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
|
/* Ergo, version 3.8.2, a program for linear scaling electronic structure
* calculations.
* Copyright (C) 2023 Elias Rudberg, Emanuel H. Rubensson, Pawel Salek,
* and Anastasia Kruchinina.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* Primary academic reference:
* Ergo: An open-source program for linear-scaling electronic structure
* calculations,
* Elias Rudberg, Emanuel H. Rubensson, Pawel Salek, and Anastasia
* Kruchinina,
* SoftwareX 7, 107 (2018),
* <http://dx.doi.org/10.1016/j.softx.2018.03.005>
*
* For further information about Ergo, see <http://www.ergoscf.org>.
*/
/** @file xyz_file_parser.cc
@brief Functionality for parsing a file in xyz file format,
storing the result as a molecule object.
@author: Elias Rudberg <em>responsible</em>
*/
#include <stdio.h>
#include <stdlib.h>
#include <memory.h>
#include <math.h>
#include <string.h>
#include <cassert>
#include "xyz_file_parser.h"
#include "output.h"
#include "memorymanag.h"
#include "units.h"
#include "atom_labels.h"
#include "utilities.h"
int
readMoleculeFileInXyzFormat(Molecule& result,
const char* fileName,
int netCharge,
bool expectPlainCharges)
{
FILE* f = fopen(fileName, "rt");
if(f == NULL) {
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error opening file '%s'", fileName);
return -1;
}
long int fileSize = get_file_size(fileName);
if(fileSize < 0) {
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error getting file size for file '%s'", fileName);
return -1;
}
size_t bufSize = fileSize + 10000;
std::vector<char> buf(bufSize);
memset(&buf[0], 0, bufSize);
int nBytes = (int)fread(&buf[0], sizeof(char), bufSize, f);
fclose(f);
if(nBytes <= 0) {
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error reading file '%s'", fileName);
return -1;
}
do_output(LOG_CAT_INFO, LOG_AREA_MAIN, "read_molecule_file_in_xyz_format: File '%s' read OK, nBytes = %i", fileName, nBytes);
const char* p = &buf[0];
// Get number of atoms from first line
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
int nAtoms = atoi(p);
do_output(LOG_CAT_INFO, LOG_AREA_MAIN, "read_molecule_file_in_xyz_format: nAtoms = %6i", nAtoms);
// Skip rest of line
while(*p != '\n' && *p != '\0')
p++;
p++;
// Skip one line
while(*p != '\n' && *p != '\0')
p++;
p++;
// Now p should point to the line with the first atom
int atomIndex;
for(atomIndex = 0; atomIndex < nAtoms; atomIndex++)
{
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
// Now p should point to atom label.
char labelString[88];
const char* q = p;
// Move q forwarn until blank
while(*q != ' ' && *q != '\t' && *q != '\n' && *q != '\0')
q++;
int labelLen = q - p;
if(labelLen > 22)
{
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error in read_molecule_file_in_xyz_format: label too long.");
return -1;
}
memcpy(labelString, p, labelLen);
labelString[labelLen] = '\0';
p = q;
// Now we have the label string null-terminated in labelString.
// We want to handle the case when the labels have some numbers on each label, stuff like "N17" and "Fe31".
// Do this by simply replacing any digits in labelString with null-characters.
for(int i = 0; i < labelLen; i++) {
if(labelString[i] >= '0' && labelString[i] <= '9')
labelString[i] = '\0';
}
// Now p should point to first blank after label.
if(*p != ' ' && *p != '\t')
{
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error in read_molecule_file_in_xyz_format: blank not found after label.");
return -1;
}
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
// Now p should point to x coordinate.
ergo_real coord_x = atof(p);
// Skip coordinate
while((*p >= '0' && *p <= '9') || *p == '.' || *p == '-')
p++;
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
// Now p should point to y coordinate.
ergo_real coord_y = atof(p);
// Skip coordinate
while((*p >= '0' && *p <= '9') || *p == '.' || *p == '-')
p++;
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
// Now p should point to z coordinate.
ergo_real coord_z = atof(p);
// Skip coordinate
while((*p >= '0' && *p <= '9') || *p == '.' || *p == '-')
p++;
// Skip blanks
while(*p == ' ' || *p == '\t')
p++;
// Now p should point to newline character.
if(*p != '\n')
{
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN, "error in read_molecule_file_in_xyz_format: newline not found after coordinates.");
printf("p points to '%s'\n", p);
return -1;
}
// Skip to next line
p++;
// OK, now we have labelString and coords.
// Depending on the expectPlainCharges parameter, we interpret
// the labelString as a charge or as an atom label.
ergo_real atomCharge = 0;
if(expectPlainCharges) {
atomCharge = atof(labelString);
}
else {
// Get charge corresponding to labelString.
int chargeInt = get_charge_int_from_atom_label(labelString);
if(chargeInt <= 0) {
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN,
"error in read_molecule_file_in_xyz_format: label '%s' not recognized as an atom type.",
labelString);
return -1;
}
atomCharge = chargeInt;
}
result.addAtom(atomCharge,
coord_x * UNIT_one_Angstrom,
coord_y * UNIT_one_Angstrom,
coord_z * UNIT_one_Angstrom);
} // END FOR atomIndex
// accept only blank space and newlines after last atom
while(*p == ' ' || *p == '\t' || *p == '\n')
p++;
// Now p should point to end of buffer
if(*p != '\0')
{
do_output(LOG_CAT_ERROR, LOG_AREA_MAIN,
"error in read_molecule_file_in_xyz_format: garbage found after last atom.");
return -1;
}
assert(result.getNoOfAtoms() == nAtoms);
result.setNetCharge(netCharge);
return 0;
}
|