static int
add_seq_to_seq_lib(seq_lib *sl,
char *seq,
char *seq_id_plus,
const char *errfrag) {
int i = sl->seq_num;
int ss = sl->storage_size;
char offender;
char buf[2];
/* We need to allocate more storage */
if (i >= ss) {
ss += INIT_LIB_SIZE;
sl->storage_size = ss;
sl->names = (char**) p3sl_safe_realloc(sl->names, ss*sizeof(*sl->names));
sl->seqs = (char**) p3sl_safe_realloc(sl->seqs , ss*sizeof(*sl->seqs));
sl->rev_compl_seqs = p3sl_safe_realloc(sl->seqs , ss*sizeof(*sl->rev_compl_seqs));
sl->weight= (double*) p3sl_safe_realloc(sl->weight,
ss*sizeof(*sl->weight));
}
sl->seq_num = i + 1;
sl->names[i] = (char*) p3sl_safe_malloc(strlen(seq_id_plus) + 1);
strcpy(sl->names[i], seq_id_plus);
sl->weight[i] = parse_seq_name(sl->names[i]);
if(sl->weight[i] < 0) {
p3sl_append_new_chunk(&sl->error, "Illegal weight");
return 1;
}
sl->rev_compl_seqs[i] = sl->seqs[i] = (char*) p3sl_safe_malloc(strlen(seq) + 1);
strcpy(sl->seqs[i], seq);
if(strlen(sl->seqs[i]) == 0) {
p3sl_append_new_chunk(&sl->error, "Empty sequence in ");
return 1;
}
offender = upcase_and_check_char(sl->seqs[i]);
if ('\0' != offender) {
buf[0] = offender;
buf[1] = '\0';
p3sl_append(&sl->warning, "Unrecognized character (");
p3sl_append(&sl->warning, buf);
p3sl_append(&sl->warning, ") in ");
p3sl_append(&sl->warning, errfrag);
p3sl_append(&sl->warning, ", entry ");
p3sl_append(&sl->warning, seq_id_plus);
}
return 0;
}
/******************************************************************************
* Read from the current position in the file to the first symbol after the
* start of the next sequence. Set the value of the current sequence.
*
* Returns TRUE if it was able to advance to the next sequence, FALSE if
* EOF reached before the next sequence was found. Dies if other errors
* encountered.
*****************************************************************************/
BOOLEAN_T go_to_next_sequence_in_seq_reader_from_fasta(DATA_BLOCK_READER_T *reader) {
BOOLEAN_T result = FALSE;
SEQ_READER_FROM_FASTA_T *fasta_reader
= (SEQ_READER_FROM_FASTA_T *) get_data_block_reader_data(reader);
fasta_reader->current_position = 0;
int c = 0;
while((c = fgetc(fasta_reader->fasta_file)) != EOF) {
if (fasta_reader->at_start_of_line == TRUE && c == '>') {
break;
}
else if (c == '\n') {
fasta_reader->at_start_of_line = TRUE;
}
else {
fasta_reader->at_start_of_line = FALSE;
}
}
// At this point c is '>' or EOF
if (c == '>') {
BOOLEAN_T found_genomic_coordinates = FALSE;
result = read_seq_header_from_seq_reader_from_fasta(fasta_reader);
if (result == TRUE && fasta_reader->parse_genomic_coord == TRUE) {
// Look for genomic coordinates in header
found_genomic_coordinates = parse_genomic_coordinates(fasta_reader);
}
if (found_genomic_coordinates == FALSE) {
// Look for whitespace in header
// The sequence name is the string before the white space.
BOOLEAN_T found_name = FALSE;
found_name = parse_seq_name(fasta_reader);
if (found_name == FALSE) {
die(
"Unable to find sequence name in header %s.\n",
fasta_reader->sequence_header
);
}
}
}
else {
if (ferror(fasta_reader->fasta_file)) {
die(
"Error reading file:%s.\nError message: %s\n",
fasta_reader->filename,
strerror(ferror(fasta_reader->fasta_file))
);
}
else if (feof(fasta_reader->fasta_file)) {
// Reached EOF before reaching the start of the sequence
result = FALSE;
}
}
return result;
}
