/usr/share/pyshared/cclib/parser/gaussianparser.py is in python-cclib 1.1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 | # This file is part of cclib (http://cclib.sf.net), a library for parsing
# and interpreting the results of computational chemistry packages.
#
# Copyright (C) 2006, the cclib development team
#
# The library is free software, distributed under the terms of
# the GNU Lesser General Public version 2.1 or later. You should have
# received a copy of the license along with cclib. You can also access
# the full license online at http://www.gnu.org/copyleft/lgpl.html.
__revision__ = "$Revision: 1026 $"
import re
import numpy
import logfileparser
import utils
class Gaussian(logfileparser.Logfile):
"""A Gaussian 98/03 log file."""
def __init__(self, *args, **kwargs):
# Call the __init__ method of the superclass
super(Gaussian, self).__init__(logname="Gaussian", *args, **kwargs)
def __str__(self):
"""Return a string representation of the object."""
return "Gaussian log file %s" % (self.filename)
def __repr__(self):
"""Return a representation of the object."""
return 'Gaussian("%s")' % (self.filename)
def normalisesym(self, label):
"""Use standard symmetry labels instead of Gaussian labels.
To normalise:
(1) If label is one of [SG, PI, PHI, DLTA], replace by [sigma, pi, phi, delta]
(2) replace any G or U by their lowercase equivalent
>>> sym = Gaussian("dummyfile").normalisesym
>>> labels = ['A1', 'AG', 'A1G', "SG", "PI", "PHI", "DLTA", 'DLTU', 'SGG']
>>> map(sym, labels)
['A1', 'Ag', 'A1g', 'sigma', 'pi', 'phi', 'delta', 'delta.u', 'sigma.g']
"""
# note: DLT must come after DLTA
greek = [('SG', 'sigma'), ('PI', 'pi'), ('PHI', 'phi'),
('DLTA', 'delta'), ('DLT', 'delta')]
for k, v in greek:
if label.startswith(k):
tmp = label[len(k):]
label = v
if tmp:
label = v + "." + tmp
ans = label.replace("U", "u").replace("G", "g")
return ans
def before_parsing(self):
# Used to index self.scftargets[].
SCFRMS, SCFMAX, SCFENERGY = range(3)
# Flag that indicates whether it has reached the end of a geoopt.
self.optfinished = False
# Flag for identifying Coupled Cluster runs.
self.coupledcluster = False
# Fragment number for counterpoise or fragment guess calculations
# (normally zero).
self.counterpoise = 0
# Flag for identifying ONIOM calculations.
self.oniom = False
def after_parsing(self):
# Correct the percent values in the etsecs in the case of
# a restricted calculation. The following has the
# effect of including each transition twice.
if hasattr(self, "etsecs") and len(self.homos) == 1:
new_etsecs = [[(x[0], x[1], x[2] * numpy.sqrt(2)) for x in etsec]
for etsec in self.etsecs]
self.etsecs = new_etsecs
if hasattr(self, "scanenergies"):
self.scancoords = []
self.scancoords = self.atomcoords
if (hasattr(self, 'enthaply') and hasattr(self, 'temperature')
and hasattr(self, 'freeenergy')):
self.entropy = (self.enthaply - self.freeenergy)/self.temperature
def extract(self, inputfile, line):
"""Extract information from the file object inputfile."""
#Extract PES scan data
#Summary of the potential surface scan:
# N A SCF
#---- --------- -----------
# 1 109.0000 -76.43373
# 2 119.0000 -76.43011
# 3 129.0000 -76.42311
# 4 139.0000 -76.41398
# 5 149.0000 -76.40420
# 6 159.0000 -76.39541
# 7 169.0000 -76.38916
# 8 179.0000 -76.38664
# 9 189.0000 -76.38833
# 10 199.0000 -76.39391
# 11 209.0000 -76.40231
#---- --------- -----------
if "Summary of the potential surface scan:" in line:
scanenergies = []
scanparm = []
colmnames = inputfile.next()
hyphens = inputfile.next()
line = inputfile.next()
while line != hyphens:
broken = line.split()
scanenergies.append(float(broken[-1]))
scanparm.append(map(float, broken[1:-1]))
line = inputfile.next()
if not hasattr(self, "scanenergies"):
self.scanenergies = []
self.scanenergies = scanenergies
if not hasattr(self, "scanparm"):
self.scanparm = []
self.scanparm = scanparm
if not hasattr(self, "scannames"):
self.scannames = colmnames.split()[1:-1]
#Extract Thermochemistry
#Temperature 298.150 Kelvin. Pressure 1.00000 Atm.
#Zero-point correction= 0.342233 (Hartree/
#Thermal correction to Energy= 0.
#Thermal correction to Enthalpy= 0.
