fixes and cleaning

Author: shivupa

cclib/attribute_parsers/aonames.py

@@ -79,7 +79,7 @@ def natural_orbital_single_spin_parsing(fh):
                         # New atom.
                         if len(parts) > 1:
                             if i > 0:
-                                this_aonames.append(basisonatom)
+                                this_aonames.append(basisonatom)  # noqa: F821
                             basisonatom = []
                         orbital = line[11:20].strip()  # noqa: F841
                         basisonatom.append(i)
@@ -127,17 +127,20 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
         # when the parsing gets rough. This is what we do below with a regex, and a case
         # like this is tested in regression ORCA/ORCA4.0/invalid-literal-for-float.out
         # which was reported in https://github.com/cclib/cclib/issues/629
+        dependency_list = ["moenergies", "nbasis"]
+        if not base_parser.check_dependencies(dependency_list, ccdata, "atombasis"):
+            return None
         line = file_handler.last_line
         if line[0:18] == "MOLECULAR ORBITALS":
-            line = file_handler.virtual_next() # dashes
+            line = file_handler.virtual_next()  # dashes
 
             parsed_aonames = []
-            for spin in range(len(self.moenergies)):
+            for spin in range(len(ccdata.moenergies)):
                 if spin == 1:
-                    line = file_handler.virtual_next() # blank
-                for i in range(0, self.nbasis, 6):
-                    file_handler.skip_lines(["numbers", "energies, "occs", "d"], virtual=True)
-                    for j in range(self.nbasis):
+                    line = file_handler.virtual_next()  # blank
+                for i in range(0, ccdata.nbasis, 6):
+                    file_handler.skip_lines(["numbers", "energies", "occs", "d"], virtual=True)
+                    for j in range(ccdata.nbasis):
                         line = file_handler.virtual_next()
                         # Only need this in the first iteration.
                         if spin == 0 and i == 0:
@@ -148,7 +151,6 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
             return {aonames.__name__: parsed_aonames}
         return None
 
-
     @staticmethod
     def parse(file_handler, program: str, ccdata) -> Optional[dict]:
         constructed_data = None

cclib/attribute_parsers/aooverlaps.py

@@ -57,13 +57,15 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
                 dashes = file_handler.virtual_next()  # noqa: F841
                 constructed_aooverlaps = np.zeros((ccdata.nbasis, ccdata.nbasis), "d")
                 for i in range(0, ccdata.nbasis, 6):
-                    #self.updateprogress(inputfile, "Overlap")
+                    # self.updateprogress(inputfile, "Overlap")
                     header = file_handler.virtual_next()
                     size = len(header.split())
                     for j in range(ccdata.nbasis):
                         line = file_handler.virtual_next()
                         broken = line.split()
-                        constructed_aooverlaps[j, i : i + size] = list(map(float, broken[1 : size + 1]))
+                        constructed_aooverlaps[j, i : i + size] = list(
+                            map(float, broken[1 : size + 1])
+                        )
                 return {aooverlaps.__name__: constructed_aooverlaps}
         return None
 

cclib/attribute_parsers/atombasis.py

@@ -145,22 +145,17 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
             return None
         if line[0:18] == "MOLECULAR ORBITALS":
             file_handler.skip_lines(["dashes"], virtual=True)
-            #constructed_aonames = []
             constructed_atombasis = [[] for i in range(ccdata.natom)]
-            #constructed_mocoeffs = [numpy.zeros((ccdata.nbasis, ccdata.nbasis), "d")]
             for spin in range(len(ccdata.moenergies)):
                 if spin == 1:
                     file_handler.skip_lines(["blank"], virtual=True)
                 for i in range(0, ccdata.nbasis, 6):
-                    #self.updateprogress(inputfile, "Coefficients")
                     file_handler.skip_lines(["numbers", "energies", "occs", "d"], virtual=True)
                     for j in range(ccdata.nbasis):
                         line = file_handler.virtual_next()
                         # Only need this in the first iteration.
                         if spin == 0 and i == 0:
-                            atomname = line[3:5].split()[0]
                             num = int(line[0:3])
-                            orbital = line.split()[1].upper()
                             constructed_atombasis[num].append(j)
             constructed_data = {atombasis.__name__: constructed_atombasis}
             return constructed_data

cclib/attribute_parsers/atomcoords.py

@@ -35,7 +35,7 @@ def gaussian(file_handler, ccdata) -> Optional[dict]:
 
