static int select_stream_next(GtNodeStream *ns, GtGenomeNode **gn, GtError *err)
{
GtSelectStream *fs;
int had_err;
gt_error_check(err);
fs = gt_select_stream_cast(ns);
/* we still have nodes in the buffer */
if (gt_select_visitor_node_buffer_size(fs->select_visitor)) {
/* return one of them */
*gn = gt_select_visitor_get_node(fs->select_visitor);
return 0;
}
/* no nodes in the buffer -> get new nodes */
while (!(had_err = gt_node_stream_next(fs->in_stream, gn, err)) && *gn) {
gt_assert(*gn && !had_err);
had_err = gt_genome_node_accept(*gn, fs->select_visitor, err);
if (had_err) {
/* we own the node -> delete it */
gt_genome_node_delete(*gn);
*gn = NULL;
break;
}
if (gt_select_visitor_node_buffer_size(fs->select_visitor)) {
*gn = gt_select_visitor_get_node(fs->select_visitor);
return 0;
}
}
/* either we have an error or no new node */
gt_assert(had_err || !*gn);
return had_err;
}
static int filter_stream_next(GtNodeStream *gs, GtGenomeNode **gn, GtError *err)
{
GtFilterStream *fs;
int had_err;
gt_error_check(err);
fs = gt_filter_stream_cast(gs);
/* we still have nodes in the buffer */
if (gt_filter_visitor_node_buffer_size(fs->filter_visitor)) {
/* return one of them */
*gn = gt_filter_visitor_get_node(fs->filter_visitor);
return 0;
}
/* no nodes in the buffer -> get new nodes */
while (!(had_err = gt_node_stream_next(fs->in_stream, gn, err)) && *gn) {
gt_assert(*gn && !had_err);
had_err = gt_genome_node_accept(*gn, fs->filter_visitor, err);
if (had_err)
break;
if (gt_filter_visitor_node_buffer_size(fs->filter_visitor)) {
*gn = gt_filter_visitor_get_node(fs->filter_visitor);
return 0;
}
}
/* either we have an error or no new node */
gt_assert(had_err || !*gn);
return had_err;
}
int gt_feature_index_add_gff3file(GtFeatureIndex *feature_index,
const char *gff3file, GtError *err)
{
GtNodeStream *gff3_in_stream;
GtGenomeNode *gn;
GtArray *tmp;
int had_err = 0;
GtUword i;
gt_error_check(err);
gt_assert(feature_index && gff3file);
tmp = gt_array_new(sizeof (GtGenomeNode*));
gff3_in_stream = gt_gff3_in_stream_new_unsorted(1, &gff3file);
while (!(had_err = gt_node_stream_next(gff3_in_stream, &gn, err)) && gn)
gt_array_add(tmp, gn);
if (!had_err) {
GtNodeVisitor *feature_visitor = gt_feature_visitor_new(feature_index);
for (i=0;i<gt_array_size(tmp);i++) {
gn = *(GtGenomeNode**) gt_array_get(tmp, i);
/* no need to lock, add_*_node() is synchronized */
had_err = gt_genome_node_accept(gn, feature_visitor, NULL);
gt_assert(!had_err); /* cannot happen */
}
gt_node_visitor_delete(feature_visitor);
}
gt_node_stream_delete(gff3_in_stream);
for (i=0;i<gt_array_size(tmp);i++)
gt_genome_node_delete(*(GtGenomeNode**) gt_array_get(tmp, i));
gt_array_delete(tmp);
return had_err;
}
static int print_to_file_drophandler(GtGenomeNode *gn, void *data,
GtError *err)
{
GtNodeVisitor *v;
gt_assert(gn && data);
v = (GtNodeVisitor*) data;
return gt_genome_node_accept(gn, v, err);
}
static int snp_annotator_stream_process_snp(void **elem, void *info,
GtError *err)
{
int had_err = 0;
GtGenomeNode *snp = *(GtGenomeNode**) elem;
GtNodeVisitor *sav = (GtNodeVisitor*) info;
had_err = gt_genome_node_accept(snp, sav, err);
return had_err;
}
static int gt_ltr_cluster_stream_next(GtNodeStream *ns,
GtGenomeNode **gn,
GtError *err)
{
GtLTRClusterStream *lcs;
GtGenomeNode *ref_gn;
int had_err = 0;
unsigned long i = 0;