#Thermal correction to Gibbs Free Energy= 0.302940
#Sum of electronic and zero-point Energies= -563.649744
#Sum of electronic and thermal Energies= -563.636699
#Sum of electronic and thermal Enthalpies= -563.635755
#Sum of electronic and thermal Free Energies= -563.689037
if "Sum of electronic and thermal Enthalpies" in line:
if not hasattr(self, 'enthaply'):
self.enthaply = float(line.split()[6])
if "Sum of electronic and thermal Free Energies=" in line:
if not hasattr(self, 'freeenergy'):
self.freeenergy = float(line.split()[7])
if line[1:12] == "Temperature":
if not hasattr(self, 'temperature'):
self.temperature = float(line.split()[1])
# Number of atoms.
if line[1:8] == "NAtoms=":
self.updateprogress(inputfile, "Attributes", self.fupdate)
natom = int(line.split()[1])
if not hasattr(self, "natom"):
self.natom = natom
# Catch message about completed optimization.
if line[1:23] == "Optimization completed":
self.optfinished = True
self.optdone = True
# Extract the atomic numbers and coordinates from the input orientation,
# in the event the standard orientation isn't available.
if not self.optfinished and line.find("Input orientation") > -1 or line.find("Z-Matrix orientation") > -1:
# If this is a counterpoise calculation, this output means that
# the supermolecule is now being considered, so we can set:
self.counterpoise = 0
self.updateprogress(inputfile, "Attributes", self.cupdate)
if not hasattr(self, "inputcoords"):
self.inputcoords = []
self.inputatoms = []
hyphens = inputfile.next()
colmNames = inputfile.next()
colmNames = inputfile.next()
hyphens = inputfile.next()
atomcoords = []
line = inputfile.next()
while line != hyphens:
broken = line.split()
self.inputatoms.append(int(broken[1]))
atomcoords.append(map(float, broken[3:6]))
line = inputfile.next()
self.inputcoords.append(atomcoords)
if not hasattr(self, "atomnos"):
self.atomnos = numpy.array(self.inputatoms, 'i')
self.natom = len(self.atomnos)
# Extract the atomic masses.
# Typical section:
# Isotopes and Nuclear Properties:
#(Nuclear quadrupole moments (NQMom) in fm**2, nuclear magnetic moments (NMagM)
# in nuclear magnetons)
#
# Atom 1 2 3 4 5 6 7 8 9 10
# IAtWgt= 12 12 12 12 12 1 1 1 12 12
# AtmWgt= 12.0000000 12.0000000 12.0000000 12.0000000 12.0000000 1.0078250 1.0078250 1.0078250 12.0000000 12.0000000
# NucSpn= 0 0 0 0 0 1 1 1 0 0
# AtZEff= -3.6000000 -3.6000000 -3.6000000 -3.6000000 -3.6000000 -1.0000000 -1.0000000 -1.0000000 -3.6000000 -3.6000000
# NQMom= 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000
# NMagM= 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 2.7928460 2.7928460 2.7928460 0.0000000 0.0000000
# ... with blank lines dividing blocks of ten, and Leave Link 101 at the end.
# This is generally parsed before coordinates, so atomnos is not defined.
# Note that in Gaussian03 the comments are not there yet and the labels are different.
if line.strip() == "Isotopes and Nuclear Properties:":
if not hasattr(self, "atommasses"):
self.atommasses = []
line = inputfile.next()
while line[1:16] != "Leave Link 101":
if line[1:8] == "AtmWgt=":
self.atommasses.extend(map(float, line.split()[1:]))
line = inputfile.next()
# Extract the atomic numbers and coordinates of the atoms.
if not self.optfinished and line.strip() == "Standard orientation:":
self.updateprogress(inputfile, "Attributes", self.cupdate)
# If this is a counterpoise calculation, this output means that
# the supermolecule is now being considered, so we can set:
self.counterpoise = 0
if not hasattr(self, "atomcoords"):
self.atomcoords = []
hyphens = inputfile.next()
colmNames = inputfile.next()
colmNames = inputfile.next()
hyphens = inputfile.next()
atomnos = []
atomcoords = []
line = inputfile.next()
while line != hyphens:
broken = line.split()
atomnos.append(int(broken[1]))
atomcoords.append(map(float, broken[-3:]))
line = inputfile.next()
self.atomcoords.append(atomcoords)
if not hasattr(self, "natom"):
self.atomnos = numpy.array(atomnos, 'i')
self.natom = len(self.atomnos)
# make sure atomnos is added for the case where natom has already been set
elif not hasattr(self, "atomnos"):
self.atomnos = numpy.array(atomnos, 'i')
# Find the targets for SCF convergence (QM calcs).
if line[1:44] == 'Requested convergence on RMS density matrix':
if not hasattr(self, "scftargets"):
self.scftargets = []
# The following can happen with ONIOM which are mixed SCF
# and semi-empirical
if type(self.scftargets) == type(numpy.array([])):
self.scftargets = []
scftargets = []
# The RMS density matrix.
scftargets.append(self.float(line.split('=')[1].split()[0]))
line = inputfile.next()
# The MAX density matrix.
scftargets.append(self.float(line.strip().split('=')[1][:-1]))
line = inputfile.next()
# For G03, there's also the energy (not for G98).
if line[1:10] == "Requested":
scftargets.append(self.float(line.strip().split('=')[1][:-1]))
self.scftargets.append(scftargets)
