Parsing file with find gives strange results with different files

2
votes

I tried asking this question before and rightfully was informed I need to provide a fully working example so others can reproduce my result and then give guidance.

Here is a shortened version of my code for parsing the file. The point of readFileToStrings is to save the file into seperate strings based on the patterns [Atoms], [GTO], and [MO].

#include <cstring>
#include <fstream>
#include <iostream>
#include <string>

void readFileToStrings(const std::string& filename, std::string& ParticlesString,
                       std::string& GaussianString, std::string& MOString) {
    std::ifstream source(filename);
    std::string line;
    while(std::getline(source, line)) {
        if(line.find("Molpro") != std::string::npos) {
            std::getline(source, line, '['); // reads until [
        }
        if(line.find("Atoms") != std::string::npos) {
            std::getline(source, line, '['); // reads until [
            ParticlesString.append(line);
        }
        if(line.find("GTO") != std::string::npos) {
            std::getline(source, line, '['); // reads until [
            GaussianString.append(line);
        }
        if(line.find("MO") != std::string::npos) {
            std::getline(source, line, '\0'); // reads until end of file
            MOString.append(line);
        }
    }
}

int main(int argc, char** argv) {
    if(argc != 2) {
        std::cerr << "USAGE: " << argv[0] << " <filename>\n";
        return 1;
    }
    std::string filename(argv[1]), ParticlesString, GaussianString, MOString;
    readFileToStrings(filename, ParticlesString, GaussianString, MOString);

    std::cout << ParticlesString << "\n";
}

I have two different files I need to parse from different versions of a program. Here they are

file 1:

[Molden Format]
[Atoms] (AU)
O    1    8         0.000000000000       0.000000000000      -0.124302651265
H    2    1         0.000000000000      -1.424704710000       0.986386639735
H    3    1        -0.000000000000       1.424704710000       0.986386639735
[GTO]
  1 0
 s    8  1.00
    11720.0000000000         0.0007100000
     1759.0000000000         0.0054700000
      400.8000000000         0.0278370000
      113.7000000000         0.1048000000
       37.0300000000         0.2830620000
       13.2700000000         0.4487190000
        5.0250000000         0.2709520000
        1.0130000000         0.0154580000
 s    8  1.00
    11720.0000000000        -0.0001600000
     1759.0000000000        -0.0012630000
      400.8000000000        -0.0062670000
      113.7000000000        -0.0257160000
       37.0300000000        -0.0709240000
       13.2700000000        -0.1654110000
        5.0250000000        -0.1169550000
        1.0130000000         0.5573680000
 s    1  1.00
        0.3023000000         1.0000000000
 p    3  1.00
       17.7000000000         0.0430180000
        3.8540000000         0.2289130000
        1.0460000000         0.5087280000
 p    1  1.00
        0.2753000000         1.0000000000
 d    1  1.00
        1.1850000000         1.0000000000

  2 0
 s    3  1.00
       13.0100000000         0.0196850000
        1.9620000000         0.1379770000
        0.4446000000         0.4781480000
 s    1  1.00
        0.1220000000         1.0000000000
 p    1  1.00
        0.7270000000         1.0000000000

  3 0
 s    3  1.00
       13.0100000000         0.0196850000
        1.9620000000         0.1379770000
        0.4446000000         0.4781480000
 s    1  1.00
        0.1220000000         1.0000000000
 p    1  1.00
        0.7270000000         1.0000000000

[5D]
[9G]