gt_error_check(err);
lcs = gt_ltr_cluster_stream_cast(ns);
if (lcs->first_next) {
while (!(had_err = gt_node_stream_next(lcs->in_stream, gn, err)) && *gn) {
gt_assert(*gn && !had_err);
ref_gn = gt_genome_node_ref(*gn);
gt_array_add(lcs->nodes, ref_gn);
had_err = gt_genome_node_accept(*gn, (GtNodeVisitor*) lcs->lcv, err);
if (had_err) {
gt_genome_node_delete(*gn);
*gn = NULL;
break;
}
}
lcs->feat_to_encseq =
gt_ltr_cluster_prepare_seq_visitor_get_encseqs(lcs->lcv);
lcs->feat_to_encseq_keys =
gt_ltr_cluster_prepare_seq_visitor_get_features(lcs->lcv);
if (!had_err) {
for (i = 0; i < gt_str_array_size(lcs->feat_to_encseq_keys); i++) {
had_err = process_feature(lcs,
gt_str_array_get(lcs->feat_to_encseq_keys, i),
err);
if (had_err)
break;
}
}
if (!had_err) {
*gn = *(GtGenomeNode**) gt_array_get(lcs->nodes, lcs->next_index);
lcs->next_index++;
lcs->first_next = false;
return 0;
}
} else {
if (lcs->next_index >= gt_array_size(lcs->nodes))
*gn = NULL;
else {
*gn = *(GtGenomeNode**) gt_array_get(lcs->nodes, lcs->next_index);
lcs->next_index++;
}
return 0;
}
return had_err;
}
static int feature_stream_next(GtNodeStream *gs, GtGenomeNode **gn,
GtError *err)
{
GtFeatureStream *feature_stream;
int had_err;
gt_error_check(err);
feature_stream = feature_stream_cast(gs);
had_err = gt_node_stream_next(feature_stream->in_stream, gn, err);
if (!had_err && *gn)
had_err = gt_genome_node_accept(*gn, feature_stream->feature_visitor, err);
return had_err;
}
static int inter_feature_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GtInterFeatureStream *ais;
int had_err;
gt_error_check(err);
ais = gt_inter_feature_stream_cast(ns);
had_err = gt_node_stream_next(ais->in_stream, gn, err);
if (!had_err && *gn)
had_err = gt_genome_node_accept(*gn, ais->inter_feature_visitor, err);
return had_err;
}
static int genome_node_lua_accept(lua_State *L)
{
GtGenomeNode **gn;
GtNodeVisitor **gv;
GtError *err;
gn = check_genome_node(L, 1);
gv = check_genome_visitor(L, 2);
err = gt_error_new();
if (gt_genome_node_accept(*gn, *gv, err))
return gt_lua_error(L, err);
gt_error_delete(err);
return 0;
}
static int sequence_node_add_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GtSequenceNodeAddStream *s;
int had_err;
gt_error_check(err);
s = gt_sequence_node_add_stream_cast(ns);
/* stream nodes as long as we have some, record seen seqids */
if (!(had_err = gt_node_stream_next(s->in_stream, gn, err)) && *gn) {
had_err = gt_genome_node_accept(*gn, s->collect_vis, err);
}
/* if there are no more */
if (!had_err && !*gn) {
if (!s->seqids) {
s->seqids = gt_cstr_table_get_all(s->seqid_table);
}
gt_assert(s->seqids);
if (s->cur_seqid >= gt_str_array_size(s->seqids)) {
*gn = NULL;
return 0;
} else {
GtGenomeNode *new_sn;
GtUword len;
char *seq = NULL;
GtStr *seqid = gt_str_new(),
*seqstr = gt_str_new();
gt_str_append_cstr(seqid, gt_str_array_get(s->seqids, s->cur_seqid));
had_err = gt_region_mapping_get_sequence_length(s->rm, &len, seqid, err);
if (!had_err) {
had_err = gt_region_mapping_get_sequence(s->rm, &seq, seqid, 1, len,
err);
}
if (!had_err) {
gt_str_append_cstr_nt(seqstr, seq, len);
new_sn = gt_sequence_node_new(gt_str_get(seqid), seqstr);
*gn = new_sn;
}
s->cur_seqid++;
gt_free(seq);
gt_str_delete(seqid);
gt_str_delete(seqstr);
}
}
return had_err;
}
static int snp_annotator_stream_process_current_gene(GtSNPAnnotatorStream *sas,
