/usr/share/pyshared/cclib/parser/gamessparser.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 | # 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: 1030 $"
import re
import numpy
import logfileparser
import utils
class GAMESS(logfileparser.Logfile):
"""A GAMESS log file."""
SCFRMS, SCFMAX, SCFENERGY = range(3) # Used to index self.scftargets[]
def __init__(self, *args, **kwargs):
# Call the __init__ method of the superclass
super(GAMESS, self).__init__(logname="GAMESS", *args, **kwargs)
def __str__(self):
"""Return a string representation of the object."""
return "GAMESS log file %s" % (self.filename)
def __repr__(self):
"""Return a representation of the object."""
return 'GAMESS("%s")' % (self.filename)
def normalisesym(self, label):
"""Normalise the symmetries used by GAMESS.
To normalise, two rules need to be applied:
(1) Occurences of U/G in the 2/3 position of the label
must be lower-cased
(2) Two single quotation marks must be replaced by a double
>>> t = GAMESS("dummyfile").normalisesym
>>> labels = ['A', 'A1', 'A1G', "A'", "A''", "AG"]
>>> answers = map(t, labels)
>>> print answers
['A', 'A1', 'A1g', "A'", 'A"', 'Ag']
"""
if label[1:] == "''":
end = '"'
else:
end = label[1:].replace("U", "u").replace("G", "g")
return label[0] + end
def before_parsing(self):
self.firststdorient = True # Used to decide whether to wipe the atomcoords clean
self.geooptfinished = False # Used to avoid extracting the final geometry twice
self.cihamtyp = "none" # Type of CI Hamiltonian: saps or dets.
self.scftype = "none" # Type of SCF calculation: BLYP, RHF, ROHF, etc.
def extract(self, inputfile, line):
"""Extract information from the file object inputfile."""
if line [1:12] == "INPUT CARD>":
return
# We are looking for this line:
# PARAMETERS CONTROLLING GEOMETRY SEARCH ARE
# ...
# OPTTOL = 1.000E-04 RMIN = 1.500E-03
if line[10:18] == "OPTTOL =":
if not hasattr(self, "geotargets"):
opttol = float(line.split()[2])
self.geotargets = numpy.array([opttol, 3. / opttol], "d")
if line.find("FINAL") == 1:
if not hasattr(self, "scfenergies"):
self.scfenergies = []
# Has to deal with such lines as:
# FINAL R-B3LYP ENERGY IS -382.0507446475 AFTER 10 ITERATIONS
# FINAL ENERGY IS -379.7594673378 AFTER 9 ITERATIONS
# ...so take the number after the "IS"
temp = line.split()
self.scfenergies.append(utils.convertor(float(temp[temp.index("IS") + 1]), "hartree", "eV"))
# Total energies after Moller-Plesset corrections
if (line.find("RESULTS OF MOLLER-PLESSET") >= 0 or
line[6:37] == "SCHWARZ INEQUALITY TEST SKIPPED"):
# Output looks something like this:
# RESULTS OF MOLLER-PLESSET 2ND ORDER CORRECTION ARE
# E(0)= -285.7568061536
# E(1)= 0.0
# E(2)= -0.9679419329
# E(MP2)= -286.7247480864
# where E(MP2) = E(0) + E(2)
#
# with GAMESS-US 12 Jan 2009 (R3) the preceding text is different:
## DIRECT 4-INDEX TRANSFORMATION
## SCHWARZ INEQUALITY TEST SKIPPED 0 INTEGRAL BLOCKS
## E(SCF)= -76.0088477471
## E(2)= -0.1403745370
## E(MP2)= -76.1492222841
if not hasattr(self, "mpenergies"):
self.mpenergies = []
# Each iteration has a new print-out
self.mpenergies.append([])
# GAMESS-US presently supports only second order corrections (MP2)
# PC GAMESS also has higher levels (3rd and 4th), with different output
# Only the highest level MP4 energy is gathered (SDQ or SDTQ)
while re.search("DONE WITH MP(\d) ENERGY", line) is None:
line = inputfile.next()
if len(line.split()) > 0:
# Only up to MP2 correction
if line.split()[0] == "E(MP2)=":
mp2energy = float(line.split()[1])
self.mpenergies[-1].append(utils.convertor(mp2energy, "hartree", "eV"))
# MP2 before higher order calculations
if line.split()[0] == "E(MP2)":
mp2energy = float(line.split()[2])
self.mpenergies[-1].append(utils.convertor(mp2energy, "hartree", "eV"))
if line.split()[0] == "E(MP3)":
mp3energy = float(line.split()[2])
self.mpenergies[-1].append(utils.convertor(mp3energy, "hartree", "eV"))
if line.split()[0] in ["E(MP4-SDQ)", "E(MP4-SDTQ)"]:
mp4energy = float(line.split()[2])
self.mpenergies[-1].append(utils.convertor(mp4energy, "hartree", "eV"))
# Total energies after Coupled Cluster calculations
# Only the highest Coupled Cluster level result is gathered
if line[12:23] == "CCD ENERGY:":
if not hasattr(self, "ccenergies"):
self.ccenergies = []
ccenergy = float(line.split()[2])
self.ccenergies.append(utils.convertor(ccenergy, "hartree", "eV"))
if line.find("CCSD") >= 0 and line.split()[0:2] == ["CCSD", "ENERGY:"]:
if not hasattr(self, "ccenergies"):
self.ccenergies = []
ccenergy = float(line.split()[2])
line = inputfile.next()
if line[8:23] == "CCSD[T] ENERGY:":
ccenergy = float(line.split()[2])
line = inputfile.next()
if line[8:23] == "CCSD(T) ENERGY:":
ccenergy = float(line.split()[2])
self.ccenergies.append(utils.convertor(ccenergy, "hartree", "eV"))
# Also collect MP2 energies, which are always calculated before CC
if line [8:23] == "MBPT(2) ENERGY:":
if not hasattr(self, "mpenergies"):
self.mpenergies = []
self.mpenergies.append([])
mp2energy = float(line.split()[2])
self.mpenergies[-1].append(utils.convertor(mp2energy, "hartree", "eV"))
# Extract charge and multiplicity
if line[1:19] == "CHARGE OF MOLECULE":
self.charge = int(line.split()[-1])
self.mult = int(inputfile.next().split()[-1])
# etenergies (used only for CIS runs now)
if "EXCITATION ENERGIES" in line and line.find("DONE WITH") < 0:
if not hasattr(self, "etenergies"):
self.etenergies = []
header = inputfile.next().rstrip()
get_etosc = False
if header.endswith("OSC. STR."):
# water_cis_dets.out does not have the oscillator strength
# in this table...it is extracted from a different section below
get_etosc = True
self.etoscs = []
dashes = inputfile.next()
line = inputfile.next()
broken = line.split()
while len(broken) > 0:
