int main(int arfc, char **arfv)
{
/*
arfv[1] is the input file with sequence on the first line and constraint on the second line
takes constraints of the ( ) and [ ] variety
arfv[2] is the list of structures output by subopt to check
*/
if (arfc != 3) {
usage(arfv[0]);
exit(1);
}
FILE *fin, *fout;
int i, *pos, *neg;
char *C;
if (arfv[1][0] == '-' && arfv[1][1] == '\0')
fin = stdin;
else if (!(fin = fopen(arfv[1], "rb"))) {
fprintf(stderr, "unable to open %s, bailing\n", arfv[1]);
exit(1);
}
if (arfv[2][0] == '-' && arfv[2][1] == '\0')
fout = stdin;
else if (!(fout = fopen(arfv[2], "rb"))) {
fprintf(stderr, "unable to open %s, bailing\n", arfv[2]);
if (stdin != fin)
fclose(fin);
exit(1);
}
skip_sequence(fin);
C = get_structure(fin);
make_pair_table(C, &pos, &neg);
printf("constraint string:\n%s\n", C);
free(C);
printf("forced pairs:");
for (i = 1; i <= len; ++i) {
if (pos[i])
printf(" (%d,%d)", i, pos[i]);
}
printf("\n");
printf("forbidden pairs:");
for (i = 1; i <= len; ++i) {
if (neg[i])
printf(" (%d,%d)", i, neg[i]);
}
printf("\n");
while (!feof(fout)) {
char *s;
int *ps;
s = get_structure(fout);
make_pair_table(s, &ps, NULL);
if (s[0]) {
compare(s, ps, pos, neg);
}
free(s);
free(ps);
}
free(pos);
free(neg);
if (stdin != fin)
fclose(fin);
if (stdin != fin)
fclose(fout);
return 0;
}
static bool
process_sequence_aux (Genomicpos_T *seglength, Table_T accsegmentpos_table, Tableint_T chrlength_table,
char *fileroot, int ncontigs) {
char Buffer[BUFFERSIZE], accession_p[BUFFERSIZE], *accession,
chrpos_string[BUFFERSIZE], *chr_string, *coords;
Genomicpos_T chrpos1, chrpos2, lower, upper;
Genomicpos_T universal_coord = 0U;
bool revcompp;
int nitems;
/* Store sequence info */
if (fgets(Buffer,BUFFERSIZE,stdin) == NULL) {
return false;
}
if ((nitems = sscanf(Buffer,"%s %s %u",accession_p,chrpos_string,&universal_coord)) < 2) {
fprintf(stderr,"Can't parse line %s\n",Buffer);
exit(1);
} else {
if (ncontigs < 100) {
fprintf(stderr,"Logging contig %s at %s in genome %s\n",accession_p,chrpos_string,fileroot);
} else if (ncontigs == 100) {
fprintf(stderr,"More than 100 contigs. Will stop printing messages\n");
}
if (!index(chrpos_string,':')) {
fprintf(stderr,"Can't parse chromosomal coordinates %s\n",chrpos_string);
exit(1);
} else {
chr_string = strtok(chrpos_string,":");
coords = strtok(NULL,":");
if (sscanf(coords,"%u..%u",&chrpos1,&chrpos2) == 2) {
/* 1:3..5, one-based, inclusive => (2,5), zero-based, boundaries */
if (chrpos1 <= chrpos2) {
chrpos1--;
revcompp = false;
lower = chrpos1;
upper = chrpos2;
} else {
chrpos2--;
revcompp = true;
lower = chrpos2;
upper = chrpos1;
}
} else if (sscanf(coords,"%u",&chrpos1) == 1) {
/* 1:3, one-based, inclusive => (3,3), zero-based, boundaries */
revcompp = false;
lower = upper = chrpos1;
} else {
fprintf(stderr,"Can't parse chromosomal coordinates %s\n",coords);
exit(1);
}
}
#if 0
/* No longer supporting strains/types */
p = Buffer;
while (*p != '\0' && !isspace((int) *p)) { p++; } /* Skip to first space */
while (*p != '\0' && isspace((int) *p)) { p++; } /* Skip past first space */
while (*p != '\0' && !isspace((int) *p)) { p++; } /* Skip to second space */
while (*p != '\0' && isspace((int) *p)) { p++; } /* Skip past second space */
if (*p == '\0') {
contigtype = 0; /* Empty type string */
} else {
if ((ptr = rindex(p,'\n')) != NULL) {
while (isspace((int) *ptr)) { ptr--; } /* Erase empty space */
ptr++;
*ptr = '\0';
}
if ((contigtype = Tableint_get(contigtype_table,(void *) p)) == 0) {
debug(printf("Storing type %s.\n",p));
/* Store types as 1-based */
contigtype = Tableint_length(contigtype_table) + 1;
typestring = (char *) CALLOC(strlen(p)+1,sizeof(char));
strcpy(typestring,p);
Tableint_put(contigtype_table,(void *) typestring,contigtype);
*contigtypelist = List_push(*contigtypelist,typestring);
}
}
#endif
/* The '>' character was already stripped off by the last call to count_sequence() */
accession = (char *) CALLOC(strlen(accession_p)+1,sizeof(char));
strcpy(accession,accession_p);
}
if (rawp == true) {
*seglength = upper - lower;
fprintf(stderr,"Skipping %u characters\n",*seglength);
skip_sequence(*seglength);
} else {
*seglength = count_sequence();
if (*seglength != upper - lower) {
fprintf(stderr,"%s has expected sequence length %u-%u=%u but actual length %u\n",
accession,upper,lower,upper-lower,*seglength);
}
}
if (nitems < 3) {
universal_coord = 0U;
}
store_accession(accsegmentpos_table,chrlength_table,
accession,chr_string,lower,upper,revcompp,
*seglength,/*contigtype*/0,universal_coord);
return true;
}