GtError *err)
{
int had_err = 0;
GtUword i;
GtUword nof_genes = gt_array_size(sas->cur_gene_set);
gt_error_check(err);
if (gt_queue_size(sas->snps) > 0) {
/* we need to process SNPs for a gene cluster*/
gt_assert(gt_queue_size(sas->outqueue) == 0);
for (i = 0; !had_err && i < nof_genes; i++) {
GtNodeVisitor *sav;
GtFeatureNode *gene;
gene = *(GtFeatureNode**) gt_array_get(sas->cur_gene_set, i);
sav = gt_snp_annotator_visitor_new(gene, sas->tt, sas->rmap, err);
if (!sav)
had_err = -1;
if (!had_err) {
if (i < nof_genes-1) {
had_err = gt_queue_iterate(sas->snps,
snp_annotator_stream_process_snp,
sav, err);
} else {
while (!had_err && gt_queue_size(sas->snps) > 0) {
GtFeatureNode *snp = (GtFeatureNode*) gt_queue_get(sas->snps);
had_err = gt_genome_node_accept((GtGenomeNode*) snp, sav, err);
gt_queue_add(sas->outqueue, snp);
gt_genome_node_delete((GtGenomeNode*) snp);
}
}
gt_node_visitor_delete(sav);
}
gt_genome_node_delete((GtGenomeNode*) gene);
}
} else {
/* no SNPs for this gene cluster, delete it */
for (i = 0; !had_err && i < nof_genes; i++) {
gt_genome_node_delete(*(GtGenomeNode**) gt_array_get(sas->cur_gene_set,
i));
}
}
gt_assert(gt_queue_size(sas->snps) == 0);
gt_array_reset(sas->cur_gene_set);
return had_err;
}
static int visitor_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GtVisitorStream *visitor_stream;
int had_err;
gt_error_check(err);
visitor_stream = visitor_stream_cast(ns);
had_err = gt_node_stream_next(visitor_stream->in_stream, gn, err);
if (!had_err && *gn)
had_err = gt_genome_node_accept(*gn, visitor_stream->visitor, err);
if (had_err) {
/* we own the node -> delete it */
gt_genome_node_delete(*gn);
*gn = NULL;
}
return had_err;
}
static int cds_check_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GtCDSCheckStream *cs;
int had_err;
gt_error_check(err);
cs = cds_check_stream_cast(ns);
gt_assert(cs);
had_err = gt_node_stream_next(cs->in_stream, gn, err);
if (!had_err && *gn)
had_err = gt_genome_node_accept(*gn, cs->cds_check_visitor, err);
if (had_err) {
/* we own the node -> delete it */
gt_genome_node_delete(*gn);
*gn = NULL;
}
return had_err;
}
static int stat_stream_next(GtNodeStream *ns, GtGenomeNode **gn, GtError *err)
{
GtStatStream *stat_stream;
int had_err;
gt_error_check(err);
stat_stream = stat_stream_cast(ns);
had_err = gt_node_stream_next(stat_stream->in_stream, gn, err);
if (!had_err) {
gt_assert(stat_stream->stat_visitor);
if (*gn) {
if (!gt_eof_node_try_cast(*gn)) /* do not count EOF nodes */
stat_stream->number_of_DAGs++;
had_err = gt_genome_node_accept(*gn, stat_stream->stat_visitor, err);
gt_assert(!had_err); /* the status visitor is sane */
}
}
return had_err;
}
int gt_regioncov(int argc, const char **argv, GtError *err)
{
GtNodeVisitor *regioncov_visitor;
GtNodeStream *gff3_in_stream;
GtGenomeNode *gn;
RegionCovArguments arguments;
int parsed_args, had_err = 0;
gt_error_check(err);
/* option parsing */
switch (parse_options(&parsed_args, &arguments, argc, argv, err)) {
case OPTIONPARSER_OK: break;
case OPTIONPARSER_ERROR:
return -1;
case OPTIONPARSER_REQUESTS_EXIT:
return 0;
}
/* create gff3 input stream */
gt_assert(parsed_args < argc);
gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[parsed_args]);
if (arguments.verbose)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
/* create region coverage visitor */