[MO]
 Sym= A1
 Ene= -2.05504193878478176e+01
 Spin= Alpha
 Occup=  2.00000000000000000e+00
  1  1.00090233711673782e+00
  2  1.18218569881159419e-03
  3 -2.65616439031917534e-03
  4  0.00000000000000000e+00
  5  0.00000000000000000e+00
  6  1.77146011704106335e-03
  7  0.00000000000000000e+00
  8  0.00000000000000000e+00
  9 -4.80000097346545279e-04
 10  1.39013834758571625e-05
 11  0.00000000000000000e+00
 12  0.00000000000000000e+00
 13 -1.39822026074492775e-04
 14  0.00000000000000000e+00
 15 -2.48316020753471748e-04
 16  4.20097131947155702e-04
 17  0.00000000000000000e+00
 18 -5.74904249836309948e-04
 19  4.87036596243491202e-04
 20 -2.48316020753471748e-04
 21  4.20097131947155702e-04
 22  0.00000000000000000e+00
 23  5.74904249836309948e-04
 24  4.87036596243491202e-04
 Sym= A1
 Ene= -1.33767141221376074e+00
 Spin= Alpha
 Occup=  2.00000000000000000e+00
  1  8.23750319287331126e-03
  2 -4.42693483105670693e-01
  3 -3.74498035531203644e-01
  4  0.00000000000000000e+00
  5  0.00000000000000000e+00
  6 -7.94258623925411383e-02
  7  0.00000000000000000e+00
  8  0.00000000000000000e+00
  9  1.34092445806940908e-02
 10 -1.29606223143065302e-03
 11  0.00000000000000000e+00
 12  0.00000000000000000e+00
 13  2.99830598541997798e-03
 14  0.00000000000000000e+00
 15 -1.94341522346533402e-01
 16 -1.00103187758395738e-02
 17  0.00000000000000000e+00
 18 -3.73152124438631272e-02
 19  2.06694627945085245e-02
 20 -1.94341522346533402e-01
 21 -1.00103187758395738e-02
 22  0.00000000000000000e+00
 23  3.73152124438631272e-02
 24  2.06694627945085245e-02

file 2:

[Molden Format]
[Molpro variables]
_NUMVAR=  897.0000000000000    
_AVOGAD= 0.6022136736000000E+24
_BOLTZ= 0.1380658000000000E-22
_CLIGHT=  29979245800.00000    
_EV= 0.3674932379085202E-01
_ENULL= 0.8854187817000000E-11
_KJOULE= 0.3808798324128737E-03
_KJOULE/MOL= 0.3808798324128737E-03
_CM= 0.4556335267302901E-05
_CM-1= 0.4556335267302901E-05
_DEB2SI= 0.3335641000000000E-29
_AMU2AU=  1822.888390000000    
_KCAL= 0.1593601117815568E-02
_KCAL/MOL= 0.1593601117815568E-02
_KELVIN= 0.3166811411060229E-05
_JOULE= 0.4359748200000000E-17
_HERTZ= 0.1519829846004524E-15
_HZ= 0.1519829846004524E-15
_JPCAL=  4.184000000000000    
_PLANCK= 0.6626075540000000E-33
_TOA= 0.5291772109200000    
_TOANG= 0.5291772109200000    
_TORAD= 0.1745329251994330E-01
_TOCM=  219474.6306700000    
_TODEBYE=  2.541580000000000    
_TOE= 0.4803242000000000E-09
_TOEV=  27.21138505000000    
_TOHERTZ=  6579683920729000.    
_TOHZ=  6579683920729000.    
_TOK=  315775.0400000000    
_TOKCAL=  627.5096000000000    
_TOKELVIN=  315775.0400000000    
_TOKJ=  2625.500000000000    
_TOKJOULE=  2625.500000000000    
_TOKG= 0.1660565586000000E-26
_ANG=  1.889726124565062    
_ANGSTROM=  1.889726124565062    
_RPAREF=  0.000000000000000    
_RPADISS=  0.000000000000000    
_IGNORE_UNDEF=  2.000000000000000    
_STRICTCHECK=  0.000000000000000    
_SEW_ONEEL=  0.000000000000000    
_CPPDONE=FALSE
_DKROLL_DONE=  0.000000000000000    
_FOCKDONE=TRUE
_GRADONE=FALSE
_HESSDONE=FALSE
_INTDONE=TRUE
_SCFDONE=TRUE
_MODUL_BLOCK=FALSE
_MODUL_CUDA=FALSE
_MODUL_SLATER=FALSE
_MODUL_MRCC=FALSE
_MODUL_NBO6=FALSE
_MODUL_NECI=TRUE
_MODUL_AIMS=TRUE
_MRCC_EXEC=
_FITC_AO_SAVED=FALSE
_FITC_MO_SAVED=FALSE
_SHARED_FS=TRUE
_LSTYP=SEWARD
_INTYP=INTS
_GEOMTYP=ZMAT
_GRADTYP=ALASKA
_DIRECT=FALSE
_DKHO= -1.000000000000000    
_SYNCM=  0.000000000000000    
_BASIS=AUG-CC-PVTZ
_ZORIENT=  0.000000000000000    
_NELEC=  10.00000000000000    
!SPIN=  0.000000000000000    
_QSDSTEP=  0.000000000000000    
_QSDIRC=  0.000000000000000    
_PROGRAM=RHF-SCF
_CPUSTEP= 0.2000000000000002    
_SYSSTEP= 0.4000000000000004E-01
_WALLSTEP= 0.3900000000000000    
!DFSCF=  0.000000000000000    
!SCSGRD=  0.000000000000000    
_BASINP=  610.0000000000000    
_CPUTOT=  1.600000000000000    
_CPUSORT= 0.2100000000000000    
_SYSSORT= 0.3000000000000003E-01
_WALLSORT= 0.3200000002980232    
_DFTEXFAC=  1.000000000000000    
_DMX=  0.000000000000000    
_DMY=  0.000000000000000    
_DMZ= 0.7630238919693926    
_DMX_SCF=  0.000000000000000    
_DMY_SCF=  0.000000000000000    
_DMZ_SCF= 0.7630238919693926    
_EHOMO=-0.5112368090014537    
_ELUMO= 0.2975373354087893E-01
_EIGS= -20.56350049329804    
_ENERGY= -76.06120311938969    
_ENERGY_METHOD=RHF
_ENERGY_BASIS=aug-cc-pVTZ
_GEOMETRY_METHOD=
_GEOMETRY_BASIS=
_ENUC=  9.348802247698661    
_GRADEXFAC=  9999.000000000000    
_GRADMETHOD=  1.000000000000000    
_NMRMETHOD=  0.000000000000000    
_NMRMAGNET=  0.000000000000000    
!GRID_FREEZE= -1.000000000000000    
_ITERATIONS=  9.000000000000000    
_LASTNELEC=  10.00000000000000    
_LASTSPIN=  0.000000000000000    
_LASTSYM=  1.000000000000000    
_MPP_PROG=  1.000000000000000    
_MSNSTATES=  0.000000000000000    
_RS2PHASE=  0.000000000000000    
_NPROC_MPP=  23.00000000000000    
_NPROC_MPPX=  23.00000000000000    
_NPROC_SMP=  1.000000000000000    
_NUMSTEP=  0.000000000000000    
_ORBITAL=  2100.200000000000    
_PI=  3.141592653589793    
_SEIG_MIN= 0.3697027323475132E-03
_SEWPROP=TRUE
_STATUS=  1.000000000000000    
_SYSTOT= 0.1900000000000001    
_VERSION=  2015001.000000000    
_WALLTOT=  3.040000000000000    
_DATE=11-Apr-20
_LASTORB=RHF
_MACHINE= 64 bit mpp version
_OUTPUT=/global/cscratch1/sd/rbello/Quantum_Chem/molpro.xml
_PGROUP=C2v
_TIME=13:36:56
_LIBMOL=/global/common/cori/software/molpro/2015/molprop_2015_1_linux_x86_64_i8/lib/
_VIGRDC=  0.000000000000000    
!VIBCNT=  0.000000000000000    
!RGHFCNT=  0.000000000000000    
!SURFREC=  0.000000000000000    
!ROTREC=  0.000000000000000    
!POLYREC=  0.000000000000000    
!DIPREC=  0.000000000000000    
!DIP4DREC=  0.000000000000000    
!DIPROT=  0.000000000000000    
!DIP4DROT=  0.000000000000000    
!PTREC=  0.000000000000000    
!PT4DREC=  0.000000000000000    
!VSCFREC=  0.000000000000000    
!VCIREC=  0.000000000000000    
!PVCIREC=  0.000000000000000    
!VMP2REC=  0.000000000000000    
!VMCSCFREC=  0.000000000000000    
!VMRCIREC=  0.000000000000000    
!VIBSTATEREC=  0.000000000000000    
!VIBSTATECNT=  0.000000000000000    
!VIBINFO=  0.000000000000000    
!GAREC=  0.000000000000000    
!SCFORB=  21002.00000000000    
!NEWMOL= -1.000000000000000    
!NEWSYM= -1.000000000000000    
_SLFILES=slscratch
_NGSSTO=  9.000000000000000    
_SIN=SIN
_COS=COS
_TAN=TAN
_ACOS=ACOS
_ASIN=ASIN
_ATAN=ATAN
_COSH=COSH
_SINH=SINH
_TANH=TANH
_ABS=ABS
_MOD=MOD
_ERF=ERF
_REFC=REFC
_ERFC=ERFC
_HYPOT=HYPOT
_J0=J0
_J1=J1
_JN=JN
_GAMMA=GAMMA
_LGAMMA=LGAMMA
_Y0=Y0
_Y1=Y1
_YN=YN
_EXP=EXP
_LOG=LOG
_LOG10=LOG10
_SQRT=SQRT
_INT=INT
_NINT=NINT
_MAX=MAX
_MIN=MIN
_COSMO=  0.000000000000000    
_COSMOIT=  0.000000000000000    
_COSMOES=  0.000000000000000    
_COSMOEDS=  0.000000000000000    
_COSMOEC=  0.000000000000000    
_COSMOEDCORR=  0.000000000000000    
_FEPSI=  1.000000000000000    
_SL_IsMM=  0.000000000000000    
_SL_NSYM=  4.000000000000000    
_SL_System_BitSw=  0.000000000000000    
_SL_Unique_atoms=  0.000000000000000    
_SL_GRAD=  0.000000000000000    
_SL_MAXUPD_Hess=  5.000000000000000    
_SL_N_PRINT_COD=  5.000000000000000    
_SL_PRINT_CODES=  0.000000000000000    
_SL_BasType=  0.000000000000000    
_SL_Energy_Pred=  0.000000000000000    
_SL_New_Coords=  0.000000000000000    
_SL_Total_Nuclea=  0.000000000000000    
_SL_Highest_Mltp=  0.000000000000000    
_SL_Ref_Geom=  0.000000000000000    
_SL_Symmetry_ope=  1.000000000000000    
_SL_agrad=  0.000000000000000    
_SL_GrdMax=  0.000000000000000    
_SL_GrdNorm=  0.000000000000000    
_SL_GrdRMS=  0.000000000000000    
_SL_Hss_Q=  0.000000000000000    
_SL_Hss_X=  0.000000000000000    
_SL_BMxOld=  0.000000000000000    
_SL_KtB=  0.000000000000000    
_SL_TROld=  0.000000000000000    
_SL_No_of_Intern=  0.000000000000000    
_SL_Hess=  0.000000000000000    
_SL_K=  0.000000000000000    
!LATTICE= -1.000000000000000    
!NEWLATTICE=  0.000000000000000    
!LATGRAD_VAR=FALSE
!SEW_LATTICE=  1.000000000000000    
