def read_orcaout(orca_out):
# Read lines
lines = read_file(orca_out)
# CHECK FILE IS ORCA OUT
correct = False
for line in lines:
if "This ORCA versions uses" in line:
correct = True
break
if not correct: raise Exc.FileType(Exception)
# Initialize
ch, mtp, E = None, None, None
xcc, symbols, atonums = [], [], []
# basis set
basisset = ""
try:
for line in lines:
if "utilizes the basis" in line:
basisset = line.split(":")[1]
break
except:
pass
# hamiltonian
hamiltonian = ""
try:
for idx, line in enumerate(lines):
if "Hamiltonian:" in line:
hamiltonian = lines[idx + 1].split()[-1]
break
except:
pass
# level of calculation
calclevel = hamiltonian + " " + basisset
# Get ch, mtp, E
pos = None
for idx in range(len(lines)):
line = lines[idx]
if "Total Charge Charge" in line: ch = int(line.split()[-1])
if "Multiplicity Mult" in line: mtp = int(line.split()[-1])
if "FINAL SINGLE POINT ENERGY " in line: E = float(line.split()[-1])
if "CARTESIAN COORDINATES (A.U.)" in line: pos = idx
# Get xcc, symbols, atonums
if pos is None:
sys.exit(
"Unable to find 'CARTESIAN COORDINATES (A.U.)' label in file!")
pos = pos + 3
for line in lines[pos:]:
line = line.strip()
if line == "": break
idx, symbol, atonum, dummy, mass, x, y, z = line.split()
xcc = xcc + [float(x), float(y), float(z)]
symbols.append(symbol)
atonums.append(int(atonum.split(".")[0]))
# Return
return xcc, atonums, ch, mtp, E, calclevel.strip()
def read_gtsfile(gtsfile):
lines = read_file(gtsfile)
# check extension
end_gts = (gtsfile.lower()).endswith(".gts")
if (not end_gts): raise Exc.FileType(Exception)
# CHECK FILE IS GTS
correct = False
for line in lines:
if line.startswith("start_cc"):
correct = True
break
if not correct:
exception = Exc.FileIsNotGTS(Exception)
exception._var = gtsfile
raise exception
# Read cartesian coordinates
info_cc = fncs.extract_lines(lines, "start_cc", "end_cc")
xcc, atonums = [], []
for line in info_cc:
atonum, xx, yy, zz = line.split()
xcc += [float(xx), float(yy), float(zz)]
atonums.append(int(atonum))
# Read basic information
info_basic = fncs.extract_lines(lines, "start_basic", "end_basic")
ch, mtp, E, pgroup, rotsigma = None, None, None, None, None
for line in info_basic:
if line.startswith("pointgroup"): pgroup = line.split()[1]
if line.startswith("charge"): ch = int(line.split()[1])
if line.startswith("multiplicity"): mtp = int(line.split()[1])
if line.startswith("rotsigma"): rotsigma = int(line.split()[1])
if line.startswith("energy"): E = float(line.split()[1])
# Read cartesian gradient
info_grad = fncs.extract_lines(lines, "start_grad", "end_grad")
gcc = []
for line in info_grad:
gx, gy, gz = line.split()
gcc += [float(gx), float(gy), float(gz)]
# Read Hessian matrix
info_hess = fncs.extract_lines(lines, "start_hess", "end_hess")
Fcc = []
for line in info_hess:
Fcc += [float(Fij) for Fij in line.split()]
# Read frequencies (only special cases)
info_freqs = fncs.extract_lines(lines, "start_freqs", "end_freqs")
freq_list = []
for line in info_freqs:
freq_list += [float(freqs) * CM2H for freqs in line.split()]
# Return data
masses = fncs.atonums2masses(atonums)
return xcc, atonums, ch, mtp, E, gcc, Fcc, masses, pgroup, rotsigma, freq_list
def read_gauout_old(gauout):
'''
Read Gaussian output (data in final message)
and return important data
'''
# check extension
end_out = (gauout.lower()).endswith(".out")
end_log = (gauout.lower()).endswith(".log")
if (not end_out) and (not end_log):
raise Exc.FileType(Exception)
# read lines
lines = read_file(gauout)
# CHECK FILE IS GAUSSIAN OUT
correct = False
for line in lines:
if "Entering Gaussian System" in line:
correct = True
break
if not correct: raise Exc.FileType(Exception)