# Extract SCF convergence information (QM calcs).
if line[1:10] == 'Cycle 1':
if not hasattr(self, "scfvalues"):
self.scfvalues = []
scfvalues = []
line = inputfile.next()
while line.find("SCF Done") == -1:
self.updateprogress(inputfile, "QM convergence", self.fupdate)
if line.find(' E=') == 0:
self.logger.debug(line)
# RMSDP=3.74D-06 MaxDP=7.27D-05 DE=-1.73D-07 OVMax= 3.67D-05
# or
# RMSDP=1.13D-05 MaxDP=1.08D-04 OVMax= 1.66D-04
if line.find(" RMSDP") == 0:
parts = line.split()
newlist = [self.float(x.split('=')[1]) for x in parts[0:2]]
energy = 1.0
if len(parts) > 4:
energy = parts[2].split('=')[1]
if energy == "":
energy = self.float(parts[3])
else:
energy = self.float(energy)
if len(self.scftargets[0]) == 3: # Only add the energy if it's a target criteria
newlist.append(energy)
scfvalues.append(newlist)
try:
line = inputfile.next()
# May be interupted by EOF.
except StopIteration:
break
self.scfvalues.append(scfvalues)
# Extract SCF convergence information (AM1 calcs).
if line[1:4] == 'It=':
self.scftargets = numpy.array([1E-7], "d") # This is the target value for the rms
self.scfvalues = [[]]
line = inputfile.next()
while line.find(" Energy") == -1:
if self.progress:
step = inputfile.tell()
if step != oldstep:
self.progress.update(step, "AM1 Convergence")
oldstep = step
if line[1:4] == "It=":
parts = line.strip().split()
self.scfvalues[0].append(self.float(parts[-1][:-1]))
line = inputfile.next()
# Note: this needs to follow the section where 'SCF Done' is used
# to terminate a loop when extracting SCF convergence information.
if line[1:9] == 'SCF Done':
if not hasattr(self, "scfenergies"):
self.scfenergies = []
self.scfenergies.append(utils.convertor(self.float(line.split()[4]), "hartree", "eV"))
# gmagoon 5/27/09: added scfenergies reading for PM3 case
# Example line: " Energy= -0.077520562724 NIter= 14."
# See regression Gaussian03/QVGXLLKOCUKJST-UHFFFAOYAJmult3Fixed.out
if line[1:8] == 'Energy=':
if not hasattr(self, "scfenergies"):
self.scfenergies = []
self.scfenergies.append(utils.convertor(self.float(line.split()[1]), "hartree", "eV"))
# Total energies after Moller-Plesset corrections.
# Second order correction is always first, so its first occurance
# triggers creation of mpenergies (list of lists of energies).
# Further MP2 corrections are appended as found.
#
# Example MP2 output line:
# E2 = -0.9505918144D+00 EUMP2 = -0.28670924198852D+03
# Warning! this output line is subtly different for MP3/4/5 runs
if "EUMP2" in line[27:34]:
if not hasattr(self, "mpenergies"):
self.mpenergies = []
self.mpenergies.append([])
mp2energy = self.float(line.split("=")[2])
self.mpenergies[-1].append(utils.convertor(mp2energy, "hartree", "eV"))
# Example MP3 output line:
# E3= -0.10518801D-01 EUMP3= -0.75012800924D+02
if line[34:39] == "EUMP3":
mp3energy = self.float(line.split("=")[2])
self.mpenergies[-1].append(utils.convertor(mp3energy, "hartree", "eV"))
# Example MP4 output lines:
# E4(DQ)= -0.31002157D-02 UMP4(DQ)= -0.75015901139D+02
# E4(SDQ)= -0.32127241D-02 UMP4(SDQ)= -0.75016013648D+02
# E4(SDTQ)= -0.32671209D-02 UMP4(SDTQ)= -0.75016068045D+02
# Energy for most substitutions is used only (SDTQ by default)
if line[34:42] == "UMP4(DQ)":
mp4energy = self.float(line.split("=")[2])
line = inputfile.next()
if line[34:43] == "UMP4(SDQ)":
mp4energy = self.float(line.split("=")[2])
line = inputfile.next()
if line[34:44] == "UMP4(SDTQ)":
mp4energy = self.float(line.split("=")[2])
self.mpenergies[-1].append(utils.convertor(mp4energy, "hartree", "eV"))
# Example MP5 output line:
# DEMP5 = -0.11048812312D-02 MP5 = -0.75017172926D+02
if line[29:32] == "MP5":
mp5energy = self.float(line.split("=")[2])
self.mpenergies[-1].append(utils.convertor(mp5energy, "hartree", "eV"))
# Total energies after Coupled Cluster corrections.
# Second order MBPT energies (MP2) are also calculated for these runs,
# but the output is the same as when parsing for mpenergies.
# Read the consecutive correlated energies
# but append only the last one to ccenergies.
# Only the highest level energy is appended - ex. CCSD(T), not CCSD.
if line[1:10] == "DE(Corr)=" and line[27:35] == "E(CORR)=":
self.ccenergy = self.float(line.split()[3])
if line[1:10] == "T5(CCSD)=":
line = inputfile.next()
if line[1:9] == "CCSD(T)=":
self.ccenergy = self.float(line.split()[1])
if line[12:53] == "Population analysis using the SCF density":
if hasattr(self, "ccenergy"):
if not hasattr(self, "ccenergies"):
self.ccenergies = []
self.ccenergies.append(utils.convertor(self.ccenergy, "hartree", "eV"))
del self.ccenergy
# Geometry convergence information.
if line[49:59] == 'Converged?':
if not hasattr(self, "geotargets"):
self.geovalues = []
self.geotargets = numpy.array([0.0, 0.0, 0.0, 0.0], "d")
newlist = [0]*4
for i in range(4):
line = inputfile.next()
self.logger.debug(line)
parts = line.split()
try:
value = self.float(parts[2])
except ValueError:
self.logger.error("Problem parsing the value for geometry optimisation: %s is not a number." % parts[2])
else:
newlist[i] = value
self.geotargets[i] = self.float(parts[3])
self.geovalues.append(newlist)
