static int gt_extractseq_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
ExtractSeqArguments *arguments = tool_arguments;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
if (gt_str_length(arguments->fastakeyfile)) {
had_err = process_fastakeyfile(arguments->fastakeyfile, argc - parsed_args,
argv + parsed_args, arguments->width,
arguments->outfp, err);
}
else {
GtBioseqIterator *bsi;
GtBioseq *bs;
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!had_err &&
!(had_err = gt_bioseq_iterator_next(bsi, &bs, err)) && bs) {
if (arguments->frompos) {
had_err = extractseq_pos(arguments->outfp, bs, arguments->frompos,
arguments->topos, arguments->width, err);
}
else {
had_err = extractseq_match(arguments->outfp, bs,
gt_str_get(arguments->pattern),
arguments->width, err);
}
gt_bioseq_delete(bs);
}
gt_bioseq_iterator_delete(bsi);
}
return had_err;
}
static int gt_seqmutate_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
MutateArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
GtSeq *mutated_seq;
int had_err;
gt_error_check(err);
gt_assert(arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
mutated_seq = gt_mutate_seq(gt_bioseq_get_description(bioseq, i),
gt_bioseq_get_sequence(bioseq, i),
gt_bioseq_get_sequence_length(bioseq, i),
gt_bioseq_get_alphabet(bioseq),
arguments->rate);
gt_fasta_show_entry(gt_seq_get_description(mutated_seq),
gt_seq_get_orig(mutated_seq),
gt_seq_length(mutated_seq),
arguments->width, arguments->outfp);
gt_seq_delete(mutated_seq);
}
gt_bioseq_delete(bioseq);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gt_seqfilter_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqFilterArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
GtBioseq *bioseq;
unsigned long i;
unsigned long long passed = 0, filtered = 0, num_of_sequences = 0;
int had_err = 0;
gt_error_check(err);
gt_assert(tool_arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
if ((arguments->minlength == GT_UNDEF_ULONG ||
gt_bioseq_get_sequence_length(bioseq, i) >= arguments->minlength) &&
(arguments->maxlength == GT_UNDEF_ULONG ||
gt_bioseq_get_sequence_length(bioseq, i) <= arguments->maxlength) &&
(arguments->maxseqnum == GT_UNDEF_ULONG ||
passed + 1 <= arguments->maxseqnum)) {
gt_fasta_show_entry(gt_bioseq_get_description(bioseq, i),
gt_bioseq_get_sequence(bioseq, i),
gt_bioseq_get_sequence_length(bioseq, i),
arguments->width, arguments->outfp);
passed++;
}
else
filtered++;
num_of_sequences++;
}
gt_bioseq_delete(bioseq);
}
/* show statistics */
if (!had_err) {
gt_assert(passed + filtered == num_of_sequences);
fprintf(stderr, "# %llu out of %llu sequences have been removed (%.3f%%)\n",
filtered, num_of_sequences,
((double) filtered / num_of_sequences) * 100.0);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gt_shredder_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtShredderArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
int had_err;
GtStr *desc;
gt_error_check(err);
gt_assert(arguments);
/* init */
desc = gt_str_new();
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
/* shredder */
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
for (i = 0; i < arguments->coverage; i++) {
GtShredder *shredder;
unsigned long fragment_length;
const char *fragment;
shredder = gt_shredder_new(bioseq, arguments->minlength,
arguments->maxlength);
gt_shredder_set_overlap(shredder, arguments->overlap);
gt_shredder_set_sample_probability(shredder,
arguments->sample_probability);
while ((fragment = gt_shredder_shred(shredder, &fragment_length, desc))) {
gt_str_append_cstr(desc, " [shreddered fragment]");
gt_fasta_show_entry(gt_str_get(desc), fragment, fragment_length, 0);
}
gt_shredder_delete(shredder);
}
gt_bioseq_delete(bioseq);
}
/* free */
gt_bioseq_iterator_delete(bsi);
gt_str_delete(desc);
return had_err;
}
static int gt_seqtransform_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqtransformArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
unsigned long i;
GtBioseq *bioseq;
int had_err;
gt_error_check(err);
gt_assert(arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
GtAlphabet *alphabet;
bool is_protein;
alphabet = gt_bioseq_get_alphabet(bioseq);
is_protein = gt_alphabet_is_protein(alphabet);
for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
const char *desc, *suffix = NULL;
char *seq;
unsigned long seqlen;
desc = gt_bioseq_get_description(bioseq, i);
seq = gt_bioseq_get_sequence(bioseq, i);
seqlen = gt_bioseq_get_sequence_length(bioseq, i);
if (arguments->addstopaminos && is_protein && seqlen &&
seq[seqlen-1] != GT_STOP_AMINO) {
suffix = GT_STOP_AMINO_CSTR;
}
gt_fasta_show_entry_with_suffix(desc, seq, seqlen, suffix,
arguments->width, arguments->outfp);
gt_free(seq);
}
gt_bioseq_delete(bioseq);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
static int gt_seqfilter_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SeqFilterArguments *arguments = tool_arguments;
GtBioseqIterator *bsi;
GtBioseq *bioseq;
GtUint64 passed = 0, filtered = 0, num_of_sequences = 0, steps = 0;
int had_err = 0;
gt_error_check(err);
gt_assert(tool_arguments);
bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);
while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) &&
bioseq != NULL) {
GtUword i;
GtUint64 current_num = gt_bioseq_number_of_sequences(bioseq);
for (i = 0;
i < current_num &&
(arguments->maxseqnum == GT_UNDEF_UWORD ||
passed + 1 <= arguments->maxseqnum);
i++) {
char *seq;
if ((arguments->step == 1 ||
steps + 1 == arguments->step) &&
(arguments->sample_prob == 1.0 ||
gt_rand_0_to_1() <= arguments->sample_prob) &&
(arguments->minlength == GT_UNDEF_UWORD ||
gt_bioseq_get_sequence_length(bioseq, i) >= arguments->minlength) &&
(arguments->maxlength == GT_UNDEF_UWORD ||
gt_bioseq_get_sequence_length(bioseq, i) <= arguments->maxlength)) {
seq = gt_bioseq_get_sequence(bioseq, i);
gt_fasta_show_entry(gt_bioseq_get_description(bioseq, i),
seq,
gt_bioseq_get_sequence_length(bioseq, i),
arguments->width, arguments->outfp);
gt_free(seq);
passed++;
}
else {
filtered++;
}
steps = (steps + 1 == arguments->step) ? 0 : steps + 1;
}
filtered += current_num - i;
num_of_sequences += current_num;
gt_bioseq_delete(bioseq);
}
/* show statistics */
if (!had_err) {
gt_assert(passed + filtered == num_of_sequences);
fprintf(stderr, "# " GT_LLU " out of " GT_LLU
" sequences have been removed (%.3f%%)\n",
filtered, num_of_sequences,
((double) filtered / num_of_sequences) * 100.0);
}
gt_bioseq_iterator_delete(bsi);
return had_err;
}