regioncov_visitor = gt_regioncov_visitor_new(arguments.max_feature_dist);
/* pull the features through the stream and free them afterwards */
while (!(had_err = gt_node_stream_next(gff3_in_stream, &gn, err)) && gn) {
had_err = gt_genome_node_accept(gn, regioncov_visitor, err);
gt_genome_node_delete(gn);
}
/* show region coverage */
if (!had_err)
gt_regioncov_visitor_show_coverage(regioncov_visitor);
/* free */
gt_node_visitor_delete(regioncov_visitor);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static int bssm_train_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GthBSSMTrainStream *bssm_train_stream;
int had_err;
gt_error_check(err);
bssm_train_stream = bssm_train_stream_cast(ns);
had_err = gt_node_stream_next(bssm_train_stream->in_stream, gn, err);
if (!had_err && *gn) {
had_err = gt_genome_node_accept(*gn, bssm_train_stream->bssm_train_visitor,
err);
}
if (had_err) {
/* we own the node -> delete it */
gt_genome_node_delete(*gn);
*gn = NULL;
}
return had_err;
}
static int gff3_numsorted_out_stream_next(GtNodeStream *ns, GtGenomeNode **gn,
GtError *err)
{
GtGFF3NumsortedOutStream *gff3_out_stream;
int had_err = 0;
GtUword i = 0;
gt_error_check(err);
gff3_out_stream = gff3_numsorted_out_stream_cast(ns);
if (!gff3_out_stream->outqueue) {
gff3_out_stream->outqueue = gt_queue_new();
while (!(had_err =
gt_node_stream_next(gff3_out_stream->in_stream, gn, err))) {
if (!*gn) break;
gt_array_add(gff3_out_stream->buffer, *gn);
}
if (!had_err) {
gt_genome_nodes_sort_stable_with_func(gff3_out_stream->buffer,
(GtCompare) gt_genome_node_compare_numeric_seqids);
for (i = 0; !had_err && i < gt_array_size(gff3_out_stream->buffer); i++) {
GtGenomeNode *mygn = *(GtGenomeNode**)
gt_array_get(gff3_out_stream->buffer, i);
gt_queue_add(gff3_out_stream->outqueue, mygn);
}
}
}
if (gff3_out_stream->outqueue && !had_err) {
if (gt_queue_size(gff3_out_stream->outqueue) > 0) {
GtGenomeNode *mygn = (GtGenomeNode*)
gt_queue_get(gff3_out_stream->outqueue);
gt_assert(mygn);
had_err = gt_genome_node_accept(mygn, gff3_out_stream->gff3_visitor, err);
if (!had_err)
*gn = mygn;
}
}
return had_err;
}
int gt_condenseq_output_to_gff3(const GtCondenseq *condenseq,
GtError *err)
{
int had_err = 0;
GtUword idx,
name_len,
seqnum = 0, seqstart = 0, seqend = 0,
desclen;
GtStr *filename = NULL,
*id = gt_str_new_cstr("U"),
*name = gt_str_new_cstr("unique"),
*parent_unique = gt_str_new_cstr("U"),
*seqid = gt_str_new(),
*source = gt_str_new_cstr("Condenseq");
GtFile *outfile = NULL;
GtGFF3Visitor *gffv = NULL;
GtNodeVisitor *nodev = NULL;
GtFeatureNode *fnode = NULL;
GtGenomeNode *node = NULL;
GtRange range;
gt_assert(condenseq != NULL);
filename = gt_str_new_cstr(gt_condenseq_basefilename(condenseq));
name_len = gt_str_length(name);
gt_str_append_cstr(filename, ".gff3");
outfile = gt_file_new(gt_str_get(filename), "w", err);
nodev = gt_gff3_visitor_new(outfile);
gffv = (GtGFF3Visitor *) nodev;
gt_gff3_visitor_retain_id_attributes(gffv);
node = gt_feature_node_new(seqid, "experimental_feature", (GtUword) 1,
(GtUword) 1, GT_STRAND_BOTH);
fnode = (GtFeatureNode*) node;
gt_feature_node_set_source(fnode, source);
for (idx = 0; !had_err && idx < condenseq->udb_nelems; ++idx) {
GtCondenseqUnique uq = condenseq->uniques[idx];
if (seqend <= uq.orig_startpos) {
const char *desc;
gt_genome_node_delete(node);