# ONIOM energy?
try:
E_ONIOM = None
for line in lines[::-1]:
if "ONIOM: extrapolated energy" in line:
E_ONIOM = float(line.split()[-1])
break
except: E_ONIOM = None
# Get Forces if exists
key1 = "Forces (Hartrees/Bohr)"
key2 = "Cartesian Forces:"
try:
gcc = []
for line in extract_string(lines,key1,key2).split("\n")[3:-3]:
dummy, dummy, gx, gy, gz = line.split()
gcc += [float(gx),float(gy),float(gz)]
# forces to gradient
gcc = [-g_i for g_i in gcc]
except: gcc = None
if gcc == []: gcc = None
# Read string from gaussian output
DATA_LAST = []
DATA_WFCC = []
key1, key2 = "\GINC-","@"
strings = extract_string(lines,key1,key2,accumulate=True)
for string in strings:
lines = "".join([line.strip() for line in string.split()])
lines = lines.split("\\\\")
if lines == [""]: return None, None, None, None, None, None
# lines[3]: ch, mtp, symbols, xcc
str_geom = lines[3].split("\\")
ch , mtp = str_geom[0].split(",")
xcc = []
symbols = []
ch = int(ch)
mtp = int(mtp)
E = None
masses = []
for line in str_geom[1:]:
coords = line.split(",")
if len(coords) == 4:
symbol, x, y, z = line.split(",")
else:
symbol, tmp, x, y, z = line.split(",")
xcc += [float(x),float(y),float(z)]
symbols.append(symbol)
xcc = [xi/ANGSTROM for xi in xcc] # in bohr
# lines[4]: energy
E = float(lines[4].split("HF=")[1].split("\\")[0])
# Gradient
if gcc is None or len(gcc) == 0: gcc = [0.0 for x in xcc]
# Hessian
Fcc = []
for idx in range(len(lines)):
line = lines[idx]
if "NImag" not in line: continue
Fcc = [float(fij) for fij in lines[idx+1].split(",")]
# other lists
atonums = get_atonums(symbols)
masses = atonums2masses(atonums)
calclevel = ""
# Does it have hessian?
if Fcc != []: DATA_WFCC = [xcc, atonums, ch, mtp, E, gcc, Fcc, masses, calclevel]
# Save data
DATA_LAST = [xcc, atonums, ch, mtp, E, gcc, Fcc, masses, calclevel]
# Use ONIOM extrapolated energy if found!
if E_ONIOM is not None:
if len(DATA_WFCC) != 0: DATA_WFCC[4] = E_ONIOM
if len(DATA_LAST) != 0: DATA_LAST[4] = E_ONIOM
# return
if DATA_WFCC != []: return DATA_WFCC
else : return DATA_LAST
def read_fchk(fchkfile):
#------------------------#
# The labels to look for #
#------------------------#
labels = {} ; found_dict = {}
labels[0] = "Number of atoms" ; found_dict[0] = False
labels[1] = "Charge" ; found_dict[1] = False
labels[2] = "Multiplicity" ; found_dict[2] = False
labels[3] = "Total Energy" ; found_dict[3] = False
labels[4] = "Atomic numbers" ; found_dict[4] = False
labels[5] = "Current cartesian coordinates" ; found_dict[5] = False
labels[6] = "Real atomic weights" ; found_dict[6] = False
labels[7] = "Cartesian Gradient" ; found_dict[7] = False
labels[8] = "Cartesian Force Constants" ; found_dict[8] = False
# mandatory labels in fchk
idx_basic_labels = [0,1,2,3,4,5,6]
# initialization
natoms = None ; ch = None ; mtp = None ; E = None
atonums = [] ; masses = []
xcc = [] ; gcc = [] ; Fcc = []
# read file
lines = read_file(fchkfile)
# check extension
end_fchk = (fchkfile.lower()).endswith(".fchk")
if (not end_fchk): raise Exc.FileType(Exception)
# CHECK FILE IS FCHK
correct = False
for line in lines:
if line.startswith("Current cartesian coordinates "):
correct = True
break
if not correct: raise Exc.FileType(Exception)
# Get level of calculation
calclevel = " ".join(lines[1].split()[1:])
# get data from lines
for idx in range(len(lines)):
line = lines[idx]
# Number of atoms
if line.startswith(labels[0]):
found_dict[0] = True
natoms = int(line.split()[-1])
# Charge
elif line.startswith(labels[1]):
found_dict[1] = True
ch = int(line.split()[-1])
# Spin multiplicity
elif line.startswith(labels[2]):
found_dict[2] = True