# Take hartree value with more numbers, and convert.
# Note that the values listed after this are also less exact!
etenergy = float(broken[1])
self.etenergies.append(utils.convertor(etenergy, "hartree", "cm-1"))
if get_etosc:
etosc = float(broken[-1])
self.etoscs.append(etosc)
broken = inputfile.next().split()
# Detect the CI hamiltonian type, if applicable.
# Should always be detected if CIS is done.
if line[8:64] == "RESULTS FROM SPIN-ADAPTED ANTISYMMETRIZED PRODUCT (SAPS)":
self.cihamtyp = "saps"
if line[8:64] == "RESULTS FROM DETERMINANT BASED ATOMIC ORBITAL CI-SINGLES":
self.cihamtyp = "dets"
# etsecs (used only for CIS runs for now)
if line[1:14] == "EXCITED STATE":
if not hasattr(self, 'etsecs'):
self.etsecs = []
if not hasattr(self, 'etsyms'):
self.etsyms = []
statenumber = int(line.split()[2])
spin = int(float(line.split()[7]))
if spin == 0:
sym = "Singlet"
if spin == 1:
sym = "Triplet"
sym += '-' + line.split()[-1]
self.etsyms.append(sym)
# skip 5 lines
for i in range(5):
line = inputfile.next()
line = inputfile.next()
CIScontribs = []
while line.strip()[0] != "-":
MOtype = 0
# alpha/beta are specified for hamtyp=dets
if self.cihamtyp == "dets":
if line.split()[0] == "BETA":
MOtype = 1
fromMO = int(line.split()[-3])-1
toMO = int(line.split()[-2])-1
coeff = float(line.split()[-1])
# With the SAPS hamiltonian, the coefficients are multiplied
# by sqrt(2) so that they normalize to 1.
# With DETS, both alpha and beta excitations are printed.
# if self.cihamtyp == "saps":
# coeff /= numpy.sqrt(2.0)
CIScontribs.append([(fromMO,MOtype), (toMO,MOtype), coeff])
line = inputfile.next()
self.etsecs.append(CIScontribs)
# etoscs (used only for CIS runs now)
if line[1:50] == "TRANSITION FROM THE GROUND STATE TO EXCITED STATE":
if not hasattr(self, "etoscs"):
self.etoscs = []
statenumber = int(line.split()[-1])
# skip 7 lines
for i in range(8):
line = inputfile.next()
strength = float(line.split()[3])
self.etoscs.append(strength)