seqnum = gt_condenseq_pos2seqnum(condenseq, uq.orig_startpos);
seqstart = gt_condenseq_seqstartpos(condenseq, seqnum);
seqend = seqstart + condenseq_seqlength_help(condenseq, seqnum, seqstart);
desc = gt_condenseq_description(condenseq, &desclen, seqnum);
gt_str_reset(seqid);
gt_str_append_cstr_nt(seqid, desc, desclen);
node = gt_feature_node_new(seqid, "experimental_feature", (GtUword) 1,
(GtUword) 1, GT_STRAND_BOTH);
fnode = (GtFeatureNode*) node;
gt_feature_node_set_source(fnode, source);
}
gt_str_set_length(name, name_len);
gt_str_append_uword(name, idx);
gt_str_set_length(id, (GtUword) 1);
gt_str_append_uword(id, idx);
gt_feature_node_set_attribute(fnode, "Name", gt_str_get(name));
gt_feature_node_set_attribute(fnode, "ID", gt_str_get(id));
/* 1 Based coordinates! */
range.start = uq.orig_startpos + 1 - seqstart;
range.end = uq.orig_startpos + uq.len - seqstart;
gt_genome_node_set_range(node, &range);
had_err = gt_genome_node_accept(node, nodev, err);
}
gt_str_reset(name);
gt_str_append_cstr(name, "link");
gt_str_reset(id);
gt_str_append_cstr(id, "L");
name_len = gt_str_length(name);
seqend = 0;
for (idx = 0; !had_err && idx < condenseq->ldb_nelems; ++idx) {
GtCondenseqLink link = condenseq->links[idx];
if (seqend <= link.orig_startpos) {
const char *desc;
gt_genome_node_delete(node);
seqnum = gt_condenseq_pos2seqnum(condenseq, link.orig_startpos);
seqstart = gt_condenseq_seqstartpos(condenseq, seqnum);
seqend = seqstart + condenseq_seqlength_help(condenseq, seqnum, seqstart);
desc = gt_condenseq_description(condenseq, &desclen, seqnum);
gt_str_reset(seqid);
gt_str_append_cstr_nt(seqid, desc, desclen);
node = gt_feature_node_new(seqid, "experimental_feature", (GtUword) 1,
(GtUword) 1, GT_STRAND_BOTH);
fnode = (GtFeatureNode*) node;
gt_feature_node_set_source(fnode, source);
}
gt_str_set_length(name, name_len);
gt_str_append_uword(name, idx);
gt_str_set_length(id, (GtUword) 1);
gt_str_append_uword(id, idx);
gt_feature_node_set_attribute(fnode, "Name", gt_str_get(name));
gt_feature_node_set_attribute(fnode, "ID", gt_str_get(id));
gt_str_set_length(parent_unique, (GtUword) 1);
gt_str_append_uword(parent_unique, link.unique_id);
gt_feature_node_set_attribute(fnode, "Derives_from",
gt_str_get(parent_unique));
/* 1 Based coordinates! */
range.start = link.orig_startpos + 1 - seqstart;
range.end = link.orig_startpos + link.len - seqstart;
gt_genome_node_set_range(node, &range);
had_err = gt_genome_node_accept(node, nodev, err);
}
gt_file_delete(outfile);
gt_genome_node_delete(node);
gt_node_visitor_delete(nodev);
gt_str_delete(filename);
gt_str_delete(id);
gt_str_delete(name);
gt_str_delete(parent_unique);
gt_str_delete(seqid);
gt_str_delete(source);
return had_err;
}
int gt_ltrfileout_stream_next(GtNodeStream *ns, GtGenomeNode **gn, GtError *err)
{
GtLTRdigestFileOutStream *ls;
GtFeatureNode *fn;
GtRange lltr_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
rltr_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
ppt_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD},
pbs_rng = {GT_UNDEF_UWORD, GT_UNDEF_UWORD};
int had_err;
GtUword i=0;
gt_error_check(err);
ls = gt_ltrdigest_file_out_stream_cast(ns);
/* initialize this element */
memset(&ls->element, 0, sizeof (GtLTRElement));
/* get annotations from parser */
had_err = gt_node_stream_next(ls->in_stream, gn, err);
