def parse_xyz_from_file(path):
"""
Parse xyz coordinated from:
.xyz - XYZ file
.gjf - Gaussian input file
.out or .log - ESS output file (Gaussian, QChem, Molpro)
other - Molpro or QChem input file
"""
lines = _get_lines_from_file(path)
file_extension = os.path.splitext(path)[1]
xyz = None
relevant_lines = list()
if file_extension == '.xyz':
relevant_lines = lines[2:]
elif file_extension == '.gjf':
start_parsing = False
for line in lines:
if start_parsing and line and line != '\n' and line != '\r\n':
relevant_lines.append(line)
elif start_parsing:
break
else:
splits = line.split()
if len(splits) == 2 and all([s.isdigit() for s in splits]):
start_parsing = True
elif 'out' in file_extension or 'log' in file_extension:
log = determine_qm_software(fullpath=path)
coords, number, _ = log.loadGeometry()
xyz = get_xyz_string(coords=coords, numbers=number)
else:
record = False
for line in lines:
if '$end' in line or '}' in line:
break
if record and len(line.split()) == 4:
relevant_lines.append(line)
elif '$molecule' in line:
record = True
elif 'geometry={' in line:
record = True
if not relevant_lines:
raise ParserError(
'Could not parse xyz coordinates from file {0}'.format(path))
if xyz is None and relevant_lines:
xyz = ''.join([line for line in relevant_lines if line])
return standardize_xyz_string(xyz)
def test_standardize_xyz_string(self):
"""Test the standardize_xyz_string function"""
xyz = """
C -0.67567701 1.18507660 0.04672449
H -0.25592948 1.62415961 0.92757746
H -2.26870864 1.38030564 0.05865317
O -0.36671999 -0.21081064 0.01630374
H -0.73553821 -0.63718986 0.79332805
C -0.08400571 1.86907236 -1.19973252
H -0.50375517 1.42998100 -2.08057962
H -0.31518819 2.91354759 -1.17697025
H 0.97802159 1.73893214 -1.20769117
O -3.69788377 1.55609096 0.07050345
O -4.28667752 0.37487691 0.04916102
H -4.01978712 -0.12970163 0.82103635
"""
expected_xyz = """ C -0.67567701 1.18507660 0.04672449
H -0.25592948 1.62415961 0.92757746
H -2.26870864 1.38030564 0.05865317
O -0.36671999 -0.21081064 0.01630374
H -0.73553821 -0.63718986 0.79332805
C -0.08400571 1.86907236 -1.19973252
H -0.50375517 1.42998100 -2.08057962
H -0.31518819 2.91354759 -1.17697025
H 0.97802159 1.73893214 -1.20769117
O -3.69788377 1.55609096 0.07050345
O -4.28667752 0.37487691 0.04916102
H -4.01978712 -0.12970163 0.82103635"""
new_xyz = converter.standardize_xyz_string(xyz)
self.assertEqual(new_xyz, expected_xyz)
gaussian_format = """
1 8 0 3.132319 0.769111 -0.080869
2 8 0 3.387436 -2.116759 -0.038585
3 6 0 -2.369193 -0.546956 0.566827
4 6 0 -3.153606 0.171059 1.663074
5 6 0 -2.728027 -2.026445 0.459268
6 6 0 2.331560 -1.734235 -0.921481
7 6 0 3.650113 2.049169 0.275835
8 6 0 -0.931216 -0.186900 0.428193
9 6 0 1.352858 -0.755151 -0.308464
10 6 0 1.794338 0.522302 0.098410
11 6 0 0.011593 -1.079560 -0.135497
12 6 0 -0.448289 1.082102 0.804298
13 6 0 0.893169 1.436443 0.649904
14 1 0 -2.891135 -0.053945 -0.499139
15 1 0 2.748799 -1.311472 -1.847528
16 1 0 1.809915 -2.658319 -1.182148
17 1 0 -3.112208 1.258826 1.567630
18 1 0 -4.207732 -0.116551 1.619167
19 1 0 -2.768847 -0.097847 2.656934
20 1 0 -2.294986 -2.598417 1.292175
21 1 0 -3.813897 -2.151504 0.498488
22 1 0 -2.382172 -2.478656 -0.474306
23 1 0 3.525166 2.241957 1.347801
24 1 0 4.712607 2.018400 0.032537
25 1 0 3.166236 2.845374 -0.301663
26 1 0 -0.305960 -2.070003 -0.442894
27 1 0 -1.122381 1.816000 1.229392
28 1 0 1.217512 2.421293 0.964523
29 1 0 3.889221 -1.315416 0.166971
30 8 0 -3.433048 0.461721 -1.530756
31 8 0 -2.894879 1.761778 -1.591557
32 1 0 -2.124573 1.652495 -2.176005
"""
expected_xyz = """O 3.132319 0.769111 -0.080869
O 3.387436 -2.116759 -0.038585
C -2.369193 -0.546956 0.566827
C -3.153606 0.171059 1.663074
C -2.728027 -2.026445 0.459268
C 2.331560 -1.734235 -0.921481
C 3.650113 2.049169 0.275835
C -0.931216 -0.186900 0.428193
C 1.352858 -0.755151 -0.308464
C 1.794338 0.522302 0.098410
C 0.011593 -1.079560 -0.135497
C -0.448289 1.082102 0.804298
C 0.893169 1.436443 0.649904
H -2.891135 -0.053945 -0.499139
H 2.748799 -1.311472 -1.847528
H 1.809915 -2.658319 -1.182148
H -3.112208 1.258826 1.567630
H -4.207732 -0.116551 1.619167
H -2.768847 -0.097847 2.656934
H -2.294986 -2.598417 1.292175
H -3.813897 -2.151504 0.498488
H -2.382172 -2.478656 -0.474306
H 3.525166 2.241957 1.347801
H 4.712607 2.018400 0.032537
H 3.166236 2.845374 -0.301663
H -0.305960 -2.070003 -0.442894
H -1.122381 1.816000 1.229392
H 1.217512 2.421293 0.964523
H 3.889221 -1.315416 0.166971
O -3.433048 0.461721 -1.530756
O -2.894879 1.761778 -1.591557
H -2.124573 1.652495 -2.176005"""
new_xyz = converter.standardize_xyz_string(gaussian_format)
self.assertEqual(new_xyz, expected_xyz)