# TD-DFT for GAMESS-US.
# The format for excitations has changed a bit between 2007 and 2012.
# Original format parser was written for:
#
# -------------------
# TRIPLET EXCITATIONS
# -------------------
#
# STATE # 1 ENERGY = 3.027228 EV
# OSCILLATOR STRENGTH = 0.000000
# DRF COEF OCC VIR
# --- ---- --- ---
# 35 -1.105383 35 -> 36
# 69 -0.389181 34 -> 37
# 103 -0.405078 33 -> 38
# 137 0.252485 32 -> 39
# 168 -0.158406 28 -> 40
#
# STATE # 2 ENERGY = 4.227763 EV
# ...
#
# Here is the corresponding 2012 version:
#
# -------------------
# TRIPLET EXCITATIONS
# -------------------
#
# STATE # 1 ENERGY = 3.027297 EV
# OSCILLATOR STRENGTH = 0.000000
# LAMBDA DIAGNOSTIC = 0.925 (RYDBERG/CHARGE TRANSFER CHARACTER)
# SYMMETRY OF STATE = A
# EXCITATION DE-EXCITATION
# OCC VIR AMPLITUDE AMPLITUDE
# I A X(I->A) Y(A->I)
# --- --- -------- --------
# 35 36 -0.929190 -0.176167
# 34 37 -0.279823 -0.109414
# ...
#
# We discern these two by the presence of the arrow in the old version.
#
# The "LET EXCITATIONS" pattern used below catches both
# singlet and triplet excitations output.
if line[14:29] == "LET EXCITATIONS":
self.etenergies = []
self.etoscs = []
self.etsecs = []
etsyms = []
minuses = inputfile.next()
blanks = inputfile.next()
# Loop while states are still being printed.
line = inputfile.next()
while line[1:6] == "STATE":
if self.progress:
self.updateprogress(inputfile, "Excited States")
etenergy = utils.convertor(float(line.split()[-2]), "eV", "cm-1")
etoscs = float(inputfile.next().split()[-1])
self.etenergies.append(etenergy)
self.etoscs.append(etoscs)
# Symmetry is not always present, especially in old versions.
# Newer versions, on the other hand, can also provide a line
# with lambda diagnostic and some extra headers.
line = inputfile.next()
if "LAMBDA DIAGNOSTIC" in line:
line = inputfile.next()
if "SYMMETRY" in line:
etsyms.append(line.split()[-1])
line = inputfile.next()
if "EXCITATION" in line and "DE-EXCITATION" in line:
line = inputfile.next()
if line.count("AMPLITUDE") == 2:
line = inputfile.next()
minuses = inputfile.next()
CIScontribs = []
line = inputfile.next()
while line.strip():
cols = line.split()
if "->" in line:
i_occ_vir = [2, 4]
i_coeff = 1
else:
i_occ_vir = [0, 1]
i_coeff = 2
fromMO, toMO = [int(cols[i]) - 1 for i in i_occ_vir]
coeff = float(cols[i_coeff])
CIScontribs.append([(fromMO, 0), (toMO, 0), coeff])
line = inputfile.next()
self.etsecs.append(CIScontribs)
line = inputfile.next()
# The symmetries are not always present.
if etsyms:
self.etsyms = etsyms
# Maximum and RMS gradients.
if "MAXIMUM GRADIENT" in line or "RMS GRADIENT" in line:
parts = line.split()
# Avoid parsing the following...
## YOU SHOULD RESTART "OPTIMIZE" RUNS WITH THE COORDINATES
## WHOSE ENERGY IS LOWEST. RESTART "SADPOINT" RUNS WITH THE
## COORDINATES WHOSE RMS GRADIENT IS SMALLEST. THESE ARE NOT
## ALWAYS THE LAST POINT COMPUTED!
if parts[0] not in ["MAXIMUM", "RMS", "(1)"]:
return
if not hasattr(self, "geovalues"):
self.geovalues = []
# Newer versions (around 2006) have both maximum and RMS on one line:
# MAXIMUM GRADIENT = 0.0531540 RMS GRADIENT = 0.0189223
if len(parts) == 8:
maximum = float(parts[3])
rms = float(parts[7])
# In older versions of GAMESS, this spanned two lines, like this:
# MAXIMUM GRADIENT = 0.057578167
# RMS GRADIENT = 0.027589766
if len(parts) == 4:
maximum = float(parts[3])
line = inputfile.next()
parts = line.split()
rms = float(parts[3])
# FMO also prints two final one- and two-body gradients (see exam37):
# (1) MAXIMUM GRADIENT = 0.0531540 RMS GRADIENT = 0.0189223
if len(parts) == 9:
maximum = float(parts[4])
rms = float(parts[8])
self.geovalues.append([maximum, rms])
if line[11:50] == "ATOMIC COORDINATES":
# This is the input orientation, which is the only data available for
# SP calcs, but which should be overwritten by the standard orientation
# values, which is the only information available for all geoopt cycles.
if not hasattr(self, "atomcoords"):
self.atomcoords = []
self.atomnos = []
line = inputfile.next()
atomcoords = []
atomnos = []
line = inputfile.next()
while line.strip():
temp = line.strip().split()
atomcoords.append([utils.convertor(float(x), "bohr", "Angstrom") for x in temp[2:5]])
atomnos.append(int(round(float(temp[1])))) # Don't use the atom name as this is arbitary
line = inputfile.next()
self.atomnos = numpy.array(atomnos, "i")
self.atomcoords.append(atomcoords)
if line[12:40] == "EQUILIBRIUM GEOMETRY LOCATED":
# Prevent extraction of the final geometry twice
self.geooptfinished = True
if line[1:29] == "COORDINATES OF ALL ATOMS ARE" and not self.geooptfinished:
# This is the standard orientation, which is the only coordinate
# information available for all geometry optimisation cycles.
# The input orientation will be overwritten if this is a geometry optimisation
# We assume that a previous Input Orientation has been found and
# used to extract the atomnos
if self.progress:
self.updateprogress(inputfile, "Coordinates")
if self.firststdorient:
self.firststdorient = False
# Wipes out the single input coordinate at the start of the file
self.atomcoords = []
line = inputfile.next()
hyphens = inputfile.next()
atomcoords = []
line = inputfile.next()
for i in range(self.natom):
temp = line.strip().split()
atomcoords.append(map(float, temp[2:5]))
line = inputfile.next()
self.atomcoords.append(atomcoords)