if (!had_err && *gn)
{
GtFeatureNodeIterator* gni;
GtFeatureNode *mygn;
/* only process feature nodes */
if (!(fn = gt_feature_node_try_cast(*gn)))
return 0;
ls->element.pdomorder = gt_array_new(sizeof (const char*));
/* fill LTRElement structure from GFF3 subgraph */
gni = gt_feature_node_iterator_new(fn);
for (mygn = fn; mygn != NULL; mygn = gt_feature_node_iterator_next(gni))
(void) gt_genome_node_accept((GtGenomeNode*) mygn,
(GtNodeVisitor*) ls->lv,
err);
gt_feature_node_iterator_delete(gni);
}
if (!had_err && ls->element.mainnode != NULL)
{
char desc[GT_MAXFASTAHEADER];
GtFeatureNode *ltr3, *ltr5;
GtStr *sdesc, *sreg, *seq;
/* find sequence in GtEncseq */
sreg = gt_genome_node_get_seqid((GtGenomeNode*) ls->element.mainnode);
sdesc = gt_str_new();
had_err = gt_region_mapping_get_description(ls->rmap, sdesc, sreg, err);
if (!had_err) {
GtRange rng;
ls->element.seqid = gt_calloc((size_t) ls->seqnamelen+1, sizeof (char));
(void) snprintf(ls->element.seqid,
MIN((size_t) gt_str_length(sdesc),
(size_t) ls->seqnamelen)+1,
"%s", gt_str_get(sdesc));
gt_cstr_rep(ls->element.seqid, ' ', '_');
if (gt_str_length(sdesc) > (GtUword) ls->seqnamelen)
ls->element.seqid[ls->seqnamelen] = '\0';
(void) gt_ltrelement_format_description(&ls->element,
ls->seqnamelen,
desc,
(size_t) (GT_MAXFASTAHEADER-1));
gt_str_delete(sdesc);
/* output basic retrotransposon data */
lltr_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.leftLTR);
rltr_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.rightLTR);
rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.mainnode);
gt_file_xprintf(ls->tabout_file,
GT_WU"\t"GT_WU"\t"GT_WU"\t%s\t"GT_WU"\t"GT_WU"\t"GT_WU"\t"
GT_WU"\t"GT_WU"\t"GT_WU"\t",
rng.start, rng.end, gt_ltrelement_length(&ls->element),
ls->element.seqid, lltr_rng.start, lltr_rng.end,
gt_ltrelement_leftltrlen(&ls->element), rltr_rng.start,
rltr_rng.end, gt_ltrelement_rightltrlen(&ls->element));
}
seq = gt_str_new();
/* output TSDs */
if (!had_err && ls->element.leftTSD != NULL)
{
GtRange tsd_rng;
tsd_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.leftTSD);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.leftTSD,
gt_symbol(gt_ft_target_site_duplication),
false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t",
tsd_rng.start,
tsd_rng.end,
gt_str_get(seq));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t");
if (!had_err && ls->element.rightTSD != NULL)
{
GtRange tsd_rng;
tsd_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.rightTSD);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.rightTSD,
gt_symbol(gt_ft_target_site_duplication),
false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t",
tsd_rng.start,
tsd_rng.end,
gt_str_get(seq));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t");
/* output PPT */
if (!had_err && ls->element.ppt != NULL)
{
GtStrand ppt_strand = gt_feature_node_get_strand(ls->element.ppt);
ppt_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.ppt);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.ppt,
gt_symbol(gt_ft_RR_tract), false,
NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_range_length(&ppt_rng),
GT_FSWIDTH, ls->pptout_file);
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%s\t%c\t%d\t",
ppt_rng.start,
ppt_rng.end,
gt_str_get(seq),
GT_STRAND_CHARS[ppt_strand],
(ppt_strand == GT_STRAND_FORWARD ?