!LOCAL=  0.000000000000000    
!SAVEDOM= -1.000000000000000    
!RESTDOM= -1.000000000000000    
!SAVEDOM_HF= -1.000000000000000    
!RESTDOM_HF= -1.000000000000000    
!HESSREC=  0.000000000000000    
!FREQREC=  0.000000000000000    
!NMODREC=  0.000000000000000    
!GTASKS=  0.000000000000000    
!HTASKS=  0.000000000000000    
!SAVEDOM_EOM= -1.000000000000000    
!RESTDOM_EOM= -1.000000000000000    
!GRADSTATE= -1.000000000000000    
!THRCHG= 0.1000000000000000    
!DEBUG= -1.000000000000000    
!CFIT_CPHF=  0.000000000000000    
!RDOMAUX_CPHF=  3.000000000000000    
!THRAO_CPHF= 0.1000000000000000E-09
!THRMO_CPHF= 0.1000000000000000E-08
!THROV_CPHF= 0.1000000000000000E-11
!THRSW_CPHF= 0.1000000000000000E-09
!THRPROD_CPHF= 0.1000000000000000E-08
!THRAOPR_CPHF= 0.1000000000000000E-11
!CFIT_SCFGRD=  0.000000000000000    
!RDOMAUX_SCFGRD=  5.000000000000000    
!THRAO_SCFGRD= 0.1000000000000000E-09
!THRMO_SCFGRD= 0.1000000000000000E-08
!THROV_SCFGRD= 0.1000000000000000E-11
!THRSW_SCFGRD= 0.1000000000000000E-09
!THRPROD_SCFGRD= 0.1000000000000000E-08
!THRAOPR_SCFGRD= 0.1000000000000000E-11
!LOCFIT_SCF=  0.000000000000000    
!LOCFIT_MP2= -1.000000000000000    
_RIDOM=  0.000000000000000    
!CC2_METHOD=  0.000000000000000    
_BASIS2006=FALSE
_SVDDEL= -1.000000000000000    
_SVDDELA= -1.000000000000000    
_SVDDELP= -1.000000000000000    
_SVDDELF= -1.000000000000000    
_SVDDELS= -1.000000000000000    
_SVDDEL_ABS= -1.000000000000000    
_SVDDELA_ABS= -1.000000000000000    
_SVDDELP_ABS= -1.000000000000000    
_SVDDELF_ABS= -1.000000000000000    
_SVDDELS_ABS= -1.000000000000000    
_MAXBASIS=  0.000000000000000    
!OPT_CONICAL=  0.000000000000000    
!CLEARSP_JGRID=  0.000000000000000    
_GRDHYBR=  0.000000000000000    
_STATEGRAD=  1.000000000000000    
_4EXT_NDISKS=  1.000000000000000    
!ZMP=  0.000000000000000    
_MAXIT_ZMP=  500.0000000000000    
_MAXDIS_ZMP=  100.0000000000000    
_ACCU_ZMP=  14.00000000000000    
_SHIFTA_ZMP= -100.0000000000000    
!EMBEDFLAG=  1.000000000000000    
!EMBED=FALSE
!EMBED_F12=FALSE
!EMBEDNUC=  0.000000000000000    
_EMBEDENERGY=  0.000000000000000    
_KSPACETIME=  0.000000000000000    
_RSPACETIME=  0.000000000000000    
!EMBED_DFC=FALSE
!NUM_VOIDS=  0.000000000000000    
_IBODY=  0.000000000000000    
_EMBE_TOTAL=  0.000000000000000    
_EMBE_HF=  0.000000000000000    
_EMBE_CORR=  0.000000000000000    
!EMBED_PROJ=FALSE
!EMBED_TRUNC=  0.000000000000000    
!EMB_PROJ_ZMU=  1000000.000000000    
!CORRECTION=  0.000000000000000    
!CORRECTION_HF=  0.000000000000000    
!EMBED_ENERGY=  0.000000000000000    
!EMBED_NAXC=FALSE
!EMBED_AORB=  0.000000000000000    
!EMBED_NACORR=  0.000000000000000    
!EMBED_MP2=FALSE
!EMBED_TRUNC_PERTURBATION=FALSE
!EMBED_FROZEN=  0.000000000000000    
_CHANGE_BASIS=FALSE
_RESTORE_BASIS=FALSE
_FIX_EMBED_GUESS=FALSE
!EDFT=  0.000000000000000    
_IFASTLATGRAD=  0.000000000000000    
_SINDEX=  0.000000000000000    
_AVDOM_OSV=  0.000000000000000    
_AVDOM_PNO=  0.000000000000000    
_AVDOM_PAO=  0.000000000000000    
_AVDOM_LMO=  0.000000000000000    
_CC2OSV_FLAG=  0.000000000000000    
_TMADC2_FLAG=FALSE
_PROPADC2_FLAG=FALSE
_LEN_VirQ=  0.000000000000000    
_GRDCC2LR_FLAG=FALSE
_GRDADC2_FLAG=FALSE
R=  0.000000000000000    
AHOH=  104.4776000000000    
GX1=  0.000000000000000    
GY1=  0.000000000000000    
GZ1=  0.000000000000000    
GX2=  0.000000000000000    
GY2= 0.7530886081000000    
GZ2= 0.5642560353000000    
GX3=  0.000000000000000    
GY3=-0.7530886081000000    
GZ3= 0.5642560353000000    
ACCU=  13.00000000000000    
NITORT=  1.000000000000000    
[Atoms] Angs
O     1    8         0.0000000000        0.0000000000        0.0000000000
H     2    1         0.0000000000        0.7530886081        0.5642560353
H     3    1         0.0000000000       -0.7530886081        0.5642560353
[GTO]
   1 0
 s   10  1.00
  0.1533000000D+05  0.5079996682D-03
  0.2299000000D+04  0.3928997434D-02
  0.5224000000D+03  0.2024298678D-01
  0.1473000000D+03  0.7918094828D-01
  0.4755000000D+02  0.2306868493D+00
  0.1676000000D+02  0.4331177171D+00
  0.6207000000D+01  0.3502597712D+00
  0.1752000000D+01  0.4272797209D-01
  0.6882000000D+00 -0.8153994674D-02
  0.2384000000D+00  0.2380998445D-02
 s   10  1.00
  0.1533000000D+05 -0.1150000604D-03
  0.2299000000D+04 -0.8950004697D-03
  0.5224000000D+03 -0.4636002433D-02
  0.1473000000D+03 -0.1872400983D-01
  0.4755000000D+02 -0.5846303068D-01
  0.1676000000D+02 -0.1364630716D+00
  0.6207000000D+01 -0.1757400922D+00
  0.1752000000D+01  0.1609340845D+00
  0.6882000000D+00  0.6034183167D+00
  0.2384000000D+00  0.3787651988D+00
 s   10  1.00
  0.1533000000D+05  0.0000000000D+00
  0.2299000000D+04  0.0000000000D+00
  0.5224000000D+03  0.0000000000D+00
  0.1473000000D+03  0.0000000000D+00
  0.4755000000D+02  0.0000000000D+00
  0.1676000000D+02  0.0000000000D+00
  0.6207000000D+01  0.0000000000D+00
  0.1752000000D+01  0.1000000000D+01
  0.6882000000D+00  0.0000000000D+00
  0.2384000000D+00  0.0000000000D+00
 s   10  1.00
  0.1533000000D+05  0.0000000000D+00
  0.2299000000D+04  0.0000000000D+00
  0.5224000000D+03  0.0000000000D+00
  0.1473000000D+03  0.0000000000D+00
  0.4755000000D+02  0.0000000000D+00
  0.1676000000D+02  0.0000000000D+00
  0.6207000000D+01  0.0000000000D+00
  0.1752000000D+01  0.0000000000D+00
  0.6882000000D+00  0.0000000000D+00
  0.2384000000D+00  0.1000000000D+01
 s    1  1.00
  0.7376000000D-01  0.1000000000D+01
 p    5  1.00
  0.3446000000D+02  0.1592799074D-01
  0.7749000000D+01  0.9973994203D-01
  0.2280000000D+01  0.3104918195D+00
  0.7156000000D+00  0.4910257146D+00
  0.2140000000D+00  0.3363368045D+00
 p    5  1.00
  0.3446000000D+02  0.0000000000D+00
  0.7749000000D+01  0.0000000000D+00
  0.2280000000D+01  0.0000000000D+00
  0.7156000000D+00  0.1000000000D+01
  0.2140000000D+00  0.0000000000D+00
 p    5  1.00
  0.3446000000D+02  0.0000000000D+00
  0.7749000000D+01  0.0000000000D+00
  0.2280000000D+01  0.0000000000D+00
  0.7156000000D+00  0.0000000000D+00
  0.2140000000D+00  0.1000000000D+01
 p    1  1.00
  0.5974000000D-01  0.1000000000D+01
 d    1  1.00
  0.2314000000D+01  0.1000000000D+01
 d    1  1.00
  0.6450000000D+00  0.1000000000D+01
 d    1  1.00
  0.2140000000D+00  0.1000000000D+01
 f    1  1.00
  0.1428000000D+01  0.1000000000D+01
 f    1  1.00
  0.5000000000D+00  0.1000000000D+01
  
