src/gromacs/gmxpreprocess/xlate.cpp

   1 /*
   2  * This file is part of the GROMACS molecular simulation package.
   3  *
   4  * Copyright (c) 1991-2000, University of Groningen, The Netherlands.
   5  * Copyright (c) 2001-2004, The GROMACS development team.
   6  * Copyright (c) 2013,2014,2015,2017, by the GROMACS development team, led by
   7  * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
   8  * and including many others, as listed in the AUTHORS file in the
   9  * top-level source directory and at http://www.gromacs.org.
  10  *
  11  * GROMACS is free software; you can redistribute it and/or
  12  * modify it under the terms of the GNU Lesser General Public License
  13  * as published by the Free Software Foundation; either version 2.1
  14  * of the License, or (at your option) any later version.
  15  *
  16  * GROMACS is distributed in the hope that it will be useful,
  17  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  18  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  19  * Lesser General Public License for more details.
  20  *
  21  * You should have received a copy of the GNU Lesser General Public
  22  * License along with GROMACS; if not, see
  23  * http://www.gnu.org/licenses, or write to the Free Software Foundation,
  24  * Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA.
  25  *
  26  * If you want to redistribute modifications to GROMACS, please
  27  * consider that scientific software is very special. Version
  28  * control is crucial - bugs must be traceable. We will be happy to
  29  * consider code for inclusion in the official distribution, but
  30  * derived work must not be called official GROMACS. Details are found
  31  * in the README & COPYING files - if they are missing, get the
  32  * official version at http://www.gromacs.org.
  33  *
  34  * To help us fund GROMACS development, we humbly ask that you cite
  35  * the research papers on the package. Check out http://www.gromacs.org.
  36  */
  37 #include "gmxpre.h"
  38
  39 #include "xlate.h"
  40
  41 #include <ctype.h>
  42 #include <string.h>
  43
  44 #include "gromacs/gmxpreprocess/fflibutil.h"
  45 #include "gromacs/gmxpreprocess/hackblock.h"
  46 #include "gromacs/topology/residuetypes.h"
  47 #include "gromacs/topology/symtab.h"
  48 #include "gromacs/utility/cstringutil.h"
  49 #include "gromacs/utility/fatalerror.h"
  50 #include "gromacs/utility/futil.h"
  51 #include "gromacs/utility/smalloc.h"
  52 #include "gromacs/utility/strdb.h"
  53
  54 typedef struct {
  55     char *filebase;
  56     char *res;
  57     char *atom;
  58     char *replace;
  59 } t_xlate_atom;
  60
  61 static void get_xlatoms(const char *fn, FILE *fp,
  62                         int *nptr, t_xlate_atom **xlptr)
  63 {
  64     char          filebase[STRLEN];
  65     char          line[STRLEN];
  66     char          abuf[1024], rbuf[1024], repbuf[1024], dumbuf[1024];
  67     char         *_ptr;
  68     int           n, na, idum;
  69     t_xlate_atom *xl;
  70
  71     fflib_filename_base(fn, filebase, STRLEN);
  72
  73     n  = *nptr;
  74     xl = *xlptr;
  75
  76     while (get_a_line(fp, line, STRLEN))
  77     {
  78         na = sscanf(line, "%s%s%s%s", rbuf, abuf, repbuf, dumbuf);
  79         /* Check if we are reading an old format file with the number of items
  80          * on the first line.
  81          */
  82         if (na == 1 && n == *nptr && sscanf(rbuf, "%d", &idum) == 1)
  83         {
  84             continue;
  85         }
  86         if (na != 3)
  87         {
  88             gmx_fatal(FARGS, "Expected a residue name and two atom names in file '%s', not '%s'", fn, line);
  89         }
  90
  91         srenew(xl, n+1);
  92         xl[n].filebase = gmx_strdup(filebase);
  93
  94         /* Use wildcards... */
  95         if (strcmp(rbuf, "*") != 0)
  96         {
  97             xl[n].res = gmx_strdup(rbuf);
  98         }
  99         else
 100         {
 101             xl[n].res = nullptr;
 102         }
 103
 104         /* Replace underscores in the string by spaces */
 105         while ((_ptr = strchr(abuf, '_')) != nullptr)
 106         {
 107             *_ptr = ' ';
 108         }
 109
 110         xl[n].atom    = gmx_strdup(abuf);
 111         xl[n].replace = gmx_strdup(repbuf);
 112         n++;
 113     }
 114
 115     *nptr  = n;
 116     *xlptr = xl;
 117 }
 118
 119 static void done_xlatom(int nxlate, t_xlate_atom *xlatom)
 120 {
 121     int i;
 122
 123     for (i = 0; (i < nxlate); i++)
 124     {
 125         sfree(xlatom[i].filebase);
 126         if (xlatom[i].res != nullptr)
 127         {
 128             sfree(xlatom[i].res);
 129         }
 130         sfree(xlatom[i].atom);
 131         sfree(xlatom[i].replace);
 132     }
 133     sfree(xlatom);
 134 }
 135
 136 void rename_atoms(const char *xlfile, const char *ffdir,
 137                   t_atoms *atoms, t_symtab *symtab, const t_restp *restp,