mtp = int(line.split()[-1])
# Total Energy
elif line.startswith(labels[3]):
found_dict[3] = True
E = float(line.split()[-1])
# Atomic Numbers
elif line.startswith(labels[4]):
found_dict[4] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(atonums) != length:
nextline = lines[idx2]
atonums += [int(i) for i in nextline.split()]
idx2 += 1
# Cartesian Coordinates
elif line.startswith(labels[5]):
found_dict[5] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(xcc) != length:
nextline = lines[idx2]
xcc += [float(i) for i in nextline.split()]
idx2 += 1
# List of atomic masses
elif line.startswith(labels[6]):
found_dict[6] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(masses) != length:
nextline = lines[idx2]
masses += [float(i) for i in nextline.split()]
idx2 += 1
# Cartesian Gradient
elif line.startswith(labels[7]) and natoms != 1:
found_dict[7] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(gcc) != length:
nextline = lines[idx2]
gcc += [float(i) for i in nextline.split()]
idx2 += 1
# Cartesian Force Constant Matrix
elif line.startswith(labels[8]) and natoms != 1:
found_dict[8] = True
length = int(line.split()[-1])
idx2 = idx+1
while len(Fcc) != length:
nextline = lines[idx2]
Fcc += [float(fij) for fij in nextline.split()]
idx2 += 1
# Return data
#if gcc == []: gcc = None
#if Fcc == []: Fcc = None
return xcc,atonums,ch,mtp,E,gcc,Fcc,masses, calclevel.strip()
def read_orcaout(orca_out):
# Read lines
lines = read_file(orca_out)
# CHECK FILE IS ORCA OUT
correct = False
for line in lines:
if "This ORCA versions uses" in line:
correct = True
break
if not correct: raise Exc.FileType(Exception)
# Initialize
ch, mtp, E = None, None, None
xcc, symbols, atonums = [], [], []
# basis set
basisset = ""
try:
for line in lines:
if "utilizes the basis" in line:
basisset = line.split(":")[1]
break
except:
pass
# hamiltonian
hamiltonian = ""
try:
for idx, line in enumerate(lines):
if "Hamiltonian:" in line:
hamiltonian = lines[idx + 1].split()[-1]
break
except:
pass
# level of calculation
calclevel = hamiltonian + " " + basisset
# Get ch, mtp, E
pos_cart = None
pos_zmat = None
for idx in range(len(lines)):
line = lines[idx]
if "Total Charge Charge" in line: ch = int(line.split()[-1])
if "Multiplicity Mult" in line: mtp = int(line.split()[-1])
if "FINAL SINGLE POINT ENERGY " in line: E = float(line.split()[-1])
if "CARTESIAN COORDINATES (A.U.)" in line: pos_cart = idx
if "INTERNAL COORDINATES (ANGST" in line: pos_zmat = idx
# Get xcc, symbols, atonums
if pos_cart is None:
sys.exit(
"Unable to find 'CARTESIAN COORDINATES (A.U.)' label in file!")
pos_cart += 3
for line in lines[pos_cart:]:
line = line.strip()
if line == "": break
idx, symbol, atonum, dummy, mass, x, y, z = line.split()
if symbol == "-": symbol = "XX"
xcc += [float(x), float(y), float(z)]
symbols.append(symbol)
atonums.append(int(atonum.split(".")[0]))
# data in internal coordinates
lzmat = None
if pos_zmat is not None:
pos_zmat += 2
lzmat = []
for idx, line in enumerate(lines[pos_zmat:]):
line = line.strip()
if line == "": break
symbol, atk, atj, ati, dist, angle, dihedral = line.split()
if symbol == "-": symbol = "XX"
atk, atj, ati = int(atk) - 1, int(atj) - 1, int(ati) - 1
dist, angle, dihedral = float(dist), float(angle), float(dihedral)
if idx == 0: connections, values = (), ()
elif idx == 1: connections, values = (atk, ), (dist, )
elif idx == 2: connections, values = (atk, atj), (dist, angle)
else:
connections, values = (atk, atj, ati), (dist, angle, dihedral)
data = (symbol, connections, values)
lzmat += [data]
# Return
return xcc, lzmat, atonums, ch, mtp, E, calclevel.strip()