   2 0
 s    5  1.00
  0.3387000000D+02  0.6067999217D-02
  0.5095000000D+01  0.4530799416D-01
  0.1159000000D+01  0.2028219738D+00
  0.3258000000D+00  0.5039029350D+00
  0.1027000000D+00  0.3834209505D+00
 s    5  1.00
  0.3387000000D+02  0.0000000000D+00
  0.5095000000D+01  0.0000000000D+00
  0.1159000000D+01  0.0000000000D+00
  0.3258000000D+00  0.1000000000D+01
  0.1027000000D+00  0.0000000000D+00
 s    5  1.00
  0.3387000000D+02  0.0000000000D+00
  0.5095000000D+01  0.0000000000D+00
  0.1159000000D+01  0.0000000000D+00
  0.3258000000D+00  0.0000000000D+00
  0.1027000000D+00  0.1000000000D+01
 s    1  1.00
  0.2526000000D-01  0.1000000000D+01
 p    1  1.00
  0.1407000000D+01  0.1000000000D+01
 p    1  1.00
  0.3880000000D+00  0.1000000000D+01
 p    1  1.00
  0.1020000000D+00  0.1000000000D+01
 d    1  1.00
  0.1057000000D+01  0.1000000000D+01
 d    1  1.00
  0.2470000000D+00  0.1000000000D+01
  