# Section with SCF information.
#
# The space at the start of the search string is to differentiate from MCSCF.
# Everything before the search string is stored as the type of SCF.
# SCF types may include: BLYP, RHF, ROHF, UHF, etc.
#
# For example, in exam17 the section looks like this (note that this is GVB):
# ------------------------
# ROHF-GVB SCF CALCULATION
# ------------------------
# GVB STEP WILL USE 119875 WORDS OF MEMORY.
#
# MAXIT= 30 NPUNCH= 2 SQCDF TOL=1.0000E-05
# NUCLEAR ENERGY= 6.1597411978
# EXTRAP=T DAMP=F SHIFT=F RSTRCT=F DIIS=F SOSCF=F
#
# ITER EX TOTAL ENERGY E CHANGE SQCDF DIIS ERROR
# 0 0 -38.298939963 -38.298939963 0.131784454 0.000000000
# 1 1 -38.332044339 -0.033104376 0.026019716 0.000000000
# ... and will be terminated by a blank line.
if line.rstrip()[-16:] == " SCF CALCULATION":
# Remember the type of SCF.
self.scftype = line.strip()[:-16]
dashes = inputfile.next()
while line [:5] != " ITER":
if self.progress:
self.updateprogress(inputfile, "Attributes")
# GVB uses SQCDF for checking convergence (for example in exam17).
if "GVB" in self.scftype and "SQCDF TOL=" in line:
scftarget = float(line.split("=")[-1])
# Normally however the density is used as the convergence criterium.
# Deal with various versions:
# (GAMESS VERSION = 12 DEC 2003)
# DENSITY MATRIX CONV= 2.00E-05 DFT GRID SWITCH THRESHOLD= 3.00E-04
# (GAMESS VERSION = 22 FEB 2006)
# DENSITY MATRIX CONV= 1.00E-05
# (PC GAMESS version 6.2, Not DFT?)
# DENSITY CONV= 1.00E-05
elif "DENSITY CONV" in line or "DENSITY MATRIX CONV" in line:
scftarget = float(line.split()[-1])
line = inputfile.next()
if not hasattr(self, "scftargets"):
self.scftargets = []
self.scftargets.append([scftarget])
if not hasattr(self,"scfvalues"):
self.scfvalues = []
line = inputfile.next()
# Normally the iteration print in 6 columns.
# For ROHF, however, it is 5 columns, thus this extra parameter.
if "ROHF" in self.scftype:
valcol = 4
else:
valcol = 5
# SCF iterations are terminated by a blank line.
# The first four characters usually contains the step number.
# However, lines can also contain messages, including:
# * * * INITIATING DIIS PROCEDURE * * *
# CONVERGED TO SWOFF, SO DFT CALCULATION IS NOW SWITCHED ON
# DFT CODE IS SWITCHING BACK TO THE FINER GRID
values = []
while line.strip():
try:
temp = int(line[0:4])
except ValueError:
pass
else:
values.append([float(line.split()[valcol])])
line = inputfile.next()
self.scfvalues.append(values)