 138                   gmx_bool bResname, gmx_residuetype_t *rt, gmx_bool bReorderNum,
 139                   gmx_bool bVerbose)
 140 {
 141     FILE         *fp;
 142     int           nxlate, a, i, resind;
 143     t_xlate_atom *xlatom;
 144     int           nf;
 145     char        **f;
 146     char          c, *rnm, atombuf[32], *ptr0, *ptr1;
 147     gmx_bool      bReorderedNum, bRenamed, bMatch;
 148     gmx_bool      bStartTerm, bEndTerm;
 149
 150     nxlate = 0;
 151     xlatom = nullptr;
 152     if (xlfile != nullptr)
 153     {
 154         fp = libopen(xlfile);
 155         get_xlatoms(xlfile, fp, &nxlate, &xlatom);
 156         fclose(fp);
 157     }
 158     else
 159     {
 160         nf = fflib_search_file_end(ffdir, ".arn", FALSE, &f);
 161         for (i = 0; i < nf; i++)
 162         {
 163             fp = fflib_open(f[i]);
 164             get_xlatoms(f[i], fp, &nxlate, &xlatom);
 165             gmx_ffclose(fp);
 166             sfree(f[i]);
 167         }
 168         sfree(f);
 169     }
 170
 171     for (a = 0; (a < atoms->nr); a++)
 172     {
 173         resind = atoms->atom[a].resind;
 174
 175         bStartTerm = (resind == 0) || atoms->resinfo[resind].chainnum != atoms->resinfo[resind-1].chainnum;
 176         bEndTerm   = (resind >= atoms->nres-1) || atoms->resinfo[resind].chainnum != atoms->resinfo[resind+1].chainnum;
 177
 178         if (bResname)
 179         {
 180             rnm = *(atoms->resinfo[resind].name);
 181         }
 182         else
 183         {
 184             rnm = *(atoms->resinfo[resind].rtp);
 185         }
 186
 187         strcpy(atombuf, *(atoms->atomname[a]));
 188         bReorderedNum = FALSE;
 189         if (bReorderNum)
 190         {
 191             if (isdigit(atombuf[0]))
 192             {
 193                 c = atombuf[0];
 194                 for (i = 0; ((size_t)i < strlen(atombuf)-1); i++)
 195                 {
 196                     atombuf[i] = atombuf[i+1];
 197                 }
 198                 atombuf[i]    = c;
 199                 bReorderedNum = TRUE;
 200             }
 201         }
 202         bRenamed = FALSE;
 203         for (i = 0; (i < nxlate) && !bRenamed; i++)
 204         {
 205             /* Check if the base file name of the rtp and arn entry match */
 206             if (restp == nullptr ||
 207                 gmx_strcasecmp(restp[resind].filebase, xlatom[i].filebase) == 0)
 208             {
 209                 /* Match the residue name */
 210                 bMatch = (xlatom[i].res == nullptr ||
 211                           (gmx_strcasecmp("protein-nterm", xlatom[i].res) == 0 &&
 212                            gmx_residuetype_is_protein(rt, rnm) && bStartTerm) ||
 213                           (gmx_strcasecmp("protein-cterm", xlatom[i].res) == 0 &&
 214                            gmx_residuetype_is_protein(rt, rnm) && bEndTerm) ||
 215                           (gmx_strcasecmp("protein", xlatom[i].res) == 0 &&
 216                            gmx_residuetype_is_protein(rt, rnm)) ||
 217                           (gmx_strcasecmp("DNA", xlatom[i].res) == 0 &&
 218                            gmx_residuetype_is_dna(rt, rnm)) ||
 219                           (gmx_strcasecmp("RNA", xlatom[i].res) == 0 &&
 220                            gmx_residuetype_is_rna(rt, rnm)));
 221                 if (!bMatch)
 222                 {
 223                     ptr0 = rnm;
 224                     ptr1 = xlatom[i].res;
 225                     while (ptr0[0] != '\0' && ptr1[0] != '\0' &&
 226                            (ptr0[0] == ptr1[0] || ptr1[0] == '?'))
 227                     {
 228                         ptr0++;
 229                         ptr1++;
 230                     }
 231                     bMatch = (ptr0[0] == '\0' && ptr1[0] == '\0');
 232                 }
 233                 if (bMatch && strcmp(atombuf, xlatom[i].atom) == 0)
 234                 {
 235                     /* We have a match. */
 236                     /* Don't free the old atomname,
 237                      * since it might be in the symtab.
 238                      */
 239                     ptr0 = gmx_strdup(xlatom[i].replace);
 240                     if (bVerbose)
 241                     {
 242                         printf("Renaming atom '%s' in residue %d %s to '%s'\n",
 243                                *atoms->atomname[a],
 244                                atoms->resinfo[resind].nr,
 245                                *atoms->resinfo[resind].name,
 246                                ptr0);
 247                     }
 248                     atoms->atomname[a] = put_symtab(symtab, ptr0);
 249                     bRenamed           = TRUE;
 250                 }
 251             }
 252         }
 253         if (bReorderedNum && !bRenamed)
 254         {
 255             atoms->atomname[a] = put_symtab(symtab, atombuf);
 256         }
 257     }
 258
 259     done_xlatom(nxlate, xlatom);
 260 }