   3 0
 s    5  1.00
  0.3387000000D+02  0.6067999217D-02
  0.5095000000D+01  0.4530799416D-01
  0.1159000000D+01  0.2028219738D+00
  0.3258000000D+00  0.5039029350D+00
  0.1027000000D+00  0.3834209505D+00
 s    5  1.00
  0.3387000000D+02  0.0000000000D+00
  0.5095000000D+01  0.0000000000D+00
  0.1159000000D+01  0.0000000000D+00
  0.3258000000D+00  0.1000000000D+01
  0.1027000000D+00  0.0000000000D+00
 s    5  1.00
  0.3387000000D+02  0.0000000000D+00
  0.5095000000D+01  0.0000000000D+00
  0.1159000000D+01  0.0000000000D+00
  0.3258000000D+00  0.0000000000D+00
  0.1027000000D+00  0.1000000000D+01
 s    1  1.00
  0.2526000000D-01  0.1000000000D+01
 p    1  1.00
  0.1407000000D+01  0.1000000000D+01
 p    1  1.00
  0.3880000000D+00  0.1000000000D+01
 p    1  1.00
  0.1020000000D+00  0.1000000000D+01
 d    1  1.00
  0.1057000000D+01  0.1000000000D+01
 d    1  1.00
  0.2470000000D+00  0.1000000000D+01
 