# Extract normal coordinate analysis, including vibrational frequencies (vibfreq),
# IT intensities (vibirs) and displacements (vibdisps).
#
# This section typically looks like the following in GAMESS-US:
#
# MODES 1 TO 6 ARE TAKEN AS ROTATIONS AND TRANSLATIONS.
#
# FREQUENCIES IN CM**-1, IR INTENSITIES IN DEBYE**2/AMU-ANGSTROM**2,
# REDUCED MASSES IN AMU.
#
# 1 2 3 4 5
# FREQUENCY: 52.49 41.45 17.61 9.23 10.61
# REDUCED MASS: 3.92418 3.77048 5.43419 6.44636 5.50693
# IR INTENSITY: 0.00013 0.00001 0.00004 0.00000 0.00003
#
# ...or in the case of a numerical Hessian job...
#
# MODES 1 TO 5 ARE TAKEN AS ROTATIONS AND TRANSLATIONS.
#
# FREQUENCIES IN CM**-1, IR INTENSITIES IN DEBYE**2/AMU-ANGSTROM**2,
# REDUCED MASSES IN AMU.
#
# 1 2 3 4 5
# FREQUENCY: 0.05 0.03 0.03 30.89 30.94
# REDUCED MASS: 8.50125 8.50137 8.50136 1.06709 1.06709
#
# ...whereas PC-GAMESS has...
#
# MODES 1 TO 6 ARE TAKEN AS ROTATIONS AND TRANSLATIONS.
#
# FREQUENCIES IN CM**-1, IR INTENSITIES IN DEBYE**2/AMU-ANGSTROM**2
#
# 1 2 3 4 5
# FREQUENCY: 5.89 1.46 0.01 0.01 0.01
# IR INTENSITY: 0.00000 0.00000 0.00000 0.00000 0.00000
#
# If Raman is present we have (for PC-GAMESS)...
#
# MODES 1 TO 6 ARE TAKEN AS ROTATIONS AND TRANSLATIONS.
#
# FREQUENCIES IN CM**-1, IR INTENSITIES IN DEBYE**2/AMU-ANGSTROM**2
# RAMAN INTENSITIES IN ANGSTROM**4/AMU, DEPOLARIZATIONS ARE DIMENSIONLESS
#
# 1 2 3 4 5
# FREQUENCY: 5.89 1.46 0.04 0.03 0.01
# IR INTENSITY: 0.00000 0.00000 0.00000 0.00000 0.00000
# RAMAN INTENSITY: 12.675 1.828 0.000 0.000 0.000
# DEPOLARIZATION: 0.750 0.750 0.124 0.009 0.750
#
# If GAMESS-US or PC-GAMESS has not reached the stationary point we have
# and additional warning, repeated twice, like so (see n_water.log for an example):
#
# *******************************************************
# * THIS IS NOT A STATIONARY POINT ON THE MOLECULAR PES *
# * THE VIBRATIONAL ANALYSIS IS NOT VALID !!! *
# *******************************************************
#
# There can also be additional warnings about the selection of modes, for example:
#
# * * * WARNING, MODE 6 HAS BEEN CHOSEN AS A VIBRATION
# WHILE MODE12 IS ASSUMED TO BE A TRANSLATION/ROTATION.
# PLEASE VERIFY THE PROGRAM'S DECISION MANUALLY!
#
if "NORMAL COORDINATE ANALYSIS IN THE HARMONIC APPROXIMATION" in line:
self.vibfreqs = []
self.vibirs = []
self.vibdisps = []
# Need to get to the modes line, which is often preceeded by
# a list of atomic weights and some possible warnings.
# Pass the warnings to the logger if they are there.
while not "MODES" in line:
if self.progress:
self.updateprogress(inputfile, "Frequency Information")
line = inputfile.next()
if "THIS IS NOT A STATIONARY POINT" in line:
msg = "\n This is not a stationary point on the molecular PES"
msg += "\n The vibrational analysis is not valid!!!"
self.logger.warning(msg)
if "* * * WARNING, MODE" in line:
line1 = line.strip()
line2 = inputfile.next().strip()
line3 = inputfile.next().strip()
self.logger.warning("\n " + "\n ".join((line1,line2,line3)))
# In at least one case (regression zolm_dft3a.log) for older version of GAMESS-US,
# the header concerning the range of nodes is formatted wrong and can look like so:
# MODES 9 TO14 ARE TAKEN AS ROTATIONS AND TRANSLATIONS.
# ... although it's unclear whether this happens for all two-digit values.
startrot = int(line.split()[1])
if len(line.split()[2]) == 2:
endrot = int(line.split()[3])
else:
endrot = int(line.split()[2][2:])
blank = inputfile.next()
line = inputfile.next()
# This is to skip the output associated with symmetry analysis, fixes bug #3476063.
if "ANALYZING SYMMETRY OF NORMAL MODES" in line:
blank = inputfile.next()
line = inputfile.next()
while line != blank:
line = inputfile.next()
# Skip over FREQUENCIES, etc., and get past the possibly second warning.
line = inputfile.next()
while line != blank:
line = inputfile.next()
line = inputfile.next()
if "*****" in line:
while line != blank:
line = inputfile.next()
line = inputfile.next()
while not "SAYVETZ" in line:
if self.progress:
self.updateprogress(inputfile, "Frequency Information")
# Note: there may be imaginary frequencies like this (which we make negative):
# FREQUENCY: 825.18 I 111.53 12.62 10.70 0.89
#
# A note for debuggers: some of these frequencies will be removed later,
# assumed to be translations or rotations (see startrot/endrot above).
for col in inputfile.next().split()[1:]:
if col == "I":
self.vibfreqs[-1] *= -1
else:
self.vibfreqs.append(float(col))
line = inputfile.next()
# Skip the symmetry (appears in newer versions), fixes bug #3476063.
if line.find("SYMMETRY") >= 0:
line = inputfile.next()
# Skip the reduced mass (not always present).
if line.find("REDUCED") >= 0:
line = inputfile.next()
# Not present in numerical Hessian calculations.
if line.find("IR INTENSITY") >= 0:
irIntensity = map(float, line.strip().split()[2:])
self.vibirs.extend([utils.convertor(x, "Debye^2/amu-Angstrom^2", "km/mol") for x in irIntensity])
line = inputfile.next()
# Read in Raman vibrational intensities if present.
if line.find("RAMAN") >= 0:
if not hasattr(self,"vibramans"):
self.vibramans = []
ramanIntensity = line.strip().split()
self.vibramans.extend(map(float, ramanIntensity[2:]))
depolar = inputfile.next()
line = inputfile.next()
# This line seems always to be blank.
assert line == blank
# Extract the Cartesian displacement vectors.
p = [ [], [], [], [], [] ]
for j in range(self.natom):
q = [ [], [], [], [], [] ]
for coord in ['x', 'y', 'z']:
cols = map(float, inputfile.next()[21:].split())
for i, val in enumerate(cols):
q[i].append(val)
for k in range(len(cols)):
p[k].append(q[k])
self.vibdisps.extend(p[:len(cols)])
# Skip the Sayvetz stuff at the end.
for j in range(10):
line = inputfile.next()
blank = inputfile.next()
line = inputfile.next()
