int read_population(FILE *f, long generation)
{
long i, j;
get_line(buf, 256, f);
psize = strtol(buf, (char **) NULL, 10);
if ((seq = (SEQ *) malloc(psize * sizeof(SEQ))) == NULL)
return (-1);
for (i = 0; i < psize; i++)
{
if (gn_read_id(&(seq[i].node_id), f) < 0)
{
fprintf(stderr, "error reading genome ID %ld, generation %ld -- exit\n", i, generation);
for (j = 0; j < i; j++)
free_genome(&(seq[i].genome));
free(seq);
return (-1);
}
gn_node_idstring(&(seq[i].node_id), seq[i].name);
if (read_genome(f, &(seq[i].genome), 0) < 0)
{
fprintf(stderr, "error reading genome %ld, generation %ld -- exit\n", i, generation);
for (j = 0; j < i; j++)
free_genome(&(seq[i].genome));
free(seq);
return (-1);
}
}
return (0);
}
int main (int argc, char** argv) {
if (argc != 7) usage(argc, argv);
string fasta_filename = argv[1];
string masks_filename = argv[2];
string scov_filename = argv[3];
out_file = argv[4];
window_size = atoi(argv[5]);
num_bins = atoi(argv[6]);
//fprintf(stderr,"Using window_size %d, num_bins %d\n",window_size,num_bins);
double bins_lambdas[num_bins];
sequence = read_genome(fasta_filename); //read in fasta file
//printf("Read in %d chars from %s\n",sequence_length,fasta_filename);
ifstream inf;
open_file_binary(inf, scov_filename);
scov = new double[sequence.length()];
inf.read((char *) scov, sizeof(double) * sequence.length());
inf.close();
//read in the masks
open_file_binary(inf, masks_filename);
masks = new char[sequence.length()];
if (masks ==NULL) {
fprintf(stderr,"Problem with allocating memory!\n");
exit(1);
}
inf.read(masks, sequence.length());
inf.close();
build_gc_bins(bins_lambdas);
delete[] scov;
delete[] masks;
return 0;
}
int write_generation_pirdna(FILE *infile, FILE *outfile, const char *fname, long generation, int code)
{
GENOME genome;
GN_NODE_ID node;
long i, psize;
char name[80], comment[512];
get_line(buf, 256, infile);
psize = strtol(buf, (char **) NULL, 10);
for (i = 0; i < psize; i++)
{
if (gn_read_id(&node, infile) < 0)
{
fprintf(stderr, "error reading genome ID %ld, generation %ld -- exit\n", i, generation);
exit (EXIT_FAILURE);
}
if (read_genome(infile, &genome, 0) < 0)
{
fprintf(stderr, "error reading genome %ld, generation %ld -- exit\n", i, generation);
exit (EXIT_FAILURE);
}
gn_node_idstring(&node, name);
sprintf(comment, "File: %s, generation: %ld, #%ld, length: %ld", fname, generation, i, genome.length);
switch (code)
{
case CODE_DNA:
write_pirdna(outfile, &genome, name, comment);
break;
case CODE_GC:
write_pirbin(outfile, &genome, name, comment, "cg");
break;
default:
fprintf(stderr, "Code type %d unknown\n", code);
free_genome(&genome);
return (-1);
}
free_genome(&genome);
}
return (0);
}
int read_genomes(FILE *genomefile, POPULATION *pop)
{
long i, j;
get_line(buf, 256, genomefile);
pop->size = strtol(buf, (char **) NULL, 10);
if ((pop->seq = (SEQ *) malloc(pop->size * sizeof(SEQ))) == NULL)
return (-1);
for (i = 0; i < pop->size; i++)
{
if (gn_read_id(&(pop->seq[i].node_id), genomefile) < 0)
{
fprintf(stderr, "error reading genome ID %ld\n", i);
for (j = 0; j < i; j++)
free_genome(&(pop->seq[i].genome));
free(pop->seq);
return (-1);
}
gn_node_idstring(&(pop->seq[i].node_id), pop->seq[i].name);
if (read_genome(genomefile, &(pop->seq[i].genome), 0) < 0)
{
fprintf(stderr, "error reading genome %ld\n", i);
for (j = 0; j < i; j++)
free_genome(&(pop->seq[i].genome));
free(pop->seq);
return (-1);
}
}
pop->max_len = 0;
for (i = 0; i < pop->size; i++)
{
if (pop->max_len < pop->seq[i].genome.length)
pop-> max_len = pop->seq[i].genome.length;
}
return (0);
}
/**
Returns:
-1 - if we need to terminate (EOF or mapping is not readable)
0 - if the line was processed correctly
*/
static int readline(FILE * fp){
char c; /* char red */
char name[MAX_NAME+1]; /* name of file */