 
[MO]
 Sym=      1.1
 Ene=     -20.5635
 Spin= Alpha
 Occup=    2.000000
1 0.99886977633685
2 -0.002215397472811
3 0.001339812894581
4 -0.000004180768445
5 0.000548838632543
6 0.0
7 0.0
8 0.004778581946589
9 0.0
10 0.0
11 -0.003730531833399
12 0.0
13 0.0
14 -0.001157169841262
15 0.0
16 0.0
17 0.000185654641842
18 -0.000090895245319
19 0.000082587393316
20 0.000008307852004
21 0.0
22 0.0
23 0.0
24 0.000444705577625
25 -0.000386073005962
26 -0.000058632571663
27 0.0
28 0.0
29 0.0
30 -0.000178445813651
31 0.000109582826994
32 0.000068862986658
33 0.0
34 0.0
35 0.0
36 0.0
37 0.0
38 -0.000039290663317
39 0.0
40 0.0
41 -0.000009119140879
42 0.0
43 0.0
44 0.000061833097313
45 0.0
46 0.0
47 0.0
48 0.000101391442167
49 0.0
50 0.0
51 0.000087807533700
52 0.0
53 0.0
54 -0.000223838427914
55 0.0
56 0.002239240169404
57 -0.000535094559902
58 -0.001276546316515
59 0.000012380675065
60 0.0
61 -0.000102597933280
62 -0.000055538548035
63 0.0
64 -0.000530661889263
65 -0.000462529931180
66 0.0
67 -0.000076124646814
68 -0.000038598432129
69 0.000102705643914
70 -0.000063087655025
71 -0.000039617988889
72 0.0
73 0.0
74 -0.000189205570701
75 -0.000216447626108
76 0.000193585960579
77 0.000022861665528
78 0.0
79 0.0
80 0.000379059881317
81 0.002239240169404
82 -0.000535094559902
83 -0.001276546316515
84 0.000012380675065
85 0.0
86 0.000102597933280
87 -0.000055538548035
88 0.0
89 0.000530661889263
90 -0.000462529931180
91 0.0
92 0.000076124646814
93 -0.000038598432129
94 0.000102705643914
95 -0.000063087655025
96 -0.000039617988889
97 0.0
98 0.0
99 0.000189205570701
100 -0.000216447626108
101 0.000193585960579
102 0.000022861665528
103 0.0
104 0.0
105 -0.000379059881317