abs((int) (rltr_rng.start - ppt_rng.end)) :
abs((int) (lltr_rng.end - ppt_rng.start))));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t\t\t");
/* output PBS */
if (!had_err && ls->element.pbs != NULL)
{
GtStrand pbs_strand;
pbs_strand = gt_feature_node_get_strand(ls->element.pbs);
pbs_rng = gt_genome_node_get_range((GtGenomeNode*) ls->element.pbs);
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.pbs,
gt_symbol(gt_ft_primer_binding_site),
false, NULL, NULL, ls->rmap, err);
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_range_length(&pbs_rng),
GT_FSWIDTH, ls->pbsout_file);
gt_file_xprintf(ls->tabout_file,
""GT_WU"\t"GT_WU"\t%c\t%s\t%s\t%s\t%s\t%s\t",
pbs_rng.start,
pbs_rng.end,
GT_STRAND_CHARS[pbs_strand],
gt_feature_node_get_attribute(ls->element.pbs, "trna"),
gt_str_get(seq),
gt_feature_node_get_attribute(ls->element.pbs,
"pbsoffset"),
gt_feature_node_get_attribute(ls->element.pbs,
"trnaoffset"),
gt_feature_node_get_attribute(ls->element.pbs,
"edist"));
}
gt_str_reset(seq);
} else gt_file_xprintf(ls->tabout_file, "\t\t\t\t\t\t\t\t");
/* output protein domains */
if (!had_err && ls->element.pdoms != NULL)
{
GtStr *pdomorderstr = gt_str_new();
for (i=0; !had_err && i<gt_array_size(ls->element.pdomorder); i++)
{
const char* key = *(const char**) gt_array_get(ls->element.pdomorder,
i);
GtArray *entry = (GtArray*) gt_hashmap_get(ls->element.pdoms, key);
had_err = write_pdom(ls, entry, key, ls->rmap, desc, err);
}
if (GT_STRAND_REVERSE == gt_feature_node_get_strand(ls->element.mainnode))
gt_array_reverse(ls->element.pdomorder);
for (i=0 ;!had_err && i<gt_array_size(ls->element.pdomorder); i++)
{
const char* name = *(const char**) gt_array_get(ls->element.pdomorder,
i);
gt_str_append_cstr(pdomorderstr, name);
if (i != gt_array_size(ls->element.pdomorder)-1)
gt_str_append_cstr(pdomorderstr, "/");
}
gt_file_xprintf(ls->tabout_file, "%s", gt_str_get(pdomorderstr));
gt_str_delete(pdomorderstr);
}
/* output LTRs (we just expect them to exist) */
switch (gt_feature_node_get_strand(ls->element.mainnode))
{
case GT_STRAND_REVERSE:
ltr5 = ls->element.rightLTR;
ltr3 = ls->element.leftLTR;
break;
case GT_STRAND_FORWARD:
default:
ltr5 = ls->element.leftLTR;
ltr3 = ls->element.rightLTR;
break;
}
if (!had_err) {
had_err = gt_extract_feature_sequence(seq, (GtGenomeNode*) ltr5,
gt_symbol(gt_ft_long_terminal_repeat),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->ltr5out_file);
gt_str_reset(seq);
}
if (!had_err) {
had_err = gt_extract_feature_sequence(seq, (GtGenomeNode*) ltr3,
gt_symbol(gt_ft_long_terminal_repeat),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc, gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->ltr3out_file);
gt_str_reset(seq);
}
/* output complete oriented element */
if (!had_err) {
had_err = gt_extract_feature_sequence(seq,
(GtGenomeNode*) ls->element.mainnode,
gt_symbol(gt_ft_LTR_retrotransposon),
false,
NULL, NULL, ls->rmap, err);
}
if (!had_err) {
gt_fasta_show_entry(desc,gt_str_get(seq), gt_str_length(seq),
GT_FSWIDTH, ls->elemout_file);
gt_str_reset(seq);
}
gt_file_xprintf(ls->tabout_file, "\n");
gt_str_delete(seq);
}
gt_hashmap_delete(ls->element.pdoms);
gt_array_delete(ls->element.pdomorder);
gt_free(ls->element.seqid);
return had_err;
}