h str = {h_str}")
+                b_str = row_col_pairs[0][1]  # 'C14'
+                print(f"b str {b_str}")
+                a_str = cols_second_lowest[0]     # 'C4'
+                print(f"a str {a_str}")
 
-            h = int(re.findall(r'\d+', h_str)[0])
-            b = int(re.findall(r'\d+', b_str)[0])
-            a = int(re.findall(r'\d+', a_str)[0])
+                h = int(re.findall(r'\d+', h_str)[0])
+                b = int(re.findall(r'\d+', b_str)[0])
+                a = int(re.findall(r'\d+', a_str)[0])
 
-            # log info a, b, h1, h2, b_atom, a_atom, h_atom, val_inc
-            logger.info(f'a: {a}, b: {b}, h: {h}')
+                # log info a, b, h1, h2, b_atom, a_atom, h_atom, val_inc
+                logger.info(f'a: {a}, b: {b}, h: {h}')
+            else:
+                crest_run = False
+                print(f"Received more than one result for second lowest: {cols_second_lowest}")
         else:
             crest_run = False
-            print(f"Received more than one result for second lowest: {cols_second_lowest}")
+            print("H21 does not have a second lowest unique value. Will not do CREST")
+        
+
 
         ####
 

arc/species/converter.py

@@ -71,7 +71,59 @@ def str_to_str(xyz_str: str,
     """
     if not isinstance(xyz_str, str):
         raise ConverterError(f'Expected a string input, got {type(xyz_str)}')
-    pass
+    if project_directory is not None and os.path.isfile(os.path.join(project_directory, xyz_str)):
+        xyz_str = os.path.join(project_directory, xyz_str)    
+    
+
+    BOHR_TO_ANGSTROM = 0.529177
+    ANGSTROM_TO_BOHR = 1.8897259886
+
+    if convert_to.lower() == 'angstrom':
+        conversion_factor = BOHR_TO_ANGSTROM
+    elif convert_to.lower() == 'bohr':
+        conversion_factor = ANGSTROM_TO_BOHR
+    else:
+        raise ValueError("Invalid target unit. Choose 'angstrom' or 'bohr'.")
+
+
+    processed_lines = list()
+    # Split the string into lines
+    lxyz = xyz_str.strip().split()
+
+    atom_first = False if is_str_float(lxyz[0]) else True
+    lxyz = xyz_str.strip().splitlines()
+
+    for idx, item in enumerate(lxyz):
+        parts = item.strip().split()
+
+        if len(parts) != 4:
+            raise ConverterError(f'xyz_str has an incorrect format, expected 4 elements in each line, '
+                                    f'got "{item}" in:\n{xyz_str}')
+        if atom_first:
+            atom, x_str, y_str, z_str = parts
+        else:
+            x_str, y_str, z_str, atom = parts
+        
+        try:
+            x = float(x_str) * conversion_factor
+            y = float(y_str) * conversion_factor
+            z = float(z_str) * conversion_factor
+        
+        except ValueError:
+            raise ConverterError(f'Could not convert {x_str}, {y_str}, or {z_str} to floats.')
+        
+        if reverse_atoms and atom_first:
+            formatted_line = f'{x} {y} {z} {atom}'
+        elif reverse_atoms and not atom_first:
+            formatted_line = f'{atom} {x} {y} {z}'
+        elif not reverse_atoms and atom_first:
+            formatted_line = f'{atom} {x} {y} {z}'
+        elif not reverse_atoms and not atom_first:
+            formatted_line = f'{x} {y} {z} {atom}'
+        
+        processed_lines.append(formatted_line)
+    
+    return '\n'.join(processed_lines)
 
 
 def str_to_xyz(xyz_str: str,