     @staticmethod
     def ORCA(file_handler, ccdata) -> Optional[dict]:
-        """ Grab cartesian coordinates
+        """Grab cartesian coordinates
         ---------------------------------
         CARTESIAN COORDINATES (ANGSTROEM)
         ---------------------------------
@@ -55,10 +55,9 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
                     curr_atomcoords.append([float(x), float(y), float(z)])
                 line = file_handler.virtual_next()
             constructed_atomcoords.append(curr_atomcoords)
-            return {atomcoords.__name__ : np.array(constructed_atomcoords)}
+            return {atomcoords.__name__: np.array(constructed_atomcoords)}
         return None
 
-
     @staticmethod
     def psi4(file_handler, ccdata) -> Optional[dict]:
         line = file_handler.last_line

cclib/attribute_parsers/atomnos.py

@@ -53,7 +53,7 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
                 if atom[-1] != ">":
                     constructed_atomnos.append(table.number[atom])
                 line = file_handler.virtual_next()
-            return {atomnos.__name__ : np.array(constructed_atomnos)}
+            return {atomnos.__name__: np.array(constructed_atomnos)}
         return None
 
     @staticmethod

cclib/attribute_parsers/charge.py

@@ -52,8 +52,8 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
         if not base_parser.check_dependencies(dependency_list, ccdata, "charge"):
             return None
         if "input_file_contents" in ccdata.metadata:
-            #parsed from inputfile content
-            lines = ccdata.metdata["input_file_contents"].split('\n')
+            # parsed from inputfile content
+            lines = ccdata.metdata["input_file_contents"].split("\n")
             lines_iter = iter(lines[:-1])
             for line in lines_iter:
                 line = line.strip()

cclib/attribute_parsers/gbasis.py

@@ -122,7 +122,7 @@ def gaussian(file_handler, ccdata) -> Optional[dict]:
     @staticmethod
     def ORCA(file_handler, ccdata) -> Optional[dict]:
         line = file_handler.last_line
-        if not "gbasis_tmp_atnames" in ccdata.parser_state:
+        if "gbasis_tmp_atnames" not in ccdata.parser_state:
             return None
         # Basis set information
         # ORCA prints this out in a somewhat indirect fashion.

cclib/attribute_parsers/mocoeffs.py

@@ -2,10 +2,13 @@
 #
 # This file is part of cclib (http://cclib.github.io) and is distributed under
 # the terms of the BSD 3-Clause License.
+import re
 from typing import Optional
 
 from cclib.attribute_parsers.base_parser import base_parser
 
+import numpy
+
 
 class mocoeffs(base_parser):
     """
@@ -100,7 +103,7 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
                     file_handler.skip_lines(["blank"], virtual=True)
                     constructed_mocoeffs.append(numpy.zeros((ccdata.nbasis, ccdata.nbasis), "d"))
                 for i in range(0, ccdata.nbasis, 6):
-                    #self.updateprogress(inputfile, "Coefficients")
+                    # self.updateprogress(inputfile, "Coefficients")
                     file_handler.skip_lines(["numbers", "energies", "occs", "d"], virtual=True)
                     for j in range(ccdata.nbasis):
                         line = file_handler.virtual_next()
@@ -109,12 +112,13 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
                         coeffs = re.findall(r"-?\d+\.\d{6}", line)
                         # Something is very wrong if this does not hold.
                         assert len(coeffs) <= 6
-                        constructed_mocoeffs[spin][i : i + len(coeffs), j] = [float(c) for c in coeffs]
+                        constructed_mocoeffs[spin][i : i + len(coeffs), j] = [
+                            float(c) for c in coeffs
+                        ]
             constructed_data = {mocoeffs.__name__: constructed_mocoeffs}
             return constructed_data
         return None
 