# Exclude rotations and translations.
self.vibfreqs = numpy.array(self.vibfreqs[:startrot-1]+self.vibfreqs[endrot:], "d")
self.vibirs = numpy.array(self.vibirs[:startrot-1]+self.vibirs[endrot:], "d")
self.vibdisps = numpy.array(self.vibdisps[:startrot-1]+self.vibdisps[endrot:], "d")
if hasattr(self, "vibramans"):
self.vibramans = numpy.array(self.vibramans[:startrot-1]+self.vibramans[endrot:], "d")
if line[5:21] == "ATOMIC BASIS SET":
self.gbasis = []
line = inputfile.next()
while line.find("SHELL")<0:
line = inputfile.next()
blank = inputfile.next()
atomname = inputfile.next()
# shellcounter stores the shell no of the last shell
# in the previous set of primitives
shellcounter = 1
while line.find("TOTAL NUMBER")<0:
blank = inputfile.next()
line = inputfile.next()
shellno = int(line.split()[0])
shellgap = shellno - shellcounter
gbasis = [] # Stores basis sets on one atom
shellsize = 0
while len(line.split())!=1 and line.find("TOTAL NUMBER")<0:
shellsize += 1
coeff = {}
# coefficients and symmetries for a block of rows
while line.strip():
temp = line.strip().split()
sym = temp[1]
assert sym in ['S', 'P', 'D', 'F', 'G', 'L']
if sym == "L": # L refers to SP
if len(temp)==6: # GAMESS US
coeff.setdefault("S", []).append( (float(temp[3]), float(temp[4])) )
coeff.setdefault("P", []).append( (float(temp[3]), float(temp[5])) )
else: # PC GAMESS
assert temp[6][-1] == temp[9][-1] == ')'
coeff.setdefault("S", []).append( (float(temp[3]), float(temp[6][:-1])) )
coeff.setdefault("P", []).append( (float(temp[3]), float(temp[9][:-1])) )
else:
if len(temp)==5: # GAMESS US
coeff.setdefault(sym, []).append( (float(temp[3]), float(temp[4])) )
else: # PC GAMESS
assert temp[6][-1] == ')'
coeff.setdefault(sym, []).append( (float(temp[3]), float(temp[6][:-1])) )
line = inputfile.next()
# either a blank or a continuation of the block
if sym == "L":
gbasis.append( ('S', coeff['S']))
gbasis.append( ('P', coeff['P']))
else:
gbasis.append( (sym, coeff[sym]))
line = inputfile.next()
# either the start of the next block or the start of a new atom or
# the end of the basis function section
numtoadd = 1 + (shellgap / shellsize)
shellcounter = shellno + shellsize
for x in range(numtoadd):
self.gbasis.append(gbasis)
if line.find("EIGENVECTORS") == 10 or line.find("MOLECULAR OBRITALS") == 10:
# The details returned come from the *final* report of evalues and
# the last list of symmetries in the log file.
# Should be followed by lines like this:
# ------------
# EIGENVECTORS
# ------------
#
# 1 2 3 4 5
# -10.0162 -10.0161 -10.0039 -10.0039 -10.0029
# BU AG BU AG AG
# 1 C 1 S 0.699293 0.699290 -0.027566 0.027799 0.002412
# 2 C 1 S 0.031569 0.031361 0.004097 -0.004054 -0.000605
# 3 C 1 X 0.000908 0.000632 -0.004163 0.004132 0.000619
# 4 C 1 Y -0.000019 0.000033 0.000668 -0.000651 0.005256
# 5 C 1 Z 0.000000 0.000000 0.000000 0.000000 0.000000
# 6 C 2 S -0.699293 0.699290 0.027566 0.027799 0.002412
# 7 C 2 S -0.031569 0.031361 -0.004097 -0.004054 -0.000605
# 8 C 2 X 0.000908 -0.000632 -0.004163 -0.004132 -0.000619
# 9 C 2 Y -0.000019 -0.000033 0.000668 0.000651 -0.005256
# 10 C 2 Z 0.000000 0.000000 0.000000 0.000000 0.000000
# 11 C 3 S -0.018967 -0.019439 0.011799 -0.014884 -0.452328
# 12 C 3 S -0.007748 -0.006932 0.000680 -0.000695 -0.024917
# 13 C 3 X 0.002628 0.002997 0.000018 0.000061 -0.003608
# and so forth... with blanks lines between blocks of 5 orbitals each.
# Warning! There are subtle differences between GAMESS-US and PC-GAMES
# in the formatting of the first four columns.
#
# Watch out for F orbitals...
# PC GAMESS
# 19 C 1 YZ 0.000000 0.000000 0.000000 0.000000 0.000000
# 20 C XXX 0.000000 0.000000 0.000000 0.000000 0.002249
# 21 C YYY 0.000000 0.000000 -0.025555 0.000000 0.000000
# 22 C ZZZ 0.000000 0.000000 0.000000 0.002249 0.000000
# 23 C XXY 0.000000 0.000000 0.001343 0.000000 0.000000
# GAMESS US
# 55 C 1 XYZ 0.000000 0.000000 0.000000 0.000000 0.000000
# 56 C 1XXXX -0.000014 -0.000067 0.000000 0.000000 0.000000
#
# This is fine for GeoOpt and SP, but may be weird for TD and Freq.
# This is the stuff that we can read from these blocks.
self.moenergies = [[]]
self.mosyms = [[]]
if not hasattr(self, "nmo"):
self.nmo = self.nbasis
self.mocoeffs = [numpy.zeros((self.nmo, self.nbasis), "d")]
readatombasis = False
if not hasattr(self, "atombasis"):
self.atombasis = []
self.aonames = []
for i in range(self.natom):
self.atombasis.append([])
self.aonames = []
readatombasis = True
dashes = inputfile.next()
for base in range(0, self.nmo, 5):
if self.progress:
self.updateprogress(inputfile, "Coefficients")
line = inputfile.next()
# Make sure that this section does not end prematurely - checked by regression test 2CO.ccsd.aug-cc-pVDZ.out.
if line.strip() != "":
break;
numbers = inputfile.next() # Eigenvector numbers.