# Gradients.
# Read in the cartesian energy gradients (forces) from a block like this:
# -------------------------------------------------------------------
# Center Atomic Forces (Hartrees/Bohr)
# Number Number X Y Z
# -------------------------------------------------------------------
# 1 1 -0.012534744 -0.021754635 -0.008346094
# 2 6 0.018984731 0.032948887 -0.038003451
# 3 1 -0.002133484 -0.006226040 0.023174772
# 4 1 -0.004316502 -0.004968213 0.023174772
# -2 -0.001830728 -0.000743108 -0.000196625
# ------------------------------------------------------------------
#
# The "-2" line is for a dummy atom
#
# Then optimization is done in internal coordinates, Gaussian also
# print the forces in internal coordinates, which can be produced from
# the above. This block looks like this:
# Variable Old X -DE/DX Delta X Delta X Delta X New X
# (Linear) (Quad) (Total)
# ch 2.05980 0.01260 0.00000 0.01134 0.01134 2.07114
# hch 1.75406 0.09547 0.00000 0.24861 0.24861 2.00267
# hchh 2.09614 0.01261 0.00000 0.16875 0.16875 2.26489
# Item Value Threshold Converged?
if line[37:43] == "Forces":
if not hasattr(self, "grads"):
self.grads = []
header = inputfile.next()
dashes = inputfile.next()
line = inputfile.next()
forces = []
while line != dashes:
broken = line.split()
Fx, Fy, Fz = broken[-3:]
forces.append([float(Fx), float(Fy), float(Fz)])
line = inputfile.next()
self.grads.append(forces)
# Charge and multiplicity.
# If counterpoise correction is used, multiple lines match.
# The first one contains charge/multiplicity of the whole molecule.:
# Charge = 0 Multiplicity = 1 in supermolecule
# Charge = 0 Multiplicity = 1 in fragment 1.
# Charge = 0 Multiplicity = 1 in fragment 2.
if line[1:7] == 'Charge' and line.find("Multiplicity")>=0:
regex = ".*=(.*)Mul.*=\s*-?(\d+).*"
match = re.match(regex, line)
assert match, "Something unusual about the line: '%s'" % line
if not hasattr(self, "charge"):
self.charge = int(match.groups()[0])
if not hasattr(self, "mult"):
self.mult = int(match.groups()[1])
# Orbital symmetries.
if line[1:20] == 'Orbital symmetries:' and not hasattr(self, "mosyms"):
# For counterpoise fragments, skip these lines.
if self.counterpoise != 0: return
self.updateprogress(inputfile, "MO Symmetries", self.fupdate)
self.mosyms = [[]]
line = inputfile.next()
unres = False
if line.find("Alpha Orbitals") == 1:
unres = True
line = inputfile.next()
i = 0
while len(line) > 18 and line[17] == '(':
if line.find('Virtual') >= 0:
self.homos = numpy.array([i-1], "i") # 'HOMO' indexes the HOMO in the arrays
parts = line[17:].split()
for x in parts:
self.mosyms[0].append(self.normalisesym(x.strip('()')))
i += 1
line = inputfile.next()
if unres:
line = inputfile.next()
# Repeat with beta orbital information
i = 0
self.mosyms.append([])
while len(line) > 18 and line[17] == '(':
if line.find('Virtual')>=0:
# Here we consider beta
# If there was also an alpha virtual orbital,
# we will store two indices in the array
# Otherwise there is no alpha virtual orbital,
# only beta virtual orbitals, and we initialize
# the array with one element. See the regression
# QVGXLLKOCUKJST-UHFFFAOYAJmult3Fixed.out
# donated by Gregory Magoon (gmagoon).
if (hasattr(self, "homos")):
# Extend the array to two elements
# 'HOMO' indexes the HOMO in the arrays
self.homos.resize([2])
self.homos[1] = i-1
else:
# 'HOMO' indexes the HOMO in the arrays
self.homos = numpy.array([i-1], "i")
parts = line[17:].split()
for x in parts:
self.mosyms[1].append(self.normalisesym(x.strip('()')))
i += 1
line = inputfile.next()
# Alpha/Beta electron eigenvalues.
if line[1:6] == "Alpha" and line.find("eigenvalues") >= 0:
# For counterpoise fragments, skip these lines.
if self.counterpoise != 0: return
# For ONIOM calcs, ignore this section in order to bypass assertion failure.
if self.oniom: return
self.updateprogress(inputfile, "Eigenvalues", self.fupdate)
self.moenergies = [[]]
HOMO = -2
while line.find('Alpha') == 1:
if line.split()[1] == "virt." and HOMO == -2:
# If there aren't any symmetries, this is a good way to find the HOMO.
# Also, check for consistency if homos was already parsed.
HOMO = len(self.moenergies[0])-1
if hasattr(self, "homos"):
assert HOMO == self.homos[0]
else:
self.homos = numpy.array([HOMO], "i")
# Convert to floats and append to moenergies, but sometimes Gaussian
# doesn't print correctly so test for ValueError (bug 1756789).
part = line[28:]
i = 0
while i*10+4 < len(part):
s = part[i*10:(i+1)*10]
try:
x = self.float(s)
except ValueError:
x = numpy.nan
self.moenergies[0].append(utils.convertor(x, "hartree", "eV"))
i += 1
line = inputfile.next()
# If, at this point, self.homos is unset, then there were not
# any alpha virtual orbitals
if not hasattr(self, "homos"):
HOMO = len(self.moenergies[0])-1
self.homos = numpy.array([HOMO], "i")
if line.find('Beta') == 2:
self.moenergies.append([])
HOMO = -2
while line.find('Beta') == 2:
if line.split()[1] == "virt." and HOMO == -2:
# If there aren't any symmetries, this is a good way to find the HOMO.
# Also, check for consistency if homos was already parsed.
HOMO = len(self.moenergies[1])-1
if len(self.homos) == 2:
assert HOMO == self.homos[1]
else:
self.homos.resize([2])
self.homos[1] = HOMO
part = line[28:]
i = 0
while i*10+4 < len(part):
x = part[i*10:(i+1)*10]
self.moenergies[1].append(utils.convertor(self.float(x), "hartree", "eV"))
i += 1
line = inputfile.next()
self.moenergies = [numpy.array(x, "d") for x in self.moenergies]
# Gaussian Rev <= B.0.3 (?)
# AO basis set in the form of general basis input:
# 1 0
# S 3 1.00 0.000000000000
# 0.7161683735D+02 0.1543289673D+00
# 0.1304509632D+02 0.5353281423D+00
# 0.3530512160D+01 0.4446345422D+00
# SP 3 1.00 0.000000000000
# 0.2941249355D+01 -0.9996722919D-01 0.1559162750D+00
# 0.6834830964D+00 0.3995128261D+00 0.6076837186D+00
# 0.2222899159D+00 0.7001154689D+00 0.3919573931D+00
if line[1:16] == "AO basis set in":
# For counterpoise fragment calcualtions, skip these lines.
if self.counterpoise != 0: return
self.gbasis = []
line = inputfile.next()
while line.strip():
gbasis = []
line = inputfile.next()
while line.find("*")<0:
temp = line.split()
symtype = temp[0]
numgau = int(temp[1])
gau = []
for i in range(numgau):
temp = map(self.float, inputfile.next().split())
gau.append(temp)
for i, x in enumerate(symtype):
newgau = [(z[0], z[i+1]) for z in gau]
gbasis.append((x, newgau))
line = inputfile.next() # i.e. "****" or "SP ...."
self.gbasis.append(gbasis)
line = inputfile.next() # i.e. "20 0" or blank line
# Start of the IR/Raman frequency section.
# Caution is advised here, as additional frequency blocks
# can be printed by Gaussian (with slightly different formats),
# often doubling the information printed.
# See, for a non-standard exmaple, regression Gaussian98/test_H2.log
if line[1:14] == "Harmonic freq":
self.updateprogress(inputfile, "Frequency Information", self.fupdate)
removeold = False
# The whole block should not have any blank lines.
while line.strip() != "":
# The line with indices
if line[1:15].strip() == "" and line[15:22].strip().isdigit():
freqbase = int(line[15:22])
if freqbase == 1 and hasattr(self, 'vibfreqs'):
# This is a reparse of this information
removeold = True
# Lines with symmetries and symm. indices begin with whitespace.
if line[1:15].strip() == "" and not line[15:22].strip().isdigit():
if not hasattr(self, 'vibsyms'):
self.vibsyms = []
syms = line.split()
self.vibsyms.extend(syms)
if line[1:15] == "Frequencies --":
if not hasattr(self, 'vibfreqs'):
self.vibfreqs = []
if removeold: # This is a reparse, so throw away the old info
if hasattr(self, "vibsyms"):
# We have already parsed the vibsyms so don't throw away!
self.vibsyms = self.vibsyms[-len(line[15:].split()):]
if hasattr(self, "vibirs"):
self.vibirs = []
if hasattr(self, 'vibfreqs'):
self.vibfreqs = []
if hasattr(self, 'vibramans'):
self.vibramans = []
if hasattr(self, 'vibdisps'):
self.vibdisps = []
removeold = False
freqs = [self.float(f) for f in line[15:].split()]
self.vibfreqs.extend(freqs)
if line[1:15] == "IR Inten --":
if not hasattr(self, 'vibirs'):
self.vibirs = []
irs = [self.float(f) for f in line[15:].split()]
self.vibirs.extend(irs)
if line[1:15] == "Raman Activ --":
if not hasattr(self, 'vibramans'):
self.vibramans = []
ramans = [self.float(f) for f in line[15:].split()]
self.vibramans.extend(ramans)
# Block with displacement should start with this.
if line.strip().split()[0:3] == ["Atom", "AN", "X"]:
if not hasattr(self, 'vibdisps'):
self.vibdisps = []
disps = []
for n in range(self.natom):
line = inputfile.next()
numbers = [float(s) for s in line[10:].split()]
N = len(numbers) / 3
if not disps:
for n in range(N):
disps.append([])
for n in range(N):
disps[n].append(numbers[3*n:3*n+3])
self.vibdisps.extend(disps)
line = inputfile.next()