-
     @staticmethod
     def parse(file_handler, program: str, ccdata) -> Optional[dict]:
         constructed_data = None

cclib/attribute_parsers/moenergies.py

@@ -57,39 +57,23 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
         line = file_handler.last_line
         if line[0:16] == "ORBITAL ENERGIES":
             file_handler.skip_lines(["d", "text", "text"], virtual=True)
-            #constructed_mooccnos = [[]]
             constructed_moenergies = [[]]
-            #constructed_mosyms = [[]]
             line = file_handler.virtual_next()
             while len(line) > 20:  # restricted calcs are terminated by ------
                 info = line.split()
-                #mooccno = int(float(info[1]))
                 moenergy = float(info[2])
-                #mosym = "A"
-                #if self.uses_symmetry:
-                #    mosym = self.normalisesym(info[4].split("-")[1])
-                #self.mooccnos[0].append(mooccno)
                 constructed_moenergies[0].append(moenergy)
-                #self.mosyms[0].append(mosym)
                 line = file_handler.virtual_next()
             line = file_handler.virtual_next()
             # handle beta orbitals for UHF
             if line[17:35] == "SPIN DOWN ORBITALS":
                 file_handler.skip_lines(["text"], virtual=True)
-                #constructed_mooccnos.append([])
                 constructed_moenergies.append([])
-                #constructed_mosyms.append([])
                 line = file_handler.virtual_next()
                 while len(line) > 20:  # actually terminated by ------
                     info = line.split()
-                    #mooccno = int(float(info[1]))
                     moenergy = float(info[2])
-                    #mosym = "A"
-                    #if self.uses_symmetry:
-                    #    mosym = self.normalisesym(info[4].split("-")[1])
-                    #constructed_mooccnos[1].append(mooccno)
                     constructed_moenergies[1].append(moenergy)
-                    #constructed_mosyms[1].append(mosym)
                     line = file_handler.virtual_next()
             constructed_moenergies = [np.array(x, "d") for x in constructed_moenergies]
             return {moenergies.__name__: constructed_moenergies}

cclib/attribute_parsers/mosyms.py

@@ -30,11 +30,11 @@ def gaussian_normalizesym(label):
     ans = label.replace("U", "u").replace("G", "g")
     return ans
 
+
 def orca_normalizesym(label):
-        """ORCA does not require normalizing symmetry labels."""
-        return label
+    """ORCA does not require normalizing symmetry labels."""
+    return label
 
- 
 
 def qchem_parse_orbital_energies_and_symmetries(file_handler):
     """Parse the 'Orbital Energies (a.u.)' block appearing after SCF converges,
@@ -209,14 +209,10 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
             uses_symmetry = ccdata.parser_state["uses_symmetry"]
         if line[0:16] == "ORBITAL ENERGIES":
             file_handler.skip_lines(["d", "text", "text"], virtual=True)
-            #constructed_mooccnos = [[]]
-            #constructed_moenergies = [[]]
             constructed_mosyms = [[]]
             line = file_handler.virtual_next()
             while len(line) > 20:  # restricted calcs are terminated by ------
                 info = line.split()
-                #mooccno = int(float(info[1]))
-                #moenergy = float(info[2])
                 mosym = "A"
                 if uses_symmetry:
                     mosym = orca_normalizesym(info[4].split("-")[1])
@@ -226,25 +222,18 @@ def ORCA(file_handler, ccdata) -> Optional[dict]:
             # handle beta orbitals for UHF
             if line[17:35] == "SPIN DOWN ORBITALS":
                 file_handler.skip_lines(["text"], virtual=True)
-                #constructed_mooccnos.append([])
-                #constructed_moenergies.append([])
                 constructed_mosyms.append([])
                 line = file_handler.virtual_next()
                 while len(line) > 20:  # actually terminated by ------
                     info = line.split()
-                    #mooccno = int(float(info[1]))
-                    #moenergy = float(info[2])
                     mosym = "A"
                     if uses_symmetry:
                         mosym = orca_normalizesym(info[4].split("-")[1])
-                    #constructed_mooccnos[1].append(mooccno)
-                    #constructed_moenergies[1].append(moenergy)
                     constructed_mosyms[1].append(mosym)
                     line = file_handler.virtual_next()
             return {mosyms.__name__: constructed_mosyms}
         return None
 
-
     @staticmethod
     def parse(file_handler, program: str, ccdata) -> Optional[dict]:
         constructed_data = None