int splicing_exonset_append(splicing_exonset_t *ex, const char *seqid,
int start, int end) {
size_t idx;
int seen=splicing_strvector_search(&ex->seqids, seqid, &idx);
if (seen) {
SPLICING_CHECK(splicing_vector_int_push_back(&ex->seqid, idx));
} else {
size_t size=splicing_strvector_size(&ex->seqids);
SPLICING_CHECK(splicing_strvector_append(&ex->seqids, seqid));
SPLICING_CHECK(splicing_vector_int_push_back(&ex->seqid, size));
}
SPLICING_CHECK(splicing_vector_int_push_back(&ex->start, start));
SPLICING_CHECK(splicing_vector_int_push_back(&ex->end, end));
return 0;
}
int splicing_gff_append(splicing_gff_t *gff, const char *seqid,
const char *source, splicing_type_t type, int start,
int end, double score, splicing_strand_t strand,
int phase, const char *ID, const char *parent) {
if (type == SPLICING_TYPE_GENE) {
gff->nogenes++;
SPLICING_CHECK(splicing_vector_int_push_back(&gff->genes, gff->n));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->strand, strand));
} else if (type == SPLICING_TYPE_MRNA) {
gff->notranscripts++;
SPLICING_CHECK(splicing_vector_int_push_back(&gff->transcripts, gff->n));
}
if (type == SPLICING_TYPE_GENE) {
/* Seqid */
if (!strcmp(seqid, gff->last_seqid)) {
int last=splicing_vector_int_tail(&gff->seqid);
SPLICING_CHECK(splicing_vector_int_push_back(&gff->seqid, last));
} else {
size_t idx;
int seen=splicing_strvector_search(&gff->seqids, seqid, &idx);
if (seen) {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->seqid, idx));
gff->last_seqid=splicing_strvector_get(&gff->seqids, idx);
} else {
size_t size=splicing_strvector_size(&gff->seqids);
SPLICING_CHECK(splicing_strvector_append(&gff->seqids, seqid));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->seqid, size));
gff->last_source=splicing_strvector_get(&gff->seqids, size);
}
}
/* Source */
if (!strcmp(source, gff->last_source)) {
int last=splicing_vector_int_tail(&gff->source);
SPLICING_CHECK(splicing_vector_int_push_back(&gff->source, last));
} else {
size_t idx;
int seen=splicing_strvector_search(&gff->sources, source, &idx);
if (seen) {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->source, idx));
gff->last_source=splicing_strvector_get(&gff->sources, idx);
} else {
size_t size=splicing_strvector_size(&gff->sources);
SPLICING_CHECK(splicing_strvector_append(&gff->sources, source));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->source, size));
gff->last_source=splicing_strvector_get(&gff->sources, size);
}
}
}
/* Parent */
if (!parent || !parent[0]) {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->parent, -1));
} else if (!strcmp(parent, gff->last_gene_id)) {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->parent,
gff->last_gene_no));
} else if (!strcmp(parent, gff->last_mrna_id)) {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->parent,
gff->last_mrna_no));
} else {
size_t idx;
int seen=splicing_strvector_search(&gff->ID, parent, &idx);
if (!seen) {
SPLICING_WARNING("Unknown parent ID, invalid GFF file");
SPLICING_CHECK(splicing_vector_int_push_back(&gff->parent, -1));
} else {
SPLICING_CHECK(splicing_vector_int_push_back(&gff->parent, idx));
}
}
SPLICING_CHECK(splicing_vector_int_push_back(&gff->type, type));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->start, start));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->end, end));
SPLICING_CHECK(splicing_vector_push_back(&gff->score, score));
SPLICING_CHECK(splicing_vector_int_push_back(&gff->phase, phase));
SPLICING_CHECK(splicing_strvector_append(&gff->ID, ID));
/* Update last gene/mrna */
if (type == SPLICING_TYPE_GENE) {
gff->last_gene_id = splicing_strvector_get(&gff->ID, gff->n);
gff->last_gene_no = gff->n;
} else if (type == SPLICING_TYPE_MRNA) {
gff->last_mrna_id = splicing_strvector_get(&gff->ID, gff->n);
gff->last_mrna_no = gff->n;
}
gff->n += 1;
return 0;
}