# Sometimes there are some blank lines here.
while not line.strip():
line = inputfile.next()
# Eigenvalues for these orbitals (in hartrees).
try:
self.moenergies[0].extend([utils.convertor(float(x), "hartree", "eV") for x in line.split()])
except:
self.logger.warning('MO section found but could not be parsed!')
break;
# Orbital symmetries.
line = inputfile.next()
if line.strip():
self.mosyms[0].extend(map(self.normalisesym, line.split()))
# Now we have nbasis lines.
# Going to use the same method as for normalise_aonames()
# to extract basis set information.
p = re.compile("(\d+)\s*([A-Z][A-Z]?)\s*(\d+)\s*([A-Z]+)")
oldatom = '0'
i_atom = 0 # counter to keep track of n_atoms > 99
flag_w = True # flag necessary to keep from adding 100's at wrong time
for i in range(self.nbasis):
line = inputfile.next()
# If line is empty, break (ex. for FMO in exam37).
if not line.strip(): break
# Fill atombasis and aonames only first time around
if readatombasis and base == 0:
aonames = []
start = line[:17].strip()
m = p.search(start)
if m:
g = m.groups()
g2 = int(g[2]) # atom index in GAMESS file; changes to 0 after 99
# Check if we have moved to a hundred
# if so, increment the counter and add it to the parsed value
# There will be subsequent 0's as that atoms AO's are parsed
# so wait until the next atom is parsed before resetting flag
if g2 == 0 and flag_w:
i_atom = i_atom + 100
flag_w = False # handle subsequent AO's
if g2 != 0:
flag_w = True # reset flag
g2 = g2 + i_atom
aoname = "%s%i_%s" % (g[1].capitalize(), g2, g[3])
oldatom = str(g2)
atomno = g2-1
orbno = int(g[0])-1
else: # For F orbitals, as shown above
g = [x.strip() for x in line.split()]
aoname = "%s%s_%s" % (g[1].capitalize(), oldatom, g[2])
atomno = int(oldatom)-1
orbno = int(g[0])-1
self.atombasis[atomno].append(orbno)
self.aonames.append(aoname)
coeffs = line[15:] # Strip off the crud at the start.
j = 0
while j*11+4 < len(coeffs):
self.mocoeffs[0][base+j, i] = float(coeffs[j * 11:(j + 1) * 11])
j += 1
line = inputfile.next()
# If it's restricted and no more properties:
# ...... END OF RHF/DFT CALCULATION ......
# If there are more properties (DENSITY MATRIX):
# --------------
#
# If it's unrestricted we have:
#
# ----- BETA SET -----
#
# ------------
# EIGENVECTORS
# ------------
#
# 1 2 3 4 5
# ... and so forth.
line = inputfile.next()
if line[2:22] == "----- BETA SET -----":
self.mocoeffs.append(numpy.zeros((self.nmo, self.nbasis), "d"))
self.moenergies.append([])
self.mosyms.append([])
for i in range(4):
line = inputfile.next()
for base in range(0, self.nmo, 5):
if self.progress:
self.updateprogress(inputfile, "Coefficients")
blank = inputfile.next()
line = inputfile.next() # Eigenvector no
line = inputfile.next()
self.moenergies[1].extend([utils.convertor(float(x), "hartree", "eV") for x in line.split()])
line = inputfile.next()
self.mosyms[1].extend(map(self.normalisesym, line.split()))
for i in range(self.nbasis):
line = inputfile.next()
temp = line[15:] # Strip off the crud at the start
j = 0
while j * 11 + 4 < len(temp):
self.mocoeffs[1][base+j, i] = float(temp[j * 11:(j + 1) * 11])
j += 1
line = inputfile.next()
self.moenergies = [numpy.array(x, "d") for x in self.moenergies]
# Natural orbitals - presently support only CIS.
# Looks basically the same as eigenvectors, without symmetry labels.
if line[10:30] == "CIS NATURAL ORBITALS":
self.nocoeffs = numpy.zeros((self.nmo, self.nbasis), "d")
dashes = inputfile.next()
for base in range(0, self.nmo, 5):
blank = inputfile.next()
numbers = inputfile.next() # Eigenvector numbers.
# Eigenvalues for these natural orbitals (not in hartrees!).
# Sometimes there are some blank lines before it.
line = inputfile.next()
while not line.strip():
line = inputfile.next()
eigenvalues = line
# Orbital symemtry labels are normally here for MO coefficients.
line = inputfile.next()
# Now we have nbasis lines with the coefficients.
for i in range(self.nbasis):
line = inputfile.next()
coeffs = line[15:]
j = 0
while j*11+4 < len(coeffs):
self.nocoeffs[base+j, i] = float(coeffs[j * 11:(j + 1) * 11])
j += 1
# We cannot trust this self.homos until we come to the phrase:
# SYMMETRIES FOR INITAL GUESS ORBITALS FOLLOW
# which either is followed by "ALPHA" or "BOTH" at which point we can say
# for certain that it is an un/restricted calculations.
# Note that MCSCF calcs also print this search string, so make sure
# that self.homos does not exist yet.
if line[1:28] == "NUMBER OF OCCUPIED ORBITALS" and not hasattr(self,'homos'):
homos = [int(line.split()[-1])-1]
line = inputfile.next()
homos.append(int(line.split()[-1])-1)
self.homos = numpy.array(homos, "i")
if line.find("SYMMETRIES FOR INITIAL GUESS ORBITALS FOLLOW") >= 0:
# Not unrestricted, so lop off the second index.
# In case the search string above was not used (ex. FMO in exam38),
# we can try to use the next line which should also contain the
# number of occupied orbitals.
if line.find("BOTH SET(S)") >= 0:
nextline = inputfile.next()
if "ORBITALS ARE OCCUPIED" in nextline:
homos = int(nextline.split()[0])-1
if hasattr(self,"homos"):
try:
assert self.homos[0] == homos
except AssertionError:
self.logger.warning("Number of occupied orbitals not consistent. This is normal for ECP and FMO jobs.")