The main difference is file 2 has the [Molpro variables] section.

My output for file 1 (Note: expected/desired output):

O    1    8         0.000000000000       0.000000000000      -0.124302651265
H    2    1         0.000000000000      -1.424704710000       0.986386639735
H    3    1        -0.000000000000       1.424704710000       0.986386639735

My output for file 2:

in other words it's blank.

However, if I change the string to find from line.fing("Atoms") to line.find("toms") this is my output

file 1:

O    1    8         0.000000000000       0.000000000000      -0.124302651265
H    2    1         0.000000000000      -1.424704710000       0.986386639735
H    3    1        -0.000000000000       1.424704710000       0.986386639735

file 2:

Atoms] Angs
O    1    8         0.000000000000       0.000000000000      -0.124302651265
H    2    1         0.000000000000      -1.424704710000       0.986386639735
H    3    1        -0.000000000000       1.424704710000       0.986386639735
2
c++stringparsing

2 Answers

2
votes

There is an issue here:

if (line.find("Molpro") != std::string::npos) {
    std::getline(source, line, '['); // reads until [
}
if (line.find("Atoms") != std::string::npos) {

In file2, once you read Molpro, you are extracting everything until the next [, and overwriting line. In the current iteration of the while loop, the search for Atoms fails (as it should), but then you check for the string MO, which does exist in the file (and causes everything remaining in the file to be skipped). This causes you to skip the Atoms string that you are looking for as well.

Simply adding continue as shown here:

if (line.find("Molpro") != std::string::npos) {
    std::getline(source, line, '['); // reads until [
    continue; // <-- here
}
if (line.find("Atoms") != std::string::npos) {

and running ./a.out file2 on my machine generates the output:

O     1    8         0.0000000000        0.0000000000        0.0000000000
H     2    1         0.0000000000        0.7530886081        0.5642560353
H     3    1         0.0000000000       -0.7530886081        0.5642560353

which seems correct.

Frankly, I don't know why doing a find(toms) generates the output it does; my guess is it has something to do with the several dozen occurences of MO in file2. Anyway, the effects of the bug are not too important, once the bug is found.

I suggest thinking about how your code is structured. It seems you might be expecting the branches to be mutually exclusive, in which case you should have nested if-else statements for each of the strings you're looking for.

1
votes

Lets step through this.

while (std::getline(source, line)) { 

    // Just read the line: 
    // [Molpro variables]
    //
    //  So line contains the string: "[Molpro variables]"

    if (line.find("Molpro") != std::string::npos) {
       // this is finds the word:  Molpro
       // So we enter the if statement.

       std::getline(source, line, '['); 
       // This reads all the way to the next '['
       // Which is the lines ending with:
       //        NITORT=  1.000000000000000    
       //        [  => Note this character is discarded.
       //              It is not on the stream nor in the variable line
       // Thus the next line of characters left on the stream are:
       //        Atoms] Angs
       //
       // But the main thing to remember is that you have a lot of text
       // inside the variable `line` (about 339 lines).
    }

    if(line.find("Atoms") != std::string::npos) {

       // We don't find the word "Atoms" in the 339 lines.
       // Though if you look you will see atoms in those 339
       // So this is the case where this if statement is not entered.
       // So the next two lines do not get executed.
        std::getline(source, line, '['); // reads until [
        ParticlesString.append(line);
    }


    if(line.find("GTO") != std::string::npos) {
        // GTO is not in the 339 lines.
        // So this code is not executed.
        std::getline(source, line, '['); // reads until [
        GaussianString.append(line); 
    }
    if(line.find("MO") != std::string::npos) {

        // You will find the string "MO" in the 339 lines read above.
        // So the following code will be executed.

        std::getline(source, line, '\0'); // reads until end of file
        // You have read the data from >Atoms] Ang all the way to the
        // end of the file.
      
        MOString.append(line);
    }
 }
 // The loop is not re-executed.
 // As you read the whole file.

To be blunt your design is flawed:

You should set up a state machine that tracks what part of the file you are in. DOn't try to skip forward just wait for the correct section header to appear then set the section.

void readFileToStrings(const std::string& filename,
                         std::string& ParticlesString,
                         std::string& GaussianString, 
                         std::string& MOString) {
    std::ifstream file(filename);
    std::string section = "None";

    std::string line;
    // Only read lines in one place
    // This is your control for processing the file
    while(std::getline(file, line)) {

       // Check to ses if you are entering a special section of
       // the data file. It seems like each section starts with
       // [XXXX] So check for the ones that are important to you.
       if (line.substr(0, 7) == "[Atoms]") {
           section = "Atoms";
       else if (line.substr(0, 5) == "[GTO]") {
           section = "GTO";
       else if (line.substr(0, 4) == "[MO]") {
           section = "MO";
       else if (line[0] == '[') {
           // Make sure you notice when you move to a section you
           // don't care about.
           section = "None";
       else {
           // We are reading a data line:
           // So for each data line append it to the appropriate
           // work items.
           if (section == "Atoms") {
               ParticlesString.append(line);
           }
           else if (section == "GTO") {
               GaussianString.append(line);
           }
           else if (section == "MO") {
               MOString.append(line);
           }
       }
   }