char output_filename[1024];
int i; /* reused in few places */
FILE *fdw = NULL;
int ret = 0;
if((c=getc(fp))==EOF)
return -1;
lineNum++;
while(c=='\r')
c=getc(fp);
if(c=='\n')
return 0;
/* read name */
i = 0;
while(1){
name[i++]=c;
if(i==MAX_NAME){ /* out of buffer - cut the name */
name[i]='\0';
break;
}
if((c=getc(fp))==EOF)
return -1;
if(c=='\n')
return 0; /* ignore - not complete line */
while(c=='\r')
c=getc(fp);
if(c==FIELDS_DELIMITER){
name[i] = '\0';
break;
}
}
/* skip the rest, 5 tabs, until genome. Exit in case of EOL and EOL */
for(i=0; i<5; i++){
while(1){
c=getc(fp);
while(c=='\r')
c=getc(fp);
if(c==EOF)
return -1;
if(c=='\n')
return 0;
if(c==FIELDS_DELIMITER){
break;
}
}
}
/* Here we have genome ahead, so we can create the file */
create_filepath(name, output_filename);
if(debug) printf("%s\n", output_filename);
if((fdw = fopen(output_filename, "w")) == NULL){
fprintf(stderr, "Can't open output file %s. Please create target directory and verify write permissions\n", output_filename);
return -1;
}
if(fputs(header(), fdw)<0){
fprintf(stderr, "Can't write into file: %s\n", strerror(errno));
return -1;
}
else{
ret = read_genome(fp, fdw);
}
fclose(fdw);
return ret;
}
int write_generation_phylipdna(FILE *infile, FILE *outfile, long generation, int code)
{
SEQ *seq;
long i, j, l, psize, max_len;
char name[80];
get_line(buf, 256, infile);
psize = strtol(buf, (char **) NULL, 10);
if ((seq = (SEQ *) malloc(psize * sizeof(SEQ))) == NULL)
return (-1);
for (i = 0; i < psize; i++)
{
if (gn_read_id(&(seq[i].node_id), infile) < 0)
{
fprintf(stderr, "error reading genome ID %ld, generation %ld -- exit\n", i, generation);
for (j = 0; j < i; j++)
free_genome(&(seq[i].genome));
free(seq);
return (-1);
}
if (read_genome(infile, &(seq[i].genome), 0) < 0)
{
fprintf(stderr, "error reading genome %ld, generation %ld -- exit\n", i, generation);
for (j = 0; j < i; j++)
free_genome(&(seq[i].genome));
free(seq);
return (-1);
}
}
max_len = 0;
for (i = 0; i < psize; i++)
{
if (max_len < seq[i].genome.length)
max_len = seq[i].genome.length;
}
switch (code)
{
case CODE_DNA:
fprintf(outfile, "%ld %ld\n", psize, max_len * 4);
for (i = 0; i < psize; i++)
{
gn_node_idstring(&(seq[i].node_id), name);
l = strlen(name);
for (j = 0; j < 10; j++)
{
if (j < l)
fputc(name[j], outfile);
else
fputc(' ', outfile);
}
for (j = 0; j < ((max_len < 13) ? max_len : 13); j++)
{
if (j < seq[i].genome.length)
fprint_dnachars(outfile, seq[i].genome.g[j]);
else
fprintf(outfile, "----");
}
fprintf(outfile, "\n");
}
for (l = j; l < max_len; l += 15)
{
fprintf(outfile, "\n");
for (i = 0; i < psize; i++)
{
for (j = l; j < ((l + 15 < max_len) ? l + 15 : max_len); j++)
{
if (j < seq[i].genome.length)
fprint_dnachars(outfile, seq[i].genome.g[j]);
else
fprintf(outfile, "----");
}
fprintf(outfile, "\n");
}
}
break;
case CODE_GC:
fprintf(outfile, "%ld %ld\n", psize, max_len * 8);
for (i = 0; i < psize; i++)
{
gn_node_idstring(&(seq[i].node_id), name);
l = strlen(name);
for (j = 0; j < 10; j++)
{
if (j < l)
fputc(name[j], outfile);
else
fputc(' ', outfile);
}
for (j = 0; j < ((max_len < 7) ? max_len : 7); j++)
{
if (j < seq[i].genome.length)
fprint_binchars(outfile, seq[i].genome.g[j], "cg");
else
fprintf(outfile, "--------");
}
fprintf(outfile, "\n");
}
for (l = j; l < max_len; l += 8)
{
fprintf(outfile, "\n");
for (i = 0; i < psize; i++)
{
for (j = l; j < ((l + 8 < max_len) ? l + 8 : max_len); j++)
{
if (j < seq[i].genome.length)
fprint_binchars(outfile, seq[i].genome.g[j], "cg");
else
fprintf(outfile, "--------");
}
fprintf(outfile, "\n");
}
}
break;
default:
fprintf(stderr, "Code type %d unknown\n", code);
for (i = 0; i < psize; i++)
free_genome(&(seq[i].genome));
free(seq);
return (-1);
}
for (i = 0; i < psize; i++)
free_genome(&(seq[i].genome));
free(seq);
return (0);
}