# Below is the old code for the IR/Raman frequency block, can probably be removed.
# while len(line[:15].split()) == 0:
# self.logger.debug(line)
# self.vibsyms.extend(line.split()) # Adding new symmetry
# line = inputfile.next()
# # Read in frequencies.
# freqs = [self.float(f) for f in line.split()[2:]]
# self.vibfreqs.extend(freqs)
# line = inputfile.next()
# line = inputfile.next()
# line = inputfile.next()
# irs = [self.float(f) for f in line.split()[3:]]
# self.vibirs.extend(irs)
# line = inputfile.next() # Either the header or a Raman line
# if line.find("Raman") >= 0:
# if not hasattr(self, "vibramans"):
# self.vibramans = []
# ramans = [self.float(f) for f in line.split()[3:]]
# self.vibramans.extend(ramans)
# line = inputfile.next() # Depolar (P)
# line = inputfile.next() # Depolar (U)
# line = inputfile.next() # Header
# line = inputfile.next() # First line of cartesian displacement vectors
# p = [[], [], []]
# while len(line[:15].split()) > 0:
# # Store the cartesian displacement vectors
# broken = map(float, line.strip().split()[2:])
# for i in range(0, len(broken), 3):
# p[i/3].append(broken[i:i+3])
# line = inputfile.next()
# self.vibdisps.extend(p[0:len(broken)/3])
# line = inputfile.next() # Should be the line with symmetries
# self.vibfreqs = numpy.array(self.vibfreqs, "d")
# self.vibirs = numpy.array(self.vibirs, "d")
# self.vibdisps = numpy.array(self.vibdisps, "d")
# if hasattr(self, "vibramans"):
# self.vibramans = numpy.array(self.vibramans, "d")
# Electronic transitions.
if line[1:14] == "Excited State":
if not hasattr(self, "etenergies"):
self.etenergies = []
self.etoscs = []
self.etsyms = []
self.etsecs = []
# Need to deal with lines like:
# (restricted calc)
# Excited State 1: Singlet-BU 5.3351 eV 232.39 nm f=0.1695
# (unrestricted calc) (first excited state is 2!)
# Excited State 2: ?Spin -A 0.1222 eV 10148.75 nm f=0.0000
# (Gaussian 09 ZINDO)
# Excited State 1: Singlet-?Sym 2.5938 eV 478.01 nm f=0.0000 <S**2>=0.000
p = re.compile(":(?P<sym>.*?)(?P<energy>-?\d*\.\d*) eV")
groups = p.search(line).groups()
self.etenergies.append(utils.convertor(self.float(groups[1]), "eV", "cm-1"))
self.etoscs.append(self.float(line.split("f=")[-1].split()[0]))
self.etsyms.append(groups[0].strip())
line = inputfile.next()
p = re.compile("(\d+)")
CIScontrib = []
while line.find(" ->") >= 0: # This is a contribution to the transition
parts = line.split("->")
self.logger.debug(parts)
# Has to deal with lines like:
# 32 -> 38 0.04990
# 35A -> 45A 0.01921
frommoindex = 0 # For restricted or alpha unrestricted
fromMO = parts[0].strip()
if fromMO[-1] == "B":
frommoindex = 1 # For beta unrestricted
fromMO = int(p.match(fromMO).group())-1 # subtract 1 so that it is an index into moenergies
t = parts[1].split()
tomoindex = 0
toMO = t[0]
if toMO[-1] == "B":
tomoindex = 1
toMO = int(p.match(toMO).group())-1 # subtract 1 so that it is an index into moenergies
percent = self.float(t[1])
# For restricted calculations, the percentage will be corrected
# after parsing (see after_parsing() above).
CIScontrib.append([(fromMO, frommoindex), (toMO, tomoindex), percent])
line = inputfile.next()
self.etsecs.append(CIScontrib)
# Circular dichroism data (different for G03 vs G09)
# G03
## <0|r|b> * <b|rxdel|0> (Au), Rotatory Strengths (R) in
## cgs (10**-40 erg-esu-cm/Gauss)
## state X Y Z R(length)
## 1 0.0006 0.0096 -0.0082 -0.4568
## 2 0.0251 -0.0025 0.0002 -5.3846
## 3 0.0168 0.4204 -0.3707 -15.6580
## 4 0.0721 0.9196 -0.9775 -3.3553
# G09
## 1/2[<0|r|b>*<b|rxdel|0> + (<0|rxdel|b>*<b|r|0>)*]
## Rotatory Strengths (R) in cgs (10**-40 erg-esu-cm/Gauss)
## state XX YY ZZ R(length) R(au)
## 1 -0.3893 -6.7546 5.7736 -0.4568 -0.0010
## 2 -17.7437 1.7335 -0.1435 -5.3845 -0.0114
## 3 -11.8655 -297.2604 262.1519 -15.6580 -0.0332
if (line[1:52] == "<0|r|b> * <b|rxdel|0> (Au), Rotatory Strengths (R)" or
line[1:50] == "1/2[<0|r|b>*<b|rxdel|0> + (<0|rxdel|b>*<b|r|0>)*]"):
self.etrotats = []
inputfile.next() # Units
headers = inputfile.next() # Headers
Ncolms = len(headers.split())
line = inputfile.next()
parts = line.strip().split()
while len(parts) == Ncolms:
try:
R = self.float(parts[4])
except ValueError:
# nan or -nan if there is no first excited state
# (for unrestricted calculations)
pass
else:
self.etrotats.append(R)
line = inputfile.next()
temp = line.strip().split()
parts = line.strip().split()
self.etrotats = numpy.array(self.etrotats, "d")