else:
self.homos = [homos]
self.homos = numpy.resize(self.homos, [1])
# Set the total number of atoms, only once.
# Normally GAMESS print TOTAL NUMBER OF ATOMS, however in some cases
# this is slightly different (ex. lower case for FMO in exam37).
if not hasattr(self,"natom") and "NUMBER OF ATOMS" in line.upper():
self.natom = int(line.split()[-1])
if line.find("NUMBER OF CARTESIAN GAUSSIAN BASIS") == 1 or line.find("TOTAL NUMBER OF BASIS FUNCTIONS") == 1:
# The first is from Julien's Example and the second is from Alexander's
# I think it happens if you use a polar basis function instead of a cartesian one
self.nbasis = int(line.strip().split()[-1])
elif line.find("TOTAL NUMBER OF CONTAMINANTS DROPPED") >= 0:
number = int(line.split()[-1])
if hasattr(self, "nmo"):
self.nmo -= number
else:
self.nmo = self.nbasis - number
elif line.find("SPHERICAL HARMONICS KEPT IN THE VARIATION SPACE") >= 0:
# Note that this line is present if ISPHER=1, e.g. for C_bigbasis
self.nmo = int(line.strip().split()[-1])
elif line.find("TOTAL NUMBER OF MOS IN VARIATION SPACE") == 1:
# Note that this line is not always present, so by default
# NBsUse is set equal to NBasis (see below).
self.nmo = int(line.split()[-1])
elif line.find("OVERLAP MATRIX") == 0 or line.find("OVERLAP MATRIX") == 1:
# The first is for PC-GAMESS, the second for GAMESS
# Read 1-electron overlap matrix
if not hasattr(self, "aooverlaps"):
self.aooverlaps = numpy.zeros((self.nbasis, self.nbasis), "d")
else:
self.logger.info("Reading additional aooverlaps...")
base = 0
while base < self.nbasis:
if self.progress:
self.updateprogress(inputfile, "Overlap")
blank = inputfile.next()
line = inputfile.next() # Basis fn number
blank = inputfile.next()
for i in range(self.nbasis - base): # Fewer lines each time
line = inputfile.next()
temp = line.split()
for j in range(4, len(temp)):
self.aooverlaps[base+j-4, i+base] = float(temp[j])
self.aooverlaps[i+base, base+j-4] = float(temp[j])
base += 5
# ECP Pseudopotential information
if "ECP POTENTIALS" in line:
if not hasattr(self, "coreelectrons"):
self.coreelectrons = [0]*self.natom
dashes = inputfile.next()
blank = inputfile.next()
header = inputfile.next()
while header.split()[0] == "PARAMETERS":
name = header[17:25]
atomnum = int(header[34:40])
# The pseudopotnetial is given explicitely
if header[40:50] == "WITH ZCORE":
zcore = int(header[50:55])
lmax = int(header[63:67])
self.coreelectrons[atomnum-1] = zcore
# The pseudopotnetial is copied from another atom
if header[40:55] == "ARE THE SAME AS":
atomcopy = int(header[60:])
self.coreelectrons[atomnum-1] = self.coreelectrons[atomcopy-1]
line = inputfile.next()
while line.split() <> []:
line = inputfile.next()
header = inputfile.next()
# This was used before refactoring the parser, geotargets was set here after parsing.
#if not hasattr(self, "geotargets"):
# opttol = 1e-4
# self.geotargets = numpy.array([opttol, 3. / opttol], "d")
#if hasattr(self,"geovalues"): self.geovalues = numpy.array(self.geovalues, "d")
# This is quite simple to parse, but some files seem to print certain
# lines twice, repeating the populations without charges.
# Now, unrestricted calculations are bit tricky, since GAMESS-US prints
# populations for both alpha and beta orbitals in the same format
# and with the same title, but it still prints the charges only
# at the very end. So, check for the number of columns in the header.
if "TOTAL MULLIKEN AND LOWDIN ATOMIC POPULATIONS" in line:
if not hasattr(self, "atomcharges"):
self.atomcharges = {}
header = inputfile.next()
line = inputfile.next()
double = line.strip()
if double:
header = inputfile.next()
skip = inputfile.next()
line = inputfile.next()
# Only go further if the header had five columns, which should
# be the case when both populations and charges are printed.
if not header.split() == 5:
return
mulliken, lowdin = [], []
while line.strip():
mulliken.append(float(line.split()[3]))
lowdin.append(float(line.split()[5]))
line = inputfile.next()
if line.strip() and double:
line = inputfile.next()
self.atomcharges["mulliken"] = mulliken
self.atomcharges["lowdin"] = lowdin
if __name__ == "__main__":
import doctest, gamessparser, sys
if len(sys.argv) == 1:
doctest.testmod(gamessparser, verbose=False)
if len(sys.argv) >= 2:
parser = gamessparser.GAMESS(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])
|