# Number of basis sets functions.
# Has to deal with lines like:
# NBasis = 434 NAE= 97 NBE= 97 NFC= 34 NFV= 0
# and...
# NBasis = 148 MinDer = 0 MaxDer = 0
# Although the former is in every file, it doesn't occur before
# the overlap matrix is printed.
if line[1:7] == "NBasis" or line[4:10] == "NBasis":
# For counterpoise fragment, skip these lines.
if self.counterpoise != 0: return
# For ONIOM calcs, ignore this section in order to bypass assertion failure.
if self.oniom: return
# If nbasis was already parsed, check if it changed.
nbasis = int(line.split('=')[1].split()[0])
if hasattr(self, "nbasis"):
assert nbasis == self.nbasis
else:
self.nbasis = nbasis
# Number of linearly-independent basis sets.
if line[1:7] == "NBsUse":
# For counterpoise fragment, skip these lines.
if self.counterpoise != 0: return
# For ONIOM calcs, ignore this section in order to bypass assertion failure.
if self.oniom: return
nmo = int(line.split('=')[1].split()[0])
if hasattr(self, "nmo"):
assert nmo == self.nmo
else:
self.nmo = nmo
# For AM1 calculations, set nbasis by a second method,
# as nmo may not always be explicitly stated.
if line[7:22] == "basis functions, ":
nbasis = int(line.split()[0])
if hasattr(self, "nbasis"):
assert nbasis == self.nbasis
else:
self.nbasis = nbasis
# Molecular orbital overlap matrix.
# Has to deal with lines such as:
# *** Overlap ***
# ****** Overlap ******
# Note that Gaussian sometimes drops basis functions,
# causing the overlap matrix as parsed below to not be
# symmetric (which is a problem for population analyses, etc.)
if line[1:4] == "***" and (line[5:12] == "Overlap"
or line[8:15] == "Overlap"):
# Ensure that this is the main calc and not a fragment
if self.counterpoise != 0: return
self.aooverlaps = numpy.zeros( (self.nbasis, self.nbasis), "d")
# Overlap integrals for basis fn#1 are in aooverlaps[0]
base = 0
colmNames = inputfile.next()
while base < self.nbasis:
self.updateprogress(inputfile, "Overlap", self.fupdate)
for i in range(self.nbasis-base): # Fewer lines this time
line = inputfile.next()
parts = line.split()
for j in range(len(parts)-1): # Some lines are longer than others
k = float(parts[j+1].replace("D", "E"))
self.aooverlaps[base+j, i+base] = k
self.aooverlaps[i+base, base+j] = k
base += 5
colmNames = inputfile.next()
self.aooverlaps = numpy.array(self.aooverlaps, "d")
# Molecular orbital coefficients (mocoeffs).
# Essentially only produced for SCF calculations.
# This is also the place where aonames and atombasis are parsed.
if line[5:35] == "Molecular Orbital Coefficients" or line[5:41] == "Alpha Molecular Orbital Coefficients" or line[5:40] == "Beta Molecular Orbital Coefficients":
# If counterpoise fragment, return without parsing orbital info
if self.counterpoise != 0: return
# Skip this for ONIOM calcs
if self.oniom: return
if line[5:40] == "Beta Molecular Orbital Coefficients":
beta = True
if self.popregular:
return
# This was continue before refactoring the parsers.
#continue # Not going to extract mocoeffs
# Need to add an extra array to self.mocoeffs
self.mocoeffs.append(numpy.zeros((self.nmo, self.nbasis), "d"))
else:
beta = False
self.aonames = []
self.atombasis = []
mocoeffs = [numpy.zeros((self.nmo, self.nbasis), "d")]
base = 0
self.popregular = False
for base in range(0, self.nmo, 5):
self.updateprogress(inputfile, "Coefficients", self.fupdate)
colmNames = inputfile.next()
if not colmNames.split():
self.logger.warning("Molecular coefficients header found but no coefficients.")
break;
if base == 0 and int(colmNames.split()[0]) != 1:
# Implies that this is a POP=REGULAR calculation
# and so, only aonames (not mocoeffs) will be extracted
self.popregular = True
symmetries = inputfile.next()
eigenvalues = inputfile.next()
for i in range(self.nbasis):
line = inputfile.next()
if i == 0:
# Find location of the start of the basis function name
start_of_basis_fn_name = line.find(line.split()[3]) - 1
if base == 0 and not beta: # Just do this the first time 'round
parts = line[:start_of_basis_fn_name].split()
if len(parts) > 1: # New atom
if i > 0:
self.atombasis.append(atombasis)
atombasis = []
atomname = "%s%s" % (parts[2], parts[1])
orbital = line[start_of_basis_fn_name:20].strip()
self.aonames.append("%s_%s" % (atomname, orbital))
atombasis.append(i)
part = line[21:].replace("D", "E").rstrip()
temp = []
for j in range(0, len(part), 10):
temp.append(float(part[j:j+10]))
if beta:
self.mocoeffs[1][base:base + len(part) / 10, i] = temp
else:
mocoeffs[0][base:base + len(part) / 10, i] = temp
if base == 0 and not beta: # Do the last update of atombasis
self.atombasis.append(atombasis)
if self.popregular:
# We now have aonames, so no need to continue
break
if not self.popregular and not beta:
self.mocoeffs = mocoeffs
# Natural Orbital Coefficients (nocoeffs) - alternative for mocoeffs.
# Most extensively formed after CI calculations, but not only.
# Like for mocoeffs, this is also where aonames and atombasis are parsed.
if line[5:33] == "Natural Orbital Coefficients":
self.aonames = []
self.atombasis = []
nocoeffs = numpy.zeros((self.nmo, self.nbasis), "d")
base = 0
self.popregular = False
for base in range(0, self.nmo, 5):
self.updateprogress(inputfile, "Coefficients", self.fupdate)
colmNames = inputfile.next()
if base == 0 and int(colmNames.split()[0]) != 1:
# Implies that this is a POP=REGULAR calculation
# and so, only aonames (not mocoeffs) will be extracted
self.popregular = True
# No symmetry line for natural orbitals.
# symmetries = inputfile.next()
eigenvalues = inputfile.next()
for i in range(self.nbasis):
line = inputfile.next()
# Just do this the first time 'round.
if base == 0:
# Changed below from :12 to :11 to deal with Elmar Neumann's example.
parts = line[:11].split()
# New atom.
if len(parts) > 1:
if i > 0:
self.atombasis.append(atombasis)
atombasis = []
atomname = "%s%s" % (parts[2], parts[1])
orbital = line[11:20].strip()
self.aonames.append("%s_%s" % (atomname, orbital))
atombasis.append(i)
part = line[21:].replace("D", "E").rstrip()
temp = []
for j in range(0, len(part), 10):
temp.append(float(part[j:j+10]))
nocoeffs[base:base + len(part) / 10, i] = temp
# Do the last update of atombasis.
if base == 0:
self.atombasis.append(atombasis)
# We now have aonames, so no need to continue.
if self.popregular:
break
if not self.popregular:
self.nocoeffs = nocoeffs
# For FREQ=Anharm, extract anharmonicity constants
if line[1:40] == "X matrix of Anharmonic Constants (cm-1)":
Nvibs = len(self.vibfreqs)
self.vibanharms = numpy.zeros( (Nvibs, Nvibs), "d")
base = 0
colmNames = inputfile.next()
while base < Nvibs:
for i in range(Nvibs-base): # Fewer lines this time
line = inputfile.next()
parts = line.split()
for j in range(len(parts)-1): # Some lines are longer than others
k = float(parts[j+1].replace("D", "E"))
self.vibanharms[base+j, i+base] = k
self.vibanharms[i+base, base+j] = k
base += 5
colmNames = inputfile.next()
# Pseudopotential charges.
if line.find("Pseudopotential Parameters") > -1:
dashes = inputfile.next()
label1 = inputfile.next()
label2 = inputfile.next()
dashes = inputfile.next()
line = inputfile.next()
if line.find("Centers:") < 0:
return
# This was continue before parser refactoring.
# continue
# Needs to handle code like the following:
#
# Center Atomic Valence Angular Power Coordinates
# Number Number Electrons Momentum of R Exponent Coefficient X Y Z
# ===================================================================================================================================
# Centers: 1
# Centers: 16
# Centers: 21 24
# Centers: 99100101102
# 1 44 16 -4.012684 -0.696698 0.006750
# F and up
# 0 554.3796303 -0.05152700
centers = []
while line.find("Centers:") >= 0:
temp = line[10:]
for i in range(0, len(temp)-3, 3):
centers.append(int(temp[i:i+3]))
line = inputfile.next()
centers.sort() # Not always in increasing order
self.coreelectrons = numpy.zeros(self.natom, "i")
for center in centers:
front = line[:10].strip()
while not (front and int(front) == center):
line = inputfile.next()
front = line[:10].strip()
info = line.split()
self.coreelectrons[center-1] = int(info[1]) - int(info[2])
line = inputfile.next()
# This will be printed for counterpoise calcualtions only.
# To prevent crashing, we need to know which fragment is being considered.
# Other information is also printed in lines that start like this.
if line[1:14] == 'Counterpoise:':
if line[42:50] == "fragment":
self.counterpoise = int(line[51:54])
# This will be printed only during ONIOM calcs; use it to set a flag
# that will allow assertion failures to be bypassed in the code.
if line[1:7] == "ONIOM:":
self.oniom = True
if (line[1:24] == "Mulliken atomic charges" or
line[1:22] == "Lowdin Atomic Charges"):
if not hasattr(self, "atomcharges"):
self.atomcharges = {}
ones = inputfile.next()
charges = []
nline = inputfile.next()
while not "Sum of" in nline:
charges.append(float(nline.split()[2]))
nline = inputfile.next()
if "Mulliken" in line:
self.atomcharges["mulliken"] = charges
else:
self.atomcharges["lowdin"] = charges
if __name__ == "__main__":
import doctest, gaussianparser, sys
if len(sys.argv) == 1:
doctest.testmod(gaussianparser, verbose=False)
if len(sys.argv) >= 2:
parser = gaussianparser.Gaussian(sys.argv[1])
data = parser.parse()
if len(sys.argv) > 2:
for i in range(len(sys.argv[2:])):
if hasattr(data, sys.argv[2 + i]):
print getattr(data, sys.argv[2